diff options
347 files changed, 4411 insertions, 1817 deletions
diff --git a/Documentation/admin-guide/pm/intel_pstate.rst b/Documentation/admin-guide/pm/intel_pstate.rst index ab2fe0eda1d7..8b9164990956 100644 --- a/Documentation/admin-guide/pm/intel_pstate.rst +++ b/Documentation/admin-guide/pm/intel_pstate.rst @@ -410,7 +410,7 @@ argument is passed to the kernel in the command line. That only is supported in some configurations, though (for example, if the `HWP feature is enabled in the processor <Active Mode With HWP_>`_, the operation mode of the driver cannot be changed), and if it is not - supported in the current configuration, writes to this attribute with + supported in the current configuration, writes to this attribute will fail with an appropriate error. Interpretation of Policy Attributes diff --git a/Documentation/core-api/kernel-api.rst b/Documentation/core-api/kernel-api.rst index 8e44aea366c2..76fe2d0f5e7d 100644 --- a/Documentation/core-api/kernel-api.rst +++ b/Documentation/core-api/kernel-api.rst @@ -284,7 +284,7 @@ Resources Management MTRR Handling ------------- -.. kernel-doc:: arch/x86/kernel/cpu/mtrr/main.c +.. kernel-doc:: arch/x86/kernel/cpu/mtrr/mtrr.c :export: Security Framework diff --git a/Documentation/driver-api/infrastructure.rst b/Documentation/driver-api/infrastructure.rst index bee1b9a1702f..6172f3cc3d0b 100644 --- a/Documentation/driver-api/infrastructure.rst +++ b/Documentation/driver-api/infrastructure.rst @@ -49,10 +49,10 @@ Device Drivers Base Device Drivers DMA Management ----------------------------- -.. kernel-doc:: drivers/base/dma-coherent.c +.. kernel-doc:: kernel/dma/coherent.c :export: -.. kernel-doc:: drivers/base/dma-mapping.c +.. kernel-doc:: kernel/dma/mapping.c :export: Device drivers PnP support diff --git a/Documentation/filesystems/cifs/AUTHORS b/Documentation/filesystems/cifs/AUTHORS index 9f4f87e16240..75865da2ce14 100644 --- a/Documentation/filesystems/cifs/AUTHORS +++ b/Documentation/filesystems/cifs/AUTHORS @@ -42,9 +42,11 @@ Jeff Layton (many, many fixes, as well as great work on the cifs Kerberos code) Scott Lovenberg Pavel Shilovsky (for great work adding SMB2 support, and various SMB3 features) Aurelien Aptel (for DFS SMB3 work and some key bug fixes) -Ronnie Sahlberg (for SMB3 xattr work and bug fixes) +Ronnie Sahlberg (for SMB3 xattr work, bug fixes, and lots of great work on compounding) Shirish Pargaonkar (for many ACL patches over the years) Sachin Prabhu (many bug fixes, including for reconnect, copy offload and security) +Paulo Alcantara +Long Li (some great work on RDMA, SMB Direct) Test case and Bug Report contributors @@ -58,5 +60,4 @@ mention to the Stanford Checker (SWAT) which pointed out many minor bugs in error paths. Valuable suggestions also have come from Al Viro and Dave Miller. -And thanks to the IBM LTC and Power test teams and SuSE testers for -finding multiple bugs during excellent stress test runs. +And thanks to the IBM LTC and Power test teams and SuSE and Citrix and RedHat testers for finding multiple bugs during excellent stress test runs. diff --git a/Documentation/filesystems/cifs/CHANGES b/Documentation/filesystems/cifs/CHANGES index bc0025cdd1c9..455e1cc494a9 100644 --- a/Documentation/filesystems/cifs/CHANGES +++ b/Documentation/filesystems/cifs/CHANGES @@ -1,3 +1,6 @@ +See https://wiki.samba.org/index.php/LinuxCIFSKernel for +more current information. + Version 1.62 ------------ Add sockopt=TCP_NODELAY mount option. EA (xattr) routines hardened diff --git a/Documentation/filesystems/cifs/TODO b/Documentation/filesystems/cifs/TODO index c5adf149b57f..852499aed64b 100644 --- a/Documentation/filesystems/cifs/TODO +++ b/Documentation/filesystems/cifs/TODO @@ -9,14 +9,14 @@ is a partial list of the known problems and missing features: a) SMB3 (and SMB3.02) missing optional features: - multichannel (started), integration with RDMA - - directory leases (improved metadata caching) - - T10 copy offload (copy chunk, and "Duplicate Extents" ioctl + - directory leases (improved metadata caching), started (root dir only) + - T10 copy offload ie "ODX" (copy chunk, and "Duplicate Extents" ioctl currently the only two server side copy mechanisms supported) b) improved sparse file support c) Directory entry caching relies on a 1 second timer, rather than -using Directory Leases +using Directory Leases, currently only the root file handle is cached longer d) quota support (needs minor kernel change since quota calls to make it to network filesystems or deviceless filesystems) @@ -42,6 +42,8 @@ mount or a per server basis to client UIDs or nobody if no mapping exists. Also better integration with winbind for resolving SID owners k) Add tools to take advantage of more smb3 specific ioctls and features +(passthrough ioctl/fsctl for sending various SMB3 fsctls to the server +is in progress) l) encrypted file support @@ -71,9 +73,8 @@ t) split cifs and smb3 support into separate modules so legacy (and less secure) CIFS dialect can be disabled in environments that don't need it and simplify the code. -u) Finish up SMB3.1.1 dialect support - -v) POSIX Extensions for SMB3.1.1 +v) POSIX Extensions for SMB3.1.1 (started, create and mkdir support added +so far). KNOWN BUGS ==================================== @@ -92,8 +93,8 @@ Misc testing to do 1) check out max path names and max path name components against various server types. Try nested symlinks (8 deep). Return max path name in stat -f information -2) Improve xfstest's cifs enablement and adapt xfstests where needed to test -cifs better +2) Improve xfstest's cifs/smb3 enablement and adapt xfstests where needed to test +cifs/smb3 better 3) Additional performance testing and optimization using iozone and similar - there are some easy changes that can be done to parallelize sequential writes, 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 9d5eeff51b5f..6cfd16790add 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4360,12 +4360,7 @@ L: iommu@lists.linux-foundation.org T: git git://git.infradead.org/users/hch/dma-mapping.git W: http://git.infradead.org/users/hch/dma-mapping.git S: Supported -F: lib/dma-debug.c -F: lib/dma-direct.c -F: lib/dma-noncoherent.c -F: lib/dma-virt.c -F: drivers/base/dma-mapping.c -F: drivers/base/dma-coherent.c +F: kernel/dma/ F: include/asm-generic/dma-mapping.h F: include/linux/dma-direct.h F: include/linux/dma-mapping.h @@ -9756,6 +9751,11 @@ L: linux-scsi@vger.kernel.org S: Maintained F: drivers/scsi/NCR_D700.* +NCSI LIBRARY: +M: Samuel Mendoza-Jonas <sam@mendozajonas.com> +S: Maintained +F: net/ncsi/ + NCT6775 HARDWARE MONITOR DRIVER M: Guenter Roeck <linux@roeck-us.net> L: linux-hwmon@vger.kernel.org @@ -13648,7 +13648,7 @@ M: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> L: iommu@lists.linux-foundation.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/konrad/swiotlb.git S: Supported -F: lib/swiotlb.c +F: kernel/dma/swiotlb.c F: arch/*/kernel/pci-swiotlb.c F: include/linux/swiotlb.h @@ -15572,9 +15572,17 @@ 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/ +X86 ENTRY CODE +M: Andy Lutomirski <luto@kernel.org> +L: linux-kernel@vger.kernel.org +T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/asm +S: Maintained +F: arch/x86/entry/ + X86 MCE INFRASTRUCTURE M: Tony Luck <tony.luck@intel.com> M: Borislav Petkov <bp@alien8.de> @@ -15597,7 +15605,7 @@ F: drivers/platform/x86/ F: drivers/platform/olpc/ X86 VDSO -M: Andy Lutomirski <luto@amacapital.net> +M: Andy Lutomirski <luto@kernel.org> L: linux-kernel@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/vdso S: Maintained @@ -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/s390/include/asm/css_chars.h b/arch/s390/include/asm/css_chars.h index 0563fd3e8458..480bb02ccacd 100644 --- a/arch/s390/include/asm/css_chars.h +++ b/arch/s390/include/asm/css_chars.h @@ -6,36 +6,38 @@ struct css_general_char { u64 : 12; - u32 dynio : 1; /* bit 12 */ - u32 : 4; - u32 eadm : 1; /* bit 17 */ - u32 : 23; - u32 aif : 1; /* bit 41 */ - u32 : 3; - u32 mcss : 1; /* bit 45 */ - u32 fcs : 1; /* bit 46 */ - u32 : 1; - u32 ext_mb : 1; /* bit 48 */ - u32 : 7; - u32 aif_tdd : 1; /* bit 56 */ - u32 : 1; - u32 qebsm : 1; /* bit 58 */ - u32 : 2; - u32 aiv : 1; /* bit 61 */ - u32 : 5; - u32 aif_osa : 1; /* bit 67 */ - u32 : 12; - u32 eadm_rf : 1; /* bit 80 */ - u32 : 1; - u32 cib : 1; /* bit 82 */ - u32 : 5; - u32 fcx : 1; /* bit 88 */ - u32 : 19; - u32 alt_ssi : 1; /* bit 108 */ - u32 : 1; - u32 narf : 1; /* bit 110 */ - u32 : 12; - u32 util_str : 1;/* bit 123 */ + u64 dynio : 1; /* bit 12 */ + u64 : 4; + u64 eadm : 1; /* bit 17 */ + u64 : 23; + u64 aif : 1; /* bit 41 */ + u64 : 3; + u64 mcss : 1; /* bit 45 */ + u64 fcs : 1; /* bit 46 */ + u64 : 1; + u64 ext_mb : 1; /* bit 48 */ + u64 : 7; + u64 aif_tdd : 1; /* bit 56 */ + u64 : 1; + u64 qebsm : 1; /* bit 58 */ + u64 : 2; + u64 aiv : 1; /* bit 61 */ + u64 : 2; + + u64 : 3; + u64 aif_osa : 1; /* bit 67 */ + u64 : 12; + u64 eadm_rf : 1; /* bit 80 */ + u64 : 1; + u64 cib : 1; /* bit 82 */ + u64 : 5; + u64 fcx : 1; /* bit 88 */ + u64 : 19; + u64 alt_ssi : 1; /* bit 108 */ + u64 : 1; + u64 narf : 1; /* bit 110 */ + u64 : 12; + u64 util_str : 1;/* bit 123 */ } __packed; extern struct css_general_char css_general_characteristics; 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/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c index 38a286975c31..f8fecfec5df9 100644 --- a/drivers/acpi/acpi_lpss.c +++ b/drivers/acpi/acpi_lpss.c @@ -22,6 +22,7 @@ #include <linux/pm_domain.h> #include <linux/pm_runtime.h> #include <linux/pwm.h> +#include <linux/suspend.h> #include <linux/delay.h> #include "internal.h" @@ -946,9 +947,10 @@ static void lpss_iosf_exit_d3_state(void) mutex_unlock(&lpss_iosf_mutex); } -static int acpi_lpss_suspend(struct device *dev, bool wakeup) +static int acpi_lpss_suspend(struct device *dev, bool runtime) { struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev)); + bool wakeup = runtime || device_may_wakeup(dev); int ret; if (pdata->dev_desc->flags & LPSS_SAVE_CTX) @@ -961,13 +963,14 @@ static int acpi_lpss_suspend(struct device *dev, bool wakeup) * wrong status for devices being about to be powered off. See * lpss_iosf_enter_d3_state() for further information. */ - if (lpss_quirks & LPSS_QUIRK_ALWAYS_POWER_ON && iosf_mbi_available()) + if ((runtime || !pm_suspend_via_firmware()) && + lpss_quirks & LPSS_QUIRK_ALWAYS_POWER_ON && iosf_mbi_available()) lpss_iosf_enter_d3_state(); return ret; } -static int acpi_lpss_resume(struct device *dev) +static int acpi_lpss_resume(struct device *dev, bool runtime) { struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev)); int ret; @@ -976,7 +979,8 @@ static int acpi_lpss_resume(struct device *dev) * This call is kept first to be in symmetry with * acpi_lpss_runtime_suspend() one. */ - if (lpss_quirks & LPSS_QUIRK_ALWAYS_POWER_ON && iosf_mbi_available()) + if ((runtime || !pm_resume_via_firmware()) && + lpss_quirks & LPSS_QUIRK_ALWAYS_POWER_ON && iosf_mbi_available()) lpss_iosf_exit_d3_state(); ret = acpi_dev_resume(dev); @@ -1000,12 +1004,12 @@ static int acpi_lpss_suspend_late(struct device *dev) return 0; ret = pm_generic_suspend_late(dev); - return ret ? ret : acpi_lpss_suspend(dev, device_may_wakeup(dev)); + return ret ? ret : acpi_lpss_suspend(dev, false); } static int acpi_lpss_resume_early(struct device *dev) { - int ret = acpi_lpss_resume(dev); + int ret = acpi_lpss_resume(dev, false); return ret ? ret : pm_generic_resume_early(dev); } @@ -1020,7 +1024,7 @@ static int acpi_lpss_runtime_suspend(struct device *dev) static int acpi_lpss_runtime_resume(struct device *dev) { - int ret = acpi_lpss_resume(dev); + int ret = acpi_lpss_resume(dev, true); return ret ? ret : pm_generic_runtime_resume(dev); } diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index bb94cf0731fe..442a9e24f439 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -2037,6 +2037,17 @@ static inline void acpi_ec_query_exit(void) } } +static const struct dmi_system_id acpi_ec_no_wakeup[] = { + { + .ident = "Thinkpad X1 Carbon 6th", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "20KGS3JF01"), + }, + }, + { }, +}; + int __init acpi_ec_init(void) { int result; @@ -2047,6 +2058,15 @@ int __init acpi_ec_init(void) if (result) return result; + /* + * Disable EC wakeup on following systems to prevent periodic + * wakeup from EC GPE. + */ + if (dmi_check_system(acpi_ec_no_wakeup)) { + ec_no_wakeup = true; + pr_debug("Disabling EC wakeup on suspend-to-idle\n"); + } + /* Drivers must be started after acpi_ec_query_init() */ dsdt_fail = acpi_bus_register_driver(&acpi_ec_driver); /* diff --git a/drivers/base/Makefile b/drivers/base/Makefile index b074f242a435..704f44295810 100644 --- a/drivers/base/Makefile +++ b/drivers/base/Makefile @@ -8,10 +8,7 @@ obj-y := component.o core.o bus.o dd.o syscore.o \ topology.o container.o property.o cacheinfo.o \ devcon.o obj-$(CONFIG_DEVTMPFS) += devtmpfs.o -obj-$(CONFIG_DMA_CMA) += dma-contiguous.o obj-y += power/ -obj-$(CONFIG_HAS_DMA) += dma-mapping.o -obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o obj-$(CONFIG_ISA_BUS_API) += isa.o obj-y += firmware_loader/ obj-$(CONFIG_NUMA) += node.o diff --git a/drivers/base/core.c b/drivers/base/core.c index 36622b52e419..df3e1a44707a 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -236,6 +236,13 @@ struct device_link *device_link_add(struct device *consumer, link->rpm_active = true; } pm_runtime_new_link(consumer); + /* + * If the link is being added by the consumer driver at probe + * time, balance the decrementation of the supplier's runtime PM + * usage counter after consumer probe in driver_probe_device(). + */ + if (consumer->links.status == DL_DEV_PROBING) + pm_runtime_get_noresume(supplier); } get_device(supplier); link->supplier = supplier; @@ -255,12 +262,12 @@ struct device_link *device_link_add(struct device *consumer, switch (consumer->links.status) { case DL_DEV_PROBING: /* - * Balance the decrementation of the supplier's - * runtime PM usage counter after consumer probe - * in driver_probe_device(). + * Some callers expect the link creation during + * consumer driver probe to resume the supplier + * even without DL_FLAG_RPM_ACTIVE. */ if (flags & DL_FLAG_PM_RUNTIME) - pm_runtime_get_sync(supplier); + pm_runtime_resume(supplier); link->status = DL_STATE_CONSUMER_PROBE; break; 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/bluetooth/hci_nokia.c b/drivers/bluetooth/hci_nokia.c index 14d159e2042d..2dc33e65d2d0 100644 --- a/drivers/bluetooth/hci_nokia.c +++ b/drivers/bluetooth/hci_nokia.c @@ -29,7 +29,7 @@ #include <linux/slab.h> #include <linux/string.h> #include <linux/types.h> -#include <linux/unaligned/le_struct.h> +#include <asm/unaligned.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> 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/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 1de5ec8d5ea3..ece120da3353 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -294,6 +294,7 @@ struct pstate_funcs { static struct pstate_funcs pstate_funcs __read_mostly; static int hwp_active __read_mostly; +static int hwp_mode_bdw __read_mostly; static bool per_cpu_limits __read_mostly; static bool hwp_boost __read_mostly; @@ -1413,7 +1414,15 @@ static void intel_pstate_get_cpu_pstates(struct cpudata *cpu) cpu->pstate.turbo_pstate = pstate_funcs.get_turbo(); cpu->pstate.scaling = pstate_funcs.get_scaling(); cpu->pstate.max_freq = cpu->pstate.max_pstate * cpu->pstate.scaling; - cpu->pstate.turbo_freq = cpu->pstate.turbo_pstate * cpu->pstate.scaling; + + if (hwp_active && !hwp_mode_bdw) { + unsigned int phy_max, current_max; + + intel_pstate_get_hwp_max(cpu->cpu, &phy_max, ¤t_max); + cpu->pstate.turbo_freq = phy_max * cpu->pstate.scaling; + } else { + cpu->pstate.turbo_freq = cpu->pstate.turbo_pstate * cpu->pstate.scaling; + } if (pstate_funcs.get_aperf_mperf_shift) cpu->aperf_mperf_shift = pstate_funcs.get_aperf_mperf_shift(); @@ -2467,28 +2476,36 @@ static inline bool intel_pstate_has_acpi_ppc(void) { return false; } static inline void intel_pstate_request_control_from_smm(void) {} #endif /* CONFIG_ACPI */ +#define INTEL_PSTATE_HWP_BROADWELL 0x01 + +#define ICPU_HWP(model, hwp_mode) \ + { X86_VENDOR_INTEL, 6, model, X86_FEATURE_HWP, hwp_mode } + static const struct x86_cpu_id hwp_support_ids[] __initconst = { - { X86_VENDOR_INTEL, 6, X86_MODEL_ANY, X86_FEATURE_HWP }, + ICPU_HWP(INTEL_FAM6_BROADWELL_X, INTEL_PSTATE_HWP_BROADWELL), + ICPU_HWP(INTEL_FAM6_BROADWELL_XEON_D, INTEL_PSTATE_HWP_BROADWELL), + ICPU_HWP(X86_MODEL_ANY, 0), {} }; static int __init intel_pstate_init(void) { + const struct x86_cpu_id *id; int rc; if (no_load) return -ENODEV; - if (x86_match_cpu(hwp_support_ids)) { + id = x86_match_cpu(hwp_support_ids); + if (id) { copy_cpu_funcs(&core_funcs); if (!no_hwp) { hwp_active++; + hwp_mode_bdw = id->driver_data; intel_pstate.attr = hwp_cpufreq_attrs; goto hwp_cpu_matched; } } else { - const struct x86_cpu_id *id; - id = x86_match_cpu(intel_pstate_cpu_ids); if (!id) return -ENODEV; diff --git a/drivers/cpufreq/qcom-cpufreq-kryo.c b/drivers/cpufreq/qcom-cpufreq-kryo.c index d049fe4b80c4..01bddacf5c3b 100644 --- a/drivers/cpufreq/qcom-cpufreq-kryo.c +++ b/drivers/cpufreq/qcom-cpufreq-kryo.c @@ -42,6 +42,8 @@ enum _msm8996_version { NUM_OF_MSM8996_VERSIONS, }; +struct platform_device *cpufreq_dt_pdev, *kryo_cpufreq_pdev; + static enum _msm8996_version __init qcom_cpufreq_kryo_get_msm_id(void) { size_t len; @@ -74,7 +76,6 @@ static enum _msm8996_version __init qcom_cpufreq_kryo_get_msm_id(void) static int qcom_cpufreq_kryo_probe(struct platform_device *pdev) { struct opp_table *opp_tables[NR_CPUS] = {0}; - struct platform_device *cpufreq_dt_pdev; enum _msm8996_version msm8996_version; struct nvmem_cell *speedbin_nvmem; struct device_node *np; @@ -115,6 +116,8 @@ static int qcom_cpufreq_kryo_probe(struct platform_device *pdev) speedbin = nvmem_cell_read(speedbin_nvmem, &len); nvmem_cell_put(speedbin_nvmem); + if (IS_ERR(speedbin)) + return PTR_ERR(speedbin); switch (msm8996_version) { case MSM8996_V3: @@ -127,6 +130,7 @@ static int qcom_cpufreq_kryo_probe(struct platform_device *pdev) BUG(); break; } + kfree(speedbin); for_each_possible_cpu(cpu) { cpu_dev = get_cpu_device(cpu); @@ -162,8 +166,15 @@ free_opp: return ret; } +static int qcom_cpufreq_kryo_remove(struct platform_device *pdev) +{ + platform_device_unregister(cpufreq_dt_pdev); + return 0; +} + static struct platform_driver qcom_cpufreq_kryo_driver = { .probe = qcom_cpufreq_kryo_probe, + .remove = qcom_cpufreq_kryo_remove, .driver = { .name = "qcom-cpufreq-kryo", }, @@ -198,8 +209,9 @@ static int __init qcom_cpufreq_kryo_init(void) if (unlikely(ret < 0)) return ret; - ret = PTR_ERR_OR_ZERO(platform_device_register_simple( - "qcom-cpufreq-kryo", -1, NULL, 0)); + kryo_cpufreq_pdev = platform_device_register_simple( + "qcom-cpufreq-kryo", -1, NULL, 0); + ret = PTR_ERR_OR_ZERO(kryo_cpufreq_pdev); if (0 == ret) return 0; @@ -208,5 +220,12 @@ static int __init qcom_cpufreq_kryo_init(void) } module_init(qcom_cpufreq_kryo_init); +static void __init qcom_cpufreq_kryo_exit(void) +{ + platform_device_unregister(kryo_cpufreq_pdev); + platform_driver_unregister(&qcom_cpufreq_kryo_driver); +} +module_exit(qcom_cpufreq_kryo_exit); + MODULE_DESCRIPTION("Qualcomm Technologies, Inc. Kryo CPUfreq driver"); MODULE_LICENSE("GPL v2"); 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/dmi-id.c b/drivers/firmware/dmi-id.c index 951b6c79f166..624a11cb07e2 100644 --- a/drivers/firmware/dmi-id.c +++ b/drivers/firmware/dmi-id.c @@ -47,6 +47,7 @@ DEFINE_DMI_ATTR_WITH_SHOW(product_name, 0444, DMI_PRODUCT_NAME); DEFINE_DMI_ATTR_WITH_SHOW(product_version, 0444, DMI_PRODUCT_VERSION); DEFINE_DMI_ATTR_WITH_SHOW(product_serial, 0400, DMI_PRODUCT_SERIAL); DEFINE_DMI_ATTR_WITH_SHOW(product_uuid, 0400, DMI_PRODUCT_UUID); +DEFINE_DMI_ATTR_WITH_SHOW(product_sku, 0444, DMI_PRODUCT_SKU); DEFINE_DMI_ATTR_WITH_SHOW(product_family, 0444, DMI_PRODUCT_FAMILY); DEFINE_DMI_ATTR_WITH_SHOW(board_vendor, 0444, DMI_BOARD_VENDOR); DEFINE_DMI_ATTR_WITH_SHOW(board_name, 0444, DMI_BOARD_NAME); @@ -193,6 +194,7 @@ static void __init dmi_id_init_attr_table(void) ADD_DMI_ATTR(product_serial, DMI_PRODUCT_SERIAL); ADD_DMI_ATTR(product_uuid, DMI_PRODUCT_UUID); ADD_DMI_ATTR(product_family, DMI_PRODUCT_FAMILY); + ADD_DMI_ATTR(product_sku, DMI_PRODUCT_SKU); ADD_DMI_ATTR(board_vendor, DMI_BOARD_VENDOR); ADD_DMI_ATTR(board_name, DMI_BOARD_NAME); ADD_DMI_ATTR(board_version, DMI_BOARD_VERSION); diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c index 54e66adef252..f2483548cde9 100644 --- a/drivers/firmware/dmi_scan.c +++ b/drivers/firmware/dmi_scan.c @@ -447,6 +447,7 @@ static void __init dmi_decode(const struct dmi_header *dm, void *dummy) dmi_save_ident(dm, DMI_PRODUCT_VERSION, 6); dmi_save_ident(dm, DMI_PRODUCT_SERIAL, 7); dmi_save_uuid(dm, DMI_PRODUCT_UUID, 8); + dmi_save_ident(dm, DMI_PRODUCT_SKU, 25); dmi_save_ident(dm, DMI_PRODUCT_FAMILY, 26); break; case 2: /* Base Board Information */ 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/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 3317d1536f4f..6e5284e6c028 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -2158,10 +2158,18 @@ bool amdgpu_device_asic_has_dc_support(enum amd_asic_type asic_type) switch (asic_type) { #if defined(CONFIG_DRM_AMD_DC) case CHIP_BONAIRE: - case CHIP_HAWAII: case CHIP_KAVERI: case CHIP_KABINI: case CHIP_MULLINS: + /* + * We have systems in the wild with these ASICs that require + * LVDS and VGA support which is not supported with DC. + * + * Fallback to the non-DC driver here by default so as not to + * cause regressions. + */ + return amdgpu_dc > 0; + case CHIP_HAWAII: case CHIP_CARRIZO: case CHIP_STONEY: case CHIP_POLARIS10: diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 5e4e1bd90383..3526efa8960e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -762,8 +762,7 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain, domain = amdgpu_mem_type_to_domain(bo->tbo.mem.mem_type); if (domain == AMDGPU_GEM_DOMAIN_VRAM) { adev->vram_pin_size += amdgpu_bo_size(bo); - if (bo->flags & AMDGPU_GEM_CREATE_NO_CPU_ACCESS) - adev->invisible_pin_size += amdgpu_bo_size(bo); + adev->invisible_pin_size += amdgpu_vram_mgr_bo_invisible_size(bo); } else if (domain == AMDGPU_GEM_DOMAIN_GTT) { adev->gart_pin_size += amdgpu_bo_size(bo); } @@ -790,25 +789,22 @@ int amdgpu_bo_unpin(struct amdgpu_bo *bo) bo->pin_count--; if (bo->pin_count) return 0; - for (i = 0; i < bo->placement.num_placement; i++) { - bo->placements[i].lpfn = 0; - bo->placements[i].flags &= ~TTM_PL_FLAG_NO_EVICT; - } - r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx); - if (unlikely(r)) { - dev_err(adev->dev, "%p validate failed for unpin\n", bo); - goto error; - } if (bo->tbo.mem.mem_type == TTM_PL_VRAM) { adev->vram_pin_size -= amdgpu_bo_size(bo); - if (bo->flags & AMDGPU_GEM_CREATE_NO_CPU_ACCESS) - adev->invisible_pin_size -= amdgpu_bo_size(bo); + adev->invisible_pin_size -= amdgpu_vram_mgr_bo_invisible_size(bo); } else if (bo->tbo.mem.mem_type == TTM_PL_TT) { adev->gart_pin_size -= amdgpu_bo_size(bo); } -error: + for (i = 0; i < bo->placement.num_placement; i++) { + bo->placements[i].lpfn = 0; + bo->placements[i].flags &= ~TTM_PL_FLAG_NO_EVICT; + } + r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx); + if (unlikely(r)) + dev_err(adev->dev, "%p validate failed for unpin\n", bo); + return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h index e969c879d87e..e5da4654b630 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h @@ -73,6 +73,7 @@ bool amdgpu_gtt_mgr_has_gart_addr(struct ttm_mem_reg *mem); uint64_t amdgpu_gtt_mgr_usage(struct ttm_mem_type_manager *man); int amdgpu_gtt_mgr_recover(struct ttm_mem_type_manager *man); +u64 amdgpu_vram_mgr_bo_invisible_size(struct amdgpu_bo *bo); uint64_t amdgpu_vram_mgr_usage(struct ttm_mem_type_manager *man); uint64_t amdgpu_vram_mgr_vis_usage(struct ttm_mem_type_manager *man); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c index bcf68f80bbf0..3ff08e326838 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c @@ -130,7 +130,7 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev) unsigned version_major, version_minor, family_id; int i, j, r; - INIT_DELAYED_WORK(&adev->uvd.inst->idle_work, amdgpu_uvd_idle_work_handler); + INIT_DELAYED_WORK(&adev->uvd.idle_work, amdgpu_uvd_idle_work_handler); switch (adev->asic_type) { #ifdef CONFIG_DRM_AMDGPU_CIK @@ -314,12 +314,12 @@ int amdgpu_uvd_suspend(struct amdgpu_device *adev) void *ptr; int i, j; + cancel_delayed_work_sync(&adev->uvd.idle_work); + for (j = 0; j < adev->uvd.num_uvd_inst; ++j) { if (adev->uvd.inst[j].vcpu_bo == NULL) continue; - cancel_delayed_work_sync(&adev->uvd.inst[j].idle_work); - /* only valid for physical mode */ if (adev->asic_type < CHIP_POLARIS10) { for (i = 0; i < adev->uvd.max_handles; ++i) @@ -1145,7 +1145,7 @@ int amdgpu_uvd_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle, static void amdgpu_uvd_idle_work_handler(struct work_struct *work) { struct amdgpu_device *adev = - container_of(work, struct amdgpu_device, uvd.inst->idle_work.work); + container_of(work, struct amdgpu_device, uvd.idle_work.work); unsigned fences = 0, i, j; for (i = 0; i < adev->uvd.num_uvd_inst; ++i) { @@ -1167,7 +1167,7 @@ static void amdgpu_uvd_idle_work_handler(struct work_struct *work) AMD_CG_STATE_GATE); } } else { - schedule_delayed_work(&adev->uvd.inst->idle_work, UVD_IDLE_TIMEOUT); + schedule_delayed_work(&adev->uvd.idle_work, UVD_IDLE_TIMEOUT); } } @@ -1179,7 +1179,7 @@ void amdgpu_uvd_ring_begin_use(struct amdgpu_ring *ring) if (amdgpu_sriov_vf(adev)) return; - set_clocks = !cancel_delayed_work_sync(&adev->uvd.inst->idle_work); + set_clocks = !cancel_delayed_work_sync(&adev->uvd.idle_work); if (set_clocks) { if (adev->pm.dpm_enabled) { amdgpu_dpm_enable_uvd(adev, true); @@ -1196,7 +1196,7 @@ void amdgpu_uvd_ring_begin_use(struct amdgpu_ring *ring) void amdgpu_uvd_ring_end_use(struct amdgpu_ring *ring) { if (!amdgpu_sriov_vf(ring->adev)) - schedule_delayed_work(&ring->adev->uvd.inst->idle_work, UVD_IDLE_TIMEOUT); + schedule_delayed_work(&ring->adev->uvd.idle_work, UVD_IDLE_TIMEOUT); } /** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h index b1579fba134c..8b23a1b00c76 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h @@ -44,7 +44,6 @@ struct amdgpu_uvd_inst { void *saved_bo; atomic_t handles[AMDGPU_MAX_UVD_HANDLES]; struct drm_file *filp[AMDGPU_MAX_UVD_HANDLES]; - struct delayed_work idle_work; struct amdgpu_ring ring; struct amdgpu_ring ring_enc[AMDGPU_MAX_UVD_ENC_RINGS]; struct amdgpu_irq_src irq; @@ -62,6 +61,7 @@ struct amdgpu_uvd { bool address_64_bit; bool use_ctx_buf; struct amdgpu_uvd_inst inst[AMDGPU_MAX_UVD_INSTANCES]; + struct delayed_work idle_work; }; int amdgpu_uvd_sw_init(struct amdgpu_device *adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c index 9aca653bec07..b6333f92ba45 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c @@ -97,6 +97,38 @@ static u64 amdgpu_vram_mgr_vis_size(struct amdgpu_device *adev, } /** + * amdgpu_vram_mgr_bo_invisible_size - CPU invisible BO size + * + * @bo: &amdgpu_bo buffer object (must be in VRAM) + * + * Returns: + * How much of the given &amdgpu_bo buffer object lies in CPU invisible VRAM. + */ +u64 amdgpu_vram_mgr_bo_invisible_size(struct amdgpu_bo *bo) +{ + struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); + struct ttm_mem_reg *mem = &bo->tbo.mem; + struct drm_mm_node *nodes = mem->mm_node; + unsigned pages = mem->num_pages; + u64 usage = 0; + + if (adev->gmc.visible_vram_size == adev->gmc.real_vram_size) + return 0; + + if (mem->start >= adev->gmc.visible_vram_size >> PAGE_SHIFT) + return amdgpu_bo_size(bo); + + while (nodes && pages) { + usage += nodes->size << PAGE_SHIFT; + usage -= amdgpu_vram_mgr_vis_size(adev, nodes); + pages -= nodes->size; + ++nodes; + } + + return usage; +} + +/** * amdgpu_vram_mgr_new - allocate new ranges * * @man: TTM memory type manager @@ -135,7 +167,8 @@ static int amdgpu_vram_mgr_new(struct ttm_mem_type_manager *man, num_nodes = DIV_ROUND_UP(mem->num_pages, pages_per_node); } - nodes = kcalloc(num_nodes, sizeof(*nodes), GFP_KERNEL); + nodes = kvmalloc_array(num_nodes, sizeof(*nodes), + GFP_KERNEL | __GFP_ZERO); if (!nodes) return -ENOMEM; @@ -190,7 +223,7 @@ error: drm_mm_remove_node(&nodes[i]); spin_unlock(&mgr->lock); - kfree(nodes); + kvfree(nodes); return r == -ENOSPC ? 0 : r; } @@ -229,7 +262,7 @@ static void amdgpu_vram_mgr_del(struct ttm_mem_type_manager *man, atomic64_sub(usage, &mgr->usage); atomic64_sub(vis_usage, &mgr->vis_usage); - kfree(mem->mm_node); + kvfree(mem->mm_node); mem->mm_node = NULL; } diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_powertune.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_powertune.c index dbe4b1f66784..22364875a943 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_powertune.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_powertune.c @@ -1090,7 +1090,7 @@ static int vega10_disable_se_edc_config(struct pp_hwmgr *hwmgr) static int vega10_enable_psm_gc_edc_config(struct pp_hwmgr *hwmgr) { struct amdgpu_device *adev = hwmgr->adev; - int result; + int result = 0; uint32_t num_se = 0; uint32_t count, data; diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c index 73c875db45f4..47e0992f3908 100644 --- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c +++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c @@ -839,7 +839,7 @@ static int atmel_hlcdc_plane_init_properties(struct atmel_hlcdc_plane *plane) return ret; } - if (desc->layout.xstride && desc->layout.pstride) { + if (desc->layout.xstride[0] && desc->layout.pstride[0]) { int ret; ret = drm_plane_create_rotation_property(&plane->base, diff --git a/drivers/gpu/drm/bridge/sil-sii8620.c b/drivers/gpu/drm/bridge/sil-sii8620.c index 7ab36042a822..250effa0e6b8 100644 --- a/drivers/gpu/drm/bridge/sil-sii8620.c +++ b/drivers/gpu/drm/bridge/sil-sii8620.c @@ -36,8 +36,11 @@ #define SII8620_BURST_BUF_LEN 288 #define VAL_RX_HDMI_CTRL2_DEFVAL VAL_RX_HDMI_CTRL2_IDLE_CNT(3) -#define MHL1_MAX_LCLK 225000 -#define MHL3_MAX_LCLK 600000 + +#define MHL1_MAX_PCLK 75000 +#define MHL1_MAX_PCLK_PP_MODE 150000 +#define MHL3_MAX_PCLK 200000 +#define MHL3_MAX_PCLK_PP_MODE 300000 enum sii8620_mode { CM_DISCONNECTED, @@ -80,6 +83,9 @@ struct sii8620 { u8 devcap[MHL_DCAP_SIZE]; u8 xdevcap[MHL_XDC_SIZE]; u8 avif[HDMI_INFOFRAME_SIZE(AVI)]; + bool feature_complete; + bool devcap_read; + bool sink_detected; struct edid *edid; unsigned int gen2_write_burst:1; enum sii8620_mt_state mt_state; @@ -476,7 +482,7 @@ static void sii8620_update_array(u8 *dst, u8 *src, int count) } } -static void sii8620_sink_detected(struct sii8620 *ctx, int ret) +static void sii8620_identify_sink(struct sii8620 *ctx) { static const char * const sink_str[] = { [SINK_NONE] = "NONE", @@ -487,7 +493,7 @@ static void sii8620_sink_detected(struct sii8620 *ctx, int ret) char sink_name[20]; struct device *dev = ctx->dev; - if (ret < 0) + if (!ctx->sink_detected || !ctx->devcap_read) return; sii8620_fetch_edid(ctx); @@ -496,6 +502,7 @@ static void sii8620_sink_detected(struct sii8620 *ctx, int ret) sii8620_mhl_disconnected(ctx); return; } + sii8620_set_upstream_edid(ctx); if (drm_detect_hdmi_monitor(ctx->edid)) ctx->sink_type = SINK_HDMI; @@ -508,53 +515,6 @@ static void sii8620_sink_detected(struct sii8620 *ctx, int ret) sink_str[ctx->sink_type], sink_name); } -static void sii8620_hsic_init(struct sii8620 *ctx) -{ - if (!sii8620_is_mhl3(ctx)) - return; - - sii8620_write(ctx, REG_FCGC, - BIT_FCGC_HSIC_HOSTMODE | BIT_FCGC_HSIC_ENABLE); - sii8620_setbits(ctx, REG_HRXCTRL3, - BIT_HRXCTRL3_HRX_STAY_RESET | BIT_HRXCTRL3_STATUS_EN, ~0); - sii8620_setbits(ctx, REG_TTXNUMB, MSK_TTXNUMB_TTX_NUMBPS, 4); - sii8620_setbits(ctx, REG_TRXCTRL, BIT_TRXCTRL_TRX_FROM_SE_COC, ~0); - sii8620_setbits(ctx, REG_HTXCTRL, BIT_HTXCTRL_HTX_DRVCONN1, 0); - sii8620_setbits(ctx, REG_KEEPER, MSK_KEEPER_MODE, VAL_KEEPER_MODE_HOST); - sii8620_write_seq_static(ctx, - REG_TDMLLCTL, 0, - REG_UTSRST, BIT_UTSRST_HRX_SRST | BIT_UTSRST_HTX_SRST | - BIT_UTSRST_KEEPER_SRST | BIT_UTSRST_FC_SRST, - REG_UTSRST, BIT_UTSRST_HRX_SRST | BIT_UTSRST_HTX_SRST, - REG_HRXINTL, 0xff, - REG_HRXINTH, 0xff, - REG_TTXINTL, 0xff, - REG_TTXINTH, 0xff, - REG_TRXINTL, 0xff, - REG_TRXINTH, 0xff, - REG_HTXINTL, 0xff, - REG_HTXINTH, 0xff, - REG_FCINTR0, 0xff, - REG_FCINTR1, 0xff, - REG_FCINTR2, 0xff, - REG_FCINTR3, 0xff, - REG_FCINTR4, 0xff, - REG_FCINTR5, 0xff, - REG_FCINTR6, 0xff, - REG_FCINTR7, 0xff - ); -} - -static void sii8620_edid_read(struct sii8620 *ctx, int ret) -{ - if (ret < 0) - return; - - sii8620_set_upstream_edid(ctx); - sii8620_hsic_init(ctx); - sii8620_enable_hpd(ctx); -} - static void sii8620_mr_devcap(struct sii8620 *ctx) { u8 dcap[MHL_DCAP_SIZE]; @@ -570,6 +530,8 @@ static void sii8620_mr_devcap(struct sii8620 *ctx) dcap[MHL_DCAP_ADOPTER_ID_H], dcap[MHL_DCAP_ADOPTER_ID_L], dcap[MHL_DCAP_DEVICE_ID_H], dcap[MHL_DCAP_DEVICE_ID_L]); sii8620_update_array(ctx->devcap, dcap, MHL_DCAP_SIZE); + ctx->devcap_read = true; + sii8620_identify_sink(ctx); } static void sii8620_mr_xdevcap(struct sii8620 *ctx) @@ -807,6 +769,7 @@ static void sii8620_burst_rx_all(struct sii8620 *ctx) static void sii8620_fetch_edid(struct sii8620 *ctx) { u8 lm_ddc, ddc_cmd, int3, cbus; + unsigned long timeout; int fetched, i; int edid_len = EDID_LENGTH; u8 *edid; @@ -856,23 +819,31 @@ static void sii8620_fetch_edid(struct sii8620 *ctx) REG_DDC_CMD, ddc_cmd | VAL_DDC_CMD_ENH_DDC_READ_NO_ACK ); - do { - int3 = sii8620_readb(ctx, REG_INTR3); + int3 = 0; + timeout = jiffies + msecs_to_jiffies(200); + for (;;) { cbus = sii8620_readb(ctx, REG_CBUS_STATUS); - - if (int3 & BIT_DDC_CMD_DONE) - break; - - if (!(cbus & BIT_CBUS_STATUS_CBUS_CONNECTED)) { + if (~cbus & BIT_CBUS_STATUS_CBUS_CONNECTED) { + kfree(edid); + edid = NULL; + goto end; + } + if (int3 & BIT_DDC_CMD_DONE) { + if (sii8620_readb(ctx, REG_DDC_DOUT_CNT) + >= FETCH_SIZE) + break; + } else { + int3 = sii8620_readb(ctx, REG_INTR3); + } + if (time_is_before_jiffies(timeout)) { + ctx->error = -ETIMEDOUT; + dev_err(ctx->dev, "timeout during EDID read\n"); kfree(edid); edid = NULL; goto end; } - } while (1); - - sii8620_readb(ctx, REG_DDC_STATUS); - while (sii8620_readb(ctx, REG_DDC_DOUT_CNT) < FETCH_SIZE) usleep_range(10, 20); + } sii8620_read_buf(ctx, REG_DDC_DATA, edid + fetched, FETCH_SIZE); if (fetched + FETCH_SIZE == EDID_LENGTH) { @@ -971,8 +942,17 @@ static int sii8620_hw_on(struct sii8620 *ctx) ret = regulator_bulk_enable(ARRAY_SIZE(ctx->supplies), ctx->supplies); if (ret) return ret; + usleep_range(10000, 20000); - return clk_prepare_enable(ctx->clk_xtal); + ret = clk_prepare_enable(ctx->clk_xtal); + if (ret) + return ret; + + msleep(100); + gpiod_set_value(ctx->gpio_reset, 0); + msleep(100); + + return 0; } static int sii8620_hw_off(struct sii8620 *ctx) @@ -982,17 +962,6 @@ static int sii8620_hw_off(struct sii8620 *ctx) return regulator_bulk_disable(ARRAY_SIZE(ctx->supplies), ctx->supplies); } -static void sii8620_hw_reset(struct sii8620 *ctx) -{ - usleep_range(10000, 20000); - gpiod_set_value(ctx->gpio_reset, 0); - usleep_range(5000, 20000); - gpiod_set_value(ctx->gpio_reset, 1); - usleep_range(10000, 20000); - gpiod_set_value(ctx->gpio_reset, 0); - msleep(300); -} - static void sii8620_cbus_reset(struct sii8620 *ctx) { sii8620_write(ctx, REG_PWD_SRST, BIT_PWD_SRST_CBUS_RST @@ -1048,20 +1017,11 @@ static void sii8620_stop_video(struct sii8620 *ctx) static void sii8620_set_format(struct sii8620 *ctx) { - u8 out_fmt; - if (sii8620_is_mhl3(ctx)) { sii8620_setbits(ctx, REG_M3_P0CTRL, BIT_M3_P0CTRL_MHL3_P0_PIXEL_MODE_PACKED, ctx->use_packed_pixel ? ~0 : 0); } else { - if (ctx->use_packed_pixel) - sii8620_write_seq_static(ctx, - REG_VID_MODE, BIT_VID_MODE_M1080P, - REG_MHL_TOP_CTL, BIT_MHL_TOP_CTL_MHL_PP_SEL | 1, - REG_MHLTX_CTL6, 0x60 - ); - else sii8620_write_seq_static(ctx, REG_VID_MODE, 0, REG_MHL_TOP_CTL, 1, @@ -1069,15 +1029,9 @@ static void sii8620_set_format(struct sii8620 *ctx) ); } - if (ctx->use_packed_pixel) - out_fmt = VAL_TPI_FORMAT(YCBCR422, FULL) | - BIT_TPI_OUTPUT_CSCMODE709; - else - out_fmt = VAL_TPI_FORMAT(RGB, FULL); - sii8620_write_seq(ctx, REG_TPI_INPUT, VAL_TPI_FORMAT(RGB, FULL), - REG_TPI_OUTPUT, out_fmt, + REG_TPI_OUTPUT, VAL_TPI_FORMAT(RGB, FULL), ); } @@ -1216,7 +1170,7 @@ static void sii8620_start_video(struct sii8620 *ctx) int clk = ctx->pixel_clock * (ctx->use_packed_pixel ? 2 : 3); int i; - for (i = 0; i < ARRAY_SIZE(clk_spec); ++i) + for (i = 0; i < ARRAY_SIZE(clk_spec) - 1; ++i) if (clk < clk_spec[i].max_clk) break; @@ -1534,6 +1488,16 @@ static void sii8620_set_mode(struct sii8620 *ctx, enum sii8620_mode mode) ); } +static void sii8620_hpd_unplugged(struct sii8620 *ctx) +{ + sii8620_disable_hpd(ctx); + ctx->sink_type = SINK_NONE; + ctx->sink_detected = false; + ctx->feature_complete = false; + kfree(ctx->edid); + ctx->edid = NULL; +} + static void sii8620_disconnect(struct sii8620 *ctx) { sii8620_disable_gen2_write_burst(ctx); @@ -1561,7 +1525,7 @@ static void sii8620_disconnect(struct sii8620 *ctx) REG_MHL_DP_CTL6, 0x2A, REG_MHL_DP_CTL7, 0x03 ); - sii8620_disable_hpd(ctx); + sii8620_hpd_unplugged(ctx); sii8620_write_seq_static(ctx, REG_M3_CTRL, VAL_M3_CTRL_MHL3_VALUE, REG_MHL_COC_CTL1, 0x07, @@ -1609,10 +1573,8 @@ static void sii8620_disconnect(struct sii8620 *ctx) memset(ctx->xstat, 0, sizeof(ctx->xstat)); memset(ctx->devcap, 0, sizeof(ctx->devcap)); memset(ctx->xdevcap, 0, sizeof(ctx->xdevcap)); + ctx->devcap_read = false; ctx->cbus_status = 0; - ctx->sink_type = SINK_NONE; - kfree(ctx->edid); - ctx->edid = NULL; sii8620_mt_cleanup(ctx); } @@ -1703,9 +1665,6 @@ static void sii8620_status_changed_path(struct sii8620 *ctx) sii8620_mt_write_stat(ctx, MHL_DST_REG(LINK_MODE), MHL_DST_LM_CLK_MODE_NORMAL | MHL_DST_LM_PATH_ENABLED); - if (!sii8620_is_mhl3(ctx)) - sii8620_mt_read_devcap(ctx, false); - sii8620_mt_set_cont(ctx, sii8620_sink_detected); } else { sii8620_mt_write_stat(ctx, MHL_DST_REG(LINK_MODE), MHL_DST_LM_CLK_MODE_NORMAL); @@ -1722,9 +1681,14 @@ static void sii8620_msc_mr_write_stat(struct sii8620 *ctx) sii8620_update_array(ctx->stat, st, MHL_DST_SIZE); sii8620_update_array(ctx->xstat, xst, MHL_XDS_SIZE); - if (ctx->stat[MHL_DST_CONNECTED_RDY] & MHL_DST_CONN_DCAP_RDY) + if (ctx->stat[MHL_DST_CONNECTED_RDY] & st[MHL_DST_CONNECTED_RDY] & + MHL_DST_CONN_DCAP_RDY) { sii8620_status_dcap_ready(ctx); + if (!sii8620_is_mhl3(ctx)) + sii8620_mt_read_devcap(ctx, false); + } + if (st[MHL_DST_LINK_MODE] & MHL_DST_LM_PATH_ENABLED) sii8620_status_changed_path(ctx); } @@ -1808,8 +1772,11 @@ static void sii8620_msc_mr_set_int(struct sii8620 *ctx) } if (ints[MHL_INT_RCHANGE] & MHL_INT_RC_FEAT_REQ) sii8620_send_features(ctx); - if (ints[MHL_INT_RCHANGE] & MHL_INT_RC_FEAT_COMPLETE) - sii8620_edid_read(ctx, 0); + if (ints[MHL_INT_RCHANGE] & MHL_INT_RC_FEAT_COMPLETE) { + ctx->feature_complete = true; + if (ctx->edid) + sii8620_enable_hpd(ctx); + } } static struct sii8620_mt_msg *sii8620_msc_msg_first(struct sii8620 *ctx) @@ -1884,6 +1851,15 @@ static void sii8620_irq_msc(struct sii8620 *ctx) if (stat & BIT_CBUS_MSC_MR_WRITE_STAT) sii8620_msc_mr_write_stat(ctx); + if (stat & BIT_CBUS_HPD_CHG) { + if (ctx->cbus_status & BIT_CBUS_STATUS_CBUS_HPD) { + ctx->sink_detected = true; + sii8620_identify_sink(ctx); + } else { + sii8620_hpd_unplugged(ctx); + } + } + if (stat & BIT_CBUS_MSC_MR_SET_INT) sii8620_msc_mr_set_int(ctx); @@ -1931,14 +1907,6 @@ static void sii8620_irq_edid(struct sii8620 *ctx) ctx->mt_state = MT_STATE_DONE; } -static void sii8620_scdt_high(struct sii8620 *ctx) -{ - sii8620_write_seq_static(ctx, - REG_INTR8_MASK, BIT_CEA_NEW_AVI | BIT_CEA_NEW_VSI, - REG_TPI_SC, BIT_TPI_SC_TPI_OUTPUT_MODE_0_HDMI, - ); -} - static void sii8620_irq_scdt(struct sii8620 *ctx) { u8 stat = sii8620_readb(ctx, REG_INTR5); @@ -1946,53 +1914,13 @@ static void sii8620_irq_scdt(struct sii8620 *ctx) if (stat & BIT_INTR_SCDT_CHANGE) { u8 cstat = sii8620_readb(ctx, REG_TMDS_CSTAT_P3); - if (cstat & BIT_TMDS_CSTAT_P3_SCDT) { - if (ctx->sink_type == SINK_HDMI) - /* enable infoframe interrupt */ - sii8620_scdt_high(ctx); - else - sii8620_start_video(ctx); - } + if (cstat & BIT_TMDS_CSTAT_P3_SCDT) + sii8620_start_video(ctx); } sii8620_write(ctx, REG_INTR5, stat); } -static void sii8620_new_vsi(struct sii8620 *ctx) -{ - u8 vsif[11]; - - sii8620_write(ctx, REG_RX_HDMI_CTRL2, - VAL_RX_HDMI_CTRL2_DEFVAL | - BIT_RX_HDMI_CTRL2_VSI_MON_SEL_VSI); - sii8620_read_buf(ctx, REG_RX_HDMI_MON_PKT_HEADER1, vsif, - ARRAY_SIZE(vsif)); -} - -static void sii8620_new_avi(struct sii8620 *ctx) -{ - sii8620_write(ctx, REG_RX_HDMI_CTRL2, VAL_RX_HDMI_CTRL2_DEFVAL); - sii8620_read_buf(ctx, REG_RX_HDMI_MON_PKT_HEADER1, ctx->avif, - ARRAY_SIZE(ctx->avif)); -} - -static void sii8620_irq_infr(struct sii8620 *ctx) -{ - u8 stat = sii8620_readb(ctx, REG_INTR8) - & (BIT_CEA_NEW_VSI | BIT_CEA_NEW_AVI); - - sii8620_write(ctx, REG_INTR8, stat); - - if (stat & BIT_CEA_NEW_VSI) - sii8620_new_vsi(ctx); - - if (stat & BIT_CEA_NEW_AVI) - sii8620_new_avi(ctx); - - if (stat & (BIT_CEA_NEW_VSI | BIT_CEA_NEW_AVI)) - sii8620_start_video(ctx); -} - static void sii8620_got_xdevcap(struct sii8620 *ctx, int ret) { if (ret < 0) @@ -2043,11 +1971,11 @@ static void sii8620_irq_ddc(struct sii8620 *ctx) if (stat & BIT_DDC_CMD_DONE) { sii8620_write(ctx, REG_INTR3_MASK, 0); - if (sii8620_is_mhl3(ctx)) + if (sii8620_is_mhl3(ctx) && !ctx->feature_complete) sii8620_mt_set_int(ctx, MHL_INT_REG(RCHANGE), MHL_INT_RC_FEAT_REQ); else - sii8620_edid_read(ctx, 0); + sii8620_enable_hpd(ctx); } sii8620_write(ctx, REG_INTR3, stat); } @@ -2074,7 +2002,6 @@ static irqreturn_t sii8620_irq_thread(int irq, void *data) { BIT_FAST_INTR_STAT_EDID, sii8620_irq_edid }, { BIT_FAST_INTR_STAT_DDC, sii8620_irq_ddc }, { BIT_FAST_INTR_STAT_SCDT, sii8620_irq_scdt }, - { BIT_FAST_INTR_STAT_INFR, sii8620_irq_infr }, }; struct sii8620 *ctx = data; u8 stats[LEN_FAST_INTR_STAT]; @@ -2112,7 +2039,6 @@ static void sii8620_cable_in(struct sii8620 *ctx) dev_err(dev, "Error powering on, %d.\n", ret); return; } - sii8620_hw_reset(ctx); sii8620_read_buf(ctx, REG_VND_IDL, ver, ARRAY_SIZE(ver)); ret = sii8620_clear_error(ctx); @@ -2268,17 +2194,43 @@ static void sii8620_detach(struct drm_bridge *bridge) rc_unregister_device(ctx->rc_dev); } +static int sii8620_is_packing_required(struct sii8620 *ctx, + const struct drm_display_mode *mode) +{ + int max_pclk, max_pclk_pp_mode; + + if (sii8620_is_mhl3(ctx)) { + max_pclk = MHL3_MAX_PCLK; + max_pclk_pp_mode = MHL3_MAX_PCLK_PP_MODE; + } else { + max_pclk = MHL1_MAX_PCLK; + max_pclk_pp_mode = MHL1_MAX_PCLK_PP_MODE; + } + + if (mode->clock < max_pclk) + return 0; + else if (mode->clock < max_pclk_pp_mode) + return 1; + else + return -1; +} + static enum drm_mode_status sii8620_mode_valid(struct drm_bridge *bridge, const struct drm_display_mode *mode) { struct sii8620 *ctx = bridge_to_sii8620(bridge); + int pack_required = sii8620_is_packing_required(ctx, mode); bool can_pack = ctx->devcap[MHL_DCAP_VID_LINK_MODE] & MHL_DCAP_VID_LINK_PPIXEL; - unsigned int max_pclk = sii8620_is_mhl3(ctx) ? MHL3_MAX_LCLK : - MHL1_MAX_LCLK; - max_pclk /= can_pack ? 2 : 3; - return (mode->clock > max_pclk) ? MODE_CLOCK_HIGH : MODE_OK; + switch (pack_required) { + case 0: + return MODE_OK; + case 1: + return (can_pack) ? MODE_OK : MODE_CLOCK_HIGH; + default: + return MODE_CLOCK_HIGH; + } } static bool sii8620_mode_fixup(struct drm_bridge *bridge, @@ -2286,43 +2238,16 @@ static bool sii8620_mode_fixup(struct drm_bridge *bridge, struct drm_display_mode *adjusted_mode) { struct sii8620 *ctx = bridge_to_sii8620(bridge); - int max_lclk; - bool ret = true; mutex_lock(&ctx->lock); - max_lclk = sii8620_is_mhl3(ctx) ? MHL3_MAX_LCLK : MHL1_MAX_LCLK; - if (max_lclk > 3 * adjusted_mode->clock) { - ctx->use_packed_pixel = 0; - goto end; - } - if ((ctx->devcap[MHL_DCAP_VID_LINK_MODE] & MHL_DCAP_VID_LINK_PPIXEL) && - max_lclk > 2 * adjusted_mode->clock) { - ctx->use_packed_pixel = 1; - goto end; - } - ret = false; -end: - if (ret) { - u8 vic = drm_match_cea_mode(adjusted_mode); - - if (!vic) { - union hdmi_infoframe frm; - u8 mhl_vic[] = { 0, 95, 94, 93, 98 }; - - /* FIXME: We need the connector here */ - drm_hdmi_vendor_infoframe_from_display_mode( - &frm.vendor.hdmi, NULL, adjusted_mode); - vic = frm.vendor.hdmi.vic; - if (vic >= ARRAY_SIZE(mhl_vic)) - vic = 0; - vic = mhl_vic[vic]; - } - ctx->video_code = vic; - ctx->pixel_clock = adjusted_mode->clock; - } + ctx->use_packed_pixel = sii8620_is_packing_required(ctx, adjusted_mode); + ctx->video_code = drm_match_cea_mode(adjusted_mode); + ctx->pixel_clock = adjusted_mode->clock; + mutex_unlock(&ctx->lock); - return ret; + + return true; } static const struct drm_bridge_funcs sii8620_bridge_funcs = { diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c index b553a6f2ff0e..7af748ed1c58 100644 --- a/drivers/gpu/drm/drm_drv.c +++ b/drivers/gpu/drm/drm_drv.c @@ -369,13 +369,6 @@ EXPORT_SYMBOL(drm_dev_exit); */ void drm_dev_unplug(struct drm_device *dev) { - drm_dev_unregister(dev); - - mutex_lock(&drm_global_mutex); - if (dev->open_count == 0) - drm_dev_put(dev); - mutex_unlock(&drm_global_mutex); - /* * After synchronizing any critical read section is guaranteed to see * the new value of ->unplugged, and any critical section which might @@ -384,6 +377,13 @@ void drm_dev_unplug(struct drm_device *dev) */ dev->unplugged = true; synchronize_srcu(&drm_unplug_srcu); + + drm_dev_unregister(dev); + + mutex_lock(&drm_global_mutex); + if (dev->open_count == 0) + drm_dev_put(dev); + mutex_unlock(&drm_global_mutex); } EXPORT_SYMBOL(drm_dev_unplug); diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 34c125e2d90c..7014a96546f4 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -340,14 +340,21 @@ struct drm_i915_file_private { unsigned int bsd_engine; -/* Client can have a maximum of 3 contexts banned before - * it is denied of creating new contexts. As one context - * ban needs 4 consecutive hangs, and more if there is - * progress in between, this is a last resort stop gap measure - * to limit the badly behaving clients access to gpu. +/* + * Every context ban increments per client ban score. Also + * hangs in short succession increments ban score. If ban threshold + * is reached, client is considered banned and submitting more work + * will fail. This is a stop gap measure to limit the badly behaving + * clients access to gpu. Note that unbannable contexts never increment + * the client ban score. */ -#define I915_MAX_CLIENT_CONTEXT_BANS 3 - atomic_t context_bans; +#define I915_CLIENT_SCORE_HANG_FAST 1 +#define I915_CLIENT_FAST_HANG_JIFFIES (60 * HZ) +#define I915_CLIENT_SCORE_CONTEXT_BAN 3 +#define I915_CLIENT_SCORE_BANNED 9 + /** ban_score: Accumulated score of all ctx bans and fast hangs. */ + atomic_t ban_score; + unsigned long hang_timestamp; }; /* Interface history: diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 3704f4c0c2c9..d44ad7bc1e94 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -2933,32 +2933,54 @@ i915_gem_object_pwrite_gtt(struct drm_i915_gem_object *obj, return 0; } +static void i915_gem_client_mark_guilty(struct drm_i915_file_private *file_priv, + const struct i915_gem_context *ctx) +{ + unsigned int score; + unsigned long prev_hang; + + if (i915_gem_context_is_banned(ctx)) + score = I915_CLIENT_SCORE_CONTEXT_BAN; + else + score = 0; + + prev_hang = xchg(&file_priv->hang_timestamp, jiffies); + if (time_before(jiffies, prev_hang + I915_CLIENT_FAST_HANG_JIFFIES)) + score += I915_CLIENT_SCORE_HANG_FAST; + + if (score) { + atomic_add(score, &file_priv->ban_score); + + DRM_DEBUG_DRIVER("client %s: gained %u ban score, now %u\n", + ctx->name, score, + atomic_read(&file_priv->ban_score)); + } +} + static void i915_gem_context_mark_guilty(struct i915_gem_context *ctx) { - bool banned; + unsigned int score; + bool banned, bannable; atomic_inc(&ctx->guilty_count); - banned = false; - if (i915_gem_context_is_bannable(ctx)) { - unsigned int score; + bannable = i915_gem_context_is_bannable(ctx); + score = atomic_add_return(CONTEXT_SCORE_GUILTY, &ctx->ban_score); + banned = score >= CONTEXT_SCORE_BAN_THRESHOLD; - score = atomic_add_return(CONTEXT_SCORE_GUILTY, - &ctx->ban_score); - banned = score >= CONTEXT_SCORE_BAN_THRESHOLD; + DRM_DEBUG_DRIVER("context %s: guilty %d, score %u, ban %s\n", + ctx->name, atomic_read(&ctx->guilty_count), + score, yesno(banned && bannable)); - DRM_DEBUG_DRIVER("context %s marked guilty (score %d) banned? %s\n", - ctx->name, score, yesno(banned)); - } - if (!banned) + /* Cool contexts don't accumulate client ban score */ + if (!bannable) return; - i915_gem_context_set_banned(ctx); - if (!IS_ERR_OR_NULL(ctx->file_priv)) { - atomic_inc(&ctx->file_priv->context_bans); - DRM_DEBUG_DRIVER("client %s has had %d context banned\n", - ctx->name, atomic_read(&ctx->file_priv->context_bans)); - } + if (banned) + i915_gem_context_set_banned(ctx); + + if (!IS_ERR_OR_NULL(ctx->file_priv)) + i915_gem_client_mark_guilty(ctx->file_priv, ctx); } static void i915_gem_context_mark_innocent(struct i915_gem_context *ctx) @@ -5736,6 +5758,7 @@ int i915_gem_open(struct drm_i915_private *i915, struct drm_file *file) INIT_LIST_HEAD(&file_priv->mm.request_list); file_priv->bsd_engine = -1; + file_priv->hang_timestamp = jiffies; ret = i915_gem_context_open(i915, file); if (ret) diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c index 33f8a4b3c981..060335d3d9e0 100644 --- a/drivers/gpu/drm/i915/i915_gem_context.c +++ b/drivers/gpu/drm/i915/i915_gem_context.c @@ -652,7 +652,7 @@ int i915_gem_switch_to_kernel_context(struct drm_i915_private *dev_priv) static bool client_is_banned(struct drm_i915_file_private *file_priv) { - return atomic_read(&file_priv->context_bans) > I915_MAX_CLIENT_CONTEXT_BANS; + return atomic_read(&file_priv->ban_score) >= I915_CLIENT_SCORE_BANNED; } int i915_gem_context_create_ioctl(struct drm_device *dev, void *data, diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index f627a8c47c58..22df17c8ca9b 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -489,7 +489,9 @@ eb_validate_vma(struct i915_execbuffer *eb, } static int -eb_add_vma(struct i915_execbuffer *eb, unsigned int i, struct i915_vma *vma) +eb_add_vma(struct i915_execbuffer *eb, + unsigned int i, unsigned batch_idx, + struct i915_vma *vma) { struct drm_i915_gem_exec_object2 *entry = &eb->exec[i]; int err; @@ -522,6 +524,24 @@ eb_add_vma(struct i915_execbuffer *eb, unsigned int i, struct i915_vma *vma) eb->flags[i] = entry->flags; vma->exec_flags = &eb->flags[i]; + /* + * SNA is doing fancy tricks with compressing batch buffers, which leads + * to negative relocation deltas. Usually that works out ok since the + * relocate address is still positive, except when the batch is placed + * very low in the GTT. Ensure this doesn't happen. + * + * Note that actual hangs have only been observed on gen7, but for + * paranoia do it everywhere. + */ + if (i == batch_idx) { + if (!(eb->flags[i] & EXEC_OBJECT_PINNED)) + eb->flags[i] |= __EXEC_OBJECT_NEEDS_BIAS; + if (eb->reloc_cache.has_fence) + eb->flags[i] |= EXEC_OBJECT_NEEDS_FENCE; + + eb->batch = vma; + } + err = 0; if (eb_pin_vma(eb, entry, vma)) { if (entry->offset != vma->node.start) { @@ -716,7 +736,7 @@ static int eb_lookup_vmas(struct i915_execbuffer *eb) { struct radix_tree_root *handles_vma = &eb->ctx->handles_vma; struct drm_i915_gem_object *obj; - unsigned int i; + unsigned int i, batch; int err; if (unlikely(i915_gem_context_is_closed(eb->ctx))) @@ -728,6 +748,8 @@ static int eb_lookup_vmas(struct i915_execbuffer *eb) INIT_LIST_HEAD(&eb->relocs); INIT_LIST_HEAD(&eb->unbound); + batch = eb_batch_index(eb); + for (i = 0; i < eb->buffer_count; i++) { u32 handle = eb->exec[i].handle; struct i915_lut_handle *lut; @@ -770,33 +792,16 @@ static int eb_lookup_vmas(struct i915_execbuffer *eb) lut->handle = handle; add_vma: - err = eb_add_vma(eb, i, vma); + err = eb_add_vma(eb, i, batch, vma); if (unlikely(err)) goto err_vma; GEM_BUG_ON(vma != eb->vma[i]); GEM_BUG_ON(vma->exec_flags != &eb->flags[i]); + GEM_BUG_ON(drm_mm_node_allocated(&vma->node) && + eb_vma_misplaced(&eb->exec[i], vma, eb->flags[i])); } - /* take note of the batch buffer before we might reorder the lists */ - i = eb_batch_index(eb); - eb->batch = eb->vma[i]; - GEM_BUG_ON(eb->batch->exec_flags != &eb->flags[i]); - - /* - * SNA is doing fancy tricks with compressing batch buffers, which leads - * to negative relocation deltas. Usually that works out ok since the - * relocate address is still positive, except when the batch is placed - * very low in the GTT. Ensure this doesn't happen. - * - * Note that actual hangs have only been observed on gen7, but for - * paranoia do it everywhere. - */ - if (!(eb->flags[i] & EXEC_OBJECT_PINNED)) - eb->flags[i] |= __EXEC_OBJECT_NEEDS_BIAS; - if (eb->reloc_cache.has_fence) - eb->flags[i] |= EXEC_OBJECT_NEEDS_FENCE; - eb->args->flags |= __EXEC_VALIDATED; return eb_reserve(eb); diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index f9bc3aaa90d0..4a02747ac658 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -1893,9 +1893,17 @@ static void i9xx_pipestat_irq_ack(struct drm_i915_private *dev_priv, /* * Clear the PIPE*STAT regs before the IIR + * + * Toggle the enable bits to make sure we get an + * edge in the ISR pipe event bit if we don't clear + * all the enabled status bits. Otherwise the edge + * triggered IIR on i965/g4x wouldn't notice that + * an interrupt is still pending. */ - if (pipe_stats[pipe]) - I915_WRITE(reg, enable_mask | pipe_stats[pipe]); + if (pipe_stats[pipe]) { + I915_WRITE(reg, pipe_stats[pipe]); + I915_WRITE(reg, enable_mask); + } } spin_unlock(&dev_priv->irq_lock); } diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index f11bb213ec07..7720569f2024 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -2425,12 +2425,17 @@ enum i915_power_well_id { #define _3D_CHICKEN _MMIO(0x2084) #define _3D_CHICKEN_HIZ_PLANE_DISABLE_MSAA_4X_SNB (1 << 10) #define _3D_CHICKEN2 _MMIO(0x208c) + +#define FF_SLICE_CHICKEN _MMIO(0x2088) +#define FF_SLICE_CHICKEN_CL_PROVOKING_VERTEX_FIX (1 << 1) + /* Disables pipelining of read flushes past the SF-WIZ interface. * Required on all Ironlake steppings according to the B-Spec, but the * particular danger of not doing so is not specified. */ # define _3D_CHICKEN2_WM_READ_PIPELINED (1 << 14) #define _3D_CHICKEN3 _MMIO(0x2090) +#define _3D_CHICKEN_SF_PROVOKING_VERTEX_FIX (1 << 12) #define _3D_CHICKEN_SF_DISABLE_OBJEND_CULL (1 << 10) #define _3D_CHICKEN3_AA_LINE_QUALITY_FIX_ENABLE (1 << 5) #define _3D_CHICKEN3_SF_DISABLE_FASTCLIP_CULL (1 << 5) diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c index de0e22322c76..072b326d5ee0 100644 --- a/drivers/gpu/drm/i915/intel_crt.c +++ b/drivers/gpu/drm/i915/intel_crt.c @@ -304,6 +304,9 @@ intel_crt_mode_valid(struct drm_connector *connector, int max_dotclk = dev_priv->max_dotclk_freq; int max_clock; + if (mode->flags & DRM_MODE_FLAG_DBLSCAN) + return MODE_NO_DBLESCAN; + if (mode->clock < 25000) return MODE_CLOCK_LOW; @@ -337,6 +340,12 @@ static bool intel_crt_compute_config(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config, struct drm_connector_state *conn_state) { + struct drm_display_mode *adjusted_mode = + &pipe_config->base.adjusted_mode; + + if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN) + return false; + return true; } @@ -344,6 +353,12 @@ static bool pch_crt_compute_config(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config, struct drm_connector_state *conn_state) { + struct drm_display_mode *adjusted_mode = + &pipe_config->base.adjusted_mode; + + if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN) + return false; + pipe_config->has_pch_encoder = true; return true; @@ -354,6 +369,11 @@ static bool hsw_crt_compute_config(struct intel_encoder *encoder, struct drm_connector_state *conn_state) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + struct drm_display_mode *adjusted_mode = + &pipe_config->base.adjusted_mode; + + if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN) + return false; pipe_config->has_pch_encoder = true; diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index dee3a8e659f1..2cc6faa1daa8 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -14469,12 +14469,22 @@ static enum drm_mode_status intel_mode_valid(struct drm_device *dev, const struct drm_display_mode *mode) { + /* + * Can't reject DBLSCAN here because Xorg ddxen can add piles + * of DBLSCAN modes to the output's mode list when they detect + * the scaling mode property on the connector. And they don't + * ask the kernel to validate those modes in any way until + * modeset time at which point the client gets a protocol error. + * So in order to not upset those clients we silently ignore the + * DBLSCAN flag on such connectors. For other connectors we will + * reject modes with the DBLSCAN flag in encoder->compute_config(). + * And we always reject DBLSCAN modes in connector->mode_valid() + * as we never want such modes on the connector's mode list. + */ + if (mode->vscan > 1) return MODE_NO_VSCAN; - if (mode->flags & DRM_MODE_FLAG_DBLSCAN) - return MODE_NO_DBLESCAN; - if (mode->flags & DRM_MODE_FLAG_HSKEW) return MODE_H_ILLEGAL; diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 8320f0e8e3be..16faea30114a 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -420,6 +420,9 @@ intel_dp_mode_valid(struct drm_connector *connector, int max_rate, mode_rate, max_lanes, max_link_clock; int max_dotclk; + if (mode->flags & DRM_MODE_FLAG_DBLSCAN) + return MODE_NO_DBLESCAN; + max_dotclk = intel_dp_downstream_max_dotclock(intel_dp); if (intel_dp_is_edp(intel_dp) && fixed_mode) { @@ -1862,7 +1865,10 @@ intel_dp_compute_config(struct intel_encoder *encoder, conn_state->scaling_mode); } - if ((IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) && + if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN) + return false; + + if (HAS_GMCH_DISPLAY(dev_priv) && adjusted_mode->flags & DRM_MODE_FLAG_INTERLACE) return false; @@ -2784,16 +2790,6 @@ static void g4x_disable_dp(struct intel_encoder *encoder, const struct drm_connector_state *old_conn_state) { intel_disable_dp(encoder, old_crtc_state, old_conn_state); - - /* disable the port before the pipe on g4x */ - intel_dp_link_down(encoder, old_crtc_state); -} - -static void ilk_disable_dp(struct intel_encoder *encoder, - const struct intel_crtc_state *old_crtc_state, - const struct drm_connector_state *old_conn_state) -{ - intel_disable_dp(encoder, old_crtc_state, old_conn_state); } static void vlv_disable_dp(struct intel_encoder *encoder, @@ -2807,13 +2803,19 @@ static void vlv_disable_dp(struct intel_encoder *encoder, intel_disable_dp(encoder, old_crtc_state, old_conn_state); } -static void ilk_post_disable_dp(struct intel_encoder *encoder, +static void g4x_post_disable_dp(struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base); enum port port = encoder->port; + /* + * Bspec does not list a specific disable sequence for g4x DP. + * Follow the ilk+ sequence (disable pipe before the port) for + * g4x DP as it does not suffer from underruns like the normal + * g4x modeset sequence (disable pipe after the port). + */ intel_dp_link_down(encoder, old_crtc_state); /* Only ilk+ has port A */ @@ -6337,7 +6339,7 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port, drm_connector_init(dev, connector, &intel_dp_connector_funcs, type); drm_connector_helper_add(connector, &intel_dp_connector_helper_funcs); - if (!IS_VALLEYVIEW(dev_priv) && !IS_CHERRYVIEW(dev_priv)) + if (!HAS_GMCH_DISPLAY(dev_priv)) connector->interlace_allowed = true; connector->doublescan_allowed = 0; @@ -6436,15 +6438,11 @@ bool intel_dp_init(struct drm_i915_private *dev_priv, intel_encoder->enable = vlv_enable_dp; intel_encoder->disable = vlv_disable_dp; intel_encoder->post_disable = vlv_post_disable_dp; - } else if (INTEL_GEN(dev_priv) >= 5) { - intel_encoder->pre_enable = g4x_pre_enable_dp; - intel_encoder->enable = g4x_enable_dp; - intel_encoder->disable = ilk_disable_dp; - intel_encoder->post_disable = ilk_post_disable_dp; } else { intel_encoder->pre_enable = g4x_pre_enable_dp; intel_encoder->enable = g4x_enable_dp; intel_encoder->disable = g4x_disable_dp; + intel_encoder->post_disable = g4x_post_disable_dp; } intel_dig_port->dp.output_reg = output_reg; diff --git a/drivers/gpu/drm/i915/intel_dp_mst.c b/drivers/gpu/drm/i915/intel_dp_mst.c index 9e6956c08688..5890500a3a8b 100644 --- a/drivers/gpu/drm/i915/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/intel_dp_mst.c @@ -48,6 +48,9 @@ static bool intel_dp_mst_compute_config(struct intel_encoder *encoder, bool reduce_m_n = drm_dp_has_quirk(&intel_dp->desc, DP_DPCD_QUIRK_LIMITED_M_N); + if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN) + return false; + pipe_config->has_pch_encoder = false; bpp = 24; if (intel_dp->compliance.test_data.bpc) { @@ -366,6 +369,9 @@ intel_dp_mst_mode_valid(struct drm_connector *connector, if (!intel_dp) return MODE_ERROR; + if (mode->flags & DRM_MODE_FLAG_DBLSCAN) + return MODE_NO_DBLESCAN; + max_link_clock = intel_dp_max_link_rate(intel_dp); max_lanes = intel_dp_max_lane_count(intel_dp); diff --git a/drivers/gpu/drm/i915/intel_dsi.c b/drivers/gpu/drm/i915/intel_dsi.c index cf39ca90d887..f349b3920199 100644 --- a/drivers/gpu/drm/i915/intel_dsi.c +++ b/drivers/gpu/drm/i915/intel_dsi.c @@ -326,6 +326,9 @@ static bool intel_dsi_compute_config(struct intel_encoder *encoder, conn_state->scaling_mode); } + if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN) + return false; + /* DSI uses short packets for sync events, so clear mode flags for DSI */ adjusted_mode->flags = 0; @@ -1266,6 +1269,9 @@ intel_dsi_mode_valid(struct drm_connector *connector, DRM_DEBUG_KMS("\n"); + if (mode->flags & DRM_MODE_FLAG_DBLSCAN) + return MODE_NO_DBLESCAN; + if (fixed_mode) { if (mode->hdisplay > fixed_mode->hdisplay) return MODE_PANEL; diff --git a/drivers/gpu/drm/i915/intel_dvo.c b/drivers/gpu/drm/i915/intel_dvo.c index a70d767313aa..61d908e0df0e 100644 --- a/drivers/gpu/drm/i915/intel_dvo.c +++ b/drivers/gpu/drm/i915/intel_dvo.c @@ -219,6 +219,9 @@ intel_dvo_mode_valid(struct drm_connector *connector, int max_dotclk = to_i915(connector->dev)->max_dotclk_freq; int target_clock = mode->clock; + if (mode->flags & DRM_MODE_FLAG_DBLSCAN) + return MODE_NO_DBLESCAN; + /* XXX: Validate clock range */ if (fixed_mode) { @@ -254,6 +257,9 @@ static bool intel_dvo_compute_config(struct intel_encoder *encoder, if (fixed_mode) intel_fixed_panel_mode(fixed_mode, adjusted_mode); + if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN) + return false; + return true; } diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index ee929f31f7db..d8cb53ef4351 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -1557,6 +1557,9 @@ intel_hdmi_mode_valid(struct drm_connector *connector, bool force_dvi = READ_ONCE(to_intel_digital_connector_state(connector->state)->force_audio) == HDMI_AUDIO_OFF_DVI; + if (mode->flags & DRM_MODE_FLAG_DBLSCAN) + return MODE_NO_DBLESCAN; + clock = mode->clock; if ((mode->flags & DRM_MODE_FLAG_3D_MASK) == DRM_MODE_FLAG_3D_FRAME_PACKING) @@ -1677,6 +1680,9 @@ bool intel_hdmi_compute_config(struct intel_encoder *encoder, int desired_bpp; bool force_dvi = intel_conn_state->force_audio == HDMI_AUDIO_OFF_DVI; + if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN) + return false; + pipe_config->has_hdmi_sink = !force_dvi && intel_hdmi->has_hdmi_sink; if (pipe_config->has_hdmi_sink) diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index 15434cad5430..7c4c8fb1dae4 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -1545,11 +1545,21 @@ static u32 *gen9_init_indirectctx_bb(struct intel_engine_cs *engine, u32 *batch) /* WaFlushCoherentL3CacheLinesAtContextSwitch:skl,bxt,glk */ batch = gen8_emit_flush_coherentl3_wa(engine, batch); + *batch++ = MI_LOAD_REGISTER_IMM(3); + /* WaDisableGatherAtSetShaderCommonSlice:skl,bxt,kbl,glk */ - *batch++ = MI_LOAD_REGISTER_IMM(1); *batch++ = i915_mmio_reg_offset(COMMON_SLICE_CHICKEN2); *batch++ = _MASKED_BIT_DISABLE( GEN9_DISABLE_GATHER_AT_SET_SHADER_COMMON_SLICE); + + /* BSpec: 11391 */ + *batch++ = i915_mmio_reg_offset(FF_SLICE_CHICKEN); + *batch++ = _MASKED_BIT_ENABLE(FF_SLICE_CHICKEN_CL_PROVOKING_VERTEX_FIX); + + /* BSpec: 11299 */ + *batch++ = i915_mmio_reg_offset(_3D_CHICKEN3); + *batch++ = _MASKED_BIT_ENABLE(_3D_CHICKEN_SF_PROVOKING_VERTEX_FIX); + *batch++ = MI_NOOP; /* WaClearSlmSpaceAtContextSwitch:kbl */ @@ -2641,10 +2651,8 @@ static int execlists_context_deferred_alloc(struct i915_gem_context *ctx, context_size += LRC_HEADER_PAGES * PAGE_SIZE; ctx_obj = i915_gem_object_create(ctx->i915, context_size); - if (IS_ERR(ctx_obj)) { - ret = PTR_ERR(ctx_obj); - goto error_deref_obj; - } + if (IS_ERR(ctx_obj)) + return PTR_ERR(ctx_obj); vma = i915_vma_instance(ctx_obj, &ctx->i915->ggtt.base, NULL); if (IS_ERR(vma)) { diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c index d278f24ba6ae..48f618dc9abb 100644 --- a/drivers/gpu/drm/i915/intel_lvds.c +++ b/drivers/gpu/drm/i915/intel_lvds.c @@ -380,6 +380,8 @@ intel_lvds_mode_valid(struct drm_connector *connector, struct drm_display_mode *fixed_mode = intel_connector->panel.fixed_mode; int max_pixclk = to_i915(connector->dev)->max_dotclk_freq; + if (mode->flags & DRM_MODE_FLAG_DBLSCAN) + return MODE_NO_DBLESCAN; if (mode->hdisplay > fixed_mode->hdisplay) return MODE_PANEL; if (mode->vdisplay > fixed_mode->vdisplay) @@ -429,6 +431,9 @@ static bool intel_lvds_compute_config(struct intel_encoder *intel_encoder, intel_fixed_panel_mode(intel_connector->panel.fixed_mode, adjusted_mode); + if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN) + return false; + if (HAS_PCH_SPLIT(dev_priv)) { pipe_config->has_pch_encoder = true; diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c index 25005023c243..26975df4e593 100644 --- a/drivers/gpu/drm/i915/intel_sdvo.c +++ b/drivers/gpu/drm/i915/intel_sdvo.c @@ -1160,6 +1160,9 @@ static bool intel_sdvo_compute_config(struct intel_encoder *encoder, adjusted_mode); } + if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN) + return false; + /* * Make the CRTC code factor in the SDVO pixel multiplier. The * SDVO device will factor out the multiplier during mode_set. @@ -1621,6 +1624,9 @@ intel_sdvo_mode_valid(struct drm_connector *connector, struct intel_sdvo *intel_sdvo = intel_attached_sdvo(connector); int max_dotclk = to_i915(connector->dev)->max_dotclk_freq; + if (mode->flags & DRM_MODE_FLAG_DBLSCAN) + return MODE_NO_DBLESCAN; + if (intel_sdvo->pixel_clock_min > mode->clock) return MODE_CLOCK_LOW; diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c index 885fc3809f7f..b55b5c157e38 100644 --- a/drivers/gpu/drm/i915/intel_tv.c +++ b/drivers/gpu/drm/i915/intel_tv.c @@ -850,6 +850,9 @@ intel_tv_mode_valid(struct drm_connector *connector, const struct tv_mode *tv_mode = intel_tv_mode_find(connector->state); int max_dotclk = to_i915(connector->dev)->max_dotclk_freq; + if (mode->flags & DRM_MODE_FLAG_DBLSCAN) + return MODE_NO_DBLESCAN; + if (mode->clock > max_dotclk) return MODE_CLOCK_HIGH; @@ -877,16 +880,21 @@ intel_tv_compute_config(struct intel_encoder *encoder, struct drm_connector_state *conn_state) { const struct tv_mode *tv_mode = intel_tv_mode_find(conn_state); + struct drm_display_mode *adjusted_mode = + &pipe_config->base.adjusted_mode; if (!tv_mode) return false; - pipe_config->base.adjusted_mode.crtc_clock = tv_mode->clock; + if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN) + return false; + + adjusted_mode->crtc_clock = tv_mode->clock; DRM_DEBUG_KMS("forcing bpc to 8 for TV\n"); pipe_config->pipe_bpp = 8*3; /* TV has it's own notion of sync and other mode flags, so clear them. */ - pipe_config->base.adjusted_mode.flags = 0; + adjusted_mode->flags = 0; /* * FIXME: We don't check whether the input mode is actually what we want diff --git a/drivers/gpu/drm/nouveau/dispnv50/curs507a.c b/drivers/gpu/drm/nouveau/dispnv50/curs507a.c index 291c08117ab6..397143b639c6 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/curs507a.c +++ b/drivers/gpu/drm/nouveau/dispnv50/curs507a.c @@ -132,7 +132,7 @@ curs507a_new_(const struct nv50_wimm_func *func, struct nouveau_drm *drm, nvif_object_map(&wndw->wimm.base.user, NULL, 0); wndw->immd = func; - wndw->ctxdma.parent = &disp->core->chan.base.user; + wndw->ctxdma.parent = NULL; return 0; } diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c index 224963b533a6..c5a9bc1af5af 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c +++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c @@ -444,14 +444,17 @@ nv50_wndw_prepare_fb(struct drm_plane *plane, struct drm_plane_state *state) if (ret) return ret; - ctxdma = nv50_wndw_ctxdma_new(wndw, fb); - if (IS_ERR(ctxdma)) { - nouveau_bo_unpin(fb->nvbo); - return PTR_ERR(ctxdma); + if (wndw->ctxdma.parent) { + ctxdma = nv50_wndw_ctxdma_new(wndw, fb); + if (IS_ERR(ctxdma)) { + nouveau_bo_unpin(fb->nvbo); + return PTR_ERR(ctxdma); + } + + asyw->image.handle[0] = ctxdma->object.handle; } asyw->state.fence = reservation_object_get_excl_rcu(fb->nvbo->bo.resv); - asyw->image.handle[0] = ctxdma->object.handle; asyw->image.offset[0] = fb->nvbo->bo.offset; if (wndw->func->prepare) { diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c index b8cda9449241..768207fbbae3 100644 --- a/drivers/gpu/drm/qxl/qxl_display.c +++ b/drivers/gpu/drm/qxl/qxl_display.c @@ -623,7 +623,7 @@ static void qxl_cursor_atomic_update(struct drm_plane *plane, struct qxl_cursor_cmd *cmd; struct qxl_cursor *cursor; struct drm_gem_object *obj; - struct qxl_bo *cursor_bo = NULL, *user_bo = NULL; + struct qxl_bo *cursor_bo = NULL, *user_bo = NULL, *old_cursor_bo = NULL; int ret; void *user_ptr; int size = 64*64*4; @@ -677,7 +677,7 @@ static void qxl_cursor_atomic_update(struct drm_plane *plane, cursor_bo, 0); cmd->type = QXL_CURSOR_SET; - qxl_bo_unref(&qcrtc->cursor_bo); + old_cursor_bo = qcrtc->cursor_bo; qcrtc->cursor_bo = cursor_bo; cursor_bo = NULL; } else { @@ -697,6 +697,9 @@ static void qxl_cursor_atomic_update(struct drm_plane *plane, qxl_push_cursor_ring_release(qdev, release, QXL_CMD_CURSOR, false); qxl_release_fence_buffer_objects(release); + if (old_cursor_bo) + qxl_bo_unref(&old_cursor_bo); + qxl_bo_unref(&cursor_bo); return; diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c index 08747fc3ee71..8232b39e16ca 100644 --- a/drivers/gpu/drm/sun4i/sun4i_tcon.c +++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c @@ -17,7 +17,6 @@ #include <drm/drm_encoder.h> #include <drm/drm_modes.h> #include <drm/drm_of.h> -#include <drm/drm_panel.h> #include <uapi/drm/drm_mode.h> @@ -418,9 +417,6 @@ static void sun4i_tcon0_mode_set_lvds(struct sun4i_tcon *tcon, static void sun4i_tcon0_mode_set_rgb(struct sun4i_tcon *tcon, const struct drm_display_mode *mode) { - struct drm_panel *panel = tcon->panel; - struct drm_connector *connector = panel->connector; - struct drm_display_info display_info = connector->display_info; unsigned int bp, hsync, vsync; u8 clk_delay; u32 val = 0; @@ -478,27 +474,6 @@ static void sun4i_tcon0_mode_set_rgb(struct sun4i_tcon *tcon, if (mode->flags & DRM_MODE_FLAG_PVSYNC) val |= SUN4I_TCON0_IO_POL_VSYNC_POSITIVE; - /* - * On A20 and similar SoCs, the only way to achieve Positive Edge - * (Rising Edge), is setting dclk clock phase to 2/3(240°). - * By default TCON works in Negative Edge(Falling Edge), - * this is why phase is set to 0 in that case. - * Unfortunately there's no way to logically invert dclk through - * IO_POL register. - * The only acceptable way to work, triple checked with scope, - * is using clock phase set to 0° for Negative Edge and set to 240° - * for Positive Edge. - * On A33 and similar SoCs there would be a 90° phase option, - * but it divides also dclk by 2. - * Following code is a way to avoid quirks all around TCON - * and DOTCLOCK drivers. - */ - if (display_info.bus_flags & DRM_BUS_FLAG_PIXDATA_POSEDGE) - clk_set_phase(tcon->dclk, 240); - - if (display_info.bus_flags & DRM_BUS_FLAG_PIXDATA_NEGEDGE) - clk_set_phase(tcon->dclk, 0); - regmap_update_bits(tcon->regs, SUN4I_TCON0_IO_POL_REG, SUN4I_TCON0_IO_POL_HSYNC_POSITIVE | SUN4I_TCON0_IO_POL_VSYNC_POSITIVE, val); diff --git a/drivers/hid/hid-google-hammer.c b/drivers/hid/hid-google-hammer.c index 7b8e17b03cb8..6bf4da7ad63a 100644 --- a/drivers/hid/hid-google-hammer.c +++ b/drivers/hid/hid-google-hammer.c @@ -124,6 +124,8 @@ static const struct hid_device_id hammer_devices[] = { USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_STAFF) }, { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_WAND) }, + { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, + USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_WHISKERS) }, { } }; MODULE_DEVICE_TABLE(hid, hammer_devices); diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index a85634fe033f..c7981ddd8776 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -452,6 +452,7 @@ #define USB_DEVICE_ID_GOOGLE_TOUCH_ROSE 0x5028 #define USB_DEVICE_ID_GOOGLE_STAFF 0x502b #define USB_DEVICE_ID_GOOGLE_WAND 0x502d +#define USB_DEVICE_ID_GOOGLE_WHISKERS 0x5030 #define USB_VENDOR_ID_GOTOP 0x08f2 #define USB_DEVICE_ID_SUPER_Q2 0x007f diff --git a/drivers/hid/hid-steam.c b/drivers/hid/hid-steam.c index cb86cc834201..0422ec2b13d2 100644 --- a/drivers/hid/hid-steam.c +++ b/drivers/hid/hid-steam.c @@ -573,7 +573,7 @@ static bool steam_is_valve_interface(struct hid_device *hdev) static int steam_client_ll_parse(struct hid_device *hdev) { - struct steam_device *steam = hid_get_drvdata(hdev); + struct steam_device *steam = hdev->driver_data; return hid_parse_report(hdev, steam->hdev->dev_rdesc, steam->hdev->dev_rsize); @@ -590,7 +590,7 @@ static void steam_client_ll_stop(struct hid_device *hdev) static int steam_client_ll_open(struct hid_device *hdev) { - struct steam_device *steam = hid_get_drvdata(hdev); + struct steam_device *steam = hdev->driver_data; int ret; ret = hid_hw_open(steam->hdev); @@ -605,7 +605,7 @@ static int steam_client_ll_open(struct hid_device *hdev) static void steam_client_ll_close(struct hid_device *hdev) { - struct steam_device *steam = hid_get_drvdata(hdev); + struct steam_device *steam = hdev->driver_data; mutex_lock(&steam->mutex); steam->client_opened = false; @@ -623,7 +623,7 @@ static int steam_client_ll_raw_request(struct hid_device *hdev, size_t count, unsigned char report_type, int reqtype) { - struct steam_device *steam = hid_get_drvdata(hdev); + struct steam_device *steam = hdev->driver_data; return hid_hw_raw_request(steam->hdev, reportnum, buf, count, report_type, reqtype); @@ -710,7 +710,7 @@ static int steam_probe(struct hid_device *hdev, ret = PTR_ERR(steam->client_hdev); goto client_hdev_fail; } - hid_set_drvdata(steam->client_hdev, steam); + steam->client_hdev->driver_data = steam; /* * With the real steam controller interface, do not connect hidraw. diff --git a/drivers/hid/intel-ish-hid/ipc/pci-ish.c b/drivers/hid/intel-ish-hid/ipc/pci-ish.c index 582e449be9fe..a2c53ea3b5ed 100644 --- a/drivers/hid/intel-ish-hid/ipc/pci-ish.c +++ b/drivers/hid/intel-ish-hid/ipc/pci-ish.c @@ -205,8 +205,7 @@ static void ish_remove(struct pci_dev *pdev) kfree(ishtp_dev); } -#ifdef CONFIG_PM -static struct device *ish_resume_device; +static struct device __maybe_unused *ish_resume_device; /* 50ms to get resume response */ #define WAIT_FOR_RESUME_ACK_MS 50 @@ -220,7 +219,7 @@ static struct device *ish_resume_device; * in that case a simple resume message is enough, others we need * a reset sequence. */ -static void ish_resume_handler(struct work_struct *work) +static void __maybe_unused ish_resume_handler(struct work_struct *work) { struct pci_dev *pdev = to_pci_dev(ish_resume_device); struct ishtp_device *dev = pci_get_drvdata(pdev); @@ -262,7 +261,7 @@ static void ish_resume_handler(struct work_struct *work) * * Return: 0 to the pm core */ -static int ish_suspend(struct device *device) +static int __maybe_unused ish_suspend(struct device *device) { struct pci_dev *pdev = to_pci_dev(device); struct ishtp_device *dev = pci_get_drvdata(pdev); @@ -288,7 +287,7 @@ static int ish_suspend(struct device *device) return 0; } -static DECLARE_WORK(resume_work, ish_resume_handler); +static __maybe_unused DECLARE_WORK(resume_work, ish_resume_handler); /** * ish_resume() - ISH resume callback * @device: device pointer @@ -297,7 +296,7 @@ static DECLARE_WORK(resume_work, ish_resume_handler); * * Return: 0 to the pm core */ -static int ish_resume(struct device *device) +static int __maybe_unused ish_resume(struct device *device) { struct pci_dev *pdev = to_pci_dev(device); struct ishtp_device *dev = pci_get_drvdata(pdev); @@ -311,21 +310,14 @@ static int ish_resume(struct device *device) return 0; } -static const struct dev_pm_ops ish_pm_ops = { - .suspend = ish_suspend, - .resume = ish_resume, -}; -#define ISHTP_ISH_PM_OPS (&ish_pm_ops) -#else -#define ISHTP_ISH_PM_OPS NULL -#endif /* CONFIG_PM */ +static SIMPLE_DEV_PM_OPS(ish_pm_ops, ish_suspend, ish_resume); static struct pci_driver ish_driver = { .name = KBUILD_MODNAME, .id_table = ish_pci_tbl, .probe = ish_probe, .remove = ish_remove, - .driver.pm = ISHTP_ISH_PM_OPS, + .driver.pm = &ish_pm_ops, }; module_pci_driver(ish_driver); diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c index c101369b51de..d6797535fff9 100644 --- a/drivers/hid/wacom_sys.c +++ b/drivers/hid/wacom_sys.c @@ -395,6 +395,14 @@ static void wacom_usage_mapping(struct hid_device *hdev, } } + /* 2nd-generation Intuos Pro Large has incorrect Y maximum */ + if (hdev->vendor == USB_VENDOR_ID_WACOM && + hdev->product == 0x0358 && + WACOM_PEN_FIELD(field) && + wacom_equivalent_usage(usage->hid) == HID_GD_Y) { + field->logical_maximum = 43200; + } + switch (usage->hid) { case HID_GD_X: features->x_max = field->logical_maximum; diff --git a/drivers/hwmon/dell-smm-hwmon.c b/drivers/hwmon/dell-smm-hwmon.c index bf3bb7e1adab..9d3ef879dc51 100644 --- a/drivers/hwmon/dell-smm-hwmon.c +++ b/drivers/hwmon/dell-smm-hwmon.c @@ -1074,6 +1074,13 @@ static struct dmi_system_id i8k_blacklist_fan_support_dmi_table[] __initdata = { DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Vostro 3360"), }, }, + { + .ident = "Dell XPS13 9333", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "XPS13 9333"), + }, + }, { } }; diff --git a/drivers/hwmon/nct6775.c b/drivers/hwmon/nct6775.c index 155d4d1d1585..f9d1349c3286 100644 --- a/drivers/hwmon/nct6775.c +++ b/drivers/hwmon/nct6775.c @@ -4175,7 +4175,7 @@ static int nct6775_probe(struct platform_device *pdev) * The temperature is already monitored if the respective bit in <mask> * is set. */ - for (i = 0; i < 32; i++) { + for (i = 0; i < 31; i++) { if (!(data->temp_mask & BIT(i + 1))) continue; if (!reg_temp_alternate[i]) diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index 3ae2339dd27a..2094d136513d 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -736,10 +736,6 @@ static ssize_t ib_uverbs_write(struct file *filp, const char __user *buf, if (ret) return ret; - if (!file->ucontext && - (command != IB_USER_VERBS_CMD_GET_CONTEXT || extended)) - return -EINVAL; - if (extended) { if (count < (sizeof(hdr) + sizeof(ex_hdr))) return -EINVAL; @@ -759,6 +755,16 @@ static ssize_t ib_uverbs_write(struct file *filp, const char __user *buf, goto out; } + /* + * Must be after the ib_dev check, as once the RCU clears ib_dev == + * NULL means ucontext == NULL + */ + if (!file->ucontext && + (command != IB_USER_VERBS_CMD_GET_CONTEXT || extended)) { + ret = -EINVAL; + goto out; + } + if (!verify_command_mask(ib_dev, command, extended)) { ret = -EOPNOTSUPP; goto out; diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index 0b56828c1319..9d6beb948535 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -1562,11 +1562,12 @@ EXPORT_SYMBOL(ib_destroy_qp); /* Completion queues */ -struct ib_cq *ib_create_cq(struct ib_device *device, - ib_comp_handler comp_handler, - void (*event_handler)(struct ib_event *, void *), - void *cq_context, - const struct ib_cq_init_attr *cq_attr) +struct ib_cq *__ib_create_cq(struct ib_device *device, + ib_comp_handler comp_handler, + void (*event_handler)(struct ib_event *, void *), + void *cq_context, + const struct ib_cq_init_attr *cq_attr, + const char *caller) { struct ib_cq *cq; @@ -1580,12 +1581,13 @@ struct ib_cq *ib_create_cq(struct ib_device *device, cq->cq_context = cq_context; atomic_set(&cq->usecnt, 0); cq->res.type = RDMA_RESTRACK_CQ; + cq->res.kern_name = caller; rdma_restrack_add(&cq->res); } return cq; } -EXPORT_SYMBOL(ib_create_cq); +EXPORT_SYMBOL(__ib_create_cq); int rdma_set_cq_moderation(struct ib_cq *cq, u16 cq_count, u16 cq_period) { diff --git a/drivers/infiniband/hw/mlx4/mr.c b/drivers/infiniband/hw/mlx4/mr.c index ed1f253faf97..c7c85c22e4e3 100644 --- a/drivers/infiniband/hw/mlx4/mr.c +++ b/drivers/infiniband/hw/mlx4/mr.c @@ -486,8 +486,11 @@ int mlx4_ib_rereg_user_mr(struct ib_mr *mr, int flags, } if (flags & IB_MR_REREG_ACCESS) { - if (ib_access_writable(mr_access_flags) && !mmr->umem->writable) - return -EPERM; + if (ib_access_writable(mr_access_flags) && + !mmr->umem->writable) { + err = -EPERM; + goto release_mpt_entry; + } err = mlx4_mr_hw_change_access(dev->dev, *pmpt_entry, convert_access(mr_access_flags)); diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index e52dd21519b4..e3e330f59c2c 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -3199,8 +3199,8 @@ static int flow_counters_set_data(struct ib_counters *ibcounters, if (!mcounters->hw_cntrs_hndl) { mcounters->hw_cntrs_hndl = mlx5_fc_create( to_mdev(ibcounters->device)->mdev, false); - if (!mcounters->hw_cntrs_hndl) { - ret = -ENOMEM; + if (IS_ERR(mcounters->hw_cntrs_hndl)) { + ret = PTR_ERR(mcounters->hw_cntrs_hndl); goto free; } hw_hndl = true; @@ -3546,29 +3546,35 @@ static struct ib_flow *mlx5_ib_create_flow(struct ib_qp *qp, return ERR_PTR(-ENOMEM); err = ib_copy_from_udata(ucmd, udata, required_ucmd_sz); - if (err) { - kfree(ucmd); - return ERR_PTR(err); - } + if (err) + goto free_ucmd; } - if (flow_attr->priority > MLX5_IB_FLOW_LAST_PRIO) - return ERR_PTR(-ENOMEM); + if (flow_attr->priority > MLX5_IB_FLOW_LAST_PRIO) { + err = -ENOMEM; + goto free_ucmd; + } if (domain != IB_FLOW_DOMAIN_USER || flow_attr->port > dev->num_ports || (flow_attr->flags & ~(IB_FLOW_ATTR_FLAGS_DONT_TRAP | - IB_FLOW_ATTR_FLAGS_EGRESS))) - return ERR_PTR(-EINVAL); + IB_FLOW_ATTR_FLAGS_EGRESS))) { + err = -EINVAL; + goto free_ucmd; + } if (is_egress && (flow_attr->type == IB_FLOW_ATTR_ALL_DEFAULT || - flow_attr->type == IB_FLOW_ATTR_MC_DEFAULT)) - return ERR_PTR(-EINVAL); + flow_attr->type == IB_FLOW_ATTR_MC_DEFAULT)) { + err = -EINVAL; + goto free_ucmd; + } dst = kzalloc(sizeof(*dst), GFP_KERNEL); - if (!dst) - return ERR_PTR(-ENOMEM); + if (!dst) { + err = -ENOMEM; + goto free_ucmd; + } mutex_lock(&dev->flow_db->lock); @@ -3637,8 +3643,8 @@ destroy_ft: unlock: mutex_unlock(&dev->flow_db->lock); kfree(dst); +free_ucmd: kfree(ucmd); - kfree(handler); return ERR_PTR(err); } diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c index f7ac8fc9b531..f07b8df96f43 100644 --- a/drivers/infiniband/hw/qedr/verbs.c +++ b/drivers/infiniband/hw/qedr/verbs.c @@ -1957,6 +1957,9 @@ int qedr_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, } if (attr_mask & (IB_QP_AV | IB_QP_PATH_MTU)) { + if (rdma_protocol_iwarp(&dev->ibdev, 1)) + return -EINVAL; + if (attr_mask & IB_QP_PATH_MTU) { if (attr->path_mtu < IB_MTU_256 || attr->path_mtu > IB_MTU_4096) { diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c index f30eeba3f772..8be27238a86e 100644 --- a/drivers/infiniband/sw/rxe/rxe_req.c +++ b/drivers/infiniband/sw/rxe/rxe_req.c @@ -645,6 +645,9 @@ next_wqe: } else { goto exit; } + if ((wqe->wr.send_flags & IB_SEND_SIGNALED) || + qp->sq_sig_type == IB_SIGNAL_ALL_WR) + rxe_run_task(&qp->comp.task, 1); qp->req.wqe_index = next_index(qp->sq.queue, qp->req.wqe_index); goto next_wqe; @@ -709,6 +712,7 @@ next_wqe: if (fill_packet(qp, wqe, &pkt, skb, payload)) { pr_debug("qp#%d Error during fill packet\n", qp_num(qp)); + kfree_skb(skb); goto err; } @@ -740,7 +744,6 @@ next_wqe: goto next_wqe; err: - kfree_skb(skb); wqe->status = IB_WC_LOC_PROT_ERR; wqe->state = wqe_state_error; __rxe_do_task(&qp->comp.task); 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/cisco/enic/enic_clsf.c b/drivers/net/ethernet/cisco/enic/enic_clsf.c index 973c1fb70d09..99038dfc7fbe 100644 --- a/drivers/net/ethernet/cisco/enic/enic_clsf.c +++ b/drivers/net/ethernet/cisco/enic/enic_clsf.c @@ -79,7 +79,6 @@ void enic_rfs_flw_tbl_init(struct enic *enic) enic->rfs_h.max = enic->config.num_arfs; enic->rfs_h.free = enic->rfs_h.max; enic->rfs_h.toclean = 0; - enic_rfs_timer_start(enic); } void enic_rfs_flw_tbl_free(struct enic *enic) @@ -88,7 +87,6 @@ void enic_rfs_flw_tbl_free(struct enic *enic) enic_rfs_timer_stop(enic); spin_lock_bh(&enic->rfs_h.lock); - enic->rfs_h.free = 0; for (i = 0; i < (1 << ENIC_RFS_FLW_BITSHIFT); i++) { struct hlist_head *hhead; struct hlist_node *tmp; @@ -99,6 +97,7 @@ void enic_rfs_flw_tbl_free(struct enic *enic) enic_delfltr(enic, n->fltr_id); hlist_del(&n->node); kfree(n); + enic->rfs_h.free++; } } spin_unlock_bh(&enic->rfs_h.lock); diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c index 30d2eaa18c04..90c645b8538e 100644 --- a/drivers/net/ethernet/cisco/enic/enic_main.c +++ b/drivers/net/ethernet/cisco/enic/enic_main.c @@ -1920,7 +1920,7 @@ static int enic_open(struct net_device *netdev) { struct enic *enic = netdev_priv(netdev); unsigned int i; - int err; + int err, ret; err = enic_request_intr(enic); if (err) { @@ -1971,16 +1971,15 @@ static int enic_open(struct net_device *netdev) vnic_intr_unmask(&enic->intr[i]); enic_notify_timer_start(enic); - enic_rfs_flw_tbl_init(enic); + enic_rfs_timer_start(enic); return 0; err_out_free_rq: for (i = 0; i < enic->rq_count; i++) { - err = vnic_rq_disable(&enic->rq[i]); - if (err) - return err; - vnic_rq_clean(&enic->rq[i], enic_free_rq_buf); + ret = vnic_rq_disable(&enic->rq[i]); + if (!ret) + vnic_rq_clean(&enic->rq[i], enic_free_rq_buf); } enic_dev_notify_unset(enic); err_out_free_intr: @@ -2904,6 +2903,7 @@ static int enic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) timer_setup(&enic->notify_timer, enic_notify_timer, 0); + enic_rfs_flw_tbl_init(enic); enic_set_rx_coal_setting(enic); INIT_WORK(&enic->reset, enic_reset); INIT_WORK(&enic->tx_hang_reset, enic_tx_hang_reset); diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c index 78db8e62a83f..ed6c76d20b45 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.c +++ b/drivers/net/ethernet/faraday/ftgmac100.c @@ -1735,8 +1735,8 @@ static void ftgmac100_ncsi_handler(struct ncsi_dev *nd) if (unlikely(nd->state != ncsi_dev_state_functional)) return; - netdev_info(nd->dev, "NCSI interface %s\n", - nd->link_up ? "up" : "down"); + netdev_dbg(nd->dev, "NCSI interface %s\n", + nd->link_up ? "up" : "down"); } static void ftgmac100_setup_clk(struct ftgmac100 *priv) diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 8ffb7454e67c..ed6dbcfd4e96 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -2103,9 +2103,8 @@ static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring, unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2; #else unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) + - SKB_DATA_ALIGN(I40E_SKB_PAD + - (xdp->data_end - - xdp->data_hard_start)); + SKB_DATA_ALIGN(xdp->data_end - + xdp->data_hard_start); #endif struct sk_buff *skb; @@ -2124,7 +2123,7 @@ static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring, return NULL; /* update pointers within the skb to store the data */ - skb_reserve(skb, I40E_SKB_PAD + (xdp->data - xdp->data_hard_start)); + skb_reserve(skb, xdp->data - xdp->data_hard_start); __skb_put(skb, xdp->data_end - xdp->data); if (metasize) skb_metadata_set(skb, metasize); diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c index 8f31406ec894..f0b01385d5cb 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c @@ -255,9 +255,8 @@ qed_dcbx_get_app_protocol_type(struct qed_hwfn *p_hwfn, *type = DCBX_PROTOCOL_ROCE_V2; } else { *type = DCBX_MAX_PROTOCOL_TYPE; - DP_ERR(p_hwfn, - "No action required, App TLV id = 0x%x app_prio_bitmap = 0x%x\n", - id, app_prio_bitmap); + DP_ERR(p_hwfn, "No action required, App TLV entry = 0x%x\n", + app_prio_bitmap); return false; } @@ -1479,8 +1478,8 @@ static u8 qed_dcbnl_getcap(struct qed_dev *cdev, int capid, u8 *cap) *cap = 0x80; break; case DCB_CAP_ATTR_DCBX: - *cap = (DCB_CAP_DCBX_LLD_MANAGED | DCB_CAP_DCBX_VER_CEE | - DCB_CAP_DCBX_VER_IEEE | DCB_CAP_DCBX_STATIC); + *cap = (DCB_CAP_DCBX_VER_CEE | DCB_CAP_DCBX_VER_IEEE | + DCB_CAP_DCBX_STATIC); break; default: *cap = false; @@ -1548,8 +1547,6 @@ static u8 qed_dcbnl_getdcbx(struct qed_dev *cdev) if (!dcbx_info) return 0; - if (dcbx_info->operational.enabled) - mode |= DCB_CAP_DCBX_LLD_MANAGED; if (dcbx_info->operational.ieee) mode |= DCB_CAP_DCBX_VER_IEEE; if (dcbx_info->operational.cee) diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c index c97ebd681c47..012973d75ad0 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c @@ -201,8 +201,9 @@ void qed_ll2b_complete_rx_packet(void *cxt, struct qed_ll2_comp_rx_data *data) skb = build_skb(buffer->data, 0); if (!skb) { - rc = -ENOMEM; - goto out_post; + DP_INFO(cdev, "Failed to build SKB\n"); + kfree(buffer->data); + goto out_post1; } data->u.placement_offset += NET_SKB_PAD; @@ -224,8 +225,14 @@ void qed_ll2b_complete_rx_packet(void *cxt, struct qed_ll2_comp_rx_data *data) cdev->ll2->cbs->rx_cb(cdev->ll2->cb_cookie, skb, data->opaque_data_0, data->opaque_data_1); + } else { + DP_VERBOSE(p_hwfn, (NETIF_MSG_RX_STATUS | NETIF_MSG_PKTDATA | + QED_MSG_LL2 | QED_MSG_STORAGE), + "Dropping the packet\n"); + kfree(buffer->data); } +out_post1: /* Update Buffer information and update FW producer */ buffer->data = new_data; buffer->phys_addr = new_phys_addr; diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index b04d57ca5176..5c10fd7210c3 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -567,8 +567,16 @@ static irqreturn_t qed_single_int(int irq, void *dev_instance) /* Fastpath interrupts */ for (j = 0; j < 64; j++) { if ((0x2ULL << j) & status) { - hwfn->simd_proto_handler[j].func( - hwfn->simd_proto_handler[j].token); + struct qed_simd_fp_handler *p_handler = + &hwfn->simd_proto_handler[j]; + + if (p_handler->func) + p_handler->func(p_handler->token); + else + DP_NOTICE(hwfn, + "Not calling fastpath handler as it is NULL [handler #%d, status 0x%llx]\n", + j, status); + status &= ~(0x2ULL << j); rc = IRQ_HANDLED; } diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig index cb5b0f58c395..edf20361ea5f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/Kconfig +++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig @@ -111,7 +111,7 @@ config DWMAC_ROCKCHIP config DWMAC_SOCFPGA tristate "SOCFPGA dwmac support" default ARCH_SOCFPGA - depends on OF && (ARCH_SOCFPGA || COMPILE_TEST) + depends on OF && (ARCH_SOCFPGA || ARCH_STRATIX10 || COMPILE_TEST) select MFD_SYSCON help Support for ethernet controller on Altera SOCFPGA diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c index 6e359572b9f0..5b3b06a0a3bf 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c @@ -55,6 +55,7 @@ struct socfpga_dwmac { struct device *dev; struct regmap *sys_mgr_base_addr; struct reset_control *stmmac_rst; + struct reset_control *stmmac_ocp_rst; void __iomem *splitter_base; bool f2h_ptp_ref_clk; struct tse_pcs pcs; @@ -262,8 +263,8 @@ static int socfpga_dwmac_set_phy_mode(struct socfpga_dwmac *dwmac) val = SYSMGR_EMACGRP_CTRL_PHYSEL_ENUM_GMII_MII; /* Assert reset to the enet controller before changing the phy mode */ - if (dwmac->stmmac_rst) - reset_control_assert(dwmac->stmmac_rst); + reset_control_assert(dwmac->stmmac_ocp_rst); + reset_control_assert(dwmac->stmmac_rst); regmap_read(sys_mgr_base_addr, reg_offset, &ctrl); ctrl &= ~(SYSMGR_EMACGRP_CTRL_PHYSEL_MASK << reg_shift); @@ -288,8 +289,8 @@ static int socfpga_dwmac_set_phy_mode(struct socfpga_dwmac *dwmac) /* Deassert reset for the phy configuration to be sampled by * the enet controller, and operation to start in requested mode */ - if (dwmac->stmmac_rst) - reset_control_deassert(dwmac->stmmac_rst); + reset_control_deassert(dwmac->stmmac_ocp_rst); + reset_control_deassert(dwmac->stmmac_rst); if (phymode == PHY_INTERFACE_MODE_SGMII) { if (tse_pcs_init(dwmac->pcs.tse_pcs_base, &dwmac->pcs) != 0) { dev_err(dwmac->dev, "Unable to initialize TSE PCS"); @@ -324,6 +325,15 @@ static int socfpga_dwmac_probe(struct platform_device *pdev) goto err_remove_config_dt; } + dwmac->stmmac_ocp_rst = devm_reset_control_get_optional(dev, "stmmaceth-ocp"); + if (IS_ERR(dwmac->stmmac_ocp_rst)) { + ret = PTR_ERR(dwmac->stmmac_ocp_rst); + dev_err(dev, "error getting reset control of ocp %d\n", ret); + goto err_remove_config_dt; + } + + reset_control_deassert(dwmac->stmmac_ocp_rst); + ret = socfpga_dwmac_parse_data(dwmac, dev); if (ret) { dev_err(dev, "Unable to parse OF data\n"); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index e79b0d7b388a..cba46b62a1cd 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -928,6 +928,7 @@ static void stmmac_check_pcs_mode(struct stmmac_priv *priv) static int stmmac_init_phy(struct net_device *dev) { struct stmmac_priv *priv = netdev_priv(dev); + u32 tx_cnt = priv->plat->tx_queues_to_use; struct phy_device *phydev; char phy_id_fmt[MII_BUS_ID_SIZE + 3]; char bus_id[MII_BUS_ID_SIZE]; @@ -969,6 +970,15 @@ static int stmmac_init_phy(struct net_device *dev) SUPPORTED_1000baseT_Full); /* + * Half-duplex mode not supported with multiqueue + * half-duplex can only works with single queue + */ + if (tx_cnt > 1) + phydev->supported &= ~(SUPPORTED_1000baseT_Half | + SUPPORTED_100baseT_Half | + SUPPORTED_10baseT_Half); + + /* * Broken HW is sometimes missing the pull-up resistor on the * MDIO line, which results in reads to non-existent devices returning * 0 rather than 0xffff. Catch this here and treat 0 as a non-existent diff --git a/drivers/net/ethernet/sun/sungem.c b/drivers/net/ethernet/sun/sungem.c index 7a16d40a72d1..b9221fc1674d 100644 --- a/drivers/net/ethernet/sun/sungem.c +++ b/drivers/net/ethernet/sun/sungem.c @@ -60,8 +60,7 @@ #include <linux/sungem_phy.h> #include "sungem.h" -/* Stripping FCS is causing problems, disabled for now */ -#undef STRIP_FCS +#define STRIP_FCS #define DEFAULT_MSG (NETIF_MSG_DRV | \ NETIF_MSG_PROBE | \ @@ -435,7 +434,7 @@ static int gem_rxmac_reset(struct gem *gp) writel(desc_dma & 0xffffffff, gp->regs + RXDMA_DBLOW); writel(RX_RING_SIZE - 4, gp->regs + RXDMA_KICK); val = (RXDMA_CFG_BASE | (RX_OFFSET << 10) | - ((14 / 2) << 13) | RXDMA_CFG_FTHRESH_128); + (ETH_HLEN << 13) | RXDMA_CFG_FTHRESH_128); writel(val, gp->regs + RXDMA_CFG); if (readl(gp->regs + GREG_BIFCFG) & GREG_BIFCFG_M66EN) writel(((5 & RXDMA_BLANK_IPKTS) | @@ -760,7 +759,6 @@ static int gem_rx(struct gem *gp, int work_to_do) struct net_device *dev = gp->dev; int entry, drops, work_done = 0; u32 done; - __sum16 csum; if (netif_msg_rx_status(gp)) printk(KERN_DEBUG "%s: rx interrupt, done: %d, rx_new: %d\n", @@ -855,9 +853,13 @@ static int gem_rx(struct gem *gp, int work_to_do) skb = copy_skb; } - csum = (__force __sum16)htons((status & RXDCTRL_TCPCSUM) ^ 0xffff); - skb->csum = csum_unfold(csum); - skb->ip_summed = CHECKSUM_COMPLETE; + if (likely(dev->features & NETIF_F_RXCSUM)) { + __sum16 csum; + + csum = (__force __sum16)htons((status & RXDCTRL_TCPCSUM) ^ 0xffff); + skb->csum = csum_unfold(csum); + skb->ip_summed = CHECKSUM_COMPLETE; + } skb->protocol = eth_type_trans(skb, gp->dev); napi_gro_receive(&gp->napi, skb); @@ -1761,7 +1763,7 @@ static void gem_init_dma(struct gem *gp) writel(0, gp->regs + TXDMA_KICK); val = (RXDMA_CFG_BASE | (RX_OFFSET << 10) | - ((14 / 2) << 13) | RXDMA_CFG_FTHRESH_128); + (ETH_HLEN << 13) | RXDMA_CFG_FTHRESH_128); writel(val, gp->regs + RXDMA_CFG); writel(desc_dma >> 32, gp->regs + RXDMA_DBHI); @@ -2985,8 +2987,8 @@ static int gem_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) pci_set_drvdata(pdev, dev); /* We can do scatter/gather and HW checksum */ - dev->hw_features = NETIF_F_SG | NETIF_F_HW_CSUM; - dev->features |= dev->hw_features | NETIF_F_RXCSUM; + dev->hw_features = NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_RXCSUM; + dev->features = dev->hw_features; if (pci_using_dac) dev->features |= NETIF_F_HIGHDMA; diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c index 06d7c9e4dcda..a1a6445b5a7e 100644 --- a/drivers/net/ethernet/ti/davinci_emac.c +++ b/drivers/net/ethernet/ti/davinci_emac.c @@ -1385,6 +1385,11 @@ static int emac_devioctl(struct net_device *ndev, struct ifreq *ifrq, int cmd) return -EOPNOTSUPP; } +static int match_first_device(struct device *dev, void *data) +{ + return !strncmp(dev_name(dev), "davinci_mdio", 12); +} + /** * emac_dev_open - EMAC device open * @ndev: The DaVinci EMAC network adapter @@ -1484,8 +1489,14 @@ static int emac_dev_open(struct net_device *ndev) /* use the first phy on the bus if pdata did not give us a phy id */ if (!phydev && !priv->phy_id) { - phy = bus_find_device_by_name(&mdio_bus_type, NULL, - "davinci_mdio"); + /* NOTE: we can't use bus_find_device_by_name() here because + * the device name is not guaranteed to be 'davinci_mdio'. On + * some systems it can be 'davinci_mdio.0' so we need to use + * strncmp() against the first part of the string to correctly + * match it. + */ + phy = bus_find_device(&mdio_bus_type, NULL, NULL, + match_first_device); if (phy) { priv->phy_id = dev_name(phy); if (!priv->phy_id || !*priv->phy_id) diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c index f347fd9c5b28..777fa59f5e0c 100644 --- a/drivers/net/hamradio/bpqether.c +++ b/drivers/net/hamradio/bpqether.c @@ -89,10 +89,6 @@ static const char banner[] __initconst = KERN_INFO \ "AX.25: bpqether driver version 004\n"; -static char bcast_addr[6]={0xFF,0xFF,0xFF,0xFF,0xFF,0xFF}; - -static char bpq_eth_addr[6]; - static int bpq_rcv(struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *); static int bpq_device_event(struct notifier_block *, unsigned long, void *); @@ -501,8 +497,8 @@ static int bpq_new_device(struct net_device *edev) bpq->ethdev = edev; bpq->axdev = ndev; - memcpy(bpq->dest_addr, bcast_addr, sizeof(bpq_eth_addr)); - memcpy(bpq->acpt_addr, bcast_addr, sizeof(bpq_eth_addr)); + eth_broadcast_addr(bpq->dest_addr); + eth_broadcast_addr(bpq->acpt_addr); err = register_netdevice(ndev); if (err) diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 4377c26f714d..d02f0a7c534e 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -693,6 +693,7 @@ void ipvlan_link_setup(struct net_device *dev) { ether_setup(dev); + dev->max_mtu = ETH_MAX_MTU; dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING); dev->priv_flags |= IFF_UNICAST_FLT | IFF_NO_QUEUE; dev->netdev_ops = &ipvlan_netdev_ops; diff --git a/drivers/net/net_failover.c b/drivers/net/net_failover.c index 83f7420ddea5..4f390fa557e4 100644 --- a/drivers/net/net_failover.c +++ b/drivers/net/net_failover.c @@ -527,7 +527,7 @@ static int net_failover_slave_register(struct net_device *slave_dev, netif_addr_lock_bh(failover_dev); dev_uc_sync_multiple(slave_dev, failover_dev); - dev_uc_sync_multiple(slave_dev, failover_dev); + dev_mc_sync_multiple(slave_dev, failover_dev); netif_addr_unlock_bh(failover_dev); err = vlan_vids_add_by_dev(slave_dev, failover_dev); diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index b0e8b9613054..1eaec648bd1f 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -967,8 +967,7 @@ void cdc_ncm_unbind(struct usbnet *dev, struct usb_interface *intf) atomic_set(&ctx->stop, 1); - if (hrtimer_active(&ctx->tx_timer)) - hrtimer_cancel(&ctx->tx_timer); + hrtimer_cancel(&ctx->tx_timer); tasklet_kill(&ctx->bh); 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/opp/core.c b/drivers/opp/core.c index ab2f3fead6b1..31ff03dbeb83 100644 --- a/drivers/opp/core.c +++ b/drivers/opp/core.c @@ -598,7 +598,7 @@ static int _generic_set_opp_regulator(const struct opp_table *opp_table, } /* Scaling up? Scale voltage before frequency */ - if (freq > old_freq) { + if (freq >= old_freq) { ret = _set_opp_voltage(dev, reg, new_supply); if (ret) goto restore_voltage; diff --git a/drivers/pinctrl/actions/pinctrl-owl.c b/drivers/pinctrl/actions/pinctrl-owl.c index 76243caa08c6..b5c880b50bb3 100644 --- a/drivers/pinctrl/actions/pinctrl-owl.c +++ b/drivers/pinctrl/actions/pinctrl-owl.c @@ -333,7 +333,7 @@ static int owl_pin_config_set(struct pinctrl_dev *pctrldev, unsigned long flags; unsigned int param; u32 reg, bit, width, arg; - int ret, i; + int ret = 0, i; info = &pctrl->soc->padinfo[pin]; diff --git a/drivers/pinctrl/devicetree.c b/drivers/pinctrl/devicetree.c index b601039d6c69..c4aa411f5935 100644 --- a/drivers/pinctrl/devicetree.c +++ b/drivers/pinctrl/devicetree.c @@ -101,10 +101,11 @@ struct pinctrl_dev *of_pinctrl_get(struct device_node *np) } static int dt_to_map_one_config(struct pinctrl *p, - struct pinctrl_dev *pctldev, + struct pinctrl_dev *hog_pctldev, const char *statename, struct device_node *np_config) { + struct pinctrl_dev *pctldev = NULL; struct device_node *np_pctldev; const struct pinctrl_ops *ops; int ret; @@ -123,8 +124,10 @@ static int dt_to_map_one_config(struct pinctrl *p, return -EPROBE_DEFER; } /* If we're creating a hog we can use the passed pctldev */ - if (pctldev && (np_pctldev == p->dev->of_node)) + if (hog_pctldev && (np_pctldev == p->dev->of_node)) { + pctldev = hog_pctldev; break; + } pctldev = get_pinctrl_dev_from_of_node(np_pctldev); if (pctldev) break; diff --git a/drivers/pinctrl/mediatek/pinctrl-mt7622.c b/drivers/pinctrl/mediatek/pinctrl-mt7622.c index ad6da1184c9f..e3f1ab2290fc 100644 --- a/drivers/pinctrl/mediatek/pinctrl-mt7622.c +++ b/drivers/pinctrl/mediatek/pinctrl-mt7622.c @@ -1459,6 +1459,9 @@ static int mtk_gpio_to_irq(struct gpio_chip *chip, unsigned int offset) struct mtk_pinctrl *hw = gpiochip_get_data(chip); unsigned long eint_n; + if (!hw->eint) + return -ENOTSUPP; + eint_n = offset; return mtk_eint_find_irq(hw->eint, eint_n); @@ -1471,7 +1474,8 @@ static int mtk_gpio_set_config(struct gpio_chip *chip, unsigned int offset, unsigned long eint_n; u32 debounce; - if (pinconf_to_config_param(config) != PIN_CONFIG_INPUT_DEBOUNCE) + if (!hw->eint || + pinconf_to_config_param(config) != PIN_CONFIG_INPUT_DEBOUNCE) return -ENOTSUPP; debounce = pinconf_to_config_argument(config); diff --git a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c index b3799695d8db..16ff56f93501 100644 --- a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c +++ b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c @@ -1000,11 +1000,6 @@ static int mtk_eint_init(struct mtk_pinctrl *pctl, struct platform_device *pdev) return -ENOMEM; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!res) { - dev_err(&pdev->dev, "Unable to get eint resource\n"); - return -ENODEV; - } - pctl->eint->base = devm_ioremap_resource(&pdev->dev, res); if (IS_ERR(pctl->eint->base)) return PTR_ERR(pctl->eint->base); diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c index b3153c095199..e5647dac0818 100644 --- a/drivers/pinctrl/pinctrl-single.c +++ b/drivers/pinctrl/pinctrl-single.c @@ -1590,8 +1590,11 @@ static int pcs_save_context(struct pcs_device *pcs) mux_bytes = pcs->width / BITS_PER_BYTE; - if (!pcs->saved_vals) + if (!pcs->saved_vals) { pcs->saved_vals = devm_kzalloc(pcs->dev, pcs->size, GFP_ATOMIC); + if (!pcs->saved_vals) + return -ENOMEM; + } switch (pcs->width) { case 64: @@ -1651,8 +1654,13 @@ static int pinctrl_single_suspend(struct platform_device *pdev, if (!pcs) return -EINVAL; - if (pcs->flags & PCS_CONTEXT_LOSS_OFF) - pcs_save_context(pcs); + if (pcs->flags & PCS_CONTEXT_LOSS_OFF) { + int ret; + + ret = pcs_save_context(pcs); + if (ret < 0) + return ret; + } return pinctrl_force_sleep(pcs->pctl); } diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c index 767c485af59b..547dbdac9d54 100644 --- a/drivers/ptp/ptp_chardev.c +++ b/drivers/ptp/ptp_chardev.c @@ -221,7 +221,7 @@ long ptp_ioctl(struct posix_clock *pc, unsigned int cmd, unsigned long arg) } pct = &sysoff->ts[0]; for (i = 0; i < sysoff->n_samples; i++) { - getnstimeofday64(&ts); + ktime_get_real_ts64(&ts); pct->sec = ts.tv_sec; pct->nsec = ts.tv_nsec; pct++; @@ -230,7 +230,7 @@ long ptp_ioctl(struct posix_clock *pc, unsigned int cmd, unsigned long arg) pct->nsec = ts.tv_nsec; pct++; } - getnstimeofday64(&ts); + ktime_get_real_ts64(&ts); pct->sec = ts.tv_sec; pct->nsec = ts.tv_nsec; if (copy_to_user((void __user *)arg, sysoff, sizeof(*sysoff))) diff --git a/drivers/ptp/ptp_qoriq.c b/drivers/ptp/ptp_qoriq.c index 1468a1642b49..e8652c148c52 100644 --- a/drivers/ptp/ptp_qoriq.c +++ b/drivers/ptp/ptp_qoriq.c @@ -374,7 +374,7 @@ static int qoriq_ptp_probe(struct platform_device *dev) pr_err("ioremap ptp registers failed\n"); goto no_ioremap; } - getnstimeofday64(&now); + ktime_get_real_ts64(&now); ptp_qoriq_settime(&qoriq_ptp->caps, &now); tmr_ctrl = diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index 73cce3ecb97f..d3a38c421503 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -1222,80 +1222,37 @@ static void dasd_hosts_init(struct dentry *base_dentry, device->hosts_dentry = pde; } -/* - * Allocate memory for a channel program with 'cplength' channel - * command words and 'datasize' additional space. There are two - * variantes: 1) dasd_kmalloc_request uses kmalloc to get the needed - * memory and 2) dasd_smalloc_request uses the static ccw memory - * that gets allocated for each device. - */ -struct dasd_ccw_req *dasd_kmalloc_request(int magic, int cplength, - int datasize, - struct dasd_device *device) -{ - struct dasd_ccw_req *cqr; - - /* Sanity checks */ - BUG_ON(datasize > PAGE_SIZE || - (cplength*sizeof(struct ccw1)) > PAGE_SIZE); - - cqr = kzalloc(sizeof(struct dasd_ccw_req), GFP_ATOMIC); - if (cqr == NULL) - return ERR_PTR(-ENOMEM); - cqr->cpaddr = NULL; - if (cplength > 0) { - cqr->cpaddr = kcalloc(cplength, sizeof(struct ccw1), - GFP_ATOMIC | GFP_DMA); - if (cqr->cpaddr == NULL) { - kfree(cqr); - return ERR_PTR(-ENOMEM); - } - } - cqr->data = NULL; - if (datasize > 0) { - cqr->data = kzalloc(datasize, GFP_ATOMIC | GFP_DMA); - if (cqr->data == NULL) { - kfree(cqr->cpaddr); - kfree(cqr); - return ERR_PTR(-ENOMEM); - } - } - cqr->magic = magic; - set_bit(DASD_CQR_FLAGS_USE_ERP, &cqr->flags); - dasd_get_device(device); - return cqr; -} -EXPORT_SYMBOL(dasd_kmalloc_request); - -struct dasd_ccw_req *dasd_smalloc_request(int magic, int cplength, - int datasize, - struct dasd_device *device) +struct dasd_ccw_req *dasd_smalloc_request(int magic, int cplength, int datasize, + struct dasd_device *device, + struct dasd_ccw_req *cqr) { unsigned long flags; - struct dasd_ccw_req *cqr; - char *data; - int size; + char *data, *chunk; + int size = 0; - size = (sizeof(struct dasd_ccw_req) + 7L) & -8L; if (cplength > 0) size += cplength * sizeof(struct ccw1); if (datasize > 0) size += datasize; + if (!cqr) + size += (sizeof(*cqr) + 7L) & -8L; + spin_lock_irqsave(&device->mem_lock, flags); - cqr = (struct dasd_ccw_req *) - dasd_alloc_chunk(&device->ccw_chunks, size); + data = chunk = dasd_alloc_chunk(&device->ccw_chunks, size); spin_unlock_irqrestore(&device->mem_lock, flags); - if (cqr == NULL) + if (!chunk) return ERR_PTR(-ENOMEM); - memset(cqr, 0, sizeof(struct dasd_ccw_req)); - data = (char *) cqr + ((sizeof(struct dasd_ccw_req) + 7L) & -8L); - cqr->cpaddr = NULL; + if (!cqr) { + cqr = (void *) data; + data += (sizeof(*cqr) + 7L) & -8L; + } + memset(cqr, 0, sizeof(*cqr)); + cqr->mem_chunk = chunk; if (cplength > 0) { - cqr->cpaddr = (struct ccw1 *) data; - data += cplength*sizeof(struct ccw1); - memset(cqr->cpaddr, 0, cplength*sizeof(struct ccw1)); + cqr->cpaddr = data; + data += cplength * sizeof(struct ccw1); + memset(cqr->cpaddr, 0, cplength * sizeof(struct ccw1)); } - cqr->data = NULL; if (datasize > 0) { cqr->data = data; memset(cqr->data, 0, datasize); @@ -1307,33 +1264,12 @@ struct dasd_ccw_req *dasd_smalloc_request(int magic, int cplength, } EXPORT_SYMBOL(dasd_smalloc_request); -/* - * Free memory of a channel program. This function needs to free all the - * idal lists that might have been created by dasd_set_cda and the - * struct dasd_ccw_req itself. - */ -void dasd_kfree_request(struct dasd_ccw_req *cqr, struct dasd_device *device) -{ - struct ccw1 *ccw; - - /* Clear any idals used for the request. */ - ccw = cqr->cpaddr; - do { - clear_normalized_cda(ccw); - } while (ccw++->flags & (CCW_FLAG_CC | CCW_FLAG_DC)); - kfree(cqr->cpaddr); - kfree(cqr->data); - kfree(cqr); - dasd_put_device(device); -} -EXPORT_SYMBOL(dasd_kfree_request); - void dasd_sfree_request(struct dasd_ccw_req *cqr, struct dasd_device *device) { unsigned long flags; spin_lock_irqsave(&device->mem_lock, flags); - dasd_free_chunk(&device->ccw_chunks, cqr); + dasd_free_chunk(&device->ccw_chunks, cqr->mem_chunk); spin_unlock_irqrestore(&device->mem_lock, flags); dasd_put_device(device); } @@ -1885,6 +1821,33 @@ static void __dasd_device_process_ccw_queue(struct dasd_device *device, } } +static void __dasd_process_cqr(struct dasd_device *device, + struct dasd_ccw_req *cqr) +{ + char errorstring[ERRORLENGTH]; + + switch (cqr->status) { + case DASD_CQR_SUCCESS: + cqr->status = DASD_CQR_DONE; + break; + case DASD_CQR_ERROR: + cqr->status = DASD_CQR_NEED_ERP; + break; + case DASD_CQR_CLEARED: + cqr->status = DASD_CQR_TERMINATED; + break; + default: + /* internal error 12 - wrong cqr status*/ + snprintf(errorstring, ERRORLENGTH, "12 %p %x02", cqr, cqr->status); + dev_err(&device->cdev->dev, + "An error occurred in the DASD device driver, " + "reason=%s\n", errorstring); + BUG(); + } + if (cqr->callback) + cqr->callback(cqr, cqr->callback_data); +} + /* * the cqrs from the final queue are returned to the upper layer * by setting a dasd_block state and calling the callback function @@ -1895,40 +1858,18 @@ static void __dasd_device_process_final_queue(struct dasd_device *device, struct list_head *l, *n; struct dasd_ccw_req *cqr; struct dasd_block *block; - void (*callback)(struct dasd_ccw_req *, void *data); - void *callback_data; - char errorstring[ERRORLENGTH]; list_for_each_safe(l, n, final_queue) { cqr = list_entry(l, struct dasd_ccw_req, devlist); list_del_init(&cqr->devlist); block = cqr->block; - callback = cqr->callback; - callback_data = cqr->callback_data; - if (block) + if (!block) { + __dasd_process_cqr(device, cqr); + } else { spin_lock_bh(&block->queue_lock); - switch (cqr->status) { - case DASD_CQR_SUCCESS: - cqr->status = DASD_CQR_DONE; - break; - case DASD_CQR_ERROR: - cqr->status = DASD_CQR_NEED_ERP; - break; - case DASD_CQR_CLEARED: - cqr->status = DASD_CQR_TERMINATED; - break; - default: - /* internal error 12 - wrong cqr status*/ - snprintf(errorstring, ERRORLENGTH, "12 %p %x02", cqr, cqr->status); - dev_err(&device->cdev->dev, - "An error occurred in the DASD device driver, " - "reason=%s\n", errorstring); - BUG(); - } - if (cqr->callback != NULL) - (callback)(cqr, callback_data); - if (block) + __dasd_process_cqr(device, cqr); spin_unlock_bh(&block->queue_lock); + } } } @@ -3041,7 +2982,6 @@ static blk_status_t do_dasd_request(struct blk_mq_hw_ctx *hctx, cqr->callback_data = req; cqr->status = DASD_CQR_FILLED; cqr->dq = dq; - *((struct dasd_ccw_req **) blk_mq_rq_to_pdu(req)) = cqr; blk_mq_start_request(req); spin_lock(&block->queue_lock); @@ -3072,7 +3012,7 @@ enum blk_eh_timer_return dasd_times_out(struct request *req, bool reserved) unsigned long flags; int rc = 0; - cqr = *((struct dasd_ccw_req **) blk_mq_rq_to_pdu(req)); + cqr = blk_mq_rq_to_pdu(req); if (!cqr) return BLK_EH_DONE; @@ -3174,7 +3114,7 @@ static int dasd_alloc_queue(struct dasd_block *block) int rc; block->tag_set.ops = &dasd_mq_ops; - block->tag_set.cmd_size = sizeof(struct dasd_ccw_req *); + block->tag_set.cmd_size = sizeof(struct dasd_ccw_req); block->tag_set.nr_hw_queues = DASD_NR_HW_QUEUES; block->tag_set.queue_depth = DASD_MAX_LCU_DEV * DASD_REQ_PER_DEV; block->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; @@ -4038,7 +3978,8 @@ static struct dasd_ccw_req *dasd_generic_build_rdc(struct dasd_device *device, struct ccw1 *ccw; unsigned long *idaw; - cqr = dasd_smalloc_request(magic, 1 /* RDC */, rdc_buffer_size, device); + cqr = dasd_smalloc_request(magic, 1 /* RDC */, rdc_buffer_size, device, + NULL); if (IS_ERR(cqr)) { /* internal error 13 - Allocating the RDC request failed*/ diff --git a/drivers/s390/block/dasd_alias.c b/drivers/s390/block/dasd_alias.c index 5e963fe0e38d..e36a114354fc 100644 --- a/drivers/s390/block/dasd_alias.c +++ b/drivers/s390/block/dasd_alias.c @@ -407,9 +407,9 @@ static int read_unit_address_configuration(struct dasd_device *device, int rc; unsigned long flags; - cqr = dasd_kmalloc_request(DASD_ECKD_MAGIC, 1 /* PSF */ + 1 /* RSSD */, + cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1 /* PSF */ + 1 /* RSSD */, (sizeof(struct dasd_psf_prssd_data)), - device); + device, NULL); if (IS_ERR(cqr)) return PTR_ERR(cqr); cqr->startdev = device; @@ -457,7 +457,7 @@ static int read_unit_address_configuration(struct dasd_device *device, lcu->flags |= NEED_UAC_UPDATE; spin_unlock_irqrestore(&lcu->lock, flags); } - dasd_kfree_request(cqr, cqr->memdev); + dasd_sfree_request(cqr, cqr->memdev); return rc; } diff --git a/drivers/s390/block/dasd_diag.c b/drivers/s390/block/dasd_diag.c index 131f1989f6f3..e1fe02477ea8 100644 --- a/drivers/s390/block/dasd_diag.c +++ b/drivers/s390/block/dasd_diag.c @@ -536,7 +536,8 @@ static struct dasd_ccw_req *dasd_diag_build_cp(struct dasd_device *memdev, /* Build the request */ datasize = sizeof(struct dasd_diag_req) + count*sizeof(struct dasd_diag_bio); - cqr = dasd_smalloc_request(DASD_DIAG_MAGIC, 0, datasize, memdev); + cqr = dasd_smalloc_request(DASD_DIAG_MAGIC, 0, datasize, memdev, + blk_mq_rq_to_pdu(req)); if (IS_ERR(cqr)) return cqr; diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index be208e7adcb4..bbf95b78ef5d 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -886,7 +886,7 @@ static int dasd_eckd_read_conf_lpm(struct dasd_device *device, } cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1 /* RCD */, 0, /* use rcd_buf as data ara */ - device); + device, NULL); if (IS_ERR(cqr)) { DBF_DEV_EVENT(DBF_WARNING, device, "%s", "Could not allocate RCD request"); @@ -1442,7 +1442,7 @@ static int dasd_eckd_read_features(struct dasd_device *device) cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1 /* PSF */ + 1 /* RSSD */, (sizeof(struct dasd_psf_prssd_data) + sizeof(struct dasd_rssd_features)), - device); + device, NULL); if (IS_ERR(cqr)) { DBF_EVENT_DEVID(DBF_WARNING, device->cdev, "%s", "Could not " "allocate initialization request"); @@ -1504,7 +1504,7 @@ static struct dasd_ccw_req *dasd_eckd_build_psf_ssc(struct dasd_device *device, cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1 /* PSF */ , sizeof(struct dasd_psf_ssc_data), - device); + device, NULL); if (IS_ERR(cqr)) { DBF_DEV_EVENT(DBF_WARNING, device, "%s", @@ -1815,7 +1815,8 @@ dasd_eckd_analysis_ccw(struct dasd_device *device) cplength = 8; datasize = sizeof(struct DE_eckd_data) + 2*sizeof(struct LO_eckd_data); - cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, cplength, datasize, device); + cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, cplength, datasize, device, + NULL); if (IS_ERR(cqr)) return cqr; ccw = cqr->cpaddr; @@ -2092,7 +2093,8 @@ dasd_eckd_build_check_tcw(struct dasd_device *base, struct format_data_t *fdata, */ itcw_size = itcw_calc_size(0, count, 0); - cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 0, itcw_size, startdev); + cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 0, itcw_size, startdev, + NULL); if (IS_ERR(cqr)) return cqr; @@ -2186,7 +2188,7 @@ dasd_eckd_build_check(struct dasd_device *base, struct format_data_t *fdata, cplength += count; cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, cplength, datasize, - startdev); + startdev, NULL); if (IS_ERR(cqr)) return cqr; @@ -2332,7 +2334,7 @@ dasd_eckd_build_format(struct dasd_device *base, } /* Allocate the format ccw request. */ fcp = dasd_smalloc_request(DASD_ECKD_MAGIC, cplength, - datasize, startdev); + datasize, startdev, NULL); if (IS_ERR(fcp)) return fcp; @@ -3103,7 +3105,7 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_cmd_single( } /* Allocate the ccw request. */ cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, cplength, datasize, - startdev); + startdev, blk_mq_rq_to_pdu(req)); if (IS_ERR(cqr)) return cqr; ccw = cqr->cpaddr; @@ -3262,7 +3264,7 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_cmd_track( /* Allocate the ccw request. */ cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, cplength, datasize, - startdev); + startdev, blk_mq_rq_to_pdu(req)); if (IS_ERR(cqr)) return cqr; ccw = cqr->cpaddr; @@ -3595,7 +3597,8 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_tpm_track( /* Allocate the ccw request. */ itcw_size = itcw_calc_size(0, ctidaw, 0); - cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 0, itcw_size, startdev); + cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 0, itcw_size, startdev, + blk_mq_rq_to_pdu(req)); if (IS_ERR(cqr)) return cqr; @@ -3862,7 +3865,7 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_raw(struct dasd_device *startdev, /* Allocate the ccw request. */ cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, cplength, - datasize, startdev); + datasize, startdev, blk_mq_rq_to_pdu(req)); if (IS_ERR(cqr)) return cqr; @@ -4102,7 +4105,7 @@ dasd_eckd_release(struct dasd_device *device) return -EACCES; useglobal = 0; - cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1, 32, device); + cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1, 32, device, NULL); if (IS_ERR(cqr)) { mutex_lock(&dasd_reserve_mutex); useglobal = 1; @@ -4157,7 +4160,7 @@ dasd_eckd_reserve(struct dasd_device *device) return -EACCES; useglobal = 0; - cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1, 32, device); + cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1, 32, device, NULL); if (IS_ERR(cqr)) { mutex_lock(&dasd_reserve_mutex); useglobal = 1; @@ -4211,7 +4214,7 @@ dasd_eckd_steal_lock(struct dasd_device *device) return -EACCES; useglobal = 0; - cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1, 32, device); + cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1, 32, device, NULL); if (IS_ERR(cqr)) { mutex_lock(&dasd_reserve_mutex); useglobal = 1; @@ -4271,7 +4274,8 @@ static int dasd_eckd_snid(struct dasd_device *device, useglobal = 0; cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1, - sizeof(struct dasd_snid_data), device); + sizeof(struct dasd_snid_data), device, + NULL); if (IS_ERR(cqr)) { mutex_lock(&dasd_reserve_mutex); useglobal = 1; @@ -4331,7 +4335,7 @@ dasd_eckd_performance(struct dasd_device *device, void __user *argp) cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1 /* PSF */ + 1 /* RSSD */, (sizeof(struct dasd_psf_prssd_data) + sizeof(struct dasd_rssd_perf_stats_t)), - device); + device, NULL); if (IS_ERR(cqr)) { DBF_DEV_EVENT(DBF_WARNING, device, "%s", "Could not allocate initialization request"); @@ -4477,7 +4481,7 @@ static int dasd_symm_io(struct dasd_device *device, void __user *argp) psf1 = psf_data[1]; /* setup CCWs for PSF + RSSD */ - cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 2 , 0, device); + cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 2, 0, device, NULL); if (IS_ERR(cqr)) { DBF_DEV_EVENT(DBF_WARNING, device, "%s", "Could not allocate initialization request"); @@ -5037,7 +5041,7 @@ static int dasd_eckd_read_message_buffer(struct dasd_device *device, cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1 /* PSF */ + 1 /* RSSD */, (sizeof(struct dasd_psf_prssd_data) + sizeof(struct dasd_rssd_messages)), - device); + device, NULL); if (IS_ERR(cqr)) { DBF_EVENT_DEVID(DBF_WARNING, device->cdev, "%s", "Could not allocate read message buffer request"); @@ -5126,7 +5130,7 @@ static int dasd_eckd_query_host_access(struct dasd_device *device, cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1 /* PSF */ + 1 /* RSSD */, sizeof(struct dasd_psf_prssd_data) + 1, - device); + device, NULL); if (IS_ERR(cqr)) { DBF_EVENT_DEVID(DBF_WARNING, device->cdev, "%s", "Could not allocate read message buffer request"); @@ -5284,8 +5288,8 @@ dasd_eckd_psf_cuir_response(struct dasd_device *device, int response, int rc; cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1 /* PSF */ , - sizeof(struct dasd_psf_cuir_response), - device); + sizeof(struct dasd_psf_cuir_response), + device, NULL); if (IS_ERR(cqr)) { DBF_DEV_EVENT(DBF_WARNING, device, "%s", diff --git a/drivers/s390/block/dasd_eer.c b/drivers/s390/block/dasd_eer.c index 0af8c5295b65..6ef8714dc693 100644 --- a/drivers/s390/block/dasd_eer.c +++ b/drivers/s390/block/dasd_eer.c @@ -447,7 +447,7 @@ static void dasd_eer_snss_cb(struct dasd_ccw_req *cqr, void *data) * is a new ccw in device->eer_cqr. Free the "old" * snss request now. */ - dasd_kfree_request(cqr, device); + dasd_sfree_request(cqr, device); } /* @@ -472,8 +472,8 @@ int dasd_eer_enable(struct dasd_device *device) if (rc) goto out; - cqr = dasd_kmalloc_request(DASD_ECKD_MAGIC, 1 /* SNSS */, - SNSS_DATA_SIZE, device); + cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1 /* SNSS */, + SNSS_DATA_SIZE, device, NULL); if (IS_ERR(cqr)) { rc = -ENOMEM; cqr = NULL; @@ -505,7 +505,7 @@ out: spin_unlock_irqrestore(get_ccwdev_lock(device->cdev), flags); if (cqr) - dasd_kfree_request(cqr, device); + dasd_sfree_request(cqr, device); return rc; } @@ -528,7 +528,7 @@ void dasd_eer_disable(struct dasd_device *device) in_use = test_and_clear_bit(DASD_FLAG_EER_IN_USE, &device->flags); spin_unlock_irqrestore(get_ccwdev_lock(device->cdev), flags); if (cqr && !in_use) - dasd_kfree_request(cqr, device); + dasd_sfree_request(cqr, device); } /* diff --git a/drivers/s390/block/dasd_fba.c b/drivers/s390/block/dasd_fba.c index a6b132f7e869..56007a3e7f11 100644 --- a/drivers/s390/block/dasd_fba.c +++ b/drivers/s390/block/dasd_fba.c @@ -356,7 +356,8 @@ static struct dasd_ccw_req *dasd_fba_build_cp_discard( datasize = sizeof(struct DE_fba_data) + nr_ccws * (sizeof(struct LO_fba_data) + sizeof(struct ccw1)); - cqr = dasd_smalloc_request(DASD_FBA_MAGIC, cplength, datasize, memdev); + cqr = dasd_smalloc_request(DASD_FBA_MAGIC, cplength, datasize, memdev, + blk_mq_rq_to_pdu(req)); if (IS_ERR(cqr)) return cqr; @@ -490,7 +491,8 @@ static struct dasd_ccw_req *dasd_fba_build_cp_regular( datasize += (count - 1)*sizeof(struct LO_fba_data); } /* Allocate the ccw request. */ - cqr = dasd_smalloc_request(DASD_FBA_MAGIC, cplength, datasize, memdev); + cqr = dasd_smalloc_request(DASD_FBA_MAGIC, cplength, datasize, memdev, + blk_mq_rq_to_pdu(req)); if (IS_ERR(cqr)) return cqr; ccw = cqr->cpaddr; diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h index 96709b1a7bf8..976b6bd4fb05 100644 --- a/drivers/s390/block/dasd_int.h +++ b/drivers/s390/block/dasd_int.h @@ -158,40 +158,33 @@ do { \ struct dasd_ccw_req { unsigned int magic; /* Eye catcher */ + int intrc; /* internal error, e.g. from start_IO */ struct list_head devlist; /* for dasd_device request queue */ struct list_head blocklist; /* for dasd_block request queue */ - - /* Where to execute what... */ struct dasd_block *block; /* the originating block device */ struct dasd_device *memdev; /* the device used to allocate this */ struct dasd_device *startdev; /* device the request is started on */ struct dasd_device *basedev; /* base device if no block->base */ void *cpaddr; /* address of ccw or tcw */ + short retries; /* A retry counter */ unsigned char cpmode; /* 0 = cmd mode, 1 = itcw */ char status; /* status of this request */ - short retries; /* A retry counter */ + char lpm; /* logical path mask */ unsigned long flags; /* flags of this request */ struct dasd_queue *dq; - - /* ... and how */ unsigned long starttime; /* jiffies time of request start */ unsigned long expires; /* expiration period in jiffies */ - char lpm; /* logical path mask */ void *data; /* pointer to data area */ - - /* these are important for recovering erroneous requests */ - int intrc; /* internal error, e.g. from start_IO */ struct irb irb; /* device status in case of an error */ struct dasd_ccw_req *refers; /* ERP-chain queueing. */ void *function; /* originating ERP action */ + void *mem_chunk; - /* these are for statistics only */ unsigned long buildclk; /* TOD-clock of request generation */ unsigned long startclk; /* TOD-clock of request start */ unsigned long stopclk; /* TOD-clock of request interrupt */ unsigned long endclk; /* TOD-clock of request termination */ - /* Callback that is called after reaching final status. */ void (*callback)(struct dasd_ccw_req *, void *data); void *callback_data; }; @@ -714,19 +707,10 @@ extern const struct block_device_operations dasd_device_operations; extern struct kmem_cache *dasd_page_cache; struct dasd_ccw_req * -dasd_kmalloc_request(int , int, int, struct dasd_device *); -struct dasd_ccw_req * -dasd_smalloc_request(int , int, int, struct dasd_device *); -void dasd_kfree_request(struct dasd_ccw_req *, struct dasd_device *); +dasd_smalloc_request(int, int, int, struct dasd_device *, struct dasd_ccw_req *); void dasd_sfree_request(struct dasd_ccw_req *, struct dasd_device *); void dasd_wakeup_cb(struct dasd_ccw_req *, void *); -static inline int -dasd_kmalloc_set_cda(struct ccw1 *ccw, void *cda, struct dasd_device *device) -{ - return set_normalized_cda(ccw, cda); -} - struct dasd_device *dasd_alloc_device(void); void dasd_free_device(struct dasd_device *); diff --git a/drivers/s390/cio/Makefile b/drivers/s390/cio/Makefile index a070ef0efe65..f230516abb96 100644 --- a/drivers/s390/cio/Makefile +++ b/drivers/s390/cio/Makefile @@ -5,6 +5,7 @@ # The following is required for define_trace.h to find ./trace.h CFLAGS_trace.o := -I$(src) +CFLAGS_vfio_ccw_fsm.o := -I$(src) obj-y += airq.o blacklist.o chsc.o cio.o css.o chp.o idset.o isc.o \ fcx.o itcw.o crw.o ccwreq.o trace.o ioasm.o diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c index dce92b2a895d..dbe7c7ac9ac8 100644 --- a/drivers/s390/cio/vfio_ccw_cp.c +++ b/drivers/s390/cio/vfio_ccw_cp.c @@ -23,9 +23,13 @@ #define CCWCHAIN_LEN_MAX 256 struct pfn_array { + /* Starting guest physical I/O address. */ unsigned long pa_iova; + /* Array that stores PFNs of the pages need to pin. */ unsigned long *pa_iova_pfn; + /* Array that receives PFNs of the pages pinned. */ unsigned long *pa_pfn; + /* Number of pages pinned from @pa_iova. */ int pa_nr; }; @@ -46,70 +50,33 @@ struct ccwchain { }; /* - * pfn_array_pin() - pin user pages in memory + * pfn_array_alloc_pin() - alloc memory for PFNs, then pin user pages in memory * @pa: pfn_array on which to perform the operation * @mdev: the mediated device to perform pin/unpin operations + * @iova: target guest physical address + * @len: number of bytes that should be pinned from @iova * - * Attempt to pin user pages in memory. + * Attempt to allocate memory for PFNs, and pin user pages in memory. * * Usage of pfn_array: - * @pa->pa_iova starting guest physical I/O address. Assigned by caller. - * @pa->pa_iova_pfn array that stores PFNs of the pages need to pin. Allocated - * by caller. - * @pa->pa_pfn array that receives PFNs of the pages pinned. Allocated by - * caller. - * @pa->pa_nr number of pages from @pa->pa_iova to pin. Assigned by - * caller. - * number of pages pinned. Assigned by callee. + * We expect (pa_nr == 0) and (pa_iova_pfn == NULL), any field in + * this structure will be filled in by this function. * * Returns: * Number of pages pinned on success. - * If @pa->pa_nr is 0 or negative, returns 0. + * If @pa->pa_nr is not 0, or @pa->pa_iova_pfn is not NULL initially, + * returns -EINVAL. * If no pages were pinned, returns -errno. */ -static int pfn_array_pin(struct pfn_array *pa, struct device *mdev) -{ - int i, ret; - - if (pa->pa_nr <= 0) { - pa->pa_nr = 0; - return 0; - } - - pa->pa_iova_pfn[0] = pa->pa_iova >> PAGE_SHIFT; - for (i = 1; i < pa->pa_nr; i++) - pa->pa_iova_pfn[i] = pa->pa_iova_pfn[i - 1] + 1; - - ret = vfio_pin_pages(mdev, pa->pa_iova_pfn, pa->pa_nr, - IOMMU_READ | IOMMU_WRITE, pa->pa_pfn); - - if (ret > 0 && ret != pa->pa_nr) { - vfio_unpin_pages(mdev, pa->pa_iova_pfn, ret); - pa->pa_nr = 0; - return 0; - } - - return ret; -} - -/* Unpin the pages before releasing the memory. */ -static void pfn_array_unpin_free(struct pfn_array *pa, struct device *mdev) -{ - vfio_unpin_pages(mdev, pa->pa_iova_pfn, pa->pa_nr); - pa->pa_nr = 0; - kfree(pa->pa_iova_pfn); -} - -/* Alloc memory for PFNs, then pin pages with them. */ static int pfn_array_alloc_pin(struct pfn_array *pa, struct device *mdev, u64 iova, unsigned int len) { - int ret = 0; + int i, ret = 0; if (!len) return 0; - if (pa->pa_nr) + if (pa->pa_nr || pa->pa_iova_pfn) return -EINVAL; pa->pa_iova = iova; @@ -126,18 +93,39 @@ static int pfn_array_alloc_pin(struct pfn_array *pa, struct device *mdev, return -ENOMEM; pa->pa_pfn = pa->pa_iova_pfn + pa->pa_nr; - ret = pfn_array_pin(pa, mdev); + pa->pa_iova_pfn[0] = pa->pa_iova >> PAGE_SHIFT; + for (i = 1; i < pa->pa_nr; i++) + pa->pa_iova_pfn[i] = pa->pa_iova_pfn[i - 1] + 1; - if (ret > 0) - return ret; - else if (!ret) + ret = vfio_pin_pages(mdev, pa->pa_iova_pfn, pa->pa_nr, + IOMMU_READ | IOMMU_WRITE, pa->pa_pfn); + + if (ret < 0) { + goto err_out; + } else if (ret > 0 && ret != pa->pa_nr) { + vfio_unpin_pages(mdev, pa->pa_iova_pfn, ret); ret = -EINVAL; + goto err_out; + } + return ret; + +err_out: + pa->pa_nr = 0; kfree(pa->pa_iova_pfn); + pa->pa_iova_pfn = NULL; return ret; } +/* Unpin the pages before releasing the memory. */ +static void pfn_array_unpin_free(struct pfn_array *pa, struct device *mdev) +{ + vfio_unpin_pages(mdev, pa->pa_iova_pfn, pa->pa_nr); + pa->pa_nr = 0; + kfree(pa->pa_iova_pfn); +} + static int pfn_array_table_init(struct pfn_array_table *pat, int nr) { pat->pat_pa = kcalloc(nr, sizeof(*pat->pat_pa), GFP_KERNEL); @@ -365,6 +353,9 @@ static void cp_unpin_free(struct channel_program *cp) * This is the chain length not considering any TICs. * You need to do a new round for each TIC target. * + * The program is also validated for absence of not yet supported + * indirect data addressing scenarios. + * * Returns: the length of the ccw chain or -errno. */ static int ccwchain_calc_length(u64 iova, struct channel_program *cp) @@ -391,6 +382,14 @@ static int ccwchain_calc_length(u64 iova, struct channel_program *cp) do { cnt++; + /* + * As we don't want to fail direct addressing even if the + * orb specified one of the unsupported formats, we defer + * checking for IDAWs in unsupported formats to here. + */ + if ((!cp->orb.cmd.c64 || cp->orb.cmd.i2k) && ccw_is_idal(ccw)) + return -EOPNOTSUPP; + if ((!ccw_is_chain(ccw)) && (!ccw_is_tic(ccw))) break; @@ -503,7 +502,7 @@ static int ccwchain_fetch_direct(struct ccwchain *chain, struct ccw1 *ccw; struct pfn_array_table *pat; unsigned long *idaws; - int idaw_nr; + int ret; ccw = chain->ch_ccw + idx; @@ -523,18 +522,19 @@ static int ccwchain_fetch_direct(struct ccwchain *chain, * needed when translating a direct ccw to a idal ccw. */ pat = chain->ch_pat + idx; - if (pfn_array_table_init(pat, 1)) - return -ENOMEM; - idaw_nr = pfn_array_alloc_pin(pat->pat_pa, cp->mdev, - ccw->cda, ccw->count); - if (idaw_nr < 0) - return idaw_nr; + ret = pfn_array_table_init(pat, 1); + if (ret) + goto out_init; + + ret = pfn_array_alloc_pin(pat->pat_pa, cp->mdev, ccw->cda, ccw->count); + if (ret < 0) + goto out_init; /* Translate this direct ccw to a idal ccw. */ - idaws = kcalloc(idaw_nr, sizeof(*idaws), GFP_DMA | GFP_KERNEL); + idaws = kcalloc(ret, sizeof(*idaws), GFP_DMA | GFP_KERNEL); if (!idaws) { - pfn_array_table_unpin_free(pat, cp->mdev); - return -ENOMEM; + ret = -ENOMEM; + goto out_unpin; } ccw->cda = (__u32) virt_to_phys(idaws); ccw->flags |= CCW_FLAG_IDA; @@ -542,6 +542,12 @@ static int ccwchain_fetch_direct(struct ccwchain *chain, pfn_array_table_idal_create_words(pat, idaws); return 0; + +out_unpin: + pfn_array_table_unpin_free(pat, cp->mdev); +out_init: + ccw->cda = 0; + return ret; } static int ccwchain_fetch_idal(struct ccwchain *chain, @@ -571,7 +577,7 @@ static int ccwchain_fetch_idal(struct ccwchain *chain, pat = chain->ch_pat + idx; ret = pfn_array_table_init(pat, idaw_nr); if (ret) - return ret; + goto out_init; /* Translate idal ccw to use new allocated idaws. */ idaws = kzalloc(idaw_len, GFP_DMA | GFP_KERNEL); @@ -603,6 +609,8 @@ out_free_idaws: kfree(idaws); out_unpin: pfn_array_table_unpin_free(pat, cp->mdev); +out_init: + ccw->cda = 0; return ret; } @@ -656,10 +664,8 @@ int cp_init(struct channel_program *cp, struct device *mdev, union orb *orb) /* * XXX: * Only support prefetch enable mode now. - * Only support 64bit addressing idal. - * Only support 4k IDAW. */ - if (!orb->cmd.pfch || !orb->cmd.c64 || orb->cmd.i2k) + if (!orb->cmd.pfch) return -EOPNOTSUPP; INIT_LIST_HEAD(&cp->ccwchain_list); @@ -688,6 +694,10 @@ int cp_init(struct channel_program *cp, struct device *mdev, union orb *orb) ret = ccwchain_loop_tic(chain, cp); if (ret) cp_unpin_free(cp); + /* It is safe to force: if not set but idals used + * ccwchain_calc_length returns an error. + */ + cp->orb.cmd.c64 = 1; return ret; } diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c index ea6a2d0b2894..770fa9cfc310 100644 --- a/drivers/s390/cio/vfio_ccw_drv.c +++ b/drivers/s390/cio/vfio_ccw_drv.c @@ -177,6 +177,7 @@ static int vfio_ccw_sch_event(struct subchannel *sch, int process) { struct vfio_ccw_private *private = dev_get_drvdata(&sch->dev); unsigned long flags; + int rc = -EAGAIN; spin_lock_irqsave(sch->lock, flags); if (!device_is_registered(&sch->dev)) @@ -187,6 +188,7 @@ static int vfio_ccw_sch_event(struct subchannel *sch, int process) if (cio_update_schib(sch)) { vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_NOT_OPER); + rc = 0; goto out_unlock; } @@ -195,11 +197,12 @@ static int vfio_ccw_sch_event(struct subchannel *sch, int process) private->state = private->mdev ? VFIO_CCW_STATE_IDLE : VFIO_CCW_STATE_STANDBY; } + rc = 0; out_unlock: spin_unlock_irqrestore(sch->lock, flags); - return 0; + return rc; } static struct css_device_id vfio_ccw_sch_ids[] = { diff --git a/drivers/s390/cio/vfio_ccw_fsm.c b/drivers/s390/cio/vfio_ccw_fsm.c index 3c800642134e..797a82731159 100644 --- a/drivers/s390/cio/vfio_ccw_fsm.c +++ b/drivers/s390/cio/vfio_ccw_fsm.c @@ -13,6 +13,9 @@ #include "ioasm.h" #include "vfio_ccw_private.h" +#define CREATE_TRACE_POINTS +#include "vfio_ccw_trace.h" + static int fsm_io_helper(struct vfio_ccw_private *private) { struct subchannel *sch; @@ -110,6 +113,10 @@ static void fsm_disabled_irq(struct vfio_ccw_private *private, */ cio_disable_subchannel(sch); } +inline struct subchannel_id get_schid(struct vfio_ccw_private *p) +{ + return p->sch->schid; +} /* * Deal with the ccw command request from the userspace. @@ -121,6 +128,7 @@ static void fsm_io_request(struct vfio_ccw_private *private, union scsw *scsw = &private->scsw; struct ccw_io_region *io_region = &private->io_region; struct mdev_device *mdev = private->mdev; + char *errstr = "request"; private->state = VFIO_CCW_STATE_BOXED; @@ -132,15 +140,19 @@ static void fsm_io_request(struct vfio_ccw_private *private, /* Don't try to build a cp if transport mode is specified. */ if (orb->tm.b) { io_region->ret_code = -EOPNOTSUPP; + errstr = "transport mode"; goto err_out; } io_region->ret_code = cp_init(&private->cp, mdev_dev(mdev), orb); - if (io_region->ret_code) + if (io_region->ret_code) { + errstr = "cp init"; goto err_out; + } io_region->ret_code = cp_prefetch(&private->cp); if (io_region->ret_code) { + errstr = "cp prefetch"; cp_free(&private->cp); goto err_out; } @@ -148,6 +160,7 @@ static void fsm_io_request(struct vfio_ccw_private *private, /* Start channel program and wait for I/O interrupt. */ io_region->ret_code = fsm_io_helper(private); if (io_region->ret_code) { + errstr = "cp fsm_io_helper"; cp_free(&private->cp); goto err_out; } @@ -164,6 +177,8 @@ static void fsm_io_request(struct vfio_ccw_private *private, err_out: private->state = VFIO_CCW_STATE_IDLE; + trace_vfio_ccw_io_fctl(scsw->cmd.fctl, get_schid(private), + io_region->ret_code, errstr); } /* diff --git a/drivers/s390/cio/vfio_ccw_trace.h b/drivers/s390/cio/vfio_ccw_trace.h new file mode 100644 index 000000000000..b1da53ddec1f --- /dev/null +++ b/drivers/s390/cio/vfio_ccw_trace.h @@ -0,0 +1,54 @@ +/* SPDX-License-Identifier: GPL-2.0 + * Tracepoints for vfio_ccw driver + * + * Copyright IBM Corp. 2018 + * + * Author(s): Dong Jia Shi <bjsdjshi@linux.vnet.ibm.com> + * Halil Pasic <pasic@linux.vnet.ibm.com> + */ + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM vfio_ccw + +#if !defined(_VFIO_CCW_TRACE_) || defined(TRACE_HEADER_MULTI_READ) +#define _VFIO_CCW_TRACE_ + +#include <linux/tracepoint.h> + +TRACE_EVENT(vfio_ccw_io_fctl, + TP_PROTO(int fctl, struct subchannel_id schid, int errno, char *errstr), + TP_ARGS(fctl, schid, errno, errstr), + + TP_STRUCT__entry( + __field(int, fctl) + __field_struct(struct subchannel_id, schid) + __field(int, errno) + __field(char*, errstr) + ), + + TP_fast_assign( + __entry->fctl = fctl; + __entry->schid = schid; + __entry->errno = errno; + __entry->errstr = errstr; + ), + + TP_printk("schid=%x.%x.%04x fctl=%x errno=%d info=%s", + __entry->schid.cssid, + __entry->schid.ssid, + __entry->schid.sch_no, + __entry->fctl, + __entry->errno, + __entry->errstr) +); + +#endif /* _VFIO_CCW_TRACE_ */ + +/* This part must be outside protection */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE vfio_ccw_trace + +#include <trace/define_trace.h> 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/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/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index 116146022aa1..bfe999505815 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -126,6 +126,25 @@ static void cifs_debug_tcon(struct seq_file *m, struct cifs_tcon *tcon) seq_putc(m, '\n'); } +static void +cifs_dump_iface(struct seq_file *m, struct cifs_server_iface *iface) +{ + struct sockaddr_in *ipv4 = (struct sockaddr_in *)&iface->sockaddr; + struct sockaddr_in6 *ipv6 = (struct sockaddr_in6 *)&iface->sockaddr; + + seq_printf(m, "\t\tSpeed: %zu bps\n", iface->speed); + seq_puts(m, "\t\tCapabilities: "); + if (iface->rdma_capable) + seq_puts(m, "rdma "); + if (iface->rss_capable) + seq_puts(m, "rss "); + seq_putc(m, '\n'); + if (iface->sockaddr.ss_family == AF_INET) + seq_printf(m, "\t\tIPv4: %pI4\n", &ipv4->sin_addr); + else if (iface->sockaddr.ss_family == AF_INET6) + seq_printf(m, "\t\tIPv6: %pI6\n", &ipv6->sin6_addr); +} + static int cifs_debug_data_proc_show(struct seq_file *m, void *v) { struct list_head *tmp1, *tmp2, *tmp3; @@ -312,6 +331,16 @@ skip_rdma: mid_entry->mid); } spin_unlock(&GlobalMid_Lock); + + spin_lock(&ses->iface_lock); + if (ses->iface_count) + seq_printf(m, "\n\tServer interfaces: %zu\n", + ses->iface_count); + for (j = 0; j < ses->iface_count; j++) { + seq_printf(m, "\t%d)\n", j); + cifs_dump_iface(m, &ses->iface_list[j]); + } + spin_unlock(&ses->iface_lock); } } spin_unlock(&cifs_tcp_ses_lock); diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c index 937251cc61c0..ee2a8ec70056 100644 --- a/fs/cifs/cifsencrypt.c +++ b/fs/cifs/cifsencrypt.c @@ -37,7 +37,6 @@ #include <crypto/aead.h> int __cifs_calc_signature(struct smb_rqst *rqst, - int start, struct TCP_Server_Info *server, char *signature, struct shash_desc *shash) { @@ -45,16 +44,27 @@ int __cifs_calc_signature(struct smb_rqst *rqst, int rc; struct kvec *iov = rqst->rq_iov; int n_vec = rqst->rq_nvec; + int is_smb2 = server->vals->header_preamble_size == 0; - for (i = start; i < n_vec; i++) { + /* iov[0] is actual data and not the rfc1002 length for SMB2+ */ + if (is_smb2) { + if (iov[0].iov_len <= 4) + return -EIO; + i = 0; + } else { + if (n_vec < 2 || iov[0].iov_len != 4) + return -EIO; + i = 1; /* skip rfc1002 length */ + } + + for (; i < n_vec; i++) { if (iov[i].iov_len == 0) continue; if (iov[i].iov_base == NULL) { cifs_dbg(VFS, "null iovec entry\n"); return -EIO; } - if (i == 1 && iov[1].iov_len <= 4) - break; /* nothing to sign or corrupt header */ + rc = crypto_shash_update(shash, iov[i].iov_base, iov[i].iov_len); if (rc) { @@ -118,7 +128,7 @@ static int cifs_calc_signature(struct smb_rqst *rqst, return rc; } - return __cifs_calc_signature(rqst, 1, server, signature, + return __cifs_calc_signature(rqst, server, signature, &server->secmech.sdescmd5->shash); } diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 1efa2e65bc1a..bd78da59a4fd 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -33,6 +33,9 @@ #define CIFS_MAGIC_NUMBER 0xFF534D42 /* the first four bytes of SMB PDUs */ +#define CIFS_PORT 445 +#define RFC1001_PORT 139 + /* * The sizes of various internal tables and strings */ @@ -312,6 +315,10 @@ struct smb_version_operations { /* send echo request */ int (*echo)(struct TCP_Server_Info *); /* create directory */ + int (*posix_mkdir)(const unsigned int xid, struct inode *inode, + umode_t mode, struct cifs_tcon *tcon, + const char *full_path, + struct cifs_sb_info *cifs_sb); int (*mkdir)(const unsigned int, struct cifs_tcon *, const char *, struct cifs_sb_info *); /* set info on created directory */ @@ -838,6 +845,13 @@ static inline void cifs_set_net_ns(struct TCP_Server_Info *srv, struct net *net) #endif +struct cifs_server_iface { + size_t speed; + unsigned int rdma_capable : 1; + unsigned int rss_capable : 1; + struct sockaddr_storage sockaddr; +}; + /* * Session structure. One of these for each uid session with a particular host */ @@ -875,6 +889,20 @@ struct cifs_ses { #ifdef CONFIG_CIFS_SMB311 __u8 preauth_sha_hash[SMB2_PREAUTH_HASH_SIZE]; #endif /* 3.1.1 */ + + /* + * Network interfaces available on the server this session is + * connected to. + * + * Other channels can be opened by connecting and binding this + * session to interfaces from this list. + * + * iface_lock should be taken when accessing any of these fields + */ + spinlock_t iface_lock; + struct cifs_server_iface *iface_list; + size_t iface_count; + unsigned long iface_last_update; /* jiffies */ }; static inline bool @@ -883,6 +911,14 @@ cap_unix(struct cifs_ses *ses) return ses->server->vals->cap_unix & ses->capabilities; } +struct cached_fid { + bool is_valid:1; /* Do we have a useable root fid */ + struct cifs_fid *fid; + struct mutex fid_mutex; + struct cifs_tcon *tcon; + struct work_struct lease_break; +}; + /* * there is one of these for each connection to a resource on a particular * session @@ -987,9 +1023,7 @@ struct cifs_tcon { struct fscache_cookie *fscache; /* cookie for share */ #endif struct list_head pending_opens; /* list of incomplete opens */ - bool valid_root_fid:1; /* Do we have a useable root fid */ - struct mutex prfid_mutex; /* prevents reopen race after dead ses*/ - struct cifs_fid *prfid; /* handle to the directory at top of share */ + struct cached_fid crfid; /* Cached root fid */ /* BB add field for back pointer to sb struct(s)? */ }; diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index 4e0d183c3d10..03018be17283 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -112,10 +112,6 @@ extern int SendReceive2(const unsigned int /* xid */ , struct cifs_ses *, struct kvec *, int /* nvec to send */, int * /* type of buf returned */, const int flags, struct kvec * /* resp vec */); -extern int smb2_send_recv(const unsigned int xid, struct cifs_ses *pses, - struct kvec *pkvec, int nvec_to_send, - int *pbuftype, const int flags, - struct kvec *presp); extern int SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *ptcon, struct smb_hdr *in_buf , @@ -544,7 +540,7 @@ int cifs_create_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, struct cifs_sb_info *cifs_sb, const unsigned char *path, char *pbuf, unsigned int *pbytes_written); -int __cifs_calc_signature(struct smb_rqst *rqst, int start, +int __cifs_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server, char *signature, struct shash_desc *shash); enum securityEnum cifs_select_sectype(struct TCP_Server_Info *, @@ -552,6 +548,7 @@ enum securityEnum cifs_select_sectype(struct TCP_Server_Info *, struct cifs_aio_ctx *cifs_aio_ctx_alloc(void); void cifs_aio_ctx_release(struct kref *refcount); int setup_aio_ctx_iter(struct cifs_aio_ctx *ctx, struct iov_iter *iter, int rw); +void smb2_cached_lease_break(struct work_struct *work); int cifs_alloc_hash(const char *name, struct crypto_shash **shash, struct sdesc **sdesc); diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 42329b25877d..d352da325de3 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -107,10 +107,10 @@ cifs_mark_open_files_invalid(struct cifs_tcon *tcon) } spin_unlock(&tcon->open_file_lock); - mutex_lock(&tcon->prfid_mutex); - tcon->valid_root_fid = false; - memset(tcon->prfid, 0, sizeof(struct cifs_fid)); - mutex_unlock(&tcon->prfid_mutex); + mutex_lock(&tcon->crfid.fid_mutex); + tcon->crfid.is_valid = false; + memset(tcon->crfid.fid, 0, sizeof(struct cifs_fid)); + mutex_unlock(&tcon->crfid.fid_mutex); /* * BB Add call to invalidate_inodes(sb) for all superblocks mounted diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 96645a7d8f27..a57da1b88bdf 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -57,9 +57,6 @@ #include "smb2proto.h" #include "smbdirect.h" -#define CIFS_PORT 445 -#define RFC1001_PORT 139 - extern mempool_t *cifs_req_poolp; extern bool disable_legacy_dialects; @@ -3029,8 +3026,11 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info) #ifdef CONFIG_CIFS_SMB311 if ((volume_info->linux_ext) && (ses->server->posix_ext_supported)) { - if (ses->server->vals->protocol_id == SMB311_PROT_ID) + if (ses->server->vals->protocol_id == SMB311_PROT_ID) { tcon->posix_extensions = true; + printk_once(KERN_WARNING + "SMB3.11 POSIX Extensions are experimental\n"); + } } #endif /* 311 */ diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index f4697f548a39..a2cfb33e85c1 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -1575,6 +1575,17 @@ int cifs_mkdir(struct inode *inode, struct dentry *direntry, umode_t mode) goto mkdir_out; } + server = tcon->ses->server; + +#ifdef CONFIG_CIFS_SMB311 + if ((server->ops->posix_mkdir) && (tcon->posix_extensions)) { + rc = server->ops->posix_mkdir(xid, inode, mode, tcon, full_path, + cifs_sb); + d_drop(direntry); /* for time being always refresh inode info */ + goto mkdir_out; + } +#endif /* SMB311 */ + if (cap_unix(tcon->ses) && (CIFS_UNIX_POSIX_PATH_OPS_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability))) { rc = cifs_posix_mkdir(inode, direntry, mode, full_path, cifs_sb, @@ -1583,8 +1594,6 @@ int cifs_mkdir(struct inode *inode, struct dentry *direntry, umode_t mode) goto mkdir_out; } - server = tcon->ses->server; - if (!server->ops->mkdir) { rc = -ENOSYS; goto mkdir_out; diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index af29ade195c0..53e8362cbc4a 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -82,6 +82,7 @@ sesInfoAlloc(void) INIT_LIST_HEAD(&ret_buf->smb_ses_list); INIT_LIST_HEAD(&ret_buf->tcon_list); mutex_init(&ret_buf->session_mutex); + spin_lock_init(&ret_buf->iface_lock); } return ret_buf; } @@ -102,6 +103,7 @@ sesInfoFree(struct cifs_ses *buf_to_free) kfree(buf_to_free->user_name); kfree(buf_to_free->domainName); kzfree(buf_to_free->auth_key.response); + kfree(buf_to_free->iface_list); kzfree(buf_to_free); } @@ -117,8 +119,9 @@ tconInfoAlloc(void) INIT_LIST_HEAD(&ret_buf->openFileList); INIT_LIST_HEAD(&ret_buf->tcon_list); spin_lock_init(&ret_buf->open_file_lock); - mutex_init(&ret_buf->prfid_mutex); - ret_buf->prfid = kzalloc(sizeof(struct cifs_fid), GFP_KERNEL); + mutex_init(&ret_buf->crfid.fid_mutex); + ret_buf->crfid.fid = kzalloc(sizeof(struct cifs_fid), + GFP_KERNEL); #ifdef CONFIG_CIFS_STATS spin_lock_init(&ret_buf->stat_lock); #endif @@ -136,7 +139,7 @@ tconInfoFree(struct cifs_tcon *buf_to_free) atomic_dec(&tconInfoAllocCount); kfree(buf_to_free->nativeFileSystem); kzfree(buf_to_free->password); - kfree(buf_to_free->prfid); + kfree(buf_to_free->crfid.fid); kfree(buf_to_free); } diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index e2bec47c6845..3ff7cec2da81 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -454,7 +454,8 @@ cifs_convert_path_to_utf16(const char *from, struct cifs_sb_info *cifs_sb) #ifdef CONFIG_CIFS_SMB311 /* SMB311 POSIX extensions paths do not include leading slash */ else if (cifs_sb_master_tlink(cifs_sb) && - cifs_sb_master_tcon(cifs_sb)->posix_extensions) { + cifs_sb_master_tcon(cifs_sb)->posix_extensions && + (from[0] == '/')) { start_of_path = from + 1; } #endif /* 311 */ @@ -492,10 +493,11 @@ cifs_ses_oplock_break(struct work_struct *work) { struct smb2_lease_break_work *lw = container_of(work, struct smb2_lease_break_work, lease_break); - int rc; + int rc = 0; rc = SMB2_lease_break(0, tlink_tcon(lw->tlink), lw->lease_key, lw->lease_state); + cifs_dbg(FYI, "Lease release rc %d\n", rc); cifs_put_tlink(lw->tlink); kfree(lw); @@ -561,6 +563,7 @@ smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp, open->oplock = lease_state; } + return found; } @@ -603,6 +606,18 @@ smb2_is_valid_lease_break(char *buffer) return true; } spin_unlock(&tcon->open_file_lock); + + if (tcon->crfid.is_valid && + !memcmp(rsp->LeaseKey, + tcon->crfid.fid->lease_key, + SMB2_LEASE_KEY_SIZE)) { + INIT_WORK(&tcon->crfid.lease_break, + smb2_cached_lease_break); + queue_work(cifsiod_wq, + &tcon->crfid.lease_break); + spin_unlock(&cifs_tcp_ses_lock); + return true; + } } } } diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index b15f5957d645..0356b5559c71 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -294,34 +294,191 @@ smb2_negotiate_rsize(struct cifs_tcon *tcon, struct smb_vol *volume_info) return rsize; } -#ifdef CONFIG_CIFS_STATS2 + +static int +parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf, + size_t buf_len, + struct cifs_server_iface **iface_list, + size_t *iface_count) +{ + struct network_interface_info_ioctl_rsp *p; + struct sockaddr_in *addr4; + struct sockaddr_in6 *addr6; + struct iface_info_ipv4 *p4; + struct iface_info_ipv6 *p6; + struct cifs_server_iface *info; + ssize_t bytes_left; + size_t next = 0; + int nb_iface = 0; + int rc = 0; + + *iface_list = NULL; + *iface_count = 0; + + /* + * Fist pass: count and sanity check + */ + + bytes_left = buf_len; + p = buf; + while (bytes_left >= sizeof(*p)) { + nb_iface++; + next = le32_to_cpu(p->Next); + if (!next) { + bytes_left -= sizeof(*p); + break; + } + p = (struct network_interface_info_ioctl_rsp *)((u8 *)p+next); + bytes_left -= next; + } + + if (!nb_iface) { + cifs_dbg(VFS, "%s: malformed interface info\n", __func__); + rc = -EINVAL; + goto out; + } + + if (bytes_left || p->Next) + cifs_dbg(VFS, "%s: incomplete interface info\n", __func__); + + + /* + * Second pass: extract info to internal structure + */ + + *iface_list = kcalloc(nb_iface, sizeof(**iface_list), GFP_KERNEL); + if (!*iface_list) { + rc = -ENOMEM; + goto out; + } + + info = *iface_list; + bytes_left = buf_len; + p = buf; + while (bytes_left >= sizeof(*p)) { + info->speed = le64_to_cpu(p->LinkSpeed); + info->rdma_capable = le32_to_cpu(p->Capability & RDMA_CAPABLE); + info->rss_capable = le32_to_cpu(p->Capability & RSS_CAPABLE); + + cifs_dbg(FYI, "%s: adding iface %zu\n", __func__, *iface_count); + cifs_dbg(FYI, "%s: speed %zu bps\n", __func__, info->speed); + cifs_dbg(FYI, "%s: capabilities 0x%08x\n", __func__, + le32_to_cpu(p->Capability)); + + switch (p->Family) { + /* + * The kernel and wire socket structures have the same + * layout and use network byte order but make the + * conversion explicit in case either one changes. + */ + case INTERNETWORK: + addr4 = (struct sockaddr_in *)&info->sockaddr; + p4 = (struct iface_info_ipv4 *)p->Buffer; + addr4->sin_family = AF_INET; + memcpy(&addr4->sin_addr, &p4->IPv4Address, 4); + + /* [MS-SMB2] 2.2.32.5.1.1 Clients MUST ignore these */ + addr4->sin_port = cpu_to_be16(CIFS_PORT); + + cifs_dbg(FYI, "%s: ipv4 %pI4\n", __func__, + &addr4->sin_addr); + break; + case INTERNETWORKV6: + addr6 = (struct sockaddr_in6 *)&info->sockaddr; + p6 = (struct iface_info_ipv6 *)p->Buffer; + addr6->sin6_family = AF_INET6; + memcpy(&addr6->sin6_addr, &p6->IPv6Address, 16); + + /* [MS-SMB2] 2.2.32.5.1.2 Clients MUST ignore these */ + addr6->sin6_flowinfo = 0; + addr6->sin6_scope_id = 0; + addr6->sin6_port = cpu_to_be16(CIFS_PORT); + + cifs_dbg(FYI, "%s: ipv6 %pI6\n", __func__, + &addr6->sin6_addr); + break; + default: + cifs_dbg(VFS, + "%s: skipping unsupported socket family\n", + __func__); + goto next_iface; + } + + (*iface_count)++; + info++; +next_iface: + next = le32_to_cpu(p->Next); + if (!next) + break; + p = (struct network_interface_info_ioctl_rsp *)((u8 *)p+next); + bytes_left -= next; + } + + if (!*iface_count) { + rc = -EINVAL; + goto out; + } + +out: + if (rc) { + kfree(*iface_list); + *iface_count = 0; + *iface_list = NULL; + } + return rc; +} + + static int SMB3_request_interfaces(const unsigned int xid, struct cifs_tcon *tcon) { int rc; unsigned int ret_data_len = 0; - struct network_interface_info_ioctl_rsp *out_buf; + struct network_interface_info_ioctl_rsp *out_buf = NULL; + struct cifs_server_iface *iface_list; + size_t iface_count; + struct cifs_ses *ses = tcon->ses; rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID, FSCTL_QUERY_NETWORK_INTERFACE_INFO, true /* is_fsctl */, NULL /* no data input */, 0 /* no data input */, (char **)&out_buf, &ret_data_len); - if (rc != 0) + if (rc != 0) { cifs_dbg(VFS, "error %d on ioctl to get interface list\n", rc); - else if (ret_data_len < sizeof(struct network_interface_info_ioctl_rsp)) { - cifs_dbg(VFS, "server returned bad net interface info buf\n"); - rc = -EINVAL; - } else { - /* Dump info on first interface */ - cifs_dbg(FYI, "Adapter Capability 0x%x\t", - le32_to_cpu(out_buf->Capability)); - cifs_dbg(FYI, "Link Speed %lld\n", - le64_to_cpu(out_buf->LinkSpeed)); + goto out; } + + rc = parse_server_interfaces(out_buf, ret_data_len, + &iface_list, &iface_count); + if (rc) + goto out; + + spin_lock(&ses->iface_lock); + kfree(ses->iface_list); + ses->iface_list = iface_list; + ses->iface_count = iface_count; + ses->iface_last_update = jiffies; + spin_unlock(&ses->iface_lock); + +out: kfree(out_buf); return rc; } -#endif /* STATS2 */ + +void +smb2_cached_lease_break(struct work_struct *work) +{ + struct cached_fid *cfid = container_of(work, + struct cached_fid, lease_break); + mutex_lock(&cfid->fid_mutex); + if (cfid->is_valid) { + cifs_dbg(FYI, "clear cached root file handle\n"); + SMB2_close(0, cfid->tcon, cfid->fid->persistent_fid, + cfid->fid->volatile_fid); + cfid->is_valid = false; + } + mutex_unlock(&cfid->fid_mutex); +} /* * Open the directory at the root of a share @@ -331,13 +488,13 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *pfid) struct cifs_open_parms oparams; int rc; __le16 srch_path = 0; /* Null - since an open of top of share */ - u8 oplock = SMB2_OPLOCK_LEVEL_NONE; + u8 oplock = SMB2_OPLOCK_LEVEL_II; - mutex_lock(&tcon->prfid_mutex); - if (tcon->valid_root_fid) { + mutex_lock(&tcon->crfid.fid_mutex); + if (tcon->crfid.is_valid) { cifs_dbg(FYI, "found a cached root file handle\n"); - memcpy(pfid, tcon->prfid, sizeof(struct cifs_fid)); - mutex_unlock(&tcon->prfid_mutex); + memcpy(pfid, tcon->crfid.fid, sizeof(struct cifs_fid)); + mutex_unlock(&tcon->crfid.fid_mutex); return 0; } @@ -350,10 +507,11 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *pfid) rc = SMB2_open(xid, &oparams, &srch_path, &oplock, NULL, NULL, NULL); if (rc == 0) { - memcpy(tcon->prfid, pfid, sizeof(struct cifs_fid)); - tcon->valid_root_fid = true; + memcpy(tcon->crfid.fid, pfid, sizeof(struct cifs_fid)); + tcon->crfid.tcon = tcon; + tcon->crfid.is_valid = true; } - mutex_unlock(&tcon->prfid_mutex); + mutex_unlock(&tcon->crfid.fid_mutex); return rc; } @@ -383,9 +541,7 @@ smb3_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon) if (rc) return; -#ifdef CONFIG_CIFS_STATS2 SMB3_request_interfaces(xid, tcon); -#endif /* STATS2 */ SMB2_QFS_attr(xid, tcon, fid.persistent_fid, fid.volatile_fid, FS_ATTRIBUTE_INFORMATION); @@ -436,7 +592,7 @@ smb2_is_path_accessible(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_open_parms oparms; struct cifs_fid fid; - if ((*full_path == 0) && tcon->valid_root_fid) + if ((*full_path == 0) && tcon->crfid.is_valid) return 0; utf16_path = cifs_convert_path_to_utf16(full_path, cifs_sb); @@ -2151,7 +2307,7 @@ fill_transform_hdr(struct smb2_transform_hdr *tr_hdr, unsigned int orig_len, struct smb_rqst *old_rq) { struct smb2_sync_hdr *shdr = - (struct smb2_sync_hdr *)old_rq->rq_iov[1].iov_base; + (struct smb2_sync_hdr *)old_rq->rq_iov[0].iov_base; memset(tr_hdr, 0, sizeof(struct smb2_transform_hdr)); tr_hdr->ProtocolId = SMB2_TRANSFORM_PROTO_NUM; @@ -2171,14 +2327,13 @@ static inline void smb2_sg_set_buf(struct scatterlist *sg, const void *buf, } /* Assumes: - * rqst->rq_iov[0] is rfc1002 length - * rqst->rq_iov[1] is tranform header - * rqst->rq_iov[2+] data to be encrypted/decrypted + * rqst->rq_iov[0] is transform header + * rqst->rq_iov[1+] data to be encrypted/decrypted */ static struct scatterlist * init_sg(struct smb_rqst *rqst, u8 *sign) { - unsigned int sg_len = rqst->rq_nvec + rqst->rq_npages; + unsigned int sg_len = rqst->rq_nvec + rqst->rq_npages + 1; unsigned int assoc_data_len = sizeof(struct smb2_transform_hdr) - 20; struct scatterlist *sg; unsigned int i; @@ -2189,10 +2344,10 @@ init_sg(struct smb_rqst *rqst, u8 *sign) return NULL; sg_init_table(sg, sg_len); - smb2_sg_set_buf(&sg[0], rqst->rq_iov[1].iov_base + 20, assoc_data_len); - for (i = 1; i < rqst->rq_nvec - 1; i++) - smb2_sg_set_buf(&sg[i], rqst->rq_iov[i+1].iov_base, - rqst->rq_iov[i+1].iov_len); + smb2_sg_set_buf(&sg[0], rqst->rq_iov[0].iov_base + 20, assoc_data_len); + for (i = 1; i < rqst->rq_nvec; i++) + smb2_sg_set_buf(&sg[i], rqst->rq_iov[i].iov_base, + rqst->rq_iov[i].iov_len); for (j = 0; i < sg_len - 1; i++, j++) { unsigned int len, offset; @@ -2224,18 +2379,17 @@ smb2_get_enc_key(struct TCP_Server_Info *server, __u64 ses_id, int enc, u8 *key) return 1; } /* - * Encrypt or decrypt @rqst message. @rqst has the following format: - * iov[0] - rfc1002 length - * iov[1] - transform header (associate data), - * iov[2-N] and pages - data to encrypt. - * On success return encrypted data in iov[2-N] and pages, leave iov[0-1] + * Encrypt or decrypt @rqst message. @rqst[0] has the following format: + * iov[0] - transform header (associate data), + * iov[1-N] - SMB2 header and pages - data to encrypt. + * On success return encrypted data in iov[1-N] and pages, leave iov[0] * untouched. */ static int crypt_message(struct TCP_Server_Info *server, struct smb_rqst *rqst, int enc) { struct smb2_transform_hdr *tr_hdr = - (struct smb2_transform_hdr *)rqst->rq_iov[1].iov_base; + (struct smb2_transform_hdr *)rqst->rq_iov[0].iov_base; unsigned int assoc_data_len = sizeof(struct smb2_transform_hdr) - 20; int rc = 0; struct scatterlist *sg; @@ -2323,10 +2477,6 @@ free_req: return rc; } -/* - * This is called from smb_send_rqst. At this point we have the rfc1002 - * header as the first element in the vector. - */ static int smb3_init_transform_rq(struct TCP_Server_Info *server, struct smb_rqst *new_rq, struct smb_rqst *old_rq) @@ -2335,7 +2485,7 @@ smb3_init_transform_rq(struct TCP_Server_Info *server, struct smb_rqst *new_rq, struct page **pages; struct smb2_transform_hdr *tr_hdr; unsigned int npages = old_rq->rq_npages; - unsigned int orig_len = get_rfc1002_length(old_rq->rq_iov[0].iov_base); + unsigned int orig_len; int i; int rc = -ENOMEM; @@ -2355,18 +2505,14 @@ smb3_init_transform_rq(struct TCP_Server_Info *server, struct smb_rqst *new_rq, goto err_free_pages; } - /* Make space for one extra iov to hold the transform header */ iov = kmalloc_array(old_rq->rq_nvec + 1, sizeof(struct kvec), GFP_KERNEL); if (!iov) goto err_free_pages; - /* copy all iovs from the old except the 1st one (rfc1002 length) */ - memcpy(&iov[2], &old_rq->rq_iov[1], - sizeof(struct kvec) * (old_rq->rq_nvec - 1)); - /* copy the rfc1002 iov */ - iov[0].iov_base = old_rq->rq_iov[0].iov_base; - iov[0].iov_len = old_rq->rq_iov[0].iov_len; + /* copy all iovs from the old */ + memcpy(&iov[1], &old_rq->rq_iov[0], + sizeof(struct kvec) * old_rq->rq_nvec); new_rq->rq_iov = iov; new_rq->rq_nvec = old_rq->rq_nvec + 1; @@ -2375,14 +2521,12 @@ smb3_init_transform_rq(struct TCP_Server_Info *server, struct smb_rqst *new_rq, if (!tr_hdr) goto err_free_iov; + orig_len = smb2_rqst_len(old_rq, false); + /* fill the 2nd iov with a transform header */ fill_transform_hdr(tr_hdr, orig_len, old_rq); - new_rq->rq_iov[1].iov_base = tr_hdr; - new_rq->rq_iov[1].iov_len = sizeof(struct smb2_transform_hdr); - - /* Update rfc1002 header */ - inc_rfc1001_len(new_rq->rq_iov[0].iov_base, - sizeof(struct smb2_transform_hdr)); + new_rq->rq_iov[0].iov_base = tr_hdr; + new_rq->rq_iov[0].iov_len = sizeof(struct smb2_transform_hdr); /* copy pages form the old */ for (i = 0; i < npages; i++) { @@ -2426,7 +2570,7 @@ smb3_free_transform_rq(struct smb_rqst *rqst) put_page(rqst->rq_pages[i]); kfree(rqst->rq_pages); /* free transform header */ - kfree(rqst->rq_iov[1].iov_base); + kfree(rqst->rq_iov[0].iov_base); kfree(rqst->rq_iov); } @@ -2443,19 +2587,17 @@ decrypt_raw_data(struct TCP_Server_Info *server, char *buf, unsigned int buf_data_size, struct page **pages, unsigned int npages, unsigned int page_data_size) { - struct kvec iov[3]; + struct kvec iov[2]; struct smb_rqst rqst = {NULL}; int rc; - iov[0].iov_base = NULL; - iov[0].iov_len = 0; - iov[1].iov_base = buf; - iov[1].iov_len = sizeof(struct smb2_transform_hdr); - iov[2].iov_base = buf + sizeof(struct smb2_transform_hdr); - iov[2].iov_len = buf_data_size; + iov[0].iov_base = buf; + iov[0].iov_len = sizeof(struct smb2_transform_hdr); + iov[1].iov_base = buf + sizeof(struct smb2_transform_hdr); + iov[1].iov_len = buf_data_size; rqst.rq_iov = iov; - rqst.rq_nvec = 3; + rqst.rq_nvec = 2; rqst.rq_pages = pages; rqst.rq_npages = npages; rqst.rq_pagesz = PAGE_SIZE; @@ -2467,7 +2609,7 @@ decrypt_raw_data(struct TCP_Server_Info *server, char *buf, if (rc) return rc; - memmove(buf, iov[2].iov_base, buf_data_size); + memmove(buf, iov[1].iov_base, buf_data_size); server->total_read = buf_data_size + page_data_size; @@ -3170,6 +3312,7 @@ struct smb_version_operations smb311_operations = { .set_compression = smb2_set_compression, .mkdir = smb2_mkdir, .mkdir_setinfo = smb2_mkdir_setinfo, + .posix_mkdir = smb311_posix_mkdir, .rmdir = smb2_rmdir, .unlink = smb2_unlink, .rename = smb2_rename_path, diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index af032e1a3eac..810b85787c91 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -602,6 +602,7 @@ static void assemble_neg_contexts(struct smb2_negotiate_req *req, int SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses) { + struct smb_rqst rqst; struct smb2_negotiate_req *req; struct smb2_negotiate_rsp *rsp; struct kvec iov[1]; @@ -673,7 +674,11 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses) iov[0].iov_base = (char *)req; iov[0].iov_len = total_len; - rc = smb2_send_recv(xid, ses, iov, 1, &resp_buftype, flags, &rsp_iov); + memset(&rqst, 0, sizeof(struct smb_rqst)); + rqst.rq_iov = iov; + rqst.rq_nvec = 1; + + rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov); cifs_small_buf_release(req); rsp = (struct smb2_negotiate_rsp *)rsp_iov.iov_base; /* @@ -990,8 +995,9 @@ SMB2_sess_alloc_buffer(struct SMB2_sess_data *sess_data) req->PreviousSessionId = sess_data->previous_session; req->Flags = 0; /* MBZ */ - /* to enable echos and oplocks */ - req->sync_hdr.CreditRequest = cpu_to_le16(3); + + /* enough to enable echos and oplocks and one max size write */ + req->sync_hdr.CreditRequest = cpu_to_le16(130); /* only one of SMB2 signing flags may be set in SMB2 request */ if (server->sign) @@ -1027,6 +1033,7 @@ static int SMB2_sess_sendreceive(struct SMB2_sess_data *sess_data) { int rc; + struct smb_rqst rqst; struct smb2_sess_setup_req *req = sess_data->iov[0].iov_base; struct kvec rsp_iov = { NULL, 0 }; @@ -1035,10 +1042,13 @@ SMB2_sess_sendreceive(struct SMB2_sess_data *sess_data) cpu_to_le16(sizeof(struct smb2_sess_setup_req) - 1 /* pad */); req->SecurityBufferLength = cpu_to_le16(sess_data->iov[1].iov_len); - /* BB add code to build os and lm fields */ + memset(&rqst, 0, sizeof(struct smb_rqst)); + rqst.rq_iov = sess_data->iov; + rqst.rq_nvec = 2; - rc = smb2_send_recv(sess_data->xid, sess_data->ses, - sess_data->iov, 2, + /* BB add code to build os and lm fields */ + rc = cifs_send_recv(sess_data->xid, sess_data->ses, + &rqst, &sess_data->buf0_type, CIFS_LOG_ERROR | CIFS_NEG_OP, &rsp_iov); cifs_small_buf_release(sess_data->iov[0].iov_base); @@ -1376,6 +1386,7 @@ out: int SMB2_logoff(const unsigned int xid, struct cifs_ses *ses) { + struct smb_rqst rqst; struct smb2_logoff_req *req; /* response is also trivial struct */ int rc = 0; struct TCP_Server_Info *server; @@ -1413,7 +1424,11 @@ SMB2_logoff(const unsigned int xid, struct cifs_ses *ses) iov[0].iov_base = (char *)req; iov[0].iov_len = total_len; - rc = smb2_send_recv(xid, ses, iov, 1, &resp_buf_type, flags, &rsp_iov); + memset(&rqst, 0, sizeof(struct smb_rqst)); + rqst.rq_iov = iov; + rqst.rq_nvec = 1; + + rc = cifs_send_recv(xid, ses, &rqst, &resp_buf_type, flags, &rsp_iov); cifs_small_buf_release(req); /* * No tcon so can't do @@ -1443,6 +1458,7 @@ int SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, struct cifs_tcon *tcon, const struct nls_table *cp) { + struct smb_rqst rqst; struct smb2_tree_connect_req *req; struct smb2_tree_connect_rsp *rsp = NULL; struct kvec iov[2]; @@ -1499,7 +1515,11 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, !smb3_encryption_required(tcon)) req->sync_hdr.Flags |= SMB2_FLAGS_SIGNED; - rc = smb2_send_recv(xid, ses, iov, 2, &resp_buftype, flags, &rsp_iov); + memset(&rqst, 0, sizeof(struct smb_rqst)); + rqst.rq_iov = iov; + rqst.rq_nvec = 2; + + rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov); cifs_small_buf_release(req); rsp = (struct smb2_tree_connect_rsp *)rsp_iov.iov_base; @@ -1563,6 +1583,7 @@ tcon_error_exit: int SMB2_tdis(const unsigned int xid, struct cifs_tcon *tcon) { + struct smb_rqst rqst; struct smb2_tree_disconnect_req *req; /* response is trivial */ int rc = 0; struct cifs_ses *ses = tcon->ses; @@ -1593,7 +1614,11 @@ SMB2_tdis(const unsigned int xid, struct cifs_tcon *tcon) iov[0].iov_base = (char *)req; iov[0].iov_len = total_len; - rc = smb2_send_recv(xid, ses, iov, 1, &resp_buf_type, flags, &rsp_iov); + memset(&rqst, 0, sizeof(struct smb_rqst)); + rqst.rq_iov = iov; + rqst.rq_nvec = 1; + + rc = cifs_send_recv(xid, ses, &rqst, &resp_buf_type, flags, &rsp_iov); cifs_small_buf_release(req); if (rc) cifs_stats_fail_inc(tcon, SMB2_TREE_DISCONNECT_HE); @@ -1886,11 +1911,165 @@ alloc_path_with_tree_prefix(__le16 **out_path, int *out_size, int *out_len, return 0; } +#ifdef CONFIG_CIFS_SMB311 +int smb311_posix_mkdir(const unsigned int xid, struct inode *inode, + umode_t mode, struct cifs_tcon *tcon, + const char *full_path, + struct cifs_sb_info *cifs_sb) +{ + struct smb_rqst rqst; + struct smb2_create_req *req; + struct smb2_create_rsp *rsp; + struct TCP_Server_Info *server; + struct cifs_ses *ses = tcon->ses; + struct kvec iov[3]; /* make sure at least one for each open context */ + struct kvec rsp_iov = {NULL, 0}; + int resp_buftype; + int uni_path_len; + __le16 *copy_path = NULL; + int copy_size; + int rc = 0; + unsigned int n_iov = 2; + __u32 file_attributes = 0; + char *pc_buf = NULL; + int flags = 0; + unsigned int total_len; + __le16 *path = cifs_convert_path_to_utf16(full_path, cifs_sb); + + if (!path) + return -ENOMEM; + + cifs_dbg(FYI, "mkdir\n"); + + if (ses && (ses->server)) + server = ses->server; + else + return -EIO; + + rc = smb2_plain_req_init(SMB2_CREATE, tcon, (void **) &req, &total_len); + + if (rc) + return rc; + + if (smb3_encryption_required(tcon)) + flags |= CIFS_TRANSFORM_REQ; + + + req->ImpersonationLevel = IL_IMPERSONATION; + req->DesiredAccess = cpu_to_le32(FILE_WRITE_ATTRIBUTES); + /* File attributes ignored on open (used in create though) */ + req->FileAttributes = cpu_to_le32(file_attributes); + req->ShareAccess = FILE_SHARE_ALL_LE; + req->CreateDisposition = cpu_to_le32(FILE_CREATE); + req->CreateOptions = cpu_to_le32(CREATE_NOT_FILE); + + iov[0].iov_base = (char *)req; + /* -1 since last byte is buf[0] which is sent below (path) */ + iov[0].iov_len = total_len - 1; + + req->NameOffset = cpu_to_le16(sizeof(struct smb2_create_req)); + + /* [MS-SMB2] 2.2.13 NameOffset: + * If SMB2_FLAGS_DFS_OPERATIONS is set in the Flags field of + * the SMB2 header, the file name includes a prefix that will + * be processed during DFS name normalization as specified in + * section 3.3.5.9. Otherwise, the file name is relative to + * the share that is identified by the TreeId in the SMB2 + * header. + */ + if (tcon->share_flags & SHI1005_FLAGS_DFS) { + int name_len; + + req->sync_hdr.Flags |= SMB2_FLAGS_DFS_OPERATIONS; + rc = alloc_path_with_tree_prefix(©_path, ©_size, + &name_len, + tcon->treeName, path); + if (rc) { + cifs_small_buf_release(req); + return rc; + } + req->NameLength = cpu_to_le16(name_len * 2); + uni_path_len = copy_size; + path = copy_path; + } else { + uni_path_len = (2 * UniStrnlen((wchar_t *)path, PATH_MAX)) + 2; + /* MUST set path len (NameLength) to 0 opening root of share */ + req->NameLength = cpu_to_le16(uni_path_len - 2); + if (uni_path_len % 8 != 0) { + copy_size = roundup(uni_path_len, 8); + copy_path = kzalloc(copy_size, GFP_KERNEL); + if (!copy_path) { + cifs_small_buf_release(req); + return -ENOMEM; + } + memcpy((char *)copy_path, (const char *)path, + uni_path_len); + uni_path_len = copy_size; + path = copy_path; + } + } + + iov[1].iov_len = uni_path_len; + iov[1].iov_base = path; + req->RequestedOplockLevel = SMB2_OPLOCK_LEVEL_NONE; + + if (tcon->posix_extensions) { + if (n_iov > 2) { + struct create_context *ccontext = + (struct create_context *)iov[n_iov-1].iov_base; + ccontext->Next = + cpu_to_le32(iov[n_iov-1].iov_len); + } + + rc = add_posix_context(iov, &n_iov, mode); + if (rc) { + cifs_small_buf_release(req); + kfree(copy_path); + return rc; + } + pc_buf = iov[n_iov-1].iov_base; + } + + + memset(&rqst, 0, sizeof(struct smb_rqst)); + rqst.rq_iov = iov; + rqst.rq_nvec = n_iov; + + rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, + &rsp_iov); + + cifs_small_buf_release(req); + rsp = (struct smb2_create_rsp *)rsp_iov.iov_base; + + if (rc != 0) { + cifs_stats_fail_inc(tcon, SMB2_CREATE_HE); + trace_smb3_posix_mkdir_err(xid, tcon->tid, ses->Suid, + CREATE_NOT_FILE, FILE_WRITE_ATTRIBUTES, rc); + goto smb311_mkdir_exit; + } else + trace_smb3_posix_mkdir_done(xid, rsp->PersistentFileId, tcon->tid, + ses->Suid, CREATE_NOT_FILE, + FILE_WRITE_ATTRIBUTES); + + SMB2_close(xid, tcon, rsp->PersistentFileId, rsp->VolatileFileId); + + /* Eventually save off posix specific response info and timestaps */ + +smb311_mkdir_exit: + kfree(copy_path); + kfree(pc_buf); + free_rsp_buf(resp_buftype, rsp); + return rc; + +} +#endif /* SMB311 */ + int SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, __u8 *oplock, struct smb2_file_all_info *buf, struct kvec *err_iov, int *buftype) { + struct smb_rqst rqst; struct smb2_create_req *req; struct smb2_create_rsp *rsp; struct TCP_Server_Info *server; @@ -2043,7 +2222,11 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, } #endif /* SMB311 */ - rc = smb2_send_recv(xid, ses, iov, n_iov, &resp_buftype, flags, + memset(&rqst, 0, sizeof(struct smb_rqst)); + rqst.rq_iov = iov; + rqst.rq_nvec = n_iov; + + rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov); cifs_small_buf_release(req); rsp = (struct smb2_create_rsp *)rsp_iov.iov_base; @@ -2099,6 +2282,7 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, char *in_data, u32 indatalen, char **out_data, u32 *plen /* returned data len */) { + struct smb_rqst rqst; struct smb2_ioctl_req *req; struct smb2_ioctl_rsp *rsp; struct cifs_ses *ses; @@ -2189,7 +2373,11 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, if (opcode == FSCTL_VALIDATE_NEGOTIATE_INFO) req->sync_hdr.Flags |= SMB2_FLAGS_SIGNED; - rc = smb2_send_recv(xid, ses, iov, n_iov, &resp_buftype, flags, + memset(&rqst, 0, sizeof(struct smb_rqst)); + rqst.rq_iov = iov; + rqst.rq_nvec = n_iov; + + rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov); cifs_small_buf_release(req); rsp = (struct smb2_ioctl_rsp *)rsp_iov.iov_base; @@ -2274,6 +2462,7 @@ int SMB2_close_flags(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, int flags) { + struct smb_rqst rqst; struct smb2_close_req *req; struct smb2_close_rsp *rsp; struct cifs_ses *ses = tcon->ses; @@ -2301,7 +2490,11 @@ SMB2_close_flags(const unsigned int xid, struct cifs_tcon *tcon, iov[0].iov_base = (char *)req; iov[0].iov_len = total_len; - rc = smb2_send_recv(xid, ses, iov, 1, &resp_buftype, flags, &rsp_iov); + memset(&rqst, 0, sizeof(struct smb_rqst)); + rqst.rq_iov = iov; + rqst.rq_nvec = 1; + + rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov); cifs_small_buf_release(req); rsp = (struct smb2_close_rsp *)rsp_iov.iov_base; @@ -2387,6 +2580,7 @@ query_info(const unsigned int xid, struct cifs_tcon *tcon, u32 additional_info, size_t output_len, size_t min_len, void **data, u32 *dlen) { + struct smb_rqst rqst; struct smb2_query_info_req *req; struct smb2_query_info_rsp *rsp = NULL; struct kvec iov[2]; @@ -2427,7 +2621,11 @@ query_info(const unsigned int xid, struct cifs_tcon *tcon, /* 1 for Buffer */ iov[0].iov_len = total_len - 1; - rc = smb2_send_recv(xid, ses, iov, 1, &resp_buftype, flags, &rsp_iov); + memset(&rqst, 0, sizeof(struct smb_rqst)); + rqst.rq_iov = iov; + rqst.rq_nvec = 1; + + rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov); cifs_small_buf_release(req); rsp = (struct smb2_query_info_rsp *)rsp_iov.iov_base; @@ -2594,11 +2792,10 @@ SMB2_echo(struct TCP_Server_Info *server) { struct smb2_echo_req *req; int rc = 0; - struct kvec iov[2]; + struct kvec iov[1]; struct smb_rqst rqst = { .rq_iov = iov, - .rq_nvec = 2 }; + .rq_nvec = 1 }; unsigned int total_len; - __be32 rfc1002_marker; cifs_dbg(FYI, "In echo request\n"); @@ -2614,11 +2811,8 @@ SMB2_echo(struct TCP_Server_Info *server) req->sync_hdr.CreditRequest = cpu_to_le16(1); - iov[0].iov_len = 4; - rfc1002_marker = cpu_to_be32(total_len); - iov[0].iov_base = &rfc1002_marker; - iov[1].iov_len = total_len; - iov[1].iov_base = (char *)req; + iov[0].iov_len = total_len; + iov[0].iov_base = (char *)req; rc = cifs_call_async(server, &rqst, NULL, smb2_echo_callback, NULL, server, CIFS_ECHO_OP); @@ -2633,6 +2827,7 @@ int SMB2_flush(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid) { + struct smb_rqst rqst; struct smb2_flush_req *req; struct cifs_ses *ses = tcon->ses; struct kvec iov[1]; @@ -2660,7 +2855,11 @@ SMB2_flush(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, iov[0].iov_base = (char *)req; iov[0].iov_len = total_len; - rc = smb2_send_recv(xid, ses, iov, 1, &resp_buftype, flags, &rsp_iov); + memset(&rqst, 0, sizeof(struct smb_rqst)); + rqst.rq_iov = iov; + rqst.rq_nvec = 1; + + rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov); cifs_small_buf_release(req); if (rc != 0) { @@ -2848,10 +3047,9 @@ smb2_async_readv(struct cifs_readdata *rdata) struct smb2_sync_hdr *shdr; struct cifs_io_parms io_parms; struct smb_rqst rqst = { .rq_iov = rdata->iov, - .rq_nvec = 2 }; + .rq_nvec = 1 }; struct TCP_Server_Info *server; unsigned int total_len; - __be32 req_len; cifs_dbg(FYI, "%s: offset=%llu bytes=%u\n", __func__, rdata->offset, rdata->bytes); @@ -2882,12 +3080,8 @@ smb2_async_readv(struct cifs_readdata *rdata) if (smb3_encryption_required(io_parms.tcon)) flags |= CIFS_TRANSFORM_REQ; - req_len = cpu_to_be32(total_len); - - rdata->iov[0].iov_base = &req_len; - rdata->iov[0].iov_len = sizeof(__be32); - rdata->iov[1].iov_base = buf; - rdata->iov[1].iov_len = total_len; + rdata->iov[0].iov_base = buf; + rdata->iov[0].iov_len = total_len; shdr = (struct smb2_sync_hdr *)buf; @@ -2926,6 +3120,7 @@ int SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms, unsigned int *nbytes, char **buf, int *buf_type) { + struct smb_rqst rqst; int resp_buftype, rc = -EACCES; struct smb2_read_plain_req *req = NULL; struct smb2_read_rsp *rsp = NULL; @@ -2946,7 +3141,11 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms, iov[0].iov_base = (char *)req; iov[0].iov_len = total_len; - rc = smb2_send_recv(xid, ses, iov, 1, &resp_buftype, flags, &rsp_iov); + memset(&rqst, 0, sizeof(struct smb_rqst)); + rqst.rq_iov = iov; + rqst.rq_nvec = 1; + + rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov); cifs_small_buf_release(req); rsp = (struct smb2_read_rsp *)rsp_iov.iov_base; @@ -3062,10 +3261,9 @@ smb2_async_writev(struct cifs_writedata *wdata, struct smb2_sync_hdr *shdr; struct cifs_tcon *tcon = tlink_tcon(wdata->cfile->tlink); struct TCP_Server_Info *server = tcon->ses->server; - struct kvec iov[2]; + struct kvec iov[1]; struct smb_rqst rqst = { }; unsigned int total_len; - __be32 rfc1002_marker; rc = smb2_plain_req_init(SMB2_WRITE, tcon, (void **) &req, &total_len); if (rc) { @@ -3137,15 +3335,11 @@ smb2_async_writev(struct cifs_writedata *wdata, v1->length = cpu_to_le32(wdata->mr->mr->length); } #endif - /* 4 for rfc1002 length field and 1 for Buffer */ - iov[0].iov_len = 4; - rfc1002_marker = cpu_to_be32(total_len - 1 + wdata->bytes); - iov[0].iov_base = &rfc1002_marker; - iov[1].iov_len = total_len - 1; - iov[1].iov_base = (char *)req; + iov[0].iov_len = total_len - 1; + iov[0].iov_base = (char *)req; rqst.rq_iov = iov; - rqst.rq_nvec = 2; + rqst.rq_nvec = 1; rqst.rq_pages = wdata->pages; rqst.rq_offset = wdata->page_offset; rqst.rq_npages = wdata->nr_pages; @@ -3153,7 +3347,7 @@ smb2_async_writev(struct cifs_writedata *wdata, rqst.rq_tailsz = wdata->tailsz; #ifdef CONFIG_CIFS_SMB_DIRECT if (wdata->mr) { - iov[1].iov_len += sizeof(struct smbd_buffer_descriptor_v1); + iov[0].iov_len += sizeof(struct smbd_buffer_descriptor_v1); rqst.rq_npages = 0; } #endif @@ -3210,6 +3404,7 @@ int SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms, unsigned int *nbytes, struct kvec *iov, int n_vec) { + struct smb_rqst rqst; int rc = 0; struct smb2_write_req *req = NULL; struct smb2_write_rsp *rsp = NULL; @@ -3251,7 +3446,11 @@ SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms, /* 1 for Buffer */ iov[0].iov_len = total_len - 1; - rc = smb2_send_recv(xid, io_parms->tcon->ses, iov, n_vec + 1, + memset(&rqst, 0, sizeof(struct smb_rqst)); + rqst.rq_iov = iov; + rqst.rq_nvec = n_vec + 1; + + rc = cifs_send_recv(xid, io_parms->tcon->ses, &rqst, &resp_buftype, flags, &rsp_iov); cifs_small_buf_release(req); rsp = (struct smb2_write_rsp *)rsp_iov.iov_base; @@ -3323,6 +3522,7 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, int index, struct cifs_search_info *srch_inf) { + struct smb_rqst rqst; struct smb2_query_directory_req *req; struct smb2_query_directory_rsp *rsp = NULL; struct kvec iov[2]; @@ -3395,7 +3595,11 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon, iov[1].iov_base = (char *)(req->Buffer); iov[1].iov_len = len; - rc = smb2_send_recv(xid, ses, iov, 2, &resp_buftype, flags, &rsp_iov); + memset(&rqst, 0, sizeof(struct smb_rqst)); + rqst.rq_iov = iov; + rqst.rq_nvec = 2; + + rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov); cifs_small_buf_release(req); rsp = (struct smb2_query_directory_rsp *)rsp_iov.iov_base; @@ -3454,6 +3658,7 @@ send_set_info(const unsigned int xid, struct cifs_tcon *tcon, u8 info_type, u32 additional_info, unsigned int num, void **data, unsigned int *size) { + struct smb_rqst rqst; struct smb2_set_info_req *req; struct smb2_set_info_rsp *rsp = NULL; struct kvec *iov; @@ -3509,7 +3714,11 @@ send_set_info(const unsigned int xid, struct cifs_tcon *tcon, iov[i].iov_len = size[i]; } - rc = smb2_send_recv(xid, ses, iov, num, &resp_buftype, flags, + memset(&rqst, 0, sizeof(struct smb_rqst)); + rqst.rq_iov = iov; + rqst.rq_nvec = num; + + rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov); cifs_small_buf_release(req); rsp = (struct smb2_set_info_rsp *)rsp_iov.iov_base; @@ -3664,6 +3873,7 @@ SMB2_oplock_break(const unsigned int xid, struct cifs_tcon *tcon, const u64 persistent_fid, const u64 volatile_fid, __u8 oplock_level) { + struct smb_rqst rqst; int rc; struct smb2_oplock_break *req = NULL; struct cifs_ses *ses = tcon->ses; @@ -3692,7 +3902,11 @@ SMB2_oplock_break(const unsigned int xid, struct cifs_tcon *tcon, iov[0].iov_base = (char *)req; iov[0].iov_len = total_len; - rc = smb2_send_recv(xid, ses, iov, 1, &resp_buf_type, flags, &rsp_iov); + memset(&rqst, 0, sizeof(struct smb_rqst)); + rqst.rq_iov = iov; + rqst.rq_nvec = 1; + + rc = cifs_send_recv(xid, ses, &rqst, &resp_buf_type, flags, &rsp_iov); cifs_small_buf_release(req); if (rc) { @@ -3755,6 +3969,7 @@ int SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, struct kstatfs *fsdata) { + struct smb_rqst rqst; struct smb2_query_info_rsp *rsp = NULL; struct kvec iov; struct kvec rsp_iov; @@ -3773,7 +3988,11 @@ SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon, if (smb3_encryption_required(tcon)) flags |= CIFS_TRANSFORM_REQ; - rc = smb2_send_recv(xid, ses, &iov, 1, &resp_buftype, flags, &rsp_iov); + memset(&rqst, 0, sizeof(struct smb_rqst)); + rqst.rq_iov = &iov; + rqst.rq_nvec = 1; + + rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov); cifs_small_buf_release(iov.iov_base); if (rc) { cifs_stats_fail_inc(tcon, SMB2_QUERY_INFO_HE); @@ -3798,6 +4017,7 @@ int SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, int level) { + struct smb_rqst rqst; struct smb2_query_info_rsp *rsp = NULL; struct kvec iov; struct kvec rsp_iov; @@ -3829,7 +4049,11 @@ SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon, if (smb3_encryption_required(tcon)) flags |= CIFS_TRANSFORM_REQ; - rc = smb2_send_recv(xid, ses, &iov, 1, &resp_buftype, flags, &rsp_iov); + memset(&rqst, 0, sizeof(struct smb_rqst)); + rqst.rq_iov = &iov; + rqst.rq_nvec = 1; + + rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov); cifs_small_buf_release(iov.iov_base); if (rc) { cifs_stats_fail_inc(tcon, SMB2_QUERY_INFO_HE); @@ -3868,6 +4092,7 @@ smb2_lockv(const unsigned int xid, struct cifs_tcon *tcon, const __u64 persist_fid, const __u64 volatile_fid, const __u32 pid, const __u32 num_lock, struct smb2_lock_element *buf) { + struct smb_rqst rqst; int rc = 0; struct smb2_lock_req *req = NULL; struct kvec iov[2]; @@ -3900,7 +4125,12 @@ smb2_lockv(const unsigned int xid, struct cifs_tcon *tcon, iov[1].iov_len = count; cifs_stats_inc(&tcon->stats.cifs_stats.num_locks); - rc = smb2_send_recv(xid, tcon->ses, iov, 2, &resp_buf_type, flags, + + memset(&rqst, 0, sizeof(struct smb_rqst)); + rqst.rq_iov = iov; + rqst.rq_nvec = 2; + + rc = cifs_send_recv(xid, tcon->ses, &rqst, &resp_buf_type, flags, &rsp_iov); cifs_small_buf_release(req); if (rc) { @@ -3934,6 +4164,7 @@ int SMB2_lease_break(const unsigned int xid, struct cifs_tcon *tcon, __u8 *lease_key, const __le32 lease_state) { + struct smb_rqst rqst; int rc; struct smb2_lease_ack *req = NULL; struct cifs_ses *ses = tcon->ses; @@ -3964,7 +4195,11 @@ SMB2_lease_break(const unsigned int xid, struct cifs_tcon *tcon, iov[0].iov_base = (char *)req; iov[0].iov_len = total_len; - rc = smb2_send_recv(xid, ses, iov, 1, &resp_buf_type, flags, &rsp_iov); + memset(&rqst, 0, sizeof(struct smb_rqst)); + rqst.rq_iov = iov; + rqst.rq_nvec = 1; + + rc = cifs_send_recv(xid, ses, &rqst, &resp_buf_type, flags, &rsp_iov); cifs_small_buf_release(req); if (rc) { diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index a345560001ce..824dddeee3f2 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -851,8 +851,11 @@ struct validate_negotiate_info_rsp { __le16 Dialect; /* Dialect in use for the connection */ } __packed; -#define RSS_CAPABLE 0x00000001 -#define RDMA_CAPABLE 0x00000002 +#define RSS_CAPABLE cpu_to_le32(0x00000001) +#define RDMA_CAPABLE cpu_to_le32(0x00000002) + +#define INTERNETWORK cpu_to_le16(0x0002) +#define INTERNETWORKV6 cpu_to_le16(0x0017) struct network_interface_info_ioctl_rsp { __le32 Next; /* next interface. zero if this is last one */ @@ -860,7 +863,21 @@ struct network_interface_info_ioctl_rsp { __le32 Capability; /* RSS or RDMA Capable */ __le32 Reserved; __le64 LinkSpeed; - char SockAddr_Storage[128]; + __le16 Family; + __u8 Buffer[126]; +} __packed; + +struct iface_info_ipv4 { + __be16 Port; + __be32 IPv4Address; + __be64 Reserved; +} __packed; + +struct iface_info_ipv6 { + __be16 Port; + __be32 FlowInfo; + __u8 IPv6Address[16]; + __be32 ScopeId; } __packed; #define NO_FILE_ID 0xFFFFFFFFFFFFFFFFULL /* general ioctls to srv not to file */ diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index c84020057bd8..3ae208ac2a77 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -79,6 +79,10 @@ extern int smb2_set_path_size(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_sb_info *cifs_sb, bool set_alloc); extern int smb2_set_file_info(struct inode *inode, const char *full_path, FILE_BASIC_INFO *buf, const unsigned int xid); +extern int smb311_posix_mkdir(const unsigned int xid, struct inode *inode, + umode_t mode, struct cifs_tcon *tcon, + const char *full_path, + struct cifs_sb_info *cifs_sb); extern int smb2_mkdir(const unsigned int xid, struct cifs_tcon *tcon, const char *name, struct cifs_sb_info *cifs_sb); extern void smb2_mkdir_setinfo(struct inode *inode, const char *full_path, @@ -109,6 +113,8 @@ extern int smb2_unlock_range(struct cifsFileInfo *cfile, extern int smb2_push_mandatory_locks(struct cifsFileInfo *cfile); extern void smb2_reconnect_server(struct work_struct *work); extern int smb3_crypto_aead_allocate(struct TCP_Server_Info *server); +extern unsigned long +smb2_rqst_len(struct smb_rqst *rqst, bool skip_rfc1002_marker); /* * SMB2 Worker functions - most of protocol specific implementation details diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c index 349d5ccf854c..51b9437c3c7b 100644 --- a/fs/cifs/smb2transport.c +++ b/fs/cifs/smb2transport.c @@ -171,9 +171,7 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) unsigned char smb2_signature[SMB2_HMACSHA256_SIZE]; unsigned char *sigptr = smb2_signature; struct kvec *iov = rqst->rq_iov; - int iov_hdr_index = rqst->rq_nvec > 1 ? 1 : 0; - struct smb2_sync_hdr *shdr = - (struct smb2_sync_hdr *)iov[iov_hdr_index].iov_base; + struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)iov[0].iov_base; struct cifs_ses *ses; ses = smb2_find_smb_ses(server, shdr->SessionId); @@ -204,7 +202,7 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) return rc; } - rc = __cifs_calc_signature(rqst, iov_hdr_index, server, sigptr, + rc = __cifs_calc_signature(rqst, server, sigptr, &server->secmech.sdeschmacsha256->shash); if (!rc) @@ -414,9 +412,7 @@ smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) unsigned char smb3_signature[SMB2_CMACAES_SIZE]; unsigned char *sigptr = smb3_signature; struct kvec *iov = rqst->rq_iov; - int iov_hdr_index = rqst->rq_nvec > 1 ? 1 : 0; - struct smb2_sync_hdr *shdr = - (struct smb2_sync_hdr *)iov[iov_hdr_index].iov_base; + struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)iov[0].iov_base; struct cifs_ses *ses; ses = smb2_find_smb_ses(server, shdr->SessionId); @@ -447,7 +443,7 @@ smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) return rc; } - rc = __cifs_calc_signature(rqst, iov_hdr_index, server, sigptr, + rc = __cifs_calc_signature(rqst, server, sigptr, &server->secmech.sdesccmacaes->shash); if (!rc) @@ -462,7 +458,7 @@ smb2_sign_rqst(struct smb_rqst *rqst, struct TCP_Server_Info *server) { int rc = 0; struct smb2_sync_hdr *shdr = - (struct smb2_sync_hdr *)rqst->rq_iov[1].iov_base; + (struct smb2_sync_hdr *)rqst->rq_iov[0].iov_base; if (!(shdr->Flags & SMB2_FLAGS_SIGNED) || server->tcpStatus == CifsNeedNegotiate) @@ -635,7 +631,7 @@ smb2_setup_request(struct cifs_ses *ses, struct smb_rqst *rqst) { int rc; struct smb2_sync_hdr *shdr = - (struct smb2_sync_hdr *)rqst->rq_iov[1].iov_base; + (struct smb2_sync_hdr *)rqst->rq_iov[0].iov_base; struct mid_q_entry *mid; smb2_seq_num_into_buf(ses->server, shdr); @@ -656,7 +652,7 @@ smb2_setup_async_request(struct TCP_Server_Info *server, struct smb_rqst *rqst) { int rc; struct smb2_sync_hdr *shdr = - (struct smb2_sync_hdr *)rqst->rq_iov[1].iov_base; + (struct smb2_sync_hdr *)rqst->rq_iov[0].iov_base; struct mid_q_entry *mid; smb2_seq_num_into_buf(server, shdr); diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c index e459c97151b3..6fd94d9ffac2 100644 --- a/fs/cifs/smbdirect.c +++ b/fs/cifs/smbdirect.c @@ -18,6 +18,7 @@ #include "smbdirect.h" #include "cifs_debug.h" #include "cifsproto.h" +#include "smb2proto.h" static struct smbd_response *get_empty_queue_buffer( struct smbd_connection *info); @@ -2087,7 +2088,7 @@ int smbd_send(struct smbd_connection *info, struct smb_rqst *rqst) struct kvec vec; int nvecs; int size; - unsigned int buflen = 0, remaining_data_length; + unsigned int buflen, remaining_data_length; int start, i, j; int max_iov_size = info->max_send_size - sizeof(struct smbd_data_transfer); @@ -2111,25 +2112,13 @@ int smbd_send(struct smbd_connection *info, struct smb_rqst *rqst) log_write(ERR, "expected the pdu length in 1st iov, but got %zu\n", rqst->rq_iov[0].iov_len); return -EINVAL; } - iov = &rqst->rq_iov[1]; - - /* total up iov array first */ - for (i = 0; i < rqst->rq_nvec-1; i++) { - buflen += iov[i].iov_len; - } /* * Add in the page array if there is one. The caller needs to set * rq_tailsz to PAGE_SIZE when the buffer has multiple pages and * ends at page boundary */ - if (rqst->rq_npages) { - if (rqst->rq_npages == 1) - buflen += rqst->rq_tailsz; - else - buflen += rqst->rq_pagesz * (rqst->rq_npages - 1) - - rqst->rq_offset + rqst->rq_tailsz; - } + buflen = smb2_rqst_len(rqst, true); if (buflen + sizeof(struct smbd_data_transfer) > info->max_fragmented_send_size) { @@ -2139,6 +2128,8 @@ int smbd_send(struct smbd_connection *info, struct smb_rqst *rqst) goto done; } + iov = &rqst->rq_iov[1]; + cifs_dbg(FYI, "Sending smb (RDMA): smb_len=%u\n", buflen); for (i = 0; i < rqst->rq_nvec-1; i++) dump_smb(iov[i].iov_base, iov[i].iov_len); diff --git a/fs/cifs/trace.h b/fs/cifs/trace.h index 61e74d455d90..67e413f6ee4d 100644 --- a/fs/cifs/trace.h +++ b/fs/cifs/trace.h @@ -378,7 +378,7 @@ DEFINE_EVENT(smb3_open_err_class, smb3_##name, \ TP_ARGS(xid, tid, sesid, create_options, desired_access, rc)) DEFINE_SMB3_OPEN_ERR_EVENT(open_err); - +DEFINE_SMB3_OPEN_ERR_EVENT(posix_mkdir_err); DECLARE_EVENT_CLASS(smb3_open_done_class, TP_PROTO(unsigned int xid, @@ -420,6 +420,7 @@ DEFINE_EVENT(smb3_open_done_class, smb3_##name, \ TP_ARGS(xid, fid, tid, sesid, create_options, desired_access)) DEFINE_SMB3_OPEN_DONE_EVENT(open_done); +DEFINE_SMB3_OPEN_DONE_EVENT(posix_mkdir_done); #endif /* _CIFS_TRACE_H */ diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 1f1a68f89110..fb57dfbfb749 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -201,15 +201,24 @@ smb_send_kvec(struct TCP_Server_Info *server, struct msghdr *smb_msg, return 0; } -static unsigned long -rqst_len(struct smb_rqst *rqst) +unsigned long +smb2_rqst_len(struct smb_rqst *rqst, bool skip_rfc1002_marker) { unsigned int i; - struct kvec *iov = rqst->rq_iov; + struct kvec *iov; + int nvec; unsigned long buflen = 0; + if (skip_rfc1002_marker && rqst->rq_iov[0].iov_len == 4) { + iov = &rqst->rq_iov[1]; + nvec = rqst->rq_nvec - 1; + } else { + iov = rqst->rq_iov; + nvec = rqst->rq_nvec; + } + /* total up iov array first */ - for (i = 0; i < rqst->rq_nvec; i++) + for (i = 0; i < nvec; i++) buflen += iov[i].iov_len; /* @@ -236,18 +245,20 @@ rqst_len(struct smb_rqst *rqst) } static int -__smb_send_rqst(struct TCP_Server_Info *server, struct smb_rqst *rqst) +__smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, + struct smb_rqst *rqst) { - int rc; - struct kvec *iov = rqst->rq_iov; - int n_vec = rqst->rq_nvec; - unsigned int smb_buf_length = get_rfc1002_length(iov[0].iov_base); - unsigned long send_length; - unsigned int i; + int rc = 0; + struct kvec *iov; + int n_vec; + unsigned int send_length = 0; + unsigned int i, j; size_t total_len = 0, sent, size; struct socket *ssocket = server->ssocket; struct msghdr smb_msg; int val = 1; + __be32 rfc1002_marker; + if (cifs_rdma_enabled(server) && server->smbd_conn) { rc = smbd_send(server->smbd_conn, rqst); goto smbd_done; @@ -255,51 +266,67 @@ __smb_send_rqst(struct TCP_Server_Info *server, struct smb_rqst *rqst) if (ssocket == NULL) return -ENOTSOCK; - /* sanity check send length */ - send_length = rqst_len(rqst); - if (send_length != smb_buf_length + 4) { - WARN(1, "Send length mismatch(send_length=%lu smb_buf_length=%u)\n", - send_length, smb_buf_length); - return -EIO; - } - - if (n_vec < 2) - return -EIO; - - cifs_dbg(FYI, "Sending smb: smb_len=%u\n", smb_buf_length); - dump_smb(iov[0].iov_base, iov[0].iov_len); - dump_smb(iov[1].iov_base, iov[1].iov_len); - /* cork the socket */ kernel_setsockopt(ssocket, SOL_TCP, TCP_CORK, (char *)&val, sizeof(val)); - size = 0; - for (i = 0; i < n_vec; i++) - size += iov[i].iov_len; + for (j = 0; j < num_rqst; j++) + send_length += smb2_rqst_len(&rqst[j], true); + rfc1002_marker = cpu_to_be32(send_length); - iov_iter_kvec(&smb_msg.msg_iter, WRITE | ITER_KVEC, iov, n_vec, size); + /* Generate a rfc1002 marker for SMB2+ */ + if (server->vals->header_preamble_size == 0) { + struct kvec hiov = { + .iov_base = &rfc1002_marker, + .iov_len = 4 + }; + iov_iter_kvec(&smb_msg.msg_iter, WRITE | ITER_KVEC, &hiov, + 1, 4); + rc = smb_send_kvec(server, &smb_msg, &sent); + if (rc < 0) + goto uncork; - rc = smb_send_kvec(server, &smb_msg, &sent); - if (rc < 0) - goto uncork; + total_len += sent; + send_length += 4; + } - total_len += sent; + cifs_dbg(FYI, "Sending smb: smb_len=%u\n", send_length); - /* now walk the page array and send each page in it */ - for (i = 0; i < rqst->rq_npages; i++) { - struct bio_vec bvec; + for (j = 0; j < num_rqst; j++) { + iov = rqst[j].rq_iov; + n_vec = rqst[j].rq_nvec; - bvec.bv_page = rqst->rq_pages[i]; - rqst_page_get_length(rqst, i, &bvec.bv_len, &bvec.bv_offset); + size = 0; + for (i = 0; i < n_vec; i++) { + dump_smb(iov[i].iov_base, iov[i].iov_len); + size += iov[i].iov_len; + } + + iov_iter_kvec(&smb_msg.msg_iter, WRITE | ITER_KVEC, + iov, n_vec, size); - iov_iter_bvec(&smb_msg.msg_iter, WRITE | ITER_BVEC, - &bvec, 1, bvec.bv_len); rc = smb_send_kvec(server, &smb_msg, &sent); if (rc < 0) - break; + goto uncork; total_len += sent; + + /* now walk the page array and send each page in it */ + for (i = 0; i < rqst[j].rq_npages; i++) { + struct bio_vec bvec; + + bvec.bv_page = rqst[j].rq_pages[i]; + rqst_page_get_length(&rqst[j], i, &bvec.bv_len, + &bvec.bv_offset); + + iov_iter_bvec(&smb_msg.msg_iter, WRITE | ITER_BVEC, + &bvec, 1, bvec.bv_len); + rc = smb_send_kvec(server, &smb_msg, &sent); + if (rc < 0) + break; + + total_len += sent; + } } uncork: @@ -308,9 +335,9 @@ uncork: kernel_setsockopt(ssocket, SOL_TCP, TCP_CORK, (char *)&val, sizeof(val)); - if ((total_len > 0) && (total_len != smb_buf_length + 4)) { + if ((total_len > 0) && (total_len != send_length)) { cifs_dbg(FYI, "partial send (wanted=%u sent=%zu): terminating session\n", - smb_buf_length + 4, total_len); + send_length, total_len); /* * If we have only sent part of an SMB then the next SMB could * be taken as the remainder of this one. We need to kill the @@ -335,7 +362,7 @@ smb_send_rqst(struct TCP_Server_Info *server, struct smb_rqst *rqst, int flags) int rc; if (!(flags & CIFS_TRANSFORM_REQ)) - return __smb_send_rqst(server, rqst); + return __smb_send_rqst(server, 1, rqst); if (!server->ops->init_transform_rq || !server->ops->free_transform_rq) { @@ -347,7 +374,7 @@ smb_send_rqst(struct TCP_Server_Info *server, struct smb_rqst *rqst, int flags) if (rc) return rc; - rc = __smb_send_rqst(server, &cur_rqst); + rc = __smb_send_rqst(server, 1, &cur_rqst); server->ops->free_transform_rq(&cur_rqst); return rc; } @@ -365,7 +392,7 @@ smb_send(struct TCP_Server_Info *server, struct smb_hdr *smb_buffer, iov[1].iov_base = (char *)smb_buffer + 4; iov[1].iov_len = smb_buf_length; - return __smb_send_rqst(server, &rqst); + return __smb_send_rqst(server, 1, &rqst); } static int @@ -730,7 +757,6 @@ cifs_send_recv(const unsigned int xid, struct cifs_ses *ses, * to the same server. We may make this configurable later or * use ses->maxReq. */ - rc = wait_for_free_request(ses->server, timeout, optype); if (rc) return rc; @@ -766,8 +792,8 @@ cifs_send_recv(const unsigned int xid, struct cifs_ses *ses, #ifdef CONFIG_CIFS_SMB311 if ((ses->status == CifsNew) || (optype & CIFS_NEG_OP)) - smb311_update_preauth_hash(ses, rqst->rq_iov+1, - rqst->rq_nvec-1); + smb311_update_preauth_hash(ses, rqst->rq_iov, + rqst->rq_nvec); #endif if (timeout == CIFS_ASYNC_OP) @@ -812,8 +838,8 @@ cifs_send_recv(const unsigned int xid, struct cifs_ses *ses, #ifdef CONFIG_CIFS_SMB311 if ((ses->status == CifsNew) || (optype & CIFS_NEG_OP)) { struct kvec iov = { - .iov_base = buf, - .iov_len = midQ->resp_buf_size + .iov_base = resp_iov->iov_base, + .iov_len = resp_iov->iov_len }; smb311_update_preauth_hash(ses, &iov, 1); } @@ -872,49 +898,6 @@ SendReceive2(const unsigned int xid, struct cifs_ses *ses, return rc; } -/* Like SendReceive2 but iov[0] does not contain an rfc1002 header */ -int -smb2_send_recv(const unsigned int xid, struct cifs_ses *ses, - struct kvec *iov, int n_vec, int *resp_buf_type /* ret */, - const int flags, struct kvec *resp_iov) -{ - struct smb_rqst rqst; - struct kvec s_iov[CIFS_MAX_IOV_SIZE], *new_iov; - int rc; - int i; - __u32 count; - __be32 rfc1002_marker; - - if (n_vec + 1 > CIFS_MAX_IOV_SIZE) { - new_iov = kmalloc_array(n_vec + 1, sizeof(struct kvec), - GFP_KERNEL); - if (!new_iov) - return -ENOMEM; - } else - new_iov = s_iov; - - /* 1st iov is an RFC1002 Session Message length */ - memcpy(new_iov + 1, iov, (sizeof(struct kvec) * n_vec)); - - count = 0; - for (i = 1; i < n_vec + 1; i++) - count += new_iov[i].iov_len; - - rfc1002_marker = cpu_to_be32(count); - - new_iov[0].iov_base = &rfc1002_marker; - new_iov[0].iov_len = 4; - - memset(&rqst, 0, sizeof(struct smb_rqst)); - rqst.rq_iov = new_iov; - rqst.rq_nvec = n_vec + 1; - - rc = cifs_send_recv(xid, ses, &rqst, resp_buf_type, flags, resp_iov); - if (n_vec + 1 > CIFS_MAX_IOV_SIZE) - kfree(new_iov); - return rc; -} - int SendReceive(const unsigned int xid, struct cifs_ses *ses, struct smb_hdr *in_buf, struct smb_hdr *out_buf, diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index cc40802ddfa8..00e759f05161 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -748,7 +748,6 @@ extern void ext2_free_blocks (struct inode *, unsigned long, unsigned long); extern unsigned long ext2_count_free_blocks (struct super_block *); extern unsigned long ext2_count_dirs (struct super_block *); -extern void ext2_check_blocks_bitmap (struct super_block *); extern struct ext2_group_desc * ext2_get_group_desc(struct super_block * sb, unsigned int block_group, struct buffer_head ** bh); @@ -771,7 +770,6 @@ extern void ext2_set_link(struct inode *, struct ext2_dir_entry_2 *, struct page extern struct inode * ext2_new_inode (struct inode *, umode_t, const struct qstr *); extern void ext2_free_inode (struct inode *); extern unsigned long ext2_count_free_inodes (struct super_block *); -extern void ext2_check_inodes_bitmap (struct super_block *); extern unsigned long ext2_count_free (struct buffer_head *, unsigned); /* inode.c */ diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 25ab1274090f..8ff53f8da3bc 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -557,6 +557,9 @@ static int parse_options(char *options, struct super_block *sb, set_opt (opts->s_mount_opt, NO_UID32); break; case Opt_nocheck: + ext2_msg(sb, KERN_WARNING, + "Option nocheck/check=none is deprecated and" + " will be removed in June 2020."); clear_opt (opts->s_mount_opt, CHECK); break; case Opt_debug: @@ -1335,9 +1338,6 @@ static int ext2_remount (struct super_block * sb, int * flags, char * data) new_opts.s_resgid = sbi->s_resgid; spin_unlock(&sbi->s_lock); - /* - * Allow the "check" option to be passed as a remount option. - */ if (!parse_options(data, sb, &new_opts)) return -EINVAL; diff --git a/fs/jfs/xattr.c b/fs/jfs/xattr.c index c60f3d32ee91..a6797986b625 100644 --- a/fs/jfs/xattr.c +++ b/fs/jfs/xattr.c @@ -491,15 +491,17 @@ static int ea_get(struct inode *inode, struct ea_buffer *ea_buf, int min_size) if (size > PSIZE) { /* * To keep the rest of the code simple. Allocate a - * contiguous buffer to work with + * contiguous buffer to work with. Make the buffer large + * enough to make use of the whole extent. */ - ea_buf->xattr = kmalloc(size, GFP_KERNEL); + ea_buf->max_size = (size + sb->s_blocksize - 1) & + ~(sb->s_blocksize - 1); + + ea_buf->xattr = kmalloc(ea_buf->max_size, GFP_KERNEL); if (ea_buf->xattr == NULL) return -ENOMEM; ea_buf->flag = EA_MALLOC; - ea_buf->max_size = (size + sb->s_blocksize - 1) & - ~(sb->s_blocksize - 1); if (ea_size == 0) return 0; diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index bbd0465535eb..f033f3a69a3b 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -883,8 +883,10 @@ struct inode *nfs_delegation_find_inode(struct nfs_client *clp, rcu_read_lock(); list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) { res = nfs_delegation_find_inode_server(server, fhandle); - if (res != ERR_PTR(-ENOENT)) + if (res != ERR_PTR(-ENOENT)) { + rcu_read_unlock(); return res; + } } rcu_read_unlock(); return ERR_PTR(-ENOENT); diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index d4a07acad598..8f003792ccde 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -1243,17 +1243,18 @@ static int ff_layout_read_done_cb(struct rpc_task *task, hdr->ds_clp, hdr->lseg, hdr->pgio_mirror_idx); + clear_bit(NFS_IOHDR_RESEND_PNFS, &hdr->flags); + clear_bit(NFS_IOHDR_RESEND_MDS, &hdr->flags); switch (err) { case -NFS4ERR_RESET_TO_PNFS: if (ff_layout_choose_best_ds_for_read(hdr->lseg, hdr->pgio_mirror_idx + 1, &hdr->pgio_mirror_idx)) goto out_eagain; - ff_layout_read_record_layoutstats_done(task, hdr); - pnfs_read_resend_pnfs(hdr); + set_bit(NFS_IOHDR_RESEND_PNFS, &hdr->flags); return task->tk_status; case -NFS4ERR_RESET_TO_MDS: - ff_layout_reset_read(hdr); + set_bit(NFS_IOHDR_RESEND_MDS, &hdr->flags); return task->tk_status; case -EAGAIN: goto out_eagain; @@ -1403,6 +1404,10 @@ static void ff_layout_read_release(void *data) struct nfs_pgio_header *hdr = data; ff_layout_read_record_layoutstats_done(&hdr->task, hdr); + if (test_bit(NFS_IOHDR_RESEND_PNFS, &hdr->flags)) + pnfs_read_resend_pnfs(hdr); + else if (test_bit(NFS_IOHDR_RESEND_MDS, &hdr->flags)) + ff_layout_reset_read(hdr); pnfs_generic_rw_release(data); } @@ -1423,12 +1428,14 @@ static int ff_layout_write_done_cb(struct rpc_task *task, hdr->ds_clp, hdr->lseg, hdr->pgio_mirror_idx); + clear_bit(NFS_IOHDR_RESEND_PNFS, &hdr->flags); + clear_bit(NFS_IOHDR_RESEND_MDS, &hdr->flags); switch (err) { case -NFS4ERR_RESET_TO_PNFS: - ff_layout_reset_write(hdr, true); + set_bit(NFS_IOHDR_RESEND_PNFS, &hdr->flags); return task->tk_status; case -NFS4ERR_RESET_TO_MDS: - ff_layout_reset_write(hdr, false); + set_bit(NFS_IOHDR_RESEND_MDS, &hdr->flags); return task->tk_status; case -EAGAIN: return -EAGAIN; @@ -1575,6 +1582,10 @@ static void ff_layout_write_release(void *data) struct nfs_pgio_header *hdr = data; ff_layout_write_record_layoutstats_done(&hdr->task, hdr); + if (test_bit(NFS_IOHDR_RESEND_PNFS, &hdr->flags)) + ff_layout_reset_write(hdr, true); + else if (test_bit(NFS_IOHDR_RESEND_MDS, &hdr->flags)) + ff_layout_reset_write(hdr, false); pnfs_generic_rw_release(data); } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index ed45090e4df6..6dd146885da9 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3294,6 +3294,7 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data) struct nfs4_closedata *calldata = data; struct nfs4_state *state = calldata->state; struct inode *inode = calldata->inode; + struct pnfs_layout_hdr *lo; bool is_rdonly, is_wronly, is_rdwr; int call_close = 0; @@ -3337,6 +3338,12 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data) goto out_wait; } + lo = calldata->arg.lr_args ? calldata->arg.lr_args->layout : NULL; + if (lo && !pnfs_layout_is_valid(lo)) { + calldata->arg.lr_args = NULL; + calldata->res.lr_res = NULL; + } + if (calldata->arg.fmode == 0) task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_CLOSE]; @@ -5972,12 +5979,19 @@ static void nfs4_delegreturn_release(void *calldata) static void nfs4_delegreturn_prepare(struct rpc_task *task, void *data) { struct nfs4_delegreturndata *d_data; + struct pnfs_layout_hdr *lo; d_data = (struct nfs4_delegreturndata *)data; if (!d_data->lr.roc && nfs4_wait_on_layoutreturn(d_data->inode, task)) return; + lo = d_data->args.lr_args ? d_data->args.lr_args->layout : NULL; + if (lo && !pnfs_layout_is_valid(lo)) { + d_data->args.lr_args = NULL; + d_data->res.lr_res = NULL; + } + nfs4_setup_sequence(d_data->res.server->nfs_client, &d_data->args.seq_args, &d_data->res.seq_res, @@ -8650,6 +8664,8 @@ nfs4_layoutget_handle_exception(struct rpc_task *task, dprintk("--> %s tk_status => %d\n", __func__, -task->tk_status); + nfs4_sequence_free_slot(&lgp->res.seq_res); + switch (nfs4err) { case 0: goto out; @@ -8714,7 +8730,6 @@ nfs4_layoutget_handle_exception(struct rpc_task *task, goto out; } - nfs4_sequence_free_slot(&lgp->res.seq_res); err = nfs4_handle_exception(server, nfs4err, exception); if (!status) { if (exception->retry) @@ -8786,20 +8801,22 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, long *timeout) if (IS_ERR(task)) return ERR_CAST(task); status = rpc_wait_for_completion_task(task); - if (status == 0) { + if (status != 0) + goto out; + + /* if layoutp->len is 0, nfs4_layoutget_prepare called rpc_exit */ + if (task->tk_status < 0 || lgp->res.layoutp->len == 0) { status = nfs4_layoutget_handle_exception(task, lgp, &exception); *timeout = exception.timeout; - } - + } else + lseg = pnfs_layout_process(lgp); +out: trace_nfs4_layoutget(lgp->args.ctx, &lgp->args.range, &lgp->res.range, &lgp->res.stateid, status); - /* if layoutp->len is 0, nfs4_layoutget_prepare called rpc_exit */ - if (status == 0 && lgp->res.layoutp->len) - lseg = pnfs_layout_process(lgp); rpc_put_task(task); dprintk("<-- %s status=%d\n", __func__, status); if (status) @@ -8817,6 +8834,8 @@ nfs4_layoutreturn_prepare(struct rpc_task *task, void *calldata) &lrp->args.seq_args, &lrp->res.seq_res, task); + if (!pnfs_layout_is_valid(lrp->args.layout)) + rpc_exit(task, 0); } static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata) diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index a8f5e6b16749..3fe81424337d 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -801,6 +801,11 @@ static inline void nfs4_lgopen_release(struct nfs4_layoutget *lgp) { } +static inline bool pnfs_layout_is_valid(const struct pnfs_layout_hdr *lo) +{ + return false; +} + #endif /* CONFIG_NFS_V4_1 */ #if IS_ENABLED(CONFIG_NFS_V4_2) diff --git a/fs/proc/base.c b/fs/proc/base.c index b6572944efc3..aaffc0c30216 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -235,6 +235,10 @@ static ssize_t get_mm_cmdline(struct mm_struct *mm, char __user *buf, if (env_start != arg_end || env_start >= env_end) env_start = env_end = arg_end; + /* .. and limit it to a maximum of one page of slop */ + if (env_end >= arg_end + PAGE_SIZE) + env_end = arg_end + PAGE_SIZE - 1; + /* We're not going to care if "*ppos" has high bits set */ pos = arg_start + *ppos; @@ -254,10 +258,19 @@ static ssize_t get_mm_cmdline(struct mm_struct *mm, char __user *buf, while (count) { int got; size_t size = min_t(size_t, PAGE_SIZE, count); + long offset; - got = access_remote_vm(mm, pos, page, size, FOLL_ANON); - if (got <= 0) + /* + * Are we already starting past the official end? + * We always include the last byte that is *supposed* + * to be NUL + */ + offset = (pos >= arg_end) ? pos - arg_end + 1 : 0; + + got = access_remote_vm(mm, pos - offset, page, size + offset, FOLL_ANON); + if (got <= offset) break; + got -= offset; /* Don't walk past a NUL character once you hit arg_end */ if (pos + got >= arg_end) { @@ -276,12 +289,17 @@ static ssize_t get_mm_cmdline(struct mm_struct *mm, char __user *buf, n = arg_end - pos - 1; /* Cut off at first NUL after 'n' */ - got = n + strnlen(page+n, got-n); - if (!got) + got = n + strnlen(page+n, offset+got-n); + if (got < offset) break; + got -= offset; + + /* Include the NUL if it existed */ + if (got < size) + got++; } - got -= copy_to_user(buf, page, got); + got -= copy_to_user(buf, page+offset, got); if (unlikely(!got)) { if (!len) len = -EFAULT; diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index d88231e3b2be..fc20e06c56ba 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -711,21 +711,18 @@ EXPORT_SYMBOL(dquot_quota_sync); static unsigned long dqcache_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) { - struct list_head *head; struct dquot *dquot; unsigned long freed = 0; spin_lock(&dq_list_lock); - head = free_dquots.prev; - while (head != &free_dquots && sc->nr_to_scan) { - dquot = list_entry(head, struct dquot, dq_free); + while (!list_empty(&free_dquots) && sc->nr_to_scan) { + dquot = list_first_entry(&free_dquots, struct dquot, dq_free); remove_dquot_hash(dquot); remove_free_dquot(dquot); remove_inuse(dquot); do_destroy_dquot(dquot); sc->nr_to_scan--; freed++; - head = free_dquots.prev; } spin_unlock(&dq_list_lock); return freed; diff --git a/fs/udf/balloc.c b/fs/udf/balloc.c index 1b961b1d9699..fcda0fc97b90 100644 --- a/fs/udf/balloc.c +++ b/fs/udf/balloc.c @@ -533,8 +533,7 @@ static int udf_table_prealloc_blocks(struct super_block *sb, udf_write_aext(table, &epos, &eloc, (etype << 30) | elen, 1); } else - udf_delete_aext(table, epos, eloc, - (etype << 30) | elen); + udf_delete_aext(table, epos); } else { alloc_count = 0; } @@ -630,7 +629,7 @@ static udf_pblk_t udf_table_new_block(struct super_block *sb, if (goal_elen) udf_write_aext(table, &goal_epos, &goal_eloc, goal_elen, 1); else - udf_delete_aext(table, goal_epos, goal_eloc, goal_elen); + udf_delete_aext(table, goal_epos); brelse(goal_epos.bh); udf_add_free_space(sb, partition, -1); diff --git a/fs/udf/directory.c b/fs/udf/directory.c index 0a98a2369738..d9523013096f 100644 --- a/fs/udf/directory.c +++ b/fs/udf/directory.c @@ -141,10 +141,7 @@ struct fileIdentDesc *udf_fileident_read(struct inode *dir, loff_t *nf_pos, fibh->ebh->b_data, sizeof(struct fileIdentDesc) + fibh->soffset); - fi_len = (sizeof(struct fileIdentDesc) + - cfi->lengthFileIdent + - le16_to_cpu(cfi->lengthOfImpUse) + 3) & ~3; - + fi_len = udf_dir_entry_len(cfi); *nf_pos += fi_len - (fibh->eoffset - fibh->soffset); fibh->eoffset = fibh->soffset + fi_len; } else { @@ -152,6 +149,9 @@ struct fileIdentDesc *udf_fileident_read(struct inode *dir, loff_t *nf_pos, sizeof(struct fileIdentDesc)); } } + /* Got last entry outside of dir size - fs is corrupted! */ + if (*nf_pos > dir->i_size) + return NULL; return fi; } diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 7f39d17352c9..9915a58fbabd 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -1147,8 +1147,7 @@ static void udf_update_extents(struct inode *inode, struct kernel_long_ad *laarr if (startnum > endnum) { for (i = 0; i < (startnum - endnum); i++) - udf_delete_aext(inode, *epos, laarr[i].extLocation, - laarr[i].extLength); + udf_delete_aext(inode, *epos); } else if (startnum < endnum) { for (i = 0; i < (endnum - startnum); i++) { udf_insert_aext(inode, *epos, laarr[i].extLocation, @@ -2176,14 +2175,15 @@ static int8_t udf_insert_aext(struct inode *inode, struct extent_position epos, return (nelen >> 30); } -int8_t udf_delete_aext(struct inode *inode, struct extent_position epos, - struct kernel_lb_addr eloc, uint32_t elen) +int8_t udf_delete_aext(struct inode *inode, struct extent_position epos) { struct extent_position oepos; int adsize; int8_t etype; struct allocExtDesc *aed; struct udf_inode_info *iinfo; + struct kernel_lb_addr eloc; + uint32_t elen; if (epos.bh) { get_bh(epos.bh); diff --git a/fs/udf/namei.c b/fs/udf/namei.c index c586026508db..06f37ddd2997 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -351,8 +351,6 @@ static struct fileIdentDesc *udf_add_entry(struct inode *dir, loff_t f_pos; loff_t size = udf_ext0_offset(dir) + dir->i_size; int nfidlen; - uint8_t lfi; - uint16_t liu; udf_pblk_t block; struct kernel_lb_addr eloc; uint32_t elen = 0; @@ -383,7 +381,7 @@ static struct fileIdentDesc *udf_add_entry(struct inode *dir, namelen = 0; } - nfidlen = (sizeof(struct fileIdentDesc) + namelen + 3) & ~3; + nfidlen = ALIGN(sizeof(struct fileIdentDesc) + namelen, UDF_NAME_PAD); f_pos = udf_ext0_offset(dir); @@ -424,12 +422,8 @@ static struct fileIdentDesc *udf_add_entry(struct inode *dir, goto out_err; } - liu = le16_to_cpu(cfi->lengthOfImpUse); - lfi = cfi->lengthFileIdent; - if ((cfi->fileCharacteristics & FID_FILE_CHAR_DELETED) != 0) { - if (((sizeof(struct fileIdentDesc) + - liu + lfi + 3) & ~3) == nfidlen) { + if (udf_dir_entry_len(cfi) == nfidlen) { cfi->descTag.tagSerialNum = cpu_to_le16(1); cfi->fileVersionNum = cpu_to_le16(1); cfi->fileCharacteristics = 0; @@ -1201,9 +1195,7 @@ static int udf_rename(struct inode *old_dir, struct dentry *old_dentry, if (dir_fi) { dir_fi->icb.extLocation = cpu_to_lelb(UDF_I(new_dir)->i_location); - udf_update_tag((char *)dir_fi, - (sizeof(struct fileIdentDesc) + - le16_to_cpu(dir_fi->lengthOfImpUse) + 3) & ~3); + udf_update_tag((char *)dir_fi, udf_dir_entry_len(dir_fi)); if (old_iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) mark_inode_dirty(old_inode); else diff --git a/fs/udf/udfdecl.h b/fs/udf/udfdecl.h index bae311b59400..84c47dde4d26 100644 --- a/fs/udf/udfdecl.h +++ b/fs/udf/udfdecl.h @@ -132,6 +132,12 @@ struct inode *udf_find_metadata_inode_efe(struct super_block *sb, extern int udf_write_fi(struct inode *inode, struct fileIdentDesc *, struct fileIdentDesc *, struct udf_fileident_bh *, uint8_t *, uint8_t *); +static inline unsigned int udf_dir_entry_len(struct fileIdentDesc *cfi) +{ + return ALIGN(sizeof(struct fileIdentDesc) + + le16_to_cpu(cfi->lengthOfImpUse) + cfi->lengthFileIdent, + UDF_NAME_PAD); +} /* file.c */ extern long udf_ioctl(struct file *, unsigned int, unsigned long); @@ -167,8 +173,7 @@ extern int udf_add_aext(struct inode *, struct extent_position *, struct kernel_lb_addr *, uint32_t, int); extern void udf_write_aext(struct inode *, struct extent_position *, struct kernel_lb_addr *, uint32_t, int); -extern int8_t udf_delete_aext(struct inode *, struct extent_position, - struct kernel_lb_addr, uint32_t); +extern int8_t udf_delete_aext(struct inode *, struct extent_position); extern int8_t udf_next_aext(struct inode *, struct extent_position *, struct kernel_lb_addr *, uint32_t *, int); extern int8_t udf_current_aext(struct inode *, struct extent_position *, diff --git a/include/acpi/processor.h b/include/acpi/processor.h index 40a916efd7c0..1194a4c78d55 100644 --- a/include/acpi/processor.h +++ b/include/acpi/processor.h @@ -309,7 +309,7 @@ static inline void acpi_processor_ppc_exit(void) { return; } -static inline int acpi_processor_ppc_has_changed(struct acpi_processor *pr, +static inline void acpi_processor_ppc_has_changed(struct acpi_processor *pr, int event_flag) { static unsigned int printout = 1; @@ -320,7 +320,6 @@ static inline int acpi_processor_ppc_has_changed(struct acpi_processor *pr, "Consider compiling CPUfreq support into your kernel.\n"); printout = 0; } - return 0; } static inline int acpi_processor_get_bios_limit(int cpu, unsigned int *limit) { 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/atmdev.h b/include/linux/atmdev.h index 0c27515d2cf6..8124815eb121 100644 --- a/include/linux/atmdev.h +++ b/include/linux/atmdev.h @@ -214,6 +214,7 @@ struct atmphy_ops { struct atm_skb_data { struct atm_vcc *vcc; /* ATM VCC */ unsigned long atm_options; /* ATM layer options */ + unsigned int acct_truesize; /* truesize accounted to vcc */ }; #define VCC_HTABLE_SIZE 32 @@ -241,6 +242,20 @@ void vcc_insert_socket(struct sock *sk); void atm_dev_release_vccs(struct atm_dev *dev); +static inline void atm_account_tx(struct atm_vcc *vcc, struct sk_buff *skb) +{ + /* + * Because ATM skbs may not belong to a sock (and we don't + * necessarily want to), skb->truesize may be adjusted, + * escaping the hack in pskb_expand_head() which avoids + * doing so for some cases. So stash the value of truesize + * at the time we accounted it, and atm_pop_raw() can use + * that value later, in case it changes. + */ + refcount_add(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc); + ATM_SKB(skb)->acct_truesize = skb->truesize; + ATM_SKB(skb)->atm_options = vcc->atm_options; +} static inline void atm_force_charge(struct atm_vcc *vcc,int truesize) { 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/bpf.h b/include/linux/bpf.h index 995c3b1e59bf..7df32a3200f7 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -488,12 +488,15 @@ void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth); /* Map specifics */ struct xdp_buff; +struct sk_buff; struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key); void __dev_map_insert_ctx(struct bpf_map *map, u32 index); void __dev_map_flush(struct bpf_map *map); int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, struct net_device *dev_rx); +int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, + struct bpf_prog *xdp_prog); struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key); void __cpu_map_insert_ctx(struct bpf_map *map, u32 index); @@ -586,6 +589,15 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, return 0; } +struct sk_buff; + +static inline int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, + struct sk_buff *skb, + struct bpf_prog *xdp_prog) +{ + return 0; +} + static inline struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key) { diff --git a/include/linux/dma-contiguous.h b/include/linux/dma-contiguous.h index b67bf6ac907d..3c5a4cb3eb95 100644 --- a/include/linux/dma-contiguous.h +++ b/include/linux/dma-contiguous.h @@ -48,7 +48,7 @@ * CMA should not be used by the device drivers directly. It is * only a helper framework for dma-mapping subsystem. * - * For more information, see kernel-docs in drivers/base/dma-contiguous.c + * For more information, see kernel-docs in kernel/dma/contiguous.c */ #ifdef __KERNEL__ diff --git a/include/linux/filter.h b/include/linux/filter.h index 45fc0f5000d8..b615df57b7d5 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -19,6 +19,7 @@ #include <linux/cryptohash.h> #include <linux/set_memory.h> #include <linux/kallsyms.h> +#include <linux/if_vlan.h> #include <net/sch_generic.h> @@ -469,7 +470,8 @@ struct sock_fprog_kern { }; struct bpf_binary_header { - unsigned int pages; + u16 pages; + u16 locked:1; u8 image[]; }; @@ -671,15 +673,18 @@ bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default) #define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0])) -#ifdef CONFIG_ARCH_HAS_SET_MEMORY static inline void bpf_prog_lock_ro(struct bpf_prog *fp) { +#ifdef CONFIG_ARCH_HAS_SET_MEMORY fp->locked = 1; - WARN_ON_ONCE(set_memory_ro((unsigned long)fp, fp->pages)); + if (set_memory_ro((unsigned long)fp, fp->pages)) + fp->locked = 0; +#endif } static inline void bpf_prog_unlock_ro(struct bpf_prog *fp) { +#ifdef CONFIG_ARCH_HAS_SET_MEMORY if (fp->locked) { WARN_ON_ONCE(set_memory_rw((unsigned long)fp, fp->pages)); /* In case set_memory_rw() fails, we want to be the first @@ -687,34 +692,30 @@ static inline void bpf_prog_unlock_ro(struct bpf_prog *fp) */ fp->locked = 0; } +#endif } static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) { - WARN_ON_ONCE(set_memory_ro((unsigned long)hdr, hdr->pages)); -} - -static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr) -{ - WARN_ON_ONCE(set_memory_rw((unsigned long)hdr, hdr->pages)); -} -#else -static inline void bpf_prog_lock_ro(struct bpf_prog *fp) -{ -} - -static inline void bpf_prog_unlock_ro(struct bpf_prog *fp) -{ -} - -static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) -{ +#ifdef CONFIG_ARCH_HAS_SET_MEMORY + hdr->locked = 1; + if (set_memory_ro((unsigned long)hdr, hdr->pages)) + hdr->locked = 0; +#endif } static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr) { +#ifdef CONFIG_ARCH_HAS_SET_MEMORY + if (hdr->locked) { + WARN_ON_ONCE(set_memory_rw((unsigned long)hdr, hdr->pages)); + /* In case set_memory_rw() fails, we want to be the first + * to crash here instead of some random place later on. + */ + hdr->locked = 0; + } +#endif } -#endif /* CONFIG_ARCH_HAS_SET_MEMORY */ static inline struct bpf_binary_header * bpf_jit_binary_hdr(const struct bpf_prog *fp) @@ -725,6 +726,22 @@ bpf_jit_binary_hdr(const struct bpf_prog *fp) return (void *)addr; } +#ifdef CONFIG_ARCH_HAS_SET_MEMORY +static inline int bpf_prog_check_pages_ro_single(const struct bpf_prog *fp) +{ + if (!fp->locked) + return -ENOLCK; + if (fp->jited) { + const struct bpf_binary_header *hdr = bpf_jit_binary_hdr(fp); + + if (!hdr->locked) + return -ENOLCK; + } + + return 0; +} +#endif + int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap); static inline int sk_filter(struct sock *sk, struct sk_buff *skb) { @@ -786,6 +803,21 @@ static inline bool bpf_dump_raw_ok(void) struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len); +static inline int __xdp_generic_ok_fwd_dev(struct sk_buff *skb, + struct net_device *fwd) +{ + unsigned int len; + + if (unlikely(!(fwd->flags & IFF_UP))) + return -ENETDOWN; + + len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN; + if (skb->len > len) + return -EMSGSIZE; + + return 0; +} + /* The pair of xdp_do_redirect and xdp_do_flush_map MUST be called in the * same cpu context. Further for best results no more than a single map * for the do_redirect/do_flush pair should be used. This limitation is @@ -961,6 +993,9 @@ static inline void bpf_prog_kallsyms_del(struct bpf_prog *fp) } #endif /* CONFIG_BPF_JIT */ +void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp); +void bpf_prog_kallsyms_del_all(struct bpf_prog *fp); + #define BPF_ANC BIT(15) static inline bool bpf_needs_clear_a(const struct sock_filter *first) 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/mod_devicetable.h b/include/linux/mod_devicetable.h index 2014bd19f28e..96a71a648eed 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -501,6 +501,7 @@ enum dmi_field { DMI_PRODUCT_VERSION, DMI_PRODUCT_SERIAL, DMI_PRODUCT_UUID, + DMI_PRODUCT_SKU, DMI_PRODUCT_FAMILY, DMI_BOARD_VENDOR, DMI_BOARD_NAME, diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 9dee3c23895d..712eed156d09 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1438,6 +1438,8 @@ enum { NFS_IOHDR_EOF, NFS_IOHDR_REDO, NFS_IOHDR_STAT, + NFS_IOHDR_RESEND_PNFS, + NFS_IOHDR_RESEND_MDS, }; struct nfs_io_completion; 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/net/ip6_fib.h b/include/net/ip6_fib.h index 5cba71d2dc44..71b9043aa0e7 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -170,6 +170,7 @@ struct fib6_info { unused:3; struct fib6_nh fib6_nh; + struct rcu_head rcu; }; struct rt6_info { @@ -273,7 +274,7 @@ static inline void ip6_rt_put(struct rt6_info *rt) } struct fib6_info *fib6_info_alloc(gfp_t gfp_flags); -void fib6_info_destroy(struct fib6_info *f6i); +void fib6_info_destroy_rcu(struct rcu_head *head); static inline void fib6_info_hold(struct fib6_info *f6i) { @@ -283,7 +284,7 @@ static inline void fib6_info_hold(struct fib6_info *f6i) static inline void fib6_info_release(struct fib6_info *f6i) { if (f6i && atomic_dec_and_test(&f6i->fib6_ref)) - fib6_info_destroy(f6i); + call_rcu(&f6i->rcu, fib6_info_destroy_rcu); } enum fib6_walk_state { diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 4c6241bc2039..6c003995347a 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -3391,11 +3391,14 @@ int ib_process_cq_direct(struct ib_cq *cq, int budget); * * Users can examine the cq structure to determine the actual CQ size. */ -struct ib_cq *ib_create_cq(struct ib_device *device, - ib_comp_handler comp_handler, - void (*event_handler)(struct ib_event *, void *), - void *cq_context, - const struct ib_cq_init_attr *cq_attr); +struct ib_cq *__ib_create_cq(struct ib_device *device, + ib_comp_handler comp_handler, + void (*event_handler)(struct ib_event *, void *), + void *cq_context, + const struct ib_cq_init_attr *cq_attr, + const char *caller); +#define ib_create_cq(device, cmp_hndlr, evt_hndlr, cq_ctxt, cq_attr) \ + __ib_create_cq((device), (cmp_hndlr), (evt_hndlr), (cq_ctxt), (cq_attr), KBUILD_MODNAME) /** * ib_resize_cq - Modifies the capacity of the CQ. 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/init/Kconfig b/init/Kconfig index 5a52f07259a2..fde3d09e8b27 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1719,10 +1719,6 @@ source "arch/Kconfig" endmenu # General setup -config HAVE_GENERIC_DMA_COHERENT - bool - default n - config RT_MUTEXES bool diff --git a/kernel/Makefile b/kernel/Makefile index d2001624fe7a..04bc07c2b42a 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -41,6 +41,7 @@ obj-y += printk/ obj-y += irq/ obj-y += rcu/ obj-y += livepatch/ +obj-y += dma/ obj-$(CONFIG_CHECKPOINT_RESTORE) += kcmp.o obj-$(CONFIG_FREEZER) += freezer.o diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 9f1493705f40..a9e6c04d0f4a 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -350,6 +350,20 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, return prog_adj; } +void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp) +{ + int i; + + for (i = 0; i < fp->aux->func_cnt; i++) + bpf_prog_kallsyms_del(fp->aux->func[i]); +} + +void bpf_prog_kallsyms_del_all(struct bpf_prog *fp) +{ + bpf_prog_kallsyms_del_subprogs(fp); + bpf_prog_kallsyms_del(fp); +} + #ifdef CONFIG_BPF_JIT /* All BPF JIT sysctl knobs here. */ int bpf_jit_enable __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_ALWAYS_ON); @@ -584,6 +598,8 @@ bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, bpf_fill_ill_insns(hdr, size); hdr->pages = size / PAGE_SIZE; + hdr->locked = 0; + hole = min_t(unsigned int, size - (proglen + sizeof(*hdr)), PAGE_SIZE - sizeof(*hdr)); start = (get_random_int() % hole) & ~(alignment - 1); @@ -1434,6 +1450,33 @@ static int bpf_check_tail_call(const struct bpf_prog *fp) return 0; } +static int bpf_prog_check_pages_ro_locked(const struct bpf_prog *fp) +{ +#ifdef CONFIG_ARCH_HAS_SET_MEMORY + int i, err; + + for (i = 0; i < fp->aux->func_cnt; i++) { + err = bpf_prog_check_pages_ro_single(fp->aux->func[i]); + if (err) + return err; + } + + return bpf_prog_check_pages_ro_single(fp); +#endif + return 0; +} + +static void bpf_prog_select_func(struct bpf_prog *fp) +{ +#ifndef CONFIG_BPF_JIT_ALWAYS_ON + u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1); + + fp->bpf_func = interpreters[(round_up(stack_depth, 32) / 32) - 1]; +#else + fp->bpf_func = __bpf_prog_ret0_warn; +#endif +} + /** * bpf_prog_select_runtime - select exec runtime for BPF program * @fp: bpf_prog populated with internal BPF program @@ -1444,13 +1487,13 @@ static int bpf_check_tail_call(const struct bpf_prog *fp) */ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) { -#ifndef CONFIG_BPF_JIT_ALWAYS_ON - u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1); + /* In case of BPF to BPF calls, verifier did all the prep + * work with regards to JITing, etc. + */ + if (fp->bpf_func) + goto finalize; - fp->bpf_func = interpreters[(round_up(stack_depth, 32) / 32) - 1]; -#else - fp->bpf_func = __bpf_prog_ret0_warn; -#endif + bpf_prog_select_func(fp); /* eBPF JITs can rewrite the program in case constant * blinding is active. However, in case of error during @@ -1471,6 +1514,8 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) if (*err) return fp; } + +finalize: bpf_prog_lock_ro(fp); /* The tail call compatibility check can only be done at @@ -1479,7 +1524,17 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) * all eBPF JITs might immediately support all features. */ *err = bpf_check_tail_call(fp); - + if (*err) + return fp; + + /* Checkpoint: at this point onwards any cBPF -> eBPF or + * native eBPF program is read-only. If we failed to change + * the page attributes (e.g. allocation failure from + * splitting large pages), then reject the whole program + * in order to guarantee not ending up with any W+X pages + * from BPF side in kernel. + */ + *err = bpf_prog_check_pages_ro_locked(fp); return fp; } EXPORT_SYMBOL_GPL(bpf_prog_select_runtime); diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index a7cc7b3494a9..642c97f6d1b8 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -345,6 +345,20 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, return bq_enqueue(dst, xdpf, dev_rx); } +int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, + struct bpf_prog *xdp_prog) +{ + int err; + + err = __xdp_generic_ok_fwd_dev(skb, dst->dev); + if (unlikely(err)) + return err; + skb->dev = dst->dev; + generic_xdp_tx(skb, xdp_prog); + + return 0; +} + static void *dev_map_lookup_elem(struct bpf_map *map, void *key) { struct bpf_dtab_netdev *obj = __dev_map_lookup_elem(map, *(u32 *)key); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 0fa20624707f..35dc466641f2 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1034,14 +1034,9 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu) static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock) { if (atomic_dec_and_test(&prog->aux->refcnt)) { - int i; - /* bpf_prog_free_id() must be called first */ bpf_prog_free_id(prog, do_idr_lock); - - for (i = 0; i < prog->aux->func_cnt; i++) - bpf_prog_kallsyms_del(prog->aux->func[i]); - bpf_prog_kallsyms_del(prog); + bpf_prog_kallsyms_del_all(prog); call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu); } @@ -1358,9 +1353,7 @@ static int bpf_prog_load(union bpf_attr *attr) if (err < 0) goto free_used_maps; - /* eBPF program is ready to be JITed */ - if (!prog->bpf_func) - prog = bpf_prog_select_runtime(prog, &err); + prog = bpf_prog_select_runtime(prog, &err); if (err < 0) goto free_used_maps; @@ -1384,6 +1377,7 @@ static int bpf_prog_load(union bpf_attr *attr) return err; free_used_maps: + bpf_prog_kallsyms_del_subprogs(prog); free_used_maps(prog->aux); free_prog: bpf_prog_uncharge_memlock(prog); diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig new file mode 100644 index 000000000000..9bd54304446f --- /dev/null +++ b/kernel/dma/Kconfig @@ -0,0 +1,50 @@ + +config HAS_DMA + bool + depends on !NO_DMA + default y + +config NEED_SG_DMA_LENGTH + bool + +config NEED_DMA_MAP_STATE + bool + +config ARCH_DMA_ADDR_T_64BIT + def_bool 64BIT || PHYS_ADDR_T_64BIT + +config HAVE_GENERIC_DMA_COHERENT + bool + +config ARCH_HAS_SYNC_DMA_FOR_DEVICE + bool + +config ARCH_HAS_SYNC_DMA_FOR_CPU + bool + select NEED_DMA_MAP_STATE + +config DMA_DIRECT_OPS + bool + depends on HAS_DMA + +config DMA_NONCOHERENT_OPS + bool + depends on HAS_DMA + select DMA_DIRECT_OPS + +config DMA_NONCOHERENT_MMAP + bool + depends on DMA_NONCOHERENT_OPS + +config DMA_NONCOHERENT_CACHE_SYNC + bool + depends on DMA_NONCOHERENT_OPS + +config DMA_VIRT_OPS + bool + depends on HAS_DMA + +config SWIOTLB + bool + select DMA_DIRECT_OPS + select NEED_DMA_MAP_STATE diff --git a/kernel/dma/Makefile b/kernel/dma/Makefile new file mode 100644 index 000000000000..6de44e4eb454 --- /dev/null +++ b/kernel/dma/Makefile @@ -0,0 +1,11 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-$(CONFIG_HAS_DMA) += mapping.o +obj-$(CONFIG_DMA_CMA) += contiguous.o +obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += coherent.o +obj-$(CONFIG_DMA_DIRECT_OPS) += direct.o +obj-$(CONFIG_DMA_NONCOHERENT_OPS) += noncoherent.o +obj-$(CONFIG_DMA_VIRT_OPS) += virt.o +obj-$(CONFIG_DMA_API_DEBUG) += debug.o +obj-$(CONFIG_SWIOTLB) += swiotlb.o + diff --git a/drivers/base/dma-coherent.c b/kernel/dma/coherent.c index 597d40893862..597d40893862 100644 --- a/drivers/base/dma-coherent.c +++ b/kernel/dma/coherent.c diff --git a/drivers/base/dma-contiguous.c b/kernel/dma/contiguous.c index d987dcd1bd56..d987dcd1bd56 100644 --- a/drivers/base/dma-contiguous.c +++ b/kernel/dma/contiguous.c diff --git a/lib/dma-debug.c b/kernel/dma/debug.c index c007d25bee09..c007d25bee09 100644 --- a/lib/dma-debug.c +++ b/kernel/dma/debug.c diff --git a/lib/dma-direct.c b/kernel/dma/direct.c index 8be8106270c2..8be8106270c2 100644 --- a/lib/dma-direct.c +++ b/kernel/dma/direct.c diff --git a/drivers/base/dma-mapping.c b/kernel/dma/mapping.c index f831a582209c..d2a92ddaac4d 100644 --- a/drivers/base/dma-mapping.c +++ b/kernel/dma/mapping.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * drivers/base/dma-mapping.c - arch-independent dma-mapping routines + * arch-independent dma-mapping routines * * Copyright (c) 2006 SUSE Linux Products GmbH * Copyright (c) 2006 Tejun Heo <teheo@suse.de> diff --git a/lib/dma-noncoherent.c b/kernel/dma/noncoherent.c index 79e9a757387f..79e9a757387f 100644 --- a/lib/dma-noncoherent.c +++ b/kernel/dma/noncoherent.c diff --git a/lib/swiotlb.c b/kernel/dma/swiotlb.c index 04b68d9dffac..04b68d9dffac 100644 --- a/lib/swiotlb.c +++ b/kernel/dma/swiotlb.c diff --git a/lib/dma-virt.c b/kernel/dma/virt.c index 8e61a02ef9ca..631ddec4b60a 100644 --- a/lib/dma-virt.c +++ b/kernel/dma/virt.c @@ -1,7 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 /* - * lib/dma-virt.c - * * DMA operations that map to virtual addresses without flushing memory. */ #include <linux/export.h> 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/Kconfig b/lib/Kconfig index e34b04b56057..706836ec314d 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -420,60 +420,15 @@ config HAS_IOPORT_MAP depends on HAS_IOMEM && !NO_IOPORT_MAP default y -config HAS_DMA - bool - depends on !NO_DMA - default y +source "kernel/dma/Kconfig" config SGL_ALLOC bool default n -config NEED_SG_DMA_LENGTH - bool - -config NEED_DMA_MAP_STATE - bool - -config ARCH_DMA_ADDR_T_64BIT - def_bool 64BIT || PHYS_ADDR_T_64BIT - config IOMMU_HELPER bool -config ARCH_HAS_SYNC_DMA_FOR_DEVICE - bool - -config ARCH_HAS_SYNC_DMA_FOR_CPU - bool - select NEED_DMA_MAP_STATE - -config DMA_DIRECT_OPS - bool - depends on HAS_DMA - -config DMA_NONCOHERENT_OPS - bool - depends on HAS_DMA - select DMA_DIRECT_OPS - -config DMA_NONCOHERENT_MMAP - bool - depends on DMA_NONCOHERENT_OPS - -config DMA_NONCOHERENT_CACHE_SYNC - bool - depends on DMA_NONCOHERENT_OPS - -config DMA_VIRT_OPS - bool - depends on HAS_DMA - -config SWIOTLB - bool - select DMA_DIRECT_OPS - select NEED_DMA_MAP_STATE - config CHECK_SIGNATURE bool diff --git a/lib/Makefile b/lib/Makefile index 956b320292fe..90dc5520b784 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -23,15 +23,12 @@ 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-$(CONFIG_PRINTK) += dump_stack.o lib-$(CONFIG_MMU) += ioremap.o lib-$(CONFIG_SMP) += cpumask.o -lib-$(CONFIG_DMA_DIRECT_OPS) += dma-direct.o -lib-$(CONFIG_DMA_NONCOHERENT_OPS) += dma-noncoherent.o -lib-$(CONFIG_DMA_VIRT_OPS) += dma-virt.o lib-y += kobject.o klist.o obj-y += lockref.o @@ -98,10 +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-$(CONFIG_CRC_CCITT) += crc-ccitt.o @@ -148,7 +141,6 @@ obj-$(CONFIG_SMP) += percpu_counter.o obj-$(CONFIG_AUDIT_GENERIC) += audit.o obj-$(CONFIG_AUDIT_COMPAT_GENERIC) += compat_audit.o -obj-$(CONFIG_SWIOTLB) += swiotlb.o obj-$(CONFIG_IOMMU_HELPER) += iommu-helper.o obj-$(CONFIG_FAULT_INJECTION) += fault-inject.o obj-$(CONFIG_NOTIFIER_ERROR_INJECTION) += notifier-error-inject.o @@ -169,8 +161,6 @@ obj-$(CONFIG_NLATTR) += nlattr.o obj-$(CONFIG_LRU_CACHE) += lru_cache.o -obj-$(CONFIG_DMA_API_DEBUG) += dma-debug.o - obj-$(CONFIG_GENERIC_CSUM) += checksum.o obj-$(CONFIG_GENERIC_ATOMIC64) += atomic64.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/mm/memblock.c b/mm/memblock.c index cc16d70b8333..03d48d8835ba 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -20,7 +20,6 @@ #include <linux/kmemleak.h> #include <linux/seq_file.h> #include <linux/memblock.h> -#include <linux/bootmem.h> #include <asm/sections.h> #include <linux/io.h> diff --git a/net/atm/br2684.c b/net/atm/br2684.c index 36b3adacc0dd..10462de734ea 100644 --- a/net/atm/br2684.c +++ b/net/atm/br2684.c @@ -252,8 +252,7 @@ static int br2684_xmit_vcc(struct sk_buff *skb, struct net_device *dev, ATM_SKB(skb)->vcc = atmvcc = brvcc->atmvcc; pr_debug("atm_skb(%p)->vcc(%p)->dev(%p)\n", skb, atmvcc, atmvcc->dev); - refcount_add(skb->truesize, &sk_atm(atmvcc)->sk_wmem_alloc); - ATM_SKB(skb)->atm_options = atmvcc->atm_options; + atm_account_tx(atmvcc, skb); dev->stats.tx_packets++; dev->stats.tx_bytes += skb->len; diff --git a/net/atm/clip.c b/net/atm/clip.c index 66caa48a27c2..d795b9c5aea4 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -381,8 +381,7 @@ static netdev_tx_t clip_start_xmit(struct sk_buff *skb, memcpy(here, llc_oui, sizeof(llc_oui)); ((__be16 *) here)[3] = skb->protocol; } - refcount_add(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc); - ATM_SKB(skb)->atm_options = vcc->atm_options; + atm_account_tx(vcc, skb); entry->vccs->last_use = jiffies; pr_debug("atm_skb(%p)->vcc(%p)->dev(%p)\n", skb, vcc, vcc->dev); old = xchg(&entry->vccs->xoff, 1); /* assume XOFF ... */ diff --git a/net/atm/common.c b/net/atm/common.c index 1f2af59935db..ff5748b2190f 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -630,10 +630,9 @@ int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t size) goto out; } pr_debug("%d += %d\n", sk_wmem_alloc_get(sk), skb->truesize); - refcount_add(skb->truesize, &sk->sk_wmem_alloc); + atm_account_tx(vcc, skb); skb->dev = NULL; /* for paths shared with net_device interfaces */ - ATM_SKB(skb)->atm_options = vcc->atm_options; if (!copy_from_iter_full(skb_put(skb, size), size, &m->msg_iter)) { kfree_skb(skb); error = -EFAULT; diff --git a/net/atm/lec.c b/net/atm/lec.c index 5a95fcf6f9b6..d7f5cf5b7594 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -182,9 +182,8 @@ lec_send(struct atm_vcc *vcc, struct sk_buff *skb) struct net_device *dev = skb->dev; ATM_SKB(skb)->vcc = vcc; - ATM_SKB(skb)->atm_options = vcc->atm_options; + atm_account_tx(vcc, skb); - refcount_add(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc); if (vcc->send(vcc, skb) < 0) { dev->stats.tx_dropped++; return; diff --git a/net/atm/mpc.c b/net/atm/mpc.c index 75620c2f2617..24b53c4c39c6 100644 --- a/net/atm/mpc.c +++ b/net/atm/mpc.c @@ -555,8 +555,7 @@ static int send_via_shortcut(struct sk_buff *skb, struct mpoa_client *mpc) sizeof(struct llc_snap_hdr)); } - refcount_add(skb->truesize, &sk_atm(entry->shortcut)->sk_wmem_alloc); - ATM_SKB(skb)->atm_options = entry->shortcut->atm_options; + atm_account_tx(entry->shortcut, skb); entry->shortcut->send(entry->shortcut, skb); entry->packets_fwded++; mpc->in_ops->put(entry); diff --git a/net/atm/pppoatm.c b/net/atm/pppoatm.c index 21d9d341a619..af8c4b38b746 100644 --- a/net/atm/pppoatm.c +++ b/net/atm/pppoatm.c @@ -350,8 +350,7 @@ static int pppoatm_send(struct ppp_channel *chan, struct sk_buff *skb) return 1; } - refcount_add(skb->truesize, &sk_atm(ATM_SKB(skb)->vcc)->sk_wmem_alloc); - ATM_SKB(skb)->atm_options = ATM_SKB(skb)->vcc->atm_options; + atm_account_tx(vcc, skb); pr_debug("atm_skb(%p)->vcc(%p)->dev(%p)\n", skb, ATM_SKB(skb)->vcc, ATM_SKB(skb)->vcc->dev); ret = ATM_SKB(skb)->vcc->send(ATM_SKB(skb)->vcc, skb) diff --git a/net/atm/raw.c b/net/atm/raw.c index ee10e8d46185..b3ba44aab0ee 100644 --- a/net/atm/raw.c +++ b/net/atm/raw.c @@ -35,8 +35,8 @@ static void atm_pop_raw(struct atm_vcc *vcc, struct sk_buff *skb) struct sock *sk = sk_atm(vcc); pr_debug("(%d) %d -= %d\n", - vcc->vci, sk_wmem_alloc_get(sk), skb->truesize); - WARN_ON(refcount_sub_and_test(skb->truesize, &sk->sk_wmem_alloc)); + vcc->vci, sk_wmem_alloc_get(sk), ATM_SKB(skb)->acct_truesize); + WARN_ON(refcount_sub_and_test(ATM_SKB(skb)->acct_truesize, &sk->sk_wmem_alloc)); dev_kfree_skb_any(skb); sk->sk_write_space(sk); } diff --git a/net/bpfilter/.gitignore b/net/bpfilter/.gitignore new file mode 100644 index 000000000000..e97084e3eea2 --- /dev/null +++ b/net/bpfilter/.gitignore @@ -0,0 +1 @@ +bpfilter_umh diff --git a/net/bpfilter/Makefile b/net/bpfilter/Makefile index e0bbe7583e58..dd86b022eff0 100644 --- a/net/bpfilter/Makefile +++ b/net/bpfilter/Makefile @@ -21,8 +21,10 @@ endif # which bpfilter_kern.c passes further into umh blob loader at run-time quiet_cmd_copy_umh = GEN $@ cmd_copy_umh = echo ':' > $(obj)/.bpfilter_umh.o.cmd; \ - $(OBJCOPY) -I binary -O `$(OBJDUMP) -f $<|grep format|cut -d' ' -f8` \ - -B `$(OBJDUMP) -f $<|grep architecture|cut -d, -f1|cut -d' ' -f2` \ + $(OBJCOPY) -I binary \ + `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 $< $@ $(obj)/bpfilter_umh.o: $(obj)/bpfilter_umh diff --git a/net/core/dev.c b/net/core/dev.c index 57b7bab5f70b..a5aa1c7444e6 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -8643,7 +8643,8 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char /* We get here if we can't use the current device name */ if (!pat) goto out; - if (dev_get_valid_name(net, dev, pat) < 0) + err = dev_get_valid_name(net, dev, pat); + if (err < 0) goto out; } @@ -8655,7 +8656,6 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char dev_close(dev); /* And unlink it from device chain */ - err = -ENODEV; unlist_netdevice(dev); synchronize_net(); diff --git a/net/core/filter.c b/net/core/filter.c index 3d9ba7e5965a..e7f12e9f598c 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3214,20 +3214,6 @@ err: } EXPORT_SYMBOL_GPL(xdp_do_redirect); -static int __xdp_generic_ok_fwd_dev(struct sk_buff *skb, struct net_device *fwd) -{ - unsigned int len; - - if (unlikely(!(fwd->flags & IFF_UP))) - return -ENETDOWN; - - len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN; - if (skb->len > len) - return -EMSGSIZE; - - return 0; -} - static int xdp_do_generic_redirect_map(struct net_device *dev, struct sk_buff *skb, struct xdp_buff *xdp, @@ -3256,10 +3242,11 @@ static int xdp_do_generic_redirect_map(struct net_device *dev, } if (map->map_type == BPF_MAP_TYPE_DEVMAP) { - if (unlikely((err = __xdp_generic_ok_fwd_dev(skb, fwd)))) + struct bpf_dtab_netdev *dst = fwd; + + err = dev_map_generic_redirect(dst, skb, xdp_prog); + if (unlikely(err)) goto err; - skb->dev = fwd; - generic_xdp_tx(skb, xdp_prog); } else if (map->map_type == BPF_MAP_TYPE_XSKMAP) { struct xdp_sock *xs = fwd; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 31ff46daae97..3647167c8fa3 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -243,9 +243,9 @@ static inline int compute_score(struct sock *sk, struct net *net, bool dev_match = (sk->sk_bound_dev_if == dif || sk->sk_bound_dev_if == sdif); - if (exact_dif && !dev_match) + if (!dev_match) return -1; - if (sk->sk_bound_dev_if && dev_match) + if (sk->sk_bound_dev_if) score += 4; } if (sk->sk_incoming_cpu == raw_smp_processor_id()) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index af5a830ff6ad..b3308e9d9762 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1145,7 +1145,8 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, cork->fragsize = ip_sk_use_pmtu(sk) ? dst_mtu(&rt->dst) : rt->dst.dev->mtu; - cork->gso_size = sk->sk_type == SOCK_DGRAM ? ipc->gso_size : 0; + cork->gso_size = sk->sk_type == SOCK_DGRAM && + sk->sk_protocol == IPPROTO_UDP ? ipc->gso_size : 0; cork->dst = &rt->dst; cork->length = 0; cork->ttl = ipc->ttl; diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 2febe26de6a1..595ad408dba0 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -113,9 +113,9 @@ static inline int compute_score(struct sock *sk, struct net *net, bool dev_match = (sk->sk_bound_dev_if == dif || sk->sk_bound_dev_if == sdif); - if (exact_dif && !dev_match) + if (!dev_match) return -1; - if (sk->sk_bound_dev_if && dev_match) + if (sk->sk_bound_dev_if) score++; } if (sk->sk_incoming_cpu == raw_smp_processor_id()) diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 39d1d487eca2..1fb2f3118d60 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -167,8 +167,9 @@ struct fib6_info *fib6_info_alloc(gfp_t gfp_flags) return f6i; } -void fib6_info_destroy(struct fib6_info *f6i) +void fib6_info_destroy_rcu(struct rcu_head *head) { + struct fib6_info *f6i = container_of(head, struct fib6_info, rcu); struct rt6_exception_bucket *bucket; struct dst_metrics *m; @@ -206,7 +207,7 @@ void fib6_info_destroy(struct fib6_info *f6i) kfree(f6i); } -EXPORT_SYMBOL_GPL(fib6_info_destroy); +EXPORT_SYMBOL_GPL(fib6_info_destroy_rcu); static struct fib6_node *node_alloc(struct net *net) { diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 021e5aef6ba3..a14fb4fcdf18 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1219,7 +1219,8 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork, if (mtu < IPV6_MIN_MTU) return -EINVAL; cork->base.fragsize = mtu; - cork->base.gso_size = sk->sk_type == SOCK_DGRAM ? ipc6->gso_size : 0; + cork->base.gso_size = sk->sk_type == SOCK_DGRAM && + sk->sk_protocol == IPPROTO_UDP ? ipc6->gso_size : 0; if (dst_allfrag(xfrm_dst_path(&rt->dst))) cork->base.flags |= IPCORK_ALLFRAG; diff --git a/net/ncsi/ncsi-aen.c b/net/ncsi/ncsi-aen.c index e7b05de1e6d1..25e483e8278b 100644 --- a/net/ncsi/ncsi-aen.c +++ b/net/ncsi/ncsi-aen.c @@ -73,8 +73,8 @@ static int ncsi_aen_handler_lsc(struct ncsi_dev_priv *ndp, ncm->data[2] = data; ncm->data[4] = ntohl(lsc->oem_status); - netdev_info(ndp->ndev.dev, "NCSI: LSC AEN - channel %u state %s\n", - nc->id, data & 0x1 ? "up" : "down"); + netdev_dbg(ndp->ndev.dev, "NCSI: LSC AEN - channel %u state %s\n", + nc->id, data & 0x1 ? "up" : "down"); chained = !list_empty(&nc->link); state = nc->state; @@ -148,9 +148,9 @@ static int ncsi_aen_handler_hncdsc(struct ncsi_dev_priv *ndp, hncdsc = (struct ncsi_aen_hncdsc_pkt *)h; ncm->data[3] = ntohl(hncdsc->status); spin_unlock_irqrestore(&nc->lock, flags); - netdev_printk(KERN_DEBUG, ndp->ndev.dev, - "NCSI: host driver %srunning on channel %u\n", - ncm->data[3] & 0x1 ? "" : "not ", nc->id); + netdev_dbg(ndp->ndev.dev, + "NCSI: host driver %srunning on channel %u\n", + ncm->data[3] & 0x1 ? "" : "not ", nc->id); return 0; } diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c index 5561e221b71f..091284760d21 100644 --- a/net/ncsi/ncsi-manage.c +++ b/net/ncsi/ncsi-manage.c @@ -788,8 +788,8 @@ static void ncsi_configure_channel(struct ncsi_dev_priv *ndp) } break; case ncsi_dev_state_config_done: - netdev_printk(KERN_DEBUG, ndp->ndev.dev, - "NCSI: channel %u config done\n", nc->id); + netdev_dbg(ndp->ndev.dev, "NCSI: channel %u config done\n", + nc->id); spin_lock_irqsave(&nc->lock, flags); if (nc->reconfigure_needed) { /* This channel's configuration has been updated @@ -804,8 +804,7 @@ static void ncsi_configure_channel(struct ncsi_dev_priv *ndp) list_add_tail_rcu(&nc->link, &ndp->channel_queue); spin_unlock_irqrestore(&ndp->lock, flags); - netdev_printk(KERN_DEBUG, dev, - "Dirty NCSI channel state reset\n"); + netdev_dbg(dev, "Dirty NCSI channel state reset\n"); ncsi_process_next_channel(ndp); break; } @@ -816,9 +815,9 @@ static void ncsi_configure_channel(struct ncsi_dev_priv *ndp) } else { hot_nc = NULL; nc->state = NCSI_CHANNEL_INACTIVE; - netdev_warn(ndp->ndev.dev, - "NCSI: channel %u link down after config\n", - nc->id); + netdev_dbg(ndp->ndev.dev, + "NCSI: channel %u link down after config\n", + nc->id); } spin_unlock_irqrestore(&nc->lock, flags); @@ -908,9 +907,9 @@ static int ncsi_choose_active_channel(struct ncsi_dev_priv *ndp) } ncm = &found->modes[NCSI_MODE_LINK]; - netdev_printk(KERN_DEBUG, ndp->ndev.dev, - "NCSI: Channel %u added to queue (link %s)\n", - found->id, ncm->data[2] & 0x1 ? "up" : "down"); + netdev_dbg(ndp->ndev.dev, + "NCSI: Channel %u added to queue (link %s)\n", + found->id, ncm->data[2] & 0x1 ? "up" : "down"); out: spin_lock_irqsave(&ndp->lock, flags); @@ -1199,14 +1198,14 @@ int ncsi_process_next_channel(struct ncsi_dev_priv *ndp) switch (old_state) { case NCSI_CHANNEL_INACTIVE: ndp->ndev.state = ncsi_dev_state_config; - netdev_info(ndp->ndev.dev, "NCSI: configuring channel %u\n", - nc->id); + netdev_dbg(ndp->ndev.dev, "NCSI: configuring channel %u\n", + nc->id); ncsi_configure_channel(ndp); break; case NCSI_CHANNEL_ACTIVE: ndp->ndev.state = ncsi_dev_state_suspend; - netdev_info(ndp->ndev.dev, "NCSI: suspending channel %u\n", - nc->id); + netdev_dbg(ndp->ndev.dev, "NCSI: suspending channel %u\n", + nc->id); ncsi_suspend_channel(ndp); break; default: @@ -1226,8 +1225,6 @@ out: return ncsi_choose_active_channel(ndp); } - netdev_printk(KERN_DEBUG, ndp->ndev.dev, - "NCSI: No more channels to process\n"); ncsi_report_link(ndp, false); return -ENODEV; } @@ -1318,9 +1315,9 @@ static int ncsi_kick_channels(struct ncsi_dev_priv *ndp) if ((ndp->ndev.state & 0xff00) == ncsi_dev_state_config || !list_empty(&nc->link)) { - netdev_printk(KERN_DEBUG, nd->dev, - "NCSI: channel %p marked dirty\n", - nc); + netdev_dbg(nd->dev, + "NCSI: channel %p marked dirty\n", + nc); nc->reconfigure_needed = true; } spin_unlock_irqrestore(&nc->lock, flags); @@ -1338,8 +1335,7 @@ static int ncsi_kick_channels(struct ncsi_dev_priv *ndp) list_add_tail_rcu(&nc->link, &ndp->channel_queue); spin_unlock_irqrestore(&ndp->lock, flags); - netdev_printk(KERN_DEBUG, nd->dev, - "NCSI: kicked channel %p\n", nc); + netdev_dbg(nd->dev, "NCSI: kicked channel %p\n", nc); n++; } } @@ -1370,8 +1366,8 @@ int ncsi_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) list_for_each_entry_rcu(vlan, &ndp->vlan_vids, list) { n_vids++; if (vlan->vid == vid) { - netdev_printk(KERN_DEBUG, dev, - "NCSI: vid %u already registered\n", vid); + netdev_dbg(dev, "NCSI: vid %u already registered\n", + vid); return 0; } } @@ -1390,7 +1386,7 @@ int ncsi_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) vlan->vid = vid; list_add_rcu(&vlan->list, &ndp->vlan_vids); - netdev_printk(KERN_DEBUG, dev, "NCSI: Added new vid %u\n", vid); + netdev_dbg(dev, "NCSI: Added new vid %u\n", vid); found = ncsi_kick_channels(ndp) != 0; @@ -1419,8 +1415,7 @@ int ncsi_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid) /* Remove the VLAN id from our internal list */ list_for_each_entry_safe(vlan, tmp, &ndp->vlan_vids, list) if (vlan->vid == vid) { - netdev_printk(KERN_DEBUG, dev, - "NCSI: vid %u found, removing\n", vid); + netdev_dbg(dev, "NCSI: vid %u found, removing\n", vid); list_del_rcu(&vlan->list); found = true; kfree(vlan); @@ -1547,7 +1542,7 @@ void ncsi_stop_dev(struct ncsi_dev *nd) } } - netdev_printk(KERN_DEBUG, ndp->ndev.dev, "NCSI: Stopping device\n"); + netdev_dbg(ndp->ndev.dev, "NCSI: Stopping device\n"); ncsi_report_link(ndp, true); } EXPORT_SYMBOL_GPL(ncsi_stop_dev); diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 8527cfdc446d..20d7d36b2fc9 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -415,7 +415,8 @@ static void tcf_ife_cleanup(struct tc_action *a) spin_unlock_bh(&ife->tcf_lock); p = rcu_dereference_protected(ife->params, 1); - kfree_rcu(p, rcu); + if (p) + kfree_rcu(p, rcu); } /* under ife->tcf_lock for existing action */ @@ -516,8 +517,6 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, saddr = nla_data(tb[TCA_IFE_SMAC]); } - ife->tcf_action = parm->action; - if (parm->flags & IFE_ENCODE) { if (daddr) ether_addr_copy(p->eth_dst, daddr); @@ -543,10 +542,8 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, NULL, NULL); if (err) { metadata_parse_err: - if (exists) - tcf_idr_release(*a, bind); if (ret == ACT_P_CREATED) - _tcf_ife_cleanup(*a); + tcf_idr_release(*a, bind); if (exists) spin_unlock_bh(&ife->tcf_lock); @@ -567,7 +564,7 @@ metadata_parse_err: err = use_all_metadata(ife); if (err) { if (ret == ACT_P_CREATED) - _tcf_ife_cleanup(*a); + tcf_idr_release(*a, bind); if (exists) spin_unlock_bh(&ife->tcf_lock); @@ -576,6 +573,7 @@ metadata_parse_err: } } + ife->tcf_action = parm->action; if (exists) spin_unlock_bh(&ife->tcf_lock); diff --git a/net/sched/sch_blackhole.c b/net/sched/sch_blackhole.c index c98a61e980ba..9c4c2bb547d7 100644 --- a/net/sched/sch_blackhole.c +++ b/net/sched/sch_blackhole.c @@ -21,7 +21,7 @@ static int blackhole_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { qdisc_drop(skb, sch, to_free); - return NET_XMIT_SUCCESS; + return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; } static struct sk_buff *blackhole_dequeue(struct Qdisc *sch) diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 3c85af058227..3fabf9f6a0f9 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -987,8 +987,6 @@ bool xprt_prepare_transmit(struct rpc_task *task) task->tk_status = -EAGAIN; goto out_unlock; } - if (!bc_prealloc(req) && !req->rq_xmit_bytes_sent) - req->rq_xid = xprt_alloc_xid(xprt); ret = true; out_unlock: spin_unlock_bh(&xprt->transport_lock); @@ -1298,7 +1296,12 @@ void xprt_retry_reserve(struct rpc_task *task) static inline __be32 xprt_alloc_xid(struct rpc_xprt *xprt) { - return (__force __be32)xprt->xid++; + __be32 xid; + + spin_lock(&xprt->reserve_lock); + xid = (__force __be32)xprt->xid++; + spin_unlock(&xprt->reserve_lock); + return xid; } static inline void xprt_init_xid(struct rpc_xprt *xprt) @@ -1316,6 +1319,7 @@ void xprt_request_init(struct rpc_task *task) req->rq_task = task; req->rq_xprt = xprt; req->rq_buffer = NULL; + req->rq_xid = xprt_alloc_xid(xprt); req->rq_connect_cookie = xprt->connect_cookie - 1; req->rq_bytes_sent = 0; req->rq_snd_buf.len = 0; diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 36919a254ba3..3b3410ada097 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -118,6 +118,9 @@ int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) u64 addr; int err; + if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index) + return -EINVAL; + if (!xskq_peek_addr(xs->umem->fq, &addr) || len > xs->umem->chunk_size_nohr) { xs->rx_dropped++; 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/bpf/bpftool/perf.c b/tools/bpf/bpftool/perf.c index ac6b1a12c9b7..b76b77dcfd1f 100644 --- a/tools/bpf/bpftool/perf.c +++ b/tools/bpf/bpftool/perf.c @@ -29,9 +29,10 @@ static bool has_perf_query_support(void) if (perf_query_supported) goto out; - fd = open(bin_name, O_RDONLY); + fd = open("/", O_RDONLY); if (fd < 0) { - p_err("perf_query_support: %s", strerror(errno)); + p_err("perf_query_support: cannot open directory \"/\" (%s)", + strerror(errno)); goto out; } diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index a4f435203fef..05f42a46d6ed 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -90,7 +90,9 @@ static void print_boot_time(__u64 nsecs, char *buf, unsigned int size) } wallclock_secs = (real_time_ts.tv_sec - boot_time_ts.tv_sec) + - nsecs / 1000000000; + (real_time_ts.tv_nsec - boot_time_ts.tv_nsec + nsecs) / + 1000000000; + if (!localtime_r(&wallclock_secs, &load_tm)) { snprintf(buf, size, "%llu", nsecs / 1000000000); 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/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8 index ca9ef7017624..d39e4ff7d0bf 100644 --- a/tools/power/x86/turbostat/turbostat.8 +++ b/tools/power/x86/turbostat/turbostat.8 @@ -56,7 +56,7 @@ name as necessary to disambiguate it from others is necessary. Note that option .PP \fB--hide column\fP do not show the specified built-in columns. May be invoked multiple times, or with a comma-separated list of column names. Use "--hide sysfs" to hide the sysfs statistics columns as a group. .PP -\fB--enable column\fP show the specified built-in columns, which are otherwise disabled, by default. Currently the only built-in counters disabled by default are "usec" and "Time_Of_Day_Seconds". +\fB--enable column\fP show the specified built-in columns, which are otherwise disabled, by default. Currently the only built-in counters disabled by default are "usec", "Time_Of_Day_Seconds", "APIC" and "X2APIC". The column name "all" can be used to enable all disabled-by-default built-in counters. .PP \fB--show column\fP show only the specified built-in columns. May be invoked multiple times, or with a comma-separated list of column names. Use "--show sysfs" to show the sysfs statistics columns as a group. diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index d6cff3070ebd..4d14bbbf9b63 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -109,6 +109,7 @@ unsigned int has_hwp_activity_window; /* IA32_HWP_REQUEST[bits 41:32] */ unsigned int has_hwp_epp; /* IA32_HWP_REQUEST[bits 31:24] */ unsigned int has_hwp_pkg; /* IA32_HWP_REQUEST_PKG */ unsigned int has_misc_feature_control; +unsigned int first_counter_read = 1; #define RAPL_PKG (1 << 0) /* 0x610 MSR_PKG_POWER_LIMIT */ @@ -170,6 +171,8 @@ struct thread_data { unsigned long long irq_count; unsigned int smi_count; unsigned int cpu_id; + unsigned int apic_id; + unsigned int x2apic_id; unsigned int flags; #define CPU_IS_FIRST_THREAD_IN_CORE 0x2 #define CPU_IS_FIRST_CORE_IN_PACKAGE 0x4 @@ -381,19 +384,23 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr) } /* - * Each string in this array is compared in --show and --hide cmdline. - * Thus, strings that are proper sub-sets must follow their more specific peers. + * This list matches the column headers, except + * 1. built-in only, the sysfs counters are not here -- we learn of those at run-time + * 2. Core and CPU are moved to the end, we can't have strings that contain them + * matching on them for --show and --hide. */ struct msr_counter bic[] = { { 0x0, "usec" }, { 0x0, "Time_Of_Day_Seconds" }, { 0x0, "Package" }, + { 0x0, "Node" }, { 0x0, "Avg_MHz" }, + { 0x0, "Busy%" }, { 0x0, "Bzy_MHz" }, { 0x0, "TSC_MHz" }, { 0x0, "IRQ" }, { 0x0, "SMI", "", 32, 0, FORMAT_DELTA, NULL}, - { 0x0, "Busy%" }, + { 0x0, "sysfs" }, { 0x0, "CPU%c1" }, { 0x0, "CPU%c3" }, { 0x0, "CPU%c6" }, @@ -424,73 +431,73 @@ struct msr_counter bic[] = { { 0x0, "Cor_J" }, { 0x0, "GFX_J" }, { 0x0, "RAM_J" }, - { 0x0, "Core" }, - { 0x0, "CPU" }, { 0x0, "Mod%c6" }, - { 0x0, "sysfs" }, { 0x0, "Totl%C0" }, { 0x0, "Any%C0" }, { 0x0, "GFX%C0" }, { 0x0, "CPUGFX%" }, - { 0x0, "Node%" }, + { 0x0, "Core" }, + { 0x0, "CPU" }, + { 0x0, "APIC" }, + { 0x0, "X2APIC" }, }; - - #define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter)) #define BIC_USEC (1ULL << 0) #define BIC_TOD (1ULL << 1) #define BIC_Package (1ULL << 2) -#define BIC_Avg_MHz (1ULL << 3) -#define BIC_Bzy_MHz (1ULL << 4) -#define BIC_TSC_MHz (1ULL << 5) -#define BIC_IRQ (1ULL << 6) -#define BIC_SMI (1ULL << 7) -#define BIC_Busy (1ULL << 8) -#define BIC_CPU_c1 (1ULL << 9) -#define BIC_CPU_c3 (1ULL << 10) -#define BIC_CPU_c6 (1ULL << 11) -#define BIC_CPU_c7 (1ULL << 12) -#define BIC_ThreadC (1ULL << 13) -#define BIC_CoreTmp (1ULL << 14) -#define BIC_CoreCnt (1ULL << 15) -#define BIC_PkgTmp (1ULL << 16) -#define BIC_GFX_rc6 (1ULL << 17) -#define BIC_GFXMHz (1ULL << 18) -#define BIC_Pkgpc2 (1ULL << 19) -#define BIC_Pkgpc3 (1ULL << 20) -#define BIC_Pkgpc6 (1ULL << 21) -#define BIC_Pkgpc7 (1ULL << 22) -#define BIC_Pkgpc8 (1ULL << 23) -#define BIC_Pkgpc9 (1ULL << 24) -#define BIC_Pkgpc10 (1ULL << 25) -#define BIC_CPU_LPI (1ULL << 26) -#define BIC_SYS_LPI (1ULL << 27) -#define BIC_PkgWatt (1ULL << 26) -#define BIC_CorWatt (1ULL << 27) -#define BIC_GFXWatt (1ULL << 28) -#define BIC_PkgCnt (1ULL << 29) -#define BIC_RAMWatt (1ULL << 30) -#define BIC_PKG__ (1ULL << 31) -#define BIC_RAM__ (1ULL << 32) -#define BIC_Pkg_J (1ULL << 33) -#define BIC_Cor_J (1ULL << 34) -#define BIC_GFX_J (1ULL << 35) -#define BIC_RAM_J (1ULL << 36) -#define BIC_Core (1ULL << 37) -#define BIC_CPU (1ULL << 38) -#define BIC_Mod_c6 (1ULL << 39) -#define BIC_sysfs (1ULL << 40) -#define BIC_Totl_c0 (1ULL << 41) -#define BIC_Any_c0 (1ULL << 42) -#define BIC_GFX_c0 (1ULL << 43) -#define BIC_CPUGFX (1ULL << 44) -#define BIC_Node (1ULL << 45) - -#define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD) +#define BIC_Node (1ULL << 3) +#define BIC_Avg_MHz (1ULL << 4) +#define BIC_Busy (1ULL << 5) +#define BIC_Bzy_MHz (1ULL << 6) +#define BIC_TSC_MHz (1ULL << 7) +#define BIC_IRQ (1ULL << 8) +#define BIC_SMI (1ULL << 9) +#define BIC_sysfs (1ULL << 10) +#define BIC_CPU_c1 (1ULL << 11) +#define BIC_CPU_c3 (1ULL << 12) +#define BIC_CPU_c6 (1ULL << 13) +#define BIC_CPU_c7 (1ULL << 14) +#define BIC_ThreadC (1ULL << 15) +#define BIC_CoreTmp (1ULL << 16) +#define BIC_CoreCnt (1ULL << 17) +#define BIC_PkgTmp (1ULL << 18) +#define BIC_GFX_rc6 (1ULL << 19) +#define BIC_GFXMHz (1ULL << 20) +#define BIC_Pkgpc2 (1ULL << 21) +#define BIC_Pkgpc3 (1ULL << 22) +#define BIC_Pkgpc6 (1ULL << 23) +#define BIC_Pkgpc7 (1ULL << 24) +#define BIC_Pkgpc8 (1ULL << 25) +#define BIC_Pkgpc9 (1ULL << 26) +#define BIC_Pkgpc10 (1ULL << 27) +#define BIC_CPU_LPI (1ULL << 28) +#define BIC_SYS_LPI (1ULL << 29) +#define BIC_PkgWatt (1ULL << 30) +#define BIC_CorWatt (1ULL << 31) +#define BIC_GFXWatt (1ULL << 32) +#define BIC_PkgCnt (1ULL << 33) +#define BIC_RAMWatt (1ULL << 34) +#define BIC_PKG__ (1ULL << 35) +#define BIC_RAM__ (1ULL << 36) +#define BIC_Pkg_J (1ULL << 37) +#define BIC_Cor_J (1ULL << 38) +#define BIC_GFX_J (1ULL << 39) +#define BIC_RAM_J (1ULL << 40) +#define BIC_Mod_c6 (1ULL << 41) +#define BIC_Totl_c0 (1ULL << 42) +#define BIC_Any_c0 (1ULL << 43) +#define BIC_GFX_c0 (1ULL << 44) +#define BIC_CPUGFX (1ULL << 45) +#define BIC_Core (1ULL << 46) +#define BIC_CPU (1ULL << 47) +#define BIC_APIC (1ULL << 48) +#define BIC_X2APIC (1ULL << 49) + +#define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC) unsigned long long bic_enabled = (0xFFFFFFFFFFFFFFFFULL & ~BIC_DISABLED_BY_DEFAULT); -unsigned long long bic_present = BIC_USEC | BIC_TOD | BIC_sysfs; +unsigned long long bic_present = BIC_USEC | BIC_TOD | BIC_sysfs | BIC_APIC | BIC_X2APIC; #define DO_BIC(COUNTER_NAME) (bic_enabled & bic_present & COUNTER_NAME) #define ENABLE_BIC(COUNTER_NAME) (bic_enabled |= COUNTER_NAME) @@ -517,17 +524,34 @@ void help(void) "when COMMAND completes.\n" "If no COMMAND is specified, turbostat wakes every 5-seconds\n" "to print statistics, until interrupted.\n" - "--add add a counter\n" - " eg. --add msr0x10,u64,cpu,delta,MY_TSC\n" - "--cpu cpu-set limit output to summary plus cpu-set:\n" - " {core | package | j,k,l..m,n-p }\n" - "--quiet skip decoding system configuration header\n" - "--interval sec.subsec Override default 5-second measurement interval\n" - "--help print this help message\n" - "--list list column headers only\n" - "--num_iterations num number of the measurement iterations\n" - "--out file create or truncate \"file\" for all output\n" - "--version print version information\n" + " -a, --add add a counter\n" + " eg. --add msr0x10,u64,cpu,delta,MY_TSC\n" + " -c, --cpu cpu-set limit output to summary plus cpu-set:\n" + " {core | package | j,k,l..m,n-p }\n" + " -d, --debug displays usec, Time_Of_Day_Seconds and more debugging\n" + " -D, --Dump displays the raw counter values\n" + " -e, --enable [all | column]\n" + " shows all or the specified disabled column\n" + " -H, --hide [column|column,column,...]\n" + " hide the specified column(s)\n" + " -i, --interval sec.subsec\n" + " Override default 5-second measurement interval\n" + " -J, --Joules displays energy in Joules instead of Watts\n" + " -l, --list list column headers only\n" + " -n, --num_iterations num\n" + " number of the measurement iterations\n" + " -o, --out file\n" + " create or truncate \"file\" for all output\n" + " -q, --quiet skip decoding system configuration header\n" + " -s, --show [column|column,column,...]\n" + " show only the specified column(s)\n" + " -S, --Summary\n" + " limits output to 1-line system summary per interval\n" + " -T, --TCC temperature\n" + " sets the Thermal Control Circuit temperature in\n" + " degrees Celsius\n" + " -h, --help print this help message\n" + " -v, --version print version information\n" "\n" "For more help, run \"man turbostat\"\n"); } @@ -601,6 +625,10 @@ void print_header(char *delim) outp += sprintf(outp, "%sCore", (printed++ ? delim : "")); if (DO_BIC(BIC_CPU)) outp += sprintf(outp, "%sCPU", (printed++ ? delim : "")); + if (DO_BIC(BIC_APIC)) + outp += sprintf(outp, "%sAPIC", (printed++ ? delim : "")); + if (DO_BIC(BIC_X2APIC)) + outp += sprintf(outp, "%sX2APIC", (printed++ ? delim : "")); if (DO_BIC(BIC_Avg_MHz)) outp += sprintf(outp, "%sAvg_MHz", (printed++ ? delim : "")); if (DO_BIC(BIC_Busy)) @@ -880,6 +908,10 @@ int format_counters(struct thread_data *t, struct core_data *c, outp += sprintf(outp, "%s-", (printed++ ? delim : "")); if (DO_BIC(BIC_CPU)) outp += sprintf(outp, "%s-", (printed++ ? delim : "")); + if (DO_BIC(BIC_APIC)) + outp += sprintf(outp, "%s-", (printed++ ? delim : "")); + if (DO_BIC(BIC_X2APIC)) + outp += sprintf(outp, "%s-", (printed++ ? delim : "")); } else { if (DO_BIC(BIC_Package)) { if (p) @@ -904,6 +936,10 @@ int format_counters(struct thread_data *t, struct core_data *c, } if (DO_BIC(BIC_CPU)) outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), t->cpu_id); + if (DO_BIC(BIC_APIC)) + outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), t->apic_id); + if (DO_BIC(BIC_X2APIC)) + outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), t->x2apic_id); } if (DO_BIC(BIC_Avg_MHz)) @@ -1231,6 +1267,12 @@ delta_thread(struct thread_data *new, struct thread_data *old, int i; struct msr_counter *mp; + /* we run cpuid just the 1st time, copy the results */ + if (DO_BIC(BIC_APIC)) + new->apic_id = old->apic_id; + if (DO_BIC(BIC_X2APIC)) + new->x2apic_id = old->x2apic_id; + /* * the timestamps from start of measurement interval are in "old" * the timestamp from end of measurement interval are in "new" @@ -1393,6 +1435,12 @@ int sum_counters(struct thread_data *t, struct core_data *c, int i; struct msr_counter *mp; + /* copy un-changing apic_id's */ + if (DO_BIC(BIC_APIC)) + average.threads.apic_id = t->apic_id; + if (DO_BIC(BIC_X2APIC)) + average.threads.x2apic_id = t->x2apic_id; + /* remember first tv_begin */ if (average.threads.tv_begin.tv_sec == 0) average.threads.tv_begin = t->tv_begin; @@ -1619,6 +1667,34 @@ int get_mp(int cpu, struct msr_counter *mp, unsigned long long *counterp) return 0; } +void get_apic_id(struct thread_data *t) +{ + unsigned int eax, ebx, ecx, edx, max_level; + + eax = ebx = ecx = edx = 0; + + if (!genuine_intel) + return; + + __cpuid(0, max_level, ebx, ecx, edx); + + __cpuid(1, eax, ebx, ecx, edx); + t->apic_id = (ebx >> 24) & 0xf; + + if (max_level < 0xb) + return; + + if (!DO_BIC(BIC_X2APIC)) + return; + + ecx = 0; + __cpuid(0xb, eax, ebx, ecx, edx); + t->x2apic_id = edx; + + if (debug && (t->apic_id != t->x2apic_id)) + fprintf(stderr, "cpu%d: apic 0x%x x2apic 0x%x\n", t->cpu_id, t->apic_id, t->x2apic_id); +} + /* * get_counters(...) * migrate to cpu @@ -1632,7 +1708,6 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) struct msr_counter *mp; int i; - gettimeofday(&t->tv_begin, (struct timezone *)NULL); if (cpu_migrate(cpu)) { @@ -1640,6 +1715,8 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) return -1; } + if (first_counter_read) + get_apic_id(t); retry: t->tsc = rdtsc(); /* we are running on local CPU of interest */ @@ -2432,6 +2509,12 @@ void set_node_data(void) if (pni[pkg].count > topo.nodes_per_pkg) topo.nodes_per_pkg = pni[0].count; + /* Fake 1 node per pkg for machines that don't + * expose nodes and thus avoid -nan results + */ + if (topo.nodes_per_pkg == 0) + topo.nodes_per_pkg = 1; + for (cpu = 0; cpu < topo.num_cpus; cpu++) { pkg = cpus[cpu].physical_package_id; node = cpus[cpu].physical_node_id; @@ -2879,6 +2962,7 @@ void do_sleep(void) } } + void turbostat_loop() { int retval; @@ -2892,6 +2976,7 @@ restart: snapshot_proc_sysfs_files(); retval = for_all_cpus(get_counters, EVEN_COUNTERS); + first_counter_read = 0; if (retval < -1) { exit(retval); } else if (retval == -1) { @@ -4392,7 +4477,7 @@ void process_cpuid() if (!quiet) { fprintf(outf, "%d CPUID levels; family:model:stepping 0x%x:%x:%x (%d:%d:%d)\n", max_level, family, model, stepping, family, model, stepping); - fprintf(outf, "CPUID(1): %s %s %s %s %s %s %s %s %s\n", + fprintf(outf, "CPUID(1): %s %s %s %s %s %s %s %s %s %s\n", ecx & (1 << 0) ? "SSE3" : "-", ecx & (1 << 3) ? "MONITOR" : "-", ecx & (1 << 6) ? "SMX" : "-", @@ -4401,6 +4486,7 @@ void process_cpuid() edx & (1 << 4) ? "TSC" : "-", edx & (1 << 5) ? "MSR" : "-", edx & (1 << 22) ? "ACPI-TM" : "-", + edx & (1 << 28) ? "HT" : "-", edx & (1 << 29) ? "TM" : "-"); } @@ -4652,7 +4738,6 @@ void process_cpuid() return; } - /* * in /dev/cpu/ return success for names that are numbers * ie. filter out ".", "..", "microcode". @@ -4842,6 +4927,13 @@ void init_counter(struct thread_data *thread_base, struct core_data *core_base, struct core_data *c; struct pkg_data *p; + + /* Workaround for systems where physical_node_id==-1 + * and logical_node_id==(-1 - topo.num_cpus) + */ + if (node_id < 0) + node_id = 0; + t = GET_THREAD(thread_base, thread_id, core_id, node_id, pkg_id); c = GET_CORE(core_base, core_id, node_id, pkg_id); p = GET_PKG(pkg_base, pkg_id); @@ -4946,6 +5038,7 @@ int fork_it(char **argv) snapshot_proc_sysfs_files(); status = for_all_cpus(get_counters, EVEN_COUNTERS); + first_counter_read = 0; if (status) exit(status); /* clear affinity side-effect of get_counters() */ @@ -5009,7 +5102,7 @@ int get_and_dump_counters(void) } void print_version() { - fprintf(outf, "turbostat version 18.06.01" + fprintf(outf, "turbostat version 18.06.20" " - Len Brown <lenb@kernel.org>\n"); } @@ -5381,7 +5474,7 @@ void cmdline(int argc, char **argv) break; case 'e': /* --enable specified counter */ - bic_enabled |= bic_lookup(optarg, SHOW_LIST); + bic_enabled = bic_enabled | bic_lookup(optarg, SHOW_LIST); break; case 'd': debug++; @@ -5465,7 +5558,6 @@ void cmdline(int argc, char **argv) int main(int argc, char **argv) { outf = stderr; - cmdline(argc, argv); if (!quiet) diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index 1eefe211a4a8..7eb613ffef55 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -7,3 +7,13 @@ CONFIG_CGROUP_BPF=y CONFIG_NETDEVSIM=m CONFIG_NET_CLS_ACT=y CONFIG_NET_SCH_INGRESS=y +CONFIG_NET_IPIP=y +CONFIG_IPV6=y +CONFIG_NET_IPGRE_DEMUX=y +CONFIG_NET_IPGRE=y +CONFIG_IPV6_GRE=y +CONFIG_CRYPTO_USER_API_HASH=m +CONFIG_CRYPTO_HMAC=m +CONFIG_CRYPTO_SHA256=m +CONFIG_VXLAN=y +CONFIG_GENEVE=y diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py index e78aad0a68bb..be800d0e7a84 100755 --- a/tools/testing/selftests/bpf/test_offload.py +++ b/tools/testing/selftests/bpf/test_offload.py @@ -163,6 +163,10 @@ def bpftool(args, JSON=True, ns="", fail=True): def bpftool_prog_list(expected=None, ns=""): _, progs = bpftool("prog show", JSON=True, ns=ns, fail=True) + # Remove the base progs + for p in base_progs: + if p in progs: + progs.remove(p) if expected is not None: if len(progs) != expected: fail(True, "%d BPF programs loaded, expected %d" % @@ -171,6 +175,10 @@ def bpftool_prog_list(expected=None, ns=""): def bpftool_map_list(expected=None, ns=""): _, maps = bpftool("map show", JSON=True, ns=ns, fail=True) + # Remove the base maps + for m in base_maps: + if m in maps: + maps.remove(m) if expected is not None: if len(maps) != expected: fail(True, "%d BPF maps loaded, expected %d" % @@ -585,8 +593,8 @@ skip(os.getuid() != 0, "test must be run as root") # Check tools ret, progs = bpftool("prog", fail=False) skip(ret != 0, "bpftool not installed") -# Check no BPF programs are loaded -skip(len(progs) != 0, "BPF programs already loaded on the system") +base_progs = progs +_, base_maps = bpftool("map") # Check netdevsim ret, out = cmd("modprobe netdevsim", fail=False) diff --git a/tools/testing/selftests/bpf/test_tunnel.sh b/tools/testing/selftests/bpf/test_tunnel.sh index aeb2901f21f4..546aee3e9fb4 100755 --- a/tools/testing/selftests/bpf/test_tunnel.sh +++ b/tools/testing/selftests/bpf/test_tunnel.sh @@ -608,28 +608,26 @@ setup_xfrm_tunnel() test_xfrm_tunnel() { config_device - #tcpdump -nei veth1 ip & - output=$(mktemp) - cat /sys/kernel/debug/tracing/trace_pipe | tee $output & - setup_xfrm_tunnel + > /sys/kernel/debug/tracing/trace + setup_xfrm_tunnel tc qdisc add dev veth1 clsact tc filter add dev veth1 proto ip ingress bpf da obj test_tunnel_kern.o \ sec xfrm_get_state ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 sleep 1 - grep "reqid 1" $output + grep "reqid 1" /sys/kernel/debug/tracing/trace check_err $? - grep "spi 0x1" $output + grep "spi 0x1" /sys/kernel/debug/tracing/trace check_err $? - grep "remote ip 0xac100164" $output + grep "remote ip 0xac100164" /sys/kernel/debug/tracing/trace check_err $? cleanup if [ $ret -ne 0 ]; then - echo -e ${RED}"FAIL: xfrm tunnel"${NC} - return 1 - fi - echo -e ${GREEN}"PASS: xfrm tunnel"${NC} + echo -e ${RED}"FAIL: xfrm tunnel"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: xfrm tunnel"${NC} } attach_bpf() @@ -657,6 +655,10 @@ cleanup() ip link del ip6geneve11 2> /dev/null ip link del erspan11 2> /dev/null ip link del ip6erspan11 2> /dev/null + ip xfrm policy delete dir out src 10.1.1.200/32 dst 10.1.1.100/32 2> /dev/null + ip xfrm policy delete dir in src 10.1.1.100/32 dst 10.1.1.200/32 2> /dev/null + ip xfrm state delete src 172.16.1.100 dst 172.16.1.200 proto esp spi 0x1 2> /dev/null + ip xfrm state delete src 172.16.1.200 dst 172.16.1.100 proto esp spi 0x2 2> /dev/null } cleanup_exit() @@ -668,7 +670,7 @@ cleanup_exit() check() { - ip link help $1 2>&1 | grep -q "^Usage:" + ip link help 2>&1 | grep -q "\s$1\s" if [ $? -ne 0 ];then echo "SKIP $1: iproute2 not support" cleanup 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 = { |