diff options
348 files changed, 11957 insertions, 4603 deletions
diff --git a/Documentation/devicetree/bindings/thermal/rcar-thermal.txt b/Documentation/devicetree/bindings/thermal/rcar-thermal.txt index 43404b197933..332e625f6ed0 100644 --- a/Documentation/devicetree/bindings/thermal/rcar-thermal.txt +++ b/Documentation/devicetree/bindings/thermal/rcar-thermal.txt @@ -4,7 +4,7 @@ Required properties: - compatible : "renesas,thermal-<soctype>", "renesas,rcar-thermal" as fallback. Examples with soctypes are: - - "renesas,thermal-r8a73a4" (R-Mobile AP6) + - "renesas,thermal-r8a73a4" (R-Mobile APE6) - "renesas,thermal-r8a7779" (R-Car H1) - "renesas,thermal-r8a7790" (R-Car H2) - "renesas,thermal-r8a7791" (R-Car M2-W) diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index bfcb1a62a7b4..01aa47d3b6ab 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1036,7 +1036,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted. Format: {"off" | "on" | "skip[mbr]"} efi= [EFI] - Format: { "old_map", "nochunk", "noruntime" } + Format: { "old_map", "nochunk", "noruntime", "debug" } old_map [X86-64]: switch to the old ioremap-based EFI runtime services mapping. 32-bit still uses this one by default. @@ -1044,6 +1044,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted. boot stub, as chunking can cause problems with some firmware implementations. noruntime : disable EFI runtime services support + debug: enable misc debug output efi_no_storage_paranoia [EFI; X86] Using this parameter you can use more than 50% of diff --git a/Documentation/rtc.txt b/Documentation/rtc.txt index 596b60c08b74..8446f1ea1410 100644 --- a/Documentation/rtc.txt +++ b/Documentation/rtc.txt @@ -204,266 +204,4 @@ Some common examples: * RTC_PIE_ON, RTC_PIE_OFF: These are also emulated by the generic code. -If all else fails, check out the rtc-test.c driver! - - --------------------- 8< ---------------- 8< ----------------------------- - -/* - * Real Time Clock Driver Test/Example Program - * - * Compile with: - * gcc -s -Wall -Wstrict-prototypes rtctest.c -o rtctest - * - * Copyright (C) 1996, Paul Gortmaker. - * - * Released under the GNU General Public License, version 2, - * included herein by reference. - * - */ - -#include <stdio.h> -#include <linux/rtc.h> -#include <sys/ioctl.h> -#include <sys/time.h> -#include <sys/types.h> -#include <fcntl.h> -#include <unistd.h> -#include <stdlib.h> -#include <errno.h> - - -/* - * This expects the new RTC class driver framework, working with - * clocks that will often not be clones of what the PC-AT had. - * Use the command line to specify another RTC if you need one. - */ -static const char default_rtc[] = "/dev/rtc0"; - - -int main(int argc, char **argv) -{ - int i, fd, retval, irqcount = 0; - unsigned long tmp, data; - struct rtc_time rtc_tm; - const char *rtc = default_rtc; - - switch (argc) { - case 2: - rtc = argv[1]; - /* FALLTHROUGH */ - case 1: - break; - default: - fprintf(stderr, "usage: rtctest [rtcdev]\n"); - return 1; - } - - fd = open(rtc, O_RDONLY); - - if (fd == -1) { - perror(rtc); - exit(errno); - } - - fprintf(stderr, "\n\t\t\tRTC Driver Test Example.\n\n"); - - /* Turn on update interrupts (one per second) */ - retval = ioctl(fd, RTC_UIE_ON, 0); - if (retval == -1) { - if (errno == ENOTTY) { - fprintf(stderr, - "\n...Update IRQs not supported.\n"); - goto test_READ; - } - perror("RTC_UIE_ON ioctl"); - exit(errno); - } - - fprintf(stderr, "Counting 5 update (1/sec) interrupts from reading %s:", - rtc); - fflush(stderr); - for (i=1; i<6; i++) { - /* This read will block */ - retval = read(fd, &data, sizeof(unsigned long)); - if (retval == -1) { - perror("read"); - exit(errno); - } - fprintf(stderr, " %d",i); - fflush(stderr); - irqcount++; - } - - fprintf(stderr, "\nAgain, from using select(2) on /dev/rtc:"); - fflush(stderr); - for (i=1; i<6; i++) { - struct timeval tv = {5, 0}; /* 5 second timeout on select */ - fd_set readfds; - - FD_ZERO(&readfds); - FD_SET(fd, &readfds); - /* The select will wait until an RTC interrupt happens. */ - retval = select(fd+1, &readfds, NULL, NULL, &tv); - if (retval == -1) { - perror("select"); - exit(errno); - } - /* This read won't block unlike the select-less case above. */ - retval = read(fd, &data, sizeof(unsigned long)); - if (retval == -1) { - perror("read"); - exit(errno); - } - fprintf(stderr, " %d",i); - fflush(stderr); - irqcount++; - } - - /* Turn off update interrupts */ - retval = ioctl(fd, RTC_UIE_OFF, 0); - if (retval == -1) { - perror("RTC_UIE_OFF ioctl"); - exit(errno); - } - -test_READ: - /* Read the RTC time/date */ - retval = ioctl(fd, RTC_RD_TIME, &rtc_tm); - if (retval == -1) { - perror("RTC_RD_TIME ioctl"); - exit(errno); - } - - fprintf(stderr, "\n\nCurrent RTC date/time is %d-%d-%d, %02d:%02d:%02d.\n", - rtc_tm.tm_mday, rtc_tm.tm_mon + 1, rtc_tm.tm_year + 1900, - rtc_tm.tm_hour, rtc_tm.tm_min, rtc_tm.tm_sec); - - /* Set the alarm to 5 sec in the future, and check for rollover */ - rtc_tm.tm_sec += 5; - if (rtc_tm.tm_sec >= 60) { - rtc_tm.tm_sec %= 60; - rtc_tm.tm_min++; - } - if (rtc_tm.tm_min == 60) { - rtc_tm.tm_min = 0; - rtc_tm.tm_hour++; - } - if (rtc_tm.tm_hour == 24) - rtc_tm.tm_hour = 0; - - retval = ioctl(fd, RTC_ALM_SET, &rtc_tm); - if (retval == -1) { - if (errno == ENOTTY) { - fprintf(stderr, - "\n...Alarm IRQs not supported.\n"); - goto test_PIE; - } - perror("RTC_ALM_SET ioctl"); - exit(errno); - } - - /* Read the current alarm settings */ - retval = ioctl(fd, RTC_ALM_READ, &rtc_tm); - if (retval == -1) { - perror("RTC_ALM_READ ioctl"); - exit(errno); - } - - fprintf(stderr, "Alarm time now set to %02d:%02d:%02d.\n", - rtc_tm.tm_hour, rtc_tm.tm_min, rtc_tm.tm_sec); - - /* Enable alarm interrupts */ - retval = ioctl(fd, RTC_AIE_ON, 0); - if (retval == -1) { - perror("RTC_AIE_ON ioctl"); - exit(errno); - } - - fprintf(stderr, "Waiting 5 seconds for alarm..."); - fflush(stderr); - /* This blocks until the alarm ring causes an interrupt */ - retval = read(fd, &data, sizeof(unsigned long)); - if (retval == -1) { - perror("read"); - exit(errno); - } - irqcount++; - fprintf(stderr, " okay. Alarm rang.\n"); - - /* Disable alarm interrupts */ - retval = ioctl(fd, RTC_AIE_OFF, 0); - if (retval == -1) { - perror("RTC_AIE_OFF ioctl"); - exit(errno); - } - -test_PIE: - /* Read periodic IRQ rate */ - retval = ioctl(fd, RTC_IRQP_READ, &tmp); - if (retval == -1) { - /* not all RTCs support periodic IRQs */ - if (errno == ENOTTY) { - fprintf(stderr, "\nNo periodic IRQ support\n"); - goto done; - } - perror("RTC_IRQP_READ ioctl"); - exit(errno); - } - fprintf(stderr, "\nPeriodic IRQ rate is %ldHz.\n", tmp); - - fprintf(stderr, "Counting 20 interrupts at:"); - fflush(stderr); - - /* The frequencies 128Hz, 256Hz, ... 8192Hz are only allowed for root. */ - for (tmp=2; tmp<=64; tmp*=2) { - - retval = ioctl(fd, RTC_IRQP_SET, tmp); - if (retval == -1) { - /* not all RTCs can change their periodic IRQ rate */ - if (errno == ENOTTY) { - fprintf(stderr, - "\n...Periodic IRQ rate is fixed\n"); - goto done; - } - perror("RTC_IRQP_SET ioctl"); - exit(errno); - } - - fprintf(stderr, "\n%ldHz:\t", tmp); - fflush(stderr); - - /* Enable periodic interrupts */ - retval = ioctl(fd, RTC_PIE_ON, 0); - if (retval == -1) { - perror("RTC_PIE_ON ioctl"); - exit(errno); - } - - for (i=1; i<21; i++) { - /* This blocks */ - retval = read(fd, &data, sizeof(unsigned long)); - if (retval == -1) { - perror("read"); - exit(errno); - } - fprintf(stderr, " %d",i); - fflush(stderr); - irqcount++; - } - - /* Disable periodic interrupts */ - retval = ioctl(fd, RTC_PIE_OFF, 0); - if (retval == -1) { - perror("RTC_PIE_OFF ioctl"); - exit(errno); - } - } - -done: - fprintf(stderr, "\n\n\t\t\t *** Test complete ***\n"); - - close(fd); - - return 0; -} +If all else fails, check out the tools/testing/selftests/timers/rtctest.c test! diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index b112efc816f1..bc9f6fe44e27 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -997,7 +997,7 @@ for vm-wide capabilities. 4.38 KVM_GET_MP_STATE Capability: KVM_CAP_MP_STATE -Architectures: x86, s390 +Architectures: x86, s390, arm, arm64 Type: vcpu ioctl Parameters: struct kvm_mp_state (out) Returns: 0 on success; -1 on error @@ -1011,7 +1011,7 @@ uniprocessor guests). Possible values are: - - KVM_MP_STATE_RUNNABLE: the vcpu is currently running [x86] + - KVM_MP_STATE_RUNNABLE: the vcpu is currently running [x86,arm/arm64] - KVM_MP_STATE_UNINITIALIZED: the vcpu is an application processor (AP) which has not yet received an INIT signal [x86] - KVM_MP_STATE_INIT_RECEIVED: the vcpu has received an INIT signal, and is @@ -1020,7 +1020,7 @@ Possible values are: is waiting for an interrupt [x86] - KVM_MP_STATE_SIPI_RECEIVED: the vcpu has just received a SIPI (vector accessible via KVM_GET_VCPU_EVENTS) [x86] - - KVM_MP_STATE_STOPPED: the vcpu is stopped [s390] + - KVM_MP_STATE_STOPPED: the vcpu is stopped [s390,arm/arm64] - KVM_MP_STATE_CHECK_STOP: the vcpu is in a special error state [s390] - KVM_MP_STATE_OPERATING: the vcpu is operating (running or halted) [s390] @@ -1031,11 +1031,15 @@ On x86, this ioctl is only useful after KVM_CREATE_IRQCHIP. Without an in-kernel irqchip, the multiprocessing state must be maintained by userspace on these architectures. +For arm/arm64: + +The only states that are valid are KVM_MP_STATE_STOPPED and +KVM_MP_STATE_RUNNABLE which reflect if the vcpu is paused or not. 4.39 KVM_SET_MP_STATE Capability: KVM_CAP_MP_STATE -Architectures: x86, s390 +Architectures: x86, s390, arm, arm64 Type: vcpu ioctl Parameters: struct kvm_mp_state (in) Returns: 0 on success; -1 on error @@ -1047,6 +1051,10 @@ On x86, this ioctl is only useful after KVM_CREATE_IRQCHIP. Without an in-kernel irqchip, the multiprocessing state must be maintained by userspace on these architectures. +For arm/arm64: + +The only states that are valid are KVM_MP_STATE_STOPPED and +KVM_MP_STATE_RUNNABLE which reflect if the vcpu should be paused or not. 4.40 KVM_SET_IDENTITY_MAP_ADDR @@ -1967,15 +1975,25 @@ registers, find a list below: MIPS | KVM_REG_MIPS_CP0_STATUS | 32 MIPS | KVM_REG_MIPS_CP0_CAUSE | 32 MIPS | KVM_REG_MIPS_CP0_EPC | 64 + MIPS | KVM_REG_MIPS_CP0_PRID | 32 MIPS | KVM_REG_MIPS_CP0_CONFIG | 32 MIPS | KVM_REG_MIPS_CP0_CONFIG1 | 32 MIPS | KVM_REG_MIPS_CP0_CONFIG2 | 32 MIPS | KVM_REG_MIPS_CP0_CONFIG3 | 32 + MIPS | KVM_REG_MIPS_CP0_CONFIG4 | 32 + MIPS | KVM_REG_MIPS_CP0_CONFIG5 | 32 MIPS | KVM_REG_MIPS_CP0_CONFIG7 | 32 MIPS | KVM_REG_MIPS_CP0_ERROREPC | 64 MIPS | KVM_REG_MIPS_COUNT_CTL | 64 MIPS | KVM_REG_MIPS_COUNT_RESUME | 64 MIPS | KVM_REG_MIPS_COUNT_HZ | 64 + MIPS | KVM_REG_MIPS_FPR_32(0..31) | 32 + MIPS | KVM_REG_MIPS_FPR_64(0..31) | 64 + MIPS | KVM_REG_MIPS_VEC_128(0..31) | 128 + MIPS | KVM_REG_MIPS_FCR_IR | 32 + MIPS | KVM_REG_MIPS_FCR_CSR | 32 + MIPS | KVM_REG_MIPS_MSA_IR | 32 + MIPS | KVM_REG_MIPS_MSA_CSR | 32 ARM registers are mapped using the lower 32 bits. The upper 16 of that is the register group type, or coprocessor number: @@ -2029,6 +2047,25 @@ patterns depending on whether they're 32-bit or 64-bit registers: MIPS KVM control registers (see above) have the following id bit patterns: 0x7030 0000 0002 <reg:16> +MIPS FPU registers (see KVM_REG_MIPS_FPR_{32,64}() above) have the following +id bit patterns depending on the size of the register being accessed. They are +always accessed according to the current guest FPU mode (Status.FR and +Config5.FRE), i.e. as the guest would see them, and they become unpredictable +if the guest FPU mode is changed. MIPS SIMD Architecture (MSA) vector +registers (see KVM_REG_MIPS_VEC_128() above) have similar patterns as they +overlap the FPU registers: + 0x7020 0000 0003 00 <0:3> <reg:5> (32-bit FPU registers) + 0x7030 0000 0003 00 <0:3> <reg:5> (64-bit FPU registers) + 0x7040 0000 0003 00 <0:3> <reg:5> (128-bit MSA vector registers) + +MIPS FPU control registers (see KVM_REG_MIPS_FCR_{IR,CSR} above) have the +following id bit patterns: + 0x7020 0000 0003 01 <0:3> <reg:5> + +MIPS MSA control registers (see KVM_REG_MIPS_MSA_{IR,CSR} above) have the +following id bit patterns: + 0x7020 0000 0003 02 <0:3> <reg:5> + 4.69 KVM_GET_ONE_REG @@ -2234,7 +2271,7 @@ into the hash PTE second double word). 4.75 KVM_IRQFD Capability: KVM_CAP_IRQFD -Architectures: x86 s390 +Architectures: x86 s390 arm arm64 Type: vm ioctl Parameters: struct kvm_irqfd (in) Returns: 0 on success, -1 on error @@ -2260,6 +2297,10 @@ Note that closing the resamplefd is not sufficient to disable the irqfd. The KVM_IRQFD_FLAG_RESAMPLE is only necessary on assignment and need not be specified with KVM_IRQFD_FLAG_DEASSIGN. +On ARM/ARM64, the gsi field in the kvm_irqfd struct specifies the Shared +Peripheral Interrupt (SPI) index, such that the GIC interrupt ID is +given by gsi + 32. + 4.76 KVM_PPC_ALLOCATE_HTAB Capability: KVM_CAP_PPC_ALLOC_HTAB @@ -2716,6 +2757,227 @@ The fields in each entry are defined as follows: eax, ebx, ecx, edx: the values returned by the cpuid instruction for this function/index combination +4.89 KVM_S390_MEM_OP + +Capability: KVM_CAP_S390_MEM_OP +Architectures: s390 +Type: vcpu ioctl +Parameters: struct kvm_s390_mem_op (in) +Returns: = 0 on success, + < 0 on generic error (e.g. -EFAULT or -ENOMEM), + > 0 if an exception occurred while walking the page tables + +Read or write data from/to the logical (virtual) memory of a VPCU. + +Parameters are specified via the following structure: + +struct kvm_s390_mem_op { + __u64 gaddr; /* the guest address */ + __u64 flags; /* flags */ + __u32 size; /* amount of bytes */ + __u32 op; /* type of operation */ + __u64 buf; /* buffer in userspace */ + __u8 ar; /* the access register number */ + __u8 reserved[31]; /* should be set to 0 */ +}; + +The type of operation is specified in the "op" field. It is either +KVM_S390_MEMOP_LOGICAL_READ for reading from logical memory space or +KVM_S390_MEMOP_LOGICAL_WRITE for writing to logical memory space. The +KVM_S390_MEMOP_F_CHECK_ONLY flag can be set in the "flags" field to check +whether the corresponding memory access would create an access exception +(without touching the data in the memory at the destination). In case an +access exception occurred while walking the MMU tables of the guest, the +ioctl returns a positive error number to indicate the type of exception. +This exception is also raised directly at the corresponding VCPU if the +flag KVM_S390_MEMOP_F_INJECT_EXCEPTION is set in the "flags" field. + +The start address of the memory region has to be specified in the "gaddr" +field, and the length of the region in the "size" field. "buf" is the buffer +supplied by the userspace application where the read data should be written +to for KVM_S390_MEMOP_LOGICAL_READ, or where the data that should be written +is stored for a KVM_S390_MEMOP_LOGICAL_WRITE. "buf" is unused and can be NULL +when KVM_S390_MEMOP_F_CHECK_ONLY is specified. "ar" designates the access +register number to be used. + +The "reserved" field is meant for future extensions. It is not used by +KVM with the currently defined set of flags. + +4.90 KVM_S390_GET_SKEYS + +Capability: KVM_CAP_S390_SKEYS +Architectures: s390 +Type: vm ioctl +Parameters: struct kvm_s390_skeys +Returns: 0 on success, KVM_S390_GET_KEYS_NONE if guest is not using storage + keys, negative value on error + +This ioctl is used to get guest storage key values on the s390 +architecture. The ioctl takes parameters via the kvm_s390_skeys struct. + +struct kvm_s390_skeys { + __u64 start_gfn; + __u64 count; + __u64 skeydata_addr; + __u32 flags; + __u32 reserved[9]; +}; + +The start_gfn field is the number of the first guest frame whose storage keys +you want to get. + +The count field is the number of consecutive frames (starting from start_gfn) +whose storage keys to get. The count field must be at least 1 and the maximum +allowed value is defined as KVM_S390_SKEYS_ALLOC_MAX. Values outside this range +will cause the ioctl to return -EINVAL. + +The skeydata_addr field is the address to a buffer large enough to hold count +bytes. This buffer will be filled with storage key data by the ioctl. + +4.91 KVM_S390_SET_SKEYS + +Capability: KVM_CAP_S390_SKEYS +Architectures: s390 +Type: vm ioctl +Parameters: struct kvm_s390_skeys +Returns: 0 on success, negative value on error + +This ioctl is used to set guest storage key values on the s390 +architecture. The ioctl takes parameters via the kvm_s390_skeys struct. +See section on KVM_S390_GET_SKEYS for struct definition. + +The start_gfn field is the number of the first guest frame whose storage keys +you want to set. + +The count field is the number of consecutive frames (starting from start_gfn) +whose storage keys to get. The count field must be at least 1 and the maximum +allowed value is defined as KVM_S390_SKEYS_ALLOC_MAX. Values outside this range +will cause the ioctl to return -EINVAL. + +The skeydata_addr field is the address to a buffer containing count bytes of +storage keys. Each byte in the buffer will be set as the storage key for a +single frame starting at start_gfn for count frames. + +Note: If any architecturally invalid key value is found in the given data then +the ioctl will return -EINVAL. + +4.92 KVM_S390_IRQ + +Capability: KVM_CAP_S390_INJECT_IRQ +Architectures: s390 +Type: vcpu ioctl +Parameters: struct kvm_s390_irq (in) +Returns: 0 on success, -1 on error +Errors: + EINVAL: interrupt type is invalid + type is KVM_S390_SIGP_STOP and flag parameter is invalid value + type is KVM_S390_INT_EXTERNAL_CALL and code is bigger + than the maximum of VCPUs + EBUSY: type is KVM_S390_SIGP_SET_PREFIX and vcpu is not stopped + type is KVM_S390_SIGP_STOP and a stop irq is already pending + type is KVM_S390_INT_EXTERNAL_CALL and an external call interrupt + is already pending + +Allows to inject an interrupt to the guest. + +Using struct kvm_s390_irq as a parameter allows +to inject additional payload which is not +possible via KVM_S390_INTERRUPT. + +Interrupt parameters are passed via kvm_s390_irq: + +struct kvm_s390_irq { + __u64 type; + union { + struct kvm_s390_io_info io; + struct kvm_s390_ext_info ext; + struct kvm_s390_pgm_info pgm; + struct kvm_s390_emerg_info emerg; + struct kvm_s390_extcall_info extcall; + struct kvm_s390_prefix_info prefix; + struct kvm_s390_stop_info stop; + struct kvm_s390_mchk_info mchk; + char reserved[64]; + } u; +}; + +type can be one of the following: + +KVM_S390_SIGP_STOP - sigp stop; parameter in .stop +KVM_S390_PROGRAM_INT - program check; parameters in .pgm +KVM_S390_SIGP_SET_PREFIX - sigp set prefix; parameters in .prefix +KVM_S390_RESTART - restart; no parameters +KVM_S390_INT_CLOCK_COMP - clock comparator interrupt; no parameters +KVM_S390_INT_CPU_TIMER - CPU timer interrupt; no parameters +KVM_S390_INT_EMERGENCY - sigp emergency; parameters in .emerg +KVM_S390_INT_EXTERNAL_CALL - sigp external call; parameters in .extcall +KVM_S390_MCHK - machine check interrupt; parameters in .mchk + + +Note that the vcpu ioctl is asynchronous to vcpu execution. + +4.94 KVM_S390_GET_IRQ_STATE + +Capability: KVM_CAP_S390_IRQ_STATE +Architectures: s390 +Type: vcpu ioctl +Parameters: struct kvm_s390_irq_state (out) +Returns: >= number of bytes copied into buffer, + -EINVAL if buffer size is 0, + -ENOBUFS if buffer size is too small to fit all pending interrupts, + -EFAULT if the buffer address was invalid + +This ioctl allows userspace to retrieve the complete state of all currently +pending interrupts in a single buffer. Use cases include migration +and introspection. The parameter structure contains the address of a +userspace buffer and its length: + +struct kvm_s390_irq_state { + __u64 buf; + __u32 flags; + __u32 len; + __u32 reserved[4]; +}; + +Userspace passes in the above struct and for each pending interrupt a +struct kvm_s390_irq is copied to the provided buffer. + +If -ENOBUFS is returned the buffer provided was too small and userspace +may retry with a bigger buffer. + +4.95 KVM_S390_SET_IRQ_STATE + +Capability: KVM_CAP_S390_IRQ_STATE +Architectures: s390 +Type: vcpu ioctl +Parameters: struct kvm_s390_irq_state (in) +Returns: 0 on success, + -EFAULT if the buffer address was invalid, + -EINVAL for an invalid buffer length (see below), + -EBUSY if there were already interrupts pending, + errors occurring when actually injecting the + interrupt. See KVM_S390_IRQ. + +This ioctl allows userspace to set the complete state of all cpu-local +interrupts currently pending for the vcpu. It is intended for restoring +interrupt state after a migration. The input parameter is a userspace buffer +containing a struct kvm_s390_irq_state: + +struct kvm_s390_irq_state { + __u64 buf; + __u32 len; + __u32 pad; +}; + +The userspace memory referenced by buf contains a struct kvm_s390_irq +for each interrupt to be injected into the guest. +If one of the interrupts could not be injected for some reason the +ioctl aborts. + +len must be a multiple of sizeof(struct kvm_s390_irq). It must be > 0 +and it must not exceed (max_vcpus + 32) * sizeof(struct kvm_s390_irq), +which is the maximum number of possibly pending cpu-local interrupts. + 5. The kvm_run structure ------------------------ @@ -3189,6 +3451,31 @@ Parameters: none This capability enables the in-kernel irqchip for s390. Please refer to "4.24 KVM_CREATE_IRQCHIP" for details. +6.9 KVM_CAP_MIPS_FPU + +Architectures: mips +Target: vcpu +Parameters: args[0] is reserved for future use (should be 0). + +This capability allows the use of the host Floating Point Unit by the guest. It +allows the Config1.FP bit to be set to enable the FPU in the guest. Once this is +done the KVM_REG_MIPS_FPR_* and KVM_REG_MIPS_FCR_* registers can be accessed +(depending on the current guest FPU register mode), and the Status.FR, +Config5.FRE bits are accessible via the KVM API and also from the guest, +depending on them being supported by the FPU. + +6.10 KVM_CAP_MIPS_MSA + +Architectures: mips +Target: vcpu +Parameters: args[0] is reserved for future use (should be 0). + +This capability allows the use of the MIPS SIMD Architecture (MSA) by the guest. +It allows the Config3.MSAP bit to be set to enable the use of MSA by the guest. +Once this is done the KVM_REG_MIPS_VEC_* and KVM_REG_MIPS_MSA_* registers can be +accessed, and the Config5.MSAEn bit is accessible via the KVM API and also from +the guest. + 7. Capabilities that can be enabled on VMs ------------------------------------------ @@ -3248,3 +3535,41 @@ All other orders will be handled completely in user space. Only privileged operation exceptions will be checked for in the kernel (or even in the hardware prior to interception). If this capability is not enabled, the old way of handling SIGP orders is used (partially in kernel and user space). + +7.3 KVM_CAP_S390_VECTOR_REGISTERS + +Architectures: s390 +Parameters: none +Returns: 0 on success, negative value on error + +Allows use of the vector registers introduced with z13 processor, and +provides for the synchronization between host and user space. Will +return -EINVAL if the machine does not support vectors. + +7.4 KVM_CAP_S390_USER_STSI + +Architectures: s390 +Parameters: none + +This capability allows post-handlers for the STSI instruction. After +initial handling in the kernel, KVM exits to user space with +KVM_EXIT_S390_STSI to allow user space to insert further data. + +Before exiting to userspace, kvm handlers should fill in s390_stsi field of +vcpu->run: +struct { + __u64 addr; + __u8 ar; + __u8 reserved; + __u8 fc; + __u8 sel1; + __u16 sel2; +} s390_stsi; + +@addr - guest address of STSI SYSIB +@fc - function code +@sel1 - selector 1 +@sel2 - selector 2 +@ar - access register number + +KVM handlers should exit to userspace with rc = -EREMOTE. diff --git a/Documentation/virtual/kvm/devices/s390_flic.txt b/Documentation/virtual/kvm/devices/s390_flic.txt index 4ceef53164b0..d1ad9d5cae46 100644 --- a/Documentation/virtual/kvm/devices/s390_flic.txt +++ b/Documentation/virtual/kvm/devices/s390_flic.txt @@ -27,6 +27,9 @@ Groups: Copies all floating interrupts into a buffer provided by userspace. When the buffer is too small it returns -ENOMEM, which is the indication for userspace to try again with a bigger buffer. + -ENOBUFS is returned when the allocation of a kernelspace buffer has + failed. + -EFAULT is returned when copying data to userspace failed. All interrupts remain pending, i.e. are not deleted from the list of currently pending interrupts. attr->addr contains the userspace address of the buffer into which all diff --git a/MAINTAINERS b/MAINTAINERS index efbcb50e4969..b84686826b23 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5591,6 +5591,8 @@ S: Supported F: Documentation/*/kvm*.txt F: Documentation/virtual/kvm/ F: arch/*/kvm/ +F: arch/x86/kernel/kvm.c +F: arch/x86/kernel/kvmclock.c F: arch/*/include/asm/kvm* F: include/linux/kvm* F: include/uapi/linux/kvm* @@ -8559,6 +8561,7 @@ F: include/uapi/linux/timex.h F: kernel/time/clocksource.c F: kernel/time/time*.c F: kernel/time/ntp.c +F: tools/testing/selftests/timers/ SC1200 WDT DRIVER M: Zwane Mwaikambo <zwanem@gmail.com> @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 0 SUBLEVEL = 0 -EXTRAVERSION = -rc7 +EXTRAVERSION = NAME = Hurr durr I'ma sheep # *DOCUMENTATION* @@ -779,6 +779,7 @@ KBUILD_ARFLAGS := $(call ar-option,D) # check for 'asm goto' ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC)), y) KBUILD_CFLAGS += -DCC_HAVE_ASM_GOTO + KBUILD_AFLAGS += -DCC_HAVE_ASM_GOTO endif include $(srctree)/scripts/Makefile.kasan diff --git a/arch/alpha/kernel/rtc.c b/arch/alpha/kernel/rtc.c index c8d284d8521f..f535a3fd0f60 100644 --- a/arch/alpha/kernel/rtc.c +++ b/arch/alpha/kernel/rtc.c @@ -116,7 +116,7 @@ alpha_rtc_set_time(struct device *dev, struct rtc_time *tm) } static int -alpha_rtc_set_mmss(struct device *dev, unsigned long nowtime) +alpha_rtc_set_mmss(struct device *dev, time64_t nowtime) { int retval = 0; int real_seconds, real_minutes, cmos_minutes; @@ -211,7 +211,7 @@ alpha_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long arg) static const struct rtc_class_ops alpha_rtc_ops = { .read_time = alpha_rtc_read_time, .set_time = alpha_rtc_set_time, - .set_mmss = alpha_rtc_set_mmss, + .set_mmss64 = alpha_rtc_set_mmss, .ioctl = alpha_rtc_ioctl, }; @@ -276,7 +276,7 @@ do_remote_mmss(void *data) } static int -remote_set_mmss(struct device *dev, unsigned long now) +remote_set_mmss(struct device *dev, time64_t now) { union remote_data x; if (smp_processor_id() != boot_cpuid) { @@ -290,7 +290,7 @@ remote_set_mmss(struct device *dev, unsigned long now) static const struct rtc_class_ops remote_rtc_ops = { .read_time = remote_read_time, .set_time = remote_set_time, - .set_mmss = remote_set_mmss, + .set_mmss64 = remote_set_mmss, .ioctl = alpha_rtc_ioctl, }; #endif diff --git a/arch/arm/common/bL_switcher.c b/arch/arm/common/bL_switcher.c index 6eaddc47c43d..37dc0fe1093f 100644 --- a/arch/arm/common/bL_switcher.c +++ b/arch/arm/common/bL_switcher.c @@ -151,8 +151,6 @@ static int bL_switch_to(unsigned int new_cluster_id) unsigned int mpidr, this_cpu, that_cpu; unsigned int ob_mpidr, ob_cpu, ob_cluster, ib_mpidr, ib_cpu, ib_cluster; struct completion inbound_alive; - struct tick_device *tdev; - enum clock_event_mode tdev_mode; long volatile *handshake_ptr; int ipi_nr, ret; @@ -219,13 +217,7 @@ static int bL_switch_to(unsigned int new_cluster_id) /* redirect GIC's SGIs to our counterpart */ gic_migrate_target(bL_gic_id[ib_cpu][ib_cluster]); - tdev = tick_get_device(this_cpu); - if (tdev && !cpumask_equal(tdev->evtdev->cpumask, cpumask_of(this_cpu))) - tdev = NULL; - if (tdev) { - tdev_mode = tdev->evtdev->mode; - clockevents_set_mode(tdev->evtdev, CLOCK_EVT_MODE_SHUTDOWN); - } + tick_suspend_local(); ret = cpu_pm_enter(); @@ -251,11 +243,7 @@ static int bL_switch_to(unsigned int new_cluster_id) ret = cpu_pm_exit(); - if (tdev) { - clockevents_set_mode(tdev->evtdev, tdev_mode); - clockevents_program_event(tdev->evtdev, - tdev->evtdev->next_event, 1); - } + tick_resume_local(); trace_cpu_migrate_finish(ktime_get_real_ns(), ib_mpidr); local_fiq_enable(); diff --git a/arch/arm/include/asm/jump_label.h b/arch/arm/include/asm/jump_label.h index 70f9b9bfb1f9..5f337dc5c108 100644 --- a/arch/arm/include/asm/jump_label.h +++ b/arch/arm/include/asm/jump_label.h @@ -1,7 +1,7 @@ #ifndef _ASM_ARM_JUMP_LABEL_H #define _ASM_ARM_JUMP_LABEL_H -#ifdef __KERNEL__ +#ifndef __ASSEMBLY__ #include <linux/types.h> @@ -27,8 +27,6 @@ l_yes: return true; } -#endif /* __KERNEL__ */ - typedef u32 jump_label_t; struct jump_entry { @@ -37,4 +35,5 @@ struct jump_entry { jump_label_t key; }; +#endif /* __ASSEMBLY__ */ #endif diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h index 816db0bf2dd8..d995821f1698 100644 --- a/arch/arm/include/asm/kvm_arm.h +++ b/arch/arm/include/asm/kvm_arm.h @@ -185,6 +185,7 @@ #define HSR_COND (0xfU << HSR_COND_SHIFT) #define FSC_FAULT (0x04) +#define FSC_ACCESS (0x08) #define FSC_PERM (0x0c) /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */ diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index 41008cd7c53f..d71607c16601 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -27,6 +27,8 @@ #include <asm/fpstate.h> #include <kvm/arm_arch_timer.h> +#define __KVM_HAVE_ARCH_INTC_INITIALIZED + #if defined(CONFIG_KVM_ARM_MAX_VCPUS) #define KVM_MAX_VCPUS CONFIG_KVM_ARM_MAX_VCPUS #else @@ -165,19 +167,10 @@ void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu); int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices); +int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); +int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); /* We do not have shadow page tables, hence the empty hooks */ -static inline int kvm_age_hva(struct kvm *kvm, unsigned long start, - unsigned long end) -{ - return 0; -} - -static inline int kvm_test_age_hva(struct kvm *kvm, unsigned long hva) -{ - return 0; -} - static inline void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm, unsigned long address) { diff --git a/arch/arm/include/asm/kvm_mmio.h b/arch/arm/include/asm/kvm_mmio.h index 3f83db2f6cf0..d8e90c8cb5fa 100644 --- a/arch/arm/include/asm/kvm_mmio.h +++ b/arch/arm/include/asm/kvm_mmio.h @@ -28,28 +28,6 @@ struct kvm_decode { bool sign_extend; }; -/* - * The in-kernel MMIO emulation code wants to use a copy of run->mmio, - * which is an anonymous type. Use our own type instead. - */ -struct kvm_exit_mmio { - phys_addr_t phys_addr; - u8 data[8]; - u32 len; - bool is_write; - void *private; -}; - -static inline void kvm_prepare_mmio(struct kvm_run *run, - struct kvm_exit_mmio *mmio) -{ - run->mmio.phys_addr = mmio->phys_addr; - run->mmio.len = mmio->len; - run->mmio.is_write = mmio->is_write; - memcpy(run->mmio.data, mmio->data, mmio->len); - run->exit_reason = KVM_EXIT_MMIO; -} - int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run); int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run, phys_addr_t fault_ipa); diff --git a/arch/arm/include/asm/mach/time.h b/arch/arm/include/asm/mach/time.h index 90c12e1e695c..0f79e4dec7f9 100644 --- a/arch/arm/include/asm/mach/time.h +++ b/arch/arm/include/asm/mach/time.h @@ -12,8 +12,7 @@ extern void timer_tick(void); -struct timespec; -typedef void (*clock_access_fn)(struct timespec *); +typedef void (*clock_access_fn)(struct timespec64 *); extern int register_persistent_clock(clock_access_fn read_boot, clock_access_fn read_persistent); diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h index 0db25bc32864..2499867dd0d8 100644 --- a/arch/arm/include/uapi/asm/kvm.h +++ b/arch/arm/include/uapi/asm/kvm.h @@ -198,6 +198,9 @@ struct kvm_arch_memory_slot { /* Highest supported SPI, from VGIC_NR_IRQS */ #define KVM_ARM_IRQ_GIC_MAX 127 +/* One single KVM irqchip, ie. the VGIC */ +#define KVM_NR_IRQCHIPS 1 + /* PSCI interface */ #define KVM_PSCI_FN_BASE 0x95c1ba5e #define KVM_PSCI_FN(n) (KVM_PSCI_FN_BASE + (n)) diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c index 2d2d6087b9b1..488eaac56028 100644 --- a/arch/arm/kernel/asm-offsets.c +++ b/arch/arm/kernel/asm-offsets.c @@ -190,7 +190,6 @@ int main(void) DEFINE(VCPU_HxFAR, offsetof(struct kvm_vcpu, arch.fault.hxfar)); DEFINE(VCPU_HPFAR, offsetof(struct kvm_vcpu, arch.fault.hpfar)); DEFINE(VCPU_HYP_PC, offsetof(struct kvm_vcpu, arch.fault.hyp_pc)); -#ifdef CONFIG_KVM_ARM_VGIC DEFINE(VCPU_VGIC_CPU, offsetof(struct kvm_vcpu, arch.vgic_cpu)); DEFINE(VGIC_V2_CPU_HCR, offsetof(struct vgic_cpu, vgic_v2.vgic_hcr)); DEFINE(VGIC_V2_CPU_VMCR, offsetof(struct vgic_cpu, vgic_v2.vgic_vmcr)); @@ -200,14 +199,11 @@ int main(void) DEFINE(VGIC_V2_CPU_APR, offsetof(struct vgic_cpu, vgic_v2.vgic_apr)); DEFINE(VGIC_V2_CPU_LR, offsetof(struct vgic_cpu, vgic_v2.vgic_lr)); DEFINE(VGIC_CPU_NR_LR, offsetof(struct vgic_cpu, nr_lr)); -#ifdef CONFIG_KVM_ARM_TIMER DEFINE(VCPU_TIMER_CNTV_CTL, offsetof(struct kvm_vcpu, arch.timer_cpu.cntv_ctl)); DEFINE(VCPU_TIMER_CNTV_CVAL, offsetof(struct kvm_vcpu, arch.timer_cpu.cntv_cval)); DEFINE(KVM_TIMER_CNTVOFF, offsetof(struct kvm, arch.timer.cntvoff)); DEFINE(KVM_TIMER_ENABLED, offsetof(struct kvm, arch.timer.enabled)); -#endif DEFINE(KVM_VGIC_VCTRL, offsetof(struct kvm, arch.vgic.vctrl_base)); -#endif DEFINE(KVM_VTTBR, offsetof(struct kvm, arch.vttbr)); #endif return 0; diff --git a/arch/arm/kernel/time.c b/arch/arm/kernel/time.c index 0cc7e58c47cc..a66e37e211a9 100644 --- a/arch/arm/kernel/time.c +++ b/arch/arm/kernel/time.c @@ -76,7 +76,7 @@ void timer_tick(void) } #endif -static void dummy_clock_access(struct timespec *ts) +static void dummy_clock_access(struct timespec64 *ts) { ts->tv_sec = 0; ts->tv_nsec = 0; @@ -85,12 +85,12 @@ static void dummy_clock_access(struct timespec *ts) static clock_access_fn __read_persistent_clock = dummy_clock_access; static clock_access_fn __read_boot_clock = dummy_clock_access;; -void read_persistent_clock(struct timespec *ts) +void read_persistent_clock64(struct timespec64 *ts) { __read_persistent_clock(ts); } -void read_boot_clock(struct timespec *ts) +void read_boot_clock64(struct timespec64 *ts) { __read_boot_clock(ts); } diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig index 338ace78ed18..f1f79d104309 100644 --- a/arch/arm/kvm/Kconfig +++ b/arch/arm/kvm/Kconfig @@ -18,6 +18,7 @@ if VIRTUALIZATION config KVM bool "Kernel-based Virtual Machine (KVM) support" + depends on MMU && OF select PREEMPT_NOTIFIERS select ANON_INODES select HAVE_KVM_CPU_RELAX_INTERCEPT @@ -26,10 +27,12 @@ config KVM select KVM_ARM_HOST select KVM_GENERIC_DIRTYLOG_READ_PROTECT select SRCU - depends on ARM_VIRT_EXT && ARM_LPAE + select MMU_NOTIFIER + select HAVE_KVM_EVENTFD + select HAVE_KVM_IRQFD + depends on ARM_VIRT_EXT && ARM_LPAE && ARM_ARCH_TIMER ---help--- - Support hosting virtualized guest machines. You will also - need to select one or more of the processor modules below. + Support hosting virtualized guest machines. This module provides access to the hardware capabilities through a character device node named /dev/kvm. @@ -37,10 +40,7 @@ config KVM If unsure, say N. config KVM_ARM_HOST - bool "KVM host support for ARM cpus." - depends on KVM - depends on MMU - select MMU_NOTIFIER + bool ---help--- Provides host support for ARM processors. @@ -55,20 +55,4 @@ config KVM_ARM_MAX_VCPUS large, so only choose a reasonable number that you expect to actually use. -config KVM_ARM_VGIC - bool "KVM support for Virtual GIC" - depends on KVM_ARM_HOST && OF - select HAVE_KVM_IRQCHIP - default y - ---help--- - Adds support for a hardware assisted, in-kernel GIC emulation. - -config KVM_ARM_TIMER - bool "KVM support for Architected Timers" - depends on KVM_ARM_VGIC && ARM_ARCH_TIMER - select HAVE_KVM_IRQCHIP - default y - ---help--- - Adds support for the Architected Timers in virtual machines - endif # VIRTUALIZATION diff --git a/arch/arm/kvm/Makefile b/arch/arm/kvm/Makefile index 443b8bea43e9..139e46c08b6e 100644 --- a/arch/arm/kvm/Makefile +++ b/arch/arm/kvm/Makefile @@ -7,7 +7,7 @@ ifeq ($(plus_virt),+virt) plus_virt_def := -DREQUIRES_VIRT=1 endif -ccflags-y += -Ivirt/kvm -Iarch/arm/kvm +ccflags-y += -Iarch/arm/kvm CFLAGS_arm.o := -I. $(plus_virt_def) CFLAGS_mmu.o := -I. @@ -15,12 +15,12 @@ AFLAGS_init.o := -Wa,-march=armv7-a$(plus_virt) AFLAGS_interrupts.o := -Wa,-march=armv7-a$(plus_virt) KVM := ../../../virt/kvm -kvm-arm-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o +kvm-arm-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o obj-y += kvm-arm.o init.o interrupts.o obj-y += arm.o handle_exit.o guest.o mmu.o emulate.o reset.o obj-y += coproc.o coproc_a15.o coproc_a7.o mmio.o psci.o perf.o -obj-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic.o -obj-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v2.o -obj-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v2-emul.o -obj-$(CONFIG_KVM_ARM_TIMER) += $(KVM)/arm/arch_timer.o +obj-y += $(KVM)/arm/vgic.o +obj-y += $(KVM)/arm/vgic-v2.o +obj-y += $(KVM)/arm/vgic-v2-emul.o +obj-y += $(KVM)/arm/arch_timer.o diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index 5560f74f9eee..6f536451ab78 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -61,8 +61,6 @@ static atomic64_t kvm_vmid_gen = ATOMIC64_INIT(1); static u8 kvm_next_vmid; static DEFINE_SPINLOCK(kvm_vmid_lock); -static bool vgic_present; - static void kvm_arm_set_running_vcpu(struct kvm_vcpu *vcpu) { BUG_ON(preemptible()); @@ -173,8 +171,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) int r; switch (ext) { case KVM_CAP_IRQCHIP: - r = vgic_present; - break; + case KVM_CAP_IRQFD: + case KVM_CAP_IOEVENTFD: case KVM_CAP_DEVICE_CTRL: case KVM_CAP_USER_MEMORY: case KVM_CAP_SYNC_MMU: @@ -183,6 +181,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_ARM_PSCI: case KVM_CAP_ARM_PSCI_0_2: case KVM_CAP_READONLY_MEM: + case KVM_CAP_MP_STATE: r = 1; break; case KVM_CAP_COALESCED_MMIO: @@ -268,7 +267,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) { - return 0; + return kvm_timer_should_fire(vcpu); } int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) @@ -313,13 +312,29 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { - return -EINVAL; + if (vcpu->arch.pause) + mp_state->mp_state = KVM_MP_STATE_STOPPED; + else + mp_state->mp_state = KVM_MP_STATE_RUNNABLE; + + return 0; } int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { - return -EINVAL; + switch (mp_state->mp_state) { + case KVM_MP_STATE_RUNNABLE: + vcpu->arch.pause = false; + break; + case KVM_MP_STATE_STOPPED: + vcpu->arch.pause = true; + break; + default: + return -EINVAL; + } + + return 0; } /** @@ -452,6 +467,11 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu) return 0; } +bool kvm_arch_intc_initialized(struct kvm *kvm) +{ + return vgic_initialized(kvm); +} + static void vcpu_pause(struct kvm_vcpu *vcpu) { wait_queue_head_t *wq = kvm_arch_vcpu_wq(vcpu); @@ -831,8 +851,6 @@ static int kvm_vm_ioctl_set_device_addr(struct kvm *kvm, switch (dev_id) { case KVM_ARM_DEVICE_VGIC_V2: - if (!vgic_present) - return -ENXIO; return kvm_vgic_addr(kvm, type, &dev_addr->addr, true); default: return -ENODEV; @@ -847,10 +865,7 @@ long kvm_arch_vm_ioctl(struct file *filp, switch (ioctl) { case KVM_CREATE_IRQCHIP: { - if (vgic_present) - return kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); - else - return -ENXIO; + return kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); } case KVM_ARM_SET_DEVICE_ADDR: { struct kvm_arm_device_addr dev_addr; @@ -1035,10 +1050,6 @@ static int init_hyp_mode(void) if (err) goto out_free_context; -#ifdef CONFIG_KVM_ARM_VGIC - vgic_present = true; -#endif - /* * Init HYP architected timer support */ diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c index 384bab67c462..d503fbb787d3 100644 --- a/arch/arm/kvm/guest.c +++ b/arch/arm/kvm/guest.c @@ -109,22 +109,6 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) return -EINVAL; } -#ifndef CONFIG_KVM_ARM_TIMER - -#define NUM_TIMER_REGS 0 - -static int copy_timer_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) -{ - return 0; -} - -static bool is_timer_reg(u64 index) -{ - return false; -} - -#else - #define NUM_TIMER_REGS 3 static bool is_timer_reg(u64 index) @@ -152,8 +136,6 @@ static int copy_timer_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) return 0; } -#endif - static int set_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { void __user *uaddr = (void __user *)(long)reg->addr; diff --git a/arch/arm/kvm/interrupts_head.S b/arch/arm/kvm/interrupts_head.S index 14d488388480..35e4a3a0c476 100644 --- a/arch/arm/kvm/interrupts_head.S +++ b/arch/arm/kvm/interrupts_head.S @@ -402,7 +402,6 @@ vcpu .req r0 @ vcpu pointer always in r0 * Assumes vcpu pointer in vcpu reg */ .macro save_vgic_state -#ifdef CONFIG_KVM_ARM_VGIC /* Get VGIC VCTRL base into r2 */ ldr r2, [vcpu, #VCPU_KVM] ldr r2, [r2, #KVM_VGIC_VCTRL] @@ -460,7 +459,6 @@ ARM_BE8(rev r6, r6 ) subs r4, r4, #1 bne 1b 2: -#endif .endm /* @@ -469,7 +467,6 @@ ARM_BE8(rev r6, r6 ) * Assumes vcpu pointer in vcpu reg */ .macro restore_vgic_state -#ifdef CONFIG_KVM_ARM_VGIC /* Get VGIC VCTRL base into r2 */ ldr r2, [vcpu, #VCPU_KVM] ldr r2, [r2, #KVM_VGIC_VCTRL] @@ -501,7 +498,6 @@ ARM_BE8(rev r6, r6 ) subs r4, r4, #1 bne 1b 2: -#endif .endm #define CNTHCTL_PL1PCTEN (1 << 0) @@ -515,7 +511,6 @@ ARM_BE8(rev r6, r6 ) * Clobbers r2-r5 */ .macro save_timer_state -#ifdef CONFIG_KVM_ARM_TIMER ldr r4, [vcpu, #VCPU_KVM] ldr r2, [r4, #KVM_TIMER_ENABLED] cmp r2, #0 @@ -537,7 +532,6 @@ ARM_BE8(rev r6, r6 ) mcrr p15, 4, r2, r2, c14 @ CNTVOFF 1: -#endif @ Allow physical timer/counter access for the host mrc p15, 4, r2, c14, c1, 0 @ CNTHCTL orr r2, r2, #(CNTHCTL_PL1PCEN | CNTHCTL_PL1PCTEN) @@ -559,7 +553,6 @@ ARM_BE8(rev r6, r6 ) bic r2, r2, #CNTHCTL_PL1PCEN mcr p15, 4, r2, c14, c1, 0 @ CNTHCTL -#ifdef CONFIG_KVM_ARM_TIMER ldr r4, [vcpu, #VCPU_KVM] ldr r2, [r4, #KVM_TIMER_ENABLED] cmp r2, #0 @@ -579,7 +572,6 @@ ARM_BE8(rev r6, r6 ) and r2, r2, #3 mcr p15, 0, r2, c14, c3, 1 @ CNTV_CTL 1: -#endif .endm .equ vmentry, 0 diff --git a/arch/arm/kvm/mmio.c b/arch/arm/kvm/mmio.c index 5d3bfc0eb3f0..974b1c606d04 100644 --- a/arch/arm/kvm/mmio.c +++ b/arch/arm/kvm/mmio.c @@ -121,12 +121,11 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run) return 0; } -static int decode_hsr(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, - struct kvm_exit_mmio *mmio) +static int decode_hsr(struct kvm_vcpu *vcpu, bool *is_write, int *len) { unsigned long rt; - int len; - bool is_write, sign_extend; + int access_size; + bool sign_extend; if (kvm_vcpu_dabt_isextabt(vcpu)) { /* cache operation on I/O addr, tell guest unsupported */ @@ -140,17 +139,15 @@ static int decode_hsr(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, return 1; } - len = kvm_vcpu_dabt_get_as(vcpu); - if (unlikely(len < 0)) - return len; + access_size = kvm_vcpu_dabt_get_as(vcpu); + if (unlikely(access_size < 0)) + return access_size; - is_write = kvm_vcpu_dabt_iswrite(vcpu); + *is_write = kvm_vcpu_dabt_iswrite(vcpu); sign_extend = kvm_vcpu_dabt_issext(vcpu); rt = kvm_vcpu_dabt_get_rd(vcpu); - mmio->is_write = is_write; - mmio->phys_addr = fault_ipa; - mmio->len = len; + *len = access_size; vcpu->arch.mmio_decode.sign_extend = sign_extend; vcpu->arch.mmio_decode.rt = rt; @@ -165,20 +162,20 @@ static int decode_hsr(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run, phys_addr_t fault_ipa) { - struct kvm_exit_mmio mmio; unsigned long data; unsigned long rt; int ret; + bool is_write; + int len; + u8 data_buf[8]; /* - * Prepare MMIO operation. First stash it in a private - * structure that we can use for in-kernel emulation. If the - * kernel can't handle it, copy it into run->mmio and let user - * space do its magic. + * Prepare MMIO operation. First decode the syndrome data we get + * from the CPU. Then try if some in-kernel emulation feels + * responsible, otherwise let user space do its magic. */ - if (kvm_vcpu_dabt_isvalid(vcpu)) { - ret = decode_hsr(vcpu, fault_ipa, &mmio); + ret = decode_hsr(vcpu, &is_write, &len); if (ret) return ret; } else { @@ -188,21 +185,34 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run, rt = vcpu->arch.mmio_decode.rt; - if (mmio.is_write) { - data = vcpu_data_guest_to_host(vcpu, *vcpu_reg(vcpu, rt), - mmio.len); + if (is_write) { + data = vcpu_data_guest_to_host(vcpu, *vcpu_reg(vcpu, rt), len); + + trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, len, fault_ipa, data); + mmio_write_buf(data_buf, len, data); - trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, mmio.len, - fault_ipa, data); - mmio_write_buf(mmio.data, mmio.len, data); + ret = kvm_io_bus_write(vcpu, KVM_MMIO_BUS, fault_ipa, len, + data_buf); } else { - trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, mmio.len, + trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, len, fault_ipa, 0); + + ret = kvm_io_bus_read(vcpu, KVM_MMIO_BUS, fault_ipa, len, + data_buf); } - if (vgic_handle_mmio(vcpu, run, &mmio)) + /* Now prepare kvm_run for the potential return to userland. */ + run->mmio.is_write = is_write; + run->mmio.phys_addr = fault_ipa; + run->mmio.len = len; + memcpy(run->mmio.data, data_buf, len); + + if (!ret) { + /* We handled the access successfully in the kernel. */ + kvm_handle_mmio_return(vcpu, run); return 1; + } - kvm_prepare_mmio(run, &mmio); + run->exit_reason = KVM_EXIT_MMIO; return 0; } diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 5656d79c5a44..15b050d46fc9 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -1330,10 +1330,51 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, out_unlock: spin_unlock(&kvm->mmu_lock); + kvm_set_pfn_accessed(pfn); kvm_release_pfn_clean(pfn); return ret; } +/* + * Resolve the access fault by making the page young again. + * Note that because the faulting entry is guaranteed not to be + * cached in the TLB, we don't need to invalidate anything. + */ +static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa) +{ + pmd_t *pmd; + pte_t *pte; + pfn_t pfn; + bool pfn_valid = false; + + trace_kvm_access_fault(fault_ipa); + + spin_lock(&vcpu->kvm->mmu_lock); + + pmd = stage2_get_pmd(vcpu->kvm, NULL, fault_ipa); + if (!pmd || pmd_none(*pmd)) /* Nothing there */ + goto out; + + if (kvm_pmd_huge(*pmd)) { /* THP, HugeTLB */ + *pmd = pmd_mkyoung(*pmd); + pfn = pmd_pfn(*pmd); + pfn_valid = true; + goto out; + } + + pte = pte_offset_kernel(pmd, fault_ipa); + if (pte_none(*pte)) /* Nothing there either */ + goto out; + + *pte = pte_mkyoung(*pte); /* Just a page... */ + pfn = pte_pfn(*pte); + pfn_valid = true; +out: + spin_unlock(&vcpu->kvm->mmu_lock); + if (pfn_valid) + kvm_set_pfn_accessed(pfn); +} + /** * kvm_handle_guest_abort - handles all 2nd stage aborts * @vcpu: the VCPU pointer @@ -1364,7 +1405,8 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run) /* Check the stage-2 fault is trans. fault or write fault */ fault_status = kvm_vcpu_trap_get_fault_type(vcpu); - if (fault_status != FSC_FAULT && fault_status != FSC_PERM) { + if (fault_status != FSC_FAULT && fault_status != FSC_PERM && + fault_status != FSC_ACCESS) { kvm_err("Unsupported FSC: EC=%#x xFSC=%#lx ESR_EL2=%#lx\n", kvm_vcpu_trap_get_class(vcpu), (unsigned long)kvm_vcpu_trap_get_fault(vcpu), @@ -1400,6 +1442,12 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run) /* Userspace should not be able to register out-of-bounds IPAs */ VM_BUG_ON(fault_ipa >= KVM_PHYS_SIZE); + if (fault_status == FSC_ACCESS) { + handle_access_fault(vcpu, fault_ipa); + ret = 1; + goto out_unlock; + } + ret = user_mem_abort(vcpu, fault_ipa, memslot, hva, fault_status); if (ret == 0) ret = 1; @@ -1408,15 +1456,16 @@ out_unlock: return ret; } -static void handle_hva_to_gpa(struct kvm *kvm, - unsigned long start, - unsigned long end, - void (*handler)(struct kvm *kvm, - gpa_t gpa, void *data), - void *data) +static int handle_hva_to_gpa(struct kvm *kvm, + unsigned long start, + unsigned long end, + int (*handler)(struct kvm *kvm, + gpa_t gpa, void *data), + void *data) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; + int ret = 0; slots = kvm_memslots(kvm); @@ -1440,14 +1489,17 @@ static void handle_hva_to_gpa(struct kvm *kvm, for (; gfn < gfn_end; ++gfn) { gpa_t gpa = gfn << PAGE_SHIFT; - handler(kvm, gpa, data); + ret |= handler(kvm, gpa, data); } } + + return ret; } -static void kvm_unmap_hva_handler(struct kvm *kvm, gpa_t gpa, void *data) +static int kvm_unmap_hva_handler(struct kvm *kvm, gpa_t gpa, void *data) { unmap_stage2_range(kvm, gpa, PAGE_SIZE); + return 0; } int kvm_unmap_hva(struct kvm *kvm, unsigned long hva) @@ -1473,7 +1525,7 @@ int kvm_unmap_hva_range(struct kvm *kvm, return 0; } -static void kvm_set_spte_handler(struct kvm *kvm, gpa_t gpa, void *data) +static int kvm_set_spte_handler(struct kvm *kvm, gpa_t gpa, void *data) { pte_t *pte = (pte_t *)data; @@ -1485,6 +1537,7 @@ static void kvm_set_spte_handler(struct kvm *kvm, gpa_t gpa, void *data) * through this calling path. */ stage2_set_pte(kvm, NULL, gpa, pte, 0); + return 0; } @@ -1501,6 +1554,67 @@ void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte) handle_hva_to_gpa(kvm, hva, end, &kvm_set_spte_handler, &stage2_pte); } +static int kvm_age_hva_handler(struct kvm *kvm, gpa_t gpa, void *data) +{ + pmd_t *pmd; + pte_t *pte; + + pmd = stage2_get_pmd(kvm, NULL, gpa); + if (!pmd || pmd_none(*pmd)) /* Nothing there */ + return 0; + + if (kvm_pmd_huge(*pmd)) { /* THP, HugeTLB */ + if (pmd_young(*pmd)) { + *pmd = pmd_mkold(*pmd); + return 1; + } + + return 0; + } + + pte = pte_offset_kernel(pmd, gpa); + if (pte_none(*pte)) + return 0; + + if (pte_young(*pte)) { + *pte = pte_mkold(*pte); /* Just a page... */ + return 1; + } + + return 0; +} + +static int kvm_test_age_hva_handler(struct kvm *kvm, gpa_t gpa, void *data) +{ + pmd_t *pmd; + pte_t *pte; + + pmd = stage2_get_pmd(kvm, NULL, gpa); + if (!pmd || pmd_none(*pmd)) /* Nothing there */ + return 0; + + if (kvm_pmd_huge(*pmd)) /* THP, HugeTLB */ + return pmd_young(*pmd); + + pte = pte_offset_kernel(pmd, gpa); + if (!pte_none(*pte)) /* Just a page... */ + return pte_young(*pte); + + return 0; +} + +int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end) +{ + trace_kvm_age_hva(start, end); + return handle_hva_to_gpa(kvm, start, end, kvm_age_hva_handler, NULL); +} + +int kvm_test_age_hva(struct kvm *kvm, unsigned long hva) +{ + trace_kvm_test_age_hva(hva); + return handle_hva_to_gpa(kvm, hva, hva, kvm_test_age_hva_handler, NULL); +} + void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu) { mmu_free_memory_cache(&vcpu->arch.mmu_page_cache); diff --git a/arch/arm/kvm/trace.h b/arch/arm/kvm/trace.h index 6817664b46b8..0ec35392d208 100644 --- a/arch/arm/kvm/trace.h +++ b/arch/arm/kvm/trace.h @@ -68,6 +68,21 @@ TRACE_EVENT(kvm_guest_fault, __entry->hxfar, __entry->vcpu_pc) ); +TRACE_EVENT(kvm_access_fault, + TP_PROTO(unsigned long ipa), + TP_ARGS(ipa), + + TP_STRUCT__entry( + __field( unsigned long, ipa ) + ), + + TP_fast_assign( + __entry->ipa = ipa; + ), + + TP_printk("IPA: %lx", __entry->ipa) +); + TRACE_EVENT(kvm_irq_line, TP_PROTO(unsigned int type, int vcpu_idx, int irq_num, int level), TP_ARGS(type, vcpu_idx, irq_num, level), @@ -210,6 +225,39 @@ TRACE_EVENT(kvm_set_spte_hva, TP_printk("mmu notifier set pte hva: %#08lx", __entry->hva) ); +TRACE_EVENT(kvm_age_hva, + TP_PROTO(unsigned long start, unsigned long end), + TP_ARGS(start, end), + + TP_STRUCT__entry( + __field( unsigned long, start ) + __field( unsigned long, end ) + ), + + TP_fast_assign( + __entry->start = start; + __entry->end = end; + ), + + TP_printk("mmu notifier age hva: %#08lx -- %#08lx", + __entry->start, __entry->end) +); + +TRACE_EVENT(kvm_test_age_hva, + TP_PROTO(unsigned long hva), + TP_ARGS(hva), + + TP_STRUCT__entry( + __field( unsigned long, hva ) + ), + + TP_fast_assign( + __entry->hva = hva; + ), + + TP_printk("mmu notifier test age hva: %#08lx", __entry->hva) +); + TRACE_EVENT(kvm_hvc, TP_PROTO(unsigned long vcpu_pc, unsigned long r0, unsigned long imm), TP_ARGS(vcpu_pc, r0, imm), diff --git a/arch/arm/mach-omap2/cpuidle44xx.c b/arch/arm/mach-omap2/cpuidle44xx.c index 01e398a868bc..57d429830e09 100644 --- a/arch/arm/mach-omap2/cpuidle44xx.c +++ b/arch/arm/mach-omap2/cpuidle44xx.c @@ -14,7 +14,7 @@ #include <linux/cpuidle.h> #include <linux/cpu_pm.h> #include <linux/export.h> -#include <linux/clockchips.h> +#include <linux/tick.h> #include <asm/cpuidle.h> #include <asm/proc-fns.h> @@ -84,7 +84,6 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev, { struct idle_statedata *cx = state_ptr + index; u32 mpuss_can_lose_context = 0; - int cpu_id = smp_processor_id(); /* * CPU0 has to wait and stay ON until CPU1 is OFF state. @@ -112,7 +111,7 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev, mpuss_can_lose_context = (cx->mpu_state == PWRDM_POWER_RET) && (cx->mpu_logic_state == PWRDM_POWER_OFF); - clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu_id); + tick_broadcast_enter(); /* * Call idle CPU PM enter notifier chain so that @@ -169,7 +168,7 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev, if (dev->cpu == 0 && mpuss_can_lose_context) cpu_cluster_pm_exit(); - clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu_id); + tick_broadcast_exit(); fail: cpuidle_coupled_parallel_barrier(dev, &abort_barrier); @@ -184,8 +183,7 @@ fail: */ static void omap_setup_broadcast_timer(void *arg) { - int cpu = smp_processor_id(); - clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ON, &cpu); + tick_broadcast_enable(); } static struct cpuidle_driver omap4_idle_driver = { diff --git a/arch/arm/mach-tegra/cpuidle-tegra114.c b/arch/arm/mach-tegra/cpuidle-tegra114.c index f2b586d7b15d..155807fa6fdd 100644 --- a/arch/arm/mach-tegra/cpuidle-tegra114.c +++ b/arch/arm/mach-tegra/cpuidle-tegra114.c @@ -15,7 +15,7 @@ */ #include <asm/firmware.h> -#include <linux/clockchips.h> +#include <linux/tick.h> #include <linux/cpuidle.h> #include <linux/cpu_pm.h> #include <linux/kernel.h> @@ -44,7 +44,7 @@ static int tegra114_idle_power_down(struct cpuidle_device *dev, tegra_set_cpu_in_lp2(); cpu_pm_enter(); - clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &dev->cpu); + tick_broadcast_enter(); call_firmware_op(prepare_idle); @@ -52,7 +52,7 @@ static int tegra114_idle_power_down(struct cpuidle_device *dev, if (call_firmware_op(do_idle, 0) == -ENOSYS) cpu_suspend(0, tegra30_sleep_cpu_secondary_finish); - clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &dev->cpu); + tick_broadcast_exit(); cpu_pm_exit(); tegra_clear_cpu_in_lp2(); diff --git a/arch/arm/mach-tegra/cpuidle-tegra20.c b/arch/arm/mach-tegra/cpuidle-tegra20.c index 4f25a7c7ca0f..48844ae6c3a1 100644 --- a/arch/arm/mach-tegra/cpuidle-tegra20.c +++ b/arch/arm/mach-tegra/cpuidle-tegra20.c @@ -20,7 +20,7 @@ */ #include <linux/clk/tegra.h> -#include <linux/clockchips.h> +#include <linux/tick.h> #include <linux/cpuidle.h> #include <linux/cpu_pm.h> #include <linux/kernel.h> @@ -136,11 +136,11 @@ static bool tegra20_cpu_cluster_power_down(struct cpuidle_device *dev, if (tegra20_reset_cpu_1() || !tegra_cpu_rail_off_ready()) return false; - clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &dev->cpu); + tick_broadcast_enter(); tegra_idle_lp2_last(); - clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &dev->cpu); + tick_broadcast_exit(); if (cpu_online(1)) tegra20_wake_cpu1_from_reset(); @@ -153,13 +153,13 @@ static bool tegra20_idle_enter_lp2_cpu_1(struct cpuidle_device *dev, struct cpuidle_driver *drv, int index) { - clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &dev->cpu); + tick_broadcast_enter(); cpu_suspend(0, tegra20_sleep_cpu_secondary_finish); tegra20_cpu_clear_resettable(); - clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &dev->cpu); + tick_broadcast_exit(); return true; } diff --git a/arch/arm/mach-tegra/cpuidle-tegra30.c b/arch/arm/mach-tegra/cpuidle-tegra30.c index f8815ed65d9d..84d809a3cba3 100644 --- a/arch/arm/mach-tegra/cpuidle-tegra30.c +++ b/arch/arm/mach-tegra/cpuidle-tegra30.c @@ -20,7 +20,7 @@ */ #include <linux/clk/tegra.h> -#include <linux/clockchips.h> +#include <linux/tick.h> #include <linux/cpuidle.h> #include <linux/cpu_pm.h> #include <linux/kernel.h> @@ -76,11 +76,11 @@ static bool tegra30_cpu_cluster_power_down(struct cpuidle_device *dev, return false; } - clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &dev->cpu); + tick_broadcast_enter(); tegra_idle_lp2_last(); - clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &dev->cpu); + tick_broadcast_exit(); return true; } @@ -90,13 +90,13 @@ static bool tegra30_cpu_core_power_down(struct cpuidle_device *dev, struct cpuidle_driver *drv, int index) { - clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &dev->cpu); + tick_broadcast_enter(); smp_wmb(); cpu_suspend(0, tegra30_sleep_cpu_secondary_finish); - clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &dev->cpu); + tick_broadcast_exit(); return true; } diff --git a/arch/arm/plat-omap/counter_32k.c b/arch/arm/plat-omap/counter_32k.c index 61b4d705c267..2438b96004c1 100644 --- a/arch/arm/plat-omap/counter_32k.c +++ b/arch/arm/plat-omap/counter_32k.c @@ -44,24 +44,20 @@ static u64 notrace omap_32k_read_sched_clock(void) } /** - * omap_read_persistent_clock - Return time from a persistent clock. + * omap_read_persistent_clock64 - Return time from a persistent clock. * * Reads the time from a source which isn't disabled during PM, the * 32k sync timer. Convert the cycles elapsed since last read into - * nsecs and adds to a monotonically increasing timespec. + * nsecs and adds to a monotonically increasing timespec64. */ -static struct timespec persistent_ts; +static struct timespec64 persistent_ts; static cycles_t cycles; static unsigned int persistent_mult, persistent_shift; -static DEFINE_SPINLOCK(read_persistent_clock_lock); -static void omap_read_persistent_clock(struct timespec *ts) +static void omap_read_persistent_clock64(struct timespec64 *ts) { unsigned long long nsecs; cycles_t last_cycles; - unsigned long flags; - - spin_lock_irqsave(&read_persistent_clock_lock, flags); last_cycles = cycles; cycles = sync32k_cnt_reg ? readl_relaxed(sync32k_cnt_reg) : 0; @@ -69,11 +65,9 @@ static void omap_read_persistent_clock(struct timespec *ts) nsecs = clocksource_cyc2ns(cycles - last_cycles, persistent_mult, persistent_shift); - timespec_add_ns(&persistent_ts, nsecs); + timespec64_add_ns(&persistent_ts, nsecs); *ts = persistent_ts; - - spin_unlock_irqrestore(&read_persistent_clock_lock, flags); } /** @@ -103,7 +97,7 @@ int __init omap_init_clocksource_32k(void __iomem *vbase) /* * 120000 rough estimate from the calculations in - * __clocksource_updatefreq_scale. + * __clocksource_update_freq_scale. */ clocks_calc_mult_shift(&persistent_mult, &persistent_shift, 32768, NSEC_PER_SEC, 120000); @@ -116,7 +110,7 @@ int __init omap_init_clocksource_32k(void __iomem *vbase) } sched_clock_register(omap_32k_read_sched_clock, 32, 32768); - register_persistent_clock(NULL, omap_read_persistent_clock); + register_persistent_clock(NULL, omap_read_persistent_clock64); pr_info("OMAP clocksource: 32k_counter at 32768 Hz\n"); return 0; diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h index 92bbae381598..70522450ca23 100644 --- a/arch/arm64/include/asm/esr.h +++ b/arch/arm64/include/asm/esr.h @@ -90,6 +90,7 @@ #define ESR_ELx_FSC (0x3F) #define ESR_ELx_FSC_TYPE (0x3C) #define ESR_ELx_FSC_EXTABT (0x10) +#define ESR_ELx_FSC_ACCESS (0x08) #define ESR_ELx_FSC_FAULT (0x04) #define ESR_ELx_FSC_PERM (0x0C) #define ESR_ELx_CV (UL(1) << 24) diff --git a/arch/arm64/include/asm/jump_label.h b/arch/arm64/include/asm/jump_label.h index 076a1c714049..c0e5165c2f76 100644 --- a/arch/arm64/include/asm/jump_label.h +++ b/arch/arm64/include/asm/jump_label.h @@ -18,11 +18,12 @@ */ #ifndef __ASM_JUMP_LABEL_H #define __ASM_JUMP_LABEL_H + +#ifndef __ASSEMBLY__ + #include <linux/types.h> #include <asm/insn.h> -#ifdef __KERNEL__ - #define JUMP_LABEL_NOP_SIZE AARCH64_INSN_SIZE static __always_inline bool arch_static_branch(struct static_key *key) @@ -39,8 +40,6 @@ l_yes: return true; } -#endif /* __KERNEL__ */ - typedef u64 jump_label_t; struct jump_entry { @@ -49,4 +48,5 @@ struct jump_entry { jump_label_t key; }; +#endif /* __ASSEMBLY__ */ #endif /* __ASM_JUMP_LABEL_H */ diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 54bb4ba97441..ac6fafb95fe7 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -188,6 +188,7 @@ /* For compatibility with fault code shared with 32-bit */ #define FSC_FAULT ESR_ELx_FSC_FAULT +#define FSC_ACCESS ESR_ELx_FSC_ACCESS #define FSC_PERM ESR_ELx_FSC_PERM /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */ diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 8ac3c70fe3c6..f0f58c9beec0 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -28,6 +28,8 @@ #include <asm/kvm_asm.h> #include <asm/kvm_mmio.h> +#define __KVM_HAVE_ARCH_INTC_INITIALIZED + #if defined(CONFIG_KVM_ARM_MAX_VCPUS) #define KVM_MAX_VCPUS CONFIG_KVM_ARM_MAX_VCPUS #else @@ -177,19 +179,10 @@ int kvm_unmap_hva(struct kvm *kvm, unsigned long hva); int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end); void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); +int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); +int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); /* We do not have shadow page tables, hence the empty hooks */ -static inline int kvm_age_hva(struct kvm *kvm, unsigned long start, - unsigned long end) -{ - return 0; -} - -static inline int kvm_test_age_hva(struct kvm *kvm, unsigned long hva) -{ - return 0; -} - static inline void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm, unsigned long address) { diff --git a/arch/arm64/include/asm/kvm_mmio.h b/arch/arm64/include/asm/kvm_mmio.h index 9f52beb7cb13..889c908ee631 100644 --- a/arch/arm64/include/asm/kvm_mmio.h +++ b/arch/arm64/include/asm/kvm_mmio.h @@ -31,28 +31,6 @@ struct kvm_decode { bool sign_extend; }; -/* - * The in-kernel MMIO emulation code wants to use a copy of run->mmio, - * which is an anonymous type. Use our own type instead. - */ -struct kvm_exit_mmio { - phys_addr_t phys_addr; - u8 data[8]; - u32 len; - bool is_write; - void *private; -}; - -static inline void kvm_prepare_mmio(struct kvm_run *run, - struct kvm_exit_mmio *mmio) -{ - run->mmio.phys_addr = mmio->phys_addr; - run->mmio.len = mmio->len; - run->mmio.is_write = mmio->is_write; - memcpy(run->mmio.data, mmio->data, mmio->len); - run->exit_reason = KVM_EXIT_MMIO; -} - int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run); int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run, phys_addr_t fault_ipa); diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index 3ef77a466018..c154c0b7eb60 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -191,6 +191,9 @@ struct kvm_arch_memory_slot { /* Highest supported SPI, from VGIC_NR_IRQS */ #define KVM_ARM_IRQ_GIC_MAX 127 +/* One single KVM irqchip, ie. the VGIC */ +#define KVM_NR_IRQCHIPS 1 + /* PSCI interface */ #define KVM_PSCI_FN_BASE 0x95c1ba5e #define KVM_PSCI_FN(n) (KVM_PSCI_FN_BASE + (n)) diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c index 32aeea083d93..ec37ab3f524f 100644 --- a/arch/arm64/kernel/vdso.c +++ b/arch/arm64/kernel/vdso.c @@ -200,7 +200,7 @@ up_fail: void update_vsyscall(struct timekeeper *tk) { struct timespec xtime_coarse; - u32 use_syscall = strcmp(tk->tkr.clock->name, "arch_sys_counter"); + u32 use_syscall = strcmp(tk->tkr_mono.clock->name, "arch_sys_counter"); ++vdso_data->tb_seq_count; smp_wmb(); @@ -213,11 +213,11 @@ void update_vsyscall(struct timekeeper *tk) vdso_data->wtm_clock_nsec = tk->wall_to_monotonic.tv_nsec; if (!use_syscall) { - vdso_data->cs_cycle_last = tk->tkr.cycle_last; + vdso_data->cs_cycle_last = tk->tkr_mono.cycle_last; vdso_data->xtime_clock_sec = tk->xtime_sec; - vdso_data->xtime_clock_nsec = tk->tkr.xtime_nsec; - vdso_data->cs_mult = tk->tkr.mult; - vdso_data->cs_shift = tk->tkr.shift; + vdso_data->xtime_clock_nsec = tk->tkr_mono.xtime_nsec; + vdso_data->cs_mult = tk->tkr_mono.mult; + vdso_data->cs_shift = tk->tkr_mono.shift; } smp_wmb(); diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index f5590c81d95f..5105e297ed5f 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -18,6 +18,7 @@ if VIRTUALIZATION config KVM bool "Kernel-based Virtual Machine (KVM) support" + depends on OF select MMU_NOTIFIER select PREEMPT_NOTIFIERS select ANON_INODES @@ -25,10 +26,10 @@ config KVM select HAVE_KVM_ARCH_TLB_FLUSH_ALL select KVM_MMIO select KVM_ARM_HOST - select KVM_ARM_VGIC - select KVM_ARM_TIMER select KVM_GENERIC_DIRTYLOG_READ_PROTECT select SRCU + select HAVE_KVM_EVENTFD + select HAVE_KVM_IRQFD ---help--- Support hosting virtualized guest machines. @@ -50,17 +51,4 @@ config KVM_ARM_MAX_VCPUS large, so only choose a reasonable number that you expect to actually use. -config KVM_ARM_VGIC - bool - depends on KVM_ARM_HOST && OF - select HAVE_KVM_IRQCHIP - ---help--- - Adds support for a hardware assisted, in-kernel GIC emulation. - -config KVM_ARM_TIMER - bool - depends on KVM_ARM_VGIC - ---help--- - Adds support for the Architected Timers in virtual machines. - endif # VIRTUALIZATION diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile index 4e6e09ee4033..d5904f876cdb 100644 --- a/arch/arm64/kvm/Makefile +++ b/arch/arm64/kvm/Makefile @@ -2,7 +2,7 @@ # Makefile for Kernel-based Virtual Machine module # -ccflags-y += -Ivirt/kvm -Iarch/arm64/kvm +ccflags-y += -Iarch/arm64/kvm CFLAGS_arm.o := -I. CFLAGS_mmu.o := -I. @@ -11,7 +11,7 @@ ARM=../../../arch/arm/kvm obj-$(CONFIG_KVM_ARM_HOST) += kvm.o -kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o +kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o kvm-$(CONFIG_KVM_ARM_HOST) += $(ARM)/arm.o $(ARM)/mmu.o $(ARM)/mmio.o kvm-$(CONFIG_KVM_ARM_HOST) += $(ARM)/psci.o $(ARM)/perf.o @@ -19,11 +19,11 @@ kvm-$(CONFIG_KVM_ARM_HOST) += emulate.o inject_fault.o regmap.o kvm-$(CONFIG_KVM_ARM_HOST) += hyp.o hyp-init.o handle_exit.o kvm-$(CONFIG_KVM_ARM_HOST) += guest.o reset.o sys_regs.o sys_regs_generic_v8.o -kvm-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic.o -kvm-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v2.o -kvm-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v2-emul.o -kvm-$(CONFIG_KVM_ARM_VGIC) += vgic-v2-switch.o -kvm-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v3.o -kvm-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v3-emul.o -kvm-$(CONFIG_KVM_ARM_VGIC) += vgic-v3-switch.o -kvm-$(CONFIG_KVM_ARM_TIMER) += $(KVM)/arm/arch_timer.o +kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic.o +kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v2.o +kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v2-emul.o +kvm-$(CONFIG_KVM_ARM_HOST) += vgic-v2-switch.o +kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v3.o +kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v3-emul.o +kvm-$(CONFIG_KVM_ARM_HOST) += vgic-v3-switch.o +kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/arch_timer.o diff --git a/arch/mips/include/asm/asmmacro-32.h b/arch/mips/include/asm/asmmacro-32.h index cdac7b3eeaf7..80386470d3a4 100644 --- a/arch/mips/include/asm/asmmacro-32.h +++ b/arch/mips/include/asm/asmmacro-32.h @@ -16,38 +16,38 @@ .set push SET_HARDFLOAT cfc1 \tmp, fcr31 - swc1 $f0, THREAD_FPR0_LS64(\thread) - swc1 $f1, THREAD_FPR1_LS64(\thread) - swc1 $f2, THREAD_FPR2_LS64(\thread) - swc1 $f3, THREAD_FPR3_LS64(\thread) - swc1 $f4, THREAD_FPR4_LS64(\thread) - swc1 $f5, THREAD_FPR5_LS64(\thread) - swc1 $f6, THREAD_FPR6_LS64(\thread) - swc1 $f7, THREAD_FPR7_LS64(\thread) - swc1 $f8, THREAD_FPR8_LS64(\thread) - swc1 $f9, THREAD_FPR9_LS64(\thread) - swc1 $f10, THREAD_FPR10_LS64(\thread) - swc1 $f11, THREAD_FPR11_LS64(\thread) - swc1 $f12, THREAD_FPR12_LS64(\thread) - swc1 $f13, THREAD_FPR13_LS64(\thread) - swc1 $f14, THREAD_FPR14_LS64(\thread) - swc1 $f15, THREAD_FPR15_LS64(\thread) - swc1 $f16, THREAD_FPR16_LS64(\thread) - swc1 $f17, THREAD_FPR17_LS64(\thread) - swc1 $f18, THREAD_FPR18_LS64(\thread) - swc1 $f19, THREAD_FPR19_LS64(\thread) - swc1 $f20, THREAD_FPR20_LS64(\thread) - swc1 $f21, THREAD_FPR21_LS64(\thread) - swc1 $f22, THREAD_FPR22_LS64(\thread) - swc1 $f23, THREAD_FPR23_LS64(\thread) - swc1 $f24, THREAD_FPR24_LS64(\thread) - swc1 $f25, THREAD_FPR25_LS64(\thread) - swc1 $f26, THREAD_FPR26_LS64(\thread) - swc1 $f27, THREAD_FPR27_LS64(\thread) - swc1 $f28, THREAD_FPR28_LS64(\thread) - swc1 $f29, THREAD_FPR29_LS64(\thread) - swc1 $f30, THREAD_FPR30_LS64(\thread) - swc1 $f31, THREAD_FPR31_LS64(\thread) + swc1 $f0, THREAD_FPR0(\thread) + swc1 $f1, THREAD_FPR1(\thread) + swc1 $f2, THREAD_FPR2(\thread) + swc1 $f3, THREAD_FPR3(\thread) + swc1 $f4, THREAD_FPR4(\thread) + swc1 $f5, THREAD_FPR5(\thread) + swc1 $f6, THREAD_FPR6(\thread) + swc1 $f7, THREAD_FPR7(\thread) + swc1 $f8, THREAD_FPR8(\thread) + swc1 $f9, THREAD_FPR9(\thread) + swc1 $f10, THREAD_FPR10(\thread) + swc1 $f11, THREAD_FPR11(\thread) + swc1 $f12, THREAD_FPR12(\thread) + swc1 $f13, THREAD_FPR13(\thread) + swc1 $f14, THREAD_FPR14(\thread) + swc1 $f15, THREAD_FPR15(\thread) + swc1 $f16, THREAD_FPR16(\thread) + swc1 $f17, THREAD_FPR17(\thread) + swc1 $f18, THREAD_FPR18(\thread) + swc1 $f19, THREAD_FPR19(\thread) + swc1 $f20, THREAD_FPR20(\thread) + swc1 $f21, THREAD_FPR21(\thread) + swc1 $f22, THREAD_FPR22(\thread) + swc1 $f23, THREAD_FPR23(\thread) + swc1 $f24, THREAD_FPR24(\thread) + swc1 $f25, THREAD_FPR25(\thread) + swc1 $f26, THREAD_FPR26(\thread) + swc1 $f27, THREAD_FPR27(\thread) + swc1 $f28, THREAD_FPR28(\thread) + swc1 $f29, THREAD_FPR29(\thread) + swc1 $f30, THREAD_FPR30(\thread) + swc1 $f31, THREAD_FPR31(\thread) sw \tmp, THREAD_FCR31(\thread) .set pop .endm @@ -56,38 +56,38 @@ .set push SET_HARDFLOAT lw \tmp, THREAD_FCR31(\thread) - lwc1 $f0, THREAD_FPR0_LS64(\thread) - lwc1 $f1, THREAD_FPR1_LS64(\thread) - lwc1 $f2, THREAD_FPR2_LS64(\thread) - lwc1 $f3, THREAD_FPR3_LS64(\thread) - lwc1 $f4, THREAD_FPR4_LS64(\thread) - lwc1 $f5, THREAD_FPR5_LS64(\thread) - lwc1 $f6, THREAD_FPR6_LS64(\thread) - lwc1 $f7, THREAD_FPR7_LS64(\thread) - lwc1 $f8, THREAD_FPR8_LS64(\thread) - lwc1 $f9, THREAD_FPR9_LS64(\thread) - lwc1 $f10, THREAD_FPR10_LS64(\thread) - lwc1 $f11, THREAD_FPR11_LS64(\thread) - lwc1 $f12, THREAD_FPR12_LS64(\thread) - lwc1 $f13, THREAD_FPR13_LS64(\thread) - lwc1 $f14, THREAD_FPR14_LS64(\thread) - lwc1 $f15, THREAD_FPR15_LS64(\thread) - lwc1 $f16, THREAD_FPR16_LS64(\thread) - lwc1 $f17, THREAD_FPR17_LS64(\thread) - lwc1 $f18, THREAD_FPR18_LS64(\thread) - lwc1 $f19, THREAD_FPR19_LS64(\thread) - lwc1 $f20, THREAD_FPR20_LS64(\thread) - lwc1 $f21, THREAD_FPR21_LS64(\thread) - lwc1 $f22, THREAD_FPR22_LS64(\thread) - lwc1 $f23, THREAD_FPR23_LS64(\thread) - lwc1 $f24, THREAD_FPR24_LS64(\thread) - lwc1 $f25, THREAD_FPR25_LS64(\thread) - lwc1 $f26, THREAD_FPR26_LS64(\thread) - lwc1 $f27, THREAD_FPR27_LS64(\thread) - lwc1 $f28, THREAD_FPR28_LS64(\thread) - lwc1 $f29, THREAD_FPR29_LS64(\thread) - lwc1 $f30, THREAD_FPR30_LS64(\thread) - lwc1 $f31, THREAD_FPR31_LS64(\thread) + lwc1 $f0, THREAD_FPR0(\thread) + lwc1 $f1, THREAD_FPR1(\thread) + lwc1 $f2, THREAD_FPR2(\thread) + lwc1 $f3, THREAD_FPR3(\thread) + lwc1 $f4, THREAD_FPR4(\thread) + lwc1 $f5, THREAD_FPR5(\thread) + lwc1 $f6, THREAD_FPR6(\thread) + lwc1 $f7, THREAD_FPR7(\thread) + lwc1 $f8, THREAD_FPR8(\thread) + lwc1 $f9, THREAD_FPR9(\thread) + lwc1 $f10, THREAD_FPR10(\thread) + lwc1 $f11, THREAD_FPR11(\thread) + lwc1 $f12, THREAD_FPR12(\thread) + lwc1 $f13, THREAD_FPR13(\thread) + lwc1 $f14, THREAD_FPR14(\thread) + lwc1 $f15, THREAD_FPR15(\thread) + lwc1 $f16, THREAD_FPR16(\thread) + lwc1 $f17, THREAD_FPR17(\thread) + lwc1 $f18, THREAD_FPR18(\thread) + lwc1 $f19, THREAD_FPR19(\thread) + lwc1 $f20, THREAD_FPR20(\thread) + lwc1 $f21, THREAD_FPR21(\thread) + lwc1 $f22, THREAD_FPR22(\thread) + lwc1 $f23, THREAD_FPR23(\thread) + lwc1 $f24, THREAD_FPR24(\thread) + lwc1 $f25, THREAD_FPR25(\thread) + lwc1 $f26, THREAD_FPR26(\thread) + lwc1 $f27, THREAD_FPR27(\thread) + lwc1 $f28, THREAD_FPR28(\thread) + lwc1 $f29, THREAD_FPR29(\thread) + lwc1 $f30, THREAD_FPR30(\thread) + lwc1 $f31, THREAD_FPR31(\thread) ctc1 \tmp, fcr31 .set pop .endm diff --git a/arch/mips/include/asm/asmmacro.h b/arch/mips/include/asm/asmmacro.h index 0cae4595e985..6156ac8c4cfb 100644 --- a/arch/mips/include/asm/asmmacro.h +++ b/arch/mips/include/asm/asmmacro.h @@ -60,22 +60,22 @@ .set push SET_HARDFLOAT cfc1 \tmp, fcr31 - sdc1 $f0, THREAD_FPR0_LS64(\thread) - sdc1 $f2, THREAD_FPR2_LS64(\thread) - sdc1 $f4, THREAD_FPR4_LS64(\thread) - sdc1 $f6, THREAD_FPR6_LS64(\thread) - sdc1 $f8, THREAD_FPR8_LS64(\thread) - sdc1 $f10, THREAD_FPR10_LS64(\thread) - sdc1 $f12, THREAD_FPR12_LS64(\thread) - sdc1 $f14, THREAD_FPR14_LS64(\thread) - sdc1 $f16, THREAD_FPR16_LS64(\thread) - sdc1 $f18, THREAD_FPR18_LS64(\thread) - sdc1 $f20, THREAD_FPR20_LS64(\thread) - sdc1 $f22, THREAD_FPR22_LS64(\thread) - sdc1 $f24, THREAD_FPR24_LS64(\thread) - sdc1 $f26, THREAD_FPR26_LS64(\thread) - sdc1 $f28, THREAD_FPR28_LS64(\thread) - sdc1 $f30, THREAD_FPR30_LS64(\thread) + sdc1 $f0, THREAD_FPR0(\thread) + sdc1 $f2, THREAD_FPR2(\thread) + sdc1 $f4, THREAD_FPR4(\thread) + sdc1 $f6, THREAD_FPR6(\thread) + sdc1 $f8, THREAD_FPR8(\thread) + sdc1 $f10, THREAD_FPR10(\thread) + sdc1 $f12, THREAD_FPR12(\thread) + sdc1 $f14, THREAD_FPR14(\thread) + sdc1 $f16, THREAD_FPR16(\thread) + sdc1 $f18, THREAD_FPR18(\thread) + sdc1 $f20, THREAD_FPR20(\thread) + sdc1 $f22, THREAD_FPR22(\thread) + sdc1 $f24, THREAD_FPR24(\thread) + sdc1 $f26, THREAD_FPR26(\thread) + sdc1 $f28, THREAD_FPR28(\thread) + sdc1 $f30, THREAD_FPR30(\thread) sw \tmp, THREAD_FCR31(\thread) .set pop .endm @@ -84,22 +84,22 @@ .set push .set mips64r2 SET_HARDFLOAT - sdc1 $f1, THREAD_FPR1_LS64(\thread) - sdc1 $f3, THREAD_FPR3_LS64(\thread) - sdc1 $f5, THREAD_FPR5_LS64(\thread) - sdc1 $f7, THREAD_FPR7_LS64(\thread) - sdc1 $f9, THREAD_FPR9_LS64(\thread) - sdc1 $f11, THREAD_FPR11_LS64(\thread) - sdc1 $f13, THREAD_FPR13_LS64(\thread) - sdc1 $f15, THREAD_FPR15_LS64(\thread) - sdc1 $f17, THREAD_FPR17_LS64(\thread) - sdc1 $f19, THREAD_FPR19_LS64(\thread) - sdc1 $f21, THREAD_FPR21_LS64(\thread) - sdc1 $f23, THREAD_FPR23_LS64(\thread) - sdc1 $f25, THREAD_FPR25_LS64(\thread) - sdc1 $f27, THREAD_FPR27_LS64(\thread) - sdc1 $f29, THREAD_FPR29_LS64(\thread) - sdc1 $f31, THREAD_FPR31_LS64(\thread) + sdc1 $f1, THREAD_FPR1(\thread) + sdc1 $f3, THREAD_FPR3(\thread) + sdc1 $f5, THREAD_FPR5(\thread) + sdc1 $f7, THREAD_FPR7(\thread) + sdc1 $f9, THREAD_FPR9(\thread) + sdc1 $f11, THREAD_FPR11(\thread) + sdc1 $f13, THREAD_FPR13(\thread) + sdc1 $f15, THREAD_FPR15(\thread) + sdc1 $f17, THREAD_FPR17(\thread) + sdc1 $f19, THREAD_FPR19(\thread) + sdc1 $f21, THREAD_FPR21(\thread) + sdc1 $f23, THREAD_FPR23(\thread) + sdc1 $f25, THREAD_FPR25(\thread) + sdc1 $f27, THREAD_FPR27(\thread) + sdc1 $f29, THREAD_FPR29(\thread) + sdc1 $f31, THREAD_FPR31(\thread) .set pop .endm @@ -118,22 +118,22 @@ .set push SET_HARDFLOAT lw \tmp, THREAD_FCR31(\thread) - ldc1 $f0, THREAD_FPR0_LS64(\thread) - ldc1 $f2, THREAD_FPR2_LS64(\thread) - ldc1 $f4, THREAD_FPR4_LS64(\thread) - ldc1 $f6, THREAD_FPR6_LS64(\thread) - ldc1 $f8, THREAD_FPR8_LS64(\thread) - ldc1 $f10, THREAD_FPR10_LS64(\thread) - ldc1 $f12, THREAD_FPR12_LS64(\thread) - ldc1 $f14, THREAD_FPR14_LS64(\thread) - ldc1 $f16, THREAD_FPR16_LS64(\thread) - ldc1 $f18, THREAD_FPR18_LS64(\thread) - ldc1 $f20, THREAD_FPR20_LS64(\thread) - ldc1 $f22, THREAD_FPR22_LS64(\thread) - ldc1 $f24, THREAD_FPR24_LS64(\thread) - ldc1 $f26, THREAD_FPR26_LS64(\thread) - ldc1 $f28, THREAD_FPR28_LS64(\thread) - ldc1 $f30, THREAD_FPR30_LS64(\thread) + ldc1 $f0, THREAD_FPR0(\thread) + ldc1 $f2, THREAD_FPR2(\thread) + ldc1 $f4, THREAD_FPR4(\thread) + ldc1 $f6, THREAD_FPR6(\thread) + ldc1 $f8, THREAD_FPR8(\thread) + ldc1 $f10, THREAD_FPR10(\thread) + ldc1 $f12, THREAD_FPR12(\thread) + ldc1 $f14, THREAD_FPR14(\thread) + ldc1 $f16, THREAD_FPR16(\thread) + ldc1 $f18, THREAD_FPR18(\thread) + ldc1 $f20, THREAD_FPR20(\thread) + ldc1 $f22, THREAD_FPR22(\thread) + ldc1 $f24, THREAD_FPR24(\thread) + ldc1 $f26, THREAD_FPR26(\thread) + ldc1 $f28, THREAD_FPR28(\thread) + ldc1 $f30, THREAD_FPR30(\thread) ctc1 \tmp, fcr31 .endm @@ -141,22 +141,22 @@ .set push .set mips64r2 SET_HARDFLOAT - ldc1 $f1, THREAD_FPR1_LS64(\thread) - ldc1 $f3, THREAD_FPR3_LS64(\thread) - ldc1 $f5, THREAD_FPR5_LS64(\thread) - ldc1 $f7, THREAD_FPR7_LS64(\thread) - ldc1 $f9, THREAD_FPR9_LS64(\thread) - ldc1 $f11, THREAD_FPR11_LS64(\thread) - ldc1 $f13, THREAD_FPR13_LS64(\thread) - ldc1 $f15, THREAD_FPR15_LS64(\thread) - ldc1 $f17, THREAD_FPR17_LS64(\thread) - ldc1 $f19, THREAD_FPR19_LS64(\thread) - ldc1 $f21, THREAD_FPR21_LS64(\thread) - ldc1 $f23, THREAD_FPR23_LS64(\thread) - ldc1 $f25, THREAD_FPR25_LS64(\thread) - ldc1 $f27, THREAD_FPR27_LS64(\thread) - ldc1 $f29, THREAD_FPR29_LS64(\thread) - ldc1 $f31, THREAD_FPR31_LS64(\thread) + ldc1 $f1, THREAD_FPR1(\thread) + ldc1 $f3, THREAD_FPR3(\thread) + ldc1 $f5, THREAD_FPR5(\thread) + ldc1 $f7, THREAD_FPR7(\thread) + ldc1 $f9, THREAD_FPR9(\thread) + ldc1 $f11, THREAD_FPR11(\thread) + ldc1 $f13, THREAD_FPR13(\thread) + ldc1 $f15, THREAD_FPR15(\thread) + ldc1 $f17, THREAD_FPR17(\thread) + ldc1 $f19, THREAD_FPR19(\thread) + ldc1 $f21, THREAD_FPR21(\thread) + ldc1 $f23, THREAD_FPR23(\thread) + ldc1 $f25, THREAD_FPR25(\thread) + ldc1 $f27, THREAD_FPR27(\thread) + ldc1 $f29, THREAD_FPR29(\thread) + ldc1 $f31, THREAD_FPR31(\thread) .set pop .endm @@ -211,6 +211,22 @@ .endm #ifdef TOOLCHAIN_SUPPORTS_MSA + .macro _cfcmsa rd, cs + .set push + .set mips32r2 + .set msa + cfcmsa \rd, $\cs + .set pop + .endm + + .macro _ctcmsa cd, rs + .set push + .set mips32r2 + .set msa + ctcmsa $\cd, \rs + .set pop + .endm + .macro ld_d wd, off, base .set push .set mips32r2 @@ -227,35 +243,35 @@ .set pop .endm - .macro copy_u_w rd, ws, n + .macro copy_u_w ws, n .set push .set mips32r2 .set msa - copy_u.w \rd, $w\ws[\n] + copy_u.w $1, $w\ws[\n] .set pop .endm - .macro copy_u_d rd, ws, n + .macro copy_u_d ws, n .set push .set mips64r2 .set msa - copy_u.d \rd, $w\ws[\n] + copy_u.d $1, $w\ws[\n] .set pop .endm - .macro insert_w wd, n, rs + .macro insert_w wd, n .set push .set mips32r2 .set msa - insert.w $w\wd[\n], \rs + insert.w $w\wd[\n], $1 .set pop .endm - .macro insert_d wd, n, rs + .macro insert_d wd, n .set push .set mips64r2 .set msa - insert.d $w\wd[\n], \rs + insert.d $w\wd[\n], $1 .set pop .endm #else @@ -283,7 +299,7 @@ /* * Temporary until all toolchains in use include MSA support. */ - .macro cfcmsa rd, cs + .macro _cfcmsa rd, cs .set push .set noat SET_HARDFLOAT @@ -293,7 +309,7 @@ .set pop .endm - .macro ctcmsa cd, rs + .macro _ctcmsa cd, rs .set push .set noat SET_HARDFLOAT @@ -320,44 +336,36 @@ .set pop .endm - .macro copy_u_w rd, ws, n + .macro copy_u_w ws, n .set push .set noat SET_HARDFLOAT .insn .word COPY_UW_MSA_INSN | (\n << 16) | (\ws << 11) - /* move triggers an assembler bug... */ - or \rd, $1, zero .set pop .endm - .macro copy_u_d rd, ws, n + .macro copy_u_d ws, n .set push .set noat SET_HARDFLOAT .insn .word COPY_UD_MSA_INSN | (\n << 16) | (\ws << 11) - /* move triggers an assembler bug... */ - or \rd, $1, zero .set pop .endm - .macro insert_w wd, n, rs + .macro insert_w wd, n .set push .set noat SET_HARDFLOAT - /* move triggers an assembler bug... */ - or $1, \rs, zero .word INSERT_W_MSA_INSN | (\n << 16) | (\wd << 6) .set pop .endm - .macro insert_d wd, n, rs + .macro insert_d wd, n .set push .set noat SET_HARDFLOAT - /* move triggers an assembler bug... */ - or $1, \rs, zero .word INSERT_D_MSA_INSN | (\n << 16) | (\wd << 6) .set pop .endm @@ -399,7 +407,7 @@ .set push .set noat SET_HARDFLOAT - cfcmsa $1, MSA_CSR + _cfcmsa $1, MSA_CSR sw $1, THREAD_MSA_CSR(\thread) .set pop .endm @@ -409,7 +417,7 @@ .set noat SET_HARDFLOAT lw $1, THREAD_MSA_CSR(\thread) - ctcmsa MSA_CSR, $1 + _ctcmsa MSA_CSR, $1 .set pop ld_d 0, THREAD_FPR0, \thread ld_d 1, THREAD_FPR1, \thread @@ -452,9 +460,6 @@ insert_w \wd, 2 insert_w \wd, 3 #endif - .if 31-\wd - msa_init_upper (\wd+1) - .endif .endm .macro msa_init_all_upper @@ -463,6 +468,37 @@ SET_HARDFLOAT not $1, zero msa_init_upper 0 + msa_init_upper 1 + msa_init_upper 2 + msa_init_upper 3 + msa_init_upper 4 + msa_init_upper 5 + msa_init_upper 6 + msa_init_upper 7 + msa_init_upper 8 + msa_init_upper 9 + msa_init_upper 10 + msa_init_upper 11 + msa_init_upper 12 + msa_init_upper 13 + msa_init_upper 14 + msa_init_upper 15 + msa_init_upper 16 + msa_init_upper 17 + msa_init_upper 18 + msa_init_upper 19 + msa_init_upper 20 + msa_init_upper 21 + msa_init_upper 22 + msa_init_upper 23 + msa_init_upper 24 + msa_init_upper 25 + msa_init_upper 26 + msa_init_upper 27 + msa_init_upper 28 + msa_init_upper 29 + msa_init_upper 30 + msa_init_upper 31 .set pop .endm diff --git a/arch/mips/include/asm/fpu.h b/arch/mips/include/asm/fpu.h index dd083e999b08..b104ad9d655f 100644 --- a/arch/mips/include/asm/fpu.h +++ b/arch/mips/include/asm/fpu.h @@ -48,6 +48,12 @@ enum fpu_mode { #define FPU_FR_MASK 0x1 }; +#define __disable_fpu() \ +do { \ + clear_c0_status(ST0_CU1); \ + disable_fpu_hazard(); \ +} while (0) + static inline int __enable_fpu(enum fpu_mode mode) { int fr; @@ -86,7 +92,12 @@ fr_common: enable_fpu_hazard(); /* check FR has the desired value */ - return (!!(read_c0_status() & ST0_FR) == !!fr) ? 0 : SIGFPE; + if (!!(read_c0_status() & ST0_FR) == !!fr) + return 0; + + /* unsupported FR value */ + __disable_fpu(); + return SIGFPE; default: BUG(); @@ -95,12 +106,6 @@ fr_common: return SIGFPE; } -#define __disable_fpu() \ -do { \ - clear_c0_status(ST0_CU1); \ - disable_fpu_hazard(); \ -} while (0) - #define clear_fpu_owner() clear_thread_flag(TIF_USEDFPU) static inline int __is_fpu_owner(void) @@ -170,6 +175,7 @@ static inline void lose_fpu(int save) } disable_msa(); clear_thread_flag(TIF_USEDMSA); + __disable_fpu(); } else if (is_fpu_owner()) { if (save) _save_fp(current); diff --git a/arch/mips/include/asm/jump_label.h b/arch/mips/include/asm/jump_label.h index fdbff44e5482..608aa57799c8 100644 --- a/arch/mips/include/asm/jump_label.h +++ b/arch/mips/include/asm/jump_label.h @@ -8,9 +8,9 @@ #ifndef _ASM_MIPS_JUMP_LABEL_H #define _ASM_MIPS_JUMP_LABEL_H -#include <linux/types.h> +#ifndef __ASSEMBLY__ -#ifdef __KERNEL__ +#include <linux/types.h> #define JUMP_LABEL_NOP_SIZE 4 @@ -39,8 +39,6 @@ l_yes: return true; } -#endif /* __KERNEL__ */ - #ifdef CONFIG_64BIT typedef u64 jump_label_t; #else @@ -53,4 +51,5 @@ struct jump_entry { jump_label_t key; }; +#endif /* __ASSEMBLY__ */ #endif /* _ASM_MIPS_JUMP_LABEL_H */ diff --git a/arch/mips/include/asm/kdebug.h b/arch/mips/include/asm/kdebug.h index 6a9af5fcb5d7..cba22ab7ad4d 100644 --- a/arch/mips/include/asm/kdebug.h +++ b/arch/mips/include/asm/kdebug.h @@ -10,7 +10,8 @@ enum die_val { DIE_RI, DIE_PAGE_FAULT, DIE_BREAK, - DIE_SSTEPBP + DIE_SSTEPBP, + DIE_MSAFP }; #endif /* _ASM_MIPS_KDEBUG_H */ diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index ac4fc716062b..4c25823563fe 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -21,10 +21,10 @@ /* MIPS KVM register ids */ #define MIPS_CP0_32(_R, _S) \ - (KVM_REG_MIPS | KVM_REG_SIZE_U32 | 0x10000 | (8 * (_R) + (_S))) + (KVM_REG_MIPS_CP0 | KVM_REG_SIZE_U32 | (8 * (_R) + (_S))) #define MIPS_CP0_64(_R, _S) \ - (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 0x10000 | (8 * (_R) + (_S))) + (KVM_REG_MIPS_CP0 | KVM_REG_SIZE_U64 | (8 * (_R) + (_S))) #define KVM_REG_MIPS_CP0_INDEX MIPS_CP0_32(0, 0) #define KVM_REG_MIPS_CP0_ENTRYLO0 MIPS_CP0_64(2, 0) @@ -42,11 +42,14 @@ #define KVM_REG_MIPS_CP0_STATUS MIPS_CP0_32(12, 0) #define KVM_REG_MIPS_CP0_CAUSE MIPS_CP0_32(13, 0) #define KVM_REG_MIPS_CP0_EPC MIPS_CP0_64(14, 0) +#define KVM_REG_MIPS_CP0_PRID MIPS_CP0_32(15, 0) #define KVM_REG_MIPS_CP0_EBASE MIPS_CP0_64(15, 1) #define KVM_REG_MIPS_CP0_CONFIG MIPS_CP0_32(16, 0) #define KVM_REG_MIPS_CP0_CONFIG1 MIPS_CP0_32(16, 1) #define KVM_REG_MIPS_CP0_CONFIG2 MIPS_CP0_32(16, 2) #define KVM_REG_MIPS_CP0_CONFIG3 MIPS_CP0_32(16, 3) +#define KVM_REG_MIPS_CP0_CONFIG4 MIPS_CP0_32(16, 4) +#define KVM_REG_MIPS_CP0_CONFIG5 MIPS_CP0_32(16, 5) #define KVM_REG_MIPS_CP0_CONFIG7 MIPS_CP0_32(16, 7) #define KVM_REG_MIPS_CP0_XCONTEXT MIPS_CP0_64(20, 0) #define KVM_REG_MIPS_CP0_ERROREPC MIPS_CP0_64(30, 0) @@ -119,6 +122,10 @@ struct kvm_vcpu_stat { u32 syscall_exits; u32 resvd_inst_exits; u32 break_inst_exits; + u32 trap_inst_exits; + u32 msa_fpe_exits; + u32 fpe_exits; + u32 msa_disabled_exits; u32 flush_dcache_exits; u32 halt_successful_poll; u32 halt_wakeup; @@ -138,6 +145,10 @@ enum kvm_mips_exit_types { SYSCALL_EXITS, RESVD_INST_EXITS, BREAK_INST_EXITS, + TRAP_INST_EXITS, + MSA_FPE_EXITS, + FPE_EXITS, + MSA_DISABLED_EXITS, FLUSH_DCACHE_EXITS, MAX_KVM_MIPS_EXIT_TYPES }; @@ -206,6 +217,8 @@ struct mips_coproc { #define MIPS_CP0_CONFIG1_SEL 1 #define MIPS_CP0_CONFIG2_SEL 2 #define MIPS_CP0_CONFIG3_SEL 3 +#define MIPS_CP0_CONFIG4_SEL 4 +#define MIPS_CP0_CONFIG5_SEL 5 /* Config0 register bits */ #define CP0C0_M 31 @@ -262,31 +275,6 @@ struct mips_coproc { #define CP0C3_SM 1 #define CP0C3_TL 0 -/* Have config1, Cacheable, noncoherent, write-back, write allocate*/ -#define MIPS_CONFIG0 \ - ((1 << CP0C0_M) | (0x3 << CP0C0_K0)) - -/* Have config2, no coprocessor2 attached, no MDMX support attached, - no performance counters, watch registers present, - no code compression, EJTAG present, no FPU, no watch registers */ -#define MIPS_CONFIG1 \ -((1 << CP0C1_M) | \ - (0 << CP0C1_C2) | (0 << CP0C1_MD) | (0 << CP0C1_PC) | \ - (0 << CP0C1_WR) | (0 << CP0C1_CA) | (1 << CP0C1_EP) | \ - (0 << CP0C1_FP)) - -/* Have config3, no tertiary/secondary caches implemented */ -#define MIPS_CONFIG2 \ -((1 << CP0C2_M)) - -/* No config4, no DSP ASE, no large physaddr (PABITS), - no external interrupt controller, no vectored interrupts, - no 1kb pages, no SmartMIPS ASE, no trace logic */ -#define MIPS_CONFIG3 \ -((0 << CP0C3_M) | (0 << CP0C3_DSPP) | (0 << CP0C3_LPA) | \ - (0 << CP0C3_VEIC) | (0 << CP0C3_VInt) | (0 << CP0C3_SP) | \ - (0 << CP0C3_SM) | (0 << CP0C3_TL)) - /* MMU types, the first four entries have the same layout as the CP0C0_MT field. */ enum mips_mmu_types { @@ -321,7 +309,9 @@ enum mips_mmu_types { */ #define T_TRAP 13 /* Trap instruction */ #define T_VCEI 14 /* Virtual coherency exception */ +#define T_MSAFPE 14 /* MSA floating point exception */ #define T_FPE 15 /* Floating point exception */ +#define T_MSADIS 21 /* MSA disabled exception */ #define T_WATCH 23 /* Watch address reference */ #define T_VCED 31 /* Virtual coherency data */ @@ -374,6 +364,9 @@ struct kvm_mips_tlb { long tlb_lo1; }; +#define KVM_MIPS_FPU_FPU 0x1 +#define KVM_MIPS_FPU_MSA 0x2 + #define KVM_MIPS_GUEST_TLB_SIZE 64 struct kvm_vcpu_arch { void *host_ebase, *guest_ebase; @@ -395,6 +388,8 @@ struct kvm_vcpu_arch { /* FPU State */ struct mips_fpu_struct fpu; + /* Which FPU state is loaded (KVM_MIPS_FPU_*) */ + unsigned int fpu_inuse; /* COP0 State */ struct mips_coproc *cop0; @@ -441,6 +436,9 @@ struct kvm_vcpu_arch { /* WAIT executed */ int wait; + + u8 fpu_enabled; + u8 msa_enabled; }; @@ -482,11 +480,15 @@ struct kvm_vcpu_arch { #define kvm_read_c0_guest_config1(cop0) (cop0->reg[MIPS_CP0_CONFIG][1]) #define kvm_read_c0_guest_config2(cop0) (cop0->reg[MIPS_CP0_CONFIG][2]) #define kvm_read_c0_guest_config3(cop0) (cop0->reg[MIPS_CP0_CONFIG][3]) +#define kvm_read_c0_guest_config4(cop0) (cop0->reg[MIPS_CP0_CONFIG][4]) +#define kvm_read_c0_guest_config5(cop0) (cop0->reg[MIPS_CP0_CONFIG][5]) #define kvm_read_c0_guest_config7(cop0) (cop0->reg[MIPS_CP0_CONFIG][7]) #define kvm_write_c0_guest_config(cop0, val) (cop0->reg[MIPS_CP0_CONFIG][0] = (val)) #define kvm_write_c0_guest_config1(cop0, val) (cop0->reg[MIPS_CP0_CONFIG][1] = (val)) #define kvm_write_c0_guest_config2(cop0, val) (cop0->reg[MIPS_CP0_CONFIG][2] = (val)) #define kvm_write_c0_guest_config3(cop0, val) (cop0->reg[MIPS_CP0_CONFIG][3] = (val)) +#define kvm_write_c0_guest_config4(cop0, val) (cop0->reg[MIPS_CP0_CONFIG][4] = (val)) +#define kvm_write_c0_guest_config5(cop0, val) (cop0->reg[MIPS_CP0_CONFIG][5] = (val)) #define kvm_write_c0_guest_config7(cop0, val) (cop0->reg[MIPS_CP0_CONFIG][7] = (val)) #define kvm_read_c0_guest_errorepc(cop0) (cop0->reg[MIPS_CP0_ERROR_PC][0]) #define kvm_write_c0_guest_errorepc(cop0, val) (cop0->reg[MIPS_CP0_ERROR_PC][0] = (val)) @@ -567,6 +569,31 @@ static inline void _kvm_atomic_change_c0_guest_reg(unsigned long *reg, kvm_set_c0_guest_ebase(cop0, ((val) & (change))); \ } +/* Helpers */ + +static inline bool kvm_mips_guest_can_have_fpu(struct kvm_vcpu_arch *vcpu) +{ + return (!__builtin_constant_p(cpu_has_fpu) || cpu_has_fpu) && + vcpu->fpu_enabled; +} + +static inline bool kvm_mips_guest_has_fpu(struct kvm_vcpu_arch *vcpu) +{ + return kvm_mips_guest_can_have_fpu(vcpu) && + kvm_read_c0_guest_config1(vcpu->cop0) & MIPS_CONF1_FP; +} + +static inline bool kvm_mips_guest_can_have_msa(struct kvm_vcpu_arch *vcpu) +{ + return (!__builtin_constant_p(cpu_has_msa) || cpu_has_msa) && + vcpu->msa_enabled; +} + +static inline bool kvm_mips_guest_has_msa(struct kvm_vcpu_arch *vcpu) +{ + return kvm_mips_guest_can_have_msa(vcpu) && + kvm_read_c0_guest_config3(vcpu->cop0) & MIPS_CONF3_MSA; +} struct kvm_mips_callbacks { int (*handle_cop_unusable)(struct kvm_vcpu *vcpu); @@ -578,6 +605,10 @@ struct kvm_mips_callbacks { int (*handle_syscall)(struct kvm_vcpu *vcpu); int (*handle_res_inst)(struct kvm_vcpu *vcpu); int (*handle_break)(struct kvm_vcpu *vcpu); + int (*handle_trap)(struct kvm_vcpu *vcpu); + int (*handle_msa_fpe)(struct kvm_vcpu *vcpu); + int (*handle_fpe)(struct kvm_vcpu *vcpu); + int (*handle_msa_disabled)(struct kvm_vcpu *vcpu); int (*vm_init)(struct kvm *kvm); int (*vcpu_init)(struct kvm_vcpu *vcpu); int (*vcpu_setup)(struct kvm_vcpu *vcpu); @@ -596,6 +627,8 @@ struct kvm_mips_callbacks { const struct kvm_one_reg *reg, s64 *v); int (*set_one_reg)(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg, s64 v); + int (*vcpu_get_regs)(struct kvm_vcpu *vcpu); + int (*vcpu_set_regs)(struct kvm_vcpu *vcpu); }; extern struct kvm_mips_callbacks *kvm_mips_callbacks; int kvm_mips_emulation_init(struct kvm_mips_callbacks **install_callbacks); @@ -606,6 +639,19 @@ int kvm_arch_vcpu_dump_regs(struct kvm_vcpu *vcpu); /* Trampoline ASM routine to start running in "Guest" context */ extern int __kvm_mips_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu); +/* FPU/MSA context management */ +void __kvm_save_fpu(struct kvm_vcpu_arch *vcpu); +void __kvm_restore_fpu(struct kvm_vcpu_arch *vcpu); +void __kvm_restore_fcsr(struct kvm_vcpu_arch *vcpu); +void __kvm_save_msa(struct kvm_vcpu_arch *vcpu); +void __kvm_restore_msa(struct kvm_vcpu_arch *vcpu); +void __kvm_restore_msa_upper(struct kvm_vcpu_arch *vcpu); +void __kvm_restore_msacsr(struct kvm_vcpu_arch *vcpu); +void kvm_own_fpu(struct kvm_vcpu *vcpu); +void kvm_own_msa(struct kvm_vcpu *vcpu); +void kvm_drop_fpu(struct kvm_vcpu *vcpu); +void kvm_lose_fpu(struct kvm_vcpu *vcpu); + /* TLB handling */ uint32_t kvm_get_kernel_asid(struct kvm_vcpu *vcpu); @@ -711,6 +757,26 @@ extern enum emulation_result kvm_mips_emulate_bp_exc(unsigned long cause, struct kvm_run *run, struct kvm_vcpu *vcpu); +extern enum emulation_result kvm_mips_emulate_trap_exc(unsigned long cause, + uint32_t *opc, + struct kvm_run *run, + struct kvm_vcpu *vcpu); + +extern enum emulation_result kvm_mips_emulate_msafpe_exc(unsigned long cause, + uint32_t *opc, + struct kvm_run *run, + struct kvm_vcpu *vcpu); + +extern enum emulation_result kvm_mips_emulate_fpe_exc(unsigned long cause, + uint32_t *opc, + struct kvm_run *run, + struct kvm_vcpu *vcpu); + +extern enum emulation_result kvm_mips_emulate_msadis_exc(unsigned long cause, + uint32_t *opc, + struct kvm_run *run, + struct kvm_vcpu *vcpu); + extern enum emulation_result kvm_mips_complete_mmio_load(struct kvm_vcpu *vcpu, struct kvm_run *run); @@ -749,6 +815,11 @@ enum emulation_result kvm_mips_emulate_load(uint32_t inst, struct kvm_run *run, struct kvm_vcpu *vcpu); +unsigned int kvm_mips_config1_wrmask(struct kvm_vcpu *vcpu); +unsigned int kvm_mips_config3_wrmask(struct kvm_vcpu *vcpu); +unsigned int kvm_mips_config4_wrmask(struct kvm_vcpu *vcpu); +unsigned int kvm_mips_config5_wrmask(struct kvm_vcpu *vcpu); + /* Dynamic binary translation */ extern int kvm_mips_trans_cache_index(uint32_t inst, uint32_t *opc, struct kvm_vcpu *vcpu); diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h index b5dcbee01fd7..9b3b48e21c22 100644 --- a/arch/mips/include/asm/processor.h +++ b/arch/mips/include/asm/processor.h @@ -105,7 +105,7 @@ union fpureg { #ifdef CONFIG_CPU_LITTLE_ENDIAN # define FPR_IDX(width, idx) (idx) #else -# define FPR_IDX(width, idx) ((FPU_REG_WIDTH / (width)) - 1 - (idx)) +# define FPR_IDX(width, idx) ((idx) ^ ((64 / (width)) - 1)) #endif #define BUILD_FPR_ACCESS(width) \ diff --git a/arch/mips/include/uapi/asm/kvm.h b/arch/mips/include/uapi/asm/kvm.h index 2c04b6d9ff85..6985eb59b085 100644 --- a/arch/mips/include/uapi/asm/kvm.h +++ b/arch/mips/include/uapi/asm/kvm.h @@ -36,77 +36,85 @@ struct kvm_regs { /* * for KVM_GET_FPU and KVM_SET_FPU - * - * If Status[FR] is zero (32-bit FPU), the upper 32-bits of the FPRs - * are zero filled. */ struct kvm_fpu { - __u64 fpr[32]; - __u32 fir; - __u32 fccr; - __u32 fexr; - __u32 fenr; - __u32 fcsr; - __u32 pad; }; /* - * For MIPS, we use KVM_SET_ONE_REG and KVM_GET_ONE_REG to access CP0 + * For MIPS, we use KVM_SET_ONE_REG and KVM_GET_ONE_REG to access various * registers. The id field is broken down as follows: * - * bits[2..0] - Register 'sel' index. - * bits[7..3] - Register 'rd' index. - * bits[15..8] - Must be zero. - * bits[31..16] - 1 -> CP0 registers. - * bits[51..32] - Must be zero. * bits[63..52] - As per linux/kvm.h + * bits[51..32] - Must be zero. + * bits[31..16] - Register set. + * + * Register set = 0: GP registers from kvm_regs (see definitions below). + * + * Register set = 1: CP0 registers. + * bits[15..8] - Must be zero. + * bits[7..3] - Register 'rd' index. + * bits[2..0] - Register 'sel' index. + * + * Register set = 2: KVM specific registers (see definitions below). + * + * Register set = 3: FPU / MSA registers (see definitions below). * * Other sets registers may be added in the future. Each set would * have its own identifier in bits[31..16]. - * - * The registers defined in struct kvm_regs are also accessible, the - * id values for these are below. */ -#define KVM_REG_MIPS_R0 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 0) -#define KVM_REG_MIPS_R1 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 1) -#define KVM_REG_MIPS_R2 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 2) -#define KVM_REG_MIPS_R3 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 3) -#define KVM_REG_MIPS_R4 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 4) -#define KVM_REG_MIPS_R5 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 5) -#define KVM_REG_MIPS_R6 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 6) -#define KVM_REG_MIPS_R7 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 7) -#define KVM_REG_MIPS_R8 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 8) -#define KVM_REG_MIPS_R9 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 9) -#define KVM_REG_MIPS_R10 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 10) -#define KVM_REG_MIPS_R11 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 11) -#define KVM_REG_MIPS_R12 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 12) -#define KVM_REG_MIPS_R13 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 13) -#define KVM_REG_MIPS_R14 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 14) -#define KVM_REG_MIPS_R15 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 15) -#define KVM_REG_MIPS_R16 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 16) -#define KVM_REG_MIPS_R17 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 17) -#define KVM_REG_MIPS_R18 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 18) -#define KVM_REG_MIPS_R19 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 19) -#define KVM_REG_MIPS_R20 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 20) -#define KVM_REG_MIPS_R21 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 21) -#define KVM_REG_MIPS_R22 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 22) -#define KVM_REG_MIPS_R23 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 23) -#define KVM_REG_MIPS_R24 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 24) -#define KVM_REG_MIPS_R25 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 25) -#define KVM_REG_MIPS_R26 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 26) -#define KVM_REG_MIPS_R27 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 27) -#define KVM_REG_MIPS_R28 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 28) -#define KVM_REG_MIPS_R29 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 29) -#define KVM_REG_MIPS_R30 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 30) -#define KVM_REG_MIPS_R31 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 31) - -#define KVM_REG_MIPS_HI (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 32) -#define KVM_REG_MIPS_LO (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 33) -#define KVM_REG_MIPS_PC (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 34) - -/* KVM specific control registers */ +#define KVM_REG_MIPS_GP (KVM_REG_MIPS | 0x0000000000000000ULL) +#define KVM_REG_MIPS_CP0 (KVM_REG_MIPS | 0x0000000000010000ULL) +#define KVM_REG_MIPS_KVM (KVM_REG_MIPS | 0x0000000000020000ULL) +#define KVM_REG_MIPS_FPU (KVM_REG_MIPS | 0x0000000000030000ULL) + + +/* + * KVM_REG_MIPS_GP - General purpose registers from kvm_regs. + */ + +#define KVM_REG_MIPS_R0 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 0) +#define KVM_REG_MIPS_R1 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 1) +#define KVM_REG_MIPS_R2 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 2) +#define KVM_REG_MIPS_R3 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 3) +#define KVM_REG_MIPS_R4 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 4) +#define KVM_REG_MIPS_R5 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 5) +#define KVM_REG_MIPS_R6 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 6) +#define KVM_REG_MIPS_R7 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 7) +#define KVM_REG_MIPS_R8 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 8) +#define KVM_REG_MIPS_R9 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 9) +#define KVM_REG_MIPS_R10 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 10) +#define KVM_REG_MIPS_R11 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 11) +#define KVM_REG_MIPS_R12 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 12) +#define KVM_REG_MIPS_R13 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 13) +#define KVM_REG_MIPS_R14 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 14) +#define KVM_REG_MIPS_R15 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 15) +#define KVM_REG_MIPS_R16 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 16) +#define KVM_REG_MIPS_R17 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 17) +#define KVM_REG_MIPS_R18 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 18) +#define KVM_REG_MIPS_R19 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 19) +#define KVM_REG_MIPS_R20 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 20) +#define KVM_REG_MIPS_R21 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 21) +#define KVM_REG_MIPS_R22 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 22) +#define KVM_REG_MIPS_R23 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 23) +#define KVM_REG_MIPS_R24 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 24) +#define KVM_REG_MIPS_R25 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 25) +#define KVM_REG_MIPS_R26 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 26) +#define KVM_REG_MIPS_R27 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 27) +#define KVM_REG_MIPS_R28 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 28) +#define KVM_REG_MIPS_R29 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 29) +#define KVM_REG_MIPS_R30 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 30) +#define KVM_REG_MIPS_R31 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 31) + +#define KVM_REG_MIPS_HI (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 32) +#define KVM_REG_MIPS_LO (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 33) +#define KVM_REG_MIPS_PC (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 34) + + +/* + * KVM_REG_MIPS_KVM - KVM specific control registers. + */ /* * CP0_Count control @@ -118,8 +126,7 @@ struct kvm_fpu { * safely without losing time or guest timer interrupts. * Other: Reserved, do not change. */ -#define KVM_REG_MIPS_COUNT_CTL (KVM_REG_MIPS | KVM_REG_SIZE_U64 | \ - 0x20000 | 0) +#define KVM_REG_MIPS_COUNT_CTL (KVM_REG_MIPS_KVM | KVM_REG_SIZE_U64 | 0) #define KVM_REG_MIPS_COUNT_CTL_DC 0x00000001 /* @@ -131,15 +138,46 @@ struct kvm_fpu { * emulated. * Modifications to times in the future are rejected. */ -#define KVM_REG_MIPS_COUNT_RESUME (KVM_REG_MIPS | KVM_REG_SIZE_U64 | \ - 0x20000 | 1) +#define KVM_REG_MIPS_COUNT_RESUME (KVM_REG_MIPS_KVM | KVM_REG_SIZE_U64 | 1) /* * CP0_Count rate in Hz * Specifies the rate of the CP0_Count timer in Hz. Modifications occur without * discontinuities in CP0_Count. */ -#define KVM_REG_MIPS_COUNT_HZ (KVM_REG_MIPS | KVM_REG_SIZE_U64 | \ - 0x20000 | 2) +#define KVM_REG_MIPS_COUNT_HZ (KVM_REG_MIPS_KVM | KVM_REG_SIZE_U64 | 2) + + +/* + * KVM_REG_MIPS_FPU - Floating Point and MIPS SIMD Architecture (MSA) registers. + * + * bits[15..8] - Register subset (see definitions below). + * bits[7..5] - Must be zero. + * bits[4..0] - Register number within register subset. + */ + +#define KVM_REG_MIPS_FPR (KVM_REG_MIPS_FPU | 0x0000000000000000ULL) +#define KVM_REG_MIPS_FCR (KVM_REG_MIPS_FPU | 0x0000000000000100ULL) +#define KVM_REG_MIPS_MSACR (KVM_REG_MIPS_FPU | 0x0000000000000200ULL) + +/* + * KVM_REG_MIPS_FPR - Floating point / Vector registers. + */ +#define KVM_REG_MIPS_FPR_32(n) (KVM_REG_MIPS_FPR | KVM_REG_SIZE_U32 | (n)) +#define KVM_REG_MIPS_FPR_64(n) (KVM_REG_MIPS_FPR | KVM_REG_SIZE_U64 | (n)) +#define KVM_REG_MIPS_VEC_128(n) (KVM_REG_MIPS_FPR | KVM_REG_SIZE_U128 | (n)) + +/* + * KVM_REG_MIPS_FCR - Floating point control registers. + */ +#define KVM_REG_MIPS_FCR_IR (KVM_REG_MIPS_FCR | KVM_REG_SIZE_U32 | 0) +#define KVM_REG_MIPS_FCR_CSR (KVM_REG_MIPS_FCR | KVM_REG_SIZE_U32 | 31) + +/* + * KVM_REG_MIPS_MSACR - MIPS SIMD Architecture (MSA) control registers. + */ +#define KVM_REG_MIPS_MSA_IR (KVM_REG_MIPS_MSACR | KVM_REG_SIZE_U32 | 0) +#define KVM_REG_MIPS_MSA_CSR (KVM_REG_MIPS_MSACR | KVM_REG_SIZE_U32 | 1) + /* * KVM MIPS specific structures and definitions diff --git a/arch/mips/kernel/asm-offsets.c b/arch/mips/kernel/asm-offsets.c index 750d67ac41e9..e59fd7cfac9e 100644 --- a/arch/mips/kernel/asm-offsets.c +++ b/arch/mips/kernel/asm-offsets.c @@ -167,72 +167,6 @@ void output_thread_fpu_defines(void) OFFSET(THREAD_FPR30, task_struct, thread.fpu.fpr[30]); OFFSET(THREAD_FPR31, task_struct, thread.fpu.fpr[31]); - /* the least significant 64 bits of each FP register */ - OFFSET(THREAD_FPR0_LS64, task_struct, - thread.fpu.fpr[0].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR1_LS64, task_struct, - thread.fpu.fpr[1].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR2_LS64, task_struct, - thread.fpu.fpr[2].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR3_LS64, task_struct, - thread.fpu.fpr[3].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR4_LS64, task_struct, - thread.fpu.fpr[4].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR5_LS64, task_struct, - thread.fpu.fpr[5].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR6_LS64, task_struct, - thread.fpu.fpr[6].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR7_LS64, task_struct, - thread.fpu.fpr[7].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR8_LS64, task_struct, - thread.fpu.fpr[8].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR9_LS64, task_struct, - thread.fpu.fpr[9].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR10_LS64, task_struct, - thread.fpu.fpr[10].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR11_LS64, task_struct, - thread.fpu.fpr[11].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR12_LS64, task_struct, - thread.fpu.fpr[12].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR13_LS64, task_struct, - thread.fpu.fpr[13].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR14_LS64, task_struct, - thread.fpu.fpr[14].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR15_LS64, task_struct, - thread.fpu.fpr[15].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR16_LS64, task_struct, - thread.fpu.fpr[16].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR17_LS64, task_struct, - thread.fpu.fpr[17].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR18_LS64, task_struct, - thread.fpu.fpr[18].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR19_LS64, task_struct, - thread.fpu.fpr[19].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR20_LS64, task_struct, - thread.fpu.fpr[20].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR21_LS64, task_struct, - thread.fpu.fpr[21].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR22_LS64, task_struct, - thread.fpu.fpr[22].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR23_LS64, task_struct, - thread.fpu.fpr[23].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR24_LS64, task_struct, - thread.fpu.fpr[24].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR25_LS64, task_struct, - thread.fpu.fpr[25].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR26_LS64, task_struct, - thread.fpu.fpr[26].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR27_LS64, task_struct, - thread.fpu.fpr[27].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR28_LS64, task_struct, - thread.fpu.fpr[28].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR29_LS64, task_struct, - thread.fpu.fpr[29].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR30_LS64, task_struct, - thread.fpu.fpr[30].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR31_LS64, task_struct, - thread.fpu.fpr[31].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FCR31, task_struct, thread.fpu.fcr31); OFFSET(THREAD_MSA_CSR, task_struct, thread.fpu.msacsr); BLANK(); @@ -470,6 +404,45 @@ void output_kvm_defines(void) OFFSET(VCPU_LO, kvm_vcpu_arch, lo); OFFSET(VCPU_HI, kvm_vcpu_arch, hi); OFFSET(VCPU_PC, kvm_vcpu_arch, pc); + BLANK(); + + OFFSET(VCPU_FPR0, kvm_vcpu_arch, fpu.fpr[0]); + OFFSET(VCPU_FPR1, kvm_vcpu_arch, fpu.fpr[1]); + OFFSET(VCPU_FPR2, kvm_vcpu_arch, fpu.fpr[2]); + OFFSET(VCPU_FPR3, kvm_vcpu_arch, fpu.fpr[3]); + OFFSET(VCPU_FPR4, kvm_vcpu_arch, fpu.fpr[4]); + OFFSET(VCPU_FPR5, kvm_vcpu_arch, fpu.fpr[5]); + OFFSET(VCPU_FPR6, kvm_vcpu_arch, fpu.fpr[6]); + OFFSET(VCPU_FPR7, kvm_vcpu_arch, fpu.fpr[7]); + OFFSET(VCPU_FPR8, kvm_vcpu_arch, fpu.fpr[8]); + OFFSET(VCPU_FPR9, kvm_vcpu_arch, fpu.fpr[9]); + OFFSET(VCPU_FPR10, kvm_vcpu_arch, fpu.fpr[10]); + OFFSET(VCPU_FPR11, kvm_vcpu_arch, fpu.fpr[11]); + OFFSET(VCPU_FPR12, kvm_vcpu_arch, fpu.fpr[12]); + OFFSET(VCPU_FPR13, kvm_vcpu_arch, fpu.fpr[13]); + OFFSET(VCPU_FPR14, kvm_vcpu_arch, fpu.fpr[14]); + OFFSET(VCPU_FPR15, kvm_vcpu_arch, fpu.fpr[15]); + OFFSET(VCPU_FPR16, kvm_vcpu_arch, fpu.fpr[16]); + OFFSET(VCPU_FPR17, kvm_vcpu_arch, fpu.fpr[17]); + OFFSET(VCPU_FPR18, kvm_vcpu_arch, fpu.fpr[18]); + OFFSET(VCPU_FPR19, kvm_vcpu_arch, fpu.fpr[19]); + OFFSET(VCPU_FPR20, kvm_vcpu_arch, fpu.fpr[20]); + OFFSET(VCPU_FPR21, kvm_vcpu_arch, fpu.fpr[21]); + OFFSET(VCPU_FPR22, kvm_vcpu_arch, fpu.fpr[22]); + OFFSET(VCPU_FPR23, kvm_vcpu_arch, fpu.fpr[23]); + OFFSET(VCPU_FPR24, kvm_vcpu_arch, fpu.fpr[24]); + OFFSET(VCPU_FPR25, kvm_vcpu_arch, fpu.fpr[25]); + OFFSET(VCPU_FPR26, kvm_vcpu_arch, fpu.fpr[26]); + OFFSET(VCPU_FPR27, kvm_vcpu_arch, fpu.fpr[27]); + OFFSET(VCPU_FPR28, kvm_vcpu_arch, fpu.fpr[28]); + OFFSET(VCPU_FPR29, kvm_vcpu_arch, fpu.fpr[29]); + OFFSET(VCPU_FPR30, kvm_vcpu_arch, fpu.fpr[30]); + OFFSET(VCPU_FPR31, kvm_vcpu_arch, fpu.fpr[31]); + + OFFSET(VCPU_FCR31, kvm_vcpu_arch, fpu.fcr31); + OFFSET(VCPU_MSA_CSR, kvm_vcpu_arch, fpu.msacsr); + BLANK(); + OFFSET(VCPU_COP0, kvm_vcpu_arch, cop0); OFFSET(VCPU_GUEST_KERNEL_ASID, kvm_vcpu_arch, guest_kernel_asid); OFFSET(VCPU_GUEST_USER_ASID, kvm_vcpu_arch, guest_user_asid); diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S index 2ebaabe3af15..af42e7003f12 100644 --- a/arch/mips/kernel/genex.S +++ b/arch/mips/kernel/genex.S @@ -360,12 +360,15 @@ NESTED(nmi_handler, PT_SIZE, sp) .set mips1 SET_HARDFLOAT cfc1 a1, fcr31 - li a2, ~(0x3f << 12) - and a2, a1 - ctc1 a2, fcr31 .set pop - TRACE_IRQS_ON - STI + CLI + TRACE_IRQS_OFF + .endm + + .macro __build_clear_msa_fpe + _cfcmsa a1, MSA_CSR + CLI + TRACE_IRQS_OFF .endm .macro __build_clear_ade @@ -426,7 +429,7 @@ NESTED(nmi_handler, PT_SIZE, sp) BUILD_HANDLER cpu cpu sti silent /* #11 */ BUILD_HANDLER ov ov sti silent /* #12 */ BUILD_HANDLER tr tr sti silent /* #13 */ - BUILD_HANDLER msa_fpe msa_fpe sti silent /* #14 */ + BUILD_HANDLER msa_fpe msa_fpe msa_fpe silent /* #14 */ BUILD_HANDLER fpe fpe fpe silent /* #15 */ BUILD_HANDLER ftlb ftlb none silent /* #16 */ BUILD_HANDLER msa msa sti silent /* #21 */ diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c index 510452812594..7da6e324dd35 100644 --- a/arch/mips/kernel/ptrace.c +++ b/arch/mips/kernel/ptrace.c @@ -46,6 +46,26 @@ #define CREATE_TRACE_POINTS #include <trace/events/syscalls.h> +static void init_fp_ctx(struct task_struct *target) +{ + /* If FP has been used then the target already has context */ + if (tsk_used_math(target)) + return; + + /* Begin with data registers set to all 1s... */ + memset(&target->thread.fpu.fpr, ~0, sizeof(target->thread.fpu.fpr)); + + /* ...and FCSR zeroed */ + target->thread.fpu.fcr31 = 0; + + /* + * Record that the target has "used" math, such that the context + * just initialised, and any modifications made by the caller, + * aren't discarded. + */ + set_stopped_child_used_math(target); +} + /* * Called by kernel/ptrace.c when detaching.. * @@ -142,6 +162,7 @@ int ptrace_setfpregs(struct task_struct *child, __u32 __user *data) if (!access_ok(VERIFY_READ, data, 33 * 8)) return -EIO; + init_fp_ctx(child); fregs = get_fpu_regs(child); for (i = 0; i < 32; i++) { @@ -439,6 +460,8 @@ static int fpr_set(struct task_struct *target, /* XXX fcr31 */ + init_fp_ctx(target); + if (sizeof(target->thread.fpu.fpr[i]) == sizeof(elf_fpreg_t)) return user_regset_copyin(&pos, &count, &kbuf, &ubuf, &target->thread.fpu, @@ -660,12 +683,7 @@ long arch_ptrace(struct task_struct *child, long request, case FPR_BASE ... FPR_BASE + 31: { union fpureg *fregs = get_fpu_regs(child); - if (!tsk_used_math(child)) { - /* FP not yet used */ - memset(&child->thread.fpu, ~0, - sizeof(child->thread.fpu)); - child->thread.fpu.fcr31 = 0; - } + init_fp_ctx(child); #ifdef CONFIG_32BIT if (test_thread_flag(TIF_32BIT_FPREGS)) { /* diff --git a/arch/mips/kernel/r4k_fpu.S b/arch/mips/kernel/r4k_fpu.S index 676c5030a953..1d88af26ba82 100644 --- a/arch/mips/kernel/r4k_fpu.S +++ b/arch/mips/kernel/r4k_fpu.S @@ -34,7 +34,6 @@ .endm .set noreorder - .set MIPS_ISA_ARCH_LEVEL_RAW LEAF(_save_fp_context) .set push @@ -103,6 +102,7 @@ LEAF(_save_fp_context) /* Save 32-bit process floating point context */ LEAF(_save_fp_context32) .set push + .set MIPS_ISA_ARCH_LEVEL_RAW SET_HARDFLOAT cfc1 t1, fcr31 diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 33984c04b60b..5b4d711f878d 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -701,6 +701,13 @@ asmlinkage void do_ov(struct pt_regs *regs) int process_fpemu_return(int sig, void __user *fault_addr) { + /* + * We can't allow the emulated instruction to leave any of the cause + * bits set in FCSR. If they were then the kernel would take an FP + * exception when restoring FP context. + */ + current->thread.fpu.fcr31 &= ~FPU_CSR_ALL_X; + if (sig == SIGSEGV || sig == SIGBUS) { struct siginfo si = {0}; si.si_addr = fault_addr; @@ -781,6 +788,11 @@ asmlinkage void do_fpe(struct pt_regs *regs, unsigned long fcr31) if (notify_die(DIE_FP, "FP exception", regs, 0, regs_to_trapnr(regs), SIGFPE) == NOTIFY_STOP) goto out; + + /* Clear FCSR.Cause before enabling interrupts */ + write_32bit_cp1_register(CP1_STATUS, fcr31 & ~FPU_CSR_ALL_X); + local_irq_enable(); + die_if_kernel("FP exception in kernel code", regs); if (fcr31 & FPU_CSR_UNI_X) { @@ -804,18 +816,12 @@ asmlinkage void do_fpe(struct pt_regs *regs, unsigned long fcr31) sig = fpu_emulator_cop1Handler(regs, ¤t->thread.fpu, 1, &fault_addr); - /* - * We can't allow the emulated instruction to leave any of - * the cause bit set in $fcr31. - */ - current->thread.fpu.fcr31 &= ~FPU_CSR_ALL_X; + /* If something went wrong, signal */ + process_fpemu_return(sig, fault_addr); /* Restore the hardware register state */ own_fpu(1); /* Using the FPU again. */ - /* If something went wrong, signal */ - process_fpemu_return(sig, fault_addr); - goto out; } else if (fcr31 & FPU_CSR_INV_X) info.si_code = FPE_FLTINV; @@ -1392,13 +1398,22 @@ out: exception_exit(prev_state); } -asmlinkage void do_msa_fpe(struct pt_regs *regs) +asmlinkage void do_msa_fpe(struct pt_regs *regs, unsigned int msacsr) { enum ctx_state prev_state; prev_state = exception_enter(); + if (notify_die(DIE_MSAFP, "MSA FP exception", regs, 0, + regs_to_trapnr(regs), SIGFPE) == NOTIFY_STOP) + goto out; + + /* Clear MSACSR.Cause before enabling interrupts */ + write_msa_csr(msacsr & ~MSA_CSR_CAUSEF); + local_irq_enable(); + die_if_kernel("do_msa_fpe invoked from kernel context!", regs); force_sig(SIGFPE, current); +out: exception_exit(prev_state); } diff --git a/arch/mips/kvm/Makefile b/arch/mips/kvm/Makefile index 401fe027c261..637ebbebd549 100644 --- a/arch/mips/kvm/Makefile +++ b/arch/mips/kvm/Makefile @@ -1,13 +1,15 @@ # Makefile for KVM support for MIPS # -common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o coalesced_mmio.o) +common-objs-y = $(addprefix ../../../virt/kvm/, kvm_main.o coalesced_mmio.o) EXTRA_CFLAGS += -Ivirt/kvm -Iarch/mips/kvm -kvm-objs := $(common-objs) mips.o emulate.o locore.o \ +common-objs-$(CONFIG_CPU_HAS_MSA) += msa.o + +kvm-objs := $(common-objs-y) mips.o emulate.o locore.o \ interrupt.o stats.o commpage.o \ - dyntrans.o trap_emul.o + dyntrans.o trap_emul.o fpu.o obj-$(CONFIG_KVM) += kvm.o obj-y += callback.o tlb.o diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c index fb3e8dfd1ff6..6230f376a44e 100644 --- a/arch/mips/kvm/emulate.c +++ b/arch/mips/kvm/emulate.c @@ -884,6 +884,84 @@ enum emulation_result kvm_mips_emul_tlbp(struct kvm_vcpu *vcpu) return EMULATE_DONE; } +/** + * kvm_mips_config1_wrmask() - Find mask of writable bits in guest Config1 + * @vcpu: Virtual CPU. + * + * Finds the mask of bits which are writable in the guest's Config1 CP0 + * register, by userland (currently read-only to the guest). + */ +unsigned int kvm_mips_config1_wrmask(struct kvm_vcpu *vcpu) +{ + unsigned int mask = 0; + + /* Permit FPU to be present if FPU is supported */ + if (kvm_mips_guest_can_have_fpu(&vcpu->arch)) + mask |= MIPS_CONF1_FP; + + return mask; +} + +/** + * kvm_mips_config3_wrmask() - Find mask of writable bits in guest Config3 + * @vcpu: Virtual CPU. + * + * Finds the mask of bits which are writable in the guest's Config3 CP0 + * register, by userland (currently read-only to the guest). + */ +unsigned int kvm_mips_config3_wrmask(struct kvm_vcpu *vcpu) +{ + /* Config4 is optional */ + unsigned int mask = MIPS_CONF_M; + + /* Permit MSA to be present if MSA is supported */ + if (kvm_mips_guest_can_have_msa(&vcpu->arch)) + mask |= MIPS_CONF3_MSA; + + return mask; +} + +/** + * kvm_mips_config4_wrmask() - Find mask of writable bits in guest Config4 + * @vcpu: Virtual CPU. + * + * Finds the mask of bits which are writable in the guest's Config4 CP0 + * register, by userland (currently read-only to the guest). + */ +unsigned int kvm_mips_config4_wrmask(struct kvm_vcpu *vcpu) +{ + /* Config5 is optional */ + return MIPS_CONF_M; +} + +/** + * kvm_mips_config5_wrmask() - Find mask of writable bits in guest Config5 + * @vcpu: Virtual CPU. + * + * Finds the mask of bits which are writable in the guest's Config5 CP0 + * register, by the guest itself. + */ +unsigned int kvm_mips_config5_wrmask(struct kvm_vcpu *vcpu) +{ + unsigned int mask = 0; + + /* Permit MSAEn changes if MSA supported and enabled */ + if (kvm_mips_guest_has_msa(&vcpu->arch)) + mask |= MIPS_CONF5_MSAEN; + + /* + * Permit guest FPU mode changes if FPU is enabled and the relevant + * feature exists according to FIR register. + */ + if (kvm_mips_guest_has_fpu(&vcpu->arch)) { + if (cpu_has_fre) + mask |= MIPS_CONF5_FRE; + /* We don't support UFR or UFE */ + } + + return mask; +} + enum emulation_result kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc, uint32_t cause, struct kvm_run *run, struct kvm_vcpu *vcpu) @@ -1021,18 +1099,114 @@ enum emulation_result kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc, kvm_mips_write_compare(vcpu, vcpu->arch.gprs[rt]); } else if ((rd == MIPS_CP0_STATUS) && (sel == 0)) { - kvm_write_c0_guest_status(cop0, - vcpu->arch.gprs[rt]); + unsigned int old_val, val, change; + + old_val = kvm_read_c0_guest_status(cop0); + val = vcpu->arch.gprs[rt]; + change = val ^ old_val; + + /* Make sure that the NMI bit is never set */ + val &= ~ST0_NMI; + + /* + * Don't allow CU1 or FR to be set unless FPU + * capability enabled and exists in guest + * configuration. + */ + if (!kvm_mips_guest_has_fpu(&vcpu->arch)) + val &= ~(ST0_CU1 | ST0_FR); + + /* + * Also don't allow FR to be set if host doesn't + * support it. + */ + if (!(current_cpu_data.fpu_id & MIPS_FPIR_F64)) + val &= ~ST0_FR; + + + /* Handle changes in FPU mode */ + preempt_disable(); + + /* + * FPU and Vector register state is made + * UNPREDICTABLE by a change of FR, so don't + * even bother saving it. + */ + if (change & ST0_FR) + kvm_drop_fpu(vcpu); + + /* + * If MSA state is already live, it is undefined + * how it interacts with FR=0 FPU state, and we + * don't want to hit reserved instruction + * exceptions trying to save the MSA state later + * when CU=1 && FR=1, so play it safe and save + * it first. + */ + if (change & ST0_CU1 && !(val & ST0_FR) && + vcpu->arch.fpu_inuse & KVM_MIPS_FPU_MSA) + kvm_lose_fpu(vcpu); + /* - * Make sure that CU1 and NMI bits are - * never set + * Propagate CU1 (FPU enable) changes + * immediately if the FPU context is already + * loaded. When disabling we leave the context + * loaded so it can be quickly enabled again in + * the near future. */ - kvm_clear_c0_guest_status(cop0, - (ST0_CU1 | ST0_NMI)); + if (change & ST0_CU1 && + vcpu->arch.fpu_inuse & KVM_MIPS_FPU_FPU) + change_c0_status(ST0_CU1, val); + + preempt_enable(); + + kvm_write_c0_guest_status(cop0, val); #ifdef CONFIG_KVM_MIPS_DYN_TRANS - kvm_mips_trans_mtc0(inst, opc, vcpu); + /* + * If FPU present, we need CU1/FR bits to take + * effect fairly soon. + */ + if (!kvm_mips_guest_has_fpu(&vcpu->arch)) + kvm_mips_trans_mtc0(inst, opc, vcpu); #endif + } else if ((rd == MIPS_CP0_CONFIG) && (sel == 5)) { + unsigned int old_val, val, change, wrmask; + + old_val = kvm_read_c0_guest_config5(cop0); + val = vcpu->arch.gprs[rt]; + + /* Only a few bits are writable in Config5 */ + wrmask = kvm_mips_config5_wrmask(vcpu); + change = (val ^ old_val) & wrmask; + val = old_val ^ change; + + + /* Handle changes in FPU/MSA modes */ + preempt_disable(); + + /* + * Propagate FRE changes immediately if the FPU + * context is already loaded. + */ + if (change & MIPS_CONF5_FRE && + vcpu->arch.fpu_inuse & KVM_MIPS_FPU_FPU) + change_c0_config5(MIPS_CONF5_FRE, val); + + /* + * Propagate MSAEn changes immediately if the + * MSA context is already loaded. When disabling + * we leave the context loaded so it can be + * quickly enabled again in the near future. + */ + if (change & MIPS_CONF5_MSAEN && + vcpu->arch.fpu_inuse & KVM_MIPS_FPU_MSA) + change_c0_config5(MIPS_CONF5_MSAEN, + val); + + preempt_enable(); + + kvm_write_c0_guest_config5(cop0, val); } else if ((rd == MIPS_CP0_CAUSE) && (sel == 0)) { uint32_t old_cause, new_cause; @@ -1970,6 +2144,146 @@ enum emulation_result kvm_mips_emulate_bp_exc(unsigned long cause, return er; } +enum emulation_result kvm_mips_emulate_trap_exc(unsigned long cause, + uint32_t *opc, + struct kvm_run *run, + struct kvm_vcpu *vcpu) +{ + struct mips_coproc *cop0 = vcpu->arch.cop0; + struct kvm_vcpu_arch *arch = &vcpu->arch; + enum emulation_result er = EMULATE_DONE; + + if ((kvm_read_c0_guest_status(cop0) & ST0_EXL) == 0) { + /* save old pc */ + kvm_write_c0_guest_epc(cop0, arch->pc); + kvm_set_c0_guest_status(cop0, ST0_EXL); + + if (cause & CAUSEF_BD) + kvm_set_c0_guest_cause(cop0, CAUSEF_BD); + else + kvm_clear_c0_guest_cause(cop0, CAUSEF_BD); + + kvm_debug("Delivering TRAP @ pc %#lx\n", arch->pc); + + kvm_change_c0_guest_cause(cop0, (0xff), + (T_TRAP << CAUSEB_EXCCODE)); + + /* Set PC to the exception entry point */ + arch->pc = KVM_GUEST_KSEG0 + 0x180; + + } else { + kvm_err("Trying to deliver TRAP when EXL is already set\n"); + er = EMULATE_FAIL; + } + + return er; +} + +enum emulation_result kvm_mips_emulate_msafpe_exc(unsigned long cause, + uint32_t *opc, + struct kvm_run *run, + struct kvm_vcpu *vcpu) +{ + struct mips_coproc *cop0 = vcpu->arch.cop0; + struct kvm_vcpu_arch *arch = &vcpu->arch; + enum emulation_result er = EMULATE_DONE; + + if ((kvm_read_c0_guest_status(cop0) & ST0_EXL) == 0) { + /* save old pc */ + kvm_write_c0_guest_epc(cop0, arch->pc); + kvm_set_c0_guest_status(cop0, ST0_EXL); + + if (cause & CAUSEF_BD) + kvm_set_c0_guest_cause(cop0, CAUSEF_BD); + else + kvm_clear_c0_guest_cause(cop0, CAUSEF_BD); + + kvm_debug("Delivering MSAFPE @ pc %#lx\n", arch->pc); + + kvm_change_c0_guest_cause(cop0, (0xff), + (T_MSAFPE << CAUSEB_EXCCODE)); + + /* Set PC to the exception entry point */ + arch->pc = KVM_GUEST_KSEG0 + 0x180; + + } else { + kvm_err("Trying to deliver MSAFPE when EXL is already set\n"); + er = EMULATE_FAIL; + } + + return er; +} + +enum emulation_result kvm_mips_emulate_fpe_exc(unsigned long cause, + uint32_t *opc, + struct kvm_run *run, + struct kvm_vcpu *vcpu) +{ + struct mips_coproc *cop0 = vcpu->arch.cop0; + struct kvm_vcpu_arch *arch = &vcpu->arch; + enum emulation_result er = EMULATE_DONE; + + if ((kvm_read_c0_guest_status(cop0) & ST0_EXL) == 0) { + /* save old pc */ + kvm_write_c0_guest_epc(cop0, arch->pc); + kvm_set_c0_guest_status(cop0, ST0_EXL); + + if (cause & CAUSEF_BD) + kvm_set_c0_guest_cause(cop0, CAUSEF_BD); + else + kvm_clear_c0_guest_cause(cop0, CAUSEF_BD); + + kvm_debug("Delivering FPE @ pc %#lx\n", arch->pc); + + kvm_change_c0_guest_cause(cop0, (0xff), + (T_FPE << CAUSEB_EXCCODE)); + + /* Set PC to the exception entry point */ + arch->pc = KVM_GUEST_KSEG0 + 0x180; + + } else { + kvm_err("Trying to deliver FPE when EXL is already set\n"); + er = EMULATE_FAIL; + } + + return er; +} + +enum emulation_result kvm_mips_emulate_msadis_exc(unsigned long cause, + uint32_t *opc, + struct kvm_run *run, + struct kvm_vcpu *vcpu) +{ + struct mips_coproc *cop0 = vcpu->arch.cop0; + struct kvm_vcpu_arch *arch = &vcpu->arch; + enum emulation_result er = EMULATE_DONE; + + if ((kvm_read_c0_guest_status(cop0) & ST0_EXL) == 0) { + /* save old pc */ + kvm_write_c0_guest_epc(cop0, arch->pc); + kvm_set_c0_guest_status(cop0, ST0_EXL); + + if (cause & CAUSEF_BD) + kvm_set_c0_guest_cause(cop0, CAUSEF_BD); + else + kvm_clear_c0_guest_cause(cop0, CAUSEF_BD); + + kvm_debug("Delivering MSADIS @ pc %#lx\n", arch->pc); + + kvm_change_c0_guest_cause(cop0, (0xff), + (T_MSADIS << CAUSEB_EXCCODE)); + + /* Set PC to the exception entry point */ + arch->pc = KVM_GUEST_KSEG0 + 0x180; + + } else { + kvm_err("Trying to deliver MSADIS when EXL is already set\n"); + er = EMULATE_FAIL; + } + + return er; +} + /* ll/sc, rdhwr, sync emulation */ #define OPCODE 0xfc000000 @@ -2176,6 +2490,10 @@ enum emulation_result kvm_mips_check_privilege(unsigned long cause, case T_SYSCALL: case T_BREAK: case T_RES_INST: + case T_TRAP: + case T_MSAFPE: + case T_FPE: + case T_MSADIS: break; case T_COP_UNUSABLE: diff --git a/arch/mips/kvm/fpu.S b/arch/mips/kvm/fpu.S new file mode 100644 index 000000000000..531fbf5131c0 --- /dev/null +++ b/arch/mips/kvm/fpu.S @@ -0,0 +1,122 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * FPU context handling code for KVM. + * + * Copyright (C) 2015 Imagination Technologies Ltd. + */ + +#include <asm/asm.h> +#include <asm/asm-offsets.h> +#include <asm/fpregdef.h> +#include <asm/mipsregs.h> +#include <asm/regdef.h> + + .set noreorder + .set noat + +LEAF(__kvm_save_fpu) + .set push + .set mips64r2 + SET_HARDFLOAT + mfc0 t0, CP0_STATUS + sll t0, t0, 5 # is Status.FR set? + bgez t0, 1f # no: skip odd doubles + nop + sdc1 $f1, VCPU_FPR1(a0) + sdc1 $f3, VCPU_FPR3(a0) + sdc1 $f5, VCPU_FPR5(a0) + sdc1 $f7, VCPU_FPR7(a0) + sdc1 $f9, VCPU_FPR9(a0) + sdc1 $f11, VCPU_FPR11(a0) + sdc1 $f13, VCPU_FPR13(a0) + sdc1 $f15, VCPU_FPR15(a0) + sdc1 $f17, VCPU_FPR17(a0) + sdc1 $f19, VCPU_FPR19(a0) + sdc1 $f21, VCPU_FPR21(a0) + sdc1 $f23, VCPU_FPR23(a0) + sdc1 $f25, VCPU_FPR25(a0) + sdc1 $f27, VCPU_FPR27(a0) + sdc1 $f29, VCPU_FPR29(a0) + sdc1 $f31, VCPU_FPR31(a0) +1: sdc1 $f0, VCPU_FPR0(a0) + sdc1 $f2, VCPU_FPR2(a0) + sdc1 $f4, VCPU_FPR4(a0) + sdc1 $f6, VCPU_FPR6(a0) + sdc1 $f8, VCPU_FPR8(a0) + sdc1 $f10, VCPU_FPR10(a0) + sdc1 $f12, VCPU_FPR12(a0) + sdc1 $f14, VCPU_FPR14(a0) + sdc1 $f16, VCPU_FPR16(a0) + sdc1 $f18, VCPU_FPR18(a0) + sdc1 $f20, VCPU_FPR20(a0) + sdc1 $f22, VCPU_FPR22(a0) + sdc1 $f24, VCPU_FPR24(a0) + sdc1 $f26, VCPU_FPR26(a0) + sdc1 $f28, VCPU_FPR28(a0) + jr ra + sdc1 $f30, VCPU_FPR30(a0) + .set pop + END(__kvm_save_fpu) + +LEAF(__kvm_restore_fpu) + .set push + .set mips64r2 + SET_HARDFLOAT + mfc0 t0, CP0_STATUS + sll t0, t0, 5 # is Status.FR set? + bgez t0, 1f # no: skip odd doubles + nop + ldc1 $f1, VCPU_FPR1(a0) + ldc1 $f3, VCPU_FPR3(a0) + ldc1 $f5, VCPU_FPR5(a0) + ldc1 $f7, VCPU_FPR7(a0) + ldc1 $f9, VCPU_FPR9(a0) + ldc1 $f11, VCPU_FPR11(a0) + ldc1 $f13, VCPU_FPR13(a0) + ldc1 $f15, VCPU_FPR15(a0) + ldc1 $f17, VCPU_FPR17(a0) + ldc1 $f19, VCPU_FPR19(a0) + ldc1 $f21, VCPU_FPR21(a0) + ldc1 $f23, VCPU_FPR23(a0) + ldc1 $f25, VCPU_FPR25(a0) + ldc1 $f27, VCPU_FPR27(a0) + ldc1 $f29, VCPU_FPR29(a0) + ldc1 $f31, VCPU_FPR31(a0) +1: ldc1 $f0, VCPU_FPR0(a0) + ldc1 $f2, VCPU_FPR2(a0) + ldc1 $f4, VCPU_FPR4(a0) + ldc1 $f6, VCPU_FPR6(a0) + ldc1 $f8, VCPU_FPR8(a0) + ldc1 $f10, VCPU_FPR10(a0) + ldc1 $f12, VCPU_FPR12(a0) + ldc1 $f14, VCPU_FPR14(a0) + ldc1 $f16, VCPU_FPR16(a0) + ldc1 $f18, VCPU_FPR18(a0) + ldc1 $f20, VCPU_FPR20(a0) + ldc1 $f22, VCPU_FPR22(a0) + ldc1 $f24, VCPU_FPR24(a0) + ldc1 $f26, VCPU_FPR26(a0) + ldc1 $f28, VCPU_FPR28(a0) + jr ra + ldc1 $f30, VCPU_FPR30(a0) + .set pop + END(__kvm_restore_fpu) + +LEAF(__kvm_restore_fcsr) + .set push + SET_HARDFLOAT + lw t0, VCPU_FCR31(a0) + /* + * The ctc1 must stay at this offset in __kvm_restore_fcsr. + * See kvm_mips_csr_die_notify() which handles t0 containing a value + * which triggers an FP Exception, which must be stepped over and + * ignored since the set cause bits must remain there for the guest. + */ + ctc1 t0, fcr31 + jr ra + nop + .set pop + END(__kvm_restore_fcsr) diff --git a/arch/mips/kvm/locore.S b/arch/mips/kvm/locore.S index 4a68b176d6e4..c567240386a0 100644 --- a/arch/mips/kvm/locore.S +++ b/arch/mips/kvm/locore.S @@ -36,6 +36,8 @@ #define PT_HOST_USERLOCAL PT_EPC #define CP0_DDATA_LO $28,3 +#define CP0_CONFIG3 $16,3 +#define CP0_CONFIG5 $16,5 #define CP0_EBASE $15,1 #define CP0_INTCTL $12,1 @@ -353,6 +355,42 @@ NESTED (MIPSX(GuestException), CALLFRAME_SIZ, ra) LONG_L k0, VCPU_HOST_EBASE(k1) mtc0 k0,CP0_EBASE + /* + * If FPU is enabled, save FCR31 and clear it so that later ctc1's don't + * trigger FPE for pending exceptions. + */ + .set at + and v1, v0, ST0_CU1 + beqz v1, 1f + nop + .set push + SET_HARDFLOAT + cfc1 t0, fcr31 + sw t0, VCPU_FCR31(k1) + ctc1 zero,fcr31 + .set pop + .set noat +1: + +#ifdef CONFIG_CPU_HAS_MSA + /* + * If MSA is enabled, save MSACSR and clear it so that later + * instructions don't trigger MSAFPE for pending exceptions. + */ + mfc0 t0, CP0_CONFIG3 + ext t0, t0, 28, 1 /* MIPS_CONF3_MSAP */ + beqz t0, 1f + nop + mfc0 t0, CP0_CONFIG5 + ext t0, t0, 27, 1 /* MIPS_CONF5_MSAEN */ + beqz t0, 1f + nop + _cfcmsa t0, MSA_CSR + sw t0, VCPU_MSA_CSR(k1) + _ctcmsa MSA_CSR, zero +1: +#endif + /* Now that the new EBASE has been loaded, unset BEV and KSU_USER */ .set at and v0, v0, ~(ST0_EXL | KSU_USER | ST0_IE) diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index c9eccf5df912..bb68e8d520e8 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -11,6 +11,7 @@ #include <linux/errno.h> #include <linux/err.h> +#include <linux/kdebug.h> #include <linux/module.h> #include <linux/vmalloc.h> #include <linux/fs.h> @@ -48,6 +49,10 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "syscall", VCPU_STAT(syscall_exits), KVM_STAT_VCPU }, { "resvd_inst", VCPU_STAT(resvd_inst_exits), KVM_STAT_VCPU }, { "break_inst", VCPU_STAT(break_inst_exits), KVM_STAT_VCPU }, + { "trap_inst", VCPU_STAT(trap_inst_exits), KVM_STAT_VCPU }, + { "msa_fpe", VCPU_STAT(msa_fpe_exits), KVM_STAT_VCPU }, + { "fpe", VCPU_STAT(fpe_exits), KVM_STAT_VCPU }, + { "msa_disabled", VCPU_STAT(msa_disabled_exits), KVM_STAT_VCPU }, { "flush_dcache", VCPU_STAT(flush_dcache_exits), KVM_STAT_VCPU }, { "halt_successful_poll", VCPU_STAT(halt_successful_poll), KVM_STAT_VCPU }, { "halt_wakeup", VCPU_STAT(halt_wakeup), KVM_STAT_VCPU }, @@ -504,10 +509,13 @@ static u64 kvm_mips_get_one_regs[] = { KVM_REG_MIPS_CP0_STATUS, KVM_REG_MIPS_CP0_CAUSE, KVM_REG_MIPS_CP0_EPC, + KVM_REG_MIPS_CP0_PRID, KVM_REG_MIPS_CP0_CONFIG, KVM_REG_MIPS_CP0_CONFIG1, KVM_REG_MIPS_CP0_CONFIG2, KVM_REG_MIPS_CP0_CONFIG3, + KVM_REG_MIPS_CP0_CONFIG4, + KVM_REG_MIPS_CP0_CONFIG5, KVM_REG_MIPS_CP0_CONFIG7, KVM_REG_MIPS_CP0_ERROREPC, @@ -520,10 +528,14 @@ static int kvm_mips_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { struct mips_coproc *cop0 = vcpu->arch.cop0; + struct mips_fpu_struct *fpu = &vcpu->arch.fpu; int ret; s64 v; + s64 vs[2]; + unsigned int idx; switch (reg->id) { + /* General purpose registers */ case KVM_REG_MIPS_R0 ... KVM_REG_MIPS_R31: v = (long)vcpu->arch.gprs[reg->id - KVM_REG_MIPS_R0]; break; @@ -537,6 +549,67 @@ static int kvm_mips_get_reg(struct kvm_vcpu *vcpu, v = (long)vcpu->arch.pc; break; + /* Floating point registers */ + case KVM_REG_MIPS_FPR_32(0) ... KVM_REG_MIPS_FPR_32(31): + if (!kvm_mips_guest_has_fpu(&vcpu->arch)) + return -EINVAL; + idx = reg->id - KVM_REG_MIPS_FPR_32(0); + /* Odd singles in top of even double when FR=0 */ + if (kvm_read_c0_guest_status(cop0) & ST0_FR) + v = get_fpr32(&fpu->fpr[idx], 0); + else + v = get_fpr32(&fpu->fpr[idx & ~1], idx & 1); + break; + case KVM_REG_MIPS_FPR_64(0) ... KVM_REG_MIPS_FPR_64(31): + if (!kvm_mips_guest_has_fpu(&vcpu->arch)) + return -EINVAL; + idx = reg->id - KVM_REG_MIPS_FPR_64(0); + /* Can't access odd doubles in FR=0 mode */ + if (idx & 1 && !(kvm_read_c0_guest_status(cop0) & ST0_FR)) + return -EINVAL; + v = get_fpr64(&fpu->fpr[idx], 0); + break; + case KVM_REG_MIPS_FCR_IR: + if (!kvm_mips_guest_has_fpu(&vcpu->arch)) + return -EINVAL; + v = boot_cpu_data.fpu_id; + break; + case KVM_REG_MIPS_FCR_CSR: + if (!kvm_mips_guest_has_fpu(&vcpu->arch)) + return -EINVAL; + v = fpu->fcr31; + break; + + /* MIPS SIMD Architecture (MSA) registers */ + case KVM_REG_MIPS_VEC_128(0) ... KVM_REG_MIPS_VEC_128(31): + if (!kvm_mips_guest_has_msa(&vcpu->arch)) + return -EINVAL; + /* Can't access MSA registers in FR=0 mode */ + if (!(kvm_read_c0_guest_status(cop0) & ST0_FR)) + return -EINVAL; + idx = reg->id - KVM_REG_MIPS_VEC_128(0); +#ifdef CONFIG_CPU_LITTLE_ENDIAN + /* least significant byte first */ + vs[0] = get_fpr64(&fpu->fpr[idx], 0); + vs[1] = get_fpr64(&fpu->fpr[idx], 1); +#else + /* most significant byte first */ + vs[0] = get_fpr64(&fpu->fpr[idx], 1); + vs[1] = get_fpr64(&fpu->fpr[idx], 0); +#endif + break; + case KVM_REG_MIPS_MSA_IR: + if (!kvm_mips_guest_has_msa(&vcpu->arch)) + return -EINVAL; + v = boot_cpu_data.msa_id; + break; + case KVM_REG_MIPS_MSA_CSR: + if (!kvm_mips_guest_has_msa(&vcpu->arch)) + return -EINVAL; + v = fpu->msacsr; + break; + + /* Co-processor 0 registers */ case KVM_REG_MIPS_CP0_INDEX: v = (long)kvm_read_c0_guest_index(cop0); break; @@ -573,8 +646,8 @@ static int kvm_mips_get_reg(struct kvm_vcpu *vcpu, case KVM_REG_MIPS_CP0_EPC: v = (long)kvm_read_c0_guest_epc(cop0); break; - case KVM_REG_MIPS_CP0_ERROREPC: - v = (long)kvm_read_c0_guest_errorepc(cop0); + case KVM_REG_MIPS_CP0_PRID: + v = (long)kvm_read_c0_guest_prid(cop0); break; case KVM_REG_MIPS_CP0_CONFIG: v = (long)kvm_read_c0_guest_config(cop0); @@ -588,9 +661,18 @@ static int kvm_mips_get_reg(struct kvm_vcpu *vcpu, case KVM_REG_MIPS_CP0_CONFIG3: v = (long)kvm_read_c0_guest_config3(cop0); break; + case KVM_REG_MIPS_CP0_CONFIG4: + v = (long)kvm_read_c0_guest_config4(cop0); + break; + case KVM_REG_MIPS_CP0_CONFIG5: + v = (long)kvm_read_c0_guest_config5(cop0); + break; case KVM_REG_MIPS_CP0_CONFIG7: v = (long)kvm_read_c0_guest_config7(cop0); break; + case KVM_REG_MIPS_CP0_ERROREPC: + v = (long)kvm_read_c0_guest_errorepc(cop0); + break; /* registers to be handled specially */ case KVM_REG_MIPS_CP0_COUNT: case KVM_REG_MIPS_COUNT_CTL: @@ -612,6 +694,10 @@ static int kvm_mips_get_reg(struct kvm_vcpu *vcpu, u32 v32 = (u32)v; return put_user(v32, uaddr32); + } else if ((reg->id & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U128) { + void __user *uaddr = (void __user *)(long)reg->addr; + + return copy_to_user(uaddr, vs, 16); } else { return -EINVAL; } @@ -621,7 +707,10 @@ static int kvm_mips_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { struct mips_coproc *cop0 = vcpu->arch.cop0; - u64 v; + struct mips_fpu_struct *fpu = &vcpu->arch.fpu; + s64 v; + s64 vs[2]; + unsigned int idx; if ((reg->id & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U64) { u64 __user *uaddr64 = (u64 __user *)(long)reg->addr; @@ -635,11 +724,16 @@ static int kvm_mips_set_reg(struct kvm_vcpu *vcpu, if (get_user(v32, uaddr32) != 0) return -EFAULT; v = (s64)v32; + } else if ((reg->id & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U128) { + void __user *uaddr = (void __user *)(long)reg->addr; + + return copy_from_user(vs, uaddr, 16); } else { return -EINVAL; } switch (reg->id) { + /* General purpose registers */ case KVM_REG_MIPS_R0: /* Silently ignore requests to set $0 */ break; @@ -656,6 +750,64 @@ static int kvm_mips_set_reg(struct kvm_vcpu *vcpu, vcpu->arch.pc = v; break; + /* Floating point registers */ + case KVM_REG_MIPS_FPR_32(0) ... KVM_REG_MIPS_FPR_32(31): + if (!kvm_mips_guest_has_fpu(&vcpu->arch)) + return -EINVAL; + idx = reg->id - KVM_REG_MIPS_FPR_32(0); + /* Odd singles in top of even double when FR=0 */ + if (kvm_read_c0_guest_status(cop0) & ST0_FR) + set_fpr32(&fpu->fpr[idx], 0, v); + else + set_fpr32(&fpu->fpr[idx & ~1], idx & 1, v); + break; + case KVM_REG_MIPS_FPR_64(0) ... KVM_REG_MIPS_FPR_64(31): + if (!kvm_mips_guest_has_fpu(&vcpu->arch)) + return -EINVAL; + idx = reg->id - KVM_REG_MIPS_FPR_64(0); + /* Can't access odd doubles in FR=0 mode */ + if (idx & 1 && !(kvm_read_c0_guest_status(cop0) & ST0_FR)) + return -EINVAL; + set_fpr64(&fpu->fpr[idx], 0, v); + break; + case KVM_REG_MIPS_FCR_IR: + if (!kvm_mips_guest_has_fpu(&vcpu->arch)) + return -EINVAL; + /* Read-only */ + break; + case KVM_REG_MIPS_FCR_CSR: + if (!kvm_mips_guest_has_fpu(&vcpu->arch)) + return -EINVAL; + fpu->fcr31 = v; + break; + + /* MIPS SIMD Architecture (MSA) registers */ + case KVM_REG_MIPS_VEC_128(0) ... KVM_REG_MIPS_VEC_128(31): + if (!kvm_mips_guest_has_msa(&vcpu->arch)) + return -EINVAL; + idx = reg->id - KVM_REG_MIPS_VEC_128(0); +#ifdef CONFIG_CPU_LITTLE_ENDIAN + /* least significant byte first */ + set_fpr64(&fpu->fpr[idx], 0, vs[0]); + set_fpr64(&fpu->fpr[idx], 1, vs[1]); +#else + /* most significant byte first */ + set_fpr64(&fpu->fpr[idx], 1, vs[0]); + set_fpr64(&fpu->fpr[idx], 0, vs[1]); +#endif + break; + case KVM_REG_MIPS_MSA_IR: + if (!kvm_mips_guest_has_msa(&vcpu->arch)) + return -EINVAL; + /* Read-only */ + break; + case KVM_REG_MIPS_MSA_CSR: + if (!kvm_mips_guest_has_msa(&vcpu->arch)) + return -EINVAL; + fpu->msacsr = v; + break; + + /* Co-processor 0 registers */ case KVM_REG_MIPS_CP0_INDEX: kvm_write_c0_guest_index(cop0, v); break; @@ -686,6 +838,9 @@ static int kvm_mips_set_reg(struct kvm_vcpu *vcpu, case KVM_REG_MIPS_CP0_EPC: kvm_write_c0_guest_epc(cop0, v); break; + case KVM_REG_MIPS_CP0_PRID: + kvm_write_c0_guest_prid(cop0, v); + break; case KVM_REG_MIPS_CP0_ERROREPC: kvm_write_c0_guest_errorepc(cop0, v); break; @@ -693,6 +848,12 @@ static int kvm_mips_set_reg(struct kvm_vcpu *vcpu, case KVM_REG_MIPS_CP0_COUNT: case KVM_REG_MIPS_CP0_COMPARE: case KVM_REG_MIPS_CP0_CAUSE: + case KVM_REG_MIPS_CP0_CONFIG: + case KVM_REG_MIPS_CP0_CONFIG1: + case KVM_REG_MIPS_CP0_CONFIG2: + case KVM_REG_MIPS_CP0_CONFIG3: + case KVM_REG_MIPS_CP0_CONFIG4: + case KVM_REG_MIPS_CP0_CONFIG5: case KVM_REG_MIPS_COUNT_CTL: case KVM_REG_MIPS_COUNT_RESUME: case KVM_REG_MIPS_COUNT_HZ: @@ -703,6 +864,33 @@ static int kvm_mips_set_reg(struct kvm_vcpu *vcpu, return 0; } +static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, + struct kvm_enable_cap *cap) +{ + int r = 0; + + if (!kvm_vm_ioctl_check_extension(vcpu->kvm, cap->cap)) + return -EINVAL; + if (cap->flags) + return -EINVAL; + if (cap->args[0]) + return -EINVAL; + + switch (cap->cap) { + case KVM_CAP_MIPS_FPU: + vcpu->arch.fpu_enabled = true; + break; + case KVM_CAP_MIPS_MSA: + vcpu->arch.msa_enabled = true; + break; + default: + r = -EINVAL; + break; + } + + return r; +} + long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -760,6 +948,15 @@ long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, r = kvm_vcpu_ioctl_interrupt(vcpu, &irq); break; } + case KVM_ENABLE_CAP: { + struct kvm_enable_cap cap; + + r = -EFAULT; + if (copy_from_user(&cap, argp, sizeof(cap))) + goto out; + r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap); + break; + } default: r = -ENOIOCTLCMD; } @@ -868,11 +1065,30 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) switch (ext) { case KVM_CAP_ONE_REG: + case KVM_CAP_ENABLE_CAP: r = 1; break; case KVM_CAP_COALESCED_MMIO: r = KVM_COALESCED_MMIO_PAGE_OFFSET; break; + case KVM_CAP_MIPS_FPU: + r = !!cpu_has_fpu; + break; + case KVM_CAP_MIPS_MSA: + /* + * We don't support MSA vector partitioning yet: + * 1) It would require explicit support which can't be tested + * yet due to lack of support in current hardware. + * 2) It extends the state that would need to be saved/restored + * by e.g. QEMU for migration. + * + * When vector partitioning hardware becomes available, support + * could be added by requiring a flag when enabling + * KVM_CAP_MIPS_MSA capability to indicate that userland knows + * to save/restore the appropriate extra state. + */ + r = cpu_has_msa && !(boot_cpu_data.msa_id & MSA_IR_WRPF); + break; default: r = 0; break; @@ -1119,6 +1335,30 @@ int kvm_mips_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu) ret = kvm_mips_callbacks->handle_break(vcpu); break; + case T_TRAP: + ++vcpu->stat.trap_inst_exits; + trace_kvm_exit(vcpu, TRAP_INST_EXITS); + ret = kvm_mips_callbacks->handle_trap(vcpu); + break; + + case T_MSAFPE: + ++vcpu->stat.msa_fpe_exits; + trace_kvm_exit(vcpu, MSA_FPE_EXITS); + ret = kvm_mips_callbacks->handle_msa_fpe(vcpu); + break; + + case T_FPE: + ++vcpu->stat.fpe_exits; + trace_kvm_exit(vcpu, FPE_EXITS); + ret = kvm_mips_callbacks->handle_fpe(vcpu); + break; + + case T_MSADIS: + ++vcpu->stat.msa_disabled_exits; + trace_kvm_exit(vcpu, MSA_DISABLED_EXITS); + ret = kvm_mips_callbacks->handle_msa_disabled(vcpu); + break; + default: kvm_err("Exception Code: %d, not yet handled, @ PC: %p, inst: 0x%08x BadVaddr: %#lx Status: %#lx\n", exccode, opc, kvm_get_inst(opc, vcpu), badvaddr, @@ -1146,12 +1386,233 @@ skip_emul: } } + if (ret == RESUME_GUEST) { + /* + * If FPU / MSA are enabled (i.e. the guest's FPU / MSA context + * is live), restore FCR31 / MSACSR. + * + * This should be before returning to the guest exception + * vector, as it may well cause an [MSA] FP exception if there + * are pending exception bits unmasked. (see + * kvm_mips_csr_die_notifier() for how that is handled). + */ + if (kvm_mips_guest_has_fpu(&vcpu->arch) && + read_c0_status() & ST0_CU1) + __kvm_restore_fcsr(&vcpu->arch); + + if (kvm_mips_guest_has_msa(&vcpu->arch) && + read_c0_config5() & MIPS_CONF5_MSAEN) + __kvm_restore_msacsr(&vcpu->arch); + } + /* Disable HTW before returning to guest or host */ htw_stop(); return ret; } +/* Enable FPU for guest and restore context */ +void kvm_own_fpu(struct kvm_vcpu *vcpu) +{ + struct mips_coproc *cop0 = vcpu->arch.cop0; + unsigned int sr, cfg5; + + preempt_disable(); + + sr = kvm_read_c0_guest_status(cop0); + + /* + * If MSA state is already live, it is undefined how it interacts with + * FR=0 FPU state, and we don't want to hit reserved instruction + * exceptions trying to save the MSA state later when CU=1 && FR=1, so + * play it safe and save it first. + * + * In theory we shouldn't ever hit this case since kvm_lose_fpu() should + * get called when guest CU1 is set, however we can't trust the guest + * not to clobber the status register directly via the commpage. + */ + if (cpu_has_msa && sr & ST0_CU1 && !(sr & ST0_FR) && + vcpu->arch.fpu_inuse & KVM_MIPS_FPU_MSA) + kvm_lose_fpu(vcpu); + + /* + * Enable FPU for guest + * We set FR and FRE according to guest context + */ + change_c0_status(ST0_CU1 | ST0_FR, sr); + if (cpu_has_fre) { + cfg5 = kvm_read_c0_guest_config5(cop0); + change_c0_config5(MIPS_CONF5_FRE, cfg5); + } + enable_fpu_hazard(); + + /* If guest FPU state not active, restore it now */ + if (!(vcpu->arch.fpu_inuse & KVM_MIPS_FPU_FPU)) { + __kvm_restore_fpu(&vcpu->arch); + vcpu->arch.fpu_inuse |= KVM_MIPS_FPU_FPU; + } + + preempt_enable(); +} + +#ifdef CONFIG_CPU_HAS_MSA +/* Enable MSA for guest and restore context */ +void kvm_own_msa(struct kvm_vcpu *vcpu) +{ + struct mips_coproc *cop0 = vcpu->arch.cop0; + unsigned int sr, cfg5; + + preempt_disable(); + + /* + * Enable FPU if enabled in guest, since we're restoring FPU context + * anyway. We set FR and FRE according to guest context. + */ + if (kvm_mips_guest_has_fpu(&vcpu->arch)) { + sr = kvm_read_c0_guest_status(cop0); + + /* + * If FR=0 FPU state is already live, it is undefined how it + * interacts with MSA state, so play it safe and save it first. + */ + if (!(sr & ST0_FR) && + (vcpu->arch.fpu_inuse & (KVM_MIPS_FPU_FPU | + KVM_MIPS_FPU_MSA)) == KVM_MIPS_FPU_FPU) + kvm_lose_fpu(vcpu); + + change_c0_status(ST0_CU1 | ST0_FR, sr); + if (sr & ST0_CU1 && cpu_has_fre) { + cfg5 = kvm_read_c0_guest_config5(cop0); + change_c0_config5(MIPS_CONF5_FRE, cfg5); + } + } + + /* Enable MSA for guest */ + set_c0_config5(MIPS_CONF5_MSAEN); + enable_fpu_hazard(); + + switch (vcpu->arch.fpu_inuse & (KVM_MIPS_FPU_FPU | KVM_MIPS_FPU_MSA)) { + case KVM_MIPS_FPU_FPU: + /* + * Guest FPU state already loaded, only restore upper MSA state + */ + __kvm_restore_msa_upper(&vcpu->arch); + vcpu->arch.fpu_inuse |= KVM_MIPS_FPU_MSA; + break; + case 0: + /* Neither FPU or MSA already active, restore full MSA state */ + __kvm_restore_msa(&vcpu->arch); + vcpu->arch.fpu_inuse |= KVM_MIPS_FPU_MSA; + if (kvm_mips_guest_has_fpu(&vcpu->arch)) + vcpu->arch.fpu_inuse |= KVM_MIPS_FPU_FPU; + break; + default: + break; + } + + preempt_enable(); +} +#endif + +/* Drop FPU & MSA without saving it */ +void kvm_drop_fpu(struct kvm_vcpu *vcpu) +{ + preempt_disable(); + if (cpu_has_msa && vcpu->arch.fpu_inuse & KVM_MIPS_FPU_MSA) { + disable_msa(); + vcpu->arch.fpu_inuse &= ~KVM_MIPS_FPU_MSA; + } + if (vcpu->arch.fpu_inuse & KVM_MIPS_FPU_FPU) { + clear_c0_status(ST0_CU1 | ST0_FR); + vcpu->arch.fpu_inuse &= ~KVM_MIPS_FPU_FPU; + } + preempt_enable(); +} + +/* Save and disable FPU & MSA */ +void kvm_lose_fpu(struct kvm_vcpu *vcpu) +{ + /* + * FPU & MSA get disabled in root context (hardware) when it is disabled + * in guest context (software), but the register state in the hardware + * may still be in use. This is why we explicitly re-enable the hardware + * before saving. + */ + + preempt_disable(); + if (cpu_has_msa && vcpu->arch.fpu_inuse & KVM_MIPS_FPU_MSA) { + set_c0_config5(MIPS_CONF5_MSAEN); + enable_fpu_hazard(); + + __kvm_save_msa(&vcpu->arch); + + /* Disable MSA & FPU */ + disable_msa(); + if (vcpu->arch.fpu_inuse & KVM_MIPS_FPU_FPU) + clear_c0_status(ST0_CU1 | ST0_FR); + vcpu->arch.fpu_inuse &= ~(KVM_MIPS_FPU_FPU | KVM_MIPS_FPU_MSA); + } else if (vcpu->arch.fpu_inuse & KVM_MIPS_FPU_FPU) { + set_c0_status(ST0_CU1); + enable_fpu_hazard(); + + __kvm_save_fpu(&vcpu->arch); + vcpu->arch.fpu_inuse &= ~KVM_MIPS_FPU_FPU; + + /* Disable FPU */ + clear_c0_status(ST0_CU1 | ST0_FR); + } + preempt_enable(); +} + +/* + * Step over a specific ctc1 to FCSR and a specific ctcmsa to MSACSR which are + * used to restore guest FCSR/MSACSR state and may trigger a "harmless" FP/MSAFP + * exception if cause bits are set in the value being written. + */ +static int kvm_mips_csr_die_notify(struct notifier_block *self, + unsigned long cmd, void *ptr) +{ + struct die_args *args = (struct die_args *)ptr; + struct pt_regs *regs = args->regs; + unsigned long pc; + + /* Only interested in FPE and MSAFPE */ + if (cmd != DIE_FP && cmd != DIE_MSAFP) + return NOTIFY_DONE; + + /* Return immediately if guest context isn't active */ + if (!(current->flags & PF_VCPU)) + return NOTIFY_DONE; + + /* Should never get here from user mode */ + BUG_ON(user_mode(regs)); + + pc = instruction_pointer(regs); + switch (cmd) { + case DIE_FP: + /* match 2nd instruction in __kvm_restore_fcsr */ + if (pc != (unsigned long)&__kvm_restore_fcsr + 4) + return NOTIFY_DONE; + break; + case DIE_MSAFP: + /* match 2nd/3rd instruction in __kvm_restore_msacsr */ + if (!cpu_has_msa || + pc < (unsigned long)&__kvm_restore_msacsr + 4 || + pc > (unsigned long)&__kvm_restore_msacsr + 8) + return NOTIFY_DONE; + break; + } + + /* Move PC forward a little and continue executing */ + instruction_pointer(regs) += 4; + + return NOTIFY_STOP; +} + +static struct notifier_block kvm_mips_csr_die_notifier = { + .notifier_call = kvm_mips_csr_die_notify, +}; + int __init kvm_mips_init(void) { int ret; @@ -1161,6 +1622,8 @@ int __init kvm_mips_init(void) if (ret) return ret; + register_die_notifier(&kvm_mips_csr_die_notifier); + /* * On MIPS, kernel modules are executed from "mapped space", which * requires TLBs. The TLB handling code is statically linked with @@ -1173,7 +1636,6 @@ int __init kvm_mips_init(void) kvm_mips_release_pfn_clean = kvm_release_pfn_clean; kvm_mips_is_error_pfn = is_error_pfn; - pr_info("KVM/MIPS Initialized\n"); return 0; } @@ -1185,7 +1647,7 @@ void __exit kvm_mips_exit(void) kvm_mips_release_pfn_clean = NULL; kvm_mips_is_error_pfn = NULL; - pr_info("KVM/MIPS unloaded\n"); + unregister_die_notifier(&kvm_mips_csr_die_notifier); } module_init(kvm_mips_init); diff --git a/arch/mips/kvm/msa.S b/arch/mips/kvm/msa.S new file mode 100644 index 000000000000..d02f0c6cc2cc --- /dev/null +++ b/arch/mips/kvm/msa.S @@ -0,0 +1,161 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * MIPS SIMD Architecture (MSA) context handling code for KVM. + * + * Copyright (C) 2015 Imagination Technologies Ltd. + */ + +#include <asm/asm.h> +#include <asm/asm-offsets.h> +#include <asm/asmmacro.h> +#include <asm/regdef.h> + + .set noreorder + .set noat + +LEAF(__kvm_save_msa) + st_d 0, VCPU_FPR0, a0 + st_d 1, VCPU_FPR1, a0 + st_d 2, VCPU_FPR2, a0 + st_d 3, VCPU_FPR3, a0 + st_d 4, VCPU_FPR4, a0 + st_d 5, VCPU_FPR5, a0 + st_d 6, VCPU_FPR6, a0 + st_d 7, VCPU_FPR7, a0 + st_d 8, VCPU_FPR8, a0 + st_d 9, VCPU_FPR9, a0 + st_d 10, VCPU_FPR10, a0 + st_d 11, VCPU_FPR11, a0 + st_d 12, VCPU_FPR12, a0 + st_d 13, VCPU_FPR13, a0 + st_d 14, VCPU_FPR14, a0 + st_d 15, VCPU_FPR15, a0 + st_d 16, VCPU_FPR16, a0 + st_d 17, VCPU_FPR17, a0 + st_d 18, VCPU_FPR18, a0 + st_d 19, VCPU_FPR19, a0 + st_d 20, VCPU_FPR20, a0 + st_d 21, VCPU_FPR21, a0 + st_d 22, VCPU_FPR22, a0 + st_d 23, VCPU_FPR23, a0 + st_d 24, VCPU_FPR24, a0 + st_d 25, VCPU_FPR25, a0 + st_d 26, VCPU_FPR26, a0 + st_d 27, VCPU_FPR27, a0 + st_d 28, VCPU_FPR28, a0 + st_d 29, VCPU_FPR29, a0 + st_d 30, VCPU_FPR30, a0 + st_d 31, VCPU_FPR31, a0 + jr ra + nop + END(__kvm_save_msa) + +LEAF(__kvm_restore_msa) + ld_d 0, VCPU_FPR0, a0 + ld_d 1, VCPU_FPR1, a0 + ld_d 2, VCPU_FPR2, a0 + ld_d 3, VCPU_FPR3, a0 + ld_d 4, VCPU_FPR4, a0 + ld_d 5, VCPU_FPR5, a0 + ld_d 6, VCPU_FPR6, a0 + ld_d 7, VCPU_FPR7, a0 + ld_d 8, VCPU_FPR8, a0 + ld_d 9, VCPU_FPR9, a0 + ld_d 10, VCPU_FPR10, a0 + ld_d 11, VCPU_FPR11, a0 + ld_d 12, VCPU_FPR12, a0 + ld_d 13, VCPU_FPR13, a0 + ld_d 14, VCPU_FPR14, a0 + ld_d 15, VCPU_FPR15, a0 + ld_d 16, VCPU_FPR16, a0 + ld_d 17, VCPU_FPR17, a0 + ld_d 18, VCPU_FPR18, a0 + ld_d 19, VCPU_FPR19, a0 + ld_d 20, VCPU_FPR20, a0 + ld_d 21, VCPU_FPR21, a0 + ld_d 22, VCPU_FPR22, a0 + ld_d 23, VCPU_FPR23, a0 + ld_d 24, VCPU_FPR24, a0 + ld_d 25, VCPU_FPR25, a0 + ld_d 26, VCPU_FPR26, a0 + ld_d 27, VCPU_FPR27, a0 + ld_d 28, VCPU_FPR28, a0 + ld_d 29, VCPU_FPR29, a0 + ld_d 30, VCPU_FPR30, a0 + ld_d 31, VCPU_FPR31, a0 + jr ra + nop + END(__kvm_restore_msa) + + .macro kvm_restore_msa_upper wr, off, base + .set push + .set noat +#ifdef CONFIG_64BIT + ld $1, \off(\base) + insert_d \wr, 1 +#elif defined(CONFIG_CPU_LITTLE_ENDIAN) + lw $1, \off(\base) + insert_w \wr, 2 + lw $1, (\off+4)(\base) + insert_w \wr, 3 +#else /* CONFIG_CPU_BIG_ENDIAN */ + lw $1, (\off+4)(\base) + insert_w \wr, 2 + lw $1, \off(\base) + insert_w \wr, 3 +#endif + .set pop + .endm + +LEAF(__kvm_restore_msa_upper) + kvm_restore_msa_upper 0, VCPU_FPR0 +8, a0 + kvm_restore_msa_upper 1, VCPU_FPR1 +8, a0 + kvm_restore_msa_upper 2, VCPU_FPR2 +8, a0 + kvm_restore_msa_upper 3, VCPU_FPR3 +8, a0 + kvm_restore_msa_upper 4, VCPU_FPR4 +8, a0 + kvm_restore_msa_upper 5, VCPU_FPR5 +8, a0 + kvm_restore_msa_upper 6, VCPU_FPR6 +8, a0 + kvm_restore_msa_upper 7, VCPU_FPR7 +8, a0 + kvm_restore_msa_upper 8, VCPU_FPR8 +8, a0 + kvm_restore_msa_upper 9, VCPU_FPR9 +8, a0 + kvm_restore_msa_upper 10, VCPU_FPR10+8, a0 + kvm_restore_msa_upper 11, VCPU_FPR11+8, a0 + kvm_restore_msa_upper 12, VCPU_FPR12+8, a0 + kvm_restore_msa_upper 13, VCPU_FPR13+8, a0 + kvm_restore_msa_upper 14, VCPU_FPR14+8, a0 + kvm_restore_msa_upper 15, VCPU_FPR15+8, a0 + kvm_restore_msa_upper 16, VCPU_FPR16+8, a0 + kvm_restore_msa_upper 17, VCPU_FPR17+8, a0 + kvm_restore_msa_upper 18, VCPU_FPR18+8, a0 + kvm_restore_msa_upper 19, VCPU_FPR19+8, a0 + kvm_restore_msa_upper 20, VCPU_FPR20+8, a0 + kvm_restore_msa_upper 21, VCPU_FPR21+8, a0 + kvm_restore_msa_upper 22, VCPU_FPR22+8, a0 + kvm_restore_msa_upper 23, VCPU_FPR23+8, a0 + kvm_restore_msa_upper 24, VCPU_FPR24+8, a0 + kvm_restore_msa_upper 25, VCPU_FPR25+8, a0 + kvm_restore_msa_upper 26, VCPU_FPR26+8, a0 + kvm_restore_msa_upper 27, VCPU_FPR27+8, a0 + kvm_restore_msa_upper 28, VCPU_FPR28+8, a0 + kvm_restore_msa_upper 29, VCPU_FPR29+8, a0 + kvm_restore_msa_upper 30, VCPU_FPR30+8, a0 + kvm_restore_msa_upper 31, VCPU_FPR31+8, a0 + jr ra + nop + END(__kvm_restore_msa_upper) + +LEAF(__kvm_restore_msacsr) + lw t0, VCPU_MSA_CSR(a0) + /* + * The ctcmsa must stay at this offset in __kvm_restore_msacsr. + * See kvm_mips_csr_die_notify() which handles t0 containing a value + * which triggers an MSA FP Exception, which must be stepped over and + * ignored since the set cause bits must remain there for the guest. + */ + _ctcmsa MSA_CSR, t0 + jr ra + nop + END(__kvm_restore_msacsr) diff --git a/arch/mips/kvm/stats.c b/arch/mips/kvm/stats.c index a74d6024c5ad..888bb67070ac 100644 --- a/arch/mips/kvm/stats.c +++ b/arch/mips/kvm/stats.c @@ -25,6 +25,10 @@ char *kvm_mips_exit_types_str[MAX_KVM_MIPS_EXIT_TYPES] = { "System Call", "Reserved Inst", "Break Inst", + "Trap Inst", + "MSA FPE", + "FPE", + "MSA Disabled", "D-Cache Flushes", }; diff --git a/arch/mips/kvm/tlb.c b/arch/mips/kvm/tlb.c index b6beb0e07b1b..aed0ac2a4972 100644 --- a/arch/mips/kvm/tlb.c +++ b/arch/mips/kvm/tlb.c @@ -733,6 +733,9 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) } } + /* restore guest state to registers */ + kvm_mips_callbacks->vcpu_set_regs(vcpu); + local_irq_restore(flags); } @@ -751,6 +754,9 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) vcpu->arch.preempt_entryhi = read_c0_entryhi(); vcpu->arch.last_sched_cpu = cpu; + /* save guest state in registers */ + kvm_mips_callbacks->vcpu_get_regs(vcpu); + if (((cpu_context(cpu, current->mm) ^ asid_cache(cpu)) & ASID_VERSION_MASK)) { kvm_debug("%s: Dropping MMU Context: %#lx\n", __func__, diff --git a/arch/mips/kvm/trap_emul.c b/arch/mips/kvm/trap_emul.c index fd7257b70e65..d836ed5b0bc7 100644 --- a/arch/mips/kvm/trap_emul.c +++ b/arch/mips/kvm/trap_emul.c @@ -39,16 +39,30 @@ static gpa_t kvm_trap_emul_gva_to_gpa_cb(gva_t gva) static int kvm_trap_emul_handle_cop_unusable(struct kvm_vcpu *vcpu) { + struct mips_coproc *cop0 = vcpu->arch.cop0; struct kvm_run *run = vcpu->run; uint32_t __user *opc = (uint32_t __user *) vcpu->arch.pc; unsigned long cause = vcpu->arch.host_cp0_cause; enum emulation_result er = EMULATE_DONE; int ret = RESUME_GUEST; - if (((cause & CAUSEF_CE) >> CAUSEB_CE) == 1) - er = kvm_mips_emulate_fpu_exc(cause, opc, run, vcpu); - else + if (((cause & CAUSEF_CE) >> CAUSEB_CE) == 1) { + /* FPU Unusable */ + if (!kvm_mips_guest_has_fpu(&vcpu->arch) || + (kvm_read_c0_guest_status(cop0) & ST0_CU1) == 0) { + /* + * Unusable/no FPU in guest: + * deliver guest COP1 Unusable Exception + */ + er = kvm_mips_emulate_fpu_exc(cause, opc, run, vcpu); + } else { + /* Restore FPU state */ + kvm_own_fpu(vcpu); + er = EMULATE_DONE; + } + } else { er = kvm_mips_emulate_inst(cause, opc, run, vcpu); + } switch (er) { case EMULATE_DONE: @@ -330,6 +344,107 @@ static int kvm_trap_emul_handle_break(struct kvm_vcpu *vcpu) return ret; } +static int kvm_trap_emul_handle_trap(struct kvm_vcpu *vcpu) +{ + struct kvm_run *run = vcpu->run; + uint32_t __user *opc = (uint32_t __user *)vcpu->arch.pc; + unsigned long cause = vcpu->arch.host_cp0_cause; + enum emulation_result er = EMULATE_DONE; + int ret = RESUME_GUEST; + + er = kvm_mips_emulate_trap_exc(cause, opc, run, vcpu); + if (er == EMULATE_DONE) { + ret = RESUME_GUEST; + } else { + run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + ret = RESUME_HOST; + } + return ret; +} + +static int kvm_trap_emul_handle_msa_fpe(struct kvm_vcpu *vcpu) +{ + struct kvm_run *run = vcpu->run; + uint32_t __user *opc = (uint32_t __user *)vcpu->arch.pc; + unsigned long cause = vcpu->arch.host_cp0_cause; + enum emulation_result er = EMULATE_DONE; + int ret = RESUME_GUEST; + + er = kvm_mips_emulate_msafpe_exc(cause, opc, run, vcpu); + if (er == EMULATE_DONE) { + ret = RESUME_GUEST; + } else { + run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + ret = RESUME_HOST; + } + return ret; +} + +static int kvm_trap_emul_handle_fpe(struct kvm_vcpu *vcpu) +{ + struct kvm_run *run = vcpu->run; + uint32_t __user *opc = (uint32_t __user *)vcpu->arch.pc; + unsigned long cause = vcpu->arch.host_cp0_cause; + enum emulation_result er = EMULATE_DONE; + int ret = RESUME_GUEST; + + er = kvm_mips_emulate_fpe_exc(cause, opc, run, vcpu); + if (er == EMULATE_DONE) { + ret = RESUME_GUEST; + } else { + run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + ret = RESUME_HOST; + } + return ret; +} + +/** + * kvm_trap_emul_handle_msa_disabled() - Guest used MSA while disabled in root. + * @vcpu: Virtual CPU context. + * + * Handle when the guest attempts to use MSA when it is disabled. + */ +static int kvm_trap_emul_handle_msa_disabled(struct kvm_vcpu *vcpu) +{ + struct mips_coproc *cop0 = vcpu->arch.cop0; + struct kvm_run *run = vcpu->run; + uint32_t __user *opc = (uint32_t __user *) vcpu->arch.pc; + unsigned long cause = vcpu->arch.host_cp0_cause; + enum emulation_result er = EMULATE_DONE; + int ret = RESUME_GUEST; + + if (!kvm_mips_guest_has_msa(&vcpu->arch) || + (kvm_read_c0_guest_status(cop0) & (ST0_CU1 | ST0_FR)) == ST0_CU1) { + /* + * No MSA in guest, or FPU enabled and not in FR=1 mode, + * guest reserved instruction exception + */ + er = kvm_mips_emulate_ri_exc(cause, opc, run, vcpu); + } else if (!(kvm_read_c0_guest_config5(cop0) & MIPS_CONF5_MSAEN)) { + /* MSA disabled by guest, guest MSA disabled exception */ + er = kvm_mips_emulate_msadis_exc(cause, opc, run, vcpu); + } else { + /* Restore MSA/FPU state */ + kvm_own_msa(vcpu); + er = EMULATE_DONE; + } + + switch (er) { + case EMULATE_DONE: + ret = RESUME_GUEST; + break; + + case EMULATE_FAIL: + run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + ret = RESUME_HOST; + break; + + default: + BUG(); + } + return ret; +} + static int kvm_trap_emul_vm_init(struct kvm *kvm) { return 0; @@ -351,8 +466,9 @@ static int kvm_trap_emul_vcpu_setup(struct kvm_vcpu *vcpu) * guest will come up as expected, for now we simulate a MIPS 24kc */ kvm_write_c0_guest_prid(cop0, 0x00019300); - kvm_write_c0_guest_config(cop0, - MIPS_CONFIG0 | (0x1 << CP0C0_AR) | + /* Have config1, Cacheable, noncoherent, write-back, write allocate */ + kvm_write_c0_guest_config(cop0, MIPS_CONF_M | (0x3 << CP0C0_K0) | + (0x1 << CP0C0_AR) | (MMU_TYPE_R4000 << CP0C0_MT)); /* Read the cache characteristics from the host Config1 Register */ @@ -368,10 +484,18 @@ static int kvm_trap_emul_vcpu_setup(struct kvm_vcpu *vcpu) (1 << CP0C1_WR) | (1 << CP0C1_CA)); kvm_write_c0_guest_config1(cop0, config1); - kvm_write_c0_guest_config2(cop0, MIPS_CONFIG2); - /* MIPS_CONFIG2 | (read_c0_config2() & 0xfff) */ - kvm_write_c0_guest_config3(cop0, MIPS_CONFIG3 | (0 << CP0C3_VInt) | - (1 << CP0C3_ULRI)); + /* Have config3, no tertiary/secondary caches implemented */ + kvm_write_c0_guest_config2(cop0, MIPS_CONF_M); + /* MIPS_CONF_M | (read_c0_config2() & 0xfff) */ + + /* Have config4, UserLocal */ + kvm_write_c0_guest_config3(cop0, MIPS_CONF_M | MIPS_CONF3_ULRI); + + /* Have config5 */ + kvm_write_c0_guest_config4(cop0, MIPS_CONF_M); + + /* No config6 */ + kvm_write_c0_guest_config5(cop0, 0); /* Set Wait IE/IXMT Ignore in Config7, IAR, AR */ kvm_write_c0_guest_config7(cop0, (MIPS_CONF7_WII) | (1 << 10)); @@ -416,6 +540,7 @@ static int kvm_trap_emul_set_one_reg(struct kvm_vcpu *vcpu, { struct mips_coproc *cop0 = vcpu->arch.cop0; int ret = 0; + unsigned int cur, change; switch (reg->id) { case KVM_REG_MIPS_CP0_COUNT: @@ -444,6 +569,44 @@ static int kvm_trap_emul_set_one_reg(struct kvm_vcpu *vcpu, kvm_write_c0_guest_cause(cop0, v); } break; + case KVM_REG_MIPS_CP0_CONFIG: + /* read-only for now */ + break; + case KVM_REG_MIPS_CP0_CONFIG1: + cur = kvm_read_c0_guest_config1(cop0); + change = (cur ^ v) & kvm_mips_config1_wrmask(vcpu); + if (change) { + v = cur ^ change; + kvm_write_c0_guest_config1(cop0, v); + } + break; + case KVM_REG_MIPS_CP0_CONFIG2: + /* read-only for now */ + break; + case KVM_REG_MIPS_CP0_CONFIG3: + cur = kvm_read_c0_guest_config3(cop0); + change = (cur ^ v) & kvm_mips_config3_wrmask(vcpu); + if (change) { + v = cur ^ change; + kvm_write_c0_guest_config3(cop0, v); + } + break; + case KVM_REG_MIPS_CP0_CONFIG4: + cur = kvm_read_c0_guest_config4(cop0); + change = (cur ^ v) & kvm_mips_config4_wrmask(vcpu); + if (change) { + v = cur ^ change; + kvm_write_c0_guest_config4(cop0, v); + } + break; + case KVM_REG_MIPS_CP0_CONFIG5: + cur = kvm_read_c0_guest_config5(cop0); + change = (cur ^ v) & kvm_mips_config5_wrmask(vcpu); + if (change) { + v = cur ^ change; + kvm_write_c0_guest_config5(cop0, v); + } + break; case KVM_REG_MIPS_COUNT_CTL: ret = kvm_mips_set_count_ctl(vcpu, v); break; @@ -459,6 +622,18 @@ static int kvm_trap_emul_set_one_reg(struct kvm_vcpu *vcpu, return ret; } +static int kvm_trap_emul_vcpu_get_regs(struct kvm_vcpu *vcpu) +{ + kvm_lose_fpu(vcpu); + + return 0; +} + +static int kvm_trap_emul_vcpu_set_regs(struct kvm_vcpu *vcpu) +{ + return 0; +} + static struct kvm_mips_callbacks kvm_trap_emul_callbacks = { /* exit handlers */ .handle_cop_unusable = kvm_trap_emul_handle_cop_unusable, @@ -470,6 +645,10 @@ static struct kvm_mips_callbacks kvm_trap_emul_callbacks = { .handle_syscall = kvm_trap_emul_handle_syscall, .handle_res_inst = kvm_trap_emul_handle_res_inst, .handle_break = kvm_trap_emul_handle_break, + .handle_trap = kvm_trap_emul_handle_trap, + .handle_msa_fpe = kvm_trap_emul_handle_msa_fpe, + .handle_fpe = kvm_trap_emul_handle_fpe, + .handle_msa_disabled = kvm_trap_emul_handle_msa_disabled, .vm_init = kvm_trap_emul_vm_init, .vcpu_init = kvm_trap_emul_vcpu_init, @@ -483,6 +662,8 @@ static struct kvm_mips_callbacks kvm_trap_emul_callbacks = { .irq_clear = kvm_mips_irq_clear_cb, .get_one_reg = kvm_trap_emul_get_one_reg, .set_one_reg = kvm_trap_emul_set_one_reg, + .vcpu_get_regs = kvm_trap_emul_vcpu_get_regs, + .vcpu_set_regs = kvm_trap_emul_vcpu_set_regs, }; int kvm_mips_emulation_init(struct kvm_mips_callbacks **install_callbacks) diff --git a/arch/mips/lasat/sysctl.c b/arch/mips/lasat/sysctl.c index 3b7f65cc4218..cf9b4633257e 100644 --- a/arch/mips/lasat/sysctl.c +++ b/arch/mips/lasat/sysctl.c @@ -75,11 +75,11 @@ static int rtctmp; int proc_dolasatrtc(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { - struct timespec ts; + struct timespec64 ts; int r; if (!write) { - read_persistent_clock(&ts); + read_persistent_clock64(&ts); rtctmp = ts.tv_sec; /* check for time < 0 and set to 0 */ if (rtctmp < 0) diff --git a/arch/nios2/include/asm/thread_info.h b/arch/nios2/include/asm/thread_info.h index 1f266575beb5..a16e55cbd8ad 100644 --- a/arch/nios2/include/asm/thread_info.h +++ b/arch/nios2/include/asm/thread_info.h @@ -47,7 +47,6 @@ struct thread_info { 0-0x7FFFFFFF for user-thead 0-0xFFFFFFFF for kernel-thread */ - struct restart_block restart_block; struct pt_regs *regs; }; @@ -64,9 +63,6 @@ struct thread_info { .cpu = 0, \ .preempt_count = INIT_PREEMPT_COUNT, \ .addr_limit = KERNEL_DS, \ - .restart_block = { \ - .fn = do_no_restart_syscall, \ - }, \ } #define init_thread_info (init_thread_union.thread_info) diff --git a/arch/nios2/include/uapi/asm/ptrace.h b/arch/nios2/include/uapi/asm/ptrace.h index 71a330597adf..eff00e67c0a2 100644 --- a/arch/nios2/include/uapi/asm/ptrace.h +++ b/arch/nios2/include/uapi/asm/ptrace.h @@ -60,12 +60,17 @@ #define PTR_IPENDING 37 #define PTR_CPUID 38 #define PTR_CTL6 39 -#define PTR_CTL7 40 +#define PTR_EXCEPTION 40 #define PTR_PTEADDR 41 #define PTR_TLBACC 42 #define PTR_TLBMISC 43 +#define PTR_ECCINJ 44 +#define PTR_BADADDR 45 +#define PTR_CONFIG 46 +#define PTR_MPUBASE 47 +#define PTR_MPUACC 48 -#define NUM_PTRACE_REG (PTR_TLBMISC + 1) +#define NUM_PTRACE_REG (PTR_MPUACC + 1) /* User structures for general purpose registers. */ struct user_pt_regs { diff --git a/arch/nios2/kernel/entry.S b/arch/nios2/kernel/entry.S index 7729bd3f2e79..27b006c52e12 100644 --- a/arch/nios2/kernel/entry.S +++ b/arch/nios2/kernel/entry.S @@ -161,7 +161,7 @@ ENTRY(inthandler) *********************************************************************** */ ENTRY(handle_trap) - ldw r24, -4(ea) /* instruction that caused the exception */ + ldwio r24, -4(ea) /* instruction that caused the exception */ srli r24, r24, 4 andi r24, r24, 0x7c movia r9,trap_table diff --git a/arch/nios2/kernel/signal.c b/arch/nios2/kernel/signal.c index dda41e4fe707..20662b0f6c9e 100644 --- a/arch/nios2/kernel/signal.c +++ b/arch/nios2/kernel/signal.c @@ -43,7 +43,7 @@ static inline int rt_restore_ucontext(struct pt_regs *regs, int err; /* Always make any pending restarted system calls return -EINTR */ - current_thread_info()->restart_block.fn = do_no_restart_syscall; + current->restart_block.fn = do_no_restart_syscall; err = __get_user(temp, &uc->uc_mcontext.version); if (temp != MCONTEXT_VERSION) diff --git a/arch/nios2/mm/cacheflush.c b/arch/nios2/mm/cacheflush.c index 2ae482b42669..796642932e2e 100644 --- a/arch/nios2/mm/cacheflush.c +++ b/arch/nios2/mm/cacheflush.c @@ -23,9 +23,6 @@ static void __flush_dcache(unsigned long start, unsigned long end) end += (cpuinfo.dcache_line_size - 1); end &= ~(cpuinfo.dcache_line_size - 1); - if (end > start + cpuinfo.dcache_size) - end = start + cpuinfo.dcache_size; - for (addr = start; addr < end; addr += cpuinfo.dcache_line_size) { __asm__ __volatile__ (" flushda 0(%0)\n" : /* Outputs */ diff --git a/arch/powerpc/kvm/mpic.c b/arch/powerpc/kvm/mpic.c index 39b3a8f816f2..6249cdc834d1 100644 --- a/arch/powerpc/kvm/mpic.c +++ b/arch/powerpc/kvm/mpic.c @@ -34,7 +34,7 @@ #include <asm/kvm_para.h> #include <asm/kvm_host.h> #include <asm/kvm_ppc.h> -#include "iodev.h" +#include <kvm/iodev.h> #define MAX_CPU 32 #define MAX_SRC 256 @@ -289,11 +289,6 @@ static inline void IRQ_resetbit(struct irq_queue *q, int n_IRQ) clear_bit(n_IRQ, q->queue); } -static inline int IRQ_testbit(struct irq_queue *q, int n_IRQ) -{ - return test_bit(n_IRQ, q->queue); -} - static void IRQ_check(struct openpic *opp, struct irq_queue *q) { int irq = -1; @@ -1374,8 +1369,9 @@ static int kvm_mpic_write_internal(struct openpic *opp, gpa_t addr, u32 val) return -ENXIO; } -static int kvm_mpic_read(struct kvm_io_device *this, gpa_t addr, - int len, void *ptr) +static int kvm_mpic_read(struct kvm_vcpu *vcpu, + struct kvm_io_device *this, + gpa_t addr, int len, void *ptr) { struct openpic *opp = container_of(this, struct openpic, mmio); int ret; @@ -1415,8 +1411,9 @@ static int kvm_mpic_read(struct kvm_io_device *this, gpa_t addr, return ret; } -static int kvm_mpic_write(struct kvm_io_device *this, gpa_t addr, - int len, const void *ptr) +static int kvm_mpic_write(struct kvm_vcpu *vcpu, + struct kvm_io_device *this, + gpa_t addr, int len, const void *ptr) { struct openpic *opp = container_of(this, struct openpic, mmio); int ret; diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 27c0face86f4..24bfe401373e 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -807,7 +807,7 @@ int kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu, idx = srcu_read_lock(&vcpu->kvm->srcu); - ret = kvm_io_bus_read(vcpu->kvm, KVM_MMIO_BUS, run->mmio.phys_addr, + ret = kvm_io_bus_read(vcpu, KVM_MMIO_BUS, run->mmio.phys_addr, bytes, &run->mmio.data); srcu_read_unlock(&vcpu->kvm->srcu, idx); @@ -880,7 +880,7 @@ int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu, idx = srcu_read_lock(&vcpu->kvm->srcu); - ret = kvm_io_bus_write(vcpu->kvm, KVM_MMIO_BUS, run->mmio.phys_addr, + ret = kvm_io_bus_write(vcpu, KVM_MMIO_BUS, run->mmio.phys_addr, bytes, &run->mmio.data); srcu_read_unlock(&vcpu->kvm->srcu, idx); diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S index 0509bca5e830..fcbe899fe299 100644 --- a/arch/powerpc/platforms/powernv/opal-wrappers.S +++ b/arch/powerpc/platforms/powernv/opal-wrappers.S @@ -9,11 +9,11 @@ * 2 of the License, or (at your option) any later version. */ +#include <linux/jump_label.h> #include <asm/ppc_asm.h> #include <asm/hvcall.h> #include <asm/asm-offsets.h> #include <asm/opal.h> -#include <asm/jump_label.h> .section ".text" diff --git a/arch/powerpc/platforms/pseries/hvCall.S b/arch/powerpc/platforms/pseries/hvCall.S index ccd53f91e8aa..74b5b8e239c8 100644 --- a/arch/powerpc/platforms/pseries/hvCall.S +++ b/arch/powerpc/platforms/pseries/hvCall.S @@ -7,12 +7,12 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ +#include <linux/jump_label.h> #include <asm/hvcall.h> #include <asm/processor.h> #include <asm/ppc_asm.h> #include <asm/asm-offsets.h> #include <asm/ptrace.h> -#include <asm/jump_label.h> .section ".text" diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index b5682fd6c984..b7a67e3d2201 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -26,7 +26,7 @@ #include <linux/dma-mapping.h> #include <linux/console.h> #include <linux/export.h> -#include <linux/static_key.h> +#include <linux/jump_label.h> #include <asm/processor.h> #include <asm/mmu.h> #include <asm/page.h> diff --git a/arch/s390/include/asm/jump_label.h b/arch/s390/include/asm/jump_label.h index 58642fd29c87..2b77e235b5fb 100644 --- a/arch/s390/include/asm/jump_label.h +++ b/arch/s390/include/asm/jump_label.h @@ -1,6 +1,8 @@ #ifndef _ASM_S390_JUMP_LABEL_H #define _ASM_S390_JUMP_LABEL_H +#ifndef __ASSEMBLY__ + #include <linux/types.h> #define JUMP_LABEL_NOP_SIZE 6 @@ -39,4 +41,5 @@ struct jump_entry { jump_label_t key; }; +#endif /* __ASSEMBLY__ */ #endif diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index f407bbf5ee94..d01fc588b5c3 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -172,7 +172,9 @@ struct kvm_s390_sie_block { __u32 fac; /* 0x01a0 */ __u8 reserved1a4[20]; /* 0x01a4 */ __u64 cbrlo; /* 0x01b8 */ - __u8 reserved1c0[30]; /* 0x01c0 */ + __u8 reserved1c0[8]; /* 0x01c0 */ + __u32 ecd; /* 0x01c8 */ + __u8 reserved1cc[18]; /* 0x01cc */ __u64 pp; /* 0x01de */ __u8 reserved1e6[2]; /* 0x01e6 */ __u64 itdba; /* 0x01e8 */ @@ -183,11 +185,17 @@ struct kvm_s390_itdb { __u8 data[256]; } __packed; +struct kvm_s390_vregs { + __vector128 vrs[32]; + __u8 reserved200[512]; /* for future vector expansion */ +} __packed; + struct sie_page { struct kvm_s390_sie_block sie_block; __u8 reserved200[1024]; /* 0x0200 */ struct kvm_s390_itdb itdb; /* 0x0600 */ - __u8 reserved700[2304]; /* 0x0700 */ + __u8 reserved700[1280]; /* 0x0700 */ + struct kvm_s390_vregs vregs; /* 0x0c00 */ } __packed; struct kvm_vcpu_stat { @@ -238,6 +246,7 @@ struct kvm_vcpu_stat { u32 instruction_sigp_stop; u32 instruction_sigp_stop_store_status; u32 instruction_sigp_store_status; + u32 instruction_sigp_store_adtl_status; u32 instruction_sigp_arch; u32 instruction_sigp_prefix; u32 instruction_sigp_restart; @@ -270,6 +279,7 @@ struct kvm_vcpu_stat { #define PGM_SPECIAL_OPERATION 0x13 #define PGM_OPERAND 0x15 #define PGM_TRACE_TABEL 0x16 +#define PGM_VECTOR_PROCESSING 0x1b #define PGM_SPACE_SWITCH 0x1c #define PGM_HFP_SQUARE_ROOT 0x1d #define PGM_PC_TRANSLATION_SPEC 0x1f @@ -334,6 +344,11 @@ enum irq_types { IRQ_PEND_COUNT }; +/* We have 2M for virtio device descriptor pages. Smallest amount of + * memory per page is 24 bytes (1 queue), so (2048*1024) / 24 = 87381 + */ +#define KVM_S390_MAX_VIRTIO_IRQS 87381 + /* * Repressible (non-floating) machine check interrupts * subclass bits in MCIC @@ -411,13 +426,32 @@ struct kvm_s390_local_interrupt { unsigned long pending_irqs; }; +#define FIRQ_LIST_IO_ISC_0 0 +#define FIRQ_LIST_IO_ISC_1 1 +#define FIRQ_LIST_IO_ISC_2 2 +#define FIRQ_LIST_IO_ISC_3 3 +#define FIRQ_LIST_IO_ISC_4 4 +#define FIRQ_LIST_IO_ISC_5 5 +#define FIRQ_LIST_IO_ISC_6 6 +#define FIRQ_LIST_IO_ISC_7 7 +#define FIRQ_LIST_PFAULT 8 +#define FIRQ_LIST_VIRTIO 9 +#define FIRQ_LIST_COUNT 10 +#define FIRQ_CNTR_IO 0 +#define FIRQ_CNTR_SERVICE 1 +#define FIRQ_CNTR_VIRTIO 2 +#define FIRQ_CNTR_PFAULT 3 +#define FIRQ_MAX_COUNT 4 + struct kvm_s390_float_interrupt { + unsigned long pending_irqs; spinlock_t lock; - struct list_head list; - atomic_t active; + struct list_head lists[FIRQ_LIST_COUNT]; + int counters[FIRQ_MAX_COUNT]; + struct kvm_s390_mchk_info mchk; + struct kvm_s390_ext_info srv_signal; int next_rr_cpu; unsigned long idle_mask[BITS_TO_LONGS(KVM_MAX_VCPUS)]; - unsigned int irq_count; }; struct kvm_hw_wp_info_arch { @@ -465,6 +499,7 @@ struct kvm_vcpu_arch { s390_fp_regs host_fpregs; unsigned int host_acrs[NUM_ACRS]; s390_fp_regs guest_fpregs; + struct kvm_s390_vregs *host_vregs; struct kvm_s390_local_interrupt local_int; struct hrtimer ckc_timer; struct kvm_s390_pgm_info pgm; @@ -553,6 +588,7 @@ struct kvm_arch{ int use_cmma; int user_cpu_state_ctrl; int user_sigp; + int user_stsi; struct s390_io_adapter *adapters[MAX_S390_IO_ADAPTERS]; wait_queue_head_t ipte_wq; int ipte_lock_count; diff --git a/arch/s390/include/uapi/asm/kvm.h b/arch/s390/include/uapi/asm/kvm.h index 9c77e60b9a26..ef1a5fcc6c66 100644 --- a/arch/s390/include/uapi/asm/kvm.h +++ b/arch/s390/include/uapi/asm/kvm.h @@ -150,6 +150,7 @@ struct kvm_guest_debug_arch { #define KVM_SYNC_CRS (1UL << 3) #define KVM_SYNC_ARCH0 (1UL << 4) #define KVM_SYNC_PFAULT (1UL << 5) +#define KVM_SYNC_VRS (1UL << 6) /* definition of registers in kvm_run */ struct kvm_sync_regs { __u64 prefix; /* prefix register */ @@ -164,6 +165,9 @@ struct kvm_sync_regs { __u64 pft; /* pfault token [PFAULT] */ __u64 pfs; /* pfault select [PFAULT] */ __u64 pfc; /* pfault compare [PFAULT] */ + __u64 vrs[32][2]; /* vector registers */ + __u8 reserved[512]; /* for future vector expansion */ + __u32 fpc; /* only valid with vector registers */ }; #define KVM_REG_S390_TODPR (KVM_REG_S390 | KVM_REG_SIZE_U32 | 0x1) diff --git a/arch/s390/include/uapi/asm/sie.h b/arch/s390/include/uapi/asm/sie.h index d4096fdfc6ab..ee69c0854c88 100644 --- a/arch/s390/include/uapi/asm/sie.h +++ b/arch/s390/include/uapi/asm/sie.h @@ -230,7 +230,7 @@ * and returns a key, which can be used to find a mnemonic name * of the instruction in the icpt_insn_codes table. */ -#define icpt_insn_decoder(insn) \ +#define icpt_insn_decoder(insn) ( \ INSN_DECODE_IPA0(0x01, insn, 48, 0xff) \ INSN_DECODE_IPA0(0xaa, insn, 48, 0x0f) \ INSN_DECODE_IPA0(0xb2, insn, 48, 0xff) \ @@ -239,6 +239,6 @@ INSN_DECODE_IPA0(0xe5, insn, 48, 0xff) \ INSN_DECODE_IPA0(0xeb, insn, 16, 0xff) \ INSN_DECODE_IPA0(0xc8, insn, 48, 0x0f) \ - INSN_DECODE(insn) + INSN_DECODE(insn)) #endif /* _UAPI_ASM_S390_SIE_H */ diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index e07e91605353..8dc4db10d160 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -171,6 +171,7 @@ int main(void) #else /* CONFIG_32BIT */ DEFINE(__LC_DATA_EXC_CODE, offsetof(struct _lowcore, data_exc_code)); DEFINE(__LC_MCCK_FAIL_STOR_ADDR, offsetof(struct _lowcore, failing_storage_address)); + DEFINE(__LC_VX_SAVE_AREA_ADDR, offsetof(struct _lowcore, vector_save_area_addr)); DEFINE(__LC_EXT_PARAMS2, offsetof(struct _lowcore, ext_params2)); DEFINE(SAVE_AREA_BASE, offsetof(struct _lowcore, floating_pt_save_area)); DEFINE(__LC_PASTE, offsetof(struct _lowcore, paste)); diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index 20660dddb2d6..170ddd2018b3 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -215,20 +215,20 @@ void update_vsyscall(struct timekeeper *tk) { u64 nsecps; - if (tk->tkr.clock != &clocksource_tod) + if (tk->tkr_mono.clock != &clocksource_tod) return; /* Make userspace gettimeofday spin until we're done. */ ++vdso_data->tb_update_count; smp_wmb(); - vdso_data->xtime_tod_stamp = tk->tkr.cycle_last; + vdso_data->xtime_tod_stamp = tk->tkr_mono.cycle_last; vdso_data->xtime_clock_sec = tk->xtime_sec; - vdso_data->xtime_clock_nsec = tk->tkr.xtime_nsec; + vdso_data->xtime_clock_nsec = tk->tkr_mono.xtime_nsec; vdso_data->wtom_clock_sec = tk->xtime_sec + tk->wall_to_monotonic.tv_sec; - vdso_data->wtom_clock_nsec = tk->tkr.xtime_nsec + - + ((u64) tk->wall_to_monotonic.tv_nsec << tk->tkr.shift); - nsecps = (u64) NSEC_PER_SEC << tk->tkr.shift; + vdso_data->wtom_clock_nsec = tk->tkr_mono.xtime_nsec + + + ((u64) tk->wall_to_monotonic.tv_nsec << tk->tkr_mono.shift); + nsecps = (u64) NSEC_PER_SEC << tk->tkr_mono.shift; while (vdso_data->wtom_clock_nsec >= nsecps) { vdso_data->wtom_clock_nsec -= nsecps; vdso_data->wtom_clock_sec++; @@ -236,7 +236,7 @@ void update_vsyscall(struct timekeeper *tk) vdso_data->xtime_coarse_sec = tk->xtime_sec; vdso_data->xtime_coarse_nsec = - (long)(tk->tkr.xtime_nsec >> tk->tkr.shift); + (long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift); vdso_data->wtom_coarse_sec = vdso_data->xtime_coarse_sec + tk->wall_to_monotonic.tv_sec; vdso_data->wtom_coarse_nsec = @@ -246,8 +246,8 @@ void update_vsyscall(struct timekeeper *tk) vdso_data->wtom_coarse_sec++; } - vdso_data->tk_mult = tk->tkr.mult; - vdso_data->tk_shift = tk->tkr.shift; + vdso_data->tk_mult = tk->tkr_mono.mult; + vdso_data->tk_shift = tk->tkr_mono.shift; smp_wmb(); ++vdso_data->tb_update_count; } @@ -283,7 +283,7 @@ void __init time_init(void) if (register_external_irq(EXT_IRQ_TIMING_ALERT, timing_alert_interrupt)) panic("Couldn't request external interrupt 0x1406"); - if (clocksource_register(&clocksource_tod) != 0) + if (__clocksource_register(&clocksource_tod) != 0) panic("Could not register TOD clock source"); /* Enable TOD clock interrupts on the boot cpu. */ diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c index 9254afff250c..fc7ec95848c3 100644 --- a/arch/s390/kvm/diag.c +++ b/arch/s390/kvm/diag.c @@ -77,7 +77,7 @@ static int __diag_page_ref_service(struct kvm_vcpu *vcpu) if (vcpu->run->s.regs.gprs[rx] & 7) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - rc = read_guest(vcpu, vcpu->run->s.regs.gprs[rx], &parm, sizeof(parm)); + rc = read_guest(vcpu, vcpu->run->s.regs.gprs[rx], rx, &parm, sizeof(parm)); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); if (parm.parm_version != 2 || parm.parm_len < 5 || parm.code != 0x258) @@ -213,7 +213,7 @@ static int __diag_virtio_hypercall(struct kvm_vcpu *vcpu) * - gpr 3 contains the virtqueue index (passed as datamatch) * - gpr 4 contains the index on the bus (optionally) */ - ret = kvm_io_bus_write_cookie(vcpu->kvm, KVM_VIRTIO_CCW_NOTIFY_BUS, + ret = kvm_io_bus_write_cookie(vcpu, KVM_VIRTIO_CCW_NOTIFY_BUS, vcpu->run->s.regs.gprs[2] & 0xffffffff, 8, &vcpu->run->s.regs.gprs[3], vcpu->run->s.regs.gprs[4]); @@ -230,7 +230,7 @@ static int __diag_virtio_hypercall(struct kvm_vcpu *vcpu) int kvm_s390_handle_diag(struct kvm_vcpu *vcpu) { - int code = kvm_s390_get_base_disp_rs(vcpu) & 0xffff; + int code = kvm_s390_get_base_disp_rs(vcpu, NULL) & 0xffff; if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c index 267523cac6de..a7559f7207df 100644 --- a/arch/s390/kvm/gaccess.c +++ b/arch/s390/kvm/gaccess.c @@ -10,6 +10,7 @@ #include <asm/pgtable.h> #include "kvm-s390.h" #include "gaccess.h" +#include <asm/switch_to.h> union asce { unsigned long val; @@ -207,6 +208,54 @@ union raddress { unsigned long pfra : 52; /* Page-Frame Real Address */ }; +union alet { + u32 val; + struct { + u32 reserved : 7; + u32 p : 1; + u32 alesn : 8; + u32 alen : 16; + }; +}; + +union ald { + u32 val; + struct { + u32 : 1; + u32 alo : 24; + u32 all : 7; + }; +}; + +struct ale { + unsigned long i : 1; /* ALEN-Invalid Bit */ + unsigned long : 5; + unsigned long fo : 1; /* Fetch-Only Bit */ + unsigned long p : 1; /* Private Bit */ + unsigned long alesn : 8; /* Access-List-Entry Sequence Number */ + unsigned long aleax : 16; /* Access-List-Entry Authorization Index */ + unsigned long : 32; + unsigned long : 1; + unsigned long asteo : 25; /* ASN-Second-Table-Entry Origin */ + unsigned long : 6; + unsigned long astesn : 32; /* ASTE Sequence Number */ +} __packed; + +struct aste { + unsigned long i : 1; /* ASX-Invalid Bit */ + unsigned long ato : 29; /* Authority-Table Origin */ + unsigned long : 1; + unsigned long b : 1; /* Base-Space Bit */ + unsigned long ax : 16; /* Authorization Index */ + unsigned long atl : 12; /* Authority-Table Length */ + unsigned long : 2; + unsigned long ca : 1; /* Controlled-ASN Bit */ + unsigned long ra : 1; /* Reusable-ASN Bit */ + unsigned long asce : 64; /* Address-Space-Control Element */ + unsigned long ald : 32; + unsigned long astesn : 32; + /* .. more fields there */ +} __packed; int ipte_lock_held(struct kvm_vcpu *vcpu) { @@ -307,15 +356,157 @@ void ipte_unlock(struct kvm_vcpu *vcpu) ipte_unlock_simple(vcpu); } -static unsigned long get_vcpu_asce(struct kvm_vcpu *vcpu) +static int ar_translation(struct kvm_vcpu *vcpu, union asce *asce, ar_t ar, + int write) +{ + union alet alet; + struct ale ale; + struct aste aste; + unsigned long ald_addr, authority_table_addr; + union ald ald; + int eax, rc; + u8 authority_table; + + if (ar >= NUM_ACRS) + return -EINVAL; + + save_access_regs(vcpu->run->s.regs.acrs); + alet.val = vcpu->run->s.regs.acrs[ar]; + + if (ar == 0 || alet.val == 0) { + asce->val = vcpu->arch.sie_block->gcr[1]; + return 0; + } else if (alet.val == 1) { + asce->val = vcpu->arch.sie_block->gcr[7]; + return 0; + } + + if (alet.reserved) + return PGM_ALET_SPECIFICATION; + + if (alet.p) + ald_addr = vcpu->arch.sie_block->gcr[5]; + else + ald_addr = vcpu->arch.sie_block->gcr[2]; + ald_addr &= 0x7fffffc0; + + rc = read_guest_real(vcpu, ald_addr + 16, &ald.val, sizeof(union ald)); + if (rc) + return rc; + + if (alet.alen / 8 > ald.all) + return PGM_ALEN_TRANSLATION; + + if (0x7fffffff - ald.alo * 128 < alet.alen * 16) + return PGM_ADDRESSING; + + rc = read_guest_real(vcpu, ald.alo * 128 + alet.alen * 16, &ale, + sizeof(struct ale)); + if (rc) + return rc; + + if (ale.i == 1) + return PGM_ALEN_TRANSLATION; + if (ale.alesn != alet.alesn) + return PGM_ALE_SEQUENCE; + + rc = read_guest_real(vcpu, ale.asteo * 64, &aste, sizeof(struct aste)); + if (rc) + return rc; + + if (aste.i) + return PGM_ASTE_VALIDITY; + if (aste.astesn != ale.astesn) + return PGM_ASTE_SEQUENCE; + + if (ale.p == 1) { + eax = (vcpu->arch.sie_block->gcr[8] >> 16) & 0xffff; + if (ale.aleax != eax) { + if (eax / 16 > aste.atl) + return PGM_EXTENDED_AUTHORITY; + + authority_table_addr = aste.ato * 4 + eax / 4; + + rc = read_guest_real(vcpu, authority_table_addr, + &authority_table, + sizeof(u8)); + if (rc) + return rc; + + if ((authority_table & (0x40 >> ((eax & 3) * 2))) == 0) + return PGM_EXTENDED_AUTHORITY; + } + } + + if (ale.fo == 1 && write) + return PGM_PROTECTION; + + asce->val = aste.asce; + return 0; +} + +struct trans_exc_code_bits { + unsigned long addr : 52; /* Translation-exception Address */ + unsigned long fsi : 2; /* Access Exception Fetch/Store Indication */ + unsigned long : 6; + unsigned long b60 : 1; + unsigned long b61 : 1; + unsigned long as : 2; /* ASCE Identifier */ +}; + +enum { + FSI_UNKNOWN = 0, /* Unknown wether fetch or store */ + FSI_STORE = 1, /* Exception was due to store operation */ + FSI_FETCH = 2 /* Exception was due to fetch operation */ +}; + +static int get_vcpu_asce(struct kvm_vcpu *vcpu, union asce *asce, + ar_t ar, int write) { + int rc; + psw_t *psw = &vcpu->arch.sie_block->gpsw; + struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm; + struct trans_exc_code_bits *tec_bits; + + memset(pgm, 0, sizeof(*pgm)); + tec_bits = (struct trans_exc_code_bits *)&pgm->trans_exc_code; + tec_bits->fsi = write ? FSI_STORE : FSI_FETCH; + tec_bits->as = psw_bits(*psw).as; + + if (!psw_bits(*psw).t) { + asce->val = 0; + asce->r = 1; + return 0; + } + switch (psw_bits(vcpu->arch.sie_block->gpsw).as) { case PSW_AS_PRIMARY: - return vcpu->arch.sie_block->gcr[1]; + asce->val = vcpu->arch.sie_block->gcr[1]; + return 0; case PSW_AS_SECONDARY: - return vcpu->arch.sie_block->gcr[7]; + asce->val = vcpu->arch.sie_block->gcr[7]; + return 0; case PSW_AS_HOME: - return vcpu->arch.sie_block->gcr[13]; + asce->val = vcpu->arch.sie_block->gcr[13]; + return 0; + case PSW_AS_ACCREG: + rc = ar_translation(vcpu, asce, ar, write); + switch (rc) { + case PGM_ALEN_TRANSLATION: + case PGM_ALE_SEQUENCE: + case PGM_ASTE_VALIDITY: + case PGM_ASTE_SEQUENCE: + case PGM_EXTENDED_AUTHORITY: + vcpu->arch.pgm.exc_access_id = ar; + break; + case PGM_PROTECTION: + tec_bits->b60 = 1; + tec_bits->b61 = 1; + break; + } + if (rc > 0) + pgm->code = rc; + return rc; } return 0; } @@ -330,10 +521,11 @@ static int deref_table(struct kvm *kvm, unsigned long gpa, unsigned long *val) * @vcpu: virtual cpu * @gva: guest virtual address * @gpa: points to where guest physical (absolute) address should be stored + * @asce: effective asce * @write: indicates if access is a write access * * Translate a guest virtual address into a guest absolute address by means - * of dynamic address translation as specified by the architecuture. + * of dynamic address translation as specified by the architecture. * If the resulting absolute address is not available in the configuration * an addressing exception is indicated and @gpa will not be changed. * @@ -345,7 +537,8 @@ static int deref_table(struct kvm *kvm, unsigned long gpa, unsigned long *val) * by the architecture */ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva, - unsigned long *gpa, int write) + unsigned long *gpa, const union asce asce, + int write) { union vaddress vaddr = {.addr = gva}; union raddress raddr = {.addr = gva}; @@ -354,12 +547,10 @@ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva, union ctlreg0 ctlreg0; unsigned long ptr; int edat1, edat2; - union asce asce; ctlreg0.val = vcpu->arch.sie_block->gcr[0]; edat1 = ctlreg0.edat && test_kvm_facility(vcpu->kvm, 8); edat2 = edat1 && test_kvm_facility(vcpu->kvm, 78); - asce.val = get_vcpu_asce(vcpu); if (asce.r) goto real_address; ptr = asce.origin * 4096; @@ -506,48 +697,30 @@ static inline int is_low_address(unsigned long ga) return (ga & ~0x11fful) == 0; } -static int low_address_protection_enabled(struct kvm_vcpu *vcpu) +static int low_address_protection_enabled(struct kvm_vcpu *vcpu, + const union asce asce) { union ctlreg0 ctlreg0 = {.val = vcpu->arch.sie_block->gcr[0]}; psw_t *psw = &vcpu->arch.sie_block->gpsw; - union asce asce; if (!ctlreg0.lap) return 0; - asce.val = get_vcpu_asce(vcpu); if (psw_bits(*psw).t && asce.p) return 0; return 1; } -struct trans_exc_code_bits { - unsigned long addr : 52; /* Translation-exception Address */ - unsigned long fsi : 2; /* Access Exception Fetch/Store Indication */ - unsigned long : 7; - unsigned long b61 : 1; - unsigned long as : 2; /* ASCE Identifier */ -}; - -enum { - FSI_UNKNOWN = 0, /* Unknown wether fetch or store */ - FSI_STORE = 1, /* Exception was due to store operation */ - FSI_FETCH = 2 /* Exception was due to fetch operation */ -}; - static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga, unsigned long *pages, unsigned long nr_pages, - int write) + const union asce asce, int write) { struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm; psw_t *psw = &vcpu->arch.sie_block->gpsw; struct trans_exc_code_bits *tec_bits; int lap_enabled, rc; - memset(pgm, 0, sizeof(*pgm)); tec_bits = (struct trans_exc_code_bits *)&pgm->trans_exc_code; - tec_bits->fsi = write ? FSI_STORE : FSI_FETCH; - tec_bits->as = psw_bits(*psw).as; - lap_enabled = low_address_protection_enabled(vcpu); + lap_enabled = low_address_protection_enabled(vcpu, asce); while (nr_pages) { ga = kvm_s390_logical_to_effective(vcpu, ga); tec_bits->addr = ga >> PAGE_SHIFT; @@ -557,7 +730,7 @@ static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga, } ga &= PAGE_MASK; if (psw_bits(*psw).t) { - rc = guest_translate(vcpu, ga, pages, write); + rc = guest_translate(vcpu, ga, pages, asce, write); if (rc < 0) return rc; if (rc == PGM_PROTECTION) @@ -578,7 +751,7 @@ static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga, return 0; } -int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, void *data, +int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data, unsigned long len, int write) { psw_t *psw = &vcpu->arch.sie_block->gpsw; @@ -591,20 +764,19 @@ int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, void *data, if (!len) return 0; - /* Access register mode is not supported yet. */ - if (psw_bits(*psw).t && psw_bits(*psw).as == PSW_AS_ACCREG) - return -EOPNOTSUPP; + rc = get_vcpu_asce(vcpu, &asce, ar, write); + if (rc) + return rc; nr_pages = (((ga & ~PAGE_MASK) + len - 1) >> PAGE_SHIFT) + 1; pages = pages_array; if (nr_pages > ARRAY_SIZE(pages_array)) pages = vmalloc(nr_pages * sizeof(unsigned long)); if (!pages) return -ENOMEM; - asce.val = get_vcpu_asce(vcpu); need_ipte_lock = psw_bits(*psw).t && !asce.r; if (need_ipte_lock) ipte_lock(vcpu); - rc = guest_page_range(vcpu, ga, pages, nr_pages, write); + rc = guest_page_range(vcpu, ga, pages, nr_pages, asce, write); for (idx = 0; idx < nr_pages && !rc; idx++) { gpa = *(pages + idx) + (ga & ~PAGE_MASK); _len = min(PAGE_SIZE - (gpa & ~PAGE_MASK), len); @@ -652,7 +824,7 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, * Note: The IPTE lock is not taken during this function, so the caller * has to take care of this. */ -int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, +int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar, unsigned long *gpa, int write) { struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm; @@ -661,26 +833,21 @@ int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, union asce asce; int rc; - /* Access register mode is not supported yet. */ - if (psw_bits(*psw).t && psw_bits(*psw).as == PSW_AS_ACCREG) - return -EOPNOTSUPP; - gva = kvm_s390_logical_to_effective(vcpu, gva); - memset(pgm, 0, sizeof(*pgm)); tec = (struct trans_exc_code_bits *)&pgm->trans_exc_code; - tec->as = psw_bits(*psw).as; - tec->fsi = write ? FSI_STORE : FSI_FETCH; + rc = get_vcpu_asce(vcpu, &asce, ar, write); tec->addr = gva >> PAGE_SHIFT; - if (is_low_address(gva) && low_address_protection_enabled(vcpu)) { + if (rc) + return rc; + if (is_low_address(gva) && low_address_protection_enabled(vcpu, asce)) { if (write) { rc = pgm->code = PGM_PROTECTION; return rc; } } - asce.val = get_vcpu_asce(vcpu); if (psw_bits(*psw).t && !asce.r) { /* Use DAT? */ - rc = guest_translate(vcpu, gva, gpa, write); + rc = guest_translate(vcpu, gva, gpa, asce, write); if (rc > 0) { if (rc == PGM_PROTECTION) tec->b61 = 1; @@ -697,28 +864,51 @@ int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, } /** - * kvm_s390_check_low_addr_protection - check for low-address protection - * @ga: Guest address + * check_gva_range - test a range of guest virtual addresses for accessibility + */ +int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar, + unsigned long length, int is_write) +{ + unsigned long gpa; + unsigned long currlen; + int rc = 0; + + ipte_lock(vcpu); + while (length > 0 && !rc) { + currlen = min(length, PAGE_SIZE - (gva % PAGE_SIZE)); + rc = guest_translate_address(vcpu, gva, ar, &gpa, is_write); + gva += currlen; + length -= currlen; + } + ipte_unlock(vcpu); + + return rc; +} + +/** + * kvm_s390_check_low_addr_prot_real - check for low-address protection + * @gra: Guest real address * * Checks whether an address is subject to low-address protection and set * up vcpu->arch.pgm accordingly if necessary. * * Return: 0 if no protection exception, or PGM_PROTECTION if protected. */ -int kvm_s390_check_low_addr_protection(struct kvm_vcpu *vcpu, unsigned long ga) +int kvm_s390_check_low_addr_prot_real(struct kvm_vcpu *vcpu, unsigned long gra) { struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm; psw_t *psw = &vcpu->arch.sie_block->gpsw; struct trans_exc_code_bits *tec_bits; + union ctlreg0 ctlreg0 = {.val = vcpu->arch.sie_block->gcr[0]}; - if (!is_low_address(ga) || !low_address_protection_enabled(vcpu)) + if (!ctlreg0.lap || !is_low_address(gra)) return 0; memset(pgm, 0, sizeof(*pgm)); tec_bits = (struct trans_exc_code_bits *)&pgm->trans_exc_code; tec_bits->fsi = FSI_STORE; tec_bits->as = psw_bits(*psw).as; - tec_bits->addr = ga >> PAGE_SHIFT; + tec_bits->addr = gra >> PAGE_SHIFT; pgm->code = PGM_PROTECTION; return pgm->code; diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h index 0149cf15058a..ef03726cc661 100644 --- a/arch/s390/kvm/gaccess.h +++ b/arch/s390/kvm/gaccess.h @@ -156,9 +156,11 @@ int read_guest_lc(struct kvm_vcpu *vcpu, unsigned long gra, void *data, } int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, - unsigned long *gpa, int write); + ar_t ar, unsigned long *gpa, int write); +int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar, + unsigned long length, int is_write); -int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, void *data, +int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data, unsigned long len, int write); int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, @@ -168,6 +170,7 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, * write_guest - copy data from kernel space to guest space * @vcpu: virtual cpu * @ga: guest address + * @ar: access register * @data: source address in kernel space * @len: number of bytes to copy * @@ -176,8 +179,7 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, * If DAT is off data will be copied to guest real or absolute memory. * If DAT is on data will be copied to the address space as specified by * the address space bits of the PSW: - * Primary, secondory or home space (access register mode is currently not - * implemented). + * Primary, secondary, home space or access register mode. * The addressing mode of the PSW is also inspected, so that address wrap * around is taken into account for 24-, 31- and 64-bit addressing mode, * if the to be copied data crosses page boundaries in guest address space. @@ -210,16 +212,17 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, * if data has been changed in guest space in case of an exception. */ static inline __must_check -int write_guest(struct kvm_vcpu *vcpu, unsigned long ga, void *data, +int write_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data, unsigned long len) { - return access_guest(vcpu, ga, data, len, 1); + return access_guest(vcpu, ga, ar, data, len, 1); } /** * read_guest - copy data from guest space to kernel space * @vcpu: virtual cpu * @ga: guest address + * @ar: access register * @data: destination address in kernel space * @len: number of bytes to copy * @@ -229,10 +232,10 @@ int write_guest(struct kvm_vcpu *vcpu, unsigned long ga, void *data, * data will be copied from guest space to kernel space. */ static inline __must_check -int read_guest(struct kvm_vcpu *vcpu, unsigned long ga, void *data, +int read_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data, unsigned long len) { - return access_guest(vcpu, ga, data, len, 0); + return access_guest(vcpu, ga, ar, data, len, 0); } /** @@ -330,6 +333,6 @@ int read_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, void *data, void ipte_lock(struct kvm_vcpu *vcpu); void ipte_unlock(struct kvm_vcpu *vcpu); int ipte_lock_held(struct kvm_vcpu *vcpu); -int kvm_s390_check_low_addr_protection(struct kvm_vcpu *vcpu, unsigned long ga); +int kvm_s390_check_low_addr_prot_real(struct kvm_vcpu *vcpu, unsigned long gra); #endif /* __KVM_S390_GACCESS_H */ diff --git a/arch/s390/kvm/guestdbg.c b/arch/s390/kvm/guestdbg.c index 3e8d4092ce30..e97b3455d7e6 100644 --- a/arch/s390/kvm/guestdbg.c +++ b/arch/s390/kvm/guestdbg.c @@ -191,8 +191,8 @@ static int __import_wp_info(struct kvm_vcpu *vcpu, if (!wp_info->old_data) return -ENOMEM; /* try to backup the original value */ - ret = read_guest(vcpu, wp_info->phys_addr, wp_info->old_data, - wp_info->len); + ret = read_guest_abs(vcpu, wp_info->phys_addr, wp_info->old_data, + wp_info->len); if (ret) { kfree(wp_info->old_data); wp_info->old_data = NULL; @@ -362,8 +362,8 @@ static struct kvm_hw_wp_info_arch *any_wp_changed(struct kvm_vcpu *vcpu) continue; /* refetch the wp data and compare it to the old value */ - if (!read_guest(vcpu, wp_info->phys_addr, temp, - wp_info->len)) { + if (!read_guest_abs(vcpu, wp_info->phys_addr, temp, + wp_info->len)) { if (memcmp(temp, wp_info->old_data, wp_info->len)) { kfree(temp); return wp_info; diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index bebd2157edd0..9e3779e3e496 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -165,6 +165,7 @@ static void __extract_prog_irq(struct kvm_vcpu *vcpu, pgm_info->mon_class_nr = vcpu->arch.sie_block->mcn; pgm_info->mon_code = vcpu->arch.sie_block->tecmc; break; + case PGM_VECTOR_PROCESSING: case PGM_DATA: pgm_info->data_exc_code = vcpu->arch.sie_block->dxc; break; @@ -319,7 +320,7 @@ static int handle_mvpg_pei(struct kvm_vcpu *vcpu) /* Make sure that the source is paged-in */ rc = guest_translate_address(vcpu, vcpu->run->s.regs.gprs[reg2], - &srcaddr, 0); + reg2, &srcaddr, 0); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); rc = kvm_arch_fault_in_page(vcpu, srcaddr, 0); @@ -328,7 +329,7 @@ static int handle_mvpg_pei(struct kvm_vcpu *vcpu) /* Make sure that the destination is paged-in */ rc = guest_translate_address(vcpu, vcpu->run->s.regs.gprs[reg1], - &dstaddr, 1); + reg1, &dstaddr, 1); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); rc = kvm_arch_fault_in_page(vcpu, dstaddr, 1); diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 073b5f387d1d..9de47265ef73 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -1,7 +1,7 @@ /* * handling kvm guest interrupts * - * Copyright IBM Corp. 2008,2014 + * Copyright IBM Corp. 2008, 2015 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License (version 2 only) @@ -17,9 +17,12 @@ #include <linux/signal.h> #include <linux/slab.h> #include <linux/bitmap.h> +#include <linux/vmalloc.h> #include <asm/asm-offsets.h> +#include <asm/dis.h> #include <asm/uaccess.h> #include <asm/sclp.h> +#include <asm/isc.h> #include "kvm-s390.h" #include "gaccess.h" #include "trace-s390.h" @@ -32,11 +35,6 @@ #define PFAULT_DONE 0x0680 #define VIRTIO_PARAM 0x0d00 -static int is_ioint(u64 type) -{ - return ((type & 0xfffe0000u) != 0xfffe0000u); -} - int psw_extint_disabled(struct kvm_vcpu *vcpu) { return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_EXT); @@ -72,70 +70,45 @@ static int ckc_interrupts_enabled(struct kvm_vcpu *vcpu) return 1; } -static u64 int_word_to_isc_bits(u32 int_word) +static int ckc_irq_pending(struct kvm_vcpu *vcpu) +{ + if (!(vcpu->arch.sie_block->ckc < + get_tod_clock_fast() + vcpu->arch.sie_block->epoch)) + return 0; + return ckc_interrupts_enabled(vcpu); +} + +static int cpu_timer_interrupts_enabled(struct kvm_vcpu *vcpu) +{ + return !psw_extint_disabled(vcpu) && + (vcpu->arch.sie_block->gcr[0] & 0x400ul); +} + +static int cpu_timer_irq_pending(struct kvm_vcpu *vcpu) +{ + return (vcpu->arch.sie_block->cputm >> 63) && + cpu_timer_interrupts_enabled(vcpu); +} + +static inline int is_ioirq(unsigned long irq_type) { - u8 isc = (int_word & 0x38000000) >> 27; + return ((irq_type >= IRQ_PEND_IO_ISC_0) && + (irq_type <= IRQ_PEND_IO_ISC_7)); +} +static uint64_t isc_to_isc_bits(int isc) +{ return (0x80 >> isc) << 24; } -static int __must_check __interrupt_is_deliverable(struct kvm_vcpu *vcpu, - struct kvm_s390_interrupt_info *inti) +static inline u8 int_word_to_isc(u32 int_word) { - switch (inti->type) { - case KVM_S390_INT_EXTERNAL_CALL: - if (psw_extint_disabled(vcpu)) - return 0; - if (vcpu->arch.sie_block->gcr[0] & 0x2000ul) - return 1; - return 0; - case KVM_S390_INT_EMERGENCY: - if (psw_extint_disabled(vcpu)) - return 0; - if (vcpu->arch.sie_block->gcr[0] & 0x4000ul) - return 1; - return 0; - case KVM_S390_INT_CLOCK_COMP: - return ckc_interrupts_enabled(vcpu); - case KVM_S390_INT_CPU_TIMER: - if (psw_extint_disabled(vcpu)) - return 0; - if (vcpu->arch.sie_block->gcr[0] & 0x400ul) - return 1; - return 0; - case KVM_S390_INT_SERVICE: - case KVM_S390_INT_PFAULT_INIT: - case KVM_S390_INT_PFAULT_DONE: - case KVM_S390_INT_VIRTIO: - if (psw_extint_disabled(vcpu)) - return 0; - if (vcpu->arch.sie_block->gcr[0] & 0x200ul) - return 1; - return 0; - case KVM_S390_PROGRAM_INT: - case KVM_S390_SIGP_STOP: - case KVM_S390_SIGP_SET_PREFIX: - case KVM_S390_RESTART: - return 1; - case KVM_S390_MCHK: - if (psw_mchk_disabled(vcpu)) - return 0; - if (vcpu->arch.sie_block->gcr[14] & inti->mchk.cr14) - return 1; - return 0; - case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: - if (psw_ioint_disabled(vcpu)) - return 0; - if (vcpu->arch.sie_block->gcr[6] & - int_word_to_isc_bits(inti->io.io_int_word)) - return 1; - return 0; - default: - printk(KERN_WARNING "illegal interrupt type %llx\n", - inti->type); - BUG(); - } - return 0; + return (int_word & 0x38000000) >> 27; +} + +static inline unsigned long pending_floating_irqs(struct kvm_vcpu *vcpu) +{ + return vcpu->kvm->arch.float_int.pending_irqs; } static inline unsigned long pending_local_irqs(struct kvm_vcpu *vcpu) @@ -143,12 +116,31 @@ static inline unsigned long pending_local_irqs(struct kvm_vcpu *vcpu) return vcpu->arch.local_int.pending_irqs; } -static unsigned long deliverable_local_irqs(struct kvm_vcpu *vcpu) +static unsigned long disable_iscs(struct kvm_vcpu *vcpu, + unsigned long active_mask) +{ + int i; + + for (i = 0; i <= MAX_ISC; i++) + if (!(vcpu->arch.sie_block->gcr[6] & isc_to_isc_bits(i))) + active_mask &= ~(1UL << (IRQ_PEND_IO_ISC_0 + i)); + + return active_mask; +} + +static unsigned long deliverable_irqs(struct kvm_vcpu *vcpu) { - unsigned long active_mask = pending_local_irqs(vcpu); + unsigned long active_mask; + + active_mask = pending_local_irqs(vcpu); + active_mask |= pending_floating_irqs(vcpu); if (psw_extint_disabled(vcpu)) active_mask &= ~IRQ_PEND_EXT_MASK; + if (psw_ioint_disabled(vcpu)) + active_mask &= ~IRQ_PEND_IO_MASK; + else + active_mask = disable_iscs(vcpu, active_mask); if (!(vcpu->arch.sie_block->gcr[0] & 0x2000ul)) __clear_bit(IRQ_PEND_EXT_EXTERNAL, &active_mask); if (!(vcpu->arch.sie_block->gcr[0] & 0x4000ul)) @@ -157,8 +149,13 @@ static unsigned long deliverable_local_irqs(struct kvm_vcpu *vcpu) __clear_bit(IRQ_PEND_EXT_CLOCK_COMP, &active_mask); if (!(vcpu->arch.sie_block->gcr[0] & 0x400ul)) __clear_bit(IRQ_PEND_EXT_CPU_TIMER, &active_mask); + if (!(vcpu->arch.sie_block->gcr[0] & 0x200ul)) + __clear_bit(IRQ_PEND_EXT_SERVICE, &active_mask); if (psw_mchk_disabled(vcpu)) active_mask &= ~IRQ_PEND_MCHK_MASK; + if (!(vcpu->arch.sie_block->gcr[14] & + vcpu->kvm->arch.float_int.mchk.cr14)) + __clear_bit(IRQ_PEND_MCHK_REP, &active_mask); /* * STOP irqs will never be actively delivered. They are triggered via @@ -200,6 +197,16 @@ static void __set_cpuflag(struct kvm_vcpu *vcpu, u32 flag) atomic_set_mask(flag, &vcpu->arch.sie_block->cpuflags); } +static void set_intercept_indicators_io(struct kvm_vcpu *vcpu) +{ + if (!(pending_floating_irqs(vcpu) & IRQ_PEND_IO_MASK)) + return; + else if (psw_ioint_disabled(vcpu)) + __set_cpuflag(vcpu, CPUSTAT_IO_INT); + else + vcpu->arch.sie_block->lctl |= LCTL_CR6; +} + static void set_intercept_indicators_ext(struct kvm_vcpu *vcpu) { if (!(pending_local_irqs(vcpu) & IRQ_PEND_EXT_MASK)) @@ -226,47 +233,17 @@ static void set_intercept_indicators_stop(struct kvm_vcpu *vcpu) __set_cpuflag(vcpu, CPUSTAT_STOP_INT); } -/* Set interception request for non-deliverable local interrupts */ -static void set_intercept_indicators_local(struct kvm_vcpu *vcpu) +/* Set interception request for non-deliverable interrupts */ +static void set_intercept_indicators(struct kvm_vcpu *vcpu) { + set_intercept_indicators_io(vcpu); set_intercept_indicators_ext(vcpu); set_intercept_indicators_mchk(vcpu); set_intercept_indicators_stop(vcpu); } -static void __set_intercept_indicator(struct kvm_vcpu *vcpu, - struct kvm_s390_interrupt_info *inti) -{ - switch (inti->type) { - case KVM_S390_INT_SERVICE: - case KVM_S390_INT_PFAULT_DONE: - case KVM_S390_INT_VIRTIO: - if (psw_extint_disabled(vcpu)) - __set_cpuflag(vcpu, CPUSTAT_EXT_INT); - else - vcpu->arch.sie_block->lctl |= LCTL_CR0; - break; - case KVM_S390_MCHK: - if (psw_mchk_disabled(vcpu)) - vcpu->arch.sie_block->ictl |= ICTL_LPSW; - else - vcpu->arch.sie_block->lctl |= LCTL_CR14; - break; - case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: - if (psw_ioint_disabled(vcpu)) - __set_cpuflag(vcpu, CPUSTAT_IO_INT); - else - vcpu->arch.sie_block->lctl |= LCTL_CR6; - break; - default: - BUG(); - } -} - static u16 get_ilc(struct kvm_vcpu *vcpu) { - const unsigned short table[] = { 2, 4, 4, 6 }; - switch (vcpu->arch.sie_block->icptcode) { case ICPT_INST: case ICPT_INSTPROGI: @@ -274,7 +251,7 @@ static u16 get_ilc(struct kvm_vcpu *vcpu) case ICPT_PARTEXEC: case ICPT_IOINST: /* last instruction only stored for these icptcodes */ - return table[vcpu->arch.sie_block->ipa >> 14]; + return insn_length(vcpu->arch.sie_block->ipa >> 8); case ICPT_PROGI: return vcpu->arch.sie_block->pgmilc; default: @@ -350,38 +327,72 @@ static int __must_check __deliver_pfault_init(struct kvm_vcpu *vcpu) static int __must_check __deliver_machine_check(struct kvm_vcpu *vcpu) { + struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int; struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; - struct kvm_s390_mchk_info mchk; - int rc; + struct kvm_s390_mchk_info mchk = {}; + unsigned long adtl_status_addr; + int deliver = 0; + int rc = 0; + spin_lock(&fi->lock); spin_lock(&li->lock); - mchk = li->irq.mchk; + if (test_bit(IRQ_PEND_MCHK_EX, &li->pending_irqs) || + test_bit(IRQ_PEND_MCHK_REP, &li->pending_irqs)) { + /* + * If there was an exigent machine check pending, then any + * repressible machine checks that might have been pending + * are indicated along with it, so always clear bits for + * repressible and exigent interrupts + */ + mchk = li->irq.mchk; + clear_bit(IRQ_PEND_MCHK_EX, &li->pending_irqs); + clear_bit(IRQ_PEND_MCHK_REP, &li->pending_irqs); + memset(&li->irq.mchk, 0, sizeof(mchk)); + deliver = 1; + } /* - * If there was an exigent machine check pending, then any repressible - * machine checks that might have been pending are indicated along - * with it, so always clear both bits + * We indicate floating repressible conditions along with + * other pending conditions. Channel Report Pending and Channel + * Subsystem damage are the only two and and are indicated by + * bits in mcic and masked in cr14. */ - clear_bit(IRQ_PEND_MCHK_EX, &li->pending_irqs); - clear_bit(IRQ_PEND_MCHK_REP, &li->pending_irqs); - memset(&li->irq.mchk, 0, sizeof(mchk)); + if (test_and_clear_bit(IRQ_PEND_MCHK_REP, &fi->pending_irqs)) { + mchk.mcic |= fi->mchk.mcic; + mchk.cr14 |= fi->mchk.cr14; + memset(&fi->mchk, 0, sizeof(mchk)); + deliver = 1; + } spin_unlock(&li->lock); + spin_unlock(&fi->lock); - VCPU_EVENT(vcpu, 4, "interrupt: machine check mcic=%llx", - mchk.mcic); - trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_MCHK, - mchk.cr14, mchk.mcic); - - rc = kvm_s390_vcpu_store_status(vcpu, KVM_S390_STORE_STATUS_PREFIXED); - rc |= put_guest_lc(vcpu, mchk.mcic, - (u64 __user *) __LC_MCCK_CODE); - rc |= put_guest_lc(vcpu, mchk.failing_storage_address, - (u64 __user *) __LC_MCCK_FAIL_STOR_ADDR); - rc |= write_guest_lc(vcpu, __LC_PSW_SAVE_AREA, - &mchk.fixed_logout, sizeof(mchk.fixed_logout)); - rc |= write_guest_lc(vcpu, __LC_MCK_OLD_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - rc |= read_guest_lc(vcpu, __LC_MCK_NEW_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + if (deliver) { + VCPU_EVENT(vcpu, 4, "interrupt: machine check mcic=%llx", + mchk.mcic); + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, + KVM_S390_MCHK, + mchk.cr14, mchk.mcic); + + rc = kvm_s390_vcpu_store_status(vcpu, + KVM_S390_STORE_STATUS_PREFIXED); + rc |= read_guest_lc(vcpu, __LC_VX_SAVE_AREA_ADDR, + &adtl_status_addr, + sizeof(unsigned long)); + rc |= kvm_s390_vcpu_store_adtl_status(vcpu, + adtl_status_addr); + rc |= put_guest_lc(vcpu, mchk.mcic, + (u64 __user *) __LC_MCCK_CODE); + rc |= put_guest_lc(vcpu, mchk.failing_storage_address, + (u64 __user *) __LC_MCCK_FAIL_STOR_ADDR); + rc |= write_guest_lc(vcpu, __LC_PSW_SAVE_AREA, + &mchk.fixed_logout, + sizeof(mchk.fixed_logout)); + rc |= write_guest_lc(vcpu, __LC_MCK_OLD_PSW, + &vcpu->arch.sie_block->gpsw, + sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_MCK_NEW_PSW, + &vcpu->arch.sie_block->gpsw, + sizeof(psw_t)); + } return rc ? -EFAULT : 0; } @@ -484,7 +495,7 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; struct kvm_s390_pgm_info pgm_info; - int rc = 0; + int rc = 0, nullifying = false; u16 ilc = get_ilc(vcpu); spin_lock(&li->lock); @@ -509,6 +520,8 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) case PGM_LX_TRANSLATION: case PGM_PRIMARY_AUTHORITY: case PGM_SECONDARY_AUTHORITY: + nullifying = true; + /* fall through */ case PGM_SPACE_SWITCH: rc = put_guest_lc(vcpu, pgm_info.trans_exc_code, (u64 *)__LC_TRANS_EXC_CODE); @@ -521,6 +534,7 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) case PGM_EXTENDED_AUTHORITY: rc = put_guest_lc(vcpu, pgm_info.exc_access_id, (u8 *)__LC_EXC_ACCESS_ID); + nullifying = true; break; case PGM_ASCE_TYPE: case PGM_PAGE_TRANSLATION: @@ -534,6 +548,7 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) (u8 *)__LC_EXC_ACCESS_ID); rc |= put_guest_lc(vcpu, pgm_info.op_access_id, (u8 *)__LC_OP_ACCESS_ID); + nullifying = true; break; case PGM_MONITOR: rc = put_guest_lc(vcpu, pgm_info.mon_class_nr, @@ -541,6 +556,7 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) rc |= put_guest_lc(vcpu, pgm_info.mon_code, (u64 *)__LC_MON_CODE); break; + case PGM_VECTOR_PROCESSING: case PGM_DATA: rc = put_guest_lc(vcpu, pgm_info.data_exc_code, (u32 *)__LC_DATA_EXC_CODE); @@ -551,6 +567,15 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) rc |= put_guest_lc(vcpu, pgm_info.exc_access_id, (u8 *)__LC_EXC_ACCESS_ID); break; + case PGM_STACK_FULL: + case PGM_STACK_EMPTY: + case PGM_STACK_SPECIFICATION: + case PGM_STACK_TYPE: + case PGM_STACK_OPERATION: + case PGM_TRACE_TABEL: + case PGM_CRYPTO_OPERATION: + nullifying = true; + break; } if (pgm_info.code & PGM_PER) { @@ -564,7 +589,12 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) (u8 *) __LC_PER_ACCESS_ID); } + if (nullifying && vcpu->arch.sie_block->icptcode == ICPT_INST) + kvm_s390_rewind_psw(vcpu, ilc); + rc |= put_guest_lc(vcpu, ilc, (u16 *) __LC_PGM_ILC); + rc |= put_guest_lc(vcpu, vcpu->arch.sie_block->gbea, + (u64 *) __LC_LAST_BREAK); rc |= put_guest_lc(vcpu, pgm_info.code, (u16 *)__LC_PGM_INT_CODE); rc |= write_guest_lc(vcpu, __LC_PGM_OLD_PSW, @@ -574,16 +604,27 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) return rc ? -EFAULT : 0; } -static int __must_check __deliver_service(struct kvm_vcpu *vcpu, - struct kvm_s390_interrupt_info *inti) +static int __must_check __deliver_service(struct kvm_vcpu *vcpu) { - int rc; + struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int; + struct kvm_s390_ext_info ext; + int rc = 0; + + spin_lock(&fi->lock); + if (!(test_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs))) { + spin_unlock(&fi->lock); + return 0; + } + ext = fi->srv_signal; + memset(&fi->srv_signal, 0, sizeof(ext)); + clear_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs); + spin_unlock(&fi->lock); VCPU_EVENT(vcpu, 4, "interrupt: sclp parm:%x", - inti->ext.ext_params); + ext.ext_params); vcpu->stat.deliver_service_signal++; - trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, - inti->ext.ext_params, 0); + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_SERVICE, + ext.ext_params, 0); rc = put_guest_lc(vcpu, EXT_IRQ_SERVICE_SIG, (u16 *)__LC_EXT_INT_CODE); rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR); @@ -591,106 +632,146 @@ static int __must_check __deliver_service(struct kvm_vcpu *vcpu, &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - rc |= put_guest_lc(vcpu, inti->ext.ext_params, + rc |= put_guest_lc(vcpu, ext.ext_params, (u32 *)__LC_EXT_PARAMS); + return rc ? -EFAULT : 0; } -static int __must_check __deliver_pfault_done(struct kvm_vcpu *vcpu, - struct kvm_s390_interrupt_info *inti) +static int __must_check __deliver_pfault_done(struct kvm_vcpu *vcpu) { - int rc; + struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int; + struct kvm_s390_interrupt_info *inti; + int rc = 0; - trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, - KVM_S390_INT_PFAULT_DONE, 0, - inti->ext.ext_params2); + spin_lock(&fi->lock); + inti = list_first_entry_or_null(&fi->lists[FIRQ_LIST_PFAULT], + struct kvm_s390_interrupt_info, + list); + if (inti) { + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, + KVM_S390_INT_PFAULT_DONE, 0, + inti->ext.ext_params2); + list_del(&inti->list); + fi->counters[FIRQ_CNTR_PFAULT] -= 1; + } + if (list_empty(&fi->lists[FIRQ_LIST_PFAULT])) + clear_bit(IRQ_PEND_PFAULT_DONE, &fi->pending_irqs); + spin_unlock(&fi->lock); - rc = put_guest_lc(vcpu, EXT_IRQ_CP_SERVICE, (u16 *)__LC_EXT_INT_CODE); - rc |= put_guest_lc(vcpu, PFAULT_DONE, (u16 *)__LC_EXT_CPU_ADDR); - rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - rc |= put_guest_lc(vcpu, inti->ext.ext_params2, - (u64 *)__LC_EXT_PARAMS2); + if (inti) { + rc = put_guest_lc(vcpu, EXT_IRQ_CP_SERVICE, + (u16 *)__LC_EXT_INT_CODE); + rc |= put_guest_lc(vcpu, PFAULT_DONE, + (u16 *)__LC_EXT_CPU_ADDR); + rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, + sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, + &vcpu->arch.sie_block->gpsw, + sizeof(psw_t)); + rc |= put_guest_lc(vcpu, inti->ext.ext_params2, + (u64 *)__LC_EXT_PARAMS2); + kfree(inti); + } return rc ? -EFAULT : 0; } -static int __must_check __deliver_virtio(struct kvm_vcpu *vcpu, - struct kvm_s390_interrupt_info *inti) +static int __must_check __deliver_virtio(struct kvm_vcpu *vcpu) { - int rc; + struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int; + struct kvm_s390_interrupt_info *inti; + int rc = 0; - VCPU_EVENT(vcpu, 4, "interrupt: virtio parm:%x,parm64:%llx", - inti->ext.ext_params, inti->ext.ext_params2); - vcpu->stat.deliver_virtio_interrupt++; - trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, - inti->ext.ext_params, - inti->ext.ext_params2); + spin_lock(&fi->lock); + inti = list_first_entry_or_null(&fi->lists[FIRQ_LIST_VIRTIO], + struct kvm_s390_interrupt_info, + list); + if (inti) { + VCPU_EVENT(vcpu, 4, + "interrupt: virtio parm:%x,parm64:%llx", + inti->ext.ext_params, inti->ext.ext_params2); + vcpu->stat.deliver_virtio_interrupt++; + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, + inti->type, + inti->ext.ext_params, + inti->ext.ext_params2); + list_del(&inti->list); + fi->counters[FIRQ_CNTR_VIRTIO] -= 1; + } + if (list_empty(&fi->lists[FIRQ_LIST_VIRTIO])) + clear_bit(IRQ_PEND_VIRTIO, &fi->pending_irqs); + spin_unlock(&fi->lock); - rc = put_guest_lc(vcpu, EXT_IRQ_CP_SERVICE, (u16 *)__LC_EXT_INT_CODE); - rc |= put_guest_lc(vcpu, VIRTIO_PARAM, (u16 *)__LC_EXT_CPU_ADDR); - rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - rc |= put_guest_lc(vcpu, inti->ext.ext_params, - (u32 *)__LC_EXT_PARAMS); - rc |= put_guest_lc(vcpu, inti->ext.ext_params2, - (u64 *)__LC_EXT_PARAMS2); + if (inti) { + rc = put_guest_lc(vcpu, EXT_IRQ_CP_SERVICE, + (u16 *)__LC_EXT_INT_CODE); + rc |= put_guest_lc(vcpu, VIRTIO_PARAM, + (u16 *)__LC_EXT_CPU_ADDR); + rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, + sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, + &vcpu->arch.sie_block->gpsw, + sizeof(psw_t)); + rc |= put_guest_lc(vcpu, inti->ext.ext_params, + (u32 *)__LC_EXT_PARAMS); + rc |= put_guest_lc(vcpu, inti->ext.ext_params2, + (u64 *)__LC_EXT_PARAMS2); + kfree(inti); + } return rc ? -EFAULT : 0; } static int __must_check __deliver_io(struct kvm_vcpu *vcpu, - struct kvm_s390_interrupt_info *inti) + unsigned long irq_type) { - int rc; + struct list_head *isc_list; + struct kvm_s390_float_interrupt *fi; + struct kvm_s390_interrupt_info *inti = NULL; + int rc = 0; - VCPU_EVENT(vcpu, 4, "interrupt: I/O %llx", inti->type); - vcpu->stat.deliver_io_int++; - trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, - ((__u32)inti->io.subchannel_id << 16) | - inti->io.subchannel_nr, - ((__u64)inti->io.io_int_parm << 32) | - inti->io.io_int_word); - - rc = put_guest_lc(vcpu, inti->io.subchannel_id, - (u16 *)__LC_SUBCHANNEL_ID); - rc |= put_guest_lc(vcpu, inti->io.subchannel_nr, - (u16 *)__LC_SUBCHANNEL_NR); - rc |= put_guest_lc(vcpu, inti->io.io_int_parm, - (u32 *)__LC_IO_INT_PARM); - rc |= put_guest_lc(vcpu, inti->io.io_int_word, - (u32 *)__LC_IO_INT_WORD); - rc |= write_guest_lc(vcpu, __LC_IO_OLD_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - rc |= read_guest_lc(vcpu, __LC_IO_NEW_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - return rc ? -EFAULT : 0; -} + fi = &vcpu->kvm->arch.float_int; -static int __must_check __deliver_mchk_floating(struct kvm_vcpu *vcpu, - struct kvm_s390_interrupt_info *inti) -{ - struct kvm_s390_mchk_info *mchk = &inti->mchk; - int rc; + spin_lock(&fi->lock); + isc_list = &fi->lists[irq_type - IRQ_PEND_IO_ISC_0]; + inti = list_first_entry_or_null(isc_list, + struct kvm_s390_interrupt_info, + list); + if (inti) { + VCPU_EVENT(vcpu, 4, "interrupt: I/O %llx", inti->type); + vcpu->stat.deliver_io_int++; + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, + inti->type, + ((__u32)inti->io.subchannel_id << 16) | + inti->io.subchannel_nr, + ((__u64)inti->io.io_int_parm << 32) | + inti->io.io_int_word); + list_del(&inti->list); + fi->counters[FIRQ_CNTR_IO] -= 1; + } + if (list_empty(isc_list)) + clear_bit(irq_type, &fi->pending_irqs); + spin_unlock(&fi->lock); + + if (inti) { + rc = put_guest_lc(vcpu, inti->io.subchannel_id, + (u16 *)__LC_SUBCHANNEL_ID); + rc |= put_guest_lc(vcpu, inti->io.subchannel_nr, + (u16 *)__LC_SUBCHANNEL_NR); + rc |= put_guest_lc(vcpu, inti->io.io_int_parm, + (u32 *)__LC_IO_INT_PARM); + rc |= put_guest_lc(vcpu, inti->io.io_int_word, + (u32 *)__LC_IO_INT_WORD); + rc |= write_guest_lc(vcpu, __LC_IO_OLD_PSW, + &vcpu->arch.sie_block->gpsw, + sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_IO_NEW_PSW, + &vcpu->arch.sie_block->gpsw, + sizeof(psw_t)); + kfree(inti); + } - VCPU_EVENT(vcpu, 4, "interrupt: machine check mcic=%llx", - mchk->mcic); - trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_MCHK, - mchk->cr14, mchk->mcic); - - rc = kvm_s390_vcpu_store_status(vcpu, KVM_S390_STORE_STATUS_PREFIXED); - rc |= put_guest_lc(vcpu, mchk->mcic, - (u64 __user *) __LC_MCCK_CODE); - rc |= put_guest_lc(vcpu, mchk->failing_storage_address, - (u64 __user *) __LC_MCCK_FAIL_STOR_ADDR); - rc |= write_guest_lc(vcpu, __LC_PSW_SAVE_AREA, - &mchk->fixed_logout, sizeof(mchk->fixed_logout)); - rc |= write_guest_lc(vcpu, __LC_MCK_OLD_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - rc |= read_guest_lc(vcpu, __LC_MCK_NEW_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); return rc ? -EFAULT : 0; } @@ -698,6 +779,7 @@ typedef int (*deliver_irq_t)(struct kvm_vcpu *vcpu); static const deliver_irq_t deliver_irq_funcs[] = { [IRQ_PEND_MCHK_EX] = __deliver_machine_check, + [IRQ_PEND_MCHK_REP] = __deliver_machine_check, [IRQ_PEND_PROG] = __deliver_prog, [IRQ_PEND_EXT_EMERGENCY] = __deliver_emergency_signal, [IRQ_PEND_EXT_EXTERNAL] = __deliver_external_call, @@ -706,36 +788,11 @@ static const deliver_irq_t deliver_irq_funcs[] = { [IRQ_PEND_RESTART] = __deliver_restart, [IRQ_PEND_SET_PREFIX] = __deliver_set_prefix, [IRQ_PEND_PFAULT_INIT] = __deliver_pfault_init, + [IRQ_PEND_EXT_SERVICE] = __deliver_service, + [IRQ_PEND_PFAULT_DONE] = __deliver_pfault_done, + [IRQ_PEND_VIRTIO] = __deliver_virtio, }; -static int __must_check __deliver_floating_interrupt(struct kvm_vcpu *vcpu, - struct kvm_s390_interrupt_info *inti) -{ - int rc; - - switch (inti->type) { - case KVM_S390_INT_SERVICE: - rc = __deliver_service(vcpu, inti); - break; - case KVM_S390_INT_PFAULT_DONE: - rc = __deliver_pfault_done(vcpu, inti); - break; - case KVM_S390_INT_VIRTIO: - rc = __deliver_virtio(vcpu, inti); - break; - case KVM_S390_MCHK: - rc = __deliver_mchk_floating(vcpu, inti); - break; - case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: - rc = __deliver_io(vcpu, inti); - break; - default: - BUG(); - } - - return rc; -} - /* Check whether an external call is pending (deliverable or not) */ int kvm_s390_ext_call_pending(struct kvm_vcpu *vcpu) { @@ -751,21 +808,9 @@ int kvm_s390_ext_call_pending(struct kvm_vcpu *vcpu) int kvm_s390_vcpu_has_irq(struct kvm_vcpu *vcpu, int exclude_stop) { - struct kvm_s390_float_interrupt *fi = vcpu->arch.local_int.float_int; - struct kvm_s390_interrupt_info *inti; int rc; - rc = !!deliverable_local_irqs(vcpu); - - if ((!rc) && atomic_read(&fi->active)) { - spin_lock(&fi->lock); - list_for_each_entry(inti, &fi->list, list) - if (__interrupt_is_deliverable(vcpu, inti)) { - rc = 1; - break; - } - spin_unlock(&fi->lock); - } + rc = !!deliverable_irqs(vcpu); if (!rc && kvm_cpu_has_pending_timer(vcpu)) rc = 1; @@ -784,12 +829,7 @@ int kvm_s390_vcpu_has_irq(struct kvm_vcpu *vcpu, int exclude_stop) int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) { - if (!(vcpu->arch.sie_block->ckc < - get_tod_clock_fast() + vcpu->arch.sie_block->epoch)) - return 0; - if (!ckc_interrupts_enabled(vcpu)) - return 0; - return 1; + return ckc_irq_pending(vcpu) || cpu_timer_irq_pending(vcpu); } int kvm_s390_handle_wait(struct kvm_vcpu *vcpu) @@ -884,60 +924,45 @@ void kvm_s390_clear_local_irqs(struct kvm_vcpu *vcpu) int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; - struct kvm_s390_float_interrupt *fi = vcpu->arch.local_int.float_int; - struct kvm_s390_interrupt_info *n, *inti = NULL; deliver_irq_t func; - int deliver; int rc = 0; unsigned long irq_type; - unsigned long deliverable_irqs; + unsigned long irqs; __reset_intercept_indicators(vcpu); /* pending ckc conditions might have been invalidated */ clear_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs); - if (kvm_cpu_has_pending_timer(vcpu)) + if (ckc_irq_pending(vcpu)) set_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs); + /* pending cpu timer conditions might have been invalidated */ + clear_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs); + if (cpu_timer_irq_pending(vcpu)) + set_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs); + do { - deliverable_irqs = deliverable_local_irqs(vcpu); + irqs = deliverable_irqs(vcpu); /* bits are in the order of interrupt priority */ - irq_type = find_first_bit(&deliverable_irqs, IRQ_PEND_COUNT); + irq_type = find_first_bit(&irqs, IRQ_PEND_COUNT); if (irq_type == IRQ_PEND_COUNT) break; - func = deliver_irq_funcs[irq_type]; - if (!func) { - WARN_ON_ONCE(func == NULL); - clear_bit(irq_type, &li->pending_irqs); - continue; + if (is_ioirq(irq_type)) { + rc = __deliver_io(vcpu, irq_type); + } else { + func = deliver_irq_funcs[irq_type]; + if (!func) { + WARN_ON_ONCE(func == NULL); + clear_bit(irq_type, &li->pending_irqs); + continue; + } + rc = func(vcpu); } - rc = func(vcpu); - } while (!rc && irq_type != IRQ_PEND_COUNT); + if (rc) + break; + } while (!rc); - set_intercept_indicators_local(vcpu); - - if (!rc && atomic_read(&fi->active)) { - do { - deliver = 0; - spin_lock(&fi->lock); - list_for_each_entry_safe(inti, n, &fi->list, list) { - if (__interrupt_is_deliverable(vcpu, inti)) { - list_del(&inti->list); - fi->irq_count--; - deliver = 1; - break; - } - __set_intercept_indicator(vcpu, inti); - } - if (list_empty(&fi->list)) - atomic_set(&fi->active, 0); - spin_unlock(&fi->lock); - if (deliver) { - rc = __deliver_floating_interrupt(vcpu, inti); - kfree(inti); - } - } while (!rc && deliver); - } + set_intercept_indicators(vcpu); return rc; } @@ -1172,80 +1197,182 @@ static int __inject_cpu_timer(struct kvm_vcpu *vcpu) return 0; } +static struct kvm_s390_interrupt_info *get_io_int(struct kvm *kvm, + int isc, u32 schid) +{ + struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int; + struct list_head *isc_list = &fi->lists[FIRQ_LIST_IO_ISC_0 + isc]; + struct kvm_s390_interrupt_info *iter; + u16 id = (schid & 0xffff0000U) >> 16; + u16 nr = schid & 0x0000ffffU; + spin_lock(&fi->lock); + list_for_each_entry(iter, isc_list, list) { + if (schid && (id != iter->io.subchannel_id || + nr != iter->io.subchannel_nr)) + continue; + /* found an appropriate entry */ + list_del_init(&iter->list); + fi->counters[FIRQ_CNTR_IO] -= 1; + if (list_empty(isc_list)) + clear_bit(IRQ_PEND_IO_ISC_0 + isc, &fi->pending_irqs); + spin_unlock(&fi->lock); + return iter; + } + spin_unlock(&fi->lock); + return NULL; +} + +/* + * Dequeue and return an I/O interrupt matching any of the interruption + * subclasses as designated by the isc mask in cr6 and the schid (if != 0). + */ struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm, - u64 cr6, u64 schid) + u64 isc_mask, u32 schid) +{ + struct kvm_s390_interrupt_info *inti = NULL; + int isc; + + for (isc = 0; isc <= MAX_ISC && !inti; isc++) { + if (isc_mask & isc_to_isc_bits(isc)) + inti = get_io_int(kvm, isc, schid); + } + return inti; +} + +#define SCCB_MASK 0xFFFFFFF8 +#define SCCB_EVENT_PENDING 0x3 + +static int __inject_service(struct kvm *kvm, + struct kvm_s390_interrupt_info *inti) +{ + struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int; + + spin_lock(&fi->lock); + fi->srv_signal.ext_params |= inti->ext.ext_params & SCCB_EVENT_PENDING; + /* + * Early versions of the QEMU s390 bios will inject several + * service interrupts after another without handling a + * condition code indicating busy. + * We will silently ignore those superfluous sccb values. + * A future version of QEMU will take care of serialization + * of servc requests + */ + if (fi->srv_signal.ext_params & SCCB_MASK) + goto out; + fi->srv_signal.ext_params |= inti->ext.ext_params & SCCB_MASK; + set_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs); +out: + spin_unlock(&fi->lock); + kfree(inti); + return 0; +} + +static int __inject_virtio(struct kvm *kvm, + struct kvm_s390_interrupt_info *inti) +{ + struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int; + + spin_lock(&fi->lock); + if (fi->counters[FIRQ_CNTR_VIRTIO] >= KVM_S390_MAX_VIRTIO_IRQS) { + spin_unlock(&fi->lock); + return -EBUSY; + } + fi->counters[FIRQ_CNTR_VIRTIO] += 1; + list_add_tail(&inti->list, &fi->lists[FIRQ_LIST_VIRTIO]); + set_bit(IRQ_PEND_VIRTIO, &fi->pending_irqs); + spin_unlock(&fi->lock); + return 0; +} + +static int __inject_pfault_done(struct kvm *kvm, + struct kvm_s390_interrupt_info *inti) +{ + struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int; + + spin_lock(&fi->lock); + if (fi->counters[FIRQ_CNTR_PFAULT] >= + (ASYNC_PF_PER_VCPU * KVM_MAX_VCPUS)) { + spin_unlock(&fi->lock); + return -EBUSY; + } + fi->counters[FIRQ_CNTR_PFAULT] += 1; + list_add_tail(&inti->list, &fi->lists[FIRQ_LIST_PFAULT]); + set_bit(IRQ_PEND_PFAULT_DONE, &fi->pending_irqs); + spin_unlock(&fi->lock); + return 0; +} + +#define CR_PENDING_SUBCLASS 28 +static int __inject_float_mchk(struct kvm *kvm, + struct kvm_s390_interrupt_info *inti) +{ + struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int; + + spin_lock(&fi->lock); + fi->mchk.cr14 |= inti->mchk.cr14 & (1UL << CR_PENDING_SUBCLASS); + fi->mchk.mcic |= inti->mchk.mcic; + set_bit(IRQ_PEND_MCHK_REP, &fi->pending_irqs); + spin_unlock(&fi->lock); + kfree(inti); + return 0; +} + +static int __inject_io(struct kvm *kvm, struct kvm_s390_interrupt_info *inti) { struct kvm_s390_float_interrupt *fi; - struct kvm_s390_interrupt_info *inti, *iter; + struct list_head *list; + int isc; - if ((!schid && !cr6) || (schid && cr6)) - return NULL; fi = &kvm->arch.float_int; spin_lock(&fi->lock); - inti = NULL; - list_for_each_entry(iter, &fi->list, list) { - if (!is_ioint(iter->type)) - continue; - if (cr6 && - ((cr6 & int_word_to_isc_bits(iter->io.io_int_word)) == 0)) - continue; - if (schid) { - if (((schid & 0x00000000ffff0000) >> 16) != - iter->io.subchannel_id) - continue; - if ((schid & 0x000000000000ffff) != - iter->io.subchannel_nr) - continue; - } - inti = iter; - break; - } - if (inti) { - list_del_init(&inti->list); - fi->irq_count--; + if (fi->counters[FIRQ_CNTR_IO] >= KVM_S390_MAX_FLOAT_IRQS) { + spin_unlock(&fi->lock); + return -EBUSY; } - if (list_empty(&fi->list)) - atomic_set(&fi->active, 0); + fi->counters[FIRQ_CNTR_IO] += 1; + + isc = int_word_to_isc(inti->io.io_int_word); + list = &fi->lists[FIRQ_LIST_IO_ISC_0 + isc]; + list_add_tail(&inti->list, list); + set_bit(IRQ_PEND_IO_ISC_0 + isc, &fi->pending_irqs); spin_unlock(&fi->lock); - return inti; + return 0; } static int __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti) { struct kvm_s390_local_interrupt *li; struct kvm_s390_float_interrupt *fi; - struct kvm_s390_interrupt_info *iter; struct kvm_vcpu *dst_vcpu = NULL; int sigcpu; - int rc = 0; + u64 type = READ_ONCE(inti->type); + int rc; fi = &kvm->arch.float_int; - spin_lock(&fi->lock); - if (fi->irq_count >= KVM_S390_MAX_FLOAT_IRQS) { + + switch (type) { + case KVM_S390_MCHK: + rc = __inject_float_mchk(kvm, inti); + break; + case KVM_S390_INT_VIRTIO: + rc = __inject_virtio(kvm, inti); + break; + case KVM_S390_INT_SERVICE: + rc = __inject_service(kvm, inti); + break; + case KVM_S390_INT_PFAULT_DONE: + rc = __inject_pfault_done(kvm, inti); + break; + case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: + rc = __inject_io(kvm, inti); + break; + default: rc = -EINVAL; - goto unlock_fi; } - fi->irq_count++; - if (!is_ioint(inti->type)) { - list_add_tail(&inti->list, &fi->list); - } else { - u64 isc_bits = int_word_to_isc_bits(inti->io.io_int_word); + if (rc) + return rc; - /* Keep I/O interrupts sorted in isc order. */ - list_for_each_entry(iter, &fi->list, list) { - if (!is_ioint(iter->type)) - continue; - if (int_word_to_isc_bits(iter->io.io_int_word) - <= isc_bits) - continue; - break; - } - list_add_tail(&inti->list, &iter->list); - } - atomic_set(&fi->active, 1); - if (atomic_read(&kvm->online_vcpus) == 0) - goto unlock_fi; sigcpu = find_first_bit(fi->idle_mask, KVM_MAX_VCPUS); if (sigcpu == KVM_MAX_VCPUS) { do { @@ -1257,7 +1384,7 @@ static int __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti) dst_vcpu = kvm_get_vcpu(kvm, sigcpu); li = &dst_vcpu->arch.local_int; spin_lock(&li->lock); - switch (inti->type) { + switch (type) { case KVM_S390_MCHK: atomic_set_mask(CPUSTAT_STOP_INT, li->cpuflags); break; @@ -1270,9 +1397,8 @@ static int __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti) } spin_unlock(&li->lock); kvm_s390_vcpu_wakeup(kvm_get_vcpu(kvm, sigcpu)); -unlock_fi: - spin_unlock(&fi->lock); - return rc; + return 0; + } int kvm_s390_inject_vm(struct kvm *kvm, @@ -1332,10 +1458,10 @@ int kvm_s390_inject_vm(struct kvm *kvm, return rc; } -void kvm_s390_reinject_io_int(struct kvm *kvm, +int kvm_s390_reinject_io_int(struct kvm *kvm, struct kvm_s390_interrupt_info *inti) { - __inject_vm(kvm, inti); + return __inject_vm(kvm, inti); } int s390int_to_s390irq(struct kvm_s390_interrupt *s390int, @@ -1388,12 +1514,10 @@ void kvm_s390_clear_stop_irq(struct kvm_vcpu *vcpu) spin_unlock(&li->lock); } -int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) +static int do_inject_vcpu(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) { - struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; int rc; - spin_lock(&li->lock); switch (irq->type) { case KVM_S390_PROGRAM_INT: VCPU_EVENT(vcpu, 3, "inject: program check %d (from user)", @@ -1433,83 +1557,130 @@ int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) default: rc = -EINVAL; } + + return rc; +} + +int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + int rc; + + spin_lock(&li->lock); + rc = do_inject_vcpu(vcpu, irq); spin_unlock(&li->lock); if (!rc) kvm_s390_vcpu_wakeup(vcpu); return rc; } -void kvm_s390_clear_float_irqs(struct kvm *kvm) +static inline void clear_irq_list(struct list_head *_list) { - struct kvm_s390_float_interrupt *fi; - struct kvm_s390_interrupt_info *n, *inti = NULL; + struct kvm_s390_interrupt_info *inti, *n; - fi = &kvm->arch.float_int; - spin_lock(&fi->lock); - list_for_each_entry_safe(inti, n, &fi->list, list) { + list_for_each_entry_safe(inti, n, _list, list) { list_del(&inti->list); kfree(inti); } - fi->irq_count = 0; - atomic_set(&fi->active, 0); - spin_unlock(&fi->lock); } -static inline int copy_irq_to_user(struct kvm_s390_interrupt_info *inti, - u8 *addr) +static void inti_to_irq(struct kvm_s390_interrupt_info *inti, + struct kvm_s390_irq *irq) { - struct kvm_s390_irq __user *uptr = (struct kvm_s390_irq __user *) addr; - struct kvm_s390_irq irq = {0}; - - irq.type = inti->type; + irq->type = inti->type; switch (inti->type) { case KVM_S390_INT_PFAULT_INIT: case KVM_S390_INT_PFAULT_DONE: case KVM_S390_INT_VIRTIO: - case KVM_S390_INT_SERVICE: - irq.u.ext = inti->ext; + irq->u.ext = inti->ext; break; case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: - irq.u.io = inti->io; + irq->u.io = inti->io; break; - case KVM_S390_MCHK: - irq.u.mchk = inti->mchk; - break; - default: - return -EINVAL; } +} - if (copy_to_user(uptr, &irq, sizeof(irq))) - return -EFAULT; +void kvm_s390_clear_float_irqs(struct kvm *kvm) +{ + struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int; + int i; - return 0; -} + spin_lock(&fi->lock); + for (i = 0; i < FIRQ_LIST_COUNT; i++) + clear_irq_list(&fi->lists[i]); + for (i = 0; i < FIRQ_MAX_COUNT; i++) + fi->counters[i] = 0; + spin_unlock(&fi->lock); +}; -static int get_all_floating_irqs(struct kvm *kvm, __u8 *buf, __u64 len) +static int get_all_floating_irqs(struct kvm *kvm, u8 __user *usrbuf, u64 len) { struct kvm_s390_interrupt_info *inti; struct kvm_s390_float_interrupt *fi; + struct kvm_s390_irq *buf; + struct kvm_s390_irq *irq; + int max_irqs; int ret = 0; int n = 0; + int i; + + if (len > KVM_S390_FLIC_MAX_BUFFER || len == 0) + return -EINVAL; + + /* + * We are already using -ENOMEM to signal + * userspace it may retry with a bigger buffer, + * so we need to use something else for this case + */ + buf = vzalloc(len); + if (!buf) + return -ENOBUFS; + + max_irqs = len / sizeof(struct kvm_s390_irq); fi = &kvm->arch.float_int; spin_lock(&fi->lock); - - list_for_each_entry(inti, &fi->list, list) { - if (len < sizeof(struct kvm_s390_irq)) { + for (i = 0; i < FIRQ_LIST_COUNT; i++) { + list_for_each_entry(inti, &fi->lists[i], list) { + if (n == max_irqs) { + /* signal userspace to try again */ + ret = -ENOMEM; + goto out; + } + inti_to_irq(inti, &buf[n]); + n++; + } + } + if (test_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs)) { + if (n == max_irqs) { /* signal userspace to try again */ ret = -ENOMEM; - break; + goto out; } - ret = copy_irq_to_user(inti, buf); - if (ret) - break; - buf += sizeof(struct kvm_s390_irq); - len -= sizeof(struct kvm_s390_irq); + irq = (struct kvm_s390_irq *) &buf[n]; + irq->type = KVM_S390_INT_SERVICE; + irq->u.ext = fi->srv_signal; n++; } + if (test_bit(IRQ_PEND_MCHK_REP, &fi->pending_irqs)) { + if (n == max_irqs) { + /* signal userspace to try again */ + ret = -ENOMEM; + goto out; + } + irq = (struct kvm_s390_irq *) &buf[n]; + irq->type = KVM_S390_MCHK; + irq->u.mchk = fi->mchk; + n++; +} +out: spin_unlock(&fi->lock); + if (!ret && n > 0) { + if (copy_to_user(usrbuf, buf, sizeof(struct kvm_s390_irq) * n)) + ret = -EFAULT; + } + vfree(buf); return ret < 0 ? ret : n; } @@ -1520,7 +1691,7 @@ static int flic_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr) switch (attr->group) { case KVM_DEV_FLIC_GET_ALL_IRQS: - r = get_all_floating_irqs(dev->kvm, (u8 *) attr->addr, + r = get_all_floating_irqs(dev->kvm, (u8 __user *) attr->addr, attr->attr); break; default: @@ -1952,3 +2123,143 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, { return -EINVAL; } + +int kvm_s390_set_irq_state(struct kvm_vcpu *vcpu, void __user *irqstate, int len) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + struct kvm_s390_irq *buf; + int r = 0; + int n; + + buf = vmalloc(len); + if (!buf) + return -ENOMEM; + + if (copy_from_user((void *) buf, irqstate, len)) { + r = -EFAULT; + goto out_free; + } + + /* + * Don't allow setting the interrupt state + * when there are already interrupts pending + */ + spin_lock(&li->lock); + if (li->pending_irqs) { + r = -EBUSY; + goto out_unlock; + } + + for (n = 0; n < len / sizeof(*buf); n++) { + r = do_inject_vcpu(vcpu, &buf[n]); + if (r) + break; + } + +out_unlock: + spin_unlock(&li->lock); +out_free: + vfree(buf); + + return r; +} + +static void store_local_irq(struct kvm_s390_local_interrupt *li, + struct kvm_s390_irq *irq, + unsigned long irq_type) +{ + switch (irq_type) { + case IRQ_PEND_MCHK_EX: + case IRQ_PEND_MCHK_REP: + irq->type = KVM_S390_MCHK; + irq->u.mchk = li->irq.mchk; + break; + case IRQ_PEND_PROG: + irq->type = KVM_S390_PROGRAM_INT; + irq->u.pgm = li->irq.pgm; + break; + case IRQ_PEND_PFAULT_INIT: + irq->type = KVM_S390_INT_PFAULT_INIT; + irq->u.ext = li->irq.ext; + break; + case IRQ_PEND_EXT_EXTERNAL: + irq->type = KVM_S390_INT_EXTERNAL_CALL; + irq->u.extcall = li->irq.extcall; + break; + case IRQ_PEND_EXT_CLOCK_COMP: + irq->type = KVM_S390_INT_CLOCK_COMP; + break; + case IRQ_PEND_EXT_CPU_TIMER: + irq->type = KVM_S390_INT_CPU_TIMER; + break; + case IRQ_PEND_SIGP_STOP: + irq->type = KVM_S390_SIGP_STOP; + irq->u.stop = li->irq.stop; + break; + case IRQ_PEND_RESTART: + irq->type = KVM_S390_RESTART; + break; + case IRQ_PEND_SET_PREFIX: + irq->type = KVM_S390_SIGP_SET_PREFIX; + irq->u.prefix = li->irq.prefix; + break; + } +} + +int kvm_s390_get_irq_state(struct kvm_vcpu *vcpu, __u8 __user *buf, int len) +{ + uint8_t sigp_ctrl = vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl; + unsigned long sigp_emerg_pending[BITS_TO_LONGS(KVM_MAX_VCPUS)]; + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + unsigned long pending_irqs; + struct kvm_s390_irq irq; + unsigned long irq_type; + int cpuaddr; + int n = 0; + + spin_lock(&li->lock); + pending_irqs = li->pending_irqs; + memcpy(&sigp_emerg_pending, &li->sigp_emerg_pending, + sizeof(sigp_emerg_pending)); + spin_unlock(&li->lock); + + for_each_set_bit(irq_type, &pending_irqs, IRQ_PEND_COUNT) { + memset(&irq, 0, sizeof(irq)); + if (irq_type == IRQ_PEND_EXT_EMERGENCY) + continue; + if (n + sizeof(irq) > len) + return -ENOBUFS; + store_local_irq(&vcpu->arch.local_int, &irq, irq_type); + if (copy_to_user(&buf[n], &irq, sizeof(irq))) + return -EFAULT; + n += sizeof(irq); + } + + if (test_bit(IRQ_PEND_EXT_EMERGENCY, &pending_irqs)) { + for_each_set_bit(cpuaddr, sigp_emerg_pending, KVM_MAX_VCPUS) { + memset(&irq, 0, sizeof(irq)); + if (n + sizeof(irq) > len) + return -ENOBUFS; + irq.type = KVM_S390_INT_EMERGENCY; + irq.u.emerg.code = cpuaddr; + if (copy_to_user(&buf[n], &irq, sizeof(irq))) + return -EFAULT; + n += sizeof(irq); + } + } + + if ((sigp_ctrl & SIGP_CTRL_C) && + (atomic_read(&vcpu->arch.sie_block->cpuflags) & + CPUSTAT_ECALL_PEND)) { + if (n + sizeof(irq) > len) + return -ENOBUFS; + memset(&irq, 0, sizeof(irq)); + irq.type = KVM_S390_INT_EXTERNAL_CALL; + irq.u.extcall.code = sigp_ctrl & SIGP_CTRL_SCN_MASK; + if (copy_to_user(&buf[n], &irq, sizeof(irq))) + return -EFAULT; + n += sizeof(irq); + } + + return n; +} diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 19e17bd7aec0..afa2bd750ffc 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -25,11 +25,13 @@ #include <linux/random.h> #include <linux/slab.h> #include <linux/timer.h> +#include <linux/vmalloc.h> #include <asm/asm-offsets.h> #include <asm/lowcore.h> #include <asm/pgtable.h> #include <asm/nmi.h> #include <asm/switch_to.h> +#include <asm/isc.h> #include <asm/sclp.h> #include "kvm-s390.h" #include "gaccess.h" @@ -38,6 +40,11 @@ #include "trace.h" #include "trace-s390.h" +#define MEM_OP_MAX_SIZE 65536 /* Maximum transfer size for KVM_S390_MEM_OP */ +#define LOCAL_IRQS 32 +#define VCPU_IRQS_MAX_BUF (sizeof(struct kvm_s390_irq) * \ + (KVM_MAX_VCPUS + LOCAL_IRQS)) + #define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU struct kvm_stats_debugfs_item debugfs_entries[] = { @@ -87,6 +94,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "instruction_sigp_stop", VCPU_STAT(instruction_sigp_stop) }, { "instruction_sigp_stop_store_status", VCPU_STAT(instruction_sigp_stop_store_status) }, { "instruction_sigp_store_status", VCPU_STAT(instruction_sigp_store_status) }, + { "instruction_sigp_store_adtl_status", VCPU_STAT(instruction_sigp_store_adtl_status) }, { "instruction_sigp_set_arch", VCPU_STAT(instruction_sigp_arch) }, { "instruction_sigp_set_prefix", VCPU_STAT(instruction_sigp_prefix) }, { "instruction_sigp_restart", VCPU_STAT(instruction_sigp_restart) }, @@ -101,8 +109,8 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { /* upper facilities limit for kvm */ unsigned long kvm_s390_fac_list_mask[] = { - 0xff82fffbf4fc2000UL, - 0x005c000000000000UL, + 0xffe6fffbfcfdfc40UL, + 0x205c800000000000UL, }; unsigned long kvm_s390_fac_list_mask_size(void) @@ -171,9 +179,16 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_S390_IRQCHIP: case KVM_CAP_VM_ATTRIBUTES: case KVM_CAP_MP_STATE: + case KVM_CAP_S390_INJECT_IRQ: case KVM_CAP_S390_USER_SIGP: + case KVM_CAP_S390_USER_STSI: + case KVM_CAP_S390_SKEYS: + case KVM_CAP_S390_IRQ_STATE: r = 1; break; + case KVM_CAP_S390_MEM_OP: + r = MEM_OP_MAX_SIZE; + break; case KVM_CAP_NR_VCPUS: case KVM_CAP_MAX_VCPUS: r = KVM_MAX_VCPUS; @@ -184,6 +199,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_S390_COW: r = MACHINE_HAS_ESOP; break; + case KVM_CAP_S390_VECTOR_REGISTERS: + r = MACHINE_HAS_VX; + break; default: r = 0; } @@ -264,6 +282,18 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) kvm->arch.user_sigp = 1; r = 0; break; + case KVM_CAP_S390_VECTOR_REGISTERS: + if (MACHINE_HAS_VX) { + set_kvm_facility(kvm->arch.model.fac->mask, 129); + set_kvm_facility(kvm->arch.model.fac->list, 129); + r = 0; + } else + r = -EINVAL; + break; + case KVM_CAP_S390_USER_STSI: + kvm->arch.user_stsi = 1; + r = 0; + break; default: r = -EINVAL; break; @@ -708,6 +738,108 @@ static int kvm_s390_vm_has_attr(struct kvm *kvm, struct kvm_device_attr *attr) return ret; } +static long kvm_s390_get_skeys(struct kvm *kvm, struct kvm_s390_skeys *args) +{ + uint8_t *keys; + uint64_t hva; + unsigned long curkey; + int i, r = 0; + + if (args->flags != 0) + return -EINVAL; + + /* Is this guest using storage keys? */ + if (!mm_use_skey(current->mm)) + return KVM_S390_GET_SKEYS_NONE; + + /* Enforce sane limit on memory allocation */ + if (args->count < 1 || args->count > KVM_S390_SKEYS_MAX) + return -EINVAL; + + keys = kmalloc_array(args->count, sizeof(uint8_t), + GFP_KERNEL | __GFP_NOWARN); + if (!keys) + keys = vmalloc(sizeof(uint8_t) * args->count); + if (!keys) + return -ENOMEM; + + for (i = 0; i < args->count; i++) { + hva = gfn_to_hva(kvm, args->start_gfn + i); + if (kvm_is_error_hva(hva)) { + r = -EFAULT; + goto out; + } + + curkey = get_guest_storage_key(current->mm, hva); + if (IS_ERR_VALUE(curkey)) { + r = curkey; + goto out; + } + keys[i] = curkey; + } + + r = copy_to_user((uint8_t __user *)args->skeydata_addr, keys, + sizeof(uint8_t) * args->count); + if (r) + r = -EFAULT; +out: + kvfree(keys); + return r; +} + +static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args) +{ + uint8_t *keys; + uint64_t hva; + int i, r = 0; + + if (args->flags != 0) + return -EINVAL; + + /* Enforce sane limit on memory allocation */ + if (args->count < 1 || args->count > KVM_S390_SKEYS_MAX) + return -EINVAL; + + keys = kmalloc_array(args->count, sizeof(uint8_t), + GFP_KERNEL | __GFP_NOWARN); + if (!keys) + keys = vmalloc(sizeof(uint8_t) * args->count); + if (!keys) + return -ENOMEM; + + r = copy_from_user(keys, (uint8_t __user *)args->skeydata_addr, + sizeof(uint8_t) * args->count); + if (r) { + r = -EFAULT; + goto out; + } + + /* Enable storage key handling for the guest */ + s390_enable_skey(); + + for (i = 0; i < args->count; i++) { + hva = gfn_to_hva(kvm, args->start_gfn + i); + if (kvm_is_error_hva(hva)) { + r = -EFAULT; + goto out; + } + + /* Lowest order bit is reserved */ + if (keys[i] & 0x01) { + r = -EINVAL; + goto out; + } + + r = set_guest_storage_key(current->mm, hva, + (unsigned long)keys[i], 0); + if (r) + goto out; + } +out: + kvfree(keys); + return r; +} + long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -767,6 +899,26 @@ long kvm_arch_vm_ioctl(struct file *filp, r = kvm_s390_vm_has_attr(kvm, &attr); break; } + case KVM_S390_GET_SKEYS: { + struct kvm_s390_skeys args; + + r = -EFAULT; + if (copy_from_user(&args, argp, + sizeof(struct kvm_s390_skeys))) + break; + r = kvm_s390_get_skeys(kvm, &args); + break; + } + case KVM_S390_SET_SKEYS: { + struct kvm_s390_skeys args; + + r = -EFAULT; + if (copy_from_user(&args, argp, + sizeof(struct kvm_s390_skeys))) + break; + r = kvm_s390_set_skeys(kvm, &args); + break; + } default: r = -ENOTTY; } @@ -887,7 +1039,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm->arch.dbf = debug_register(debug_name, 8, 2, 8 * sizeof(long)); if (!kvm->arch.dbf) - goto out_nodbf; + goto out_err; /* * The architectural maximum amount of facilities is 16 kbit. To store @@ -899,7 +1051,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm->arch.model.fac = (struct kvm_s390_fac *) get_zeroed_page(GFP_KERNEL | GFP_DMA); if (!kvm->arch.model.fac) - goto out_nofac; + goto out_err; /* Populate the facility mask initially. */ memcpy(kvm->arch.model.fac->mask, S390_lowcore.stfle_fac_list, @@ -919,10 +1071,11 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm->arch.model.ibc = sclp_get_ibc() & 0x0fff; if (kvm_s390_crypto_init(kvm) < 0) - goto out_crypto; + goto out_err; spin_lock_init(&kvm->arch.float_int.lock); - INIT_LIST_HEAD(&kvm->arch.float_int.list); + for (i = 0; i < FIRQ_LIST_COUNT; i++) + INIT_LIST_HEAD(&kvm->arch.float_int.lists[i]); init_waitqueue_head(&kvm->arch.ipte_wq); mutex_init(&kvm->arch.ipte_mutex); @@ -934,7 +1087,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) } else { kvm->arch.gmap = gmap_alloc(current->mm, (1UL << 44) - 1); if (!kvm->arch.gmap) - goto out_nogmap; + goto out_err; kvm->arch.gmap->private = kvm; kvm->arch.gmap->pfault_enabled = 0; } @@ -946,15 +1099,11 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) spin_lock_init(&kvm->arch.start_stop_lock); return 0; -out_nogmap: +out_err: kfree(kvm->arch.crypto.crycb); -out_crypto: free_page((unsigned long)kvm->arch.model.fac); -out_nofac: debug_unregister(kvm->arch.dbf); -out_nodbf: free_page((unsigned long)(kvm->arch.sca)); -out_err: return rc; } @@ -1034,6 +1183,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) KVM_SYNC_CRS | KVM_SYNC_ARCH0 | KVM_SYNC_PFAULT; + if (test_kvm_facility(vcpu->kvm, 129)) + vcpu->run->kvm_valid_regs |= KVM_SYNC_VRS; if (kvm_is_ucontrol(vcpu->kvm)) return __kvm_ucontrol_vcpu_init(vcpu); @@ -1044,10 +1195,18 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { save_fp_ctl(&vcpu->arch.host_fpregs.fpc); - save_fp_regs(vcpu->arch.host_fpregs.fprs); + if (test_kvm_facility(vcpu->kvm, 129)) + save_vx_regs((__vector128 *)&vcpu->arch.host_vregs->vrs); + else + save_fp_regs(vcpu->arch.host_fpregs.fprs); save_access_regs(vcpu->arch.host_acrs); - restore_fp_ctl(&vcpu->arch.guest_fpregs.fpc); - restore_fp_regs(vcpu->arch.guest_fpregs.fprs); + if (test_kvm_facility(vcpu->kvm, 129)) { + restore_fp_ctl(&vcpu->run->s.regs.fpc); + restore_vx_regs((__vector128 *)&vcpu->run->s.regs.vrs); + } else { + restore_fp_ctl(&vcpu->arch.guest_fpregs.fpc); + restore_fp_regs(vcpu->arch.guest_fpregs.fprs); + } restore_access_regs(vcpu->run->s.regs.acrs); gmap_enable(vcpu->arch.gmap); atomic_set_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags); @@ -1057,11 +1216,19 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags); gmap_disable(vcpu->arch.gmap); - save_fp_ctl(&vcpu->arch.guest_fpregs.fpc); - save_fp_regs(vcpu->arch.guest_fpregs.fprs); + if (test_kvm_facility(vcpu->kvm, 129)) { + save_fp_ctl(&vcpu->run->s.regs.fpc); + save_vx_regs((__vector128 *)&vcpu->run->s.regs.vrs); + } else { + save_fp_ctl(&vcpu->arch.guest_fpregs.fpc); + save_fp_regs(vcpu->arch.guest_fpregs.fprs); + } save_access_regs(vcpu->run->s.regs.acrs); restore_fp_ctl(&vcpu->arch.host_fpregs.fpc); - restore_fp_regs(vcpu->arch.host_fpregs.fprs); + if (test_kvm_facility(vcpu->kvm, 129)) + restore_vx_regs((__vector128 *)&vcpu->arch.host_vregs->vrs); + else + restore_fp_regs(vcpu->arch.host_fpregs.fprs); restore_access_regs(vcpu->arch.host_acrs); } @@ -1129,6 +1296,15 @@ int kvm_s390_vcpu_setup_cmma(struct kvm_vcpu *vcpu) return 0; } +static void kvm_s390_vcpu_setup_model(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_cpu_model *model = &vcpu->kvm->arch.model; + + vcpu->arch.cpu_id = model->cpu_id; + vcpu->arch.sie_block->ibc = model->ibc; + vcpu->arch.sie_block->fac = (int) (long) model->fac->list; +} + int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) { int rc = 0; @@ -1137,6 +1313,8 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) CPUSTAT_SM | CPUSTAT_STOPPED | CPUSTAT_GED); + kvm_s390_vcpu_setup_model(vcpu); + vcpu->arch.sie_block->ecb = 6; if (test_kvm_facility(vcpu->kvm, 50) && test_kvm_facility(vcpu->kvm, 73)) vcpu->arch.sie_block->ecb |= 0x10; @@ -1147,8 +1325,11 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) vcpu->arch.sie_block->eca |= 1; if (sclp_has_sigpif()) vcpu->arch.sie_block->eca |= 0x10000000U; - vcpu->arch.sie_block->ictl |= ICTL_ISKE | ICTL_SSKE | ICTL_RRBE | - ICTL_TPROT; + if (test_kvm_facility(vcpu->kvm, 129)) { + vcpu->arch.sie_block->eca |= 0x00020000; + vcpu->arch.sie_block->ecd |= 0x20000000; + } + vcpu->arch.sie_block->ictl |= ICTL_ISKE | ICTL_SSKE | ICTL_RRBE; if (kvm_s390_cmma_enabled(vcpu->kvm)) { rc = kvm_s390_vcpu_setup_cmma(vcpu); @@ -1158,11 +1339,6 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); vcpu->arch.ckc_timer.function = kvm_s390_idle_wakeup; - mutex_lock(&vcpu->kvm->lock); - vcpu->arch.cpu_id = vcpu->kvm->arch.model.cpu_id; - vcpu->arch.sie_block->ibc = vcpu->kvm->arch.model.ibc; - mutex_unlock(&vcpu->kvm->lock); - kvm_s390_vcpu_crypto_setup(vcpu); return rc; @@ -1190,6 +1366,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, vcpu->arch.sie_block = &sie_page->sie_block; vcpu->arch.sie_block->itdba = (unsigned long) &sie_page->itdb; + vcpu->arch.host_vregs = &sie_page->vregs; vcpu->arch.sie_block->icpua = id; if (!kvm_is_ucontrol(kvm)) { @@ -1205,7 +1382,6 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, vcpu->arch.sie_block->scaol = (__u32)(__u64)kvm->arch.sca; set_bit(63 - id, (unsigned long *) &kvm->arch.sca->mcn); } - vcpu->arch.sie_block->fac = (int) (long) kvm->arch.model.fac->list; spin_lock_init(&vcpu->arch.local_int.lock); vcpu->arch.local_int.float_int = &kvm->arch.float_int; @@ -1725,6 +1901,31 @@ static int vcpu_pre_run(struct kvm_vcpu *vcpu) return 0; } +static int vcpu_post_run_fault_in_sie(struct kvm_vcpu *vcpu) +{ + psw_t *psw = &vcpu->arch.sie_block->gpsw; + u8 opcode; + int rc; + + VCPU_EVENT(vcpu, 3, "%s", "fault in sie instruction"); + trace_kvm_s390_sie_fault(vcpu); + + /* + * We want to inject an addressing exception, which is defined as a + * suppressing or terminating exception. However, since we came here + * by a DAT access exception, the PSW still points to the faulting + * instruction since DAT exceptions are nullifying. So we've got + * to look up the current opcode to get the length of the instruction + * to be able to forward the PSW. + */ + rc = read_guest(vcpu, psw->addr, 0, &opcode, 1); + if (rc) + return kvm_s390_inject_prog_cond(vcpu, rc); + psw->addr = __rewind_psw(*psw, -insn_length(opcode)); + + return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); +} + static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason) { int rc = -1; @@ -1756,11 +1957,8 @@ static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason) } } - if (rc == -1) { - VCPU_EVENT(vcpu, 3, "%s", "fault in sie instruction"); - trace_kvm_s390_sie_fault(vcpu); - rc = kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); - } + if (rc == -1) + rc = vcpu_post_run_fault_in_sie(vcpu); memcpy(&vcpu->run->s.regs.gprs[14], &vcpu->arch.sie_block->gg14, 16); @@ -1976,6 +2174,35 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr) return kvm_s390_store_status_unloaded(vcpu, addr); } +/* + * store additional status at address + */ +int kvm_s390_store_adtl_status_unloaded(struct kvm_vcpu *vcpu, + unsigned long gpa) +{ + /* Only bits 0-53 are used for address formation */ + if (!(gpa & ~0x3ff)) + return 0; + + return write_guest_abs(vcpu, gpa & ~0x3ff, + (void *)&vcpu->run->s.regs.vrs, 512); +} + +int kvm_s390_vcpu_store_adtl_status(struct kvm_vcpu *vcpu, unsigned long addr) +{ + if (!test_kvm_facility(vcpu->kvm, 129)) + return 0; + + /* + * The guest VXRS are in the host VXRs due to the lazy + * copying in vcpu load/put. Let's update our copies before we save + * it into the save area. + */ + save_vx_regs((__vector128 *)&vcpu->run->s.regs.vrs); + + return kvm_s390_store_adtl_status_unloaded(vcpu, addr); +} + static void __disable_ibs_on_vcpu(struct kvm_vcpu *vcpu) { kvm_check_request(KVM_REQ_ENABLE_IBS, vcpu); @@ -2100,6 +2327,65 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, return r; } +static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu, + struct kvm_s390_mem_op *mop) +{ + void __user *uaddr = (void __user *)mop->buf; + void *tmpbuf = NULL; + int r, srcu_idx; + const u64 supported_flags = KVM_S390_MEMOP_F_INJECT_EXCEPTION + | KVM_S390_MEMOP_F_CHECK_ONLY; + + if (mop->flags & ~supported_flags) + return -EINVAL; + + if (mop->size > MEM_OP_MAX_SIZE) + return -E2BIG; + + if (!(mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY)) { + tmpbuf = vmalloc(mop->size); + if (!tmpbuf) + return -ENOMEM; + } + + srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + + switch (mop->op) { + case KVM_S390_MEMOP_LOGICAL_READ: + if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) { + r = check_gva_range(vcpu, mop->gaddr, mop->ar, mop->size, false); + break; + } + r = read_guest(vcpu, mop->gaddr, mop->ar, tmpbuf, mop->size); + if (r == 0) { + if (copy_to_user(uaddr, tmpbuf, mop->size)) + r = -EFAULT; + } + break; + case KVM_S390_MEMOP_LOGICAL_WRITE: + if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) { + r = check_gva_range(vcpu, mop->gaddr, mop->ar, mop->size, true); + break; + } + if (copy_from_user(tmpbuf, uaddr, mop->size)) { + r = -EFAULT; + break; + } + r = write_guest(vcpu, mop->gaddr, mop->ar, tmpbuf, mop->size); + break; + default: + r = -EINVAL; + } + + srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx); + + if (r > 0 && (mop->flags & KVM_S390_MEMOP_F_INJECT_EXCEPTION) != 0) + kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm); + + vfree(tmpbuf); + return r; +} + long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -2109,6 +2395,15 @@ long kvm_arch_vcpu_ioctl(struct file *filp, long r; switch (ioctl) { + case KVM_S390_IRQ: { + struct kvm_s390_irq s390irq; + + r = -EFAULT; + if (copy_from_user(&s390irq, argp, sizeof(s390irq))) + break; + r = kvm_s390_inject_vcpu(vcpu, &s390irq); + break; + } case KVM_S390_INTERRUPT: { struct kvm_s390_interrupt s390int; struct kvm_s390_irq s390irq; @@ -2199,6 +2494,47 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap); break; } + case KVM_S390_MEM_OP: { + struct kvm_s390_mem_op mem_op; + + if (copy_from_user(&mem_op, argp, sizeof(mem_op)) == 0) + r = kvm_s390_guest_mem_op(vcpu, &mem_op); + else + r = -EFAULT; + break; + } + case KVM_S390_SET_IRQ_STATE: { + struct kvm_s390_irq_state irq_state; + + r = -EFAULT; + if (copy_from_user(&irq_state, argp, sizeof(irq_state))) + break; + if (irq_state.len > VCPU_IRQS_MAX_BUF || + irq_state.len == 0 || + irq_state.len % sizeof(struct kvm_s390_irq) > 0) { + r = -EINVAL; + break; + } + r = kvm_s390_set_irq_state(vcpu, + (void __user *) irq_state.buf, + irq_state.len); + break; + } + case KVM_S390_GET_IRQ_STATE: { + struct kvm_s390_irq_state irq_state; + + r = -EFAULT; + if (copy_from_user(&irq_state, argp, sizeof(irq_state))) + break; + if (irq_state.len == 0) { + r = -EINVAL; + break; + } + r = kvm_s390_get_irq_state(vcpu, + (__u8 __user *) irq_state.buf, + irq_state.len); + break; + } default: r = -ENOTTY; } diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index c34109aa552d..ca108b90ae56 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -70,16 +70,22 @@ static inline void kvm_s390_set_prefix(struct kvm_vcpu *vcpu, u32 prefix) kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu); } -static inline u64 kvm_s390_get_base_disp_s(struct kvm_vcpu *vcpu) +typedef u8 __bitwise ar_t; + +static inline u64 kvm_s390_get_base_disp_s(struct kvm_vcpu *vcpu, ar_t *ar) { u32 base2 = vcpu->arch.sie_block->ipb >> 28; u32 disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16); + if (ar) + *ar = base2; + return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2; } static inline void kvm_s390_get_base_disp_sse(struct kvm_vcpu *vcpu, - u64 *address1, u64 *address2) + u64 *address1, u64 *address2, + ar_t *ar_b1, ar_t *ar_b2) { u32 base1 = (vcpu->arch.sie_block->ipb & 0xf0000000) >> 28; u32 disp1 = (vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16; @@ -88,6 +94,11 @@ static inline void kvm_s390_get_base_disp_sse(struct kvm_vcpu *vcpu, *address1 = (base1 ? vcpu->run->s.regs.gprs[base1] : 0) + disp1; *address2 = (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2; + + if (ar_b1) + *ar_b1 = base1; + if (ar_b2) + *ar_b2 = base2; } static inline void kvm_s390_get_regs_rre(struct kvm_vcpu *vcpu, int *r1, int *r2) @@ -98,7 +109,7 @@ static inline void kvm_s390_get_regs_rre(struct kvm_vcpu *vcpu, int *r1, int *r2 *r2 = (vcpu->arch.sie_block->ipb & 0x000f0000) >> 16; } -static inline u64 kvm_s390_get_base_disp_rsy(struct kvm_vcpu *vcpu) +static inline u64 kvm_s390_get_base_disp_rsy(struct kvm_vcpu *vcpu, ar_t *ar) { u32 base2 = vcpu->arch.sie_block->ipb >> 28; u32 disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16) + @@ -107,14 +118,20 @@ static inline u64 kvm_s390_get_base_disp_rsy(struct kvm_vcpu *vcpu) if (disp2 & 0x80000) disp2+=0xfff00000; + if (ar) + *ar = base2; + return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + (long)(int)disp2; } -static inline u64 kvm_s390_get_base_disp_rs(struct kvm_vcpu *vcpu) +static inline u64 kvm_s390_get_base_disp_rs(struct kvm_vcpu *vcpu, ar_t *ar) { u32 base2 = vcpu->arch.sie_block->ipb >> 28; u32 disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16); + if (ar) + *ar = base2; + return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2; } @@ -125,13 +142,24 @@ static inline void kvm_s390_set_psw_cc(struct kvm_vcpu *vcpu, unsigned long cc) vcpu->arch.sie_block->gpsw.mask |= cc << 44; } -/* test availability of facility in a kvm intance */ +/* test availability of facility in a kvm instance */ static inline int test_kvm_facility(struct kvm *kvm, unsigned long nr) { return __test_facility(nr, kvm->arch.model.fac->mask) && __test_facility(nr, kvm->arch.model.fac->list); } +static inline int set_kvm_facility(u64 *fac_list, unsigned long nr) +{ + unsigned char *ptr; + + if (nr >= MAX_FACILITY_BIT) + return -EINVAL; + ptr = (unsigned char *) fac_list + (nr >> 3); + *ptr |= (0x80UL >> (nr & 7)); + return 0; +} + /* are cpu states controlled by user space */ static inline int kvm_s390_user_cpu_state_ctrl(struct kvm *kvm) { @@ -150,9 +178,9 @@ int __must_check kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq); int __must_check kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code); struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm, - u64 cr6, u64 schid); -void kvm_s390_reinject_io_int(struct kvm *kvm, - struct kvm_s390_interrupt_info *inti); + u64 isc_mask, u32 schid); +int kvm_s390_reinject_io_int(struct kvm *kvm, + struct kvm_s390_interrupt_info *inti); int kvm_s390_mask_adapter(struct kvm *kvm, unsigned int id, bool masked); /* implemented in intercept.c */ @@ -177,7 +205,10 @@ int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu); /* implemented in kvm-s390.c */ long kvm_arch_fault_in_page(struct kvm_vcpu *vcpu, gpa_t gpa, int writable); int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long addr); +int kvm_s390_store_adtl_status_unloaded(struct kvm_vcpu *vcpu, + unsigned long addr); int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr); +int kvm_s390_vcpu_store_adtl_status(struct kvm_vcpu *vcpu, unsigned long addr); void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu); void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu); void s390_vcpu_block(struct kvm_vcpu *vcpu); @@ -241,6 +272,10 @@ int kvm_s390_ext_call_pending(struct kvm_vcpu *vcpu); extern struct kvm_device_ops kvm_flic_ops; int kvm_s390_is_stop_irq_pending(struct kvm_vcpu *vcpu); void kvm_s390_clear_stop_irq(struct kvm_vcpu *vcpu); +int kvm_s390_set_irq_state(struct kvm_vcpu *vcpu, + void __user *buf, int len); +int kvm_s390_get_irq_state(struct kvm_vcpu *vcpu, + __u8 __user *buf, int len); /* implemented in guestdbg.c */ void kvm_s390_backup_guest_per_regs(struct kvm_vcpu *vcpu); diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index 351116939ea2..d22d8ee1ff9d 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -36,15 +36,16 @@ static int handle_set_clock(struct kvm_vcpu *vcpu) struct kvm_vcpu *cpup; s64 hostclk, val; int i, rc; + ar_t ar; u64 op2; if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - op2 = kvm_s390_get_base_disp_s(vcpu); + op2 = kvm_s390_get_base_disp_s(vcpu, &ar); if (op2 & 7) /* Operand must be on a doubleword boundary */ return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - rc = read_guest(vcpu, op2, &val, sizeof(val)); + rc = read_guest(vcpu, op2, ar, &val, sizeof(val)); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); @@ -68,20 +69,21 @@ static int handle_set_prefix(struct kvm_vcpu *vcpu) u64 operand2; u32 address; int rc; + ar_t ar; vcpu->stat.instruction_spx++; if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - operand2 = kvm_s390_get_base_disp_s(vcpu); + operand2 = kvm_s390_get_base_disp_s(vcpu, &ar); /* must be word boundary */ if (operand2 & 3) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); /* get the value */ - rc = read_guest(vcpu, operand2, &address, sizeof(address)); + rc = read_guest(vcpu, operand2, ar, &address, sizeof(address)); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); @@ -107,13 +109,14 @@ static int handle_store_prefix(struct kvm_vcpu *vcpu) u64 operand2; u32 address; int rc; + ar_t ar; vcpu->stat.instruction_stpx++; if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - operand2 = kvm_s390_get_base_disp_s(vcpu); + operand2 = kvm_s390_get_base_disp_s(vcpu, &ar); /* must be word boundary */ if (operand2 & 3) @@ -122,7 +125,7 @@ static int handle_store_prefix(struct kvm_vcpu *vcpu) address = kvm_s390_get_prefix(vcpu); /* get the value */ - rc = write_guest(vcpu, operand2, &address, sizeof(address)); + rc = write_guest(vcpu, operand2, ar, &address, sizeof(address)); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); @@ -136,18 +139,19 @@ static int handle_store_cpu_address(struct kvm_vcpu *vcpu) u16 vcpu_id = vcpu->vcpu_id; u64 ga; int rc; + ar_t ar; vcpu->stat.instruction_stap++; if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - ga = kvm_s390_get_base_disp_s(vcpu); + ga = kvm_s390_get_base_disp_s(vcpu, &ar); if (ga & 1) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - rc = write_guest(vcpu, ga, &vcpu_id, sizeof(vcpu_id)); + rc = write_guest(vcpu, ga, ar, &vcpu_id, sizeof(vcpu_id)); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); @@ -207,7 +211,7 @@ static int handle_test_block(struct kvm_vcpu *vcpu) kvm_s390_get_regs_rre(vcpu, NULL, ®2); addr = vcpu->run->s.regs.gprs[reg2] & PAGE_MASK; addr = kvm_s390_logical_to_effective(vcpu, addr); - if (kvm_s390_check_low_addr_protection(vcpu, addr)) + if (kvm_s390_check_low_addr_prot_real(vcpu, addr)) return kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm); addr = kvm_s390_real_to_abs(vcpu, addr); @@ -229,18 +233,20 @@ static int handle_tpi(struct kvm_vcpu *vcpu) struct kvm_s390_interrupt_info *inti; unsigned long len; u32 tpi_data[3]; - int cc, rc; + int rc; u64 addr; + ar_t ar; - rc = 0; - addr = kvm_s390_get_base_disp_s(vcpu); + addr = kvm_s390_get_base_disp_s(vcpu, &ar); if (addr & 3) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - cc = 0; + inti = kvm_s390_get_io_int(vcpu->kvm, vcpu->arch.sie_block->gcr[6], 0); - if (!inti) - goto no_interrupt; - cc = 1; + if (!inti) { + kvm_s390_set_psw_cc(vcpu, 0); + return 0; + } + tpi_data[0] = inti->io.subchannel_id << 16 | inti->io.subchannel_nr; tpi_data[1] = inti->io.io_int_parm; tpi_data[2] = inti->io.io_int_word; @@ -250,40 +256,51 @@ static int handle_tpi(struct kvm_vcpu *vcpu) * provided area. */ len = sizeof(tpi_data) - 4; - rc = write_guest(vcpu, addr, &tpi_data, len); - if (rc) - return kvm_s390_inject_prog_cond(vcpu, rc); + rc = write_guest(vcpu, addr, ar, &tpi_data, len); + if (rc) { + rc = kvm_s390_inject_prog_cond(vcpu, rc); + goto reinject_interrupt; + } } else { /* * Store the three-word I/O interruption code into * the appropriate lowcore area. */ len = sizeof(tpi_data); - if (write_guest_lc(vcpu, __LC_SUBCHANNEL_ID, &tpi_data, len)) + if (write_guest_lc(vcpu, __LC_SUBCHANNEL_ID, &tpi_data, len)) { + /* failed writes to the low core are not recoverable */ rc = -EFAULT; + goto reinject_interrupt; + } } + + /* irq was successfully handed to the guest */ + kfree(inti); + kvm_s390_set_psw_cc(vcpu, 1); + return 0; +reinject_interrupt: /* * If we encounter a problem storing the interruption code, the * instruction is suppressed from the guest's view: reinject the * interrupt. */ - if (!rc) + if (kvm_s390_reinject_io_int(vcpu->kvm, inti)) { kfree(inti); - else - kvm_s390_reinject_io_int(vcpu->kvm, inti); -no_interrupt: - /* Set condition code and we're done. */ - if (!rc) - kvm_s390_set_psw_cc(vcpu, cc); + rc = -EFAULT; + } + /* don't set the cc, a pgm irq was injected or we drop to user space */ return rc ? -EFAULT : 0; } static int handle_tsch(struct kvm_vcpu *vcpu) { - struct kvm_s390_interrupt_info *inti; + struct kvm_s390_interrupt_info *inti = NULL; + const u64 isc_mask = 0xffUL << 24; /* all iscs set */ - inti = kvm_s390_get_io_int(vcpu->kvm, 0, - vcpu->run->s.regs.gprs[1]); + /* a valid schid has at least one bit set */ + if (vcpu->run->s.regs.gprs[1]) + inti = kvm_s390_get_io_int(vcpu->kvm, isc_mask, + vcpu->run->s.regs.gprs[1]); /* * Prepare exit to userspace. @@ -386,15 +403,16 @@ int kvm_s390_handle_lpsw(struct kvm_vcpu *vcpu) psw_compat_t new_psw; u64 addr; int rc; + ar_t ar; if (gpsw->mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - addr = kvm_s390_get_base_disp_s(vcpu); + addr = kvm_s390_get_base_disp_s(vcpu, &ar); if (addr & 7) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - rc = read_guest(vcpu, addr, &new_psw, sizeof(new_psw)); + rc = read_guest(vcpu, addr, ar, &new_psw, sizeof(new_psw)); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); if (!(new_psw.mask & PSW32_MASK_BASE)) @@ -412,14 +430,15 @@ static int handle_lpswe(struct kvm_vcpu *vcpu) psw_t new_psw; u64 addr; int rc; + ar_t ar; if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - addr = kvm_s390_get_base_disp_s(vcpu); + addr = kvm_s390_get_base_disp_s(vcpu, &ar); if (addr & 7) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - rc = read_guest(vcpu, addr, &new_psw, sizeof(new_psw)); + rc = read_guest(vcpu, addr, ar, &new_psw, sizeof(new_psw)); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); vcpu->arch.sie_block->gpsw = new_psw; @@ -433,18 +452,19 @@ static int handle_stidp(struct kvm_vcpu *vcpu) u64 stidp_data = vcpu->arch.stidp_data; u64 operand2; int rc; + ar_t ar; vcpu->stat.instruction_stidp++; if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - operand2 = kvm_s390_get_base_disp_s(vcpu); + operand2 = kvm_s390_get_base_disp_s(vcpu, &ar); if (operand2 & 7) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - rc = write_guest(vcpu, operand2, &stidp_data, sizeof(stidp_data)); + rc = write_guest(vcpu, operand2, ar, &stidp_data, sizeof(stidp_data)); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); @@ -467,6 +487,7 @@ static void handle_stsi_3_2_2(struct kvm_vcpu *vcpu, struct sysinfo_3_2_2 *mem) for (n = mem->count - 1; n > 0 ; n--) memcpy(&mem->vm[n], &mem->vm[n - 1], sizeof(mem->vm[0])); + memset(&mem->vm[0], 0, sizeof(mem->vm[0])); mem->vm[0].cpus_total = cpus; mem->vm[0].cpus_configured = cpus; mem->vm[0].cpus_standby = 0; @@ -478,6 +499,17 @@ static void handle_stsi_3_2_2(struct kvm_vcpu *vcpu, struct sysinfo_3_2_2 *mem) ASCEBC(mem->vm[0].cpi, 16); } +static void insert_stsi_usr_data(struct kvm_vcpu *vcpu, u64 addr, ar_t ar, + u8 fc, u8 sel1, u16 sel2) +{ + vcpu->run->exit_reason = KVM_EXIT_S390_STSI; + vcpu->run->s390_stsi.addr = addr; + vcpu->run->s390_stsi.ar = ar; + vcpu->run->s390_stsi.fc = fc; + vcpu->run->s390_stsi.sel1 = sel1; + vcpu->run->s390_stsi.sel2 = sel2; +} + static int handle_stsi(struct kvm_vcpu *vcpu) { int fc = (vcpu->run->s.regs.gprs[0] & 0xf0000000) >> 28; @@ -486,6 +518,7 @@ static int handle_stsi(struct kvm_vcpu *vcpu) unsigned long mem = 0; u64 operand2; int rc = 0; + ar_t ar; vcpu->stat.instruction_stsi++; VCPU_EVENT(vcpu, 4, "stsi: fc: %x sel1: %x sel2: %x", fc, sel1, sel2); @@ -508,7 +541,7 @@ static int handle_stsi(struct kvm_vcpu *vcpu) return 0; } - operand2 = kvm_s390_get_base_disp_s(vcpu); + operand2 = kvm_s390_get_base_disp_s(vcpu, &ar); if (operand2 & 0xfff) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); @@ -532,16 +565,20 @@ static int handle_stsi(struct kvm_vcpu *vcpu) break; } - rc = write_guest(vcpu, operand2, (void *)mem, PAGE_SIZE); + rc = write_guest(vcpu, operand2, ar, (void *)mem, PAGE_SIZE); if (rc) { rc = kvm_s390_inject_prog_cond(vcpu, rc); goto out; } + if (vcpu->kvm->arch.user_stsi) { + insert_stsi_usr_data(vcpu, operand2, ar, fc, sel1, sel2); + rc = -EREMOTE; + } trace_kvm_s390_handle_stsi(vcpu, fc, sel1, sel2, operand2); free_page(mem); kvm_s390_set_psw_cc(vcpu, 0); vcpu->run->s.regs.gprs[0] = 0; - return 0; + return rc; out_no_data: kvm_s390_set_psw_cc(vcpu, 3); out: @@ -670,7 +707,7 @@ static int handle_pfmf(struct kvm_vcpu *vcpu) } if (vcpu->run->s.regs.gprs[reg1] & PFMF_CF) { - if (kvm_s390_check_low_addr_protection(vcpu, start)) + if (kvm_s390_check_low_addr_prot_real(vcpu, start)) return kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm); } @@ -776,13 +813,14 @@ int kvm_s390_handle_lctl(struct kvm_vcpu *vcpu) int reg, rc, nr_regs; u32 ctl_array[16]; u64 ga; + ar_t ar; vcpu->stat.instruction_lctl++; if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - ga = kvm_s390_get_base_disp_rs(vcpu); + ga = kvm_s390_get_base_disp_rs(vcpu, &ar); if (ga & 3) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); @@ -791,7 +829,7 @@ int kvm_s390_handle_lctl(struct kvm_vcpu *vcpu) trace_kvm_s390_handle_lctl(vcpu, 0, reg1, reg3, ga); nr_regs = ((reg3 - reg1) & 0xf) + 1; - rc = read_guest(vcpu, ga, ctl_array, nr_regs * sizeof(u32)); + rc = read_guest(vcpu, ga, ar, ctl_array, nr_regs * sizeof(u32)); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); reg = reg1; @@ -814,13 +852,14 @@ int kvm_s390_handle_stctl(struct kvm_vcpu *vcpu) int reg, rc, nr_regs; u32 ctl_array[16]; u64 ga; + ar_t ar; vcpu->stat.instruction_stctl++; if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - ga = kvm_s390_get_base_disp_rs(vcpu); + ga = kvm_s390_get_base_disp_rs(vcpu, &ar); if (ga & 3) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); @@ -836,7 +875,7 @@ int kvm_s390_handle_stctl(struct kvm_vcpu *vcpu) break; reg = (reg + 1) % 16; } while (1); - rc = write_guest(vcpu, ga, ctl_array, nr_regs * sizeof(u32)); + rc = write_guest(vcpu, ga, ar, ctl_array, nr_regs * sizeof(u32)); return rc ? kvm_s390_inject_prog_cond(vcpu, rc) : 0; } @@ -847,13 +886,14 @@ static int handle_lctlg(struct kvm_vcpu *vcpu) int reg, rc, nr_regs; u64 ctl_array[16]; u64 ga; + ar_t ar; vcpu->stat.instruction_lctlg++; if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - ga = kvm_s390_get_base_disp_rsy(vcpu); + ga = kvm_s390_get_base_disp_rsy(vcpu, &ar); if (ga & 7) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); @@ -862,7 +902,7 @@ static int handle_lctlg(struct kvm_vcpu *vcpu) trace_kvm_s390_handle_lctl(vcpu, 1, reg1, reg3, ga); nr_regs = ((reg3 - reg1) & 0xf) + 1; - rc = read_guest(vcpu, ga, ctl_array, nr_regs * sizeof(u64)); + rc = read_guest(vcpu, ga, ar, ctl_array, nr_regs * sizeof(u64)); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); reg = reg1; @@ -884,13 +924,14 @@ static int handle_stctg(struct kvm_vcpu *vcpu) int reg, rc, nr_regs; u64 ctl_array[16]; u64 ga; + ar_t ar; vcpu->stat.instruction_stctg++; if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - ga = kvm_s390_get_base_disp_rsy(vcpu); + ga = kvm_s390_get_base_disp_rsy(vcpu, &ar); if (ga & 7) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); @@ -906,7 +947,7 @@ static int handle_stctg(struct kvm_vcpu *vcpu) break; reg = (reg + 1) % 16; } while (1); - rc = write_guest(vcpu, ga, ctl_array, nr_regs * sizeof(u64)); + rc = write_guest(vcpu, ga, ar, ctl_array, nr_regs * sizeof(u64)); return rc ? kvm_s390_inject_prog_cond(vcpu, rc) : 0; } @@ -931,13 +972,14 @@ static int handle_tprot(struct kvm_vcpu *vcpu) unsigned long hva, gpa; int ret = 0, cc = 0; bool writable; + ar_t ar; vcpu->stat.instruction_tprot++; if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - kvm_s390_get_base_disp_sse(vcpu, &address1, &address2); + kvm_s390_get_base_disp_sse(vcpu, &address1, &address2, &ar, NULL); /* we only handle the Linux memory detection case: * access key == 0 @@ -946,11 +988,11 @@ static int handle_tprot(struct kvm_vcpu *vcpu) return -EOPNOTSUPP; if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_DAT) ipte_lock(vcpu); - ret = guest_translate_address(vcpu, address1, &gpa, 1); + ret = guest_translate_address(vcpu, address1, ar, &gpa, 1); if (ret == PGM_PROTECTION) { /* Write protected? Try again with read-only... */ cc = 1; - ret = guest_translate_address(vcpu, address1, &gpa, 0); + ret = guest_translate_address(vcpu, address1, ar, &gpa, 0); } if (ret) { if (ret == PGM_ADDRESSING || ret == PGM_TRANSLATION_SPEC) { diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c index 23b1e86b2122..72e58bd2bee7 100644 --- a/arch/s390/kvm/sigp.c +++ b/arch/s390/kvm/sigp.c @@ -393,6 +393,9 @@ static int handle_sigp_order_in_user_space(struct kvm_vcpu *vcpu, u8 order_code) case SIGP_STORE_STATUS_AT_ADDRESS: vcpu->stat.instruction_sigp_store_status++; break; + case SIGP_STORE_ADDITIONAL_STATUS: + vcpu->stat.instruction_sigp_store_adtl_status++; + break; case SIGP_SET_PREFIX: vcpu->stat.instruction_sigp_prefix++; break; @@ -431,7 +434,7 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu) if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - order_code = kvm_s390_get_base_disp_rs(vcpu); + order_code = kvm_s390_get_base_disp_rs(vcpu, NULL); if (handle_sigp_order_in_user_space(vcpu, order_code)) return -EOPNOTSUPP; @@ -473,7 +476,7 @@ int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu) int r3 = vcpu->arch.sie_block->ipa & 0x000f; u16 cpu_addr = vcpu->run->s.regs.gprs[r3]; struct kvm_vcpu *dest_vcpu; - u8 order_code = kvm_s390_get_base_disp_rs(vcpu); + u8 order_code = kvm_s390_get_base_disp_rs(vcpu, NULL); trace_kvm_s390_handle_sigp_pei(vcpu, order_code, cpu_addr); diff --git a/arch/sparc/include/asm/jump_label.h b/arch/sparc/include/asm/jump_label.h index ec2e2e2aba7d..cc9b04a2b11b 100644 --- a/arch/sparc/include/asm/jump_label.h +++ b/arch/sparc/include/asm/jump_label.h @@ -1,7 +1,7 @@ #ifndef _ASM_SPARC_JUMP_LABEL_H #define _ASM_SPARC_JUMP_LABEL_H -#ifdef __KERNEL__ +#ifndef __ASSEMBLY__ #include <linux/types.h> @@ -22,8 +22,6 @@ l_yes: return true; } -#endif /* __KERNEL__ */ - typedef u32 jump_label_t; struct jump_entry { @@ -32,4 +30,5 @@ struct jump_entry { jump_label_t key; }; +#endif /* __ASSEMBLY__ */ #endif diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c index 9ce5afe167ff..b36365f49478 100644 --- a/arch/sparc/kernel/pci.c +++ b/arch/sparc/kernel/pci.c @@ -639,10 +639,7 @@ static void pci_claim_bus_resources(struct pci_bus *bus) (unsigned long long)r->end, (unsigned int)r->flags); - if (pci_claim_resource(dev, i) == 0) - continue; - - pci_claim_bridge_resource(dev, i); + pci_claim_resource(dev, i); } } diff --git a/arch/sparc/kernel/time_32.c b/arch/sparc/kernel/time_32.c index 2f80d23a0a44..18147a5523d9 100644 --- a/arch/sparc/kernel/time_32.c +++ b/arch/sparc/kernel/time_32.c @@ -181,17 +181,13 @@ static struct clocksource timer_cs = { .rating = 100, .read = timer_cs_read, .mask = CLOCKSOURCE_MASK(64), - .shift = 2, .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; static __init int setup_timer_cs(void) { timer_cs_enabled = 1; - timer_cs.mult = clocksource_hz2mult(sparc_config.clock_rate, - timer_cs.shift); - - return clocksource_register(&timer_cs); + return clocksource_register_hz(&timer_cs, sparc_config.clock_rate); } #ifdef CONFIG_SMP diff --git a/arch/tile/kernel/time.c b/arch/tile/kernel/time.c index d412b0856c0a..00178ecf9aea 100644 --- a/arch/tile/kernel/time.c +++ b/arch/tile/kernel/time.c @@ -257,34 +257,34 @@ void update_vsyscall_tz(void) void update_vsyscall(struct timekeeper *tk) { - if (tk->tkr.clock != &cycle_counter_cs) + if (tk->tkr_mono.clock != &cycle_counter_cs) return; write_seqcount_begin(&vdso_data->tb_seq); - vdso_data->cycle_last = tk->tkr.cycle_last; - vdso_data->mask = tk->tkr.mask; - vdso_data->mult = tk->tkr.mult; - vdso_data->shift = tk->tkr.shift; + vdso_data->cycle_last = tk->tkr_mono.cycle_last; + vdso_data->mask = tk->tkr_mono.mask; + vdso_data->mult = tk->tkr_mono.mult; + vdso_data->shift = tk->tkr_mono.shift; vdso_data->wall_time_sec = tk->xtime_sec; - vdso_data->wall_time_snsec = tk->tkr.xtime_nsec; + vdso_data->wall_time_snsec = tk->tkr_mono.xtime_nsec; vdso_data->monotonic_time_sec = tk->xtime_sec + tk->wall_to_monotonic.tv_sec; - vdso_data->monotonic_time_snsec = tk->tkr.xtime_nsec + vdso_data->monotonic_time_snsec = tk->tkr_mono.xtime_nsec + ((u64)tk->wall_to_monotonic.tv_nsec - << tk->tkr.shift); + << tk->tkr_mono.shift); while (vdso_data->monotonic_time_snsec >= - (((u64)NSEC_PER_SEC) << tk->tkr.shift)) { + (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift)) { vdso_data->monotonic_time_snsec -= - ((u64)NSEC_PER_SEC) << tk->tkr.shift; + ((u64)NSEC_PER_SEC) << tk->tkr_mono.shift; vdso_data->monotonic_time_sec++; } vdso_data->wall_time_coarse_sec = tk->xtime_sec; - vdso_data->wall_time_coarse_nsec = (long)(tk->tkr.xtime_nsec >> - tk->tkr.shift); + vdso_data->wall_time_coarse_nsec = (long)(tk->tkr_mono.xtime_nsec >> + tk->tkr_mono.shift); vdso_data->monotonic_time_coarse_sec = vdso_data->wall_time_coarse_sec + tk->wall_to_monotonic.tv_sec; diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 8118e94d50ab..976b86a325e5 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -204,7 +204,6 @@ extern void clear_local_APIC(void); extern void disconnect_bsp_APIC(int virt_wire_setup); extern void disable_local_APIC(void); extern void lapic_shutdown(void); -extern int verify_local_APIC(void); extern void sync_Arb_IDs(void); extern void init_bsp_APIC(void); extern void setup_local_APIC(void); diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 25bce45c6fc4..3738b138b843 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -2,6 +2,8 @@ #define _ASM_X86_EFI_H #include <asm/i387.h> +#include <asm/pgtable.h> + /* * We map the EFI regions needed for runtime services non-contiguously, * with preserved alignment on virtual addresses starting from -4G down @@ -89,8 +91,8 @@ extern void __iomem *__init efi_ioremap(unsigned long addr, unsigned long size, extern struct efi_scratch efi_scratch; extern void __init efi_set_executable(efi_memory_desc_t *md, bool executable); extern int __init efi_memblock_x86_reserve_range(void); -extern void __init efi_call_phys_prolog(void); -extern void __init efi_call_phys_epilog(void); +extern pgd_t * __init efi_call_phys_prolog(void); +extern void __init efi_call_phys_epilog(pgd_t *save_pgd); extern void __init efi_unmap_memmap(void); extern void __init efi_memory_uc(u64 addr, unsigned long size); extern void __init efi_map_region(efi_memory_desc_t *md); diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h index 6a2cefb4395a..a4c1cf7e93f8 100644 --- a/arch/x86/include/asm/jump_label.h +++ b/arch/x86/include/asm/jump_label.h @@ -1,7 +1,7 @@ #ifndef _ASM_X86_JUMP_LABEL_H #define _ASM_X86_JUMP_LABEL_H -#ifdef __KERNEL__ +#ifndef __ASSEMBLY__ #include <linux/stringify.h> #include <linux/types.h> @@ -30,8 +30,6 @@ l_yes: return true; } -#endif /* __KERNEL__ */ - #ifdef CONFIG_X86_64 typedef u64 jump_label_t; #else @@ -44,4 +42,5 @@ struct jump_entry { jump_label_t key; }; +#endif /* __ASSEMBLY__ */ #endif diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index a236e39cc385..dea2e7e962e3 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -81,11 +81,6 @@ static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level) (base_gfn >> KVM_HPAGE_GFN_SHIFT(level)); } -#define SELECTOR_TI_MASK (1 << 2) -#define SELECTOR_RPL_MASK 0x03 - -#define IOPL_SHIFT 12 - #define KVM_PERMILLE_MMU_PAGES 20 #define KVM_MIN_ALLOC_MMU_PAGES 64 #define KVM_MMU_HASH_SHIFT 10 @@ -345,6 +340,7 @@ struct kvm_pmu { enum { KVM_DEBUGREG_BP_ENABLED = 1, KVM_DEBUGREG_WONT_EXIT = 2, + KVM_DEBUGREG_RELOAD = 4, }; struct kvm_vcpu_arch { @@ -431,6 +427,9 @@ struct kvm_vcpu_arch { int cpuid_nent; struct kvm_cpuid_entry2 cpuid_entries[KVM_MAX_CPUID_ENTRIES]; + + int maxphyaddr; + /* emulate context */ struct x86_emulate_ctxt emulate_ctxt; @@ -550,11 +549,20 @@ struct kvm_arch_memory_slot { struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1]; }; +/* + * We use as the mode the number of bits allocated in the LDR for the + * logical processor ID. It happens that these are all powers of two. + * This makes it is very easy to detect cases where the APICs are + * configured for multiple modes; in that case, we cannot use the map and + * hence cannot use kvm_irq_delivery_to_apic_fast either. + */ +#define KVM_APIC_MODE_XAPIC_CLUSTER 4 +#define KVM_APIC_MODE_XAPIC_FLAT 8 +#define KVM_APIC_MODE_X2APIC 16 + struct kvm_apic_map { struct rcu_head rcu; - u8 ldr_bits; - /* fields bellow are used to decode ldr values in different modes */ - u32 cid_shift, cid_mask, lid_mask, broadcast; + u8 mode; struct kvm_lapic *phys_map[256]; /* first index is cluster id second is cpu id in a cluster */ struct kvm_lapic *logical_map[16][16]; @@ -859,6 +867,8 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, void kvm_mmu_reset_context(struct kvm_vcpu *vcpu); void kvm_mmu_slot_remove_write_access(struct kvm *kvm, struct kvm_memory_slot *memslot); +void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, + struct kvm_memory_slot *memslot); void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, struct kvm_memory_slot *memslot); void kvm_mmu_slot_largepage_remove_write_access(struct kvm *kvm, @@ -933,6 +943,7 @@ struct x86_emulate_ctxt; int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port); void kvm_emulate_cpuid(struct kvm_vcpu *vcpu); int kvm_emulate_halt(struct kvm_vcpu *vcpu); +int kvm_vcpu_halt(struct kvm_vcpu *vcpu); int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu); void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); @@ -1128,7 +1139,6 @@ int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); -int cpuid_maxphyaddr(struct kvm_vcpu *vcpu); int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v); int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu); int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu); diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h index e62cf897f781..c1adf33fdd0d 100644 --- a/arch/x86/include/asm/kvm_para.h +++ b/arch/x86/include/asm/kvm_para.h @@ -115,7 +115,7 @@ static inline void kvm_spinlock_init(void) static inline bool kvm_para_available(void) { - return 0; + return false; } static inline unsigned int kvm_arch_para_features(void) diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h index a1410db38a1a..653dfa7662e1 100644 --- a/arch/x86/include/asm/mwait.h +++ b/arch/x86/include/asm/mwait.h @@ -30,6 +30,14 @@ static inline void __mwait(unsigned long eax, unsigned long ecx) :: "a" (eax), "c" (ecx)); } +static inline void __sti_mwait(unsigned long eax, unsigned long ecx) +{ + trace_hardirqs_on(); + /* "mwait %eax, %ecx;" */ + asm volatile("sti; .byte 0x0f, 0x01, 0xc9;" + :: "a" (eax), "c" (ecx)); +} + /* * This uses new MONITOR/MWAIT instructions on P4 processors with PNI, * which can obviate IPI to trigger checking of need_resched. diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index d6b078e9fa28..25b1cc07d496 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -95,6 +95,7 @@ unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src, struct pvclock_vsyscall_time_info { struct pvclock_vcpu_time_info pvti; + u32 migrate_count; } __attribute__((__aligned__(SMP_CACHE_BYTES))); #define PVTI_SIZE sizeof(struct pvclock_vsyscall_time_info) diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index 12a26b979bf1..f2f9b39b274a 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -231,6 +231,6 @@ __copy_from_user_inatomic_nocache(void *dst, const void __user *src, } unsigned long -copy_user_handle_tail(char *to, char *from, unsigned len, unsigned zerorest); +copy_user_handle_tail(char *to, char *from, unsigned len); #endif /* _ASM_X86_UACCESS_64_H */ diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h index c5f1a1deb91a..1fe92181ee9e 100644 --- a/arch/x86/include/uapi/asm/vmx.h +++ b/arch/x86/include/uapi/asm/vmx.h @@ -67,6 +67,7 @@ #define EXIT_REASON_EPT_VIOLATION 48 #define EXIT_REASON_EPT_MISCONFIG 49 #define EXIT_REASON_INVEPT 50 +#define EXIT_REASON_RDTSCP 51 #define EXIT_REASON_PREEMPTION_TIMER 52 #define EXIT_REASON_INVVPID 53 #define EXIT_REASON_WBINVD 54 diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index ad3639ae1b9b..dcb52850a28f 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1084,67 +1084,6 @@ void lapic_shutdown(void) local_irq_restore(flags); } -/* - * This is to verify that we're looking at a real local APIC. - * Check these against your board if the CPUs aren't getting - * started for no apparent reason. - */ -int __init verify_local_APIC(void) -{ - unsigned int reg0, reg1; - - /* - * The version register is read-only in a real APIC. - */ - reg0 = apic_read(APIC_LVR); - apic_printk(APIC_DEBUG, "Getting VERSION: %x\n", reg0); - apic_write(APIC_LVR, reg0 ^ APIC_LVR_MASK); - reg1 = apic_read(APIC_LVR); - apic_printk(APIC_DEBUG, "Getting VERSION: %x\n", reg1); - - /* - * The two version reads above should print the same - * numbers. If the second one is different, then we - * poke at a non-APIC. - */ - if (reg1 != reg0) - return 0; - - /* - * Check if the version looks reasonably. - */ - reg1 = GET_APIC_VERSION(reg0); - if (reg1 == 0x00 || reg1 == 0xff) - return 0; - reg1 = lapic_get_maxlvt(); - if (reg1 < 0x02 || reg1 == 0xff) - return 0; - - /* - * The ID register is read/write in a real APIC. - */ - reg0 = apic_read(APIC_ID); - apic_printk(APIC_DEBUG, "Getting ID: %x\n", reg0); - apic_write(APIC_ID, reg0 ^ apic->apic_id_mask); - reg1 = apic_read(APIC_ID); - apic_printk(APIC_DEBUG, "Getting ID: %x\n", reg1); - apic_write(APIC_ID, reg0); - if (reg1 != (reg0 ^ apic->apic_id_mask)) - return 0; - - /* - * The next two are just to see if we have sane values. - * They're only really relevant if we're in Virtual Wire - * compatibility mode, but most boxes are anymore. - */ - reg0 = apic_read(APIC_LVT0); - apic_printk(APIC_DEBUG, "Getting LVT0: %x\n", reg0); - reg1 = apic_read(APIC_LVT1); - apic_printk(APIC_DEBUG, "Getting LVT1: %x\n", reg1); - - return 1; -} - /** * sync_Arb_IDs - synchronize APIC bus arbitration IDs */ @@ -2283,7 +2222,6 @@ int __init APIC_init_uniprocessor(void) disable_ioapic_support(); default_setup_apic_routing(); - verify_local_APIC(); apic_bsp_setup(true); return 0; } diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 8e9dcfd630e4..c8d92950bc04 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -144,33 +144,60 @@ static void __init uv_set_apicid_hibit(void) static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id) { - int pnodeid, is_uv1, is_uv2, is_uv3; - - is_uv1 = !strcmp(oem_id, "SGI"); - is_uv2 = !strcmp(oem_id, "SGI2"); - is_uv3 = !strncmp(oem_id, "SGI3", 4); /* there are varieties of UV3 */ - if (is_uv1 || is_uv2 || is_uv3) { - uv_hub_info->hub_revision = - (is_uv1 ? UV1_HUB_REVISION_BASE : - (is_uv2 ? UV2_HUB_REVISION_BASE : - UV3_HUB_REVISION_BASE)); - pnodeid = early_get_pnodeid(); - early_get_apic_pnode_shift(); - x86_platform.is_untracked_pat_range = uv_is_untracked_pat_range; - x86_platform.nmi_init = uv_nmi_init; - if (!strcmp(oem_table_id, "UVL")) - uv_system_type = UV_LEGACY_APIC; - else if (!strcmp(oem_table_id, "UVX")) - uv_system_type = UV_X2APIC; - else if (!strcmp(oem_table_id, "UVH")) { - __this_cpu_write(x2apic_extra_bits, - pnodeid << uvh_apicid.s.pnode_shift); - uv_system_type = UV_NON_UNIQUE_APIC; - uv_set_apicid_hibit(); - return 1; - } + int pnodeid; + int uv_apic; + + if (strncmp(oem_id, "SGI", 3) != 0) + return 0; + + /* + * Determine UV arch type. + * SGI: UV100/1000 + * SGI2: UV2000/3000 + * SGI3: UV300 (truncated to 4 chars because of different varieties) + */ + uv_hub_info->hub_revision = + !strncmp(oem_id, "SGI3", 4) ? UV3_HUB_REVISION_BASE : + !strcmp(oem_id, "SGI2") ? UV2_HUB_REVISION_BASE : + !strcmp(oem_id, "SGI") ? UV1_HUB_REVISION_BASE : 0; + + if (uv_hub_info->hub_revision == 0) + goto badbios; + + pnodeid = early_get_pnodeid(); + early_get_apic_pnode_shift(); + x86_platform.is_untracked_pat_range = uv_is_untracked_pat_range; + x86_platform.nmi_init = uv_nmi_init; + + if (!strcmp(oem_table_id, "UVX")) { /* most common */ + uv_system_type = UV_X2APIC; + uv_apic = 0; + + } else if (!strcmp(oem_table_id, "UVH")) { /* only UV1 systems */ + uv_system_type = UV_NON_UNIQUE_APIC; + __this_cpu_write(x2apic_extra_bits, + pnodeid << uvh_apicid.s.pnode_shift); + uv_set_apicid_hibit(); + uv_apic = 1; + + } else if (!strcmp(oem_table_id, "UVL")) { /* only used for */ + uv_system_type = UV_LEGACY_APIC; /* very small systems */ + uv_apic = 0; + + } else { + goto badbios; } - return 0; + + pr_info("UV: OEM IDs %s/%s, System/HUB Types %d/%d, uv_apic %d\n", + oem_id, oem_table_id, uv_system_type, + uv_min_hub_revision_id, uv_apic); + + return uv_apic; + +badbios: + pr_err("UV: OEM_ID:%s OEM_TABLE_ID:%s\n", oem_id, oem_table_id); + pr_err("Current BIOS not supported, update kernel and/or BIOS\n"); + BUG(); } enum uv_system_type get_uv_system_type(void) @@ -854,10 +881,14 @@ void __init uv_system_init(void) unsigned long mmr_base, present, paddr; unsigned short pnode_mask; unsigned char n_lshift; - char *hub = (is_uv1_hub() ? "UV1" : - (is_uv2_hub() ? "UV2" : - "UV3")); + char *hub = (is_uv1_hub() ? "UV100/1000" : + (is_uv2_hub() ? "UV2000/3000" : + (is_uv3_hub() ? "UV300" : NULL))); + if (!hub) { + pr_err("UV: Unknown/unsupported UV hub\n"); + return; + } pr_info("UV: Found %s hub\n", hub); map_low_mmrs(); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 12b1cf606ddf..0c8992dbead5 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -9,7 +9,7 @@ #include <linux/sched.h> #include <linux/module.h> #include <linux/pm.h> -#include <linux/clockchips.h> +#include <linux/tick.h> #include <linux/random.h> #include <linux/user-return-notifier.h> #include <linux/dmi.h> @@ -24,6 +24,7 @@ #include <asm/syscalls.h> #include <asm/idle.h> #include <asm/uaccess.h> +#include <asm/mwait.h> #include <asm/i387.h> #include <asm/fpu-internal.h> #include <asm/debugreg.h> @@ -396,14 +397,11 @@ static void amd_e400_idle(void) if (!cpumask_test_cpu(cpu, amd_e400_c1e_mask)) { cpumask_set_cpu(cpu, amd_e400_c1e_mask); - /* - * Force broadcast so ACPI can not interfere. - */ - clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_FORCE, - &cpu); + /* Force broadcast so ACPI can not interfere. */ + tick_broadcast_force(); pr_info("Switch to broadcast mode on CPU%d\n", cpu); } - clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu); + tick_broadcast_enter(); default_idle(); @@ -412,12 +410,59 @@ static void amd_e400_idle(void) * called with interrupts disabled. */ local_irq_disable(); - clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu); + tick_broadcast_exit(); local_irq_enable(); } else default_idle(); } +/* + * Intel Core2 and older machines prefer MWAIT over HALT for C1. + * We can't rely on cpuidle installing MWAIT, because it will not load + * on systems that support only C1 -- so the boot default must be MWAIT. + * + * Some AMD machines are the opposite, they depend on using HALT. + * + * So for default C1, which is used during boot until cpuidle loads, + * use MWAIT-C1 on Intel HW that has it, else use HALT. + */ +static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c) +{ + if (c->x86_vendor != X86_VENDOR_INTEL) + return 0; + + if (!cpu_has(c, X86_FEATURE_MWAIT)) + return 0; + + return 1; +} + +/* + * MONITOR/MWAIT with no hints, used for default default C1 state. + * This invokes MWAIT with interrutps enabled and no flags, + * which is backwards compatible with the original MWAIT implementation. + */ + +static void mwait_idle(void) +{ + if (!current_set_polling_and_test()) { + if (this_cpu_has(X86_BUG_CLFLUSH_MONITOR)) { + smp_mb(); /* quirk */ + clflush((void *)¤t_thread_info()->flags); + smp_mb(); /* quirk */ + } + + __monitor((void *)¤t_thread_info()->flags, 0, 0); + if (!need_resched()) + __sti_mwait(0, 0); + else + local_irq_enable(); + } else { + local_irq_enable(); + } + __current_clr_polling(); +} + void select_idle_routine(const struct cpuinfo_x86 *c) { #ifdef CONFIG_SMP @@ -431,6 +476,9 @@ void select_idle_routine(const struct cpuinfo_x86 *c) /* E400: APIC timer interrupt does not wake up CPU from C1e */ pr_info("using AMD E400 aware idle routine\n"); x86_idle = amd_e400_idle; + } else if (prefer_mwait_c1_over_halt(c)) { + pr_info("using mwait in idle threads\n"); + x86_idle = mwait_idle; } else x86_idle = default_idle; } diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index 2f355d229a58..e5ecd20e72dd 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -141,7 +141,46 @@ void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock, set_normalized_timespec(ts, now.tv_sec, now.tv_nsec); } +static struct pvclock_vsyscall_time_info *pvclock_vdso_info; + +static struct pvclock_vsyscall_time_info * +pvclock_get_vsyscall_user_time_info(int cpu) +{ + if (!pvclock_vdso_info) { + BUG(); + return NULL; + } + + return &pvclock_vdso_info[cpu]; +} + +struct pvclock_vcpu_time_info *pvclock_get_vsyscall_time_info(int cpu) +{ + return &pvclock_get_vsyscall_user_time_info(cpu)->pvti; +} + #ifdef CONFIG_X86_64 +static int pvclock_task_migrate(struct notifier_block *nb, unsigned long l, + void *v) +{ + struct task_migration_notifier *mn = v; + struct pvclock_vsyscall_time_info *pvti; + + pvti = pvclock_get_vsyscall_user_time_info(mn->from_cpu); + + /* this is NULL when pvclock vsyscall is not initialized */ + if (unlikely(pvti == NULL)) + return NOTIFY_DONE; + + pvti->migrate_count++; + + return NOTIFY_DONE; +} + +static struct notifier_block pvclock_migrate = { + .notifier_call = pvclock_task_migrate, +}; + /* * Initialize the generic pvclock vsyscall state. This will allocate * a/some page(s) for the per-vcpu pvclock information, set up a @@ -155,12 +194,17 @@ int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i, WARN_ON (size != PVCLOCK_VSYSCALL_NR_PAGES*PAGE_SIZE); + pvclock_vdso_info = i; + for (idx = 0; idx <= (PVCLOCK_FIXMAP_END-PVCLOCK_FIXMAP_BEGIN); idx++) { __set_fixmap(PVCLOCK_FIXMAP_BEGIN + idx, __pa(i) + (idx*PAGE_SIZE), PAGE_KERNEL_VVAR); } + + register_task_migration_notifier(&pvclock_migrate); + return 0; } #endif diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 5b298a95d567..7035f6b21c3f 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1094,8 +1094,6 @@ static int __init smp_sanity_check(unsigned max_cpus) return SMP_NO_APIC; } - verify_local_APIC(); - /* * If SMP should be disabled, then really disable it! */ diff --git a/arch/x86/kernel/vsyscall_gtod.c b/arch/x86/kernel/vsyscall_gtod.c index c7d791f32b98..51e330416995 100644 --- a/arch/x86/kernel/vsyscall_gtod.c +++ b/arch/x86/kernel/vsyscall_gtod.c @@ -31,30 +31,30 @@ void update_vsyscall(struct timekeeper *tk) gtod_write_begin(vdata); /* copy vsyscall data */ - vdata->vclock_mode = tk->tkr.clock->archdata.vclock_mode; - vdata->cycle_last = tk->tkr.cycle_last; - vdata->mask = tk->tkr.mask; - vdata->mult = tk->tkr.mult; - vdata->shift = tk->tkr.shift; + vdata->vclock_mode = tk->tkr_mono.clock->archdata.vclock_mode; + vdata->cycle_last = tk->tkr_mono.cycle_last; + vdata->mask = tk->tkr_mono.mask; + vdata->mult = tk->tkr_mono.mult; + vdata->shift = tk->tkr_mono.shift; vdata->wall_time_sec = tk->xtime_sec; - vdata->wall_time_snsec = tk->tkr.xtime_nsec; + vdata->wall_time_snsec = tk->tkr_mono.xtime_nsec; vdata->monotonic_time_sec = tk->xtime_sec + tk->wall_to_monotonic.tv_sec; - vdata->monotonic_time_snsec = tk->tkr.xtime_nsec + vdata->monotonic_time_snsec = tk->tkr_mono.xtime_nsec + ((u64)tk->wall_to_monotonic.tv_nsec - << tk->tkr.shift); + << tk->tkr_mono.shift); while (vdata->monotonic_time_snsec >= - (((u64)NSEC_PER_SEC) << tk->tkr.shift)) { + (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift)) { vdata->monotonic_time_snsec -= - ((u64)NSEC_PER_SEC) << tk->tkr.shift; + ((u64)NSEC_PER_SEC) << tk->tkr_mono.shift; vdata->monotonic_time_sec++; } vdata->wall_time_coarse_sec = tk->xtime_sec; - vdata->wall_time_coarse_nsec = (long)(tk->tkr.xtime_nsec >> - tk->tkr.shift); + vdata->wall_time_coarse_nsec = (long)(tk->tkr_mono.xtime_nsec >> + tk->tkr_mono.shift); vdata->monotonic_time_coarse_sec = vdata->wall_time_coarse_sec + tk->wall_to_monotonic.tv_sec; diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 08f790dfadc9..16e8f962eaad 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -1,5 +1,5 @@ -ccflags-y += -Ivirt/kvm -Iarch/x86/kvm +ccflags-y += -Iarch/x86/kvm CFLAGS_x86.o := -I. CFLAGS_svm.o := -I. diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 8a80737ee6e6..59b69f6a2844 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -104,6 +104,9 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu) ((best->eax & 0xff00) >> 8) != 0) return -EINVAL; + /* Update physical-address width */ + vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); + kvm_pmu_cpuid_update(vcpu); return 0; } @@ -135,6 +138,21 @@ static void cpuid_fix_nx_cap(struct kvm_vcpu *vcpu) } } +int cpuid_query_maxphyaddr(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 0x80000000, 0); + if (!best || best->eax < 0x80000008) + goto not_found; + best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0); + if (best) + return best->eax & 0xff; +not_found: + return 36; +} +EXPORT_SYMBOL_GPL(cpuid_query_maxphyaddr); + /* when an old userspace process fills a new kernel module */ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid *cpuid, @@ -757,21 +775,6 @@ struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, } EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry); -int cpuid_maxphyaddr(struct kvm_vcpu *vcpu) -{ - struct kvm_cpuid_entry2 *best; - - best = kvm_find_cpuid_entry(vcpu, 0x80000000, 0); - if (!best || best->eax < 0x80000008) - goto not_found; - best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0); - if (best) - return best->eax & 0xff; -not_found: - return 36; -} -EXPORT_SYMBOL_GPL(cpuid_maxphyaddr); - /* * If no match is found, check whether we exceed the vCPU's limit * and return the content of the highest valid _standard_ leaf instead. diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 4452eedfaedd..c3b1ad9fca81 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -20,13 +20,19 @@ int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 __user *entries); void kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx); +int cpuid_query_maxphyaddr(struct kvm_vcpu *vcpu); + +static inline int cpuid_maxphyaddr(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.maxphyaddr; +} static inline bool guest_cpuid_has_xsave(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; if (!static_cpu_has(X86_FEATURE_XSAVE)) - return 0; + return false; best = kvm_find_cpuid_entry(vcpu, 1, 0); return best && (best->ecx & bit(X86_FEATURE_XSAVE)); diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 106c01557f2b..630bcb0d7a04 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -248,27 +248,7 @@ struct mode_dual { struct opcode mode64; }; -/* EFLAGS bit definitions. */ -#define EFLG_ID (1<<21) -#define EFLG_VIP (1<<20) -#define EFLG_VIF (1<<19) -#define EFLG_AC (1<<18) -#define EFLG_VM (1<<17) -#define EFLG_RF (1<<16) -#define EFLG_IOPL (3<<12) -#define EFLG_NT (1<<14) -#define EFLG_OF (1<<11) -#define EFLG_DF (1<<10) -#define EFLG_IF (1<<9) -#define EFLG_TF (1<<8) -#define EFLG_SF (1<<7) -#define EFLG_ZF (1<<6) -#define EFLG_AF (1<<4) -#define EFLG_PF (1<<2) -#define EFLG_CF (1<<0) - #define EFLG_RESERVED_ZEROS_MASK 0xffc0802a -#define EFLG_RESERVED_ONE_MASK 2 enum x86_transfer_type { X86_TRANSFER_NONE, @@ -317,7 +297,8 @@ static void invalidate_registers(struct x86_emulate_ctxt *ctxt) * These EFLAGS bits are restored from saved value during emulation, and * any changes are written back to the saved value after emulation. */ -#define EFLAGS_MASK (EFLG_OF|EFLG_SF|EFLG_ZF|EFLG_AF|EFLG_PF|EFLG_CF) +#define EFLAGS_MASK (X86_EFLAGS_OF|X86_EFLAGS_SF|X86_EFLAGS_ZF|X86_EFLAGS_AF|\ + X86_EFLAGS_PF|X86_EFLAGS_CF) #ifdef CONFIG_X86_64 #define ON64(x) x @@ -478,6 +459,25 @@ static void assign_masked(ulong *dest, ulong src, ulong mask) *dest = (*dest & ~mask) | (src & mask); } +static void assign_register(unsigned long *reg, u64 val, int bytes) +{ + /* The 4-byte case *is* correct: in 64-bit mode we zero-extend. */ + switch (bytes) { + case 1: + *(u8 *)reg = (u8)val; + break; + case 2: + *(u16 *)reg = (u16)val; + break; + case 4: + *reg = (u32)val; + break; /* 64b: zero-extend */ + case 8: + *reg = val; + break; + } +} + static inline unsigned long ad_mask(struct x86_emulate_ctxt *ctxt) { return (1UL << (ctxt->ad_bytes << 3)) - 1; @@ -943,6 +943,22 @@ FASTOP2(xadd); FASTOP2R(cmp, cmp_r); +static int em_bsf_c(struct x86_emulate_ctxt *ctxt) +{ + /* If src is zero, do not writeback, but update flags */ + if (ctxt->src.val == 0) + ctxt->dst.type = OP_NONE; + return fastop(ctxt, em_bsf); +} + +static int em_bsr_c(struct x86_emulate_ctxt *ctxt) +{ + /* If src is zero, do not writeback, but update flags */ + if (ctxt->src.val == 0) + ctxt->dst.type = OP_NONE; + return fastop(ctxt, em_bsr); +} + static u8 test_cc(unsigned int condition, unsigned long flags) { u8 rc; @@ -1399,7 +1415,7 @@ static int pio_in_emulated(struct x86_emulate_ctxt *ctxt, unsigned int in_page, n; unsigned int count = ctxt->rep_prefix ? address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) : 1; - in_page = (ctxt->eflags & EFLG_DF) ? + in_page = (ctxt->eflags & X86_EFLAGS_DF) ? offset_in_page(reg_read(ctxt, VCPU_REGS_RDI)) : PAGE_SIZE - offset_in_page(reg_read(ctxt, VCPU_REGS_RDI)); n = min3(in_page, (unsigned int)sizeof(rc->data) / size, count); @@ -1412,7 +1428,7 @@ static int pio_in_emulated(struct x86_emulate_ctxt *ctxt, } if (ctxt->rep_prefix && (ctxt->d & String) && - !(ctxt->eflags & EFLG_DF)) { + !(ctxt->eflags & X86_EFLAGS_DF)) { ctxt->dst.data = rc->data + rc->pos; ctxt->dst.type = OP_MEM_STR; ctxt->dst.count = (rc->end - rc->pos) / size; @@ -1691,21 +1707,7 @@ static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt, static void write_register_operand(struct operand *op) { - /* The 4-byte case *is* correct: in 64-bit mode we zero-extend. */ - switch (op->bytes) { - case 1: - *(u8 *)op->addr.reg = (u8)op->val; - break; - case 2: - *(u16 *)op->addr.reg = (u16)op->val; - break; - case 4: - *op->addr.reg = (u32)op->val; - break; /* 64b: zero-extend */ - case 8: - *op->addr.reg = op->val; - break; - } + return assign_register(op->addr.reg, op->val, op->bytes); } static int writeback(struct x86_emulate_ctxt *ctxt, struct operand *op) @@ -1792,32 +1794,34 @@ static int emulate_popf(struct x86_emulate_ctxt *ctxt, { int rc; unsigned long val, change_mask; - int iopl = (ctxt->eflags & X86_EFLAGS_IOPL) >> IOPL_SHIFT; + int iopl = (ctxt->eflags & X86_EFLAGS_IOPL) >> X86_EFLAGS_IOPL_BIT; int cpl = ctxt->ops->cpl(ctxt); rc = emulate_pop(ctxt, &val, len); if (rc != X86EMUL_CONTINUE) return rc; - change_mask = EFLG_CF | EFLG_PF | EFLG_AF | EFLG_ZF | EFLG_SF | EFLG_OF - | EFLG_TF | EFLG_DF | EFLG_NT | EFLG_AC | EFLG_ID; + change_mask = X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF | + X86_EFLAGS_ZF | X86_EFLAGS_SF | X86_EFLAGS_OF | + X86_EFLAGS_TF | X86_EFLAGS_DF | X86_EFLAGS_NT | + X86_EFLAGS_AC | X86_EFLAGS_ID; switch(ctxt->mode) { case X86EMUL_MODE_PROT64: case X86EMUL_MODE_PROT32: case X86EMUL_MODE_PROT16: if (cpl == 0) - change_mask |= EFLG_IOPL; + change_mask |= X86_EFLAGS_IOPL; if (cpl <= iopl) - change_mask |= EFLG_IF; + change_mask |= X86_EFLAGS_IF; break; case X86EMUL_MODE_VM86: if (iopl < 3) return emulate_gp(ctxt, 0); - change_mask |= EFLG_IF; + change_mask |= X86_EFLAGS_IF; break; default: /* real mode */ - change_mask |= (EFLG_IOPL | EFLG_IF); + change_mask |= (X86_EFLAGS_IOPL | X86_EFLAGS_IF); break; } @@ -1918,7 +1922,7 @@ static int em_pusha(struct x86_emulate_ctxt *ctxt) static int em_pushf(struct x86_emulate_ctxt *ctxt) { - ctxt->src.val = (unsigned long)ctxt->eflags & ~EFLG_VM; + ctxt->src.val = (unsigned long)ctxt->eflags & ~X86_EFLAGS_VM; return em_push(ctxt); } @@ -1926,6 +1930,7 @@ static int em_popa(struct x86_emulate_ctxt *ctxt) { int rc = X86EMUL_CONTINUE; int reg = VCPU_REGS_RDI; + u32 val; while (reg >= VCPU_REGS_RAX) { if (reg == VCPU_REGS_RSP) { @@ -1933,9 +1938,10 @@ static int em_popa(struct x86_emulate_ctxt *ctxt) --reg; } - rc = emulate_pop(ctxt, reg_rmw(ctxt, reg), ctxt->op_bytes); + rc = emulate_pop(ctxt, &val, ctxt->op_bytes); if (rc != X86EMUL_CONTINUE) break; + assign_register(reg_rmw(ctxt, reg), val, ctxt->op_bytes); --reg; } return rc; @@ -1956,7 +1962,7 @@ static int __emulate_int_real(struct x86_emulate_ctxt *ctxt, int irq) if (rc != X86EMUL_CONTINUE) return rc; - ctxt->eflags &= ~(EFLG_IF | EFLG_TF | EFLG_AC); + ctxt->eflags &= ~(X86_EFLAGS_IF | X86_EFLAGS_TF | X86_EFLAGS_AC); ctxt->src.val = get_segment_selector(ctxt, VCPU_SREG_CS); rc = em_push(ctxt); @@ -2022,10 +2028,14 @@ static int emulate_iret_real(struct x86_emulate_ctxt *ctxt) unsigned long temp_eip = 0; unsigned long temp_eflags = 0; unsigned long cs = 0; - unsigned long mask = EFLG_CF | EFLG_PF | EFLG_AF | EFLG_ZF | EFLG_SF | EFLG_TF | - EFLG_IF | EFLG_DF | EFLG_OF | EFLG_IOPL | EFLG_NT | EFLG_RF | - EFLG_AC | EFLG_ID | (1 << 1); /* Last one is the reserved bit */ - unsigned long vm86_mask = EFLG_VM | EFLG_VIF | EFLG_VIP; + unsigned long mask = X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF | + X86_EFLAGS_ZF | X86_EFLAGS_SF | X86_EFLAGS_TF | + X86_EFLAGS_IF | X86_EFLAGS_DF | X86_EFLAGS_OF | + X86_EFLAGS_IOPL | X86_EFLAGS_NT | X86_EFLAGS_RF | + X86_EFLAGS_AC | X86_EFLAGS_ID | + X86_EFLAGS_FIXED; + unsigned long vm86_mask = X86_EFLAGS_VM | X86_EFLAGS_VIF | + X86_EFLAGS_VIP; /* TODO: Add stack limit check */ @@ -2054,7 +2064,6 @@ static int emulate_iret_real(struct x86_emulate_ctxt *ctxt) ctxt->_eip = temp_eip; - if (ctxt->op_bytes == 4) ctxt->eflags = ((temp_eflags & mask) | (ctxt->eflags & vm86_mask)); else if (ctxt->op_bytes == 2) { @@ -2063,7 +2072,7 @@ static int emulate_iret_real(struct x86_emulate_ctxt *ctxt) } ctxt->eflags &= ~EFLG_RESERVED_ZEROS_MASK; /* Clear reserved zeros */ - ctxt->eflags |= EFLG_RESERVED_ONE_MASK; + ctxt->eflags |= X86_EFLAGS_FIXED; ctxt->ops->set_nmi_mask(ctxt, false); return rc; @@ -2145,12 +2154,12 @@ static int em_cmpxchg8b(struct x86_emulate_ctxt *ctxt) ((u32) (old >> 32) != (u32) reg_read(ctxt, VCPU_REGS_RDX))) { *reg_write(ctxt, VCPU_REGS_RAX) = (u32) (old >> 0); *reg_write(ctxt, VCPU_REGS_RDX) = (u32) (old >> 32); - ctxt->eflags &= ~EFLG_ZF; + ctxt->eflags &= ~X86_EFLAGS_ZF; } else { ctxt->dst.val64 = ((u64)reg_read(ctxt, VCPU_REGS_RCX) << 32) | (u32) reg_read(ctxt, VCPU_REGS_RBX); - ctxt->eflags |= EFLG_ZF; + ctxt->eflags |= X86_EFLAGS_ZF; } return X86EMUL_CONTINUE; } @@ -2222,7 +2231,7 @@ static int em_cmpxchg(struct x86_emulate_ctxt *ctxt) ctxt->src.val = ctxt->dst.orig_val; fastop(ctxt, em_cmp); - if (ctxt->eflags & EFLG_ZF) { + if (ctxt->eflags & X86_EFLAGS_ZF) { /* Success: write back to memory; no update of EAX */ ctxt->src.type = OP_NONE; ctxt->dst.val = ctxt->src.orig_val; @@ -2381,14 +2390,14 @@ static int em_syscall(struct x86_emulate_ctxt *ctxt) ops->get_msr(ctxt, MSR_SYSCALL_MASK, &msr_data); ctxt->eflags &= ~msr_data; - ctxt->eflags |= EFLG_RESERVED_ONE_MASK; + ctxt->eflags |= X86_EFLAGS_FIXED; #endif } else { /* legacy mode */ ops->get_msr(ctxt, MSR_STAR, &msr_data); ctxt->_eip = (u32)msr_data; - ctxt->eflags &= ~(EFLG_VM | EFLG_IF); + ctxt->eflags &= ~(X86_EFLAGS_VM | X86_EFLAGS_IF); } return X86EMUL_CONTINUE; @@ -2425,8 +2434,8 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt) if ((msr_data & 0xfffc) == 0x0) return emulate_gp(ctxt, 0); - ctxt->eflags &= ~(EFLG_VM | EFLG_IF); - cs_sel = (u16)msr_data & ~SELECTOR_RPL_MASK; + ctxt->eflags &= ~(X86_EFLAGS_VM | X86_EFLAGS_IF); + cs_sel = (u16)msr_data & ~SEGMENT_RPL_MASK; ss_sel = cs_sel + 8; if (efer & EFER_LMA) { cs.d = 0; @@ -2493,8 +2502,8 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt) return emulate_gp(ctxt, 0); break; } - cs_sel |= SELECTOR_RPL_MASK; - ss_sel |= SELECTOR_RPL_MASK; + cs_sel |= SEGMENT_RPL_MASK; + ss_sel |= SEGMENT_RPL_MASK; ops->set_segment(ctxt, cs_sel, &cs, 0, VCPU_SREG_CS); ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS); @@ -2512,7 +2521,7 @@ static bool emulator_bad_iopl(struct x86_emulate_ctxt *ctxt) return false; if (ctxt->mode == X86EMUL_MODE_VM86) return true; - iopl = (ctxt->eflags & X86_EFLAGS_IOPL) >> IOPL_SHIFT; + iopl = (ctxt->eflags & X86_EFLAGS_IOPL) >> X86_EFLAGS_IOPL_BIT; return ctxt->ops->cpl(ctxt) > iopl; } @@ -2782,10 +2791,8 @@ static int load_state_from_tss32(struct x86_emulate_ctxt *ctxt, return ret; ret = __load_segment_descriptor(ctxt, tss->gs, VCPU_SREG_GS, cpl, X86_TRANSFER_TASK_SWITCH, NULL); - if (ret != X86EMUL_CONTINUE) - return ret; - return X86EMUL_CONTINUE; + return ret; } static int task_switch_32(struct x86_emulate_ctxt *ctxt, @@ -2954,7 +2961,7 @@ int emulator_task_switch(struct x86_emulate_ctxt *ctxt, static void string_addr_inc(struct x86_emulate_ctxt *ctxt, int reg, struct operand *op) { - int df = (ctxt->eflags & EFLG_DF) ? -op->count : op->count; + int df = (ctxt->eflags & X86_EFLAGS_DF) ? -op->count : op->count; register_address_increment(ctxt, reg, df * op->bytes); op->addr.mem.ea = register_address(ctxt, reg); @@ -3323,7 +3330,7 @@ static int em_clts(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } -static int em_vmcall(struct x86_emulate_ctxt *ctxt) +static int em_hypercall(struct x86_emulate_ctxt *ctxt) { int rc = ctxt->ops->fix_hypercall(ctxt); @@ -3395,17 +3402,6 @@ static int em_lgdt(struct x86_emulate_ctxt *ctxt) return em_lgdt_lidt(ctxt, true); } -static int em_vmmcall(struct x86_emulate_ctxt *ctxt) -{ - int rc; - - rc = ctxt->ops->fix_hypercall(ctxt); - - /* Disable writeback. */ - ctxt->dst.type = OP_NONE; - return rc; -} - static int em_lidt(struct x86_emulate_ctxt *ctxt) { return em_lgdt_lidt(ctxt, false); @@ -3504,7 +3500,8 @@ static int em_sahf(struct x86_emulate_ctxt *ctxt) { u32 flags; - flags = EFLG_CF | EFLG_PF | EFLG_AF | EFLG_ZF | EFLG_SF; + flags = X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF | X86_EFLAGS_ZF | + X86_EFLAGS_SF; flags &= *reg_rmw(ctxt, VCPU_REGS_RAX) >> 8; ctxt->eflags &= ~0xffUL; @@ -3769,7 +3766,7 @@ static int check_perm_out(struct x86_emulate_ctxt *ctxt) static const struct opcode group7_rm0[] = { N, - I(SrcNone | Priv | EmulateOnUD, em_vmcall), + I(SrcNone | Priv | EmulateOnUD, em_hypercall), N, N, N, N, N, N, }; @@ -3781,7 +3778,7 @@ static const struct opcode group7_rm1[] = { static const struct opcode group7_rm3[] = { DIP(SrcNone | Prot | Priv, vmrun, check_svme_pa), - II(SrcNone | Prot | EmulateOnUD, em_vmmcall, vmmcall), + II(SrcNone | Prot | EmulateOnUD, em_hypercall, vmmcall), DIP(SrcNone | Prot | Priv, vmload, check_svme_pa), DIP(SrcNone | Prot | Priv, vmsave, check_svme_pa), DIP(SrcNone | Prot | Priv, stgi, check_svme), @@ -4192,7 +4189,8 @@ static const struct opcode twobyte_table[256] = { N, N, G(BitOp, group8), F(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_btc), - F(DstReg | SrcMem | ModRM, em_bsf), F(DstReg | SrcMem | ModRM, em_bsr), + I(DstReg | SrcMem | ModRM, em_bsf_c), + I(DstReg | SrcMem | ModRM, em_bsr_c), D(DstReg | SrcMem8 | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov), /* 0xC0 - 0xC7 */ F2bv(DstMem | SrcReg | ModRM | SrcWrite | Lock, em_xadd), @@ -4759,9 +4757,9 @@ static bool string_insn_completed(struct x86_emulate_ctxt *ctxt) if (((ctxt->b == 0xa6) || (ctxt->b == 0xa7) || (ctxt->b == 0xae) || (ctxt->b == 0xaf)) && (((ctxt->rep_prefix == REPE_PREFIX) && - ((ctxt->eflags & EFLG_ZF) == 0)) + ((ctxt->eflags & X86_EFLAGS_ZF) == 0)) || ((ctxt->rep_prefix == REPNE_PREFIX) && - ((ctxt->eflags & EFLG_ZF) == EFLG_ZF)))) + ((ctxt->eflags & X86_EFLAGS_ZF) == X86_EFLAGS_ZF)))) return true; return false; @@ -4913,7 +4911,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) /* All REP prefixes have the same first termination condition */ if (address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) == 0) { ctxt->eip = ctxt->_eip; - ctxt->eflags &= ~EFLG_RF; + ctxt->eflags &= ~X86_EFLAGS_RF; goto done; } } @@ -4963,9 +4961,9 @@ special_insn: } if (ctxt->rep_prefix && (ctxt->d & String)) - ctxt->eflags |= EFLG_RF; + ctxt->eflags |= X86_EFLAGS_RF; else - ctxt->eflags &= ~EFLG_RF; + ctxt->eflags &= ~X86_EFLAGS_RF; if (ctxt->execute) { if (ctxt->d & Fastop) { @@ -5014,7 +5012,7 @@ special_insn: rc = emulate_int(ctxt, ctxt->src.val); break; case 0xce: /* into */ - if (ctxt->eflags & EFLG_OF) + if (ctxt->eflags & X86_EFLAGS_OF) rc = emulate_int(ctxt, 4); break; case 0xe9: /* jmp rel */ @@ -5027,19 +5025,19 @@ special_insn: break; case 0xf5: /* cmc */ /* complement carry flag from eflags reg */ - ctxt->eflags ^= EFLG_CF; + ctxt->eflags ^= X86_EFLAGS_CF; break; case 0xf8: /* clc */ - ctxt->eflags &= ~EFLG_CF; + ctxt->eflags &= ~X86_EFLAGS_CF; break; case 0xf9: /* stc */ - ctxt->eflags |= EFLG_CF; + ctxt->eflags |= X86_EFLAGS_CF; break; case 0xfc: /* cld */ - ctxt->eflags &= ~EFLG_DF; + ctxt->eflags &= ~X86_EFLAGS_DF; break; case 0xfd: /* std */ - ctxt->eflags |= EFLG_DF; + ctxt->eflags |= X86_EFLAGS_DF; break; default: goto cannot_emulate; @@ -5100,7 +5098,7 @@ writeback: } goto done; /* skip rip writeback */ } - ctxt->eflags &= ~EFLG_RF; + ctxt->eflags &= ~X86_EFLAGS_RF; } ctxt->eip = ctxt->_eip; @@ -5137,8 +5135,7 @@ twobyte_insn: case 0x40 ... 0x4f: /* cmov */ if (test_cc(ctxt->b, ctxt->eflags)) ctxt->dst.val = ctxt->src.val; - else if (ctxt->mode != X86EMUL_MODE_PROT64 || - ctxt->op_bytes != 4) + else if (ctxt->op_bytes != 4) ctxt->dst.type = OP_NONE; /* no writeback */ break; case 0x80 ... 0x8f: /* jnz rel, etc*/ diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 298781d4cfb4..4dce6f8b6129 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -443,7 +443,8 @@ static inline int pit_in_range(gpa_t addr) (addr < KVM_PIT_BASE_ADDRESS + KVM_PIT_MEM_LENGTH)); } -static int pit_ioport_write(struct kvm_io_device *this, +static int pit_ioport_write(struct kvm_vcpu *vcpu, + struct kvm_io_device *this, gpa_t addr, int len, const void *data) { struct kvm_pit *pit = dev_to_pit(this); @@ -519,7 +520,8 @@ static int pit_ioport_write(struct kvm_io_device *this, return 0; } -static int pit_ioport_read(struct kvm_io_device *this, +static int pit_ioport_read(struct kvm_vcpu *vcpu, + struct kvm_io_device *this, gpa_t addr, int len, void *data) { struct kvm_pit *pit = dev_to_pit(this); @@ -589,7 +591,8 @@ static int pit_ioport_read(struct kvm_io_device *this, return 0; } -static int speaker_ioport_write(struct kvm_io_device *this, +static int speaker_ioport_write(struct kvm_vcpu *vcpu, + struct kvm_io_device *this, gpa_t addr, int len, const void *data) { struct kvm_pit *pit = speaker_to_pit(this); @@ -606,8 +609,9 @@ static int speaker_ioport_write(struct kvm_io_device *this, return 0; } -static int speaker_ioport_read(struct kvm_io_device *this, - gpa_t addr, int len, void *data) +static int speaker_ioport_read(struct kvm_vcpu *vcpu, + struct kvm_io_device *this, + gpa_t addr, int len, void *data) { struct kvm_pit *pit = speaker_to_pit(this); struct kvm_kpit_state *pit_state = &pit->pit_state; diff --git a/arch/x86/kvm/i8254.h b/arch/x86/kvm/i8254.h index dd1b16b611b0..c84990b42b5b 100644 --- a/arch/x86/kvm/i8254.h +++ b/arch/x86/kvm/i8254.h @@ -3,7 +3,7 @@ #include <linux/kthread.h> -#include "iodev.h" +#include <kvm/iodev.h> struct kvm_kpit_channel_state { u32 count; /* can be 65536 */ diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index 9541ba34126b..fef922ff2635 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -529,42 +529,42 @@ static int picdev_read(struct kvm_pic *s, return 0; } -static int picdev_master_write(struct kvm_io_device *dev, +static int picdev_master_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, gpa_t addr, int len, const void *val) { return picdev_write(container_of(dev, struct kvm_pic, dev_master), addr, len, val); } -static int picdev_master_read(struct kvm_io_device *dev, +static int picdev_master_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, gpa_t addr, int len, void *val) { return picdev_read(container_of(dev, struct kvm_pic, dev_master), addr, len, val); } -static int picdev_slave_write(struct kvm_io_device *dev, +static int picdev_slave_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, gpa_t addr, int len, const void *val) { return picdev_write(container_of(dev, struct kvm_pic, dev_slave), addr, len, val); } -static int picdev_slave_read(struct kvm_io_device *dev, +static int picdev_slave_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, gpa_t addr, int len, void *val) { return picdev_read(container_of(dev, struct kvm_pic, dev_slave), addr, len, val); } -static int picdev_eclr_write(struct kvm_io_device *dev, +static int picdev_eclr_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, gpa_t addr, int len, const void *val) { return picdev_write(container_of(dev, struct kvm_pic, dev_eclr), addr, len, val); } -static int picdev_eclr_read(struct kvm_io_device *dev, +static int picdev_eclr_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, gpa_t addr, int len, void *val) { return picdev_read(container_of(dev, struct kvm_pic, dev_eclr), diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 46d4449772bc..28146f03c514 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -206,6 +206,8 @@ static int ioapic_set_irq(struct kvm_ioapic *ioapic, unsigned int irq, old_irr = ioapic->irr; ioapic->irr |= mask; + if (edge) + ioapic->irr_delivered &= ~mask; if ((edge && old_irr == ioapic->irr) || (!edge && entry.fields.remote_irr)) { ret = 0; @@ -349,7 +351,7 @@ static int ioapic_service(struct kvm_ioapic *ioapic, int irq, bool line_status) irqe.shorthand = 0; if (irqe.trig_mode == IOAPIC_EDGE_TRIG) - ioapic->irr &= ~(1 << irq); + ioapic->irr_delivered |= 1 << irq; if (irq == RTC_GSI && line_status) { /* @@ -473,13 +475,6 @@ static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, } } -bool kvm_ioapic_handles_vector(struct kvm *kvm, int vector) -{ - struct kvm_ioapic *ioapic = kvm->arch.vioapic; - smp_rmb(); - return test_bit(vector, ioapic->handled_vectors); -} - void kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, int vector, int trigger_mode) { struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic; @@ -500,8 +495,8 @@ static inline int ioapic_in_range(struct kvm_ioapic *ioapic, gpa_t addr) (addr < ioapic->base_address + IOAPIC_MEM_LENGTH))); } -static int ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len, - void *val) +static int ioapic_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *this, + gpa_t addr, int len, void *val) { struct kvm_ioapic *ioapic = to_ioapic(this); u32 result; @@ -543,8 +538,8 @@ static int ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len, return 0; } -static int ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len, - const void *val) +static int ioapic_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this, + gpa_t addr, int len, const void *val) { struct kvm_ioapic *ioapic = to_ioapic(this); u32 data; @@ -599,6 +594,7 @@ static void kvm_ioapic_reset(struct kvm_ioapic *ioapic) ioapic->base_address = IOAPIC_DEFAULT_BASE_ADDRESS; ioapic->ioregsel = 0; ioapic->irr = 0; + ioapic->irr_delivered = 0; ioapic->id = 0; memset(ioapic->irq_eoi, 0x00, IOAPIC_NUM_PINS); rtc_irq_eoi_tracking_reset(ioapic); @@ -656,6 +652,7 @@ int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state) spin_lock(&ioapic->lock); memcpy(state, ioapic, sizeof(struct kvm_ioapic_state)); + state->irr &= ~ioapic->irr_delivered; spin_unlock(&ioapic->lock); return 0; } @@ -669,6 +666,7 @@ int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state) spin_lock(&ioapic->lock); memcpy(ioapic, state, sizeof(struct kvm_ioapic_state)); ioapic->irr = 0; + ioapic->irr_delivered = 0; update_handled_vectors(ioapic); kvm_vcpu_request_scan_ioapic(kvm); kvm_ioapic_inject_all(ioapic, state->irr); diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h index c2e36d934af4..ca0b0b4e6256 100644 --- a/arch/x86/kvm/ioapic.h +++ b/arch/x86/kvm/ioapic.h @@ -3,7 +3,7 @@ #include <linux/kvm_host.h> -#include "iodev.h" +#include <kvm/iodev.h> struct kvm; struct kvm_vcpu; @@ -77,6 +77,7 @@ struct kvm_ioapic { struct rtc_status rtc_status; struct delayed_work eoi_inject; u32 irq_eoi[IOAPIC_NUM_PINS]; + u32 irr_delivered; }; #ifdef DEBUG @@ -97,13 +98,19 @@ static inline struct kvm_ioapic *ioapic_irqchip(struct kvm *kvm) return kvm->arch.vioapic; } +static inline bool kvm_ioapic_handles_vector(struct kvm *kvm, int vector) +{ + struct kvm_ioapic *ioapic = kvm->arch.vioapic; + smp_rmb(); + return test_bit(vector, ioapic->handled_vectors); +} + void kvm_rtc_eoi_tracking_restore_one(struct kvm_vcpu *vcpu); bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, int short_hand, unsigned int dest, int dest_mode); int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2); void kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, int vector, int trigger_mode); -bool kvm_ioapic_handles_vector(struct kvm *kvm, int vector); int kvm_ioapic_init(struct kvm *kvm); void kvm_ioapic_destroy(struct kvm *kvm); int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id, diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index 2d03568e9498..ad68c73008c5 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -27,7 +27,7 @@ #include <linux/kvm_host.h> #include <linux/spinlock.h> -#include "iodev.h" +#include <kvm/iodev.h> #include "ioapic.h" #include "lapic.h" diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 4ee827d7bf36..d67206a7b99a 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -133,6 +133,28 @@ static inline int kvm_apic_id(struct kvm_lapic *apic) return (kvm_apic_get_reg(apic, APIC_ID) >> 24) & 0xff; } +/* The logical map is definitely wrong if we have multiple + * modes at the same time. (Physical map is always right.) + */ +static inline bool kvm_apic_logical_map_valid(struct kvm_apic_map *map) +{ + return !(map->mode & (map->mode - 1)); +} + +static inline void +apic_logical_id(struct kvm_apic_map *map, u32 dest_id, u16 *cid, u16 *lid) +{ + unsigned lid_bits; + + BUILD_BUG_ON(KVM_APIC_MODE_XAPIC_CLUSTER != 4); + BUILD_BUG_ON(KVM_APIC_MODE_XAPIC_FLAT != 8); + BUILD_BUG_ON(KVM_APIC_MODE_X2APIC != 16); + lid_bits = map->mode; + + *cid = dest_id >> lid_bits; + *lid = dest_id & ((1 << lid_bits) - 1); +} + static void recalculate_apic_map(struct kvm *kvm) { struct kvm_apic_map *new, *old = NULL; @@ -146,48 +168,6 @@ static void recalculate_apic_map(struct kvm *kvm) if (!new) goto out; - new->ldr_bits = 8; - /* flat mode is default */ - new->cid_shift = 8; - new->cid_mask = 0; - new->lid_mask = 0xff; - new->broadcast = APIC_BROADCAST; - - kvm_for_each_vcpu(i, vcpu, kvm) { - struct kvm_lapic *apic = vcpu->arch.apic; - - if (!kvm_apic_present(vcpu)) - continue; - - if (apic_x2apic_mode(apic)) { - new->ldr_bits = 32; - new->cid_shift = 16; - new->cid_mask = new->lid_mask = 0xffff; - new->broadcast = X2APIC_BROADCAST; - } else if (kvm_apic_get_reg(apic, APIC_LDR)) { - if (kvm_apic_get_reg(apic, APIC_DFR) == - APIC_DFR_CLUSTER) { - new->cid_shift = 4; - new->cid_mask = 0xf; - new->lid_mask = 0xf; - } else { - new->cid_shift = 8; - new->cid_mask = 0; - new->lid_mask = 0xff; - } - } - - /* - * All APICs have to be configured in the same mode by an OS. - * We take advatage of this while building logical id loockup - * table. After reset APICs are in software disabled mode, so if - * we find apic with different setting we assume this is the mode - * OS wants all apics to be in; build lookup table accordingly. - */ - if (kvm_apic_sw_enabled(apic)) - break; - } - kvm_for_each_vcpu(i, vcpu, kvm) { struct kvm_lapic *apic = vcpu->arch.apic; u16 cid, lid; @@ -198,11 +178,25 @@ static void recalculate_apic_map(struct kvm *kvm) aid = kvm_apic_id(apic); ldr = kvm_apic_get_reg(apic, APIC_LDR); - cid = apic_cluster_id(new, ldr); - lid = apic_logical_id(new, ldr); if (aid < ARRAY_SIZE(new->phys_map)) new->phys_map[aid] = apic; + + if (apic_x2apic_mode(apic)) { + new->mode |= KVM_APIC_MODE_X2APIC; + } else if (ldr) { + ldr = GET_APIC_LOGICAL_ID(ldr); + if (kvm_apic_get_reg(apic, APIC_DFR) == APIC_DFR_FLAT) + new->mode |= KVM_APIC_MODE_XAPIC_FLAT; + else + new->mode |= KVM_APIC_MODE_XAPIC_CLUSTER; + } + + if (!kvm_apic_logical_map_valid(new)) + continue; + + apic_logical_id(new, ldr, &cid, &lid); + if (lid && cid < ARRAY_SIZE(new->logical_map)) new->logical_map[cid][ffs(lid) - 1] = apic; } @@ -588,15 +582,23 @@ static void apic_set_tpr(struct kvm_lapic *apic, u32 tpr) apic_update_ppr(apic); } -static bool kvm_apic_broadcast(struct kvm_lapic *apic, u32 dest) +static bool kvm_apic_broadcast(struct kvm_lapic *apic, u32 mda) { - return dest == (apic_x2apic_mode(apic) ? - X2APIC_BROADCAST : APIC_BROADCAST); + if (apic_x2apic_mode(apic)) + return mda == X2APIC_BROADCAST; + + return GET_APIC_DEST_FIELD(mda) == APIC_BROADCAST; } -static bool kvm_apic_match_physical_addr(struct kvm_lapic *apic, u32 dest) +static bool kvm_apic_match_physical_addr(struct kvm_lapic *apic, u32 mda) { - return kvm_apic_id(apic) == dest || kvm_apic_broadcast(apic, dest); + if (kvm_apic_broadcast(apic, mda)) + return true; + + if (apic_x2apic_mode(apic)) + return mda == kvm_apic_id(apic); + + return mda == SET_APIC_DEST_FIELD(kvm_apic_id(apic)); } static bool kvm_apic_match_logical_addr(struct kvm_lapic *apic, u32 mda) @@ -613,6 +615,7 @@ static bool kvm_apic_match_logical_addr(struct kvm_lapic *apic, u32 mda) && (logical_id & mda & 0xffff) != 0; logical_id = GET_APIC_LOGICAL_ID(logical_id); + mda = GET_APIC_DEST_FIELD(mda); switch (kvm_apic_get_reg(apic, APIC_DFR)) { case APIC_DFR_FLAT: @@ -627,10 +630,27 @@ static bool kvm_apic_match_logical_addr(struct kvm_lapic *apic, u32 mda) } } +/* KVM APIC implementation has two quirks + * - dest always begins at 0 while xAPIC MDA has offset 24, + * - IOxAPIC messages have to be delivered (directly) to x2APIC. + */ +static u32 kvm_apic_mda(unsigned int dest_id, struct kvm_lapic *source, + struct kvm_lapic *target) +{ + bool ipi = source != NULL; + bool x2apic_mda = apic_x2apic_mode(ipi ? source : target); + + if (!ipi && dest_id == APIC_BROADCAST && x2apic_mda) + return X2APIC_BROADCAST; + + return x2apic_mda ? dest_id : SET_APIC_DEST_FIELD(dest_id); +} + bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, int short_hand, unsigned int dest, int dest_mode) { struct kvm_lapic *target = vcpu->arch.apic; + u32 mda = kvm_apic_mda(dest, source, target); apic_debug("target %p, source %p, dest 0x%x, " "dest_mode 0x%x, short_hand 0x%x\n", @@ -640,9 +660,9 @@ bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, switch (short_hand) { case APIC_DEST_NOSHORT: if (dest_mode == APIC_DEST_PHYSICAL) - return kvm_apic_match_physical_addr(target, dest); + return kvm_apic_match_physical_addr(target, mda); else - return kvm_apic_match_logical_addr(target, dest); + return kvm_apic_match_logical_addr(target, mda); case APIC_DEST_SELF: return target == source; case APIC_DEST_ALLINC: @@ -664,6 +684,7 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, struct kvm_lapic **dst; int i; bool ret = false; + bool x2apic_ipi = src && apic_x2apic_mode(src); *r = -1; @@ -675,15 +696,15 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, if (irq->shorthand) return false; + if (irq->dest_id == (x2apic_ipi ? X2APIC_BROADCAST : APIC_BROADCAST)) + return false; + rcu_read_lock(); map = rcu_dereference(kvm->arch.apic_map); if (!map) goto out; - if (irq->dest_id == map->broadcast) - goto out; - ret = true; if (irq->dest_mode == APIC_DEST_PHYSICAL) { @@ -692,16 +713,20 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, dst = &map->phys_map[irq->dest_id]; } else { - u32 mda = irq->dest_id << (32 - map->ldr_bits); - u16 cid = apic_cluster_id(map, mda); + u16 cid; + + if (!kvm_apic_logical_map_valid(map)) { + ret = false; + goto out; + } + + apic_logical_id(map, irq->dest_id, &cid, (u16 *)&bitmap); if (cid >= ARRAY_SIZE(map->logical_map)) goto out; dst = map->logical_map[cid]; - bitmap = apic_logical_id(map, mda); - if (irq->delivery_mode == APIC_DM_LOWEST) { int l = -1; for_each_set_bit(i, &bitmap, 16) { @@ -1037,7 +1062,7 @@ static int apic_mmio_in_range(struct kvm_lapic *apic, gpa_t addr) addr < apic->base_address + LAPIC_MMIO_LENGTH; } -static int apic_mmio_read(struct kvm_io_device *this, +static int apic_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *this, gpa_t address, int len, void *data) { struct kvm_lapic *apic = to_lapic(this); @@ -1357,7 +1382,7 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) return ret; } -static int apic_mmio_write(struct kvm_io_device *this, +static int apic_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this, gpa_t address, int len, const void *data) { struct kvm_lapic *apic = to_lapic(this); @@ -1497,8 +1522,6 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) return; } - if (!kvm_vcpu_is_bsp(apic->vcpu)) - value &= ~MSR_IA32_APICBASE_BSP; vcpu->arch.apic_base = value; /* update jump label if enable bit changes */ diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 0bc6c656625b..9d28383fc1e7 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -1,7 +1,7 @@ #ifndef __KVM_X86_LAPIC_H #define __KVM_X86_LAPIC_H -#include "iodev.h" +#include <kvm/iodev.h> #include <linux/kvm_host.h> @@ -148,21 +148,6 @@ static inline bool kvm_apic_vid_enabled(struct kvm *kvm) return kvm_x86_ops->vm_has_apicv(kvm); } -static inline u16 apic_cluster_id(struct kvm_apic_map *map, u32 ldr) -{ - u16 cid; - ldr >>= 32 - map->ldr_bits; - cid = (ldr >> map->cid_shift) & map->cid_mask; - - return cid; -} - -static inline u16 apic_logical_id(struct kvm_apic_map *map, u32 ldr) -{ - ldr >>= (32 - map->ldr_bits); - return ldr & map->lid_mask; -} - static inline bool kvm_apic_has_events(struct kvm_vcpu *vcpu) { return vcpu->arch.apic->pending_events; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index cee759299a35..146f295ee322 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -4465,6 +4465,79 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, kvm_flush_remote_tlbs(kvm); } +static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm, + unsigned long *rmapp) +{ + u64 *sptep; + struct rmap_iterator iter; + int need_tlb_flush = 0; + pfn_t pfn; + struct kvm_mmu_page *sp; + + for (sptep = rmap_get_first(*rmapp, &iter); sptep;) { + BUG_ON(!(*sptep & PT_PRESENT_MASK)); + + sp = page_header(__pa(sptep)); + pfn = spte_to_pfn(*sptep); + + /* + * Only EPT supported for now; otherwise, one would need to + * find out efficiently whether the guest page tables are + * also using huge pages. + */ + if (sp->role.direct && + !kvm_is_reserved_pfn(pfn) && + PageTransCompound(pfn_to_page(pfn))) { + drop_spte(kvm, sptep); + sptep = rmap_get_first(*rmapp, &iter); + need_tlb_flush = 1; + } else + sptep = rmap_get_next(&iter); + } + + return need_tlb_flush; +} + +void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, + struct kvm_memory_slot *memslot) +{ + bool flush = false; + unsigned long *rmapp; + unsigned long last_index, index; + gfn_t gfn_start, gfn_end; + + spin_lock(&kvm->mmu_lock); + + gfn_start = memslot->base_gfn; + gfn_end = memslot->base_gfn + memslot->npages - 1; + + if (gfn_start >= gfn_end) + goto out; + + rmapp = memslot->arch.rmap[0]; + last_index = gfn_to_index(gfn_end, memslot->base_gfn, + PT_PAGE_TABLE_LEVEL); + + for (index = 0; index <= last_index; ++index, ++rmapp) { + if (*rmapp) + flush |= kvm_mmu_zap_collapsible_spte(kvm, rmapp); + + if (need_resched() || spin_needbreak(&kvm->mmu_lock)) { + if (flush) { + kvm_flush_remote_tlbs(kvm); + flush = false; + } + cond_resched_lock(&kvm->mmu_lock); + } + } + + if (flush) + kvm_flush_remote_tlbs(kvm); + +out: + spin_unlock(&kvm->mmu_lock); +} + void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, struct kvm_memory_slot *memslot) { diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 8e6b7d869d2f..29fbf9dfdc54 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -38,7 +38,7 @@ static struct kvm_arch_event_perf_mapping { }; /* mapping between fixed pmc index and arch_events array */ -int fixed_pmc_events[] = {1, 0, 7}; +static int fixed_pmc_events[] = {1, 0, 7}; static bool pmc_is_gp(struct kvm_pmc *pmc) { diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index cc618c882f90..ce741b8650f6 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1261,7 +1261,7 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) svm->vcpu.arch.apic_base = APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE; - if (kvm_vcpu_is_bsp(&svm->vcpu)) + if (kvm_vcpu_is_reset_bsp(&svm->vcpu)) svm->vcpu.arch.apic_base |= MSR_IA32_APICBASE_BSP; svm_init_osvw(&svm->vcpu); @@ -1929,14 +1929,12 @@ static int nop_on_interception(struct vcpu_svm *svm) static int halt_interception(struct vcpu_svm *svm) { svm->next_rip = kvm_rip_read(&svm->vcpu) + 1; - skip_emulated_instruction(&svm->vcpu); return kvm_emulate_halt(&svm->vcpu); } static int vmmcall_interception(struct vcpu_svm *svm) { svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; - skip_emulated_instruction(&svm->vcpu); kvm_emulate_hypercall(&svm->vcpu); return 1; } @@ -2757,11 +2755,11 @@ static int invlpga_interception(struct vcpu_svm *svm) { struct kvm_vcpu *vcpu = &svm->vcpu; - trace_kvm_invlpga(svm->vmcb->save.rip, vcpu->arch.regs[VCPU_REGS_RCX], - vcpu->arch.regs[VCPU_REGS_RAX]); + trace_kvm_invlpga(svm->vmcb->save.rip, kvm_register_read(&svm->vcpu, VCPU_REGS_RCX), + kvm_register_read(&svm->vcpu, VCPU_REGS_RAX)); /* Let's treat INVLPGA the same as INVLPG (can be optimized!) */ - kvm_mmu_invlpg(vcpu, vcpu->arch.regs[VCPU_REGS_RAX]); + kvm_mmu_invlpg(vcpu, kvm_register_read(&svm->vcpu, VCPU_REGS_RAX)); svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; skip_emulated_instruction(&svm->vcpu); @@ -2770,12 +2768,18 @@ static int invlpga_interception(struct vcpu_svm *svm) static int skinit_interception(struct vcpu_svm *svm) { - trace_kvm_skinit(svm->vmcb->save.rip, svm->vcpu.arch.regs[VCPU_REGS_RAX]); + trace_kvm_skinit(svm->vmcb->save.rip, kvm_register_read(&svm->vcpu, VCPU_REGS_RAX)); kvm_queue_exception(&svm->vcpu, UD_VECTOR); return 1; } +static int wbinvd_interception(struct vcpu_svm *svm) +{ + kvm_emulate_wbinvd(&svm->vcpu); + return 1; +} + static int xsetbv_interception(struct vcpu_svm *svm) { u64 new_bv = kvm_read_edx_eax(&svm->vcpu); @@ -2902,7 +2906,8 @@ static int rdpmc_interception(struct vcpu_svm *svm) return 1; } -bool check_selective_cr0_intercepted(struct vcpu_svm *svm, unsigned long val) +static bool check_selective_cr0_intercepted(struct vcpu_svm *svm, + unsigned long val) { unsigned long cr0 = svm->vcpu.arch.cr0; bool ret = false; @@ -2940,7 +2945,10 @@ static int cr_interception(struct vcpu_svm *svm) return emulate_on_interception(svm); reg = svm->vmcb->control.exit_info_1 & SVM_EXITINFO_REG_MASK; - cr = svm->vmcb->control.exit_code - SVM_EXIT_READ_CR0; + if (svm->vmcb->control.exit_code == SVM_EXIT_CR0_SEL_WRITE) + cr = SVM_EXIT_WRITE_CR0 - SVM_EXIT_READ_CR0; + else + cr = svm->vmcb->control.exit_code - SVM_EXIT_READ_CR0; err = 0; if (cr >= 16) { /* mov to cr */ @@ -3133,7 +3141,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) static int rdmsr_interception(struct vcpu_svm *svm) { - u32 ecx = svm->vcpu.arch.regs[VCPU_REGS_RCX]; + u32 ecx = kvm_register_read(&svm->vcpu, VCPU_REGS_RCX); u64 data; if (svm_get_msr(&svm->vcpu, ecx, &data)) { @@ -3142,8 +3150,8 @@ static int rdmsr_interception(struct vcpu_svm *svm) } else { trace_kvm_msr_read(ecx, data); - svm->vcpu.arch.regs[VCPU_REGS_RAX] = data & 0xffffffff; - svm->vcpu.arch.regs[VCPU_REGS_RDX] = data >> 32; + kvm_register_write(&svm->vcpu, VCPU_REGS_RAX, data & 0xffffffff); + kvm_register_write(&svm->vcpu, VCPU_REGS_RDX, data >> 32); svm->next_rip = kvm_rip_read(&svm->vcpu) + 2; skip_emulated_instruction(&svm->vcpu); } @@ -3246,9 +3254,8 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) static int wrmsr_interception(struct vcpu_svm *svm) { struct msr_data msr; - u32 ecx = svm->vcpu.arch.regs[VCPU_REGS_RCX]; - u64 data = (svm->vcpu.arch.regs[VCPU_REGS_RAX] & -1u) - | ((u64)(svm->vcpu.arch.regs[VCPU_REGS_RDX] & -1u) << 32); + u32 ecx = kvm_register_read(&svm->vcpu, VCPU_REGS_RCX); + u64 data = kvm_read_edx_eax(&svm->vcpu); msr.data = data; msr.index = ecx; @@ -3325,7 +3332,7 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_READ_CR3] = cr_interception, [SVM_EXIT_READ_CR4] = cr_interception, [SVM_EXIT_READ_CR8] = cr_interception, - [SVM_EXIT_CR0_SEL_WRITE] = emulate_on_interception, + [SVM_EXIT_CR0_SEL_WRITE] = cr_interception, [SVM_EXIT_WRITE_CR0] = cr_interception, [SVM_EXIT_WRITE_CR3] = cr_interception, [SVM_EXIT_WRITE_CR4] = cr_interception, @@ -3376,7 +3383,7 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_STGI] = stgi_interception, [SVM_EXIT_CLGI] = clgi_interception, [SVM_EXIT_SKINIT] = skinit_interception, - [SVM_EXIT_WBINVD] = emulate_on_interception, + [SVM_EXIT_WBINVD] = wbinvd_interception, [SVM_EXIT_MONITOR] = monitor_interception, [SVM_EXIT_MWAIT] = mwait_interception, [SVM_EXIT_XSETBV] = xsetbv_interception, @@ -3555,7 +3562,7 @@ static int handle_exit(struct kvm_vcpu *vcpu) if (exit_code >= ARRAY_SIZE(svm_exit_handlers) || !svm_exit_handlers[exit_code]) { - WARN_ONCE(1, "vmx: unexpected exit reason 0x%x\n", exit_code); + WARN_ONCE(1, "svm: unexpected exit reason 0x%x\n", exit_code); kvm_queue_exception(vcpu, UD_VECTOR); return 1; } diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index ae4f6d35d19c..f5e8dce8046c 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2470,6 +2470,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) vmx->nested.nested_vmx_secondary_ctls_low = 0; vmx->nested.nested_vmx_secondary_ctls_high &= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | + SECONDARY_EXEC_RDTSCP | SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | @@ -3268,8 +3269,8 @@ static void fix_pmode_seg(struct kvm_vcpu *vcpu, int seg, * default value. */ if (seg == VCPU_SREG_CS || seg == VCPU_SREG_SS) - save->selector &= ~SELECTOR_RPL_MASK; - save->dpl = save->selector & SELECTOR_RPL_MASK; + save->selector &= ~SEGMENT_RPL_MASK; + save->dpl = save->selector & SEGMENT_RPL_MASK; save->s = 1; } vmx_set_segment(vcpu, save, seg); @@ -3842,7 +3843,7 @@ static bool code_segment_valid(struct kvm_vcpu *vcpu) unsigned int cs_rpl; vmx_get_segment(vcpu, &cs, VCPU_SREG_CS); - cs_rpl = cs.selector & SELECTOR_RPL_MASK; + cs_rpl = cs.selector & SEGMENT_RPL_MASK; if (cs.unusable) return false; @@ -3870,7 +3871,7 @@ static bool stack_segment_valid(struct kvm_vcpu *vcpu) unsigned int ss_rpl; vmx_get_segment(vcpu, &ss, VCPU_SREG_SS); - ss_rpl = ss.selector & SELECTOR_RPL_MASK; + ss_rpl = ss.selector & SEGMENT_RPL_MASK; if (ss.unusable) return true; @@ -3892,7 +3893,7 @@ static bool data_segment_valid(struct kvm_vcpu *vcpu, int seg) unsigned int rpl; vmx_get_segment(vcpu, &var, seg); - rpl = var.selector & SELECTOR_RPL_MASK; + rpl = var.selector & SEGMENT_RPL_MASK; if (var.unusable) return true; @@ -3919,7 +3920,7 @@ static bool tr_valid(struct kvm_vcpu *vcpu) if (tr.unusable) return false; - if (tr.selector & SELECTOR_TI_MASK) /* TI = 1 */ + if (tr.selector & SEGMENT_TI_MASK) /* TI = 1 */ return false; if (tr.type != 3 && tr.type != 11) /* TODO: Check if guest is in IA32e mode */ return false; @@ -3937,7 +3938,7 @@ static bool ldtr_valid(struct kvm_vcpu *vcpu) if (ldtr.unusable) return true; - if (ldtr.selector & SELECTOR_TI_MASK) /* TI = 1 */ + if (ldtr.selector & SEGMENT_TI_MASK) /* TI = 1 */ return false; if (ldtr.type != 2) return false; @@ -3954,8 +3955,8 @@ static bool cs_ss_rpl_check(struct kvm_vcpu *vcpu) vmx_get_segment(vcpu, &cs, VCPU_SREG_CS); vmx_get_segment(vcpu, &ss, VCPU_SREG_SS); - return ((cs.selector & SELECTOR_RPL_MASK) == - (ss.selector & SELECTOR_RPL_MASK)); + return ((cs.selector & SEGMENT_RPL_MASK) == + (ss.selector & SEGMENT_RPL_MASK)); } /* @@ -4711,7 +4712,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val(); kvm_set_cr8(&vmx->vcpu, 0); apic_base_msr.data = APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE; - if (kvm_vcpu_is_bsp(&vmx->vcpu)) + if (kvm_vcpu_is_reset_bsp(&vmx->vcpu)) apic_base_msr.data |= MSR_IA32_APICBASE_BSP; apic_base_msr.host_initiated = true; kvm_set_apic_base(&vmx->vcpu, &apic_base_msr); @@ -5006,7 +5007,7 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu, if (emulate_instruction(vcpu, 0) == EMULATE_DONE) { if (vcpu->arch.halt_request) { vcpu->arch.halt_request = 0; - return kvm_emulate_halt(vcpu); + return kvm_vcpu_halt(vcpu); } return 1; } @@ -5071,6 +5072,10 @@ static int handle_exception(struct kvm_vcpu *vcpu) } if (is_invalid_opcode(intr_info)) { + if (is_guest_mode(vcpu)) { + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; + } er = emulate_instruction(vcpu, EMULTYPE_TRAP_UD); if (er != EMULATE_DONE) kvm_queue_exception(vcpu, UD_VECTOR); @@ -5090,9 +5095,10 @@ static int handle_exception(struct kvm_vcpu *vcpu) !(is_page_fault(intr_info) && !(error_code & PFERR_RSVD_MASK))) { vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_SIMUL_EX; - vcpu->run->internal.ndata = 2; + vcpu->run->internal.ndata = 3; vcpu->run->internal.data[0] = vect_info; vcpu->run->internal.data[1] = intr_info; + vcpu->run->internal.data[2] = error_code; return 0; } @@ -5533,13 +5539,11 @@ static int handle_interrupt_window(struct kvm_vcpu *vcpu) static int handle_halt(struct kvm_vcpu *vcpu) { - skip_emulated_instruction(vcpu); return kvm_emulate_halt(vcpu); } static int handle_vmcall(struct kvm_vcpu *vcpu) { - skip_emulated_instruction(vcpu); kvm_emulate_hypercall(vcpu); return 1; } @@ -5570,7 +5574,6 @@ static int handle_rdpmc(struct kvm_vcpu *vcpu) static int handle_wbinvd(struct kvm_vcpu *vcpu) { - skip_emulated_instruction(vcpu); kvm_emulate_wbinvd(vcpu); return 1; } @@ -5828,7 +5831,7 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) gpa_t gpa; gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS); - if (!kvm_io_bus_write(vcpu->kvm, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) { + if (!kvm_io_bus_write(vcpu, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) { skip_emulated_instruction(vcpu); return 1; } @@ -5909,7 +5912,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) if (vcpu->arch.halt_request) { vcpu->arch.halt_request = 0; - ret = kvm_emulate_halt(vcpu); + ret = kvm_vcpu_halt(vcpu); goto out; } @@ -7318,21 +7321,21 @@ static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu, else if (port < 0x10000) bitmap = vmcs12->io_bitmap_b; else - return 1; + return true; bitmap += (port & 0x7fff) / 8; if (last_bitmap != bitmap) if (kvm_read_guest(vcpu->kvm, bitmap, &b, 1)) - return 1; + return true; if (b & (1 << (port & 7))) - return 1; + return true; port++; size--; last_bitmap = bitmap; } - return 0; + return false; } /* @@ -7348,7 +7351,7 @@ static bool nested_vmx_exit_handled_msr(struct kvm_vcpu *vcpu, gpa_t bitmap; if (!nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS)) - return 1; + return true; /* * The MSR_BITMAP page is divided into four 1024-byte bitmaps, @@ -7367,10 +7370,10 @@ static bool nested_vmx_exit_handled_msr(struct kvm_vcpu *vcpu, if (msr_index < 1024*8) { unsigned char b; if (kvm_read_guest(vcpu->kvm, bitmap + msr_index/8, &b, 1)) - return 1; + return true; return 1 & (b >> (msr_index & 7)); } else - return 1; /* let L1 handle the wrong parameter */ + return true; /* let L1 handle the wrong parameter */ } /* @@ -7392,7 +7395,7 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu, case 0: if (vmcs12->cr0_guest_host_mask & (val ^ vmcs12->cr0_read_shadow)) - return 1; + return true; break; case 3: if ((vmcs12->cr3_target_count >= 1 && @@ -7403,37 +7406,37 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu, vmcs12->cr3_target_value2 == val) || (vmcs12->cr3_target_count >= 4 && vmcs12->cr3_target_value3 == val)) - return 0; + return false; if (nested_cpu_has(vmcs12, CPU_BASED_CR3_LOAD_EXITING)) - return 1; + return true; break; case 4: if (vmcs12->cr4_guest_host_mask & (vmcs12->cr4_read_shadow ^ val)) - return 1; + return true; break; case 8: if (nested_cpu_has(vmcs12, CPU_BASED_CR8_LOAD_EXITING)) - return 1; + return true; break; } break; case 2: /* clts */ if ((vmcs12->cr0_guest_host_mask & X86_CR0_TS) && (vmcs12->cr0_read_shadow & X86_CR0_TS)) - return 1; + return true; break; case 1: /* mov from cr */ switch (cr) { case 3: if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_CR3_STORE_EXITING) - return 1; + return true; break; case 8: if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_CR8_STORE_EXITING) - return 1; + return true; break; } break; @@ -7444,14 +7447,14 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu, */ if (vmcs12->cr0_guest_host_mask & 0xe & (val ^ vmcs12->cr0_read_shadow)) - return 1; + return true; if ((vmcs12->cr0_guest_host_mask & 0x1) && !(vmcs12->cr0_read_shadow & 0x1) && (val & 0x1)) - return 1; + return true; break; } - return 0; + return false; } /* @@ -7474,48 +7477,48 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) KVM_ISA_VMX); if (vmx->nested.nested_run_pending) - return 0; + return false; if (unlikely(vmx->fail)) { pr_info_ratelimited("%s failed vm entry %x\n", __func__, vmcs_read32(VM_INSTRUCTION_ERROR)); - return 1; + return true; } switch (exit_reason) { case EXIT_REASON_EXCEPTION_NMI: if (!is_exception(intr_info)) - return 0; + return false; else if (is_page_fault(intr_info)) return enable_ept; else if (is_no_device(intr_info) && !(vmcs12->guest_cr0 & X86_CR0_TS)) - return 0; + return false; return vmcs12->exception_bitmap & (1u << (intr_info & INTR_INFO_VECTOR_MASK)); case EXIT_REASON_EXTERNAL_INTERRUPT: - return 0; + return false; case EXIT_REASON_TRIPLE_FAULT: - return 1; + return true; case EXIT_REASON_PENDING_INTERRUPT: return nested_cpu_has(vmcs12, CPU_BASED_VIRTUAL_INTR_PENDING); case EXIT_REASON_NMI_WINDOW: return nested_cpu_has(vmcs12, CPU_BASED_VIRTUAL_NMI_PENDING); case EXIT_REASON_TASK_SWITCH: - return 1; + return true; case EXIT_REASON_CPUID: if (kvm_register_read(vcpu, VCPU_REGS_RAX) == 0xa) - return 0; - return 1; + return false; + return true; case EXIT_REASON_HLT: return nested_cpu_has(vmcs12, CPU_BASED_HLT_EXITING); case EXIT_REASON_INVD: - return 1; + return true; case EXIT_REASON_INVLPG: return nested_cpu_has(vmcs12, CPU_BASED_INVLPG_EXITING); case EXIT_REASON_RDPMC: return nested_cpu_has(vmcs12, CPU_BASED_RDPMC_EXITING); - case EXIT_REASON_RDTSC: + case EXIT_REASON_RDTSC: case EXIT_REASON_RDTSCP: return nested_cpu_has(vmcs12, CPU_BASED_RDTSC_EXITING); case EXIT_REASON_VMCALL: case EXIT_REASON_VMCLEAR: case EXIT_REASON_VMLAUNCH: case EXIT_REASON_VMPTRLD: @@ -7527,7 +7530,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) * VMX instructions trap unconditionally. This allows L1 to * emulate them for its L2 guest, i.e., allows 3-level nesting! */ - return 1; + return true; case EXIT_REASON_CR_ACCESS: return nested_vmx_exit_handled_cr(vcpu, vmcs12); case EXIT_REASON_DR_ACCESS: @@ -7538,7 +7541,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) case EXIT_REASON_MSR_WRITE: return nested_vmx_exit_handled_msr(vcpu, vmcs12, exit_reason); case EXIT_REASON_INVALID_STATE: - return 1; + return true; case EXIT_REASON_MWAIT_INSTRUCTION: return nested_cpu_has(vmcs12, CPU_BASED_MWAIT_EXITING); case EXIT_REASON_MONITOR_INSTRUCTION: @@ -7548,7 +7551,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) nested_cpu_has2(vmcs12, SECONDARY_EXEC_PAUSE_LOOP_EXITING); case EXIT_REASON_MCE_DURING_VMENTRY: - return 0; + return false; case EXIT_REASON_TPR_BELOW_THRESHOLD: return nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW); case EXIT_REASON_APIC_ACCESS: @@ -7557,7 +7560,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) case EXIT_REASON_APIC_WRITE: case EXIT_REASON_EOI_INDUCED: /* apic_write and eoi_induced should exit unconditionally. */ - return 1; + return true; case EXIT_REASON_EPT_VIOLATION: /* * L0 always deals with the EPT violation. If nested EPT is @@ -7565,7 +7568,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) * missing in the guest EPT table (EPT12), the EPT violation * will be injected with nested_ept_inject_page_fault() */ - return 0; + return false; case EXIT_REASON_EPT_MISCONFIG: /* * L2 never uses directly L1's EPT, but rather L0's own EPT @@ -7573,11 +7576,11 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) * (EPT on EPT). So any problems with the structure of the * table is L0's fault. */ - return 0; + return false; case EXIT_REASON_WBINVD: return nested_cpu_has2(vmcs12, SECONDARY_EXEC_WBINVD_EXITING); case EXIT_REASON_XSETBV: - return 1; + return true; case EXIT_REASON_XSAVES: case EXIT_REASON_XRSTORS: /* * This should never happen, since it is not possible to @@ -7587,7 +7590,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) */ return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES); default: - return 1; + return true; } } @@ -8522,6 +8525,9 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu) exec_control); } } + if (nested && !vmx->rdtscp_enabled) + vmx->nested.nested_vmx_secondary_ctls_high &= + ~SECONDARY_EXEC_RDTSCP; } /* Exposing INVPCID only when PCID is exposed */ @@ -8622,10 +8628,11 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { struct vcpu_vmx *vmx = to_vmx(vcpu); + int maxphyaddr = cpuid_maxphyaddr(vcpu); if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) { - /* TODO: Also verify bits beyond physical address width are 0 */ - if (!PAGE_ALIGNED(vmcs12->apic_access_addr)) + if (!PAGE_ALIGNED(vmcs12->apic_access_addr) || + vmcs12->apic_access_addr >> maxphyaddr) return false; /* @@ -8641,8 +8648,8 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu, } if (nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) { - /* TODO: Also verify bits beyond physical address width are 0 */ - if (!PAGE_ALIGNED(vmcs12->virtual_apic_page_addr)) + if (!PAGE_ALIGNED(vmcs12->virtual_apic_page_addr) || + vmcs12->virtual_apic_page_addr >> maxphyaddr) return false; if (vmx->nested.virtual_apic_page) /* shouldn't happen */ @@ -8665,7 +8672,8 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu, } if (nested_cpu_has_posted_intr(vmcs12)) { - if (!IS_ALIGNED(vmcs12->posted_intr_desc_addr, 64)) + if (!IS_ALIGNED(vmcs12->posted_intr_desc_addr, 64) || + vmcs12->posted_intr_desc_addr >> maxphyaddr) return false; if (vmx->nested.pi_desc_page) { /* shouldn't happen */ @@ -8864,9 +8872,9 @@ static int nested_vmx_check_apicv_controls(struct kvm_vcpu *vcpu, static int nested_vmx_check_msr_switch(struct kvm_vcpu *vcpu, unsigned long count_field, - unsigned long addr_field, - int maxphyaddr) + unsigned long addr_field) { + int maxphyaddr; u64 count, addr; if (vmcs12_read_any(vcpu, count_field, &count) || @@ -8876,6 +8884,7 @@ static int nested_vmx_check_msr_switch(struct kvm_vcpu *vcpu, } if (count == 0) return 0; + maxphyaddr = cpuid_maxphyaddr(vcpu); if (!IS_ALIGNED(addr, 16) || addr >> maxphyaddr || (addr + count * sizeof(struct vmx_msr_entry) - 1) >> maxphyaddr) { pr_warn_ratelimited( @@ -8889,19 +8898,16 @@ static int nested_vmx_check_msr_switch(struct kvm_vcpu *vcpu, static int nested_vmx_check_msr_switch_controls(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { - int maxphyaddr; - if (vmcs12->vm_exit_msr_load_count == 0 && vmcs12->vm_exit_msr_store_count == 0 && vmcs12->vm_entry_msr_load_count == 0) return 0; /* Fast path */ - maxphyaddr = cpuid_maxphyaddr(vcpu); if (nested_vmx_check_msr_switch(vcpu, VM_EXIT_MSR_LOAD_COUNT, - VM_EXIT_MSR_LOAD_ADDR, maxphyaddr) || + VM_EXIT_MSR_LOAD_ADDR) || nested_vmx_check_msr_switch(vcpu, VM_EXIT_MSR_STORE_COUNT, - VM_EXIT_MSR_STORE_ADDR, maxphyaddr) || + VM_EXIT_MSR_STORE_ADDR) || nested_vmx_check_msr_switch(vcpu, VM_ENTRY_MSR_LOAD_COUNT, - VM_ENTRY_MSR_LOAD_ADDR, maxphyaddr)) + VM_ENTRY_MSR_LOAD_ADDR)) return -EINVAL; return 0; } @@ -9151,8 +9157,9 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) exec_control &= ~SECONDARY_EXEC_RDTSCP; /* Take the following fields only from vmcs12 */ exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | + SECONDARY_EXEC_RDTSCP | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | - SECONDARY_EXEC_APIC_REGISTER_VIRT); + SECONDARY_EXEC_APIC_REGISTER_VIRT); if (nested_cpu_has(vmcs12, CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)) exec_control |= vmcs12->secondary_vm_exec_control; @@ -9385,7 +9392,6 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) } if (!nested_get_vmcs12_pages(vcpu, vmcs12)) { - /*TODO: Also verify bits beyond physical address width are 0*/ nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD); return 1; } @@ -9524,7 +9530,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) vmcs12->launch_state = 1; if (vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT) - return kvm_emulate_halt(vcpu); + return kvm_vcpu_halt(vcpu); vmx->nested.nested_run_pending = 1; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 32bf19ef3115..e1a81267f3f6 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -801,6 +801,17 @@ unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_get_cr8); +static void kvm_update_dr0123(struct kvm_vcpu *vcpu) +{ + int i; + + if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) { + for (i = 0; i < KVM_NR_DB_REGS; i++) + vcpu->arch.eff_db[i] = vcpu->arch.db[i]; + vcpu->arch.switch_db_regs |= KVM_DEBUGREG_RELOAD; + } +} + static void kvm_update_dr6(struct kvm_vcpu *vcpu) { if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) @@ -1070,19 +1081,19 @@ static void update_pvclock_gtod(struct timekeeper *tk) struct pvclock_gtod_data *vdata = &pvclock_gtod_data; u64 boot_ns; - boot_ns = ktime_to_ns(ktime_add(tk->tkr.base_mono, tk->offs_boot)); + boot_ns = ktime_to_ns(ktime_add(tk->tkr_mono.base, tk->offs_boot)); write_seqcount_begin(&vdata->seq); /* copy pvclock gtod data */ - vdata->clock.vclock_mode = tk->tkr.clock->archdata.vclock_mode; - vdata->clock.cycle_last = tk->tkr.cycle_last; - vdata->clock.mask = tk->tkr.mask; - vdata->clock.mult = tk->tkr.mult; - vdata->clock.shift = tk->tkr.shift; + vdata->clock.vclock_mode = tk->tkr_mono.clock->archdata.vclock_mode; + vdata->clock.cycle_last = tk->tkr_mono.cycle_last; + vdata->clock.mask = tk->tkr_mono.mask; + vdata->clock.mult = tk->tkr_mono.mult; + vdata->clock.shift = tk->tkr_mono.shift; vdata->boot_ns = boot_ns; - vdata->nsec_base = tk->tkr.xtime_nsec; + vdata->nsec_base = tk->tkr_mono.xtime_nsec; write_seqcount_end(&vdata->seq); } @@ -3149,6 +3160,7 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, return -EINVAL; memcpy(vcpu->arch.db, dbgregs->db, sizeof(vcpu->arch.db)); + kvm_update_dr0123(vcpu); vcpu->arch.dr6 = dbgregs->dr6; kvm_update_dr6(vcpu); vcpu->arch.dr7 = dbgregs->dr7; @@ -4114,8 +4126,8 @@ static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len, do { n = min(len, 8); if (!(vcpu->arch.apic && - !kvm_iodevice_write(&vcpu->arch.apic->dev, addr, n, v)) - && kvm_io_bus_write(vcpu->kvm, KVM_MMIO_BUS, addr, n, v)) + !kvm_iodevice_write(vcpu, &vcpu->arch.apic->dev, addr, n, v)) + && kvm_io_bus_write(vcpu, KVM_MMIO_BUS, addr, n, v)) break; handled += n; addr += n; @@ -4134,8 +4146,9 @@ static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v) do { n = min(len, 8); if (!(vcpu->arch.apic && - !kvm_iodevice_read(&vcpu->arch.apic->dev, addr, n, v)) - && kvm_io_bus_read(vcpu->kvm, KVM_MMIO_BUS, addr, n, v)) + !kvm_iodevice_read(vcpu, &vcpu->arch.apic->dev, + addr, n, v)) + && kvm_io_bus_read(vcpu, KVM_MMIO_BUS, addr, n, v)) break; trace_kvm_mmio(KVM_TRACE_MMIO_READ, n, addr, *(u64 *)v); handled += n; @@ -4475,7 +4488,8 @@ mmio: return X86EMUL_CONTINUE; } -int emulator_read_write(struct x86_emulate_ctxt *ctxt, unsigned long addr, +static int emulator_read_write(struct x86_emulate_ctxt *ctxt, + unsigned long addr, void *val, unsigned int bytes, struct x86_exception *exception, const struct read_write_emulator_ops *ops) @@ -4538,7 +4552,7 @@ static int emulator_read_emulated(struct x86_emulate_ctxt *ctxt, exception, &read_emultor); } -int emulator_write_emulated(struct x86_emulate_ctxt *ctxt, +static int emulator_write_emulated(struct x86_emulate_ctxt *ctxt, unsigned long addr, const void *val, unsigned int bytes, @@ -4629,10 +4643,10 @@ static int kernel_pio(struct kvm_vcpu *vcpu, void *pd) int r; if (vcpu->arch.pio.in) - r = kvm_io_bus_read(vcpu->kvm, KVM_PIO_BUS, vcpu->arch.pio.port, + r = kvm_io_bus_read(vcpu, KVM_PIO_BUS, vcpu->arch.pio.port, vcpu->arch.pio.size, pd); else - r = kvm_io_bus_write(vcpu->kvm, KVM_PIO_BUS, + r = kvm_io_bus_write(vcpu, KVM_PIO_BUS, vcpu->arch.pio.port, vcpu->arch.pio.size, pd); return r; @@ -4705,7 +4719,7 @@ static void emulator_invlpg(struct x86_emulate_ctxt *ctxt, ulong address) kvm_mmu_invlpg(emul_to_vcpu(ctxt), address); } -int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu) +int kvm_emulate_wbinvd_noskip(struct kvm_vcpu *vcpu) { if (!need_emulate_wbinvd(vcpu)) return X86EMUL_CONTINUE; @@ -4722,19 +4736,29 @@ int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu) wbinvd(); return X86EMUL_CONTINUE; } + +int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu) +{ + kvm_x86_ops->skip_emulated_instruction(vcpu); + return kvm_emulate_wbinvd_noskip(vcpu); +} EXPORT_SYMBOL_GPL(kvm_emulate_wbinvd); + + static void emulator_wbinvd(struct x86_emulate_ctxt *ctxt) { - kvm_emulate_wbinvd(emul_to_vcpu(ctxt)); + kvm_emulate_wbinvd_noskip(emul_to_vcpu(ctxt)); } -int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long *dest) +static int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, + unsigned long *dest) { return kvm_get_dr(emul_to_vcpu(ctxt), dr, dest); } -int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long value) +static int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, + unsigned long value) { return __kvm_set_dr(emul_to_vcpu(ctxt), dr, value); @@ -5816,7 +5840,7 @@ void kvm_arch_exit(void) free_percpu(shared_msrs); } -int kvm_emulate_halt(struct kvm_vcpu *vcpu) +int kvm_vcpu_halt(struct kvm_vcpu *vcpu) { ++vcpu->stat.halt_exits; if (irqchip_in_kernel(vcpu->kvm)) { @@ -5827,6 +5851,13 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu) return 0; } } +EXPORT_SYMBOL_GPL(kvm_vcpu_halt); + +int kvm_emulate_halt(struct kvm_vcpu *vcpu) +{ + kvm_x86_ops->skip_emulated_instruction(vcpu); + return kvm_vcpu_halt(vcpu); +} EXPORT_SYMBOL_GPL(kvm_emulate_halt); int kvm_hv_hypercall(struct kvm_vcpu *vcpu) @@ -5903,7 +5934,7 @@ static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid) lapic_irq.dest_id = apicid; lapic_irq.delivery_mode = APIC_DM_REMRD; - kvm_irq_delivery_to_apic(kvm, 0, &lapic_irq, NULL); + kvm_irq_delivery_to_apic(kvm, NULL, &lapic_irq, NULL); } int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) @@ -5911,6 +5942,8 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) unsigned long nr, a0, a1, a2, a3, ret; int op_64_bit, r = 1; + kvm_x86_ops->skip_emulated_instruction(vcpu); + if (kvm_hv_hypercall_enabled(vcpu->kvm)) return kvm_hv_hypercall(vcpu); @@ -6164,7 +6197,7 @@ void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm, } /* - * Returns 1 to let __vcpu_run() continue the guest execution loop without + * Returns 1 to let vcpu_run() continue the guest execution loop without * exiting to the userspace. Otherwise, the value will be returned to the * userspace. */ @@ -6301,6 +6334,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) set_debugreg(vcpu->arch.eff_db[2], 2); set_debugreg(vcpu->arch.eff_db[3], 3); set_debugreg(vcpu->arch.dr6, 6); + vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD; } trace_kvm_entry(vcpu->vcpu_id); @@ -6382,42 +6416,47 @@ out: return r; } +static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) +{ + if (!kvm_arch_vcpu_runnable(vcpu)) { + srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_block(vcpu); + vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); + if (!kvm_check_request(KVM_REQ_UNHALT, vcpu)) + return 1; + } + + kvm_apic_accept_events(vcpu); + switch(vcpu->arch.mp_state) { + case KVM_MP_STATE_HALTED: + vcpu->arch.pv.pv_unhalted = false; + vcpu->arch.mp_state = + KVM_MP_STATE_RUNNABLE; + case KVM_MP_STATE_RUNNABLE: + vcpu->arch.apf.halted = false; + break; + case KVM_MP_STATE_INIT_RECEIVED: + break; + default: + return -EINTR; + break; + } + return 1; +} -static int __vcpu_run(struct kvm_vcpu *vcpu) +static int vcpu_run(struct kvm_vcpu *vcpu) { int r; struct kvm *kvm = vcpu->kvm; vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); - r = 1; - while (r > 0) { + for (;;) { if (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && !vcpu->arch.apf.halted) r = vcpu_enter_guest(vcpu); - else { - srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); - kvm_vcpu_block(vcpu); - vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); - if (kvm_check_request(KVM_REQ_UNHALT, vcpu)) { - kvm_apic_accept_events(vcpu); - switch(vcpu->arch.mp_state) { - case KVM_MP_STATE_HALTED: - vcpu->arch.pv.pv_unhalted = false; - vcpu->arch.mp_state = - KVM_MP_STATE_RUNNABLE; - case KVM_MP_STATE_RUNNABLE: - vcpu->arch.apf.halted = false; - break; - case KVM_MP_STATE_INIT_RECEIVED: - break; - default: - r = -EINTR; - break; - } - } - } - + else + r = vcpu_block(kvm, vcpu); if (r <= 0) break; @@ -6429,6 +6468,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) r = -EINTR; vcpu->run->exit_reason = KVM_EXIT_INTR; ++vcpu->stat.request_irq_exits; + break; } kvm_check_async_pf_completion(vcpu); @@ -6437,6 +6477,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) r = -EINTR; vcpu->run->exit_reason = KVM_EXIT_INTR; ++vcpu->stat.signal_exits; + break; } if (need_resched()) { srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); @@ -6568,7 +6609,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } else WARN_ON(vcpu->arch.pio.count || vcpu->mmio_needed); - r = __vcpu_run(vcpu); + r = vcpu_run(vcpu); out: post_kvm_run_save(vcpu); @@ -7075,11 +7116,14 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu) kvm_clear_exception_queue(vcpu); memset(vcpu->arch.db, 0, sizeof(vcpu->arch.db)); + kvm_update_dr0123(vcpu); vcpu->arch.dr6 = DR6_INIT; kvm_update_dr6(vcpu); vcpu->arch.dr7 = DR7_FIXED_1; kvm_update_dr7(vcpu); + vcpu->arch.cr2 = 0; + kvm_make_request(KVM_REQ_EVENT, vcpu); vcpu->arch.apf.msr_val = 0; vcpu->arch.st.msr_val = 0; @@ -7240,7 +7284,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) vcpu->arch.pv.pv_unhalted = false; vcpu->arch.emulate_ctxt.ops = &emulate_ops; - if (!irqchip_in_kernel(kvm) || kvm_vcpu_is_bsp(vcpu)) + if (!irqchip_in_kernel(kvm) || kvm_vcpu_is_reset_bsp(vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; else vcpu->arch.mp_state = KVM_MP_STATE_UNINITIALIZED; @@ -7288,6 +7332,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) vcpu->arch.guest_supported_xcr0 = 0; vcpu->arch.guest_xstate_size = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET; + vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); + kvm_async_pf_hash_reset(vcpu); kvm_pmu_init(vcpu); @@ -7428,7 +7474,7 @@ void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { if (!dont || free->arch.rmap[i] != dont->arch.rmap[i]) { - kvm_kvfree(free->arch.rmap[i]); + kvfree(free->arch.rmap[i]); free->arch.rmap[i] = NULL; } if (i == 0) @@ -7436,7 +7482,7 @@ void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, if (!dont || free->arch.lpage_info[i - 1] != dont->arch.lpage_info[i - 1]) { - kvm_kvfree(free->arch.lpage_info[i - 1]); + kvfree(free->arch.lpage_info[i - 1]); free->arch.lpage_info[i - 1] = NULL; } } @@ -7490,12 +7536,12 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, out_free: for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { - kvm_kvfree(slot->arch.rmap[i]); + kvfree(slot->arch.rmap[i]); slot->arch.rmap[i] = NULL; if (i == 0) continue; - kvm_kvfree(slot->arch.lpage_info[i - 1]); + kvfree(slot->arch.lpage_info[i - 1]); slot->arch.lpage_info[i - 1] = NULL; } return -ENOMEM; @@ -7618,6 +7664,23 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, new = id_to_memslot(kvm->memslots, mem->slot); /* + * Dirty logging tracks sptes in 4k granularity, meaning that large + * sptes have to be split. If live migration is successful, the guest + * in the source machine will be destroyed and large sptes will be + * created in the destination. However, if the guest continues to run + * in the source machine (for example if live migration fails), small + * sptes will remain around and cause bad performance. + * + * Scan sptes if dirty logging has been stopped, dropping those + * which can be collapsed into a single large-page spte. Later + * page faults will create the large-page sptes. + */ + if ((change != KVM_MR_DELETE) && + (old->flags & KVM_MEM_LOG_DIRTY_PAGES) && + !(new->flags & KVM_MEM_LOG_DIRTY_PAGES)) + kvm_mmu_zap_collapsible_sptes(kvm, new); + + /* * Set up write protection and/or dirty logging for the new slot. * * For KVM_MR_DELETE and KVM_MR_MOVE, the shadow pages of old slot have diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index c905e89e19fe..1f33b3d1fd68 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -69,21 +69,20 @@ EXPORT_SYMBOL(copy_in_user); * it is not necessary to optimize tail handling. */ __visible unsigned long -copy_user_handle_tail(char *to, char *from, unsigned len, unsigned zerorest) +copy_user_handle_tail(char *to, char *from, unsigned len) { - char c; - unsigned zero_len; - for (; len; --len, to++) { + char c; + if (__get_user_nocheck(c, from++, sizeof(char))) break; if (__put_user_nocheck(c, to, sizeof(char))) break; } - - for (c = 0, zero_len = len; zerorest && zero_len; --zero_len) - if (__put_user_nocheck(c, to++, sizeof(char))) - break; clac(); + + /* If the destination is a kernel buffer, we always clear the end */ + if ((unsigned long)to >= TASK_SIZE_MAX) + memset(to, 0, len); return len; } diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index dbc8627a5cdf..02744df576d5 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -85,12 +85,20 @@ static efi_status_t __init phys_efi_set_virtual_address_map( efi_memory_desc_t *virtual_map) { efi_status_t status; + unsigned long flags; + pgd_t *save_pgd; - efi_call_phys_prolog(); + save_pgd = efi_call_phys_prolog(); + + /* Disable interrupts around EFI calls: */ + local_irq_save(flags); status = efi_call_phys(efi_phys.set_virtual_address_map, memory_map_size, descriptor_size, descriptor_version, virtual_map); - efi_call_phys_epilog(); + local_irq_restore(flags); + + efi_call_phys_epilog(save_pgd); + return status; } @@ -491,7 +499,8 @@ void __init efi_init(void) if (efi_memmap_init()) return; - print_efi_memmap(); + if (efi_enabled(EFI_DBG)) + print_efi_memmap(); } void __init efi_late_init(void) @@ -939,6 +948,8 @@ static int __init arch_parse_efi_cmdline(char *str) { if (parse_option_str(str, "old_map")) set_bit(EFI_OLD_MEMMAP, &efi.flags); + if (parse_option_str(str, "debug")) + set_bit(EFI_DBG, &efi.flags); return 0; } diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c index 40e7cda52936..ed5b67338294 100644 --- a/arch/x86/platform/efi/efi_32.c +++ b/arch/x86/platform/efi/efi_32.c @@ -33,11 +33,10 @@ /* * To make EFI call EFI runtime service in physical addressing mode we need - * prolog/epilog before/after the invocation to disable interrupt, to - * claim EFI runtime service handler exclusively and to duplicate a memory in - * low memory space say 0 - 3G. + * prolog/epilog before/after the invocation to claim the EFI runtime service + * handler exclusively and to duplicate a memory mapping in low memory space, + * say 0 - 3G. */ -static unsigned long efi_rt_eflags; void efi_sync_low_kernel_mappings(void) {} void __init efi_dump_pagetable(void) {} @@ -57,21 +56,24 @@ void __init efi_map_region(efi_memory_desc_t *md) void __init efi_map_region_fixed(efi_memory_desc_t *md) {} void __init parse_efi_setup(u64 phys_addr, u32 data_len) {} -void __init efi_call_phys_prolog(void) +pgd_t * __init efi_call_phys_prolog(void) { struct desc_ptr gdt_descr; + pgd_t *save_pgd; - local_irq_save(efi_rt_eflags); - + /* Current pgd is swapper_pg_dir, we'll restore it later: */ + save_pgd = swapper_pg_dir; load_cr3(initial_page_table); __flush_tlb_all(); gdt_descr.address = __pa(get_cpu_gdt_table(0)); gdt_descr.size = GDT_SIZE - 1; load_gdt(&gdt_descr); + + return save_pgd; } -void __init efi_call_phys_epilog(void) +void __init efi_call_phys_epilog(pgd_t *save_pgd) { struct desc_ptr gdt_descr; @@ -79,10 +81,8 @@ void __init efi_call_phys_epilog(void) gdt_descr.size = GDT_SIZE - 1; load_gdt(&gdt_descr); - load_cr3(swapper_pg_dir); + load_cr3(save_pgd); __flush_tlb_all(); - - local_irq_restore(efi_rt_eflags); } void __init efi_runtime_mkexec(void) diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 17e80d829df0..a0ac0f9c307f 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -41,9 +41,6 @@ #include <asm/realmode.h> #include <asm/time.h> -static pgd_t *save_pgd __initdata; -static unsigned long efi_flags __initdata; - /* * We allocate runtime services regions bottom-up, starting from -4G, i.e. * 0xffff_ffff_0000_0000 and limit EFI VA mapping space to 64G. @@ -78,17 +75,18 @@ static void __init early_code_mapping_set_exec(int executable) } } -void __init efi_call_phys_prolog(void) +pgd_t * __init efi_call_phys_prolog(void) { unsigned long vaddress; + pgd_t *save_pgd; + int pgd; int n_pgds; if (!efi_enabled(EFI_OLD_MEMMAP)) - return; + return NULL; early_code_mapping_set_exec(1); - local_irq_save(efi_flags); n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT), PGDIR_SIZE); save_pgd = kmalloc(n_pgds * sizeof(pgd_t), GFP_KERNEL); @@ -99,24 +97,29 @@ void __init efi_call_phys_prolog(void) set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), *pgd_offset_k(vaddress)); } __flush_tlb_all(); + + return save_pgd; } -void __init efi_call_phys_epilog(void) +void __init efi_call_phys_epilog(pgd_t *save_pgd) { /* * After the lock is released, the original page table is restored. */ - int pgd; - int n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT) , PGDIR_SIZE); + int pgd_idx; + int nr_pgds; - if (!efi_enabled(EFI_OLD_MEMMAP)) + if (!save_pgd) return; - for (pgd = 0; pgd < n_pgds; pgd++) - set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), save_pgd[pgd]); + nr_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT) , PGDIR_SIZE); + + for (pgd_idx = 0; pgd_idx < nr_pgds; pgd_idx++) + set_pgd(pgd_offset_k(pgd_idx * PGDIR_SIZE), save_pgd[pgd_idx]); + kfree(save_pgd); + __flush_tlb_all(); - local_irq_restore(efi_flags); early_code_mapping_set_exec(0); } diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c index 9793322751e0..40d2473836c9 100644 --- a/arch/x86/vdso/vclock_gettime.c +++ b/arch/x86/vdso/vclock_gettime.c @@ -82,18 +82,15 @@ static notrace cycle_t vread_pvclock(int *mode) cycle_t ret; u64 last; u32 version; + u32 migrate_count; u8 flags; unsigned cpu, cpu1; /* - * Note: hypervisor must guarantee that: - * 1. cpu ID number maps 1:1 to per-CPU pvclock time info. - * 2. that per-CPU pvclock time info is updated if the - * underlying CPU changes. - * 3. that version is increased whenever underlying CPU - * changes. - * + * When looping to get a consistent (time-info, tsc) pair, we + * also need to deal with the possibility we can switch vcpus, + * so make sure we always re-fetch time-info for the current vcpu. */ do { cpu = __getcpu() & VGETCPU_CPU_MASK; @@ -102,20 +99,27 @@ static notrace cycle_t vread_pvclock(int *mode) * __getcpu() calls (Gleb). */ - pvti = get_pvti(cpu); + /* Make sure migrate_count will change if we leave the VCPU. */ + do { + pvti = get_pvti(cpu); + migrate_count = pvti->migrate_count; + + cpu1 = cpu; + cpu = __getcpu() & VGETCPU_CPU_MASK; + } while (unlikely(cpu != cpu1)); version = __pvclock_read_cycles(&pvti->pvti, &ret, &flags); /* * Test we're still on the cpu as well as the version. - * We could have been migrated just after the first - * vgetcpu but before fetching the version, so we - * wouldn't notice a version change. + * - We must read TSC of pvti's VCPU. + * - KVM doesn't follow the versioning protocol, so data could + * change before version if we left the VCPU. */ - cpu1 = __getcpu() & VGETCPU_CPU_MASK; - } while (unlikely(cpu != cpu1 || - (pvti->pvti.version & 1) || - pvti->pvti.version != version)); + smp_rmb(); + } while (unlikely((pvti->pvti.version & 1) || + pvti->pvti.version != version || + pvti->migrate_count != migrate_count)); if (unlikely(!(flags & PVCLOCK_TSC_STABLE_BIT))) *mode = VCLOCK_NONE; diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index c4df9dbd63b7..d9497698645a 100644 --- a/arch/x86/xen/suspend.c +++ b/arch/x86/xen/suspend.c @@ -1,5 +1,5 @@ #include <linux/types.h> -#include <linux/clockchips.h> +#include <linux/tick.h> #include <xen/interface/xen.h> #include <xen/grant_table.h> @@ -81,17 +81,14 @@ void xen_arch_post_suspend(int cancelled) static void xen_vcpu_notify_restore(void *data) { - unsigned long reason = (unsigned long)data; - /* Boot processor notified via generic timekeeping_resume() */ - if ( smp_processor_id() == 0) + if (smp_processor_id() == 0) return; - clockevents_notify(reason, NULL); + tick_resume_local(); } void xen_arch_resume(void) { - on_each_cpu(xen_vcpu_notify_restore, - (void *)CLOCK_EVT_NOTIFY_RESUME, 1); + on_each_cpu(xen_vcpu_notify_restore, NULL, 1); } diff --git a/block/blk-mq.c b/block/blk-mq.c index b7b8933ec241..33c428530193 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1457,7 +1457,7 @@ static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set, do { page = alloc_pages_node(set->numa_node, - GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY, + GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO, this_order); if (page) break; @@ -1479,8 +1479,6 @@ static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set, left -= to_do * rq_size; for (j = 0; j < to_do; j++) { tags->rqs[i] = p; - tags->rqs[i]->atomic_flags = 0; - tags->rqs[i]->cmd_flags = 0; if (set->ops->init_request) { if (set->ops->init_request(set->driver_data, tags->rqs[i], hctx_idx, i, diff --git a/drivers/acpi/acpi_pad.c b/drivers/acpi/acpi_pad.c index c7b105c0e1d3..6bc9cbc01ad6 100644 --- a/drivers/acpi/acpi_pad.c +++ b/drivers/acpi/acpi_pad.c @@ -26,7 +26,7 @@ #include <linux/kthread.h> #include <linux/freezer.h> #include <linux/cpu.h> -#include <linux/clockchips.h> +#include <linux/tick.h> #include <linux/slab.h> #include <linux/acpi.h> #include <asm/mwait.h> @@ -41,8 +41,6 @@ static unsigned long power_saving_mwait_eax; static unsigned char tsc_detected_unstable; static unsigned char tsc_marked_unstable; -static unsigned char lapic_detected_unstable; -static unsigned char lapic_marked_unstable; static void power_saving_mwait_init(void) { @@ -82,13 +80,10 @@ static void power_saving_mwait_init(void) */ if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC)) tsc_detected_unstable = 1; - if (!boot_cpu_has(X86_FEATURE_ARAT)) - lapic_detected_unstable = 1; break; default: - /* TSC & LAPIC could halt in idle */ + /* TSC could halt in idle */ tsc_detected_unstable = 1; - lapic_detected_unstable = 1; } #endif } @@ -155,7 +150,6 @@ static int power_saving_thread(void *data) sched_setscheduler(current, SCHED_RR, ¶m); while (!kthread_should_stop()) { - int cpu; unsigned long expire_time; try_to_freeze(); @@ -177,28 +171,15 @@ static int power_saving_thread(void *data) mark_tsc_unstable("TSC halts in idle"); tsc_marked_unstable = 1; } - if (lapic_detected_unstable && !lapic_marked_unstable) { - int i; - /* LAPIC could halt in idle, so notify users */ - for_each_online_cpu(i) - clockevents_notify( - CLOCK_EVT_NOTIFY_BROADCAST_ON, - &i); - lapic_marked_unstable = 1; - } local_irq_disable(); - cpu = smp_processor_id(); - if (lapic_marked_unstable) - clockevents_notify( - CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu); + tick_broadcast_enable(); + tick_broadcast_enter(); stop_critical_timings(); mwait_idle_with_hints(power_saving_mwait_eax, 1); start_critical_timings(); - if (lapic_marked_unstable) - clockevents_notify( - CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu); + tick_broadcast_exit(); local_irq_enable(); if (time_before(expire_time, jiffies)) { diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index c6bb9f1257c9..39e0c8e36244 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -32,7 +32,7 @@ #include <linux/acpi.h> #include <linux/dmi.h> #include <linux/sched.h> /* need_resched() */ -#include <linux/clockchips.h> +#include <linux/tick.h> #include <linux/cpuidle.h> #include <linux/syscore_ops.h> #include <acpi/processor.h> @@ -157,12 +157,11 @@ static void lapic_timer_check_state(int state, struct acpi_processor *pr, static void __lapic_timer_propagate_broadcast(void *arg) { struct acpi_processor *pr = (struct acpi_processor *) arg; - unsigned long reason; - reason = pr->power.timer_broadcast_on_state < INT_MAX ? - CLOCK_EVT_NOTIFY_BROADCAST_ON : CLOCK_EVT_NOTIFY_BROADCAST_OFF; - - clockevents_notify(reason, &pr->id); + if (pr->power.timer_broadcast_on_state < INT_MAX) + tick_broadcast_enable(); + else + tick_broadcast_disable(); } static void lapic_timer_propagate_broadcast(struct acpi_processor *pr) @@ -179,11 +178,10 @@ static void lapic_timer_state_broadcast(struct acpi_processor *pr, int state = cx - pr->power.states; if (state >= pr->power.timer_broadcast_on_state) { - unsigned long reason; - - reason = broadcast ? CLOCK_EVT_NOTIFY_BROADCAST_ENTER : - CLOCK_EVT_NOTIFY_BROADCAST_EXIT; - clockevents_notify(reason, &pr->id); + if (broadcast) + tick_broadcast_enter(); + else + tick_broadcast_exit(); } } @@ -922,7 +920,7 @@ static int acpi_processor_setup_cpuidle_states(struct acpi_processor *pr) return -EINVAL; drv->safe_state_index = -1; - for (i = 0; i < CPUIDLE_STATE_MAX; i++) { + for (i = CPUIDLE_DRIVER_STATE_START; i < CPUIDLE_STATE_MAX; i++) { drv->states[i].name[0] = '\0'; drv->states[i].desc[0] = '\0'; } diff --git a/drivers/char/ipmi/ipmi_powernv.c b/drivers/char/ipmi/ipmi_powernv.c index 79524ed2a3cb..8753b0f6a317 100644 --- a/drivers/char/ipmi/ipmi_powernv.c +++ b/drivers/char/ipmi/ipmi_powernv.c @@ -125,6 +125,7 @@ static int ipmi_powernv_recv(struct ipmi_smi_powernv *smi) spin_lock_irqsave(&smi->msg_lock, flags); if (!smi->cur_msg) { + spin_unlock_irqrestore(&smi->msg_lock, flags); pr_warn("no current message?\n"); return 0; } diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c index f6646ed3047e..518585c1ce94 100644 --- a/drivers/char/ipmi/ipmi_si_intf.c +++ b/drivers/char/ipmi/ipmi_si_intf.c @@ -263,6 +263,11 @@ struct smi_info { bool supports_event_msg_buff; /* + * Can we clear the global enables receive irq bit? + */ + bool cannot_clear_recv_irq_bit; + + /* * Did we get an attention that we did not handle? */ bool got_attn; @@ -461,6 +466,9 @@ static void smi_mod_timer(struct smi_info *smi_info, unsigned long new_val) * allocate messages, we just leave them in the BMC and run the system * polled until we can allocate some memory. Once we have some * memory, we will re-enable the interrupt. + * + * Note that we cannot just use disable_irq(), since the interrupt may + * be shared. */ static inline bool disable_si_irq(struct smi_info *smi_info) { @@ -549,20 +557,15 @@ static u8 current_global_enables(struct smi_info *smi_info, u8 base, if (smi_info->supports_event_msg_buff) enables |= IPMI_BMC_EVT_MSG_BUFF; - else - enables &= ~IPMI_BMC_EVT_MSG_BUFF; - if (smi_info->irq && !smi_info->interrupt_disabled) + if ((smi_info->irq && !smi_info->interrupt_disabled) || + smi_info->cannot_clear_recv_irq_bit) enables |= IPMI_BMC_RCV_MSG_INTR; - else - enables &= ~IPMI_BMC_RCV_MSG_INTR; if (smi_info->supports_event_msg_buff && smi_info->irq && !smi_info->interrupt_disabled) enables |= IPMI_BMC_EVT_MSG_INTR; - else - enables &= ~IPMI_BMC_EVT_MSG_INTR; *irq_on = enables & (IPMI_BMC_EVT_MSG_INTR | IPMI_BMC_RCV_MSG_INTR); @@ -2900,6 +2903,96 @@ static int try_get_dev_id(struct smi_info *smi_info) return rv; } +/* + * Some BMCs do not support clearing the receive irq bit in the global + * enables (even if they don't support interrupts on the BMC). Check + * for this and handle it properly. + */ +static void check_clr_rcv_irq(struct smi_info *smi_info) +{ + unsigned char msg[3]; + unsigned char *resp; + unsigned long resp_len; + int rv; + + resp = kmalloc(IPMI_MAX_MSG_LENGTH, GFP_KERNEL); + if (!resp) { + printk(KERN_WARNING PFX "Out of memory allocating response for" + " global enables command, cannot check recv irq bit" + " handling.\n"); + return; + } + + msg[0] = IPMI_NETFN_APP_REQUEST << 2; + msg[1] = IPMI_GET_BMC_GLOBAL_ENABLES_CMD; + smi_info->handlers->start_transaction(smi_info->si_sm, msg, 2); + + rv = wait_for_msg_done(smi_info); + if (rv) { + printk(KERN_WARNING PFX "Error getting response from get" + " global enables command, cannot check recv irq bit" + " handling.\n"); + goto out; + } + + resp_len = smi_info->handlers->get_result(smi_info->si_sm, + resp, IPMI_MAX_MSG_LENGTH); + + if (resp_len < 4 || + resp[0] != (IPMI_NETFN_APP_REQUEST | 1) << 2 || + resp[1] != IPMI_GET_BMC_GLOBAL_ENABLES_CMD || + resp[2] != 0) { + printk(KERN_WARNING PFX "Invalid return from get global" + " enables command, cannot check recv irq bit" + " handling.\n"); + rv = -EINVAL; + goto out; + } + + if ((resp[3] & IPMI_BMC_RCV_MSG_INTR) == 0) + /* Already clear, should work ok. */ + goto out; + + msg[0] = IPMI_NETFN_APP_REQUEST << 2; + msg[1] = IPMI_SET_BMC_GLOBAL_ENABLES_CMD; + msg[2] = resp[3] & ~IPMI_BMC_RCV_MSG_INTR; + smi_info->handlers->start_transaction(smi_info->si_sm, msg, 3); + + rv = wait_for_msg_done(smi_info); + if (rv) { + printk(KERN_WARNING PFX "Error getting response from set" + " global enables command, cannot check recv irq bit" + " handling.\n"); + goto out; + } + + resp_len = smi_info->handlers->get_result(smi_info->si_sm, + resp, IPMI_MAX_MSG_LENGTH); + + if (resp_len < 3 || + resp[0] != (IPMI_NETFN_APP_REQUEST | 1) << 2 || + resp[1] != IPMI_SET_BMC_GLOBAL_ENABLES_CMD) { + printk(KERN_WARNING PFX "Invalid return from get global" + " enables command, cannot check recv irq bit" + " handling.\n"); + rv = -EINVAL; + goto out; + } + + if (resp[2] != 0) { + /* + * An error when setting the event buffer bit means + * clearing the bit is not supported. + */ + printk(KERN_WARNING PFX "The BMC does not support clearing" + " the recv irq bit, compensating, but the BMC needs to" + " be fixed.\n"); + smi_info->cannot_clear_recv_irq_bit = true; + } + out: + kfree(resp); +} + static int try_enable_event_buffer(struct smi_info *smi_info) { unsigned char msg[3]; @@ -3395,6 +3488,8 @@ static int try_smi_init(struct smi_info *new_smi) goto out_err; } + check_clr_rcv_irq(new_smi); + setup_oem_data_handler(new_smi); setup_xaction_handlers(new_smi); diff --git a/drivers/char/ipmi/ipmi_ssif.c b/drivers/char/ipmi/ipmi_ssif.c index f6e378dac5f5..f40e3bd2c69c 100644 --- a/drivers/char/ipmi/ipmi_ssif.c +++ b/drivers/char/ipmi/ipmi_ssif.c @@ -468,11 +468,13 @@ static int ipmi_ssif_thread(void *data) int result; /* Wait for something to do */ - wait_for_completion(&ssif_info->wake_thread); - init_completion(&ssif_info->wake_thread); - + result = wait_for_completion_interruptible( + &ssif_info->wake_thread); if (ssif_info->stopping) break; + if (result == -ERESTARTSYS) + continue; + init_completion(&ssif_info->wake_thread); if (ssif_info->i2c_read_write == I2C_SMBUS_WRITE) { result = i2c_smbus_write_block_data( diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c index a3025e7ae35f..266469691e58 100644 --- a/drivers/clocksource/arm_arch_timer.c +++ b/drivers/clocksource/arm_arch_timer.c @@ -661,17 +661,17 @@ static const struct of_device_id arch_timer_mem_of_match[] __initconst = { }; static bool __init -arch_timer_probed(int type, const struct of_device_id *matches) +arch_timer_needs_probing(int type, const struct of_device_id *matches) { struct device_node *dn; - bool probed = true; + bool needs_probing = false; dn = of_find_matching_node(NULL, matches); if (dn && of_device_is_available(dn) && !(arch_timers_present & type)) - probed = false; + needs_probing = true; of_node_put(dn); - return probed; + return needs_probing; } static void __init arch_timer_common_init(void) @@ -680,9 +680,9 @@ static void __init arch_timer_common_init(void) /* Wait until both nodes are probed if we have two timers */ if ((arch_timers_present & mask) != mask) { - if (!arch_timer_probed(ARCH_MEM_TIMER, arch_timer_mem_of_match)) + if (arch_timer_needs_probing(ARCH_MEM_TIMER, arch_timer_mem_of_match)) return; - if (!arch_timer_probed(ARCH_CP15_TIMER, arch_timer_of_match)) + if (arch_timer_needs_probing(ARCH_CP15_TIMER, arch_timer_of_match)) return; } diff --git a/drivers/clocksource/dw_apb_timer_of.c b/drivers/clocksource/dw_apb_timer_of.c index d305fb089767..a19a3f619cc7 100644 --- a/drivers/clocksource/dw_apb_timer_of.c +++ b/drivers/clocksource/dw_apb_timer_of.c @@ -108,7 +108,7 @@ static void __init add_clocksource(struct device_node *source_timer) static u64 notrace read_sched_clock(void) { - return ~__raw_readl(sched_io_base); + return ~readl_relaxed(sched_io_base); } static const struct of_device_id sptimer_ids[] __initconst = { diff --git a/drivers/clocksource/em_sti.c b/drivers/clocksource/em_sti.c index d0a7bd66b8b9..dc3c6ee04aaa 100644 --- a/drivers/clocksource/em_sti.c +++ b/drivers/clocksource/em_sti.c @@ -210,7 +210,7 @@ static int em_sti_clocksource_enable(struct clocksource *cs) ret = em_sti_start(p, USER_CLOCKSOURCE); if (!ret) - __clocksource_updatefreq_hz(cs, p->rate); + __clocksource_update_freq_hz(cs, p->rate); return ret; } diff --git a/drivers/clocksource/sh_cmt.c b/drivers/clocksource/sh_cmt.c index 2bd13b53b727..b8ff3c64cc45 100644 --- a/drivers/clocksource/sh_cmt.c +++ b/drivers/clocksource/sh_cmt.c @@ -641,7 +641,7 @@ static int sh_cmt_clocksource_enable(struct clocksource *cs) ret = sh_cmt_start(ch, FLAG_CLOCKSOURCE); if (!ret) { - __clocksource_updatefreq_hz(cs, ch->rate); + __clocksource_update_freq_hz(cs, ch->rate); ch->cs_enabled = true; } return ret; diff --git a/drivers/clocksource/sh_tmu.c b/drivers/clocksource/sh_tmu.c index f150ca82bfaf..b6b8fa3cd211 100644 --- a/drivers/clocksource/sh_tmu.c +++ b/drivers/clocksource/sh_tmu.c @@ -272,7 +272,7 @@ static int sh_tmu_clocksource_enable(struct clocksource *cs) ret = sh_tmu_enable(ch); if (!ret) { - __clocksource_updatefreq_hz(cs, ch->rate); + __clocksource_update_freq_hz(cs, ch->rate); ch->cs_enabled = true; } diff --git a/drivers/clocksource/sun4i_timer.c b/drivers/clocksource/sun4i_timer.c index f4a9c0058b4d..1928a8912584 100644 --- a/drivers/clocksource/sun4i_timer.c +++ b/drivers/clocksource/sun4i_timer.c @@ -170,7 +170,15 @@ static void __init sun4i_timer_init(struct device_node *node) TIMER_CTL_CLK_SRC(TIMER_CTL_CLK_SRC_OSC24M), timer_base + TIMER_CTL_REG(1)); - sched_clock_register(sun4i_timer_sched_read, 32, rate); + /* + * sched_clock_register does not have priorities, and on sun6i and + * later there is a better sched_clock registered by arm_arch_timer.c + */ + if (of_machine_is_compatible("allwinner,sun4i-a10") || + of_machine_is_compatible("allwinner,sun5i-a13") || + of_machine_is_compatible("allwinner,sun5i-a10s")) + sched_clock_register(sun4i_timer_sched_read, 32, rate); + clocksource_mmio_init(timer_base + TIMER_CNTVAL_REG(1), node->name, rate, 350, 32, clocksource_mmio_readl_down); diff --git a/drivers/clocksource/tegra20_timer.c b/drivers/clocksource/tegra20_timer.c index d2616ef16770..5a112d72fc2d 100644 --- a/drivers/clocksource/tegra20_timer.c +++ b/drivers/clocksource/tegra20_timer.c @@ -51,15 +51,15 @@ static void __iomem *timer_reg_base; static void __iomem *rtc_base; -static struct timespec persistent_ts; +static struct timespec64 persistent_ts; static u64 persistent_ms, last_persistent_ms; static struct delay_timer tegra_delay_timer; #define timer_writel(value, reg) \ - __raw_writel(value, timer_reg_base + (reg)) + writel_relaxed(value, timer_reg_base + (reg)) #define timer_readl(reg) \ - __raw_readl(timer_reg_base + (reg)) + readl_relaxed(timer_reg_base + (reg)) static int tegra_timer_set_next_event(unsigned long cycles, struct clock_event_device *evt) @@ -120,26 +120,25 @@ static u64 tegra_rtc_read_ms(void) } /* - * tegra_read_persistent_clock - Return time from a persistent clock. + * tegra_read_persistent_clock64 - Return time from a persistent clock. * * Reads the time from a source which isn't disabled during PM, the * 32k sync timer. Convert the cycles elapsed since last read into - * nsecs and adds to a monotonically increasing timespec. + * nsecs and adds to a monotonically increasing timespec64. * Care must be taken that this funciton is not called while the * tegra_rtc driver could be executing to avoid race conditions * on the RTC shadow register */ -static void tegra_read_persistent_clock(struct timespec *ts) +static void tegra_read_persistent_clock64(struct timespec64 *ts) { u64 delta; - struct timespec *tsp = &persistent_ts; last_persistent_ms = persistent_ms; persistent_ms = tegra_rtc_read_ms(); delta = persistent_ms - last_persistent_ms; - timespec_add_ns(tsp, delta * NSEC_PER_MSEC); - *ts = *tsp; + timespec64_add_ns(&persistent_ts, delta * NSEC_PER_MSEC); + *ts = persistent_ts; } static unsigned long tegra_delay_timer_read_counter_long(void) @@ -252,7 +251,7 @@ static void __init tegra20_init_rtc(struct device_node *np) else clk_prepare_enable(clk); - register_persistent_clock(NULL, tegra_read_persistent_clock); + register_persistent_clock(NULL, tegra_read_persistent_clock64); } CLOCKSOURCE_OF_DECLARE(tegra20_rtc, "nvidia,tegra20-rtc", tegra20_init_rtc); diff --git a/drivers/clocksource/time-efm32.c b/drivers/clocksource/time-efm32.c index ec57ba2bbd87..5b6e3d5644c9 100644 --- a/drivers/clocksource/time-efm32.c +++ b/drivers/clocksource/time-efm32.c @@ -111,7 +111,7 @@ static irqreturn_t efm32_clock_event_handler(int irq, void *dev_id) static struct efm32_clock_event_ddata clock_event_ddata = { .evtdev = { .name = "efm32 clockevent", - .features = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_MODE_PERIODIC, + .features = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_PERIODIC, .set_mode = efm32_clock_event_set_mode, .set_next_event = efm32_clock_event_set_next_event, .rating = 200, diff --git a/drivers/clocksource/timer-atmel-pit.c b/drivers/clocksource/timer-atmel-pit.c index b5b4d4585c9a..c0304ff608b0 100644 --- a/drivers/clocksource/timer-atmel-pit.c +++ b/drivers/clocksource/timer-atmel-pit.c @@ -61,12 +61,12 @@ static inline struct pit_data *clkevt_to_pit_data(struct clock_event_device *clk static inline unsigned int pit_read(void __iomem *base, unsigned int reg_offset) { - return __raw_readl(base + reg_offset); + return readl_relaxed(base + reg_offset); } static inline void pit_write(void __iomem *base, unsigned int reg_offset, unsigned long value) { - __raw_writel(value, base + reg_offset); + writel_relaxed(value, base + reg_offset); } /* diff --git a/drivers/clocksource/timer-sun5i.c b/drivers/clocksource/timer-sun5i.c index 58597fbcc046..28aa4b7bb602 100644 --- a/drivers/clocksource/timer-sun5i.c +++ b/drivers/clocksource/timer-sun5i.c @@ -17,6 +17,7 @@ #include <linux/irq.h> #include <linux/irqreturn.h> #include <linux/reset.h> +#include <linux/slab.h> #include <linux/of.h> #include <linux/of_address.h> #include <linux/of_irq.h> @@ -36,8 +37,31 @@ #define TIMER_SYNC_TICKS 3 -static void __iomem *timer_base; -static u32 ticks_per_jiffy; +struct sun5i_timer { + void __iomem *base; + struct clk *clk; + struct notifier_block clk_rate_cb; + u32 ticks_per_jiffy; +}; + +#define to_sun5i_timer(x) \ + container_of(x, struct sun5i_timer, clk_rate_cb) + +struct sun5i_timer_clksrc { + struct sun5i_timer timer; + struct clocksource clksrc; +}; + +#define to_sun5i_timer_clksrc(x) \ + container_of(x, struct sun5i_timer_clksrc, clksrc) + +struct sun5i_timer_clkevt { + struct sun5i_timer timer; + struct clock_event_device clkevt; +}; + +#define to_sun5i_timer_clkevt(x) \ + container_of(x, struct sun5i_timer_clkevt, clkevt) /* * When we disable a timer, we need to wait at least for 2 cycles of @@ -45,30 +69,30 @@ static u32 ticks_per_jiffy; * that is already setup and runs at the same frequency than the other * timers, and we never will be disabled. */ -static void sun5i_clkevt_sync(void) +static void sun5i_clkevt_sync(struct sun5i_timer_clkevt *ce) { - u32 old = readl(timer_base + TIMER_CNTVAL_LO_REG(1)); + u32 old = readl(ce->timer.base + TIMER_CNTVAL_LO_REG(1)); - while ((old - readl(timer_base + TIMER_CNTVAL_LO_REG(1))) < TIMER_SYNC_TICKS) + while ((old - readl(ce->timer.base + TIMER_CNTVAL_LO_REG(1))) < TIMER_SYNC_TICKS) cpu_relax(); } -static void sun5i_clkevt_time_stop(u8 timer) +static void sun5i_clkevt_time_stop(struct sun5i_timer_clkevt *ce, u8 timer) { - u32 val = readl(timer_base + TIMER_CTL_REG(timer)); - writel(val & ~TIMER_CTL_ENABLE, timer_base + TIMER_CTL_REG(timer)); + u32 val = readl(ce->timer.base + TIMER_CTL_REG(timer)); + writel(val & ~TIMER_CTL_ENABLE, ce->timer.base + TIMER_CTL_REG(timer)); - sun5i_clkevt_sync(); + sun5i_clkevt_sync(ce); } -static void sun5i_clkevt_time_setup(u8 timer, u32 delay) +static void sun5i_clkevt_time_setup(struct sun5i_timer_clkevt *ce, u8 timer, u32 delay) { - writel(delay, timer_base + TIMER_INTVAL_LO_REG(timer)); + writel(delay, ce->timer.base + TIMER_INTVAL_LO_REG(timer)); } -static void sun5i_clkevt_time_start(u8 timer, bool periodic) +static void sun5i_clkevt_time_start(struct sun5i_timer_clkevt *ce, u8 timer, bool periodic) { - u32 val = readl(timer_base + TIMER_CTL_REG(timer)); + u32 val = readl(ce->timer.base + TIMER_CTL_REG(timer)); if (periodic) val &= ~TIMER_CTL_ONESHOT; @@ -76,75 +100,230 @@ static void sun5i_clkevt_time_start(u8 timer, bool periodic) val |= TIMER_CTL_ONESHOT; writel(val | TIMER_CTL_ENABLE | TIMER_CTL_RELOAD, - timer_base + TIMER_CTL_REG(timer)); + ce->timer.base + TIMER_CTL_REG(timer)); } static void sun5i_clkevt_mode(enum clock_event_mode mode, - struct clock_event_device *clk) + struct clock_event_device *clkevt) { + struct sun5i_timer_clkevt *ce = to_sun5i_timer_clkevt(clkevt); + switch (mode) { case CLOCK_EVT_MODE_PERIODIC: - sun5i_clkevt_time_stop(0); - sun5i_clkevt_time_setup(0, ticks_per_jiffy); - sun5i_clkevt_time_start(0, true); + sun5i_clkevt_time_stop(ce, 0); + sun5i_clkevt_time_setup(ce, 0, ce->timer.ticks_per_jiffy); + sun5i_clkevt_time_start(ce, 0, true); break; case CLOCK_EVT_MODE_ONESHOT: - sun5i_clkevt_time_stop(0); - sun5i_clkevt_time_start(0, false); + sun5i_clkevt_time_stop(ce, 0); + sun5i_clkevt_time_start(ce, 0, false); break; case CLOCK_EVT_MODE_UNUSED: case CLOCK_EVT_MODE_SHUTDOWN: default: - sun5i_clkevt_time_stop(0); + sun5i_clkevt_time_stop(ce, 0); break; } } static int sun5i_clkevt_next_event(unsigned long evt, - struct clock_event_device *unused) + struct clock_event_device *clkevt) { - sun5i_clkevt_time_stop(0); - sun5i_clkevt_time_setup(0, evt - TIMER_SYNC_TICKS); - sun5i_clkevt_time_start(0, false); + struct sun5i_timer_clkevt *ce = to_sun5i_timer_clkevt(clkevt); + + sun5i_clkevt_time_stop(ce, 0); + sun5i_clkevt_time_setup(ce, 0, evt - TIMER_SYNC_TICKS); + sun5i_clkevt_time_start(ce, 0, false); return 0; } -static struct clock_event_device sun5i_clockevent = { - .name = "sun5i_tick", - .rating = 340, - .features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT, - .set_mode = sun5i_clkevt_mode, - .set_next_event = sun5i_clkevt_next_event, -}; - - static irqreturn_t sun5i_timer_interrupt(int irq, void *dev_id) { - struct clock_event_device *evt = (struct clock_event_device *)dev_id; + struct sun5i_timer_clkevt *ce = (struct sun5i_timer_clkevt *)dev_id; - writel(0x1, timer_base + TIMER_IRQ_ST_REG); - evt->event_handler(evt); + writel(0x1, ce->timer.base + TIMER_IRQ_ST_REG); + ce->clkevt.event_handler(&ce->clkevt); return IRQ_HANDLED; } -static struct irqaction sun5i_timer_irq = { - .name = "sun5i_timer0", - .flags = IRQF_TIMER | IRQF_IRQPOLL, - .handler = sun5i_timer_interrupt, - .dev_id = &sun5i_clockevent, -}; +static cycle_t sun5i_clksrc_read(struct clocksource *clksrc) +{ + struct sun5i_timer_clksrc *cs = to_sun5i_timer_clksrc(clksrc); + + return ~readl(cs->timer.base + TIMER_CNTVAL_LO_REG(1)); +} + +static int sun5i_rate_cb_clksrc(struct notifier_block *nb, + unsigned long event, void *data) +{ + struct clk_notifier_data *ndata = data; + struct sun5i_timer *timer = to_sun5i_timer(nb); + struct sun5i_timer_clksrc *cs = container_of(timer, struct sun5i_timer_clksrc, timer); + + switch (event) { + case PRE_RATE_CHANGE: + clocksource_unregister(&cs->clksrc); + break; + + case POST_RATE_CHANGE: + clocksource_register_hz(&cs->clksrc, ndata->new_rate); + break; + + default: + break; + } + + return NOTIFY_DONE; +} + +static int __init sun5i_setup_clocksource(struct device_node *node, + void __iomem *base, + struct clk *clk, int irq) +{ + struct sun5i_timer_clksrc *cs; + unsigned long rate; + int ret; + + cs = kzalloc(sizeof(*cs), GFP_KERNEL); + if (!cs) + return -ENOMEM; + + ret = clk_prepare_enable(clk); + if (ret) { + pr_err("Couldn't enable parent clock\n"); + goto err_free; + } + + rate = clk_get_rate(clk); + + cs->timer.base = base; + cs->timer.clk = clk; + cs->timer.clk_rate_cb.notifier_call = sun5i_rate_cb_clksrc; + cs->timer.clk_rate_cb.next = NULL; + + ret = clk_notifier_register(clk, &cs->timer.clk_rate_cb); + if (ret) { + pr_err("Unable to register clock notifier.\n"); + goto err_disable_clk; + } + + writel(~0, base + TIMER_INTVAL_LO_REG(1)); + writel(TIMER_CTL_ENABLE | TIMER_CTL_RELOAD, + base + TIMER_CTL_REG(1)); + + cs->clksrc.name = node->name; + cs->clksrc.rating = 340; + cs->clksrc.read = sun5i_clksrc_read; + cs->clksrc.mask = CLOCKSOURCE_MASK(32); + cs->clksrc.flags = CLOCK_SOURCE_IS_CONTINUOUS; + + ret = clocksource_register_hz(&cs->clksrc, rate); + if (ret) { + pr_err("Couldn't register clock source.\n"); + goto err_remove_notifier; + } + + return 0; + +err_remove_notifier: + clk_notifier_unregister(clk, &cs->timer.clk_rate_cb); +err_disable_clk: + clk_disable_unprepare(clk); +err_free: + kfree(cs); + return ret; +} + +static int sun5i_rate_cb_clkevt(struct notifier_block *nb, + unsigned long event, void *data) +{ + struct clk_notifier_data *ndata = data; + struct sun5i_timer *timer = to_sun5i_timer(nb); + struct sun5i_timer_clkevt *ce = container_of(timer, struct sun5i_timer_clkevt, timer); + + if (event == POST_RATE_CHANGE) { + clockevents_update_freq(&ce->clkevt, ndata->new_rate); + ce->timer.ticks_per_jiffy = DIV_ROUND_UP(ndata->new_rate, HZ); + } + + return NOTIFY_DONE; +} + +static int __init sun5i_setup_clockevent(struct device_node *node, void __iomem *base, + struct clk *clk, int irq) +{ + struct sun5i_timer_clkevt *ce; + unsigned long rate; + int ret; + u32 val; + + ce = kzalloc(sizeof(*ce), GFP_KERNEL); + if (!ce) + return -ENOMEM; + + ret = clk_prepare_enable(clk); + if (ret) { + pr_err("Couldn't enable parent clock\n"); + goto err_free; + } + + rate = clk_get_rate(clk); + + ce->timer.base = base; + ce->timer.ticks_per_jiffy = DIV_ROUND_UP(rate, HZ); + ce->timer.clk = clk; + ce->timer.clk_rate_cb.notifier_call = sun5i_rate_cb_clkevt; + ce->timer.clk_rate_cb.next = NULL; + + ret = clk_notifier_register(clk, &ce->timer.clk_rate_cb); + if (ret) { + pr_err("Unable to register clock notifier.\n"); + goto err_disable_clk; + } + + ce->clkevt.name = node->name; + ce->clkevt.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT; + ce->clkevt.set_next_event = sun5i_clkevt_next_event; + ce->clkevt.set_mode = sun5i_clkevt_mode; + ce->clkevt.rating = 340; + ce->clkevt.irq = irq; + ce->clkevt.cpumask = cpu_possible_mask; + + /* Enable timer0 interrupt */ + val = readl(base + TIMER_IRQ_EN_REG); + writel(val | TIMER_IRQ_EN(0), base + TIMER_IRQ_EN_REG); + + clockevents_config_and_register(&ce->clkevt, rate, + TIMER_SYNC_TICKS, 0xffffffff); + + ret = request_irq(irq, sun5i_timer_interrupt, IRQF_TIMER | IRQF_IRQPOLL, + "sun5i_timer0", ce); + if (ret) { + pr_err("Unable to register interrupt\n"); + goto err_remove_notifier; + } + + return 0; + +err_remove_notifier: + clk_notifier_unregister(clk, &ce->timer.clk_rate_cb); +err_disable_clk: + clk_disable_unprepare(clk); +err_free: + kfree(ce); + return ret; +} static void __init sun5i_timer_init(struct device_node *node) { struct reset_control *rstc; - unsigned long rate; + void __iomem *timer_base; struct clk *clk; - int ret, irq; - u32 val; + int irq; - timer_base = of_iomap(node, 0); + timer_base = of_io_request_and_map(node, 0, of_node_full_name(node)); if (!timer_base) panic("Can't map registers"); @@ -155,35 +334,13 @@ static void __init sun5i_timer_init(struct device_node *node) clk = of_clk_get(node, 0); if (IS_ERR(clk)) panic("Can't get timer clock"); - clk_prepare_enable(clk); - rate = clk_get_rate(clk); rstc = of_reset_control_get(node, NULL); if (!IS_ERR(rstc)) reset_control_deassert(rstc); - writel(~0, timer_base + TIMER_INTVAL_LO_REG(1)); - writel(TIMER_CTL_ENABLE | TIMER_CTL_RELOAD, - timer_base + TIMER_CTL_REG(1)); - - clocksource_mmio_init(timer_base + TIMER_CNTVAL_LO_REG(1), node->name, - rate, 340, 32, clocksource_mmio_readl_down); - - ticks_per_jiffy = DIV_ROUND_UP(rate, HZ); - - /* Enable timer0 interrupt */ - val = readl(timer_base + TIMER_IRQ_EN_REG); - writel(val | TIMER_IRQ_EN(0), timer_base + TIMER_IRQ_EN_REG); - - sun5i_clockevent.cpumask = cpu_possible_mask; - sun5i_clockevent.irq = irq; - - clockevents_config_and_register(&sun5i_clockevent, rate, - TIMER_SYNC_TICKS, 0xffffffff); - - ret = setup_irq(irq, &sun5i_timer_irq); - if (ret) - pr_warn("failed to setup irq %d\n", irq); + sun5i_setup_clocksource(node, timer_base, clk, irq); + sun5i_setup_clockevent(node, timer_base, clk, irq); } CLOCKSOURCE_OF_DECLARE(sun5i_a13, "allwinner,sun5i-a13-hstimer", sun5i_timer_init); diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 28e59a48b35f..8ae655c364f4 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1698,15 +1698,18 @@ void cpufreq_resume(void) || __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS)) pr_err("%s: Failed to start governor for policy: %p\n", __func__, policy); - - /* - * schedule call cpufreq_update_policy() for boot CPU, i.e. last - * policy in list. It will verify that the current freq is in - * sync with what we believe it to be. - */ - if (list_is_last(&policy->policy_list, &cpufreq_policy_list)) - schedule_work(&policy->update); } + + /* + * schedule call cpufreq_update_policy() for first-online CPU, as that + * wouldn't be hotplugged-out on suspend. It will verify that the + * current freq is in sync with what we believe it to be. + */ + policy = cpufreq_cpu_get_raw(cpumask_first(cpu_online_mask)); + if (WARN_ON(!policy)) + return; + + schedule_work(&policy->update); } /** diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 080bd2dbde4b..7a73a279e179 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -330,9 +330,6 @@ int cpuidle_enable_device(struct cpuidle_device *dev) if (!dev->registered) return -EINVAL; - if (!dev->state_count) - dev->state_count = drv->state_count; - ret = cpuidle_add_device_sysfs(dev); if (ret) return ret; diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c index 2697e87d5b34..5db147859b90 100644 --- a/drivers/cpuidle/driver.c +++ b/drivers/cpuidle/driver.c @@ -13,7 +13,7 @@ #include <linux/sched.h> #include <linux/cpuidle.h> #include <linux/cpumask.h> -#include <linux/clockchips.h> +#include <linux/tick.h> #include "cpuidle.h" @@ -130,21 +130,20 @@ static inline void __cpuidle_unset_driver(struct cpuidle_driver *drv) #endif /** - * cpuidle_setup_broadcast_timer - enable/disable the broadcast timer + * cpuidle_setup_broadcast_timer - enable/disable the broadcast timer on a cpu * @arg: a void pointer used to match the SMP cross call API * - * @arg is used as a value of type 'long' with one of the two values: - * - CLOCK_EVT_NOTIFY_BROADCAST_ON - * - CLOCK_EVT_NOTIFY_BROADCAST_OFF + * If @arg is NULL broadcast is disabled otherwise enabled * - * Set the broadcast timer notification for the current CPU. This function - * is executed per CPU by an SMP cross call. It not supposed to be called - * directly. + * This function is executed per CPU by an SMP cross call. It's not + * supposed to be called directly. */ static void cpuidle_setup_broadcast_timer(void *arg) { - int cpu = smp_processor_id(); - clockevents_notify((long)(arg), &cpu); + if (arg) + tick_broadcast_enable(); + else + tick_broadcast_disable(); } /** @@ -239,7 +238,7 @@ static int __cpuidle_register_driver(struct cpuidle_driver *drv) if (drv->bctimer) on_each_cpu_mask(drv->cpumask, cpuidle_setup_broadcast_timer, - (void *)CLOCK_EVT_NOTIFY_BROADCAST_ON, 1); + (void *)1, 1); poll_idle_init(drv); @@ -263,7 +262,7 @@ static void __cpuidle_unregister_driver(struct cpuidle_driver *drv) if (drv->bctimer) { drv->bctimer = 0; on_each_cpu_mask(drv->cpumask, cpuidle_setup_broadcast_timer, - (void *)CLOCK_EVT_NOTIFY_BROADCAST_OFF, 1); + NULL, 1); } __cpuidle_unset_driver(drv); diff --git a/drivers/cpuidle/sysfs.c b/drivers/cpuidle/sysfs.c index 97c5903b4606..832a2c3f01ff 100644 --- a/drivers/cpuidle/sysfs.c +++ b/drivers/cpuidle/sysfs.c @@ -401,7 +401,7 @@ static int cpuidle_add_state_sysfs(struct cpuidle_device *device) struct cpuidle_driver *drv = cpuidle_get_cpu_driver(device); /* state statistics */ - for (i = 0; i < device->state_count; i++) { + for (i = 0; i < drv->state_count; i++) { kobj = kzalloc(sizeof(struct cpuidle_state_kobj), GFP_KERNEL); if (!kobj) goto error_state; @@ -433,9 +433,10 @@ error_state: */ static void cpuidle_remove_state_sysfs(struct cpuidle_device *device) { + struct cpuidle_driver *drv = cpuidle_get_cpu_driver(device); int i; - for (i = 0; i < device->state_count; i++) + for (i = 0; i < drv->state_count; i++) cpuidle_free_state_kobj(device, i); } diff --git a/drivers/dma/cppi41.c b/drivers/dma/cppi41.c index 512cb8e2805e..ceedafbd23e0 100644 --- a/drivers/dma/cppi41.c +++ b/drivers/dma/cppi41.c @@ -903,6 +903,11 @@ static const struct cppi_glue_infos *get_glue_info(struct device *dev) return of_id->data; } +#define CPPI41_DMA_BUSWIDTHS (BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) | \ + BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) | \ + BIT(DMA_SLAVE_BUSWIDTH_3_BYTES) | \ + BIT(DMA_SLAVE_BUSWIDTH_4_BYTES)) + static int cppi41_dma_probe(struct platform_device *pdev) { struct cppi41_dd *cdd; @@ -926,6 +931,10 @@ static int cppi41_dma_probe(struct platform_device *pdev) cdd->ddev.device_issue_pending = cppi41_dma_issue_pending; cdd->ddev.device_prep_slave_sg = cppi41_dma_prep_slave_sg; cdd->ddev.device_terminate_all = cppi41_stop_chan; + cdd->ddev.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV); + cdd->ddev.src_addr_widths = CPPI41_DMA_BUSWIDTHS; + cdd->ddev.dst_addr_widths = CPPI41_DMA_BUSWIDTHS; + cdd->ddev.residue_granularity = DMA_RESIDUE_GRANULARITY_BURST; cdd->ddev.dev = dev; INIT_LIST_HEAD(&cdd->ddev.channels); cpp41_dma_info.dma_cap = cdd->ddev.cap_mask; diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index f15712f2fec6..ac336a961dea 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -859,9 +859,6 @@ int dma_async_device_register(struct dma_device *device) BUG_ON(!device->device_issue_pending); BUG_ON(!device->dev); - WARN(dma_has_cap(DMA_SLAVE, device->cap_mask) && !device->directions, - "this driver doesn't support generic slave capabilities reporting\n"); - /* note: this only matters in the * CONFIG_ASYNC_TX_ENABLE_CHANNEL_SWITCH=n case */ diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c index 2eebd28b4c40..6e45a43ffe84 100644 --- a/drivers/firmware/dmi_scan.c +++ b/drivers/firmware/dmi_scan.c @@ -17,7 +17,9 @@ */ static const char dmi_empty_string[] = " "; -static u16 __initdata dmi_ver; +static u32 dmi_ver __initdata; +static u32 dmi_len; +static u16 dmi_num; /* * Catch too early calls to dmi_check_system(): */ @@ -78,7 +80,7 @@ static const char * __init dmi_string(const struct dmi_header *dm, u8 s) * We have to be cautious here. We have seen BIOSes with DMI pointers * pointing to completely the wrong place for example */ -static void dmi_table(u8 *buf, u32 len, int num, +static void dmi_table(u8 *buf, void (*decode)(const struct dmi_header *, void *), void *private_data) { @@ -91,8 +93,8 @@ static void dmi_table(u8 *buf, u32 len, int num, * off the end of the table (should never happen but sometimes does * on bogus implementations.) */ - while ((!num || i < num) && - (data - buf + sizeof(struct dmi_header)) <= len) { + while ((!dmi_num || i < dmi_num) && + (data - buf + sizeof(struct dmi_header)) <= dmi_len) { const struct dmi_header *dm = (const struct dmi_header *)data; /* @@ -101,9 +103,9 @@ static void dmi_table(u8 *buf, u32 len, int num, * table in dmi_decode or dmi_string */ data += dm->length; - while ((data - buf < len - 1) && (data[0] || data[1])) + while ((data - buf < dmi_len - 1) && (data[0] || data[1])) data++; - if (data - buf < len - 1) + if (data - buf < dmi_len - 1) decode(dm, private_data); /* @@ -118,8 +120,6 @@ static void dmi_table(u8 *buf, u32 len, int num, } static phys_addr_t dmi_base; -static u32 dmi_len; -static u16 dmi_num; static int __init dmi_walk_early(void (*decode)(const struct dmi_header *, void *)) @@ -130,7 +130,7 @@ static int __init dmi_walk_early(void (*decode)(const struct dmi_header *, if (buf == NULL) return -1; - dmi_table(buf, dmi_len, dmi_num, decode, NULL); + dmi_table(buf, decode, NULL); add_device_randomness(buf, dmi_len); @@ -201,7 +201,7 @@ static void __init dmi_save_uuid(const struct dmi_header *dm, int slot, * the UUID are supposed to be little-endian encoded. The specification * says that this is the defacto standard. */ - if (dmi_ver >= 0x0206) + if (dmi_ver >= 0x020600) sprintf(s, "%pUL", d); else sprintf(s, "%pUB", d); @@ -473,7 +473,7 @@ static void __init dmi_format_ids(char *buf, size_t len) */ static int __init dmi_present(const u8 *buf) { - int smbios_ver; + u32 smbios_ver; if (memcmp(buf, "_SM_", 4) == 0 && buf[5] < 32 && dmi_checksum(buf, buf[5])) { @@ -506,14 +506,16 @@ static int __init dmi_present(const u8 *buf) if (dmi_walk_early(dmi_decode) == 0) { if (smbios_ver) { dmi_ver = smbios_ver; - pr_info("SMBIOS %d.%d present.\n", - dmi_ver >> 8, dmi_ver & 0xFF); + pr_info("SMBIOS %d.%d%s present.\n", + dmi_ver >> 8, dmi_ver & 0xFF, + (dmi_ver < 0x0300) ? "" : ".x"); } else { dmi_ver = (buf[14] & 0xF0) << 4 | (buf[14] & 0x0F); pr_info("Legacy DMI %d.%d present.\n", dmi_ver >> 8, dmi_ver & 0xFF); } + dmi_ver <<= 8; dmi_format_ids(dmi_ids_string, sizeof(dmi_ids_string)); printk(KERN_DEBUG "DMI: %s\n", dmi_ids_string); return 0; @@ -531,14 +533,16 @@ static int __init dmi_smbios3_present(const u8 *buf) { if (memcmp(buf, "_SM3_", 5) == 0 && buf[6] < 32 && dmi_checksum(buf, buf[6])) { - dmi_ver = get_unaligned_be16(buf + 7); + dmi_ver = get_unaligned_be32(buf + 6); + dmi_ver &= 0xFFFFFF; dmi_num = 0; /* No longer specified */ dmi_len = get_unaligned_le32(buf + 12); dmi_base = get_unaligned_le64(buf + 16); if (dmi_walk_early(dmi_decode) == 0) { - pr_info("SMBIOS %d.%d present.\n", - dmi_ver >> 8, dmi_ver & 0xFF); + pr_info("SMBIOS %d.%d.%d present.\n", + dmi_ver >> 16, (dmi_ver >> 8) & 0xFF, + dmi_ver & 0xFF); dmi_format_ids(dmi_ids_string, sizeof(dmi_ids_string)); pr_debug("DMI: %s\n", dmi_ids_string); return 0; @@ -893,7 +897,7 @@ int dmi_walk(void (*decode)(const struct dmi_header *, void *), if (buf == NULL) return -1; - dmi_table(buf, dmi_len, dmi_num, decode, private_data); + dmi_table(buf, decode, private_data); dmi_unmap(buf); return 0; diff --git a/drivers/firmware/efi/libstub/arm-stub.c b/drivers/firmware/efi/libstub/arm-stub.c index dcae482a9a17..e29560e6b40b 100644 --- a/drivers/firmware/efi/libstub/arm-stub.c +++ b/drivers/firmware/efi/libstub/arm-stub.c @@ -175,7 +175,7 @@ unsigned long efi_entry(void *handle, efi_system_table_t *sys_table, unsigned long initrd_addr; u64 initrd_size = 0; unsigned long fdt_addr = 0; /* Original DTB */ - u64 fdt_size = 0; /* We don't get size from configuration table */ + unsigned long fdt_size = 0; char *cmdline_ptr = NULL; int cmdline_size = 0; unsigned long new_fdt_addr; @@ -239,8 +239,7 @@ unsigned long efi_entry(void *handle, efi_system_table_t *sys_table, } else { status = handle_cmdline_files(sys_table, image, cmdline_ptr, "dtb=", - ~0UL, (unsigned long *)&fdt_addr, - (unsigned long *)&fdt_size); + ~0UL, &fdt_addr, &fdt_size); if (status != EFI_SUCCESS) { pr_efi_err(sys_table, "Failed to load device tree!\n"); @@ -252,7 +251,7 @@ unsigned long efi_entry(void *handle, efi_system_table_t *sys_table, pr_efi(sys_table, "Using DTB from command line\n"); } else { /* Look for a device tree configuration table entry. */ - fdt_addr = (uintptr_t)get_fdt(sys_table); + fdt_addr = (uintptr_t)get_fdt(sys_table, &fdt_size); if (fdt_addr) pr_efi(sys_table, "Using DTB from configuration table\n"); } diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h index 47437b16b186..e334a01cf92f 100644 --- a/drivers/firmware/efi/libstub/efistub.h +++ b/drivers/firmware/efi/libstub/efistub.h @@ -41,7 +41,7 @@ efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table, unsigned long fdt_addr, unsigned long fdt_size); -void *get_fdt(efi_system_table_t *sys_table); +void *get_fdt(efi_system_table_t *sys_table, unsigned long *fdt_size); void efi_get_virtmap(efi_memory_desc_t *memory_map, unsigned long map_size, unsigned long desc_size, efi_memory_desc_t *runtime_map, diff --git a/drivers/firmware/efi/libstub/fdt.c b/drivers/firmware/efi/libstub/fdt.c index 91da56c4fd54..ef5d764e2a27 100644 --- a/drivers/firmware/efi/libstub/fdt.c +++ b/drivers/firmware/efi/libstub/fdt.c @@ -323,7 +323,7 @@ fail: return EFI_LOAD_ERROR; } -void *get_fdt(efi_system_table_t *sys_table) +void *get_fdt(efi_system_table_t *sys_table, unsigned long *fdt_size) { efi_guid_t fdt_guid = DEVICE_TREE_GUID; efi_config_table_t *tables; @@ -336,6 +336,11 @@ void *get_fdt(efi_system_table_t *sys_table) for (i = 0; i < sys_table->nr_tables; i++) if (efi_guidcmp(tables[i].guid, fdt_guid) == 0) { fdt = (void *) tables[i].table; + if (fdt_check_header(fdt) != 0) { + pr_efi_err(sys_table, "Invalid header detected on UEFI supplied FDT, ignoring ...\n"); + return NULL; + } + *fdt_size = fdt_totalsize(fdt); break; } diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c index 679b10e34fb5..b6f076b213bc 100644 --- a/drivers/gpu/drm/drm_crtc.c +++ b/drivers/gpu/drm/drm_crtc.c @@ -2121,7 +2121,7 @@ int drm_mode_getconnector(struct drm_device *dev, void *data, connector = drm_connector_find(dev, out_resp->connector_id); if (!connector) { ret = -ENOENT; - goto out; + goto out_unlock; } for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) @@ -2201,6 +2201,8 @@ int drm_mode_getconnector(struct drm_device *dev, void *data, out: drm_modeset_unlock(&dev->mode_config.connection_mutex); + +out_unlock: mutex_unlock(&dev->mode_config.mutex); return ret; diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index cc6ea53d2b81..5c66b568bb81 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -1095,6 +1095,7 @@ static void vlv_save_gunit_s0ix_state(struct drm_i915_private *dev_priv) /* Gunit-Display CZ domain, 0x182028-0x1821CF */ s->gu_ctl0 = I915_READ(VLV_GU_CTL0); s->gu_ctl1 = I915_READ(VLV_GU_CTL1); + s->pcbr = I915_READ(VLV_PCBR); s->clock_gate_dis2 = I915_READ(VLV_GUNIT_CLOCK_GATE2); /* @@ -1189,6 +1190,7 @@ static void vlv_restore_gunit_s0ix_state(struct drm_i915_private *dev_priv) /* Gunit-Display CZ domain, 0x182028-0x1821CF */ I915_WRITE(VLV_GU_CTL0, s->gu_ctl0); I915_WRITE(VLV_GU_CTL1, s->gu_ctl1); + I915_WRITE(VLV_PCBR, s->pcbr); I915_WRITE(VLV_GUNIT_CLOCK_GATE2, s->clock_gate_dis2); } @@ -1197,19 +1199,7 @@ int vlv_force_gfx_clock(struct drm_i915_private *dev_priv, bool force_on) u32 val; int err; - val = I915_READ(VLV_GTLC_SURVIVABILITY_REG); - WARN_ON(!!(val & VLV_GFX_CLK_FORCE_ON_BIT) == force_on); - #define COND (I915_READ(VLV_GTLC_SURVIVABILITY_REG) & VLV_GFX_CLK_STATUS_BIT) - /* Wait for a previous force-off to settle */ - if (force_on) { - err = wait_for(!COND, 20); - if (err) { - DRM_ERROR("timeout waiting for GFX clock force-off (%08x)\n", - I915_READ(VLV_GTLC_SURVIVABILITY_REG)); - return err; - } - } val = I915_READ(VLV_GTLC_SURVIVABILITY_REG); val &= ~VLV_GFX_CLK_FORCE_ON_BIT; diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 8727086cf48c..b4faa2df9d3d 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -1094,6 +1094,7 @@ struct vlv_s0ix_state { /* Display 2 CZ domain */ u32 gu_ctl0; u32 gu_ctl1; + u32 pcbr; u32 clock_gate_dis2; }; diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index b0e58522780d..5c979d0667a2 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -55,7 +55,7 @@ #include <linux/kernel.h> #include <linux/cpuidle.h> -#include <linux/clockchips.h> +#include <linux/tick.h> #include <trace/events/power.h> #include <linux/sched.h> #include <linux/notifier.h> @@ -638,12 +638,12 @@ static int intel_idle(struct cpuidle_device *dev, leave_mm(cpu); if (!(lapic_timer_reliable_states & (1 << (cstate)))) - clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu); + tick_broadcast_enter(); mwait_idle_with_hints(eax, ecx); if (!(lapic_timer_reliable_states & (1 << (cstate)))) - clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu); + tick_broadcast_exit(); return index; } @@ -665,13 +665,12 @@ static void intel_idle_freeze(struct cpuidle_device *dev, static void __setup_broadcast_timer(void *arg) { - unsigned long reason = (unsigned long)arg; - int cpu = smp_processor_id(); - - reason = reason ? - CLOCK_EVT_NOTIFY_BROADCAST_ON : CLOCK_EVT_NOTIFY_BROADCAST_OFF; + unsigned long on = (unsigned long)arg; - clockevents_notify(reason, &cpu); + if (on) + tick_broadcast_enable(); + else + tick_broadcast_disable(); } static int cpu_hotplug_notify(struct notifier_block *n, diff --git a/drivers/md/md.c b/drivers/md/md.c index 717daad71fb1..e6178787ce3d 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -249,6 +249,7 @@ static void md_make_request(struct request_queue *q, struct bio *bio) const int rw = bio_data_dir(bio); struct mddev *mddev = q->queuedata; unsigned int sectors; + int cpu; if (mddev == NULL || mddev->pers == NULL || !mddev->ready) { @@ -284,7 +285,10 @@ static void md_make_request(struct request_queue *q, struct bio *bio) sectors = bio_sectors(bio); mddev->pers->make_request(mddev, bio); - generic_start_io_acct(rw, sectors, &mddev->gendisk->part0); + cpu = part_stat_lock(); + part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]); + part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw], sectors); + part_stat_unlock(); if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended) wake_up(&mddev->sb_wait); diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 3ed9f42ddca6..3b5d7f704aa3 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -313,7 +313,7 @@ static struct strip_zone *find_zone(struct r0conf *conf, /* * remaps the bio to the target device. we separate two flows. - * power 2 flow and a general flow for the sake of perfromance + * power 2 flow and a general flow for the sake of performance */ static struct md_rdev *map_sector(struct mddev *mddev, struct strip_zone *zone, sector_t sector, sector_t *sector_offset) @@ -524,6 +524,7 @@ static void raid0_make_request(struct mddev *mddev, struct bio *bio) split = bio; } + sector = bio->bi_iter.bi_sector; zone = find_zone(mddev->private, §or); tmp_dev = map_sector(mddev, zone, sector, §or); split->bi_bdev = tmp_dev->bdev; diff --git a/drivers/media/dvb-frontends/rtl2832.c b/drivers/media/dvb-frontends/rtl2832.c index 5d2d8f45b4b6..67faa8d6950e 100644 --- a/drivers/media/dvb-frontends/rtl2832.c +++ b/drivers/media/dvb-frontends/rtl2832.c @@ -1240,7 +1240,7 @@ static int rtl2832_probe(struct i2c_client *client, dev->regmap_config.max_register = 5 * 0x100, dev->regmap_config.ranges = regmap_range_cfg, dev->regmap_config.num_ranges = ARRAY_SIZE(regmap_range_cfg), - dev->regmap_config.cache_type = REGCACHE_RBTREE, + dev->regmap_config.cache_type = REGCACHE_NONE, dev->regmap = regmap_init(&client->dev, ®map_bus, client, &dev->regmap_config); if (IS_ERR(dev->regmap)) { diff --git a/drivers/media/pci/cx23885/cx23885-417.c b/drivers/media/pci/cx23885/cx23885-417.c index e4901a503c73..63c0ee5d0bf5 100644 --- a/drivers/media/pci/cx23885/cx23885-417.c +++ b/drivers/media/pci/cx23885/cx23885-417.c @@ -1339,14 +1339,13 @@ static int vidioc_querycap(struct file *file, void *priv, strlcpy(cap->driver, dev->name, sizeof(cap->driver)); strlcpy(cap->card, cx23885_boards[tsport->dev->board].name, sizeof(cap->card)); - sprintf(cap->bus_info, "PCI:%s", pci_name(dev->pci)); - cap->capabilities = - V4L2_CAP_VIDEO_CAPTURE | - V4L2_CAP_READWRITE | - V4L2_CAP_STREAMING | - 0; + sprintf(cap->bus_info, "PCIe:%s", pci_name(dev->pci)); + cap->device_caps = V4L2_CAP_VIDEO_CAPTURE | V4L2_CAP_READWRITE | + V4L2_CAP_STREAMING; if (dev->tuner_type != TUNER_ABSENT) - cap->capabilities |= V4L2_CAP_TUNER; + cap->device_caps |= V4L2_CAP_TUNER; + cap->capabilities = cap->device_caps | V4L2_CAP_VBI_CAPTURE | + V4L2_CAP_AUDIO | V4L2_CAP_DEVICE_CAPS; return 0; } diff --git a/drivers/media/platform/s5p-jpeg/jpeg-core.c b/drivers/media/platform/s5p-jpeg/jpeg-core.c index 12f7452edce3..a92ff4249d10 100644 --- a/drivers/media/platform/s5p-jpeg/jpeg-core.c +++ b/drivers/media/platform/s5p-jpeg/jpeg-core.c @@ -1845,6 +1845,9 @@ static void exynos4_jpeg_set_img_addr(struct s5p_jpeg_ctx *ctx) struct s5p_jpeg_addr jpeg_addr; u32 pix_size, padding_bytes = 0; + jpeg_addr.cb = 0; + jpeg_addr.cr = 0; + pix_size = ctx->cap_q.w * ctx->cap_q.h; if (ctx->mode == S5P_JPEG_ENCODE) { diff --git a/drivers/media/platform/s5p-jpeg/jpeg-hw-exynos3250.c b/drivers/media/platform/s5p-jpeg/jpeg-hw-exynos3250.c index e8c2cad93962..0974b9a7a584 100644 --- a/drivers/media/platform/s5p-jpeg/jpeg-hw-exynos3250.c +++ b/drivers/media/platform/s5p-jpeg/jpeg-hw-exynos3250.c @@ -20,7 +20,7 @@ void exynos3250_jpeg_reset(void __iomem *regs) { - u32 reg = 0; + u32 reg = 1; int count = 1000; writel(1, regs + EXYNOS3250_SW_RESET); diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc.c b/drivers/media/platform/s5p-mfc/s5p_mfc.c index 8e44a59d8ec2..98374e8bad3e 100644 --- a/drivers/media/platform/s5p-mfc/s5p_mfc.c +++ b/drivers/media/platform/s5p-mfc/s5p_mfc.c @@ -833,6 +833,7 @@ static int s5p_mfc_open(struct file *file) q->type = V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE; q->io_modes = VB2_MMAP; q->drv_priv = &ctx->fh; + q->lock = &dev->mfc_mutex; if (vdev == dev->vfd_dec) { q->io_modes = VB2_MMAP; q->ops = get_dec_queue_ops(); diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_common.h b/drivers/media/platform/s5p-mfc/s5p_mfc_common.h index 15f7663dd9f5..24262bbb1a35 100644 --- a/drivers/media/platform/s5p-mfc/s5p_mfc_common.h +++ b/drivers/media/platform/s5p-mfc/s5p_mfc_common.h @@ -29,7 +29,7 @@ /* Offset base used to differentiate between CAPTURE and OUTPUT * while mmaping */ -#define DST_QUEUE_OFF_BASE (TASK_SIZE / 2) +#define DST_QUEUE_OFF_BASE (1 << 30) #define MFC_BANK1_ALLOC_CTX 0 #define MFC_BANK2_ALLOC_CTX 1 diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_opr.h b/drivers/media/platform/s5p-mfc/s5p_mfc_opr.h index de2b8c69daa5..22dfb3effda8 100644 --- a/drivers/media/platform/s5p-mfc/s5p_mfc_opr.h +++ b/drivers/media/platform/s5p-mfc/s5p_mfc_opr.h @@ -302,7 +302,7 @@ struct s5p_mfc_hw_ops { void (*write_info)(struct s5p_mfc_ctx *ctx, unsigned int data, unsigned int ofs); unsigned int (*read_info)(struct s5p_mfc_ctx *ctx, - unsigned int ofs); + unsigned long ofs); int (*get_dspl_y_adr)(struct s5p_mfc_dev *dev); int (*get_dec_y_adr)(struct s5p_mfc_dev *dev); int (*get_dspl_status)(struct s5p_mfc_dev *dev); diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_opr_v5.c b/drivers/media/platform/s5p-mfc/s5p_mfc_opr_v5.c index 0c4fcf2dfd09..b09bcd140491 100644 --- a/drivers/media/platform/s5p-mfc/s5p_mfc_opr_v5.c +++ b/drivers/media/platform/s5p-mfc/s5p_mfc_opr_v5.c @@ -263,15 +263,15 @@ static void s5p_mfc_release_dev_context_buffer_v5(struct s5p_mfc_dev *dev) static void s5p_mfc_write_info_v5(struct s5p_mfc_ctx *ctx, unsigned int data, unsigned int ofs) { - writel(data, (volatile void __iomem *)(ctx->shm.virt + ofs)); + writel(data, (void *)(ctx->shm.virt + ofs)); wmb(); } static unsigned int s5p_mfc_read_info_v5(struct s5p_mfc_ctx *ctx, - unsigned int ofs) + unsigned long ofs) { rmb(); - return readl((volatile void __iomem *)(ctx->shm.virt + ofs)); + return readl((void *)(ctx->shm.virt + ofs)); } static void s5p_mfc_dec_calc_dpb_size_v5(struct s5p_mfc_ctx *ctx) diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_opr_v6.c b/drivers/media/platform/s5p-mfc/s5p_mfc_opr_v6.c index d826c58b5d53..cefad184fe96 100644 --- a/drivers/media/platform/s5p-mfc/s5p_mfc_opr_v6.c +++ b/drivers/media/platform/s5p-mfc/s5p_mfc_opr_v6.c @@ -1852,17 +1852,17 @@ static void s5p_mfc_write_info_v6(struct s5p_mfc_ctx *ctx, unsigned int data, unsigned int ofs) { s5p_mfc_clock_on(); - writel(data, (volatile void __iomem *)((unsigned long)ofs)); + writel(data, (void *)((unsigned long)ofs)); s5p_mfc_clock_off(); } static unsigned int -s5p_mfc_read_info_v6(struct s5p_mfc_ctx *ctx, unsigned int ofs) +s5p_mfc_read_info_v6(struct s5p_mfc_ctx *ctx, unsigned long ofs) { int ret; s5p_mfc_clock_on(); - ret = readl((volatile void __iomem *)((unsigned long)ofs)); + ret = readl((void *)ofs); s5p_mfc_clock_off(); return ret; diff --git a/drivers/media/platform/s5p-tv/Kconfig b/drivers/media/platform/s5p-tv/Kconfig index 5a1835dd65e8..697aaed42486 100644 --- a/drivers/media/platform/s5p-tv/Kconfig +++ b/drivers/media/platform/s5p-tv/Kconfig @@ -20,6 +20,7 @@ if VIDEO_SAMSUNG_S5P_TV config VIDEO_SAMSUNG_S5P_HDMI tristate "Samsung HDMI Driver" depends on VIDEO_V4L2 + depends on I2C depends on VIDEO_SAMSUNG_S5P_TV select VIDEO_SAMSUNG_S5P_HDMIPHY help diff --git a/drivers/media/platform/sh_veu.c b/drivers/media/platform/sh_veu.c index a901b6248557..2554f3719b9e 100644 --- a/drivers/media/platform/sh_veu.c +++ b/drivers/media/platform/sh_veu.c @@ -1158,6 +1158,7 @@ static int sh_veu_probe(struct platform_device *pdev) } *vdev = sh_veu_videodev; + vdev->v4l2_dev = &veu->v4l2_dev; spin_lock_init(&veu->lock); mutex_init(&veu->fop_lock); vdev->lock = &veu->fop_lock; diff --git a/drivers/media/platform/soc_camera/atmel-isi.c b/drivers/media/platform/soc_camera/atmel-isi.c index 8526bf5c8429..c835beb2a1a8 100644 --- a/drivers/media/platform/soc_camera/atmel-isi.c +++ b/drivers/media/platform/soc_camera/atmel-isi.c @@ -843,6 +843,8 @@ static int isi_camera_set_bus_param(struct soc_camera_device *icd) if (isi->pdata.full_mode) cfg1 |= ISI_CFG1_FULL_MODE; + cfg1 |= ISI_CFG1_THMASK_BEATS_16; + isi_writel(isi, ISI_CTRL, ISI_CTRL_DIS); isi_writel(isi, ISI_CFG1, cfg1); diff --git a/drivers/media/platform/soc_camera/soc_camera.c b/drivers/media/platform/soc_camera/soc_camera.c index cee7b56f8404..66634b469c98 100644 --- a/drivers/media/platform/soc_camera/soc_camera.c +++ b/drivers/media/platform/soc_camera/soc_camera.c @@ -1665,7 +1665,7 @@ eclkreg: eaddpdev: platform_device_put(sasc->pdev); eallocpdev: - devm_kfree(ici->v4l2_dev.dev, sasc); + devm_kfree(ici->v4l2_dev.dev, info); dev_err(ici->v4l2_dev.dev, "group probe failed: %d\n", ret); return ret; diff --git a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c index 77dcfdf547ac..87fc0fe29ebd 100644 --- a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c +++ b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c @@ -780,8 +780,6 @@ static int rtl2832u_frontend_callback(void *adapter_priv, int component, case TUNER_RTL2832_TUA9001: return rtl2832u_tua9001_tuner_callback(d, cmd, arg); } - default: - return -EINVAL; } return 0; diff --git a/drivers/media/usb/gspca/Kconfig b/drivers/media/usb/gspca/Kconfig index 60af3b167f3b..3fd94fe7e1eb 100644 --- a/drivers/media/usb/gspca/Kconfig +++ b/drivers/media/usb/gspca/Kconfig @@ -1,6 +1,7 @@ menuconfig USB_GSPCA tristate "GSPCA based webcams" depends on VIDEO_V4L2 + depends on INPUT || INPUT=n default m ---help--- Say Y here if you want to enable selecting webcams based diff --git a/drivers/media/v4l2-core/videobuf2-core.c b/drivers/media/v4l2-core/videobuf2-core.c index bc08a829bc13..cc16e76a2493 100644 --- a/drivers/media/v4l2-core/videobuf2-core.c +++ b/drivers/media/v4l2-core/videobuf2-core.c @@ -3230,18 +3230,13 @@ int vb2_thread_stop(struct vb2_queue *q) if (threadio == NULL) return 0; - call_void_qop(q, wait_finish, q); threadio->stop = true; - vb2_internal_streamoff(q, q->type); - call_void_qop(q, wait_prepare, q); + /* Wake up all pending sleeps in the thread */ + vb2_queue_error(q); err = kthread_stop(threadio->thread); - q->fileio = NULL; - fileio->req.count = 0; - vb2_reqbufs(q, &fileio->req); - kfree(fileio); + __vb2_cleanup_fileio(q); threadio->thread = NULL; kfree(threadio); - q->fileio = NULL; q->threadio = NULL; return err; } diff --git a/drivers/media/v4l2-core/videobuf2-dma-contig.c b/drivers/media/v4l2-core/videobuf2-dma-contig.c index b481d20c8372..69e0483adfee 100644 --- a/drivers/media/v4l2-core/videobuf2-dma-contig.c +++ b/drivers/media/v4l2-core/videobuf2-dma-contig.c @@ -632,8 +632,7 @@ static void *vb2_dc_get_userptr(void *alloc_ctx, unsigned long vaddr, } /* extract page list from userspace mapping */ - ret = vb2_dc_get_user_pages(start, pages, n_pages, vma, - dma_dir == DMA_FROM_DEVICE); + ret = vb2_dc_get_user_pages(start, pages, n_pages, vma, dma_dir); if (ret) { unsigned long pfn; if (vb2_dc_get_user_pfn(start, n_pages, vma, &pfn) == 0) { diff --git a/drivers/misc/enclosure.c b/drivers/misc/enclosure.c index 38552a31304a..65fed7146e9b 100644 --- a/drivers/misc/enclosure.c +++ b/drivers/misc/enclosure.c @@ -202,16 +202,17 @@ static void enclosure_remove_links(struct enclosure_component *cdev) { char name[ENCLOSURE_NAME_SIZE]; + enclosure_link_name(cdev, name); + /* * In odd circumstances, like multipath devices, something else may * already have removed the links, so check for this condition first. */ - if (!cdev->dev->kobj.sd) - return; + if (cdev->dev->kobj.sd) + sysfs_remove_link(&cdev->dev->kobj, name); - enclosure_link_name(cdev, name); - sysfs_remove_link(&cdev->dev->kobj, name); - sysfs_remove_link(&cdev->cdev.kobj, "device"); + if (cdev->cdev.kobj.sd) + sysfs_remove_link(&cdev->cdev.kobj, "device"); } static int enclosure_add_links(struct enclosure_component *cdev) diff --git a/drivers/pci/host/pcie-designware.c b/drivers/pci/host/pcie-designware.c index 1f4ea6f2d910..2e9f84fdd9ce 100644 --- a/drivers/pci/host/pcie-designware.c +++ b/drivers/pci/host/pcie-designware.c @@ -342,7 +342,7 @@ static const struct irq_domain_ops msi_domain_ops = { .map = dw_pcie_msi_map, }; -int __init dw_pcie_host_init(struct pcie_port *pp) +int dw_pcie_host_init(struct pcie_port *pp) { struct device_node *np = pp->dev->of_node; struct platform_device *pdev = to_platform_device(pp->dev); diff --git a/drivers/pci/host/pcie-spear13xx.c b/drivers/pci/host/pcie-spear13xx.c index 866465fd3dbf..020d78890719 100644 --- a/drivers/pci/host/pcie-spear13xx.c +++ b/drivers/pci/host/pcie-spear13xx.c @@ -269,7 +269,7 @@ static struct pcie_host_ops spear13xx_pcie_host_ops = { .host_init = spear13xx_pcie_host_init, }; -static int __init spear13xx_add_pcie_port(struct pcie_port *pp, +static int spear13xx_add_pcie_port(struct pcie_port *pp, struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -299,7 +299,7 @@ static int __init spear13xx_add_pcie_port(struct pcie_port *pp, return 0; } -static int __init spear13xx_pcie_probe(struct platform_device *pdev) +static int spear13xx_pcie_probe(struct platform_device *pdev) { struct spear13xx_pcie *spear13xx_pcie; struct pcie_port *pp; @@ -370,7 +370,7 @@ static const struct of_device_id spear13xx_pcie_of_match[] = { }; MODULE_DEVICE_TABLE(of, spear13xx_pcie_of_match); -static struct platform_driver spear13xx_pcie_driver __initdata = { +static struct platform_driver spear13xx_pcie_driver = { .probe = spear13xx_pcie_probe, .driver = { .name = "spear-pcie", diff --git a/drivers/pci/hotplug/cpci_hotplug_pci.c b/drivers/pci/hotplug/cpci_hotplug_pci.c index 7d48ecae6695..788db48dbbad 100644 --- a/drivers/pci/hotplug/cpci_hotplug_pci.c +++ b/drivers/pci/hotplug/cpci_hotplug_pci.c @@ -286,11 +286,12 @@ int cpci_configure_slot(struct slot *slot) } parent = slot->dev->bus; - list_for_each_entry(dev, &parent->devices, bus_list) + list_for_each_entry(dev, &parent->devices, bus_list) { if (PCI_SLOT(dev->devfn) != PCI_SLOT(slot->devfn)) continue; if (pci_is_bridge(dev)) pci_hp_add_bridge(dev); + } pci_assign_unassigned_bridge_resources(parent->self); diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c index 489063987325..c93fbe76d281 100644 --- a/drivers/pci/pci-acpi.c +++ b/drivers/pci/pci-acpi.c @@ -248,6 +248,9 @@ int pci_get_hp_params(struct pci_dev *dev, struct hotplug_params *hpp) acpi_handle handle, phandle; struct pci_bus *pbus; + if (acpi_pci_disabled) + return -ENODEV; + handle = NULL; for (pbus = dev->bus; pbus; pbus = pbus->parent) { handle = acpi_pci_get_bridge_handle(pbus); diff --git a/drivers/pci/pcie/aer/aerdrv_errprint.c b/drivers/pci/pcie/aer/aerdrv_errprint.c index c6849d9e86ce..167fe411ce2e 100644 --- a/drivers/pci/pcie/aer/aerdrv_errprint.c +++ b/drivers/pci/pcie/aer/aerdrv_errprint.c @@ -132,16 +132,8 @@ static const char *aer_agent_string[] = { static void __print_tlp_header(struct pci_dev *dev, struct aer_header_log_regs *t) { - unsigned char *tlp = (unsigned char *)&t; - - dev_err(&dev->dev, " TLP Header:" - " %02x%02x%02x%02x %02x%02x%02x%02x" - " %02x%02x%02x%02x %02x%02x%02x%02x\n", - *(tlp + 3), *(tlp + 2), *(tlp + 1), *tlp, - *(tlp + 7), *(tlp + 6), *(tlp + 5), *(tlp + 4), - *(tlp + 11), *(tlp + 10), *(tlp + 9), - *(tlp + 8), *(tlp + 15), *(tlp + 14), - *(tlp + 13), *(tlp + 12)); + dev_err(&dev->dev, " TLP Header: %08x %08x %08x %08x\n", + t->dw0, t->dw1, t->dw2, t->dw3); } static void __aer_print_error(struct pci_dev *dev, diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c index 472a5adc4642..c29ba7e14304 100644 --- a/drivers/rtc/class.c +++ b/drivers/rtc/class.c @@ -55,7 +55,7 @@ static int rtc_suspend(struct device *dev) struct timespec64 delta, delta_delta; int err; - if (has_persistent_clock()) + if (timekeeping_rtc_skipsuspend()) return 0; if (strcmp(dev_name(&rtc->dev), CONFIG_RTC_HCTOSYS_DEVICE) != 0) @@ -102,7 +102,7 @@ static int rtc_resume(struct device *dev) struct timespec64 sleep_time; int err; - if (has_persistent_clock()) + if (timekeeping_rtc_skipresume()) return 0; rtc_hctosys_ret = -ENODEV; @@ -117,10 +117,6 @@ static int rtc_resume(struct device *dev) return 0; } - if (rtc_valid_tm(&tm) != 0) { - pr_debug("%s: bogus resume time\n", dev_name(&rtc->dev)); - return 0; - } new_rtc.tv_sec = rtc_tm_to_time64(&tm); new_rtc.tv_nsec = 0; diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c index 37215cf983e9..d43ee409a5f2 100644 --- a/drivers/rtc/interface.c +++ b/drivers/rtc/interface.c @@ -72,7 +72,11 @@ int rtc_set_time(struct rtc_device *rtc, struct rtc_time *tm) err = -ENODEV; else if (rtc->ops->set_time) err = rtc->ops->set_time(rtc->dev.parent, tm); - else if (rtc->ops->set_mmss) { + else if (rtc->ops->set_mmss64) { + time64_t secs64 = rtc_tm_to_time64(tm); + + err = rtc->ops->set_mmss64(rtc->dev.parent, secs64); + } else if (rtc->ops->set_mmss) { time64_t secs64 = rtc_tm_to_time64(tm); err = rtc->ops->set_mmss(rtc->dev.parent, secs64); } else @@ -96,6 +100,8 @@ int rtc_set_mmss(struct rtc_device *rtc, unsigned long secs) if (!rtc->ops) err = -ENODEV; + else if (rtc->ops->set_mmss64) + err = rtc->ops->set_mmss64(rtc->dev.parent, secs); else if (rtc->ops->set_mmss) err = rtc->ops->set_mmss(rtc->dev.parent, secs); else if (rtc->ops->read_time && rtc->ops->set_time) { diff --git a/drivers/rtc/rtc-ab3100.c b/drivers/rtc/rtc-ab3100.c index 1d0340fdb820..9b725c553058 100644 --- a/drivers/rtc/rtc-ab3100.c +++ b/drivers/rtc/rtc-ab3100.c @@ -43,21 +43,21 @@ /* * RTC clock functions and device struct declaration */ -static int ab3100_rtc_set_mmss(struct device *dev, unsigned long secs) +static int ab3100_rtc_set_mmss(struct device *dev, time64_t secs) { u8 regs[] = {AB3100_TI0, AB3100_TI1, AB3100_TI2, AB3100_TI3, AB3100_TI4, AB3100_TI5}; unsigned char buf[6]; - u64 fat_time = (u64) secs * AB3100_RTC_CLOCK_RATE * 2; + u64 hw_counter = secs * AB3100_RTC_CLOCK_RATE * 2; int err = 0; int i; - buf[0] = (fat_time) & 0xFF; - buf[1] = (fat_time >> 8) & 0xFF; - buf[2] = (fat_time >> 16) & 0xFF; - buf[3] = (fat_time >> 24) & 0xFF; - buf[4] = (fat_time >> 32) & 0xFF; - buf[5] = (fat_time >> 40) & 0xFF; + buf[0] = (hw_counter) & 0xFF; + buf[1] = (hw_counter >> 8) & 0xFF; + buf[2] = (hw_counter >> 16) & 0xFF; + buf[3] = (hw_counter >> 24) & 0xFF; + buf[4] = (hw_counter >> 32) & 0xFF; + buf[5] = (hw_counter >> 40) & 0xFF; for (i = 0; i < 6; i++) { err = abx500_set_register_interruptible(dev, 0, @@ -75,7 +75,7 @@ static int ab3100_rtc_set_mmss(struct device *dev, unsigned long secs) static int ab3100_rtc_read_time(struct device *dev, struct rtc_time *tm) { - unsigned long time; + time64_t time; u8 rtcval; int err; @@ -88,7 +88,7 @@ static int ab3100_rtc_read_time(struct device *dev, struct rtc_time *tm) dev_info(dev, "clock not set (lost power)"); return -EINVAL; } else { - u64 fat_time; + u64 hw_counter; u8 buf[6]; /* Read out time registers */ @@ -98,22 +98,21 @@ static int ab3100_rtc_read_time(struct device *dev, struct rtc_time *tm) if (err != 0) return err; - fat_time = ((u64) buf[5] << 40) | ((u64) buf[4] << 32) | + hw_counter = ((u64) buf[5] << 40) | ((u64) buf[4] << 32) | ((u64) buf[3] << 24) | ((u64) buf[2] << 16) | ((u64) buf[1] << 8) | (u64) buf[0]; - time = (unsigned long) (fat_time / - (u64) (AB3100_RTC_CLOCK_RATE * 2)); + time = hw_counter / (u64) (AB3100_RTC_CLOCK_RATE * 2); } - rtc_time_to_tm(time, tm); + rtc_time64_to_tm(time, tm); return rtc_valid_tm(tm); } static int ab3100_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alarm) { - unsigned long time; - u64 fat_time; + time64_t time; + u64 hw_counter; u8 buf[6]; u8 rtcval; int err; @@ -134,11 +133,11 @@ static int ab3100_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alarm) AB3100_AL0, buf, 4); if (err) return err; - fat_time = ((u64) buf[3] << 40) | ((u64) buf[2] << 32) | + hw_counter = ((u64) buf[3] << 40) | ((u64) buf[2] << 32) | ((u64) buf[1] << 24) | ((u64) buf[0] << 16); - time = (unsigned long) (fat_time / (u64) (AB3100_RTC_CLOCK_RATE * 2)); + time = hw_counter / (u64) (AB3100_RTC_CLOCK_RATE * 2); - rtc_time_to_tm(time, &alarm->time); + rtc_time64_to_tm(time, &alarm->time); return rtc_valid_tm(&alarm->time); } @@ -147,17 +146,17 @@ static int ab3100_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alarm) { u8 regs[] = {AB3100_AL0, AB3100_AL1, AB3100_AL2, AB3100_AL3}; unsigned char buf[4]; - unsigned long secs; - u64 fat_time; + time64_t secs; + u64 hw_counter; int err; int i; - rtc_tm_to_time(&alarm->time, &secs); - fat_time = (u64) secs * AB3100_RTC_CLOCK_RATE * 2; - buf[0] = (fat_time >> 16) & 0xFF; - buf[1] = (fat_time >> 24) & 0xFF; - buf[2] = (fat_time >> 32) & 0xFF; - buf[3] = (fat_time >> 40) & 0xFF; + secs = rtc_tm_to_time64(&alarm->time); + hw_counter = secs * AB3100_RTC_CLOCK_RATE * 2; + buf[0] = (hw_counter >> 16) & 0xFF; + buf[1] = (hw_counter >> 24) & 0xFF; + buf[2] = (hw_counter >> 32) & 0xFF; + buf[3] = (hw_counter >> 40) & 0xFF; /* Set the alarm */ for (i = 0; i < 4; i++) { @@ -193,7 +192,7 @@ static int ab3100_rtc_irq_enable(struct device *dev, unsigned int enabled) static const struct rtc_class_ops ab3100_rtc_ops = { .read_time = ab3100_rtc_read_time, - .set_mmss = ab3100_rtc_set_mmss, + .set_mmss64 = ab3100_rtc_set_mmss, .read_alarm = ab3100_rtc_read_alarm, .set_alarm = ab3100_rtc_set_alarm, .alarm_irq_enable = ab3100_rtc_irq_enable, diff --git a/drivers/rtc/rtc-mc13xxx.c b/drivers/rtc/rtc-mc13xxx.c index 5bce904b7ee6..32df1d812367 100644 --- a/drivers/rtc/rtc-mc13xxx.c +++ b/drivers/rtc/rtc-mc13xxx.c @@ -83,20 +83,19 @@ static int mc13xxx_rtc_read_time(struct device *dev, struct rtc_time *tm) return ret; } while (days1 != days2); - rtc_time_to_tm(days1 * SEC_PER_DAY + seconds, tm); + rtc_time64_to_tm((time64_t)days1 * SEC_PER_DAY + seconds, tm); return rtc_valid_tm(tm); } -static int mc13xxx_rtc_set_mmss(struct device *dev, unsigned long secs) +static int mc13xxx_rtc_set_mmss(struct device *dev, time64_t secs) { struct mc13xxx_rtc *priv = dev_get_drvdata(dev); unsigned int seconds, days; unsigned int alarmseconds; int ret; - seconds = secs % SEC_PER_DAY; - days = secs / SEC_PER_DAY; + days = div_s64_rem(secs, SEC_PER_DAY, &seconds); mc13xxx_lock(priv->mc13xxx); @@ -159,7 +158,7 @@ static int mc13xxx_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alarm) { struct mc13xxx_rtc *priv = dev_get_drvdata(dev); unsigned seconds, days; - unsigned long s1970; + time64_t s1970; int enabled, pending; int ret; @@ -189,10 +188,10 @@ out: alarm->enabled = enabled; alarm->pending = pending; - s1970 = days * SEC_PER_DAY + seconds; + s1970 = (time64_t)days * SEC_PER_DAY + seconds; - rtc_time_to_tm(s1970, &alarm->time); - dev_dbg(dev, "%s: %lu\n", __func__, s1970); + rtc_time64_to_tm(s1970, &alarm->time); + dev_dbg(dev, "%s: %lld\n", __func__, (long long)s1970); return 0; } @@ -200,8 +199,8 @@ out: static int mc13xxx_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alarm) { struct mc13xxx_rtc *priv = dev_get_drvdata(dev); - unsigned long s1970; - unsigned seconds, days; + time64_t s1970; + u32 seconds, days; int ret; mc13xxx_lock(priv->mc13xxx); @@ -215,20 +214,17 @@ static int mc13xxx_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alarm) if (unlikely(ret)) goto out; - ret = rtc_tm_to_time(&alarm->time, &s1970); - if (unlikely(ret)) - goto out; + s1970 = rtc_tm_to_time64(&alarm->time); - dev_dbg(dev, "%s: o%2.s %lu\n", __func__, alarm->enabled ? "n" : "ff", - s1970); + dev_dbg(dev, "%s: o%2.s %lld\n", __func__, alarm->enabled ? "n" : "ff", + (long long)s1970); ret = mc13xxx_rtc_irq_enable_unlocked(dev, alarm->enabled, MC13XXX_IRQ_TODA); if (unlikely(ret)) goto out; - seconds = s1970 % SEC_PER_DAY; - days = s1970 / SEC_PER_DAY; + days = div_s64_rem(s1970, SEC_PER_DAY, &seconds); ret = mc13xxx_reg_write(priv->mc13xxx, MC13XXX_RTCDAYA, days); if (unlikely(ret)) @@ -268,7 +264,7 @@ static irqreturn_t mc13xxx_rtc_update_handler(int irq, void *dev) static const struct rtc_class_ops mc13xxx_rtc_ops = { .read_time = mc13xxx_rtc_read_time, - .set_mmss = mc13xxx_rtc_set_mmss, + .set_mmss64 = mc13xxx_rtc_set_mmss, .read_alarm = mc13xxx_rtc_read_alarm, .set_alarm = mc13xxx_rtc_set_alarm, .alarm_irq_enable = mc13xxx_rtc_alarm_irq_enable, diff --git a/drivers/rtc/rtc-mxc.c b/drivers/rtc/rtc-mxc.c index 3c3f8d10ab43..09d422b9f7f7 100644 --- a/drivers/rtc/rtc-mxc.c +++ b/drivers/rtc/rtc-mxc.c @@ -106,7 +106,7 @@ static inline int is_imx1_rtc(struct rtc_plat_data *data) * This function is used to obtain the RTC time or the alarm value in * second. */ -static u32 get_alarm_or_time(struct device *dev, int time_alarm) +static time64_t get_alarm_or_time(struct device *dev, int time_alarm) { struct platform_device *pdev = to_platform_device(dev); struct rtc_plat_data *pdata = platform_get_drvdata(pdev); @@ -129,29 +129,28 @@ static u32 get_alarm_or_time(struct device *dev, int time_alarm) hr = hr_min >> 8; min = hr_min & 0xff; - return (((day * 24 + hr) * 60) + min) * 60 + sec; + return ((((time64_t)day * 24 + hr) * 60) + min) * 60 + sec; } /* * This function sets the RTC alarm value or the time value. */ -static void set_alarm_or_time(struct device *dev, int time_alarm, u32 time) +static void set_alarm_or_time(struct device *dev, int time_alarm, time64_t time) { - u32 day, hr, min, sec, temp; + u32 tod, day, hr, min, sec, temp; struct platform_device *pdev = to_platform_device(dev); struct rtc_plat_data *pdata = platform_get_drvdata(pdev); void __iomem *ioaddr = pdata->ioaddr; - day = time / 86400; - time -= day * 86400; + day = div_s64_rem(time, 86400, &tod); /* time is within a day now */ - hr = time / 3600; - time -= hr * 3600; + hr = tod / 3600; + tod -= hr * 3600; /* time is within an hour now */ - min = time / 60; - sec = time - min * 60; + min = tod / 60; + sec = tod - min * 60; temp = (hr << 8) + min; @@ -173,29 +172,18 @@ static void set_alarm_or_time(struct device *dev, int time_alarm, u32 time) * This function updates the RTC alarm registers and then clears all the * interrupt status bits. */ -static int rtc_update_alarm(struct device *dev, struct rtc_time *alrm) +static void rtc_update_alarm(struct device *dev, struct rtc_time *alrm) { - struct rtc_time alarm_tm, now_tm; - unsigned long now, time; + time64_t time; struct platform_device *pdev = to_platform_device(dev); struct rtc_plat_data *pdata = platform_get_drvdata(pdev); void __iomem *ioaddr = pdata->ioaddr; - now = get_alarm_or_time(dev, MXC_RTC_TIME); - rtc_time_to_tm(now, &now_tm); - alarm_tm.tm_year = now_tm.tm_year; - alarm_tm.tm_mon = now_tm.tm_mon; - alarm_tm.tm_mday = now_tm.tm_mday; - alarm_tm.tm_hour = alrm->tm_hour; - alarm_tm.tm_min = alrm->tm_min; - alarm_tm.tm_sec = alrm->tm_sec; - rtc_tm_to_time(&alarm_tm, &time); + time = rtc_tm_to_time64(alrm); /* clear all the interrupt status bits */ writew(readw(ioaddr + RTC_RTCISR), ioaddr + RTC_RTCISR); set_alarm_or_time(dev, MXC_RTC_ALARM, time); - - return 0; } static void mxc_rtc_irq_enable(struct device *dev, unsigned int bit, @@ -283,14 +271,14 @@ static int mxc_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled) */ static int mxc_rtc_read_time(struct device *dev, struct rtc_time *tm) { - u32 val; + time64_t val; /* Avoid roll-over from reading the different registers */ do { val = get_alarm_or_time(dev, MXC_RTC_TIME); } while (val != get_alarm_or_time(dev, MXC_RTC_TIME)); - rtc_time_to_tm(val, tm); + rtc_time64_to_tm(val, tm); return 0; } @@ -298,7 +286,7 @@ static int mxc_rtc_read_time(struct device *dev, struct rtc_time *tm) /* * This function sets the internal RTC time based on tm in Gregorian date. */ -static int mxc_rtc_set_mmss(struct device *dev, unsigned long time) +static int mxc_rtc_set_mmss(struct device *dev, time64_t time) { struct platform_device *pdev = to_platform_device(dev); struct rtc_plat_data *pdata = platform_get_drvdata(pdev); @@ -309,9 +297,9 @@ static int mxc_rtc_set_mmss(struct device *dev, unsigned long time) if (is_imx1_rtc(pdata)) { struct rtc_time tm; - rtc_time_to_tm(time, &tm); + rtc_time64_to_tm(time, &tm); tm.tm_year = 70; - rtc_tm_to_time(&tm, &time); + time = rtc_tm_to_time64(&tm); } /* Avoid roll-over from reading the different registers */ @@ -333,7 +321,7 @@ static int mxc_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm) struct rtc_plat_data *pdata = platform_get_drvdata(pdev); void __iomem *ioaddr = pdata->ioaddr; - rtc_time_to_tm(get_alarm_or_time(dev, MXC_RTC_ALARM), &alrm->time); + rtc_time64_to_tm(get_alarm_or_time(dev, MXC_RTC_ALARM), &alrm->time); alrm->pending = ((readw(ioaddr + RTC_RTCISR) & RTC_ALM_BIT)) ? 1 : 0; return 0; @@ -346,11 +334,8 @@ static int mxc_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm) { struct platform_device *pdev = to_platform_device(dev); struct rtc_plat_data *pdata = platform_get_drvdata(pdev); - int ret; - ret = rtc_update_alarm(dev, &alrm->time); - if (ret) - return ret; + rtc_update_alarm(dev, &alrm->time); memcpy(&pdata->g_rtc_alarm, &alrm->time, sizeof(struct rtc_time)); mxc_rtc_irq_enable(dev, RTC_ALM_BIT, alrm->enabled); @@ -362,7 +347,7 @@ static int mxc_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm) static struct rtc_class_ops mxc_rtc_ops = { .release = mxc_rtc_release, .read_time = mxc_rtc_read_time, - .set_mmss = mxc_rtc_set_mmss, + .set_mmss64 = mxc_rtc_set_mmss, .read_alarm = mxc_rtc_read_alarm, .set_alarm = mxc_rtc_set_alarm, .alarm_irq_enable = mxc_rtc_alarm_irq_enable, diff --git a/drivers/rtc/rtc-test.c b/drivers/rtc/rtc-test.c index 8f86fa91de1a..3a2da4c892d6 100644 --- a/drivers/rtc/rtc-test.c +++ b/drivers/rtc/rtc-test.c @@ -13,6 +13,10 @@ #include <linux/rtc.h> #include <linux/platform_device.h> +static int test_mmss64; +module_param(test_mmss64, int, 0644); +MODULE_PARM_DESC(test_mmss64, "Test struct rtc_class_ops.set_mmss64()."); + static struct platform_device *test0 = NULL, *test1 = NULL; static int test_rtc_read_alarm(struct device *dev, @@ -30,7 +34,13 @@ static int test_rtc_set_alarm(struct device *dev, static int test_rtc_read_time(struct device *dev, struct rtc_time *tm) { - rtc_time_to_tm(get_seconds(), tm); + rtc_time64_to_tm(ktime_get_real_seconds(), tm); + return 0; +} + +static int test_rtc_set_mmss64(struct device *dev, time64_t secs) +{ + dev_info(dev, "%s, secs = %lld\n", __func__, (long long)secs); return 0; } @@ -55,7 +65,7 @@ static int test_rtc_alarm_irq_enable(struct device *dev, unsigned int enable) return 0; } -static const struct rtc_class_ops test_rtc_ops = { +static struct rtc_class_ops test_rtc_ops = { .proc = test_rtc_proc, .read_time = test_rtc_read_time, .read_alarm = test_rtc_read_alarm, @@ -101,6 +111,11 @@ static int test_probe(struct platform_device *plat_dev) int err; struct rtc_device *rtc; + if (test_mmss64) { + test_rtc_ops.set_mmss64 = test_rtc_set_mmss64; + test_rtc_ops.set_mmss = NULL; + } + rtc = devm_rtc_device_register(&plat_dev->dev, "test", &test_rtc_ops, THIS_MODULE); if (IS_ERR(rtc)) { diff --git a/drivers/rtc/systohc.c b/drivers/rtc/systohc.c index eb71872d0361..7728d5e32bf4 100644 --- a/drivers/rtc/systohc.c +++ b/drivers/rtc/systohc.c @@ -11,7 +11,7 @@ * rtc_set_ntp_time - Save NTP synchronized time to the RTC * @now: Current time of day * - * Replacement for the NTP platform function update_persistent_clock + * Replacement for the NTP platform function update_persistent_clock64 * that stores time for later retrieval by rtc_hctosys. * * Returns 0 on successful RTC update, -ENODEV if a RTC update is not @@ -35,7 +35,10 @@ int rtc_set_ntp_time(struct timespec64 now) if (rtc) { /* rtc_hctosys exclusively uses UTC, so we call set_time here, * not set_mmss. */ - if (rtc->ops && (rtc->ops->set_time || rtc->ops->set_mmss)) + if (rtc->ops && + (rtc->ops->set_time || + rtc->ops->set_mmss64 || + rtc->ops->set_mmss)) err = rtc_set_time(rtc, &tm); rtc_class_close(rtc); } diff --git a/drivers/scsi/be2iscsi/be_main.c b/drivers/scsi/be2iscsi/be_main.c index a7cc61837818..923a2b5a2439 100644 --- a/drivers/scsi/be2iscsi/be_main.c +++ b/drivers/scsi/be2iscsi/be_main.c @@ -5734,9 +5734,9 @@ free_port: hba_free: if (phba->msix_enabled) pci_disable_msix(phba->pcidev); - iscsi_host_remove(phba->shost); pci_dev_put(phba->pcidev); iscsi_host_free(phba->shost); + pci_set_drvdata(pcidev, NULL); disable_pci: pci_disable_device(pcidev); return ret; diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 54d7a6cbb98a..b1a263137a23 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1311,9 +1311,11 @@ scsi_prep_state_check(struct scsi_device *sdev, struct request *req) "rejecting I/O to dead device\n"); ret = BLKPREP_KILL; break; - case SDEV_QUIESCE: case SDEV_BLOCK: case SDEV_CREATED_BLOCK: + ret = BLKPREP_DEFER; + break; + case SDEV_QUIESCE: /* * If the devices is blocked we defer normal commands. */ diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index 2accb6e47beb..77d64251af40 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -1181,7 +1181,7 @@ iscsit_handle_scsi_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd, * traditional iSCSI block I/O. */ if (iscsit_allocate_iovecs(cmd) < 0) { - return iscsit_add_reject_cmd(cmd, + return iscsit_reject_cmd(cmd, ISCSI_REASON_BOOKMARK_NO_RESOURCES, buf); } immed_data = cmd->immediate_data; @@ -3468,6 +3468,7 @@ iscsit_build_sendtargets_response(struct iscsi_cmd *cmd, tpg_np_list) { struct iscsi_np *np = tpg_np->tpg_np; bool inaddr_any = iscsit_check_inaddr_any(np); + char *fmt_str; if (np->np_network_transport != network_transport) continue; @@ -3495,8 +3496,12 @@ iscsit_build_sendtargets_response(struct iscsi_cmd *cmd, } } - len = sprintf(buf, "TargetAddress=" - "%s:%hu,%hu", + if (np->np_sockaddr.ss_family == AF_INET6) + fmt_str = "TargetAddress=[%s]:%hu,%hu"; + else + fmt_str = "TargetAddress=%s:%hu,%hu"; + + len = sprintf(buf, fmt_str, inaddr_any ? conn->local_ip : np->np_ip, np->np_port, tpg->tpgt); diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index 79b4ec3ca2db..7faa6aef9a4d 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -781,8 +781,8 @@ int se_dev_set_emulate_fua_write(struct se_device *dev, int flag) } if (flag && dev->transport->get_write_cache) { - pr_err("emulate_fua_write not supported for this device\n"); - return -EINVAL; + pr_warn("emulate_fua_write not supported for this device, ignoring\n"); + return 0; } if (dev->export_count) { pr_err("emulate_fua_write cannot be changed with active" diff --git a/drivers/thermal/st/st_thermal.c b/drivers/thermal/st/st_thermal.c index d1ec5804c0bb..76c515dd802b 100644 --- a/drivers/thermal/st/st_thermal.c +++ b/drivers/thermal/st/st_thermal.c @@ -25,7 +25,7 @@ * Function to allocate regfields which are common * between syscfg and memory mapped based sensors */ -int st_thermal_alloc_regfields(struct st_thermal_sensor *sensor) +static int st_thermal_alloc_regfields(struct st_thermal_sensor *sensor) { struct device *dev = sensor->dev; struct regmap *regmap = sensor->regmap; diff --git a/drivers/thermal/st/st_thermal_memmap.c b/drivers/thermal/st/st_thermal_memmap.c index 067bfcdb91d6..fc0c9e198710 100644 --- a/drivers/thermal/st/st_thermal_memmap.c +++ b/drivers/thermal/st/st_thermal_memmap.c @@ -157,7 +157,7 @@ static const struct st_thermal_sensor_ops st_mmap_sensor_ops = { }; /* Compatible device data stih416 mpe thermal sensor */ -const struct st_thermal_compat_data st_416mpe_cdata = { +static const struct st_thermal_compat_data st_416mpe_cdata = { .reg_fields = st_mmap_thermal_regfields, .ops = &st_mmap_sensor_ops, .calibration_val = 14, @@ -166,7 +166,7 @@ const struct st_thermal_compat_data st_416mpe_cdata = { }; /* Compatible device data stih407 thermal sensor */ -const struct st_thermal_compat_data st_407_cdata = { +static const struct st_thermal_compat_data st_407_cdata = { .reg_fields = st_mmap_thermal_regfields, .ops = &st_mmap_sensor_ops, .calibration_val = 16, @@ -174,19 +174,19 @@ const struct st_thermal_compat_data st_407_cdata = { .crit_temp = 120, }; -static struct of_device_id st_mmap_thermal_of_match[] = { +static const struct of_device_id st_mmap_thermal_of_match[] = { { .compatible = "st,stih416-mpe-thermal", .data = &st_416mpe_cdata }, { .compatible = "st,stih407-thermal", .data = &st_407_cdata }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, st_mmap_thermal_of_match); -int st_mmap_probe(struct platform_device *pdev) +static int st_mmap_probe(struct platform_device *pdev) { return st_thermal_register(pdev, st_mmap_thermal_of_match); } -int st_mmap_remove(struct platform_device *pdev) +static int st_mmap_remove(struct platform_device *pdev) { return st_thermal_unregister(pdev); } diff --git a/drivers/thermal/st/st_thermal_syscfg.c b/drivers/thermal/st/st_thermal_syscfg.c index 26d36a242bb8..3df5b7890703 100644 --- a/drivers/thermal/st/st_thermal_syscfg.c +++ b/drivers/thermal/st/st_thermal_syscfg.c @@ -104,7 +104,7 @@ static const struct st_thermal_sensor_ops st_syscfg_sensor_ops = { }; /* Compatible device data for stih415 sas thermal sensor */ -const struct st_thermal_compat_data st_415sas_cdata = { +static const struct st_thermal_compat_data st_415sas_cdata = { .sys_compat = "st,stih415-front-syscfg", .reg_fields = st_415sas_regfields, .ops = &st_syscfg_sensor_ops, @@ -114,7 +114,7 @@ const struct st_thermal_compat_data st_415sas_cdata = { }; /* Compatible device data for stih415 mpe thermal sensor */ -const struct st_thermal_compat_data st_415mpe_cdata = { +static const struct st_thermal_compat_data st_415mpe_cdata = { .sys_compat = "st,stih415-system-syscfg", .reg_fields = st_415mpe_regfields, .ops = &st_syscfg_sensor_ops, @@ -124,7 +124,7 @@ const struct st_thermal_compat_data st_415mpe_cdata = { }; /* Compatible device data for stih416 sas thermal sensor */ -const struct st_thermal_compat_data st_416sas_cdata = { +static const struct st_thermal_compat_data st_416sas_cdata = { .sys_compat = "st,stih416-front-syscfg", .reg_fields = st_416sas_regfields, .ops = &st_syscfg_sensor_ops, @@ -134,7 +134,7 @@ const struct st_thermal_compat_data st_416sas_cdata = { }; /* Compatible device data for stid127 thermal sensor */ -const struct st_thermal_compat_data st_127_cdata = { +static const struct st_thermal_compat_data st_127_cdata = { .sys_compat = "st,stid127-cpu-syscfg", .reg_fields = st_127_regfields, .ops = &st_syscfg_sensor_ops, @@ -143,7 +143,7 @@ const struct st_thermal_compat_data st_127_cdata = { .crit_temp = 120, }; -static struct of_device_id st_syscfg_thermal_of_match[] = { +static const struct of_device_id st_syscfg_thermal_of_match[] = { { .compatible = "st,stih415-sas-thermal", .data = &st_415sas_cdata }, { .compatible = "st,stih415-mpe-thermal", .data = &st_415mpe_cdata }, { .compatible = "st,stih416-sas-thermal", .data = &st_416sas_cdata }, @@ -152,12 +152,12 @@ static struct of_device_id st_syscfg_thermal_of_match[] = { }; MODULE_DEVICE_TABLE(of, st_syscfg_thermal_of_match); -int st_syscfg_probe(struct platform_device *pdev) +static int st_syscfg_probe(struct platform_device *pdev) { return st_thermal_register(pdev, st_syscfg_thermal_of_match); } -int st_syscfg_remove(struct platform_device *pdev) +static int st_syscfg_remove(struct platform_device *pdev) { return st_thermal_unregister(pdev); } diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index 174d3bcf8bd7..4108db7e10c1 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -458,8 +458,10 @@ static void update_temperature(struct thermal_zone_device *tz) ret = thermal_zone_get_temp(tz, &temp); if (ret) { - dev_warn(&tz->device, "failed to read out thermal zone %d\n", - tz->id); + if (ret != -EAGAIN) + dev_warn(&tz->device, + "failed to read out thermal zone (%d)\n", + ret); return; } @@ -278,11 +278,11 @@ static int aio_ring_mmap(struct file *file, struct vm_area_struct *vma) return 0; } -static void aio_ring_remap(struct file *file, struct vm_area_struct *vma) +static int aio_ring_remap(struct file *file, struct vm_area_struct *vma) { struct mm_struct *mm = vma->vm_mm; struct kioctx_table *table; - int i; + int i, res = -EINVAL; spin_lock(&mm->ioctx_lock); rcu_read_lock(); @@ -292,13 +292,17 @@ static void aio_ring_remap(struct file *file, struct vm_area_struct *vma) ctx = table->table[i]; if (ctx && ctx->aio_ring_file == file) { - ctx->user_id = ctx->mmap_base = vma->vm_start; + if (!atomic_read(&ctx->dead)) { + ctx->user_id = ctx->mmap_base = vma->vm_start; + res = 0; + } break; } } rcu_read_unlock(); spin_unlock(&mm->ioctx_lock); + return res; } static const struct file_operations aio_ring_fops = { @@ -727,6 +731,9 @@ static struct kioctx *ioctx_alloc(unsigned nr_events) err_cleanup: aio_nr_sub(ctx->max_reqs); err_ctx: + atomic_set(&ctx->dead, 1); + if (ctx->mmap_size) + vm_munmap(ctx->mmap_base, ctx->mmap_size); aio_free_ring(ctx); err: mutex_unlock(&ctx->ring_lock); @@ -748,11 +755,12 @@ static int kill_ioctx(struct mm_struct *mm, struct kioctx *ctx, { struct kioctx_table *table; - if (atomic_xchg(&ctx->dead, 1)) + spin_lock(&mm->ioctx_lock); + if (atomic_xchg(&ctx->dead, 1)) { + spin_unlock(&mm->ioctx_lock); return -EINVAL; + } - - spin_lock(&mm->ioctx_lock); table = rcu_dereference_raw(mm->ioctx_table); WARN_ON(ctx != table->table[ctx->id]); table->table[ctx->id] = NULL; diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 46e0d4e857c7..ba1790e52ff2 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -2394,7 +2394,6 @@ relock: /* * for completing the rest of the request. */ - *ppos += written; count -= written; written_buffered = generic_perform_write(file, from, *ppos); /* @@ -2409,7 +2408,6 @@ relock: goto out_dio; } - iocb->ki_pos = *ppos + written_buffered; /* We need to ensure that the page cache pages are written to * disk and invalidated to preserve the expected O_DIRECT * semantics. @@ -2418,6 +2416,7 @@ relock: ret = filemap_write_and_wait_range(file->f_mapping, *ppos, endbyte); if (ret == 0) { + iocb->ki_pos = *ppos + written_buffered; written += written_buffered; invalidate_mapping_pages(mapping, *ppos >> PAGE_CACHE_SHIFT, @@ -2440,10 +2439,14 @@ out_dio: /* buffered aio wouldn't have proper lock coverage today */ BUG_ON(ret == -EIOCBQUEUED && !(file->f_flags & O_DIRECT)); + if (unlikely(written <= 0)) + goto no_sync; + if (((file->f_flags & O_DSYNC) && !direct_io) || IS_SYNC(inode) || ((file->f_flags & O_DIRECT) && !direct_io)) { - ret = filemap_fdatawrite_range(file->f_mapping, *ppos, - *ppos + count - 1); + ret = filemap_fdatawrite_range(file->f_mapping, + iocb->ki_pos - written, + iocb->ki_pos - 1); if (ret < 0) written = ret; @@ -2454,10 +2457,12 @@ out_dio: } if (!ret) - ret = filemap_fdatawait_range(file->f_mapping, *ppos, - *ppos + count - 1); + ret = filemap_fdatawait_range(file->f_mapping, + iocb->ki_pos - written, + iocb->ki_pos - 1); } +no_sync: /* * deep in g_f_a_w_n()->ocfs2_direct_IO we pass in a ocfs2_dio_end_io * function pointer which is called when o_direct io completes so that diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h index b3f45a578344..e5966758c093 100644 --- a/include/kvm/arm_arch_timer.h +++ b/include/kvm/arm_arch_timer.h @@ -24,17 +24,14 @@ #include <linux/workqueue.h> struct arch_timer_kvm { -#ifdef CONFIG_KVM_ARM_TIMER /* Is the timer enabled */ bool enabled; /* Virtual offset */ cycle_t cntvoff; -#endif }; struct arch_timer_cpu { -#ifdef CONFIG_KVM_ARM_TIMER /* Registers: control register, timer value */ u32 cntv_ctl; /* Saved/restored */ cycle_t cntv_cval; /* Saved/restored */ @@ -55,10 +52,8 @@ struct arch_timer_cpu { /* Timer IRQ */ const struct kvm_irq_level *irq; -#endif }; -#ifdef CONFIG_KVM_ARM_TIMER int kvm_timer_hyp_init(void); void kvm_timer_enable(struct kvm *kvm); void kvm_timer_init(struct kvm *kvm); @@ -72,30 +67,6 @@ void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu); u64 kvm_arm_timer_get_reg(struct kvm_vcpu *, u64 regid); int kvm_arm_timer_set_reg(struct kvm_vcpu *, u64 regid, u64 value); -#else -static inline int kvm_timer_hyp_init(void) -{ - return 0; -}; - -static inline void kvm_timer_enable(struct kvm *kvm) {} -static inline void kvm_timer_init(struct kvm *kvm) {} -static inline void kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu, - const struct kvm_irq_level *irq) {} -static inline void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu) {} -static inline void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu) {} -static inline void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu) {} -static inline void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu) {} - -static inline int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value) -{ - return 0; -} - -static inline u64 kvm_arm_timer_get_reg(struct kvm_vcpu *vcpu, u64 regid) -{ - return 0; -} -#endif +bool kvm_timer_should_fire(struct kvm_vcpu *vcpu); #endif diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index 66203b268984..133ea00aa83b 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -24,6 +24,7 @@ #include <linux/irqreturn.h> #include <linux/spinlock.h> #include <linux/types.h> +#include <kvm/iodev.h> #define VGIC_NR_IRQS_LEGACY 256 #define VGIC_NR_SGIS 16 @@ -140,16 +141,21 @@ struct vgic_params { }; struct vgic_vm_ops { - bool (*handle_mmio)(struct kvm_vcpu *, struct kvm_run *, - struct kvm_exit_mmio *); bool (*queue_sgi)(struct kvm_vcpu *, int irq); void (*add_sgi_source)(struct kvm_vcpu *, int irq, int source); int (*init_model)(struct kvm *); int (*map_resources)(struct kvm *, const struct vgic_params *); }; +struct vgic_io_device { + gpa_t addr; + int len; + const struct vgic_io_range *reg_ranges; + struct kvm_vcpu *redist_vcpu; + struct kvm_io_device dev; +}; + struct vgic_dist { -#ifdef CONFIG_KVM_ARM_VGIC spinlock_t lock; bool in_kernel; bool ready; @@ -197,6 +203,9 @@ struct vgic_dist { /* Level-triggered interrupt queued on VCPU interface */ struct vgic_bitmap irq_queued; + /* Interrupt was active when unqueue from VCPU interface */ + struct vgic_bitmap irq_active; + /* Interrupt priority. Not used yet. */ struct vgic_bytemap irq_priority; @@ -237,8 +246,12 @@ struct vgic_dist { /* Bitmap indicating which CPU has something pending */ unsigned long *irq_pending_on_cpu; + /* Bitmap indicating which CPU has active IRQs */ + unsigned long *irq_active_on_cpu; + struct vgic_vm_ops vm_ops; -#endif + struct vgic_io_device dist_iodev; + struct vgic_io_device *redist_iodevs; }; struct vgic_v2_cpu_if { @@ -266,13 +279,18 @@ struct vgic_v3_cpu_if { }; struct vgic_cpu { -#ifdef CONFIG_KVM_ARM_VGIC /* per IRQ to LR mapping */ u8 *vgic_irq_lr_map; - /* Pending interrupts on this VCPU */ + /* Pending/active/both interrupts on this VCPU */ DECLARE_BITMAP( pending_percpu, VGIC_NR_PRIVATE_IRQS); + DECLARE_BITMAP( active_percpu, VGIC_NR_PRIVATE_IRQS); + DECLARE_BITMAP( pend_act_percpu, VGIC_NR_PRIVATE_IRQS); + + /* Pending/active/both shared interrupts, dynamically sized */ unsigned long *pending_shared; + unsigned long *active_shared; + unsigned long *pend_act_shared; /* Bitmap of used/free list registers */ DECLARE_BITMAP( lr_used, VGIC_V2_MAX_LRS); @@ -285,7 +303,6 @@ struct vgic_cpu { struct vgic_v2_cpu_if vgic_v2; struct vgic_v3_cpu_if vgic_v3; }; -#endif }; #define LR_EMPTY 0xff @@ -295,10 +312,7 @@ struct vgic_cpu { struct kvm; struct kvm_vcpu; -struct kvm_run; -struct kvm_exit_mmio; -#ifdef CONFIG_KVM_ARM_VGIC int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write); int kvm_vgic_hyp_init(void); int kvm_vgic_map_resources(struct kvm *kvm); @@ -312,8 +326,7 @@ int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num, bool level); void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg); int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu); -bool vgic_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run, - struct kvm_exit_mmio *mmio); +int kvm_vgic_vcpu_active_irq(struct kvm_vcpu *vcpu); #define irqchip_in_kernel(k) (!!((k)->arch.vgic.in_kernel)) #define vgic_initialized(k) (!!((k)->arch.vgic.nr_cpus)) @@ -335,84 +348,4 @@ static inline int vgic_v3_probe(struct device_node *vgic_node, } #endif -#else -static inline int kvm_vgic_hyp_init(void) -{ - return 0; -} - -static inline int kvm_vgic_set_addr(struct kvm *kvm, unsigned long type, u64 addr) -{ - return 0; -} - -static inline int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write) -{ - return -ENXIO; -} - -static inline int kvm_vgic_map_resources(struct kvm *kvm) -{ - return 0; -} - -static inline int kvm_vgic_create(struct kvm *kvm, u32 type) -{ - return 0; -} - -static inline void kvm_vgic_destroy(struct kvm *kvm) -{ -} - -static inline void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) -{ -} - -static inline int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu) -{ - return 0; -} - -static inline void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu) {} -static inline void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu) {} - -static inline int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, - unsigned int irq_num, bool level) -{ - return 0; -} - -static inline int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu) -{ - return 0; -} - -static inline bool vgic_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run, - struct kvm_exit_mmio *mmio) -{ - return false; -} - -static inline int irqchip_in_kernel(struct kvm *kvm) -{ - return 0; -} - -static inline bool vgic_initialized(struct kvm *kvm) -{ - return true; -} - -static inline bool vgic_ready(struct kvm *kvm) -{ - return true; -} - -static inline int kvm_vgic_get_max_vcpus(void) -{ - return KVM_MAX_VCPUS; -} -#endif - #endif diff --git a/virt/kvm/iodev.h b/include/kvm/iodev.h index 12fd3caffd2b..a6d208b916f5 100644 --- a/virt/kvm/iodev.h +++ b/include/kvm/iodev.h @@ -9,17 +9,17 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + * along with this program. If not, see <http://www.gnu.org/licenses/>. */ #ifndef __KVM_IODEV_H__ #define __KVM_IODEV_H__ #include <linux/kvm_types.h> -#include <asm/errno.h> +#include <linux/errno.h> struct kvm_io_device; +struct kvm_vcpu; /** * kvm_io_device_ops are called under kvm slots_lock. @@ -27,11 +27,13 @@ struct kvm_io_device; * or non-zero to have it passed to the next device. **/ struct kvm_io_device_ops { - int (*read)(struct kvm_io_device *this, + int (*read)(struct kvm_vcpu *vcpu, + struct kvm_io_device *this, gpa_t addr, int len, void *val); - int (*write)(struct kvm_io_device *this, + int (*write)(struct kvm_vcpu *vcpu, + struct kvm_io_device *this, gpa_t addr, int len, const void *val); @@ -49,16 +51,20 @@ static inline void kvm_iodevice_init(struct kvm_io_device *dev, dev->ops = ops; } -static inline int kvm_iodevice_read(struct kvm_io_device *dev, - gpa_t addr, int l, void *v) +static inline int kvm_iodevice_read(struct kvm_vcpu *vcpu, + struct kvm_io_device *dev, gpa_t addr, + int l, void *v) { - return dev->ops->read ? dev->ops->read(dev, addr, l, v) : -EOPNOTSUPP; + return dev->ops->read ? dev->ops->read(vcpu, dev, addr, l, v) + : -EOPNOTSUPP; } -static inline int kvm_iodevice_write(struct kvm_io_device *dev, - gpa_t addr, int l, const void *v) +static inline int kvm_iodevice_write(struct kvm_vcpu *vcpu, + struct kvm_io_device *dev, gpa_t addr, + int l, const void *v) { - return dev->ops->write ? dev->ops->write(dev, addr, l, v) : -EOPNOTSUPP; + return dev->ops->write ? dev->ops->write(vcpu, dev, addr, l, v) + : -EOPNOTSUPP; } static inline void kvm_iodevice_destructor(struct kvm_io_device *dev) diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index c294e3e25e37..a1b25e35ea5f 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -181,7 +181,9 @@ enum rq_flag_bits { __REQ_ELVPRIV, /* elevator private data attached */ __REQ_FAILED, /* set if the request failed */ __REQ_QUIET, /* don't worry about errors */ - __REQ_PREEMPT, /* set for "ide_preempt" requests */ + __REQ_PREEMPT, /* set for "ide_preempt" requests and also + for requests for which the SCSI "quiesce" + state must be ignored. */ __REQ_ALLOCED, /* request came from our alloc pool */ __REQ_COPY_USER, /* contains copies of user pages */ __REQ_FLUSH_SEQ, /* request for flush sequence */ diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index 2e4cb67f6e56..96c280b2c263 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -8,33 +8,19 @@ #ifndef _LINUX_CLOCKCHIPS_H #define _LINUX_CLOCKCHIPS_H -/* Clock event notification values */ -enum clock_event_nofitiers { - CLOCK_EVT_NOTIFY_ADD, - CLOCK_EVT_NOTIFY_BROADCAST_ON, - CLOCK_EVT_NOTIFY_BROADCAST_OFF, - CLOCK_EVT_NOTIFY_BROADCAST_FORCE, - CLOCK_EVT_NOTIFY_BROADCAST_ENTER, - CLOCK_EVT_NOTIFY_BROADCAST_EXIT, - CLOCK_EVT_NOTIFY_SUSPEND, - CLOCK_EVT_NOTIFY_RESUME, - CLOCK_EVT_NOTIFY_CPU_DYING, - CLOCK_EVT_NOTIFY_CPU_DEAD, -}; - -#ifdef CONFIG_GENERIC_CLOCKEVENTS_BUILD +#ifdef CONFIG_GENERIC_CLOCKEVENTS -#include <linux/clocksource.h> -#include <linux/cpumask.h> -#include <linux/ktime.h> -#include <linux/notifier.h> +# include <linux/clocksource.h> +# include <linux/cpumask.h> +# include <linux/ktime.h> +# include <linux/notifier.h> struct clock_event_device; struct module; -/* Clock event mode commands */ +/* Clock event mode commands for legacy ->set_mode(): OBSOLETE */ enum clock_event_mode { - CLOCK_EVT_MODE_UNUSED = 0, + CLOCK_EVT_MODE_UNUSED, CLOCK_EVT_MODE_SHUTDOWN, CLOCK_EVT_MODE_PERIODIC, CLOCK_EVT_MODE_ONESHOT, @@ -42,30 +28,49 @@ enum clock_event_mode { }; /* + * Possible states of a clock event device. + * + * DETACHED: Device is not used by clockevents core. Initial state or can be + * reached from SHUTDOWN. + * SHUTDOWN: Device is powered-off. Can be reached from PERIODIC or ONESHOT. + * PERIODIC: Device is programmed to generate events periodically. Can be + * reached from DETACHED or SHUTDOWN. + * ONESHOT: Device is programmed to generate event only once. Can be reached + * from DETACHED or SHUTDOWN. + */ +enum clock_event_state { + CLOCK_EVT_STATE_DETACHED, + CLOCK_EVT_STATE_SHUTDOWN, + CLOCK_EVT_STATE_PERIODIC, + CLOCK_EVT_STATE_ONESHOT, +}; + +/* * Clock event features */ -#define CLOCK_EVT_FEAT_PERIODIC 0x000001 -#define CLOCK_EVT_FEAT_ONESHOT 0x000002 -#define CLOCK_EVT_FEAT_KTIME 0x000004 +# define CLOCK_EVT_FEAT_PERIODIC 0x000001 +# define CLOCK_EVT_FEAT_ONESHOT 0x000002 +# define CLOCK_EVT_FEAT_KTIME 0x000004 + /* - * x86(64) specific misfeatures: + * x86(64) specific (mis)features: * * - Clockevent source stops in C3 State and needs broadcast support. * - Local APIC timer is used as a dummy device. */ -#define CLOCK_EVT_FEAT_C3STOP 0x000008 -#define CLOCK_EVT_FEAT_DUMMY 0x000010 +# define CLOCK_EVT_FEAT_C3STOP 0x000008 +# define CLOCK_EVT_FEAT_DUMMY 0x000010 /* * Core shall set the interrupt affinity dynamically in broadcast mode */ -#define CLOCK_EVT_FEAT_DYNIRQ 0x000020 -#define CLOCK_EVT_FEAT_PERCPU 0x000040 +# define CLOCK_EVT_FEAT_DYNIRQ 0x000020 +# define CLOCK_EVT_FEAT_PERCPU 0x000040 /* * Clockevent device is based on a hrtimer for broadcast */ -#define CLOCK_EVT_FEAT_HRTIMER 0x000080 +# define CLOCK_EVT_FEAT_HRTIMER 0x000080 /** * struct clock_event_device - clock event device descriptor @@ -78,10 +83,15 @@ enum clock_event_mode { * @min_delta_ns: minimum delta value in ns * @mult: nanosecond to cycles multiplier * @shift: nanoseconds to cycles divisor (power of two) - * @mode: operating mode assigned by the management code + * @mode: operating mode, relevant only to ->set_mode(), OBSOLETE + * @state: current state of the device, assigned by the core code * @features: features * @retries: number of forced programming retries - * @set_mode: set mode function + * @set_mode: legacy set mode function, only for modes <= CLOCK_EVT_MODE_RESUME. + * @set_state_periodic: switch state to periodic, if !set_mode + * @set_state_oneshot: switch state to oneshot, if !set_mode + * @set_state_shutdown: switch state to shutdown, if !set_mode + * @tick_resume: resume clkevt device, if !set_mode * @broadcast: function to broadcast events * @min_delta_ticks: minimum delta value in ticks stored for reconfiguration * @max_delta_ticks: maximum delta value in ticks stored for reconfiguration @@ -95,22 +105,31 @@ enum clock_event_mode { */ struct clock_event_device { void (*event_handler)(struct clock_event_device *); - int (*set_next_event)(unsigned long evt, - struct clock_event_device *); - int (*set_next_ktime)(ktime_t expires, - struct clock_event_device *); + int (*set_next_event)(unsigned long evt, struct clock_event_device *); + int (*set_next_ktime)(ktime_t expires, struct clock_event_device *); ktime_t next_event; u64 max_delta_ns; u64 min_delta_ns; u32 mult; u32 shift; enum clock_event_mode mode; + enum clock_event_state state; unsigned int features; unsigned long retries; + /* + * State transition callback(s): Only one of the two groups should be + * defined: + * - set_mode(), only for modes <= CLOCK_EVT_MODE_RESUME. + * - set_state_{shutdown|periodic|oneshot}(), tick_resume(). + */ + void (*set_mode)(enum clock_event_mode mode, struct clock_event_device *); + int (*set_state_periodic)(struct clock_event_device *); + int (*set_state_oneshot)(struct clock_event_device *); + int (*set_state_shutdown)(struct clock_event_device *); + int (*tick_resume)(struct clock_event_device *); + void (*broadcast)(const struct cpumask *mask); - void (*set_mode)(enum clock_event_mode mode, - struct clock_event_device *); void (*suspend)(struct clock_event_device *); void (*resume)(struct clock_event_device *); unsigned long min_delta_ticks; @@ -136,18 +155,18 @@ struct clock_event_device { * * factor = (clock_ticks << shift) / nanoseconds */ -static inline unsigned long div_sc(unsigned long ticks, unsigned long nsec, - int shift) +static inline unsigned long +div_sc(unsigned long ticks, unsigned long nsec, int shift) { - uint64_t tmp = ((uint64_t)ticks) << shift; + u64 tmp = ((u64)ticks) << shift; do_div(tmp, nsec); + return (unsigned long) tmp; } /* Clock event layer functions */ -extern u64 clockevent_delta2ns(unsigned long latch, - struct clock_event_device *evt); +extern u64 clockevent_delta2ns(unsigned long latch, struct clock_event_device *evt); extern void clockevents_register_device(struct clock_event_device *dev); extern int clockevents_unbind_device(struct clock_event_device *ced, int cpu); @@ -158,57 +177,42 @@ extern void clockevents_config_and_register(struct clock_event_device *dev, extern int clockevents_update_freq(struct clock_event_device *ce, u32 freq); -extern void clockevents_exchange_device(struct clock_event_device *old, - struct clock_event_device *new); -extern void clockevents_set_mode(struct clock_event_device *dev, - enum clock_event_mode mode); -extern int clockevents_program_event(struct clock_event_device *dev, - ktime_t expires, bool force); - -extern void clockevents_handle_noop(struct clock_event_device *dev); - static inline void clockevents_calc_mult_shift(struct clock_event_device *ce, u32 freq, u32 minsec) { - return clocks_calc_mult_shift(&ce->mult, &ce->shift, NSEC_PER_SEC, - freq, minsec); + return clocks_calc_mult_shift(&ce->mult, &ce->shift, NSEC_PER_SEC, freq, minsec); } extern void clockevents_suspend(void); extern void clockevents_resume(void); -#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST -#ifdef CONFIG_ARCH_HAS_TICK_BROADCAST +# ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST +# ifdef CONFIG_ARCH_HAS_TICK_BROADCAST extern void tick_broadcast(const struct cpumask *mask); -#else -#define tick_broadcast NULL -#endif +# else +# define tick_broadcast NULL +# endif extern int tick_receive_broadcast(void); -#endif +# endif -#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT) +# if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT) extern void tick_setup_hrtimer_broadcast(void); extern int tick_check_broadcast_expired(void); -#else +# else static inline int tick_check_broadcast_expired(void) { return 0; } -static inline void tick_setup_hrtimer_broadcast(void) {}; -#endif +static inline void tick_setup_hrtimer_broadcast(void) { } +# endif -#ifdef CONFIG_GENERIC_CLOCKEVENTS extern int clockevents_notify(unsigned long reason, void *arg); -#else -static inline int clockevents_notify(unsigned long reason, void *arg) { return 0; } -#endif - -#else /* CONFIG_GENERIC_CLOCKEVENTS_BUILD */ -static inline void clockevents_suspend(void) {} -static inline void clockevents_resume(void) {} +#else /* !CONFIG_GENERIC_CLOCKEVENTS: */ +static inline void clockevents_suspend(void) { } +static inline void clockevents_resume(void) { } static inline int clockevents_notify(unsigned long reason, void *arg) { return 0; } static inline int tick_check_broadcast_expired(void) { return 0; } -static inline void tick_setup_hrtimer_broadcast(void) {}; +static inline void tick_setup_hrtimer_broadcast(void) { } -#endif +#endif /* !CONFIG_GENERIC_CLOCKEVENTS */ -#endif +#endif /* _LINUX_CLOCKCHIPS_H */ diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 9c78d15d33e4..135509821c39 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -56,6 +56,7 @@ struct module; * @shift: cycle to nanosecond divisor (power of two) * @max_idle_ns: max idle time permitted by the clocksource (nsecs) * @maxadj: maximum adjustment value to mult (~11%) + * @max_cycles: maximum safe cycle value which won't overflow on multiplication * @flags: flags describing special properties * @archdata: arch-specific data * @suspend: suspend function for the clocksource, if necessary @@ -76,7 +77,7 @@ struct clocksource { #ifdef CONFIG_ARCH_CLOCKSOURCE_DATA struct arch_clocksource_data archdata; #endif - + u64 max_cycles; const char *name; struct list_head list; int rating; @@ -178,7 +179,6 @@ static inline s64 clocksource_cyc2ns(cycle_t cycles, u32 mult, u32 shift) } -extern int clocksource_register(struct clocksource*); extern int clocksource_unregister(struct clocksource*); extern void clocksource_touch_watchdog(void); extern struct clocksource* clocksource_get_next(void); @@ -189,7 +189,7 @@ extern struct clocksource * __init clocksource_default_clock(void); extern void clocksource_mark_unstable(struct clocksource *cs); extern u64 -clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask); +clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask, u64 *max_cycles); extern void clocks_calc_mult_shift(u32 *mult, u32 *shift, u32 from, u32 to, u32 minsec); @@ -200,7 +200,16 @@ clocks_calc_mult_shift(u32 *mult, u32 *shift, u32 from, u32 to, u32 minsec); extern int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq); extern void -__clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq); +__clocksource_update_freq_scale(struct clocksource *cs, u32 scale, u32 freq); + +/* + * Don't call this unless you are a default clocksource + * (AKA: jiffies) and absolutely have to. + */ +static inline int __clocksource_register(struct clocksource *cs) +{ + return __clocksource_register_scale(cs, 1, 0); +} static inline int clocksource_register_hz(struct clocksource *cs, u32 hz) { @@ -212,14 +221,14 @@ static inline int clocksource_register_khz(struct clocksource *cs, u32 khz) return __clocksource_register_scale(cs, 1000, khz); } -static inline void __clocksource_updatefreq_hz(struct clocksource *cs, u32 hz) +static inline void __clocksource_update_freq_hz(struct clocksource *cs, u32 hz) { - __clocksource_updatefreq_scale(cs, 1, hz); + __clocksource_update_freq_scale(cs, 1, hz); } -static inline void __clocksource_updatefreq_khz(struct clocksource *cs, u32 khz) +static inline void __clocksource_update_freq_khz(struct clocksource *cs, u32 khz) { - __clocksource_updatefreq_scale(cs, 1000, khz); + __clocksource_update_freq_scale(cs, 1000, khz); } diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 1b45e4a0519b..0e41ca0e5927 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -192,29 +192,16 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect); #include <uapi/linux/types.h> -static __always_inline void data_access_exceeds_word_size(void) -#ifdef __compiletime_warning -__compiletime_warning("data access exceeds word size and won't be atomic") -#endif -; - -static __always_inline void data_access_exceeds_word_size(void) -{ -} - static __always_inline void __read_once_size(const volatile void *p, void *res, int size) { switch (size) { case 1: *(__u8 *)res = *(volatile __u8 *)p; break; case 2: *(__u16 *)res = *(volatile __u16 *)p; break; case 4: *(__u32 *)res = *(volatile __u32 *)p; break; -#ifdef CONFIG_64BIT case 8: *(__u64 *)res = *(volatile __u64 *)p; break; -#endif default: barrier(); __builtin_memcpy((void *)res, (const void *)p, size); - data_access_exceeds_word_size(); barrier(); } } @@ -225,13 +212,10 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s case 1: *(volatile __u8 *)p = *(__u8 *)res; break; case 2: *(volatile __u16 *)p = *(__u16 *)res; break; case 4: *(volatile __u32 *)p = *(__u32 *)res; break; -#ifdef CONFIG_64BIT case 8: *(volatile __u64 *)p = *(__u64 *)res; break; -#endif default: barrier(); __builtin_memcpy((void *)p, (const void *)res, size); - data_access_exceeds_word_size(); barrier(); } } diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 306178d7309f..9c5e89254796 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -77,7 +77,6 @@ struct cpuidle_device { unsigned int cpu; int last_residency; - int state_count; struct cpuidle_state_usage states_usage[CPUIDLE_STATE_MAX]; struct cpuidle_state_kobj *kobjs[CPUIDLE_STATE_MAX]; struct cpuidle_driver_kobj *kobj_driver; diff --git a/include/linux/dmapool.h b/include/linux/dmapool.h index 022e34fcbd1b..52456aa566a0 100644 --- a/include/linux/dmapool.h +++ b/include/linux/dmapool.h @@ -14,6 +14,8 @@ #include <asm/io.h> #include <asm/scatterlist.h> +struct device; + struct dma_pool *dma_pool_create(const char *name, struct device *dev, size_t size, size_t align, size_t allocation); diff --git a/include/linux/efi.h b/include/linux/efi.h index cf7e431cbc73..af5be0368dec 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -942,6 +942,7 @@ extern int __init efi_setup_pcdp_console(char *); #define EFI_64BIT 5 /* Is the firmware 64-bit? */ #define EFI_PARAVIRT 6 /* Access is via a paravirt interface */ #define EFI_ARCH_1 7 /* First arch-specific bit */ +#define EFI_DBG 8 /* Print additional debug info at runtime */ #ifdef CONFIG_EFI /* diff --git a/include/linux/fs.h b/include/linux/fs.h index f4131e8ead74..52cc4492cb3a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1549,7 +1549,7 @@ struct file_operations { long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long); long (*compat_ioctl) (struct file *, unsigned int, unsigned long); int (*mmap) (struct file *, struct vm_area_struct *); - void (*mremap)(struct file *, struct vm_area_struct *); + int (*mremap)(struct file *, struct vm_area_struct *); int (*open) (struct inode *, struct file *); int (*flush) (struct file *, fl_owner_t id); int (*release) (struct inode *, struct file *); diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h index bf3fe719c7ce..47b9ebd4a74f 100644 --- a/include/linux/irq_work.h +++ b/include/linux/irq_work.h @@ -38,16 +38,17 @@ bool irq_work_queue(struct irq_work *work); bool irq_work_queue_on(struct irq_work *work, int cpu); #endif -void irq_work_run(void); void irq_work_tick(void); void irq_work_sync(struct irq_work *work); #ifdef CONFIG_IRQ_WORK #include <asm/irq_work.h> +void irq_work_run(void); bool irq_work_needs_cpu(void); #else static inline bool irq_work_needs_cpu(void) { return false; } +static inline void irq_work_run(void) { } #endif #endif /* _LINUX_IRQ_WORK_H */ diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 98f923b6a0ea..f4de473f226b 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -45,6 +45,12 @@ * same as using STATIC_KEY_INIT_FALSE. */ +#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_JUMP_LABEL) +# define HAVE_JUMP_LABEL +#endif + +#ifndef __ASSEMBLY__ + #include <linux/types.h> #include <linux/compiler.h> #include <linux/bug.h> @@ -55,7 +61,7 @@ extern bool static_key_initialized; "%s used before call to jump_label_init", \ __func__) -#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_JUMP_LABEL) +#ifdef HAVE_JUMP_LABEL struct static_key { atomic_t enabled; @@ -66,13 +72,18 @@ struct static_key { #endif }; -# include <asm/jump_label.h> -# define HAVE_JUMP_LABEL #else struct static_key { atomic_t enabled; }; -#endif /* CC_HAVE_ASM_GOTO && CONFIG_JUMP_LABEL */ +#endif /* HAVE_JUMP_LABEL */ +#endif /* __ASSEMBLY__ */ + +#ifdef HAVE_JUMP_LABEL +#include <asm/jump_label.h> +#endif + +#ifndef __ASSEMBLY__ enum jump_label_type { JUMP_LABEL_DISABLE = 0, @@ -203,3 +214,5 @@ static inline bool static_key_enabled(struct static_key *key) } #endif /* _LINUX_JUMP_LABEL_H */ + +#endif /* __ASSEMBLY__ */ diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index d12b2104d19b..82af5d0b996e 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -165,12 +165,12 @@ enum kvm_bus { KVM_NR_BUSES }; -int kvm_io_bus_write(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, +int kvm_io_bus_write(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, int len, const void *val); -int kvm_io_bus_write_cookie(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, - int len, const void *val, long cookie); -int kvm_io_bus_read(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, int len, - void *val); +int kvm_io_bus_write_cookie(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, + gpa_t addr, int len, const void *val, long cookie); +int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, + int len, void *val); int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, int len, struct kvm_io_device *dev); int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, @@ -658,7 +658,6 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu); int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu); void *kvm_kvzalloc(unsigned long size); -void kvm_kvfree(const void *addr); #ifndef __KVM_HAVE_ARCH_VM_ALLOC static inline struct kvm *kvm_arch_alloc_vm(void) @@ -700,6 +699,20 @@ static inline wait_queue_head_t *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu) #endif } +#ifdef __KVM_HAVE_ARCH_INTC_INITIALIZED +/* + * returns true if the virtual interrupt controller is initialized and + * ready to accept virtual IRQ. On some architectures the virtual interrupt + * controller is dynamically instantiated and this is not always true. + */ +bool kvm_arch_intc_initialized(struct kvm *kvm); +#else +static inline bool kvm_arch_intc_initialized(struct kvm *kvm) +{ + return true; +} +#endif + int kvm_arch_init_vm(struct kvm *kvm, unsigned long type); void kvm_arch_destroy_vm(struct kvm *kvm); void kvm_arch_sync_events(struct kvm *kvm); @@ -969,11 +982,16 @@ static inline int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) #endif /* CONFIG_HAVE_KVM_EVENTFD */ #ifdef CONFIG_KVM_APIC_ARCHITECTURE -static inline bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu) +static inline bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu) { return vcpu->kvm->bsp_vcpu_id == vcpu->vcpu_id; } +static inline bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu) +{ + return (vcpu->arch.apic_base & MSR_IA32_APICBASE_BSP) != 0; +} + bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu); #else diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index f279d9c158cd..2782df47101e 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -474,16 +474,15 @@ struct zone { unsigned long wait_table_bits; ZONE_PADDING(_pad1_) - - /* Write-intensive fields used from the page allocator */ - spinlock_t lock; - /* free areas of different sizes */ struct free_area free_area[MAX_ORDER]; /* zone flags, see below */ unsigned long flags; + /* Write-intensive fields used from the page allocator */ + spinlock_t lock; + ZONE_PADDING(_pad2_) /* Write-intensive fields used by page reclaim */ diff --git a/include/linux/rtc.h b/include/linux/rtc.h index dcad7ee0d746..8dcf6825fa88 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -77,6 +77,7 @@ struct rtc_class_ops { int (*read_alarm)(struct device *, struct rtc_wkalrm *); int (*set_alarm)(struct device *, struct rtc_wkalrm *); int (*proc)(struct device *, struct seq_file *); + int (*set_mmss64)(struct device *, time64_t secs); int (*set_mmss)(struct device *, unsigned long secs); int (*read_callback)(struct device *, int data); int (*alarm_irq_enable)(struct device *, unsigned int enabled); diff --git a/include/linux/sched.h b/include/linux/sched.h index a419b65770d6..3f3308824fa4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -176,6 +176,14 @@ extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load); extern void calc_global_load(unsigned long ticks); extern void update_cpu_load_nohz(void); +/* Notifier for when a task gets migrated to a new CPU */ +struct task_migration_notifier { + struct task_struct *task; + int from_cpu; + int to_cpu; +}; +extern void register_task_migration_notifier(struct notifier_block *n); + extern unsigned long get_parent_ip(unsigned long addr); extern void dump_cpu_task(int cpu); @@ -1115,15 +1123,28 @@ struct load_weight { }; struct sched_avg { + u64 last_runnable_update; + s64 decay_count; + /* + * utilization_avg_contrib describes the amount of time that a + * sched_entity is running on a CPU. It is based on running_avg_sum + * and is scaled in the range [0..SCHED_LOAD_SCALE]. + * load_avg_contrib described the amount of time that a sched_entity + * is runnable on a rq. It is based on both runnable_avg_sum and the + * weight of the task. + */ + unsigned long load_avg_contrib, utilization_avg_contrib; /* * These sums represent an infinite geometric series and so are bound * above by 1024/(1-y). Thus we only need a u32 to store them for all * choices of y < 1-2^(-32)*1024. + * running_avg_sum reflects the time that the sched_entity is + * effectively running on the CPU. + * runnable_avg_sum represents the amount of time a sched_entity is on + * a runqueue which includes the running time that is monitored by + * running_avg_sum. */ - u32 runnable_avg_sum, runnable_avg_period; - u64 last_runnable_update; - s64 decay_count; - unsigned long load_avg_contrib; + u32 runnable_avg_sum, avg_period, running_avg_sum; }; #ifdef CONFIG_SCHEDSTATS diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index f5df8f687b4d..5f68d0a391ce 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -108,7 +108,7 @@ static inline unsigned __read_seqcount_begin(const seqcount_t *s) unsigned ret; repeat: - ret = ACCESS_ONCE(s->sequence); + ret = READ_ONCE(s->sequence); if (unlikely(ret & 1)) { cpu_relax(); goto repeat; @@ -127,7 +127,7 @@ repeat: */ static inline unsigned raw_read_seqcount(const seqcount_t *s) { - unsigned ret = ACCESS_ONCE(s->sequence); + unsigned ret = READ_ONCE(s->sequence); smp_rmb(); return ret; } @@ -179,7 +179,7 @@ static inline unsigned read_seqcount_begin(const seqcount_t *s) */ static inline unsigned raw_seqcount_begin(const seqcount_t *s) { - unsigned ret = ACCESS_ONCE(s->sequence); + unsigned ret = READ_ONCE(s->sequence); smp_rmb(); return ret & ~1; } diff --git a/include/linux/tick.h b/include/linux/tick.h index 9c085dc12ae9..f8492da57ad3 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -1,7 +1,5 @@ -/* linux/include/linux/tick.h - * - * This file contains the structure definitions for tick related functions - * +/* + * Tick related global functions */ #ifndef _LINUX_TICK_H #define _LINUX_TICK_H @@ -9,149 +7,99 @@ #include <linux/clockchips.h> #include <linux/irqflags.h> #include <linux/percpu.h> -#include <linux/hrtimer.h> #include <linux/context_tracking_state.h> #include <linux/cpumask.h> #include <linux/sched.h> #ifdef CONFIG_GENERIC_CLOCKEVENTS - -enum tick_device_mode { - TICKDEV_MODE_PERIODIC, - TICKDEV_MODE_ONESHOT, -}; - -struct tick_device { - struct clock_event_device *evtdev; - enum tick_device_mode mode; -}; - -enum tick_nohz_mode { - NOHZ_MODE_INACTIVE, - NOHZ_MODE_LOWRES, - NOHZ_MODE_HIGHRES, -}; - -/** - * struct tick_sched - sched tick emulation and no idle tick control/stats - * @sched_timer: hrtimer to schedule the periodic tick in high - * resolution mode - * @last_tick: Store the last tick expiry time when the tick - * timer is modified for nohz sleeps. This is necessary - * to resume the tick timer operation in the timeline - * when the CPU returns from nohz sleep. - * @tick_stopped: Indicator that the idle tick has been stopped - * @idle_jiffies: jiffies at the entry to idle for idle time accounting - * @idle_calls: Total number of idle calls - * @idle_sleeps: Number of idle calls, where the sched tick was stopped - * @idle_entrytime: Time when the idle call was entered - * @idle_waketime: Time when the idle was interrupted - * @idle_exittime: Time when the idle state was left - * @idle_sleeptime: Sum of the time slept in idle with sched tick stopped - * @iowait_sleeptime: Sum of the time slept in idle with sched tick stopped, with IO outstanding - * @sleep_length: Duration of the current idle sleep - * @do_timer_lst: CPU was the last one doing do_timer before going idle - */ -struct tick_sched { - struct hrtimer sched_timer; - unsigned long check_clocks; - enum tick_nohz_mode nohz_mode; - ktime_t last_tick; - int inidle; - int tick_stopped; - unsigned long idle_jiffies; - unsigned long idle_calls; - unsigned long idle_sleeps; - int idle_active; - ktime_t idle_entrytime; - ktime_t idle_waketime; - ktime_t idle_exittime; - ktime_t idle_sleeptime; - ktime_t iowait_sleeptime; - ktime_t sleep_length; - unsigned long last_jiffies; - unsigned long next_jiffies; - ktime_t idle_expires; - int do_timer_last; -}; - extern void __init tick_init(void); -extern int tick_is_oneshot_available(void); -extern struct tick_device *tick_get_device(int cpu); - extern void tick_freeze(void); extern void tick_unfreeze(void); +/* Should be core only, but ARM BL switcher requires it */ +extern void tick_suspend_local(void); +/* Should be core only, but XEN resume magic and ARM BL switcher require it */ +extern void tick_resume_local(void); +extern void tick_handover_do_timer(void); +extern void tick_cleanup_dead_cpu(int cpu); +#else /* CONFIG_GENERIC_CLOCKEVENTS */ +static inline void tick_init(void) { } +static inline void tick_freeze(void) { } +static inline void tick_unfreeze(void) { } +static inline void tick_suspend_local(void) { } +static inline void tick_resume_local(void) { } +static inline void tick_handover_do_timer(void) { } +static inline void tick_cleanup_dead_cpu(int cpu) { } +#endif /* !CONFIG_GENERIC_CLOCKEVENTS */ -# ifdef CONFIG_HIGH_RES_TIMERS -extern int tick_init_highres(void); -extern int tick_program_event(ktime_t expires, int force); -extern void tick_setup_sched_timer(void); -# endif - -# if defined CONFIG_NO_HZ_COMMON || defined CONFIG_HIGH_RES_TIMERS -extern void tick_cancel_sched_timer(int cpu); -# else -static inline void tick_cancel_sched_timer(int cpu) { } -# endif - -# ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST -extern struct tick_device *tick_get_broadcast_device(void); -extern struct cpumask *tick_get_broadcast_mask(void); - -# ifdef CONFIG_TICK_ONESHOT -extern struct cpumask *tick_get_broadcast_oneshot_mask(void); -# endif - -# endif /* BROADCAST */ - -# ifdef CONFIG_TICK_ONESHOT -extern void tick_clock_notify(void); -extern int tick_check_oneshot_change(int allow_nohz); -extern struct tick_sched *tick_get_tick_sched(int cpu); +#ifdef CONFIG_TICK_ONESHOT extern void tick_irq_enter(void); -extern int tick_oneshot_mode_active(void); # ifndef arch_needs_cpu # define arch_needs_cpu() (0) # endif # else -static inline void tick_clock_notify(void) { } -static inline int tick_check_oneshot_change(int allow_nohz) { return 0; } static inline void tick_irq_enter(void) { } -static inline int tick_oneshot_mode_active(void) { return 0; } -# endif +#endif -#else /* CONFIG_GENERIC_CLOCKEVENTS */ -static inline void tick_init(void) { } -static inline void tick_freeze(void) { } -static inline void tick_unfreeze(void) { } -static inline void tick_cancel_sched_timer(int cpu) { } -static inline void tick_clock_notify(void) { } -static inline int tick_check_oneshot_change(int allow_nohz) { return 0; } -static inline void tick_irq_enter(void) { } -static inline int tick_oneshot_mode_active(void) { return 0; } -#endif /* !CONFIG_GENERIC_CLOCKEVENTS */ +#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT) +extern void hotplug_cpu__broadcast_tick_pull(int dead_cpu); +#else +static inline void hotplug_cpu__broadcast_tick_pull(int dead_cpu) { } +#endif -# ifdef CONFIG_NO_HZ_COMMON -DECLARE_PER_CPU(struct tick_sched, tick_cpu_sched); +enum tick_broadcast_mode { + TICK_BROADCAST_OFF, + TICK_BROADCAST_ON, + TICK_BROADCAST_FORCE, +}; + +enum tick_broadcast_state { + TICK_BROADCAST_EXIT, + TICK_BROADCAST_ENTER, +}; + +#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST +extern void tick_broadcast_control(enum tick_broadcast_mode mode); +#else +static inline void tick_broadcast_control(enum tick_broadcast_mode mode) { } +#endif /* BROADCAST */ + +#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT) +extern int tick_broadcast_oneshot_control(enum tick_broadcast_state state); +#else +static inline int tick_broadcast_oneshot_control(enum tick_broadcast_state state) { return 0; } +#endif -static inline int tick_nohz_tick_stopped(void) +static inline void tick_broadcast_enable(void) +{ + tick_broadcast_control(TICK_BROADCAST_ON); +} +static inline void tick_broadcast_disable(void) +{ + tick_broadcast_control(TICK_BROADCAST_OFF); +} +static inline void tick_broadcast_force(void) +{ + tick_broadcast_control(TICK_BROADCAST_FORCE); +} +static inline int tick_broadcast_enter(void) { - return __this_cpu_read(tick_cpu_sched.tick_stopped); + return tick_broadcast_oneshot_control(TICK_BROADCAST_ENTER); +} +static inline void tick_broadcast_exit(void) +{ + tick_broadcast_oneshot_control(TICK_BROADCAST_EXIT); } +#ifdef CONFIG_NO_HZ_COMMON +extern int tick_nohz_tick_stopped(void); extern void tick_nohz_idle_enter(void); extern void tick_nohz_idle_exit(void); extern void tick_nohz_irq_exit(void); extern ktime_t tick_nohz_get_sleep_length(void); extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time); extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time); - -# else /* !CONFIG_NO_HZ_COMMON */ -static inline int tick_nohz_tick_stopped(void) -{ - return 0; -} - +#else /* !CONFIG_NO_HZ_COMMON */ +static inline int tick_nohz_tick_stopped(void) { return 0; } static inline void tick_nohz_idle_enter(void) { } static inline void tick_nohz_idle_exit(void) { } @@ -163,7 +111,7 @@ static inline ktime_t tick_nohz_get_sleep_length(void) } static inline u64 get_cpu_idle_time_us(int cpu, u64 *unused) { return -1; } static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; } -# endif /* !CONFIG_NO_HZ_COMMON */ +#endif /* !CONFIG_NO_HZ_COMMON */ #ifdef CONFIG_NO_HZ_FULL extern bool tick_nohz_full_running; diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index 05af9a334893..fb86963859c7 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -16,16 +16,16 @@ * @read: Read function of @clock * @mask: Bitmask for two's complement subtraction of non 64bit clocks * @cycle_last: @clock cycle value at last update - * @mult: NTP adjusted multiplier for scaled math conversion + * @mult: (NTP adjusted) multiplier for scaled math conversion * @shift: Shift value for scaled math conversion * @xtime_nsec: Shifted (fractional) nano seconds offset for readout - * @base_mono: ktime_t (nanoseconds) base time for readout + * @base: ktime_t (nanoseconds) base time for readout * * This struct has size 56 byte on 64 bit. Together with a seqcount it * occupies a single 64byte cache line. * * The struct is separate from struct timekeeper as it is also used - * for a fast NMI safe accessor to clock monotonic. + * for a fast NMI safe accessors. */ struct tk_read_base { struct clocksource *clock; @@ -35,12 +35,13 @@ struct tk_read_base { u32 mult; u32 shift; u64 xtime_nsec; - ktime_t base_mono; + ktime_t base; }; /** * struct timekeeper - Structure holding internal timekeeping values. - * @tkr: The readout base structure + * @tkr_mono: The readout base structure for CLOCK_MONOTONIC + * @tkr_raw: The readout base structure for CLOCK_MONOTONIC_RAW * @xtime_sec: Current CLOCK_REALTIME time in seconds * @ktime_sec: Current CLOCK_MONOTONIC time in seconds * @wall_to_monotonic: CLOCK_REALTIME to CLOCK_MONOTONIC offset @@ -48,7 +49,6 @@ struct tk_read_base { * @offs_boot: Offset clock monotonic -> clock boottime * @offs_tai: Offset clock monotonic -> clock tai * @tai_offset: The current UTC to TAI offset in seconds - * @base_raw: Monotonic raw base time in ktime_t format * @raw_time: Monotonic raw base time in timespec64 format * @cycle_interval: Number of clock cycles in one NTP interval * @xtime_interval: Number of clock shifted nano seconds in one NTP @@ -76,7 +76,8 @@ struct tk_read_base { * used instead. */ struct timekeeper { - struct tk_read_base tkr; + struct tk_read_base tkr_mono; + struct tk_read_base tkr_raw; u64 xtime_sec; unsigned long ktime_sec; struct timespec64 wall_to_monotonic; @@ -84,7 +85,6 @@ struct timekeeper { ktime_t offs_boot; ktime_t offs_tai; s32 tai_offset; - ktime_t base_raw; struct timespec64 raw_time; /* The following members are for timekeeping internal use */ diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 3eaae4754275..99176af216af 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -214,12 +214,18 @@ static inline u64 ktime_get_boot_ns(void) return ktime_to_ns(ktime_get_boottime()); } +static inline u64 ktime_get_tai_ns(void) +{ + return ktime_to_ns(ktime_get_clocktai()); +} + static inline u64 ktime_get_raw_ns(void) { return ktime_to_ns(ktime_get_raw()); } extern u64 ktime_get_mono_fast_ns(void); +extern u64 ktime_get_raw_fast_ns(void); /* * Timespec interfaces utilizing the ktime based ones @@ -242,6 +248,9 @@ static inline void timekeeping_clocktai(struct timespec *ts) /* * RTC specific */ +extern bool timekeeping_rtc_skipsuspend(void); +extern bool timekeeping_rtc_skipresume(void); + extern void timekeeping_inject_sleeptime64(struct timespec64 *delta); /* @@ -253,17 +262,14 @@ extern void getnstime_raw_and_real(struct timespec *ts_raw, /* * Persistent clock related interfaces */ -extern bool persistent_clock_exist; extern int persistent_clock_is_local; -static inline bool has_persistent_clock(void) -{ - return persistent_clock_exist; -} - extern void read_persistent_clock(struct timespec *ts); +extern void read_persistent_clock64(struct timespec64 *ts); extern void read_boot_clock(struct timespec *ts); +extern void read_boot_clock64(struct timespec64 *ts); extern int update_persistent_clock(struct timespec now); +extern int update_persistent_clock64(struct timespec64 now); #endif diff --git a/include/media/atmel-isi.h b/include/media/atmel-isi.h index c2e570336269..6008b0985b7b 100644 --- a/include/media/atmel-isi.h +++ b/include/media/atmel-isi.h @@ -59,6 +59,10 @@ #define ISI_CFG1_FRATE_DIV_MASK (7 << 8) #define ISI_CFG1_DISCR (1 << 11) #define ISI_CFG1_FULL_MODE (1 << 12) +/* Definition for THMASK(ISI_V2) */ +#define ISI_CFG1_THMASK_BEATS_4 (0 << 13) +#define ISI_CFG1_THMASK_BEATS_8 (1 << 13) +#define ISI_CFG1_THMASK_BEATS_16 (2 << 13) /* Bitfields in CFG2 */ #define ISI_CFG2_GRAYSCALE (1 << 13) diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 805570650062..f574d7be7631 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -147,6 +147,16 @@ struct kvm_pit_config { #define KVM_PIT_SPEAKER_DUMMY 1 +struct kvm_s390_skeys { + __u64 start_gfn; + __u64 count; + __u64 skeydata_addr; + __u32 flags; + __u32 reserved[9]; +}; +#define KVM_S390_GET_SKEYS_NONE 1 +#define KVM_S390_SKEYS_MAX 1048576 + #define KVM_EXIT_UNKNOWN 0 #define KVM_EXIT_EXCEPTION 1 #define KVM_EXIT_IO 2 @@ -172,6 +182,7 @@ struct kvm_pit_config { #define KVM_EXIT_S390_TSCH 22 #define KVM_EXIT_EPR 23 #define KVM_EXIT_SYSTEM_EVENT 24 +#define KVM_EXIT_S390_STSI 25 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -309,6 +320,15 @@ struct kvm_run { __u32 type; __u64 flags; } system_event; + /* KVM_EXIT_S390_STSI */ + struct { + __u64 addr; + __u8 ar; + __u8 reserved; + __u8 fc; + __u8 sel1; + __u16 sel2; + } s390_stsi; /* Fix the size of the union. */ char padding[256]; }; @@ -324,7 +344,7 @@ struct kvm_run { __u64 kvm_dirty_regs; union { struct kvm_sync_regs regs; - char padding[1024]; + char padding[2048]; } s; }; @@ -365,6 +385,24 @@ struct kvm_translation { __u8 pad[5]; }; +/* for KVM_S390_MEM_OP */ +struct kvm_s390_mem_op { + /* in */ + __u64 gaddr; /* the guest address */ + __u64 flags; /* flags */ + __u32 size; /* amount of bytes */ + __u32 op; /* type of operation */ + __u64 buf; /* buffer in userspace */ + __u8 ar; /* the access register number */ + __u8 reserved[31]; /* should be set to 0 */ +}; +/* types for kvm_s390_mem_op->op */ +#define KVM_S390_MEMOP_LOGICAL_READ 0 +#define KVM_S390_MEMOP_LOGICAL_WRITE 1 +/* flags for kvm_s390_mem_op->flags */ +#define KVM_S390_MEMOP_F_CHECK_ONLY (1ULL << 0) +#define KVM_S390_MEMOP_F_INJECT_EXCEPTION (1ULL << 1) + /* for KVM_INTERRUPT */ struct kvm_interrupt { /* in */ @@ -520,6 +558,13 @@ struct kvm_s390_irq { } u; }; +struct kvm_s390_irq_state { + __u64 buf; + __u32 flags; + __u32 len; + __u32 reserved[4]; +}; + /* for KVM_SET_GUEST_DEBUG */ #define KVM_GUESTDBG_ENABLE 0x00000001 @@ -760,6 +805,14 @@ struct kvm_ppc_smmu_info { #define KVM_CAP_PPC_ENABLE_HCALL 104 #define KVM_CAP_CHECK_EXTENSION_VM 105 #define KVM_CAP_S390_USER_SIGP 106 +#define KVM_CAP_S390_VECTOR_REGISTERS 107 +#define KVM_CAP_S390_MEM_OP 108 +#define KVM_CAP_S390_USER_STSI 109 +#define KVM_CAP_S390_SKEYS 110 +#define KVM_CAP_MIPS_FPU 111 +#define KVM_CAP_MIPS_MSA 112 +#define KVM_CAP_S390_INJECT_IRQ 113 +#define KVM_CAP_S390_IRQ_STATE 114 #ifdef KVM_CAP_IRQ_ROUTING @@ -1135,6 +1188,16 @@ struct kvm_s390_ucas_mapping { #define KVM_ARM_VCPU_INIT _IOW(KVMIO, 0xae, struct kvm_vcpu_init) #define KVM_ARM_PREFERRED_TARGET _IOR(KVMIO, 0xaf, struct kvm_vcpu_init) #define KVM_GET_REG_LIST _IOWR(KVMIO, 0xb0, struct kvm_reg_list) +/* Available with KVM_CAP_S390_MEM_OP */ +#define KVM_S390_MEM_OP _IOW(KVMIO, 0xb1, struct kvm_s390_mem_op) +/* Available with KVM_CAP_S390_SKEYS */ +#define KVM_S390_GET_SKEYS _IOW(KVMIO, 0xb2, struct kvm_s390_skeys) +#define KVM_S390_SET_SKEYS _IOW(KVMIO, 0xb3, struct kvm_s390_skeys) +/* Available with KVM_CAP_S390_INJECT_IRQ */ +#define KVM_S390_IRQ _IOW(KVMIO, 0xb4, struct kvm_s390_irq) +/* Available with KVM_CAP_S390_IRQ_STATE */ +#define KVM_S390_SET_IRQ_STATE _IOW(KVMIO, 0xb5, struct kvm_s390_irq_state) +#define KVM_S390_GET_IRQ_STATE _IOW(KVMIO, 0xb6, struct kvm_s390_irq_state) #define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) #define KVM_DEV_ASSIGN_PCI_2_3 (1 << 1) diff --git a/kernel/cpu.c b/kernel/cpu.c index 1972b161c61e..82eea9c5af61 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -20,6 +20,7 @@ #include <linux/gfp.h> #include <linux/suspend.h> #include <linux/lockdep.h> +#include <linux/tick.h> #include <trace/events/power.h> #include "smpboot.h" @@ -338,6 +339,8 @@ static int __ref take_cpu_down(void *_param) return err; cpu_notify(CPU_DYING | param->mod, param->hcpu); + /* Give up timekeeping duties */ + tick_handover_do_timer(); /* Park the stopper thread */ kthread_park(current); return 0; @@ -411,10 +414,12 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) while (!idle_cpu(cpu)) cpu_relax(); + hotplug_cpu__broadcast_tick_pull(cpu); /* This actually kills the CPU. */ __cpu_die(cpu); /* CPU is completely dead: tell everyone. Too late to complain. */ + tick_cleanup_dead_cpu(cpu); cpu_notify_nofail(CPU_DEAD | mod, hcpu); check_for_tasks(cpu); diff --git a/kernel/futex.c b/kernel/futex.c index 2a5e3830e953..2579e407ff67 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -900,7 +900,7 @@ static int attach_to_pi_owner(u32 uval, union futex_key *key, if (!p) return -ESRCH; - if (!p->mm) { + if (unlikely(p->flags & PF_KTHREAD)) { put_task_struct(p); return -EPERM; } diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h index d1fe2ba5bac9..75e114bdf3f2 100644 --- a/kernel/locking/mcs_spinlock.h +++ b/kernel/locking/mcs_spinlock.h @@ -78,7 +78,7 @@ void mcs_spin_lock(struct mcs_spinlock **lock, struct mcs_spinlock *node) */ return; } - ACCESS_ONCE(prev->next) = node; + WRITE_ONCE(prev->next, node); /* Wait until the lock holder passes the lock down. */ arch_mcs_spin_lock_contended(&node->locked); @@ -91,7 +91,7 @@ void mcs_spin_lock(struct mcs_spinlock **lock, struct mcs_spinlock *node) static inline void mcs_spin_unlock(struct mcs_spinlock **lock, struct mcs_spinlock *node) { - struct mcs_spinlock *next = ACCESS_ONCE(node->next); + struct mcs_spinlock *next = READ_ONCE(node->next); if (likely(!next)) { /* @@ -100,7 +100,7 @@ void mcs_spin_unlock(struct mcs_spinlock **lock, struct mcs_spinlock *node) if (likely(cmpxchg(lock, node, NULL) == node)) return; /* Wait until the next pointer is set */ - while (!(next = ACCESS_ONCE(node->next))) + while (!(next = READ_ONCE(node->next))) cpu_relax_lowlatency(); } diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index 94674e5919cb..4cccea6b8934 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -25,7 +25,7 @@ #include <linux/spinlock.h> #include <linux/interrupt.h> #include <linux/debug_locks.h> -#include "mcs_spinlock.h" +#include <linux/osq_lock.h> /* * In the DEBUG case we are using the "NULL fastpath" for mutexes, @@ -217,44 +217,35 @@ ww_mutex_set_context_slowpath(struct ww_mutex *lock, } #ifdef CONFIG_MUTEX_SPIN_ON_OWNER -static inline bool owner_running(struct mutex *lock, struct task_struct *owner) -{ - if (lock->owner != owner) - return false; - - /* - * Ensure we emit the owner->on_cpu, dereference _after_ checking - * lock->owner still matches owner, if that fails, owner might - * point to free()d memory, if it still matches, the rcu_read_lock() - * ensures the memory stays valid. - */ - barrier(); - - return owner->on_cpu; -} - /* * Look out! "owner" is an entirely speculative pointer * access and not reliable. */ static noinline -int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner) +bool mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner) { + bool ret = true; + rcu_read_lock(); - while (owner_running(lock, owner)) { - if (need_resched()) + while (lock->owner == owner) { + /* + * Ensure we emit the owner->on_cpu, dereference _after_ + * checking lock->owner still matches owner. If that fails, + * owner might point to freed memory. If it still matches, + * the rcu_read_lock() ensures the memory stays valid. + */ + barrier(); + + if (!owner->on_cpu || need_resched()) { + ret = false; break; + } cpu_relax_lowlatency(); } rcu_read_unlock(); - /* - * We break out the loop above on need_resched() and when the - * owner changed, which is a sign for heavy contention. Return - * success only when lock->owner is NULL. - */ - return lock->owner == NULL; + return ret; } /* @@ -269,7 +260,7 @@ static inline int mutex_can_spin_on_owner(struct mutex *lock) return 0; rcu_read_lock(); - owner = ACCESS_ONCE(lock->owner); + owner = READ_ONCE(lock->owner); if (owner) retval = owner->on_cpu; rcu_read_unlock(); @@ -343,7 +334,7 @@ static bool mutex_optimistic_spin(struct mutex *lock, * As such, when deadlock detection needs to be * performed the optimistic spinning cannot be done. */ - if (ACCESS_ONCE(ww->ctx)) + if (READ_ONCE(ww->ctx)) break; } @@ -351,7 +342,7 @@ static bool mutex_optimistic_spin(struct mutex *lock, * If there's an owner, wait for it to either * release the lock or go to sleep. */ - owner = ACCESS_ONCE(lock->owner); + owner = READ_ONCE(lock->owner); if (owner && !mutex_spin_on_owner(lock, owner)) break; @@ -490,7 +481,7 @@ static inline int __sched __ww_mutex_lock_check_stamp(struct mutex *lock, struct ww_acquire_ctx *ctx) { struct ww_mutex *ww = container_of(lock, struct ww_mutex, base); - struct ww_acquire_ctx *hold_ctx = ACCESS_ONCE(ww->ctx); + struct ww_acquire_ctx *hold_ctx = READ_ONCE(ww->ctx); if (!hold_ctx) return 0; diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c index c112d00341b0..dc85ee23a26f 100644 --- a/kernel/locking/osq_lock.c +++ b/kernel/locking/osq_lock.c @@ -98,7 +98,7 @@ bool osq_lock(struct optimistic_spin_queue *lock) prev = decode_cpu(old); node->prev = prev; - ACCESS_ONCE(prev->next) = node; + WRITE_ONCE(prev->next, node); /* * Normally @prev is untouchable after the above store; because at that @@ -109,7 +109,7 @@ bool osq_lock(struct optimistic_spin_queue *lock) * cmpxchg in an attempt to undo our queueing. */ - while (!ACCESS_ONCE(node->locked)) { + while (!READ_ONCE(node->locked)) { /* * If we need to reschedule bail... so we can block. */ @@ -148,7 +148,7 @@ unqueue: * Or we race against a concurrent unqueue()'s step-B, in which * case its step-C will write us a new @node->prev pointer. */ - prev = ACCESS_ONCE(node->prev); + prev = READ_ONCE(node->prev); } /* @@ -170,8 +170,8 @@ unqueue: * it will wait in Step-A. */ - ACCESS_ONCE(next->prev) = prev; - ACCESS_ONCE(prev->next) = next; + WRITE_ONCE(next->prev, prev); + WRITE_ONCE(prev->next, next); return false; } @@ -193,11 +193,11 @@ void osq_unlock(struct optimistic_spin_queue *lock) node = this_cpu_ptr(&osq_node); next = xchg(&node->next, NULL); if (next) { - ACCESS_ONCE(next->locked) = 1; + WRITE_ONCE(next->locked, 1); return; } next = osq_wait_next(lock, node, NULL); if (next) - ACCESS_ONCE(next->locked) = 1; + WRITE_ONCE(next->locked, 1); } diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 6357265a31ad..b73279367087 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -349,7 +349,7 @@ static inline struct rt_mutex *task_blocked_on_lock(struct task_struct *p) * * @task: the task owning the mutex (owner) for which a chain walk is * probably needed - * @deadlock_detect: do we have to carry out deadlock detection? + * @chwalk: do we have to carry out deadlock detection? * @orig_lock: the mutex (can be NULL if we are walking the chain to recheck * things for a task that has just got its priority adjusted, and * is waiting on a mutex) diff --git a/kernel/locking/rwsem-spinlock.c b/kernel/locking/rwsem-spinlock.c index 2555ae15ec14..3a5048572065 100644 --- a/kernel/locking/rwsem-spinlock.c +++ b/kernel/locking/rwsem-spinlock.c @@ -85,6 +85,13 @@ __rwsem_do_wake(struct rw_semaphore *sem, int wakewrite) list_del(&waiter->list); tsk = waiter->task; + /* + * Make sure we do not wakeup the next reader before + * setting the nil condition to grant the next reader; + * otherwise we could miss the wakeup on the other + * side and end up sleeping again. See the pairing + * in rwsem_down_read_failed(). + */ smp_mb(); waiter->task = NULL; wake_up_process(tsk); diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c index 2f7cc4076f50..3417d0172a5d 100644 --- a/kernel/locking/rwsem-xadd.c +++ b/kernel/locking/rwsem-xadd.c @@ -14,8 +14,9 @@ #include <linux/init.h> #include <linux/export.h> #include <linux/sched/rt.h> +#include <linux/osq_lock.h> -#include "mcs_spinlock.h" +#include "rwsem.h" /* * Guide to the rw_semaphore's count field for common values. @@ -186,6 +187,13 @@ __rwsem_do_wake(struct rw_semaphore *sem, enum rwsem_wake_type wake_type) waiter = list_entry(next, struct rwsem_waiter, list); next = waiter->list.next; tsk = waiter->task; + /* + * Make sure we do not wakeup the next reader before + * setting the nil condition to grant the next reader; + * otherwise we could miss the wakeup on the other + * side and end up sleeping again. See the pairing + * in rwsem_down_read_failed(). + */ smp_mb(); waiter->task = NULL; wake_up_process(tsk); @@ -258,6 +266,7 @@ static inline bool rwsem_try_write_lock(long count, struct rw_semaphore *sem) RWSEM_ACTIVE_WRITE_BIAS) == RWSEM_WAITING_BIAS) { if (!list_is_singular(&sem->wait_list)) rwsem_atomic_update(RWSEM_WAITING_BIAS, sem); + rwsem_set_owner(sem); return true; } @@ -270,15 +279,17 @@ static inline bool rwsem_try_write_lock(long count, struct rw_semaphore *sem) */ static inline bool rwsem_try_write_lock_unqueued(struct rw_semaphore *sem) { - long old, count = ACCESS_ONCE(sem->count); + long old, count = READ_ONCE(sem->count); while (true) { if (!(count == 0 || count == RWSEM_WAITING_BIAS)) return false; old = cmpxchg(&sem->count, count, count + RWSEM_ACTIVE_WRITE_BIAS); - if (old == count) + if (old == count) { + rwsem_set_owner(sem); return true; + } count = old; } @@ -287,60 +298,67 @@ static inline bool rwsem_try_write_lock_unqueued(struct rw_semaphore *sem) static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem) { struct task_struct *owner; - bool on_cpu = false; + bool ret = true; if (need_resched()) return false; rcu_read_lock(); - owner = ACCESS_ONCE(sem->owner); - if (owner) - on_cpu = owner->on_cpu; - rcu_read_unlock(); - - /* - * If sem->owner is not set, yet we have just recently entered the - * slowpath, then there is a possibility reader(s) may have the lock. - * To be safe, avoid spinning in these situations. - */ - return on_cpu; -} - -static inline bool owner_running(struct rw_semaphore *sem, - struct task_struct *owner) -{ - if (sem->owner != owner) - return false; - - /* - * Ensure we emit the owner->on_cpu, dereference _after_ checking - * sem->owner still matches owner, if that fails, owner might - * point to free()d memory, if it still matches, the rcu_read_lock() - * ensures the memory stays valid. - */ - barrier(); + owner = READ_ONCE(sem->owner); + if (!owner) { + long count = READ_ONCE(sem->count); + /* + * If sem->owner is not set, yet we have just recently entered the + * slowpath with the lock being active, then there is a possibility + * reader(s) may have the lock. To be safe, bail spinning in these + * situations. + */ + if (count & RWSEM_ACTIVE_MASK) + ret = false; + goto done; + } - return owner->on_cpu; + ret = owner->on_cpu; +done: + rcu_read_unlock(); + return ret; } static noinline bool rwsem_spin_on_owner(struct rw_semaphore *sem, struct task_struct *owner) { + long count; + rcu_read_lock(); - while (owner_running(sem, owner)) { - if (need_resched()) - break; + while (sem->owner == owner) { + /* + * Ensure we emit the owner->on_cpu, dereference _after_ + * checking sem->owner still matches owner, if that fails, + * owner might point to free()d memory, if it still matches, + * the rcu_read_lock() ensures the memory stays valid. + */ + barrier(); + + /* abort spinning when need_resched or owner is not running */ + if (!owner->on_cpu || need_resched()) { + rcu_read_unlock(); + return false; + } cpu_relax_lowlatency(); } rcu_read_unlock(); + if (READ_ONCE(sem->owner)) + return true; /* new owner, continue spinning */ + /* - * We break out the loop above on need_resched() or when the - * owner changed, which is a sign for heavy contention. Return - * success only when sem->owner is NULL. + * When the owner is not set, the lock could be free or + * held by readers. Check the counter to verify the + * state. */ - return sem->owner == NULL; + count = READ_ONCE(sem->count); + return (count == 0 || count == RWSEM_WAITING_BIAS); } static bool rwsem_optimistic_spin(struct rw_semaphore *sem) @@ -358,7 +376,7 @@ static bool rwsem_optimistic_spin(struct rw_semaphore *sem) goto done; while (true) { - owner = ACCESS_ONCE(sem->owner); + owner = READ_ONCE(sem->owner); if (owner && !rwsem_spin_on_owner(sem, owner)) break; @@ -432,7 +450,7 @@ struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem) /* we're now waiting on the lock, but no longer actively locking */ if (waiting) { - count = ACCESS_ONCE(sem->count); + count = READ_ONCE(sem->count); /* * If there were already threads queued before us and there are diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index e2d3bc7f03b4..205be0ce34de 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -9,29 +9,9 @@ #include <linux/sched.h> #include <linux/export.h> #include <linux/rwsem.h> - #include <linux/atomic.h> -#ifdef CONFIG_RWSEM_SPIN_ON_OWNER -static inline void rwsem_set_owner(struct rw_semaphore *sem) -{ - sem->owner = current; -} - -static inline void rwsem_clear_owner(struct rw_semaphore *sem) -{ - sem->owner = NULL; -} - -#else -static inline void rwsem_set_owner(struct rw_semaphore *sem) -{ -} - -static inline void rwsem_clear_owner(struct rw_semaphore *sem) -{ -} -#endif +#include "rwsem.h" /* * lock for reading diff --git a/kernel/locking/rwsem.h b/kernel/locking/rwsem.h new file mode 100644 index 000000000000..870ed9a5b426 --- /dev/null +++ b/kernel/locking/rwsem.h @@ -0,0 +1,20 @@ +#ifdef CONFIG_RWSEM_SPIN_ON_OWNER +static inline void rwsem_set_owner(struct rw_semaphore *sem) +{ + sem->owner = current; +} + +static inline void rwsem_clear_owner(struct rw_semaphore *sem) +{ + sem->owner = NULL; +} + +#else +static inline void rwsem_set_owner(struct rw_semaphore *sem) +{ +} + +static inline void rwsem_clear_owner(struct rw_semaphore *sem) +{ +} +#endif diff --git a/kernel/module.c b/kernel/module.c index 99fdf94efce8..ec53f594e9c9 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -2479,6 +2479,23 @@ static int elf_header_check(struct load_info *info) return 0; } +#define COPY_CHUNK_SIZE (16*PAGE_SIZE) + +static int copy_chunked_from_user(void *dst, const void __user *usrc, unsigned long len) +{ + do { + unsigned long n = min(len, COPY_CHUNK_SIZE); + + if (copy_from_user(dst, usrc, n) != 0) + return -EFAULT; + cond_resched(); + dst += n; + usrc += n; + len -= n; + } while (len); + return 0; +} + /* Sets info->hdr and info->len. */ static int copy_module_from_user(const void __user *umod, unsigned long len, struct load_info *info) @@ -2498,7 +2515,7 @@ static int copy_module_from_user(const void __user *umod, unsigned long len, if (!info->hdr) return -ENOMEM; - if (copy_from_user(info->hdr, umod, info->len) != 0) { + if (copy_chunked_from_user(info->hdr, umod, info->len) != 0) { vfree(info->hdr); return -EFAULT; } diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index c24d5a23bf93..5235dd4e1e2f 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -955,25 +955,6 @@ static void mark_nosave_pages(struct memory_bitmap *bm) } } -static bool is_nosave_page(unsigned long pfn) -{ - struct nosave_region *region; - - list_for_each_entry(region, &nosave_regions, list) { - if (pfn >= region->start_pfn && pfn < region->end_pfn) { - pr_err("PM: %#010llx in e820 nosave region: " - "[mem %#010llx-%#010llx]\n", - (unsigned long long) pfn << PAGE_SHIFT, - (unsigned long long) region->start_pfn << PAGE_SHIFT, - ((unsigned long long) region->end_pfn << PAGE_SHIFT) - - 1); - return true; - } - } - - return false; -} - /** * create_basic_memory_bitmaps - create bitmaps needed for marking page * frames that should not be saved and free page frames. The pointers @@ -2042,7 +2023,7 @@ static int mark_unsafe_pages(struct memory_bitmap *bm) do { pfn = memory_bm_next_pfn(bm); if (likely(pfn != BM_END_OF_MAP)) { - if (likely(pfn_valid(pfn)) && !is_nosave_page(pfn)) + if (likely(pfn_valid(pfn))) swsusp_set_page_free(pfn_to_page(pfn)); else return -EFAULT; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 62671f53202a..261af7bfcb67 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -690,6 +690,23 @@ static inline bool got_nohz_idle_kick(void) bool sched_can_stop_tick(void) { /* + * FIFO realtime policy runs the highest priority task. Other runnable + * tasks are of a lower priority. The scheduler tick does nothing. + */ + if (current->policy == SCHED_FIFO) + return true; + + /* + * Round-robin realtime tasks time slice with other tasks at the same + * realtime priority. Is this task the only one at this priority? + */ + if (current->policy == SCHED_RR) { + struct sched_rt_entity *rt_se = ¤t->rt; + + return rt_se->run_list.prev == rt_se->run_list.next; + } + + /* * More than one running task need preemption. * nr_running update is assumed to be visible * after IPI is sent from wakers. @@ -996,6 +1013,13 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) rq_clock_skip_update(rq, true); } +static ATOMIC_NOTIFIER_HEAD(task_migration_notifier); + +void register_task_migration_notifier(struct notifier_block *n) +{ + atomic_notifier_chain_register(&task_migration_notifier, n); +} + #ifdef CONFIG_SMP void set_task_cpu(struct task_struct *p, unsigned int new_cpu) { @@ -1026,10 +1050,18 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) trace_sched_migrate_task(p, new_cpu); if (task_cpu(p) != new_cpu) { + struct task_migration_notifier tmn; + if (p->sched_class->migrate_task_rq) p->sched_class->migrate_task_rq(p, new_cpu); p->se.nr_migrations++; perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0); + + tmn.task = p; + tmn.from_cpu = task_cpu(p); + tmn.to_cpu = new_cpu; + + atomic_notifier_call_chain(&task_migration_notifier, 0, &tmn); } __set_task_cpu(p, new_cpu); @@ -5320,36 +5352,13 @@ static int sched_cpu_active(struct notifier_block *nfb, static int sched_cpu_inactive(struct notifier_block *nfb, unsigned long action, void *hcpu) { - unsigned long flags; - long cpu = (long)hcpu; - struct dl_bw *dl_b; - switch (action & ~CPU_TASKS_FROZEN) { case CPU_DOWN_PREPARE: - set_cpu_active(cpu, false); - - /* explicitly allow suspend */ - if (!(action & CPU_TASKS_FROZEN)) { - bool overflow; - int cpus; - - rcu_read_lock_sched(); - dl_b = dl_bw_of(cpu); - - raw_spin_lock_irqsave(&dl_b->lock, flags); - cpus = dl_bw_cpus(cpu); - overflow = __dl_overflow(dl_b, cpus, 0, 0); - raw_spin_unlock_irqrestore(&dl_b->lock, flags); - - rcu_read_unlock_sched(); - - if (overflow) - return notifier_from_errno(-EBUSY); - } + set_cpu_active((long)hcpu, false); return NOTIFY_OK; + default: + return NOTIFY_DONE; } - - return NOTIFY_DONE; } static int __init migration_init(void) @@ -5430,17 +5439,6 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, break; } - /* - * Even though we initialize ->capacity to something semi-sane, - * we leave capacity_orig unset. This allows us to detect if - * domain iteration is still funny without causing /0 traps. - */ - if (!group->sgc->capacity_orig) { - printk(KERN_CONT "\n"); - printk(KERN_ERR "ERROR: domain->cpu_capacity not set\n"); - break; - } - if (!cpumask_weight(sched_group_cpus(group))) { printk(KERN_CONT "\n"); printk(KERN_ERR "ERROR: empty group\n"); @@ -5924,7 +5922,6 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu) * die on a /0 trap. */ sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span); - sg->sgc->capacity_orig = sg->sgc->capacity; /* * Make sure the first group of this domain contains the @@ -6235,6 +6232,7 @@ sd_init(struct sched_domain_topology_level *tl, int cpu) */ if (sd->flags & SD_SHARE_CPUCAPACITY) { + sd->flags |= SD_PREFER_SIBLING; sd->imbalance_pct = 110; sd->smt_gain = 1178; /* ~15% */ @@ -7000,7 +6998,6 @@ static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action, */ case CPU_ONLINE: - case CPU_DOWN_FAILED: cpuset_update_active_cpus(true); break; default: @@ -7012,8 +7009,30 @@ static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action, static int cpuset_cpu_inactive(struct notifier_block *nfb, unsigned long action, void *hcpu) { - switch (action) { + unsigned long flags; + long cpu = (long)hcpu; + struct dl_bw *dl_b; + + switch (action & ~CPU_TASKS_FROZEN) { case CPU_DOWN_PREPARE: + /* explicitly allow suspend */ + if (!(action & CPU_TASKS_FROZEN)) { + bool overflow; + int cpus; + + rcu_read_lock_sched(); + dl_b = dl_bw_of(cpu); + + raw_spin_lock_irqsave(&dl_b->lock, flags); + cpus = dl_bw_cpus(cpu); + overflow = __dl_overflow(dl_b, cpus, 0, 0); + raw_spin_unlock_irqrestore(&dl_b->lock, flags); + + rcu_read_unlock_sched(); + + if (overflow) + return notifier_from_errno(-EBUSY); + } cpuset_update_active_cpus(false); break; case CPU_DOWN_PREPARE_FROZEN: @@ -7158,8 +7177,8 @@ void __init sched_init(void) rq->calc_load_active = 0; rq->calc_load_update = jiffies + LOAD_FREQ; init_cfs_rq(&rq->cfs); - init_rt_rq(&rq->rt, rq); - init_dl_rq(&rq->dl, rq); + init_rt_rq(&rq->rt); + init_dl_rq(&rq->dl); #ifdef CONFIG_FAIR_GROUP_SCHED root_task_group.shares = ROOT_TASK_GROUP_LOAD; INIT_LIST_HEAD(&rq->leaf_cfs_rq_list); @@ -7199,7 +7218,7 @@ void __init sched_init(void) #ifdef CONFIG_SMP rq->sd = NULL; rq->rd = NULL; - rq->cpu_capacity = SCHED_CAPACITY_SCALE; + rq->cpu_capacity = rq->cpu_capacity_orig = SCHED_CAPACITY_SCALE; rq->post_schedule = 0; rq->active_balance = 0; rq->next_balance = jiffies; @@ -7798,7 +7817,7 @@ static int sched_rt_global_constraints(void) } #endif /* CONFIG_RT_GROUP_SCHED */ -static int sched_dl_global_constraints(void) +static int sched_dl_global_validate(void) { u64 runtime = global_rt_runtime(); u64 period = global_rt_period(); @@ -7899,11 +7918,11 @@ int sched_rt_handler(struct ctl_table *table, int write, if (ret) goto undo; - ret = sched_rt_global_constraints(); + ret = sched_dl_global_validate(); if (ret) goto undo; - ret = sched_dl_global_constraints(); + ret = sched_rt_global_constraints(); if (ret) goto undo; diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 3fa8fa6d9403..5e95145088fd 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -69,7 +69,7 @@ void init_dl_bw(struct dl_bw *dl_b) dl_b->total_bw = 0; } -void init_dl_rq(struct dl_rq *dl_rq, struct rq *rq) +void init_dl_rq(struct dl_rq *dl_rq) { dl_rq->rb_root = RB_ROOT; @@ -218,6 +218,52 @@ static inline void set_post_schedule(struct rq *rq) rq->post_schedule = has_pushable_dl_tasks(rq); } +static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq); + +static void dl_task_offline_migration(struct rq *rq, struct task_struct *p) +{ + struct rq *later_rq = NULL; + bool fallback = false; + + later_rq = find_lock_later_rq(p, rq); + + if (!later_rq) { + int cpu; + + /* + * If we cannot preempt any rq, fall back to pick any + * online cpu. + */ + fallback = true; + cpu = cpumask_any_and(cpu_active_mask, tsk_cpus_allowed(p)); + if (cpu >= nr_cpu_ids) { + /* + * Fail to find any suitable cpu. + * The task will never come back! + */ + BUG_ON(dl_bandwidth_enabled()); + + /* + * If admission control is disabled we + * try a little harder to let the task + * run. + */ + cpu = cpumask_any(cpu_active_mask); + } + later_rq = cpu_rq(cpu); + double_lock_balance(rq, later_rq); + } + + deactivate_task(rq, p, 0); + set_task_cpu(p, later_rq->cpu); + activate_task(later_rq, p, ENQUEUE_REPLENISH); + + if (!fallback) + resched_curr(later_rq); + + double_unlock_balance(rq, later_rq); +} + #else static inline @@ -514,7 +560,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) unsigned long flags; struct rq *rq; - rq = task_rq_lock(current, &flags); + rq = task_rq_lock(p, &flags); /* * We need to take care of several possible races here: @@ -536,6 +582,17 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) sched_clock_tick(); update_rq_clock(rq); +#ifdef CONFIG_SMP + /* + * If we find that the rq the task was on is no longer + * available, we need to select a new rq. + */ + if (unlikely(!rq->online)) { + dl_task_offline_migration(rq, p); + goto unlock; + } +#endif + /* * If the throttle happened during sched-out; like: * @@ -569,7 +626,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) push_dl_task(rq); #endif unlock: - task_rq_unlock(rq, current, &flags); + task_rq_unlock(rq, p, &flags); return HRTIMER_NORESTART; } @@ -914,6 +971,12 @@ static void yield_task_dl(struct rq *rq) } update_rq_clock(rq); update_curr_dl(rq); + /* + * Tell update_rq_clock() that we've just updated, + * so we don't do microscopic update in schedule() + * and double the fastpath cost. + */ + rq_clock_skip_update(rq, true); } #ifdef CONFIG_SMP @@ -1659,14 +1722,6 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p) { int check_resched = 1; - /* - * If p is throttled, don't consider the possibility - * of preempting rq->curr, the check will be done right - * after its runtime will get replenished. - */ - if (unlikely(p->dl.dl_throttled)) - return; - if (task_on_rq_queued(p) && rq->curr != p) { #ifdef CONFIG_SMP if (p->nr_cpus_allowed > 1 && rq->dl.overloaded && diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 8baaf858d25c..a245c1fc6f0a 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -71,7 +71,7 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group if (!se) { struct sched_avg *avg = &cpu_rq(cpu)->avg; P(avg->runnable_avg_sum); - P(avg->runnable_avg_period); + P(avg->avg_period); return; } @@ -94,8 +94,10 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group P(se->load.weight); #ifdef CONFIG_SMP P(se->avg.runnable_avg_sum); - P(se->avg.runnable_avg_period); + P(se->avg.running_avg_sum); + P(se->avg.avg_period); P(se->avg.load_avg_contrib); + P(se->avg.utilization_avg_contrib); P(se->avg.decay_count); #endif #undef PN @@ -214,6 +216,8 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) cfs_rq->runnable_load_avg); SEQ_printf(m, " .%-30s: %ld\n", "blocked_load_avg", cfs_rq->blocked_load_avg); + SEQ_printf(m, " .%-30s: %ld\n", "utilization_load_avg", + cfs_rq->utilization_load_avg); #ifdef CONFIG_FAIR_GROUP_SCHED SEQ_printf(m, " .%-30s: %ld\n", "tg_load_contrib", cfs_rq->tg_load_contrib); @@ -636,8 +640,10 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m) P(se.load.weight); #ifdef CONFIG_SMP P(se.avg.runnable_avg_sum); - P(se.avg.runnable_avg_period); + P(se.avg.running_avg_sum); + P(se.avg.avg_period); P(se.avg.load_avg_contrib); + P(se.avg.utilization_avg_contrib); P(se.avg.decay_count); #endif P(policy); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index bcfe32088b37..ffeaa4105e48 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -670,6 +670,7 @@ static int select_idle_sibling(struct task_struct *p, int cpu); static unsigned long task_h_load(struct task_struct *p); static inline void __update_task_entity_contrib(struct sched_entity *se); +static inline void __update_task_entity_utilization(struct sched_entity *se); /* Give new task start runnable values to heavy its load in infant time */ void init_task_runnable_average(struct task_struct *p) @@ -677,9 +678,10 @@ void init_task_runnable_average(struct task_struct *p) u32 slice; slice = sched_slice(task_cfs_rq(p), &p->se) >> 10; - p->se.avg.runnable_avg_sum = slice; - p->se.avg.runnable_avg_period = slice; + p->se.avg.runnable_avg_sum = p->se.avg.running_avg_sum = slice; + p->se.avg.avg_period = slice; __update_task_entity_contrib(&p->se); + __update_task_entity_utilization(&p->se); } #else void init_task_runnable_average(struct task_struct *p) @@ -1196,9 +1198,11 @@ static void task_numa_assign(struct task_numa_env *env, static bool load_too_imbalanced(long src_load, long dst_load, struct task_numa_env *env) { - long imb, old_imb; - long orig_src_load, orig_dst_load; long src_capacity, dst_capacity; + long orig_src_load; + long load_a, load_b; + long moved_load; + long imb; /* * The load is corrected for the CPU capacity available on each node. @@ -1211,30 +1215,39 @@ static bool load_too_imbalanced(long src_load, long dst_load, dst_capacity = env->dst_stats.compute_capacity; /* We care about the slope of the imbalance, not the direction. */ - if (dst_load < src_load) - swap(dst_load, src_load); + load_a = dst_load; + load_b = src_load; + if (load_a < load_b) + swap(load_a, load_b); /* Is the difference below the threshold? */ - imb = dst_load * src_capacity * 100 - - src_load * dst_capacity * env->imbalance_pct; + imb = load_a * src_capacity * 100 - + load_b * dst_capacity * env->imbalance_pct; if (imb <= 0) return false; /* * The imbalance is above the allowed threshold. - * Compare it with the old imbalance. + * Allow a move that brings us closer to a balanced situation, + * without moving things past the point of balance. */ orig_src_load = env->src_stats.load; - orig_dst_load = env->dst_stats.load; - if (orig_dst_load < orig_src_load) - swap(orig_dst_load, orig_src_load); - - old_imb = orig_dst_load * src_capacity * 100 - - orig_src_load * dst_capacity * env->imbalance_pct; + /* + * In a task swap, there will be one load moving from src to dst, + * and another moving back. This is the net sum of both moves. + * A simple task move will always have a positive value. + * Allow the move if it brings the system closer to a balanced + * situation, without crossing over the balance point. + */ + moved_load = orig_src_load - src_load; - /* Would this change make things worse? */ - return (imb > old_imb); + if (moved_load > 0) + /* Moving src -> dst. Did we overshoot balance? */ + return src_load * dst_capacity < dst_load * src_capacity; + else + /* Moving dst -> src. Did we overshoot balance? */ + return dst_load * src_capacity < src_load * dst_capacity; } /* @@ -1675,7 +1688,7 @@ static u64 numa_get_avg_runtime(struct task_struct *p, u64 *period) *period = now - p->last_task_numa_placement; } else { delta = p->se.avg.runnable_avg_sum; - *period = p->se.avg.runnable_avg_period; + *period = p->se.avg.avg_period; } p->last_sum_exec_runtime = runtime; @@ -1765,6 +1778,8 @@ static int preferred_group_nid(struct task_struct *p, int nid) } } /* Next round, evaluate the nodes within max_group. */ + if (!max_faults) + break; nodes = max_group; } return nid; @@ -2165,8 +2180,10 @@ void task_numa_work(struct callback_head *work) vma = mm->mmap; } for (; vma; vma = vma->vm_next) { - if (!vma_migratable(vma) || !vma_policy_mof(vma)) + if (!vma_migratable(vma) || !vma_policy_mof(vma) || + is_vm_hugetlb_page(vma)) { continue; + } /* * Shared library pages mapped by multiple processes are not @@ -2501,13 +2518,15 @@ static u32 __compute_runnable_contrib(u64 n) * load_avg = u_0` + y*(u_0 + u_1*y + u_2*y^2 + ... ) * = u_0 + u_1*y + u_2*y^2 + ... [re-labeling u_i --> u_{i+1}] */ -static __always_inline int __update_entity_runnable_avg(u64 now, +static __always_inline int __update_entity_runnable_avg(u64 now, int cpu, struct sched_avg *sa, - int runnable) + int runnable, + int running) { u64 delta, periods; u32 runnable_contrib; int delta_w, decayed = 0; + unsigned long scale_freq = arch_scale_freq_capacity(NULL, cpu); delta = now - sa->last_runnable_update; /* @@ -2529,7 +2548,7 @@ static __always_inline int __update_entity_runnable_avg(u64 now, sa->last_runnable_update = now; /* delta_w is the amount already accumulated against our next period */ - delta_w = sa->runnable_avg_period % 1024; + delta_w = sa->avg_period % 1024; if (delta + delta_w >= 1024) { /* period roll-over */ decayed = 1; @@ -2542,7 +2561,10 @@ static __always_inline int __update_entity_runnable_avg(u64 now, delta_w = 1024 - delta_w; if (runnable) sa->runnable_avg_sum += delta_w; - sa->runnable_avg_period += delta_w; + if (running) + sa->running_avg_sum += delta_w * scale_freq + >> SCHED_CAPACITY_SHIFT; + sa->avg_period += delta_w; delta -= delta_w; @@ -2552,20 +2574,28 @@ static __always_inline int __update_entity_runnable_avg(u64 now, sa->runnable_avg_sum = decay_load(sa->runnable_avg_sum, periods + 1); - sa->runnable_avg_period = decay_load(sa->runnable_avg_period, + sa->running_avg_sum = decay_load(sa->running_avg_sum, + periods + 1); + sa->avg_period = decay_load(sa->avg_period, periods + 1); /* Efficiently calculate \sum (1..n_period) 1024*y^i */ runnable_contrib = __compute_runnable_contrib(periods); if (runnable) sa->runnable_avg_sum += runnable_contrib; - sa->runnable_avg_period += runnable_contrib; + if (running) + sa->running_avg_sum += runnable_contrib * scale_freq + >> SCHED_CAPACITY_SHIFT; + sa->avg_period += runnable_contrib; } /* Remainder of delta accrued against u_0` */ if (runnable) sa->runnable_avg_sum += delta; - sa->runnable_avg_period += delta; + if (running) + sa->running_avg_sum += delta * scale_freq + >> SCHED_CAPACITY_SHIFT; + sa->avg_period += delta; return decayed; } @@ -2582,6 +2612,8 @@ static inline u64 __synchronize_entity_decay(struct sched_entity *se) return 0; se->avg.load_avg_contrib = decay_load(se->avg.load_avg_contrib, decays); + se->avg.utilization_avg_contrib = + decay_load(se->avg.utilization_avg_contrib, decays); return decays; } @@ -2617,7 +2649,7 @@ static inline void __update_tg_runnable_avg(struct sched_avg *sa, /* The fraction of a cpu used by this cfs_rq */ contrib = div_u64((u64)sa->runnable_avg_sum << NICE_0_SHIFT, - sa->runnable_avg_period + 1); + sa->avg_period + 1); contrib -= cfs_rq->tg_runnable_contrib; if (abs(contrib) > cfs_rq->tg_runnable_contrib / 64) { @@ -2670,7 +2702,8 @@ static inline void __update_group_entity_contrib(struct sched_entity *se) static inline void update_rq_runnable_avg(struct rq *rq, int runnable) { - __update_entity_runnable_avg(rq_clock_task(rq), &rq->avg, runnable); + __update_entity_runnable_avg(rq_clock_task(rq), cpu_of(rq), &rq->avg, + runnable, runnable); __update_tg_runnable_avg(&rq->avg, &rq->cfs); } #else /* CONFIG_FAIR_GROUP_SCHED */ @@ -2688,7 +2721,7 @@ static inline void __update_task_entity_contrib(struct sched_entity *se) /* avoid overflowing a 32-bit type w/ SCHED_LOAD_SCALE */ contrib = se->avg.runnable_avg_sum * scale_load_down(se->load.weight); - contrib /= (se->avg.runnable_avg_period + 1); + contrib /= (se->avg.avg_period + 1); se->avg.load_avg_contrib = scale_load(contrib); } @@ -2707,6 +2740,30 @@ static long __update_entity_load_avg_contrib(struct sched_entity *se) return se->avg.load_avg_contrib - old_contrib; } + +static inline void __update_task_entity_utilization(struct sched_entity *se) +{ + u32 contrib; + + /* avoid overflowing a 32-bit type w/ SCHED_LOAD_SCALE */ + contrib = se->avg.running_avg_sum * scale_load_down(SCHED_LOAD_SCALE); + contrib /= (se->avg.avg_period + 1); + se->avg.utilization_avg_contrib = scale_load(contrib); +} + +static long __update_entity_utilization_avg_contrib(struct sched_entity *se) +{ + long old_contrib = se->avg.utilization_avg_contrib; + + if (entity_is_task(se)) + __update_task_entity_utilization(se); + else + se->avg.utilization_avg_contrib = + group_cfs_rq(se)->utilization_load_avg; + + return se->avg.utilization_avg_contrib - old_contrib; +} + static inline void subtract_blocked_load_contrib(struct cfs_rq *cfs_rq, long load_contrib) { @@ -2723,7 +2780,8 @@ static inline void update_entity_load_avg(struct sched_entity *se, int update_cfs_rq) { struct cfs_rq *cfs_rq = cfs_rq_of(se); - long contrib_delta; + long contrib_delta, utilization_delta; + int cpu = cpu_of(rq_of(cfs_rq)); u64 now; /* @@ -2735,18 +2793,22 @@ static inline void update_entity_load_avg(struct sched_entity *se, else now = cfs_rq_clock_task(group_cfs_rq(se)); - if (!__update_entity_runnable_avg(now, &se->avg, se->on_rq)) + if (!__update_entity_runnable_avg(now, cpu, &se->avg, se->on_rq, + cfs_rq->curr == se)) return; contrib_delta = __update_entity_load_avg_contrib(se); + utilization_delta = __update_entity_utilization_avg_contrib(se); if (!update_cfs_rq) return; - if (se->on_rq) + if (se->on_rq) { cfs_rq->runnable_load_avg += contrib_delta; - else + cfs_rq->utilization_load_avg += utilization_delta; + } else { subtract_blocked_load_contrib(cfs_rq, -contrib_delta); + } } /* @@ -2821,6 +2883,7 @@ static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq, } cfs_rq->runnable_load_avg += se->avg.load_avg_contrib; + cfs_rq->utilization_load_avg += se->avg.utilization_avg_contrib; /* we force update consideration on load-balancer moves */ update_cfs_rq_blocked_load(cfs_rq, !wakeup); } @@ -2839,6 +2902,7 @@ static inline void dequeue_entity_load_avg(struct cfs_rq *cfs_rq, update_cfs_rq_blocked_load(cfs_rq, !sleep); cfs_rq->runnable_load_avg -= se->avg.load_avg_contrib; + cfs_rq->utilization_load_avg -= se->avg.utilization_avg_contrib; if (sleep) { cfs_rq->blocked_load_avg += se->avg.load_avg_contrib; se->avg.decay_count = atomic64_read(&cfs_rq->decay_counter); @@ -3176,6 +3240,7 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) */ update_stats_wait_end(cfs_rq, se); __dequeue_entity(cfs_rq, se); + update_entity_load_avg(se, 1); } update_stats_curr_start(cfs_rq, se); @@ -4302,6 +4367,11 @@ static unsigned long capacity_of(int cpu) return cpu_rq(cpu)->cpu_capacity; } +static unsigned long capacity_orig_of(int cpu) +{ + return cpu_rq(cpu)->cpu_capacity_orig; +} + static unsigned long cpu_avg_load_per_task(int cpu) { struct rq *rq = cpu_rq(cpu); @@ -4715,6 +4785,33 @@ next: done: return target; } +/* + * get_cpu_usage returns the amount of capacity of a CPU that is used by CFS + * tasks. The unit of the return value must be the one of capacity so we can + * compare the usage with the capacity of the CPU that is available for CFS + * task (ie cpu_capacity). + * cfs.utilization_load_avg is the sum of running time of runnable tasks on a + * CPU. It represents the amount of utilization of a CPU in the range + * [0..SCHED_LOAD_SCALE]. The usage of a CPU can't be higher than the full + * capacity of the CPU because it's about the running time on this CPU. + * Nevertheless, cfs.utilization_load_avg can be higher than SCHED_LOAD_SCALE + * because of unfortunate rounding in avg_period and running_load_avg or just + * after migrating tasks until the average stabilizes with the new running + * time. So we need to check that the usage stays into the range + * [0..cpu_capacity_orig] and cap if necessary. + * Without capping the usage, a group could be seen as overloaded (CPU0 usage + * at 121% + CPU1 usage at 80%) whereas CPU1 has 20% of available capacity + */ +static int get_cpu_usage(int cpu) +{ + unsigned long usage = cpu_rq(cpu)->cfs.utilization_load_avg; + unsigned long capacity = capacity_orig_of(cpu); + + if (usage >= SCHED_LOAD_SCALE) + return capacity; + + return (usage * capacity) >> SCHED_LOAD_SHIFT; +} /* * select_task_rq_fair: Select target runqueue for the waking task in domains @@ -5841,12 +5938,12 @@ struct sg_lb_stats { unsigned long sum_weighted_load; /* Weighted load of group's tasks */ unsigned long load_per_task; unsigned long group_capacity; + unsigned long group_usage; /* Total usage of the group */ unsigned int sum_nr_running; /* Nr tasks running in the group */ - unsigned int group_capacity_factor; unsigned int idle_cpus; unsigned int group_weight; enum group_type group_type; - int group_has_free_capacity; + int group_no_capacity; #ifdef CONFIG_NUMA_BALANCING unsigned int nr_numa_running; unsigned int nr_preferred_running; @@ -5917,16 +6014,6 @@ static inline int get_sd_load_idx(struct sched_domain *sd, return load_idx; } -static unsigned long default_scale_capacity(struct sched_domain *sd, int cpu) -{ - return SCHED_CAPACITY_SCALE; -} - -unsigned long __weak arch_scale_freq_capacity(struct sched_domain *sd, int cpu) -{ - return default_scale_capacity(sd, cpu); -} - static unsigned long default_scale_cpu_capacity(struct sched_domain *sd, int cpu) { if ((sd->flags & SD_SHARE_CPUCAPACITY) && (sd->span_weight > 1)) @@ -5943,7 +6030,7 @@ unsigned long __weak arch_scale_cpu_capacity(struct sched_domain *sd, int cpu) static unsigned long scale_rt_capacity(int cpu) { struct rq *rq = cpu_rq(cpu); - u64 total, available, age_stamp, avg; + u64 total, used, age_stamp, avg; s64 delta; /* @@ -5959,19 +6046,12 @@ static unsigned long scale_rt_capacity(int cpu) total = sched_avg_period() + delta; - if (unlikely(total < avg)) { - /* Ensures that capacity won't end up being negative */ - available = 0; - } else { - available = total - avg; - } - - if (unlikely((s64)total < SCHED_CAPACITY_SCALE)) - total = SCHED_CAPACITY_SCALE; + used = div_u64(avg, total); - total >>= SCHED_CAPACITY_SHIFT; + if (likely(used < SCHED_CAPACITY_SCALE)) + return SCHED_CAPACITY_SCALE - used; - return div_u64(available, total); + return 1; } static void update_cpu_capacity(struct sched_domain *sd, int cpu) @@ -5986,14 +6066,7 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu) capacity >>= SCHED_CAPACITY_SHIFT; - sdg->sgc->capacity_orig = capacity; - - if (sched_feat(ARCH_CAPACITY)) - capacity *= arch_scale_freq_capacity(sd, cpu); - else - capacity *= default_scale_capacity(sd, cpu); - - capacity >>= SCHED_CAPACITY_SHIFT; + cpu_rq(cpu)->cpu_capacity_orig = capacity; capacity *= scale_rt_capacity(cpu); capacity >>= SCHED_CAPACITY_SHIFT; @@ -6009,7 +6082,7 @@ void update_group_capacity(struct sched_domain *sd, int cpu) { struct sched_domain *child = sd->child; struct sched_group *group, *sdg = sd->groups; - unsigned long capacity, capacity_orig; + unsigned long capacity; unsigned long interval; interval = msecs_to_jiffies(sd->balance_interval); @@ -6021,7 +6094,7 @@ void update_group_capacity(struct sched_domain *sd, int cpu) return; } - capacity_orig = capacity = 0; + capacity = 0; if (child->flags & SD_OVERLAP) { /* @@ -6041,19 +6114,15 @@ void update_group_capacity(struct sched_domain *sd, int cpu) * Use capacity_of(), which is set irrespective of domains * in update_cpu_capacity(). * - * This avoids capacity/capacity_orig from being 0 and + * This avoids capacity from being 0 and * causing divide-by-zero issues on boot. - * - * Runtime updates will correct capacity_orig. */ if (unlikely(!rq->sd)) { - capacity_orig += capacity_of(cpu); capacity += capacity_of(cpu); continue; } sgc = rq->sd->groups->sgc; - capacity_orig += sgc->capacity_orig; capacity += sgc->capacity; } } else { @@ -6064,39 +6133,24 @@ void update_group_capacity(struct sched_domain *sd, int cpu) group = child->groups; do { - capacity_orig += group->sgc->capacity_orig; capacity += group->sgc->capacity; group = group->next; } while (group != child->groups); } - sdg->sgc->capacity_orig = capacity_orig; sdg->sgc->capacity = capacity; } /* - * Try and fix up capacity for tiny siblings, this is needed when - * things like SD_ASYM_PACKING need f_b_g to select another sibling - * which on its own isn't powerful enough. - * - * See update_sd_pick_busiest() and check_asym_packing(). + * Check whether the capacity of the rq has been noticeably reduced by side + * activity. The imbalance_pct is used for the threshold. + * Return true is the capacity is reduced */ static inline int -fix_small_capacity(struct sched_domain *sd, struct sched_group *group) +check_cpu_capacity(struct rq *rq, struct sched_domain *sd) { - /* - * Only siblings can have significantly less than SCHED_CAPACITY_SCALE - */ - if (!(sd->flags & SD_SHARE_CPUCAPACITY)) - return 0; - - /* - * If ~90% of the cpu_capacity is still there, we're good. - */ - if (group->sgc->capacity * 32 > group->sgc->capacity_orig * 29) - return 1; - - return 0; + return ((rq->cpu_capacity * sd->imbalance_pct) < + (rq->cpu_capacity_orig * 100)); } /* @@ -6134,37 +6188,56 @@ static inline int sg_imbalanced(struct sched_group *group) } /* - * Compute the group capacity factor. - * - * Avoid the issue where N*frac(smt_capacity) >= 1 creates 'phantom' cores by - * first dividing out the smt factor and computing the actual number of cores - * and limit unit capacity with that. + * group_has_capacity returns true if the group has spare capacity that could + * be used by some tasks. + * We consider that a group has spare capacity if the * number of task is + * smaller than the number of CPUs or if the usage is lower than the available + * capacity for CFS tasks. + * For the latter, we use a threshold to stabilize the state, to take into + * account the variance of the tasks' load and to return true if the available + * capacity in meaningful for the load balancer. + * As an example, an available capacity of 1% can appear but it doesn't make + * any benefit for the load balance. */ -static inline int sg_capacity_factor(struct lb_env *env, struct sched_group *group) +static inline bool +group_has_capacity(struct lb_env *env, struct sg_lb_stats *sgs) { - unsigned int capacity_factor, smt, cpus; - unsigned int capacity, capacity_orig; + if (sgs->sum_nr_running < sgs->group_weight) + return true; - capacity = group->sgc->capacity; - capacity_orig = group->sgc->capacity_orig; - cpus = group->group_weight; + if ((sgs->group_capacity * 100) > + (sgs->group_usage * env->sd->imbalance_pct)) + return true; + + return false; +} - /* smt := ceil(cpus / capacity), assumes: 1 < smt_capacity < 2 */ - smt = DIV_ROUND_UP(SCHED_CAPACITY_SCALE * cpus, capacity_orig); - capacity_factor = cpus / smt; /* cores */ +/* + * group_is_overloaded returns true if the group has more tasks than it can + * handle. + * group_is_overloaded is not equals to !group_has_capacity because a group + * with the exact right number of tasks, has no more spare capacity but is not + * overloaded so both group_has_capacity and group_is_overloaded return + * false. + */ +static inline bool +group_is_overloaded(struct lb_env *env, struct sg_lb_stats *sgs) +{ + if (sgs->sum_nr_running <= sgs->group_weight) + return false; - capacity_factor = min_t(unsigned, - capacity_factor, DIV_ROUND_CLOSEST(capacity, SCHED_CAPACITY_SCALE)); - if (!capacity_factor) - capacity_factor = fix_small_capacity(env->sd, group); + if ((sgs->group_capacity * 100) < + (sgs->group_usage * env->sd->imbalance_pct)) + return true; - return capacity_factor; + return false; } -static enum group_type -group_classify(struct sched_group *group, struct sg_lb_stats *sgs) +static enum group_type group_classify(struct lb_env *env, + struct sched_group *group, + struct sg_lb_stats *sgs) { - if (sgs->sum_nr_running > sgs->group_capacity_factor) + if (sgs->group_no_capacity) return group_overloaded; if (sg_imbalanced(group)) @@ -6202,6 +6275,7 @@ static inline void update_sg_lb_stats(struct lb_env *env, load = source_load(i, load_idx); sgs->group_load += load; + sgs->group_usage += get_cpu_usage(i); sgs->sum_nr_running += rq->cfs.h_nr_running; if (rq->nr_running > 1) @@ -6224,11 +6298,9 @@ static inline void update_sg_lb_stats(struct lb_env *env, sgs->load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running; sgs->group_weight = group->group_weight; - sgs->group_capacity_factor = sg_capacity_factor(env, group); - sgs->group_type = group_classify(group, sgs); - if (sgs->group_capacity_factor > sgs->sum_nr_running) - sgs->group_has_free_capacity = 1; + sgs->group_no_capacity = group_is_overloaded(env, sgs); + sgs->group_type = group_classify(env, group, sgs); } /** @@ -6350,18 +6422,19 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd /* * In case the child domain prefers tasks go to siblings - * first, lower the sg capacity factor to one so that we'll try + * first, lower the sg capacity so that we'll try * and move all the excess tasks away. We lower the capacity * of a group only if the local group has the capacity to fit - * these excess tasks, i.e. nr_running < group_capacity_factor. The - * extra check prevents the case where you always pull from the - * heaviest group when it is already under-utilized (possible - * with a large weight task outweighs the tasks on the system). + * these excess tasks. The extra check prevents the case where + * you always pull from the heaviest group when it is already + * under-utilized (possible with a large weight task outweighs + * the tasks on the system). */ if (prefer_sibling && sds->local && - sds->local_stat.group_has_free_capacity) { - sgs->group_capacity_factor = min(sgs->group_capacity_factor, 1U); - sgs->group_type = group_classify(sg, sgs); + group_has_capacity(env, &sds->local_stat) && + (sgs->sum_nr_running > 1)) { + sgs->group_no_capacity = 1; + sgs->group_type = group_overloaded; } if (update_sd_pick_busiest(env, sds, sg, sgs)) { @@ -6541,11 +6614,12 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s */ if (busiest->group_type == group_overloaded && local->group_type == group_overloaded) { - load_above_capacity = - (busiest->sum_nr_running - busiest->group_capacity_factor); - - load_above_capacity *= (SCHED_LOAD_SCALE * SCHED_CAPACITY_SCALE); - load_above_capacity /= busiest->group_capacity; + load_above_capacity = busiest->sum_nr_running * + SCHED_LOAD_SCALE; + if (load_above_capacity > busiest->group_capacity) + load_above_capacity -= busiest->group_capacity; + else + load_above_capacity = ~0UL; } /* @@ -6608,6 +6682,7 @@ static struct sched_group *find_busiest_group(struct lb_env *env) local = &sds.local_stat; busiest = &sds.busiest_stat; + /* ASYM feature bypasses nice load balance check */ if ((env->idle == CPU_IDLE || env->idle == CPU_NEWLY_IDLE) && check_asym_packing(env, &sds)) return sds.busiest; @@ -6628,8 +6703,8 @@ static struct sched_group *find_busiest_group(struct lb_env *env) goto force_balance; /* SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */ - if (env->idle == CPU_NEWLY_IDLE && local->group_has_free_capacity && - !busiest->group_has_free_capacity) + if (env->idle == CPU_NEWLY_IDLE && group_has_capacity(env, local) && + busiest->group_no_capacity) goto force_balance; /* @@ -6688,7 +6763,7 @@ static struct rq *find_busiest_queue(struct lb_env *env, int i; for_each_cpu_and(i, sched_group_cpus(group), env->cpus) { - unsigned long capacity, capacity_factor, wl; + unsigned long capacity, wl; enum fbq_type rt; rq = cpu_rq(i); @@ -6717,9 +6792,6 @@ static struct rq *find_busiest_queue(struct lb_env *env, continue; capacity = capacity_of(i); - capacity_factor = DIV_ROUND_CLOSEST(capacity, SCHED_CAPACITY_SCALE); - if (!capacity_factor) - capacity_factor = fix_small_capacity(env->sd, group); wl = weighted_cpuload(i); @@ -6727,7 +6799,9 @@ static struct rq *find_busiest_queue(struct lb_env *env, * When comparing with imbalance, use weighted_cpuload() * which is not scaled with the cpu capacity. */ - if (capacity_factor && rq->nr_running == 1 && wl > env->imbalance) + + if (rq->nr_running == 1 && wl > env->imbalance && + !check_cpu_capacity(rq, env->sd)) continue; /* @@ -6775,6 +6849,19 @@ static int need_active_balance(struct lb_env *env) return 1; } + /* + * The dst_cpu is idle and the src_cpu CPU has only 1 CFS task. + * It's worth migrating the task if the src_cpu's capacity is reduced + * because of other sched_class or IRQs if more capacity stays + * available on dst_cpu. + */ + if ((env->idle != CPU_NOT_IDLE) && + (env->src_rq->cfs.h_nr_running == 1)) { + if ((check_cpu_capacity(env->src_rq, sd)) && + (capacity_of(env->src_cpu)*sd->imbalance_pct < capacity_of(env->dst_cpu)*100)) + return 1; + } + return unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2); } @@ -6874,6 +6961,9 @@ redo: schedstat_add(sd, lb_imbalance[idle], env.imbalance); + env.src_cpu = busiest->cpu; + env.src_rq = busiest; + ld_moved = 0; if (busiest->nr_running > 1) { /* @@ -6883,8 +6973,6 @@ redo: * correctly treated as an imbalance. */ env.flags |= LBF_ALL_PINNED; - env.src_cpu = busiest->cpu; - env.src_rq = busiest; env.loop_max = min(sysctl_sched_nr_migrate, busiest->nr_running); more_balance: @@ -7584,22 +7672,25 @@ end: /* * Current heuristic for kicking the idle load balancer in the presence - * of an idle cpu is the system. + * of an idle cpu in the system. * - This rq has more than one task. - * - At any scheduler domain level, this cpu's scheduler group has multiple - * busy cpu's exceeding the group's capacity. + * - This rq has at least one CFS task and the capacity of the CPU is + * significantly reduced because of RT tasks or IRQs. + * - At parent of LLC scheduler domain level, this cpu's scheduler group has + * multiple busy cpu. * - For SD_ASYM_PACKING, if the lower numbered cpu's in the scheduler * domain span are idle. */ -static inline int nohz_kick_needed(struct rq *rq) +static inline bool nohz_kick_needed(struct rq *rq) { unsigned long now = jiffies; struct sched_domain *sd; struct sched_group_capacity *sgc; int nr_busy, cpu = rq->cpu; + bool kick = false; if (unlikely(rq->idle_balance)) - return 0; + return false; /* * We may be recently in ticked or tickless idle mode. At the first @@ -7613,38 +7704,46 @@ static inline int nohz_kick_needed(struct rq *rq) * balancing. */ if (likely(!atomic_read(&nohz.nr_cpus))) - return 0; + return false; if (time_before(now, nohz.next_balance)) - return 0; + return false; if (rq->nr_running >= 2) - goto need_kick; + return true; rcu_read_lock(); sd = rcu_dereference(per_cpu(sd_busy, cpu)); - if (sd) { sgc = sd->groups->sgc; nr_busy = atomic_read(&sgc->nr_busy_cpus); - if (nr_busy > 1) - goto need_kick_unlock; + if (nr_busy > 1) { + kick = true; + goto unlock; + } + } - sd = rcu_dereference(per_cpu(sd_asym, cpu)); + sd = rcu_dereference(rq->sd); + if (sd) { + if ((rq->cfs.h_nr_running >= 1) && + check_cpu_capacity(rq, sd)) { + kick = true; + goto unlock; + } + } + sd = rcu_dereference(per_cpu(sd_asym, cpu)); if (sd && (cpumask_first_and(nohz.idle_cpus_mask, - sched_domain_span(sd)) < cpu)) - goto need_kick_unlock; - - rcu_read_unlock(); - return 0; + sched_domain_span(sd)) < cpu)) { + kick = true; + goto unlock; + } -need_kick_unlock: +unlock: rcu_read_unlock(); -need_kick: - return 1; + return kick; } #else static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) { } @@ -7660,14 +7759,16 @@ static void run_rebalance_domains(struct softirq_action *h) enum cpu_idle_type idle = this_rq->idle_balance ? CPU_IDLE : CPU_NOT_IDLE; - rebalance_domains(this_rq, idle); - /* * If this cpu has a pending nohz_balance_kick, then do the * balancing on behalf of the other idle cpus whose ticks are - * stopped. + * stopped. Do nohz_idle_balance *before* rebalance_domains to + * give the idle cpus a chance to load balance. Else we may + * load balance only within the local sched_domain hierarchy + * and abort nohz_idle_balance altogether if we pull some load. */ nohz_idle_balance(this_rq, idle); + rebalance_domains(this_rq, idle); } /* diff --git a/kernel/sched/features.h b/kernel/sched/features.h index 90284d117fe6..91e33cd485f6 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -56,6 +56,19 @@ SCHED_FEAT(NONTASK_CAPACITY, true) */ SCHED_FEAT(TTWU_QUEUE, true) +#ifdef HAVE_RT_PUSH_IPI +/* + * In order to avoid a thundering herd attack of CPUs that are + * lowering their priorities at the same time, and there being + * a single CPU that has an RT task that can migrate and is waiting + * to run, where the other CPUs will try to take that CPUs + * rq lock and possibly create a large contention, sending an + * IPI to that CPU and let that CPU push the RT task to where + * it should go may be a better scenario. + */ +SCHED_FEAT(RT_PUSH_IPI, true) +#endif + SCHED_FEAT(FORCE_SD_OVERLAP, false) SCHED_FEAT(RT_RUNTIME_SHARE, true) SCHED_FEAT(LB_MIN, false) diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 80014a178342..4d207d2abcbd 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -158,8 +158,7 @@ static void cpuidle_idle_call(void) * is used from another cpu as a broadcast timer, this call may * fail if it is not available */ - if (broadcast && - clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &dev->cpu)) + if (broadcast && tick_broadcast_enter()) goto use_default; /* Take note of the planned idle state. */ @@ -176,7 +175,7 @@ static void cpuidle_idle_call(void) idle_set_state(this_rq(), NULL); if (broadcast) - clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &dev->cpu); + tick_broadcast_exit(); /* * Give the governor an opportunity to reflect on the outcome diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index f4d4b077eba0..575da76a3874 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -6,6 +6,7 @@ #include "sched.h" #include <linux/slab.h> +#include <linux/irq_work.h> int sched_rr_timeslice = RR_TIMESLICE; @@ -59,7 +60,11 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b) raw_spin_unlock(&rt_b->rt_runtime_lock); } -void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq) +#ifdef CONFIG_SMP +static void push_irq_work_func(struct irq_work *work); +#endif + +void init_rt_rq(struct rt_rq *rt_rq) { struct rt_prio_array *array; int i; @@ -78,7 +83,14 @@ void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq) rt_rq->rt_nr_migratory = 0; rt_rq->overloaded = 0; plist_head_init(&rt_rq->pushable_tasks); + +#ifdef HAVE_RT_PUSH_IPI + rt_rq->push_flags = 0; + rt_rq->push_cpu = nr_cpu_ids; + raw_spin_lock_init(&rt_rq->push_lock); + init_irq_work(&rt_rq->push_work, push_irq_work_func); #endif +#endif /* CONFIG_SMP */ /* We start is dequeued state, because no RT tasks are queued */ rt_rq->rt_queued = 0; @@ -193,7 +205,7 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent) if (!rt_se) goto err_free_rq; - init_rt_rq(rt_rq, cpu_rq(i)); + init_rt_rq(rt_rq); rt_rq->rt_runtime = tg->rt_bandwidth.rt_runtime; init_tg_rt_entry(tg, rt_rq, rt_se, i, parent->rt_se[i]); } @@ -1778,6 +1790,164 @@ static void push_rt_tasks(struct rq *rq) ; } +#ifdef HAVE_RT_PUSH_IPI +/* + * The search for the next cpu always starts at rq->cpu and ends + * when we reach rq->cpu again. It will never return rq->cpu. + * This returns the next cpu to check, or nr_cpu_ids if the loop + * is complete. + * + * rq->rt.push_cpu holds the last cpu returned by this function, + * or if this is the first instance, it must hold rq->cpu. + */ +static int rto_next_cpu(struct rq *rq) +{ + int prev_cpu = rq->rt.push_cpu; + int cpu; + + cpu = cpumask_next(prev_cpu, rq->rd->rto_mask); + + /* + * If the previous cpu is less than the rq's CPU, then it already + * passed the end of the mask, and has started from the beginning. + * We end if the next CPU is greater or equal to rq's CPU. + */ + if (prev_cpu < rq->cpu) { + if (cpu >= rq->cpu) + return nr_cpu_ids; + + } else if (cpu >= nr_cpu_ids) { + /* + * We passed the end of the mask, start at the beginning. + * If the result is greater or equal to the rq's CPU, then + * the loop is finished. + */ + cpu = cpumask_first(rq->rd->rto_mask); + if (cpu >= rq->cpu) + return nr_cpu_ids; + } + rq->rt.push_cpu = cpu; + + /* Return cpu to let the caller know if the loop is finished or not */ + return cpu; +} + +static int find_next_push_cpu(struct rq *rq) +{ + struct rq *next_rq; + int cpu; + + while (1) { + cpu = rto_next_cpu(rq); + if (cpu >= nr_cpu_ids) + break; + next_rq = cpu_rq(cpu); + + /* Make sure the next rq can push to this rq */ + if (next_rq->rt.highest_prio.next < rq->rt.highest_prio.curr) + break; + } + + return cpu; +} + +#define RT_PUSH_IPI_EXECUTING 1 +#define RT_PUSH_IPI_RESTART 2 + +static void tell_cpu_to_push(struct rq *rq) +{ + int cpu; + + if (rq->rt.push_flags & RT_PUSH_IPI_EXECUTING) { + raw_spin_lock(&rq->rt.push_lock); + /* Make sure it's still executing */ + if (rq->rt.push_flags & RT_PUSH_IPI_EXECUTING) { + /* + * Tell the IPI to restart the loop as things have + * changed since it started. + */ + rq->rt.push_flags |= RT_PUSH_IPI_RESTART; + raw_spin_unlock(&rq->rt.push_lock); + return; + } + raw_spin_unlock(&rq->rt.push_lock); + } + + /* When here, there's no IPI going around */ + + rq->rt.push_cpu = rq->cpu; + cpu = find_next_push_cpu(rq); + if (cpu >= nr_cpu_ids) + return; + + rq->rt.push_flags = RT_PUSH_IPI_EXECUTING; + + irq_work_queue_on(&rq->rt.push_work, cpu); +} + +/* Called from hardirq context */ +static void try_to_push_tasks(void *arg) +{ + struct rt_rq *rt_rq = arg; + struct rq *rq, *src_rq; + int this_cpu; + int cpu; + + this_cpu = rt_rq->push_cpu; + + /* Paranoid check */ + BUG_ON(this_cpu != smp_processor_id()); + + rq = cpu_rq(this_cpu); + src_rq = rq_of_rt_rq(rt_rq); + +again: + if (has_pushable_tasks(rq)) { + raw_spin_lock(&rq->lock); + push_rt_task(rq); + raw_spin_unlock(&rq->lock); + } + + /* Pass the IPI to the next rt overloaded queue */ + raw_spin_lock(&rt_rq->push_lock); + /* + * If the source queue changed since the IPI went out, + * we need to restart the search from that CPU again. + */ + if (rt_rq->push_flags & RT_PUSH_IPI_RESTART) { + rt_rq->push_flags &= ~RT_PUSH_IPI_RESTART; + rt_rq->push_cpu = src_rq->cpu; + } + + cpu = find_next_push_cpu(src_rq); + + if (cpu >= nr_cpu_ids) + rt_rq->push_flags &= ~RT_PUSH_IPI_EXECUTING; + raw_spin_unlock(&rt_rq->push_lock); + + if (cpu >= nr_cpu_ids) + return; + + /* + * It is possible that a restart caused this CPU to be + * chosen again. Don't bother with an IPI, just see if we + * have more to push. + */ + if (unlikely(cpu == rq->cpu)) + goto again; + + /* Try the next RT overloaded CPU */ + irq_work_queue_on(&rt_rq->push_work, cpu); +} + +static void push_irq_work_func(struct irq_work *work) +{ + struct rt_rq *rt_rq = container_of(work, struct rt_rq, push_work); + + try_to_push_tasks(rt_rq); +} +#endif /* HAVE_RT_PUSH_IPI */ + static int pull_rt_task(struct rq *this_rq) { int this_cpu = this_rq->cpu, ret = 0, cpu; @@ -1793,6 +1963,13 @@ static int pull_rt_task(struct rq *this_rq) */ smp_rmb(); +#ifdef HAVE_RT_PUSH_IPI + if (sched_feat(RT_PUSH_IPI)) { + tell_cpu_to_push(this_rq); + return 0; + } +#endif + for_each_cpu(cpu, this_rq->rd->rto_mask) { if (this_cpu == cpu) continue; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index dc0f435a2779..e0e129993958 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -6,6 +6,7 @@ #include <linux/mutex.h> #include <linux/spinlock.h> #include <linux/stop_machine.h> +#include <linux/irq_work.h> #include <linux/tick.h> #include <linux/slab.h> @@ -362,8 +363,14 @@ struct cfs_rq { * Under CFS, load is tracked on a per-entity basis and aggregated up. * This allows for the description of both thread and group usage (in * the FAIR_GROUP_SCHED case). + * runnable_load_avg is the sum of the load_avg_contrib of the + * sched_entities on the rq. + * blocked_load_avg is similar to runnable_load_avg except that its + * the blocked sched_entities on the rq. + * utilization_load_avg is the sum of the average running time of the + * sched_entities on the rq. */ - unsigned long runnable_load_avg, blocked_load_avg; + unsigned long runnable_load_avg, blocked_load_avg, utilization_load_avg; atomic64_t decay_counter; u64 last_decay; atomic_long_t removed_load; @@ -418,6 +425,11 @@ static inline int rt_bandwidth_enabled(void) return sysctl_sched_rt_runtime >= 0; } +/* RT IPI pull logic requires IRQ_WORK */ +#ifdef CONFIG_IRQ_WORK +# define HAVE_RT_PUSH_IPI +#endif + /* Real-Time classes' related field in a runqueue: */ struct rt_rq { struct rt_prio_array active; @@ -435,7 +447,13 @@ struct rt_rq { unsigned long rt_nr_total; int overloaded; struct plist_head pushable_tasks; +#ifdef HAVE_RT_PUSH_IPI + int push_flags; + int push_cpu; + struct irq_work push_work; + raw_spinlock_t push_lock; #endif +#endif /* CONFIG_SMP */ int rt_queued; int rt_throttled; @@ -597,6 +615,7 @@ struct rq { struct sched_domain *sd; unsigned long cpu_capacity; + unsigned long cpu_capacity_orig; unsigned char idle_balance; /* For active balancing */ @@ -807,7 +826,7 @@ struct sched_group_capacity { * CPU capacity of this group, SCHED_LOAD_SCALE being max capacity * for a single CPU. */ - unsigned int capacity, capacity_orig; + unsigned int capacity; unsigned long next_update; int imbalance; /* XXX unrelated to capacity but shared group state */ /* @@ -1368,9 +1387,18 @@ static inline int hrtick_enabled(struct rq *rq) #ifdef CONFIG_SMP extern void sched_avg_update(struct rq *rq); + +#ifndef arch_scale_freq_capacity +static __always_inline +unsigned long arch_scale_freq_capacity(struct sched_domain *sd, int cpu) +{ + return SCHED_CAPACITY_SCALE; +} +#endif + static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) { - rq->rt_avg += rt_delta; + rq->rt_avg += rt_delta * arch_scale_freq_capacity(NULL, cpu_of(rq)); sched_avg_update(rq); } #else @@ -1643,8 +1671,8 @@ extern void print_rt_stats(struct seq_file *m, int cpu); extern void print_dl_stats(struct seq_file *m, int cpu); extern void init_cfs_rq(struct cfs_rq *cfs_rq); -extern void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq); -extern void init_dl_rq(struct dl_rq *dl_rq, struct rq *rq); +extern void init_rt_rq(struct rt_rq *rt_rq); +extern void init_dl_rq(struct dl_rq *dl_rq); extern void cfs_bandwidth_usage_inc(void); extern void cfs_bandwidth_usage_dec(void); diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig index d626dc98e8df..579ce1b929af 100644 --- a/kernel/time/Kconfig +++ b/kernel/time/Kconfig @@ -33,12 +33,6 @@ config ARCH_USES_GETTIMEOFFSET config GENERIC_CLOCKEVENTS bool -# Migration helper. Builds, but does not invoke -config GENERIC_CLOCKEVENTS_BUILD - bool - default y - depends on GENERIC_CLOCKEVENTS - # Architecture can handle broadcast in a driver-agnostic way config ARCH_HAS_TICK_BROADCAST bool diff --git a/kernel/time/Makefile b/kernel/time/Makefile index c09c07817d7a..01f0312419b3 100644 --- a/kernel/time/Makefile +++ b/kernel/time/Makefile @@ -2,15 +2,13 @@ obj-y += time.o timer.o hrtimer.o itimer.o posix-timers.o posix-cpu-timers.o obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o obj-y += timeconv.o timecounter.o posix-clock.o alarmtimer.o -obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD) += clockevents.o -obj-$(CONFIG_GENERIC_CLOCKEVENTS) += tick-common.o +obj-$(CONFIG_GENERIC_CLOCKEVENTS) += clockevents.o tick-common.o ifeq ($(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST),y) obj-y += tick-broadcast.o obj-$(CONFIG_TICK_ONESHOT) += tick-broadcast-hrtimer.o endif obj-$(CONFIG_GENERIC_SCHED_CLOCK) += sched_clock.o -obj-$(CONFIG_TICK_ONESHOT) += tick-oneshot.o -obj-$(CONFIG_TICK_ONESHOT) += tick-sched.o +obj-$(CONFIG_TICK_ONESHOT) += tick-oneshot.o tick-sched.o obj-$(CONFIG_TIMER_STATS) += timer_stats.o obj-$(CONFIG_DEBUG_FS) += timekeeping_debug.o obj-$(CONFIG_TEST_UDELAY) += test_udelay.o diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 55449909f114..25d942d1da27 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -94,25 +94,76 @@ u64 clockevent_delta2ns(unsigned long latch, struct clock_event_device *evt) } EXPORT_SYMBOL_GPL(clockevent_delta2ns); +static int __clockevents_set_state(struct clock_event_device *dev, + enum clock_event_state state) +{ + /* Transition with legacy set_mode() callback */ + if (dev->set_mode) { + /* Legacy callback doesn't support new modes */ + if (state > CLOCK_EVT_STATE_ONESHOT) + return -ENOSYS; + /* + * 'clock_event_state' and 'clock_event_mode' have 1-to-1 + * mapping until *_ONESHOT, and so a simple cast will work. + */ + dev->set_mode((enum clock_event_mode)state, dev); + dev->mode = (enum clock_event_mode)state; + return 0; + } + + if (dev->features & CLOCK_EVT_FEAT_DUMMY) + return 0; + + /* Transition with new state-specific callbacks */ + switch (state) { + case CLOCK_EVT_STATE_DETACHED: + /* + * This is an internal state, which is guaranteed to go from + * SHUTDOWN to DETACHED. No driver interaction required. + */ + return 0; + + case CLOCK_EVT_STATE_SHUTDOWN: + return dev->set_state_shutdown(dev); + + case CLOCK_EVT_STATE_PERIODIC: + /* Core internal bug */ + if (!(dev->features & CLOCK_EVT_FEAT_PERIODIC)) + return -ENOSYS; + return dev->set_state_periodic(dev); + + case CLOCK_EVT_STATE_ONESHOT: + /* Core internal bug */ + if (!(dev->features & CLOCK_EVT_FEAT_ONESHOT)) + return -ENOSYS; + return dev->set_state_oneshot(dev); + + default: + return -ENOSYS; + } +} + /** - * clockevents_set_mode - set the operating mode of a clock event device + * clockevents_set_state - set the operating state of a clock event device * @dev: device to modify - * @mode: new mode + * @state: new state * * Must be called with interrupts disabled ! */ -void clockevents_set_mode(struct clock_event_device *dev, - enum clock_event_mode mode) +void clockevents_set_state(struct clock_event_device *dev, + enum clock_event_state state) { - if (dev->mode != mode) { - dev->set_mode(mode, dev); - dev->mode = mode; + if (dev->state != state) { + if (__clockevents_set_state(dev, state)) + return; + + dev->state = state; /* * A nsec2cyc multiplicator of 0 is invalid and we'd crash * on it, so fix it up and emit a warning: */ - if (mode == CLOCK_EVT_MODE_ONESHOT) { + if (state == CLOCK_EVT_STATE_ONESHOT) { if (unlikely(!dev->mult)) { dev->mult = 1; WARN_ON(1); @@ -127,10 +178,28 @@ void clockevents_set_mode(struct clock_event_device *dev, */ void clockevents_shutdown(struct clock_event_device *dev) { - clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN); + clockevents_set_state(dev, CLOCK_EVT_STATE_SHUTDOWN); dev->next_event.tv64 = KTIME_MAX; } +/** + * clockevents_tick_resume - Resume the tick device before using it again + * @dev: device to resume + */ +int clockevents_tick_resume(struct clock_event_device *dev) +{ + int ret = 0; + + if (dev->set_mode) { + dev->set_mode(CLOCK_EVT_MODE_RESUME, dev); + dev->mode = CLOCK_EVT_MODE_RESUME; + } else if (dev->tick_resume) { + ret = dev->tick_resume(dev); + } + + return ret; +} + #ifdef CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST /* Limit min_delta to a jiffie */ @@ -183,7 +252,7 @@ static int clockevents_program_min_delta(struct clock_event_device *dev) delta = dev->min_delta_ns; dev->next_event = ktime_add_ns(ktime_get(), delta); - if (dev->mode == CLOCK_EVT_MODE_SHUTDOWN) + if (dev->state == CLOCK_EVT_STATE_SHUTDOWN) return 0; dev->retries++; @@ -220,7 +289,7 @@ static int clockevents_program_min_delta(struct clock_event_device *dev) delta = dev->min_delta_ns; dev->next_event = ktime_add_ns(ktime_get(), delta); - if (dev->mode == CLOCK_EVT_MODE_SHUTDOWN) + if (dev->state == CLOCK_EVT_STATE_SHUTDOWN) return 0; dev->retries++; @@ -252,7 +321,7 @@ int clockevents_program_event(struct clock_event_device *dev, ktime_t expires, dev->next_event = expires; - if (dev->mode == CLOCK_EVT_MODE_SHUTDOWN) + if (dev->state == CLOCK_EVT_STATE_SHUTDOWN) return 0; /* Shortcut for clockevent devices that can deal with ktime. */ @@ -297,7 +366,7 @@ static int clockevents_replace(struct clock_event_device *ced) struct clock_event_device *dev, *newdev = NULL; list_for_each_entry(dev, &clockevent_devices, list) { - if (dev == ced || dev->mode != CLOCK_EVT_MODE_UNUSED) + if (dev == ced || dev->state != CLOCK_EVT_STATE_DETACHED) continue; if (!tick_check_replacement(newdev, dev)) @@ -323,7 +392,7 @@ static int clockevents_replace(struct clock_event_device *ced) static int __clockevents_try_unbind(struct clock_event_device *ced, int cpu) { /* Fast track. Device is unused */ - if (ced->mode == CLOCK_EVT_MODE_UNUSED) { + if (ced->state == CLOCK_EVT_STATE_DETACHED) { list_del_init(&ced->list); return 0; } @@ -373,6 +442,37 @@ int clockevents_unbind_device(struct clock_event_device *ced, int cpu) } EXPORT_SYMBOL_GPL(clockevents_unbind); +/* Sanity check of state transition callbacks */ +static int clockevents_sanity_check(struct clock_event_device *dev) +{ + /* Legacy set_mode() callback */ + if (dev->set_mode) { + /* We shouldn't be supporting new modes now */ + WARN_ON(dev->set_state_periodic || dev->set_state_oneshot || + dev->set_state_shutdown || dev->tick_resume); + + BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED); + return 0; + } + + if (dev->features & CLOCK_EVT_FEAT_DUMMY) + return 0; + + /* New state-specific callbacks */ + if (!dev->set_state_shutdown) + return -EINVAL; + + if ((dev->features & CLOCK_EVT_FEAT_PERIODIC) && + !dev->set_state_periodic) + return -EINVAL; + + if ((dev->features & CLOCK_EVT_FEAT_ONESHOT) && + !dev->set_state_oneshot) + return -EINVAL; + + return 0; +} + /** * clockevents_register_device - register a clock event device * @dev: device to register @@ -381,7 +481,11 @@ void clockevents_register_device(struct clock_event_device *dev) { unsigned long flags; - BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED); + BUG_ON(clockevents_sanity_check(dev)); + + /* Initialize state to DETACHED */ + dev->state = CLOCK_EVT_STATE_DETACHED; + if (!dev->cpumask) { WARN_ON(num_possible_cpus() > 1); dev->cpumask = cpumask_of(smp_processor_id()); @@ -445,11 +549,11 @@ int __clockevents_update_freq(struct clock_event_device *dev, u32 freq) { clockevents_config(dev, freq); - if (dev->mode == CLOCK_EVT_MODE_ONESHOT) + if (dev->state == CLOCK_EVT_STATE_ONESHOT) return clockevents_program_event(dev, dev->next_event, false); - if (dev->mode == CLOCK_EVT_MODE_PERIODIC) - dev->set_mode(CLOCK_EVT_MODE_PERIODIC, dev); + if (dev->state == CLOCK_EVT_STATE_PERIODIC) + return __clockevents_set_state(dev, CLOCK_EVT_STATE_PERIODIC); return 0; } @@ -491,30 +595,27 @@ void clockevents_handle_noop(struct clock_event_device *dev) * @old: device to release (can be NULL) * @new: device to request (can be NULL) * - * Called from the notifier chain. clockevents_lock is held already + * Called from various tick functions with clockevents_lock held and + * interrupts disabled. */ void clockevents_exchange_device(struct clock_event_device *old, struct clock_event_device *new) { - unsigned long flags; - - local_irq_save(flags); /* * Caller releases a clock event device. We queue it into the * released list and do a notify add later. */ if (old) { module_put(old->owner); - clockevents_set_mode(old, CLOCK_EVT_MODE_UNUSED); + clockevents_set_state(old, CLOCK_EVT_STATE_DETACHED); list_del(&old->list); list_add(&old->list, &clockevents_released); } if (new) { - BUG_ON(new->mode != CLOCK_EVT_MODE_UNUSED); + BUG_ON(new->state != CLOCK_EVT_STATE_DETACHED); clockevents_shutdown(new); } - local_irq_restore(flags); } /** @@ -541,74 +642,40 @@ void clockevents_resume(void) dev->resume(dev); } -#ifdef CONFIG_GENERIC_CLOCKEVENTS +#ifdef CONFIG_HOTPLUG_CPU /** - * clockevents_notify - notification about relevant events - * Returns 0 on success, any other value on error + * tick_cleanup_dead_cpu - Cleanup the tick and clockevents of a dead cpu */ -int clockevents_notify(unsigned long reason, void *arg) +void tick_cleanup_dead_cpu(int cpu) { struct clock_event_device *dev, *tmp; unsigned long flags; - int cpu, ret = 0; raw_spin_lock_irqsave(&clockevents_lock, flags); - switch (reason) { - case CLOCK_EVT_NOTIFY_BROADCAST_ON: - case CLOCK_EVT_NOTIFY_BROADCAST_OFF: - case CLOCK_EVT_NOTIFY_BROADCAST_FORCE: - tick_broadcast_on_off(reason, arg); - break; - - case CLOCK_EVT_NOTIFY_BROADCAST_ENTER: - case CLOCK_EVT_NOTIFY_BROADCAST_EXIT: - ret = tick_broadcast_oneshot_control(reason); - break; - - case CLOCK_EVT_NOTIFY_CPU_DYING: - tick_handover_do_timer(arg); - break; - - case CLOCK_EVT_NOTIFY_SUSPEND: - tick_suspend(); - tick_suspend_broadcast(); - break; - - case CLOCK_EVT_NOTIFY_RESUME: - tick_resume(); - break; - - case CLOCK_EVT_NOTIFY_CPU_DEAD: - tick_shutdown_broadcast_oneshot(arg); - tick_shutdown_broadcast(arg); - tick_shutdown(arg); - /* - * Unregister the clock event devices which were - * released from the users in the notify chain. - */ - list_for_each_entry_safe(dev, tmp, &clockevents_released, list) + tick_shutdown_broadcast_oneshot(cpu); + tick_shutdown_broadcast(cpu); + tick_shutdown(cpu); + /* + * Unregister the clock event devices which were + * released from the users in the notify chain. + */ + list_for_each_entry_safe(dev, tmp, &clockevents_released, list) + list_del(&dev->list); + /* + * Now check whether the CPU has left unused per cpu devices + */ + list_for_each_entry_safe(dev, tmp, &clockevent_devices, list) { + if (cpumask_test_cpu(cpu, dev->cpumask) && + cpumask_weight(dev->cpumask) == 1 && + !tick_is_broadcast_device(dev)) { + BUG_ON(dev->state != CLOCK_EVT_STATE_DETACHED); list_del(&dev->list); - /* - * Now check whether the CPU has left unused per cpu devices - */ - cpu = *((int *)arg); - list_for_each_entry_safe(dev, tmp, &clockevent_devices, list) { - if (cpumask_test_cpu(cpu, dev->cpumask) && - cpumask_weight(dev->cpumask) == 1 && - !tick_is_broadcast_device(dev)) { - BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED); - list_del(&dev->list); - } } - break; - default: - break; } raw_spin_unlock_irqrestore(&clockevents_lock, flags); - return ret; } -EXPORT_SYMBOL_GPL(clockevents_notify); +#endif #ifdef CONFIG_SYSFS struct bus_type clockevents_subsys = { @@ -727,5 +794,3 @@ static int __init clockevents_init_sysfs(void) } device_initcall(clockevents_init_sysfs); #endif /* SYSFS */ - -#endif /* GENERIC_CLOCK_EVENTS */ diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 4892352f0e49..15facb1b9c60 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -142,13 +142,6 @@ static void __clocksource_unstable(struct clocksource *cs) schedule_work(&watchdog_work); } -static void clocksource_unstable(struct clocksource *cs, int64_t delta) -{ - printk(KERN_WARNING "Clocksource %s unstable (delta = %Ld ns)\n", - cs->name, delta); - __clocksource_unstable(cs); -} - /** * clocksource_mark_unstable - mark clocksource unstable via watchdog * @cs: clocksource to be marked unstable @@ -174,7 +167,7 @@ void clocksource_mark_unstable(struct clocksource *cs) static void clocksource_watchdog(unsigned long data) { struct clocksource *cs; - cycle_t csnow, wdnow, delta; + cycle_t csnow, wdnow, cslast, wdlast, delta; int64_t wd_nsec, cs_nsec; int next_cpu, reset_pending; @@ -213,6 +206,8 @@ static void clocksource_watchdog(unsigned long data) delta = clocksource_delta(csnow, cs->cs_last, cs->mask); cs_nsec = clocksource_cyc2ns(delta, cs->mult, cs->shift); + wdlast = cs->wd_last; /* save these in case we print them */ + cslast = cs->cs_last; cs->cs_last = csnow; cs->wd_last = wdnow; @@ -221,7 +216,12 @@ static void clocksource_watchdog(unsigned long data) /* Check the deviation from the watchdog clocksource. */ if ((abs(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD)) { - clocksource_unstable(cs, cs_nsec - wd_nsec); + pr_warn("timekeeping watchdog: Marking clocksource '%s' as unstable, because the skew is too large:\n", cs->name); + pr_warn(" '%s' wd_now: %llx wd_last: %llx mask: %llx\n", + watchdog->name, wdnow, wdlast, watchdog->mask); + pr_warn(" '%s' cs_now: %llx cs_last: %llx mask: %llx\n", + cs->name, csnow, cslast, cs->mask); + __clocksource_unstable(cs); continue; } @@ -469,26 +469,25 @@ static u32 clocksource_max_adjustment(struct clocksource *cs) * @shift: cycle to nanosecond divisor (power of two) * @maxadj: maximum adjustment value to mult (~11%) * @mask: bitmask for two's complement subtraction of non 64 bit counters + * @max_cyc: maximum cycle value before potential overflow (does not include + * any safety margin) + * + * NOTE: This function includes a safety margin of 50%, in other words, we + * return half the number of nanoseconds the hardware counter can technically + * cover. This is done so that we can potentially detect problems caused by + * delayed timers or bad hardware, which might result in time intervals that + * are larger then what the math used can handle without overflows. */ -u64 clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask) +u64 clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask, u64 *max_cyc) { u64 max_nsecs, max_cycles; /* * Calculate the maximum number of cycles that we can pass to the - * cyc2ns function without overflowing a 64-bit signed result. The - * maximum number of cycles is equal to ULLONG_MAX/(mult+maxadj) - * which is equivalent to the below. - * max_cycles < (2^63)/(mult + maxadj) - * max_cycles < 2^(log2((2^63)/(mult + maxadj))) - * max_cycles < 2^(log2(2^63) - log2(mult + maxadj)) - * max_cycles < 2^(63 - log2(mult + maxadj)) - * max_cycles < 1 << (63 - log2(mult + maxadj)) - * Please note that we add 1 to the result of the log2 to account for - * any rounding errors, ensure the above inequality is satisfied and - * no overflow will occur. + * cyc2ns() function without overflowing a 64-bit result. */ - max_cycles = 1ULL << (63 - (ilog2(mult + maxadj) + 1)); + max_cycles = ULLONG_MAX; + do_div(max_cycles, mult+maxadj); /* * The actual maximum number of cycles we can defer the clocksource is @@ -499,27 +498,26 @@ u64 clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask) max_cycles = min(max_cycles, mask); max_nsecs = clocksource_cyc2ns(max_cycles, mult - maxadj, shift); + /* return the max_cycles value as well if requested */ + if (max_cyc) + *max_cyc = max_cycles; + + /* Return 50% of the actual maximum, so we can detect bad values */ + max_nsecs >>= 1; + return max_nsecs; } /** - * clocksource_max_deferment - Returns max time the clocksource can be deferred - * @cs: Pointer to clocksource + * clocksource_update_max_deferment - Updates the clocksource max_idle_ns & max_cycles + * @cs: Pointer to clocksource to be updated * */ -static u64 clocksource_max_deferment(struct clocksource *cs) +static inline void clocksource_update_max_deferment(struct clocksource *cs) { - u64 max_nsecs; - - max_nsecs = clocks_calc_max_nsecs(cs->mult, cs->shift, cs->maxadj, - cs->mask); - /* - * To ensure that the clocksource does not wrap whilst we are idle, - * limit the time the clocksource can be deferred by 12.5%. Please - * note a margin of 12.5% is used because this can be computed with - * a shift, versus say 10% which would require division. - */ - return max_nsecs - (max_nsecs >> 3); + cs->max_idle_ns = clocks_calc_max_nsecs(cs->mult, cs->shift, + cs->maxadj, cs->mask, + &cs->max_cycles); } #ifndef CONFIG_ARCH_USES_GETTIMEOFFSET @@ -648,7 +646,7 @@ static void clocksource_enqueue(struct clocksource *cs) } /** - * __clocksource_updatefreq_scale - Used update clocksource with new freq + * __clocksource_update_freq_scale - Used update clocksource with new freq * @cs: clocksource to be registered * @scale: Scale factor multiplied against freq to get clocksource hz * @freq: clocksource frequency (cycles per second) divided by scale @@ -656,48 +654,64 @@ static void clocksource_enqueue(struct clocksource *cs) * This should only be called from the clocksource->enable() method. * * This *SHOULD NOT* be called directly! Please use the - * clocksource_updatefreq_hz() or clocksource_updatefreq_khz helper functions. + * __clocksource_update_freq_hz() or __clocksource_update_freq_khz() helper + * functions. */ -void __clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq) +void __clocksource_update_freq_scale(struct clocksource *cs, u32 scale, u32 freq) { u64 sec; + /* - * Calc the maximum number of seconds which we can run before - * wrapping around. For clocksources which have a mask > 32bit - * we need to limit the max sleep time to have a good - * conversion precision. 10 minutes is still a reasonable - * amount. That results in a shift value of 24 for a - * clocksource with mask >= 40bit and f >= 4GHz. That maps to - * ~ 0.06ppm granularity for NTP. We apply the same 12.5% - * margin as we do in clocksource_max_deferment() + * Default clocksources are *special* and self-define their mult/shift. + * But, you're not special, so you should specify a freq value. */ - sec = (cs->mask - (cs->mask >> 3)); - do_div(sec, freq); - do_div(sec, scale); - if (!sec) - sec = 1; - else if (sec > 600 && cs->mask > UINT_MAX) - sec = 600; - - clocks_calc_mult_shift(&cs->mult, &cs->shift, freq, - NSEC_PER_SEC / scale, sec * scale); - + if (freq) { + /* + * Calc the maximum number of seconds which we can run before + * wrapping around. For clocksources which have a mask > 32-bit + * we need to limit the max sleep time to have a good + * conversion precision. 10 minutes is still a reasonable + * amount. That results in a shift value of 24 for a + * clocksource with mask >= 40-bit and f >= 4GHz. That maps to + * ~ 0.06ppm granularity for NTP. + */ + sec = cs->mask; + do_div(sec, freq); + do_div(sec, scale); + if (!sec) + sec = 1; + else if (sec > 600 && cs->mask > UINT_MAX) + sec = 600; + + clocks_calc_mult_shift(&cs->mult, &cs->shift, freq, + NSEC_PER_SEC / scale, sec * scale); + } /* - * for clocksources that have large mults, to avoid overflow. - * Since mult may be adjusted by ntp, add an safety extra margin - * + * Ensure clocksources that have large 'mult' values don't overflow + * when adjusted. */ cs->maxadj = clocksource_max_adjustment(cs); - while ((cs->mult + cs->maxadj < cs->mult) - || (cs->mult - cs->maxadj > cs->mult)) { + while (freq && ((cs->mult + cs->maxadj < cs->mult) + || (cs->mult - cs->maxadj > cs->mult))) { cs->mult >>= 1; cs->shift--; cs->maxadj = clocksource_max_adjustment(cs); } - cs->max_idle_ns = clocksource_max_deferment(cs); + /* + * Only warn for *special* clocksources that self-define + * their mult/shift values and don't specify a freq. + */ + WARN_ONCE(cs->mult + cs->maxadj < cs->mult, + "timekeeping: Clocksource %s might overflow on 11%% adjustment\n", + cs->name); + + clocksource_update_max_deferment(cs); + + pr_info("clocksource %s: mask: 0x%llx max_cycles: 0x%llx, max_idle_ns: %lld ns\n", + cs->name, cs->mask, cs->max_cycles, cs->max_idle_ns); } -EXPORT_SYMBOL_GPL(__clocksource_updatefreq_scale); +EXPORT_SYMBOL_GPL(__clocksource_update_freq_scale); /** * __clocksource_register_scale - Used to install new clocksources @@ -714,7 +728,7 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq) { /* Initialize mult/shift and max_idle_ns */ - __clocksource_updatefreq_scale(cs, scale, freq); + __clocksource_update_freq_scale(cs, scale, freq); /* Add clocksource to the clocksource list */ mutex_lock(&clocksource_mutex); @@ -726,33 +740,6 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq) } EXPORT_SYMBOL_GPL(__clocksource_register_scale); - -/** - * clocksource_register - Used to install new clocksources - * @cs: clocksource to be registered - * - * Returns -EBUSY if registration fails, zero otherwise. - */ -int clocksource_register(struct clocksource *cs) -{ - /* calculate max adjustment for given mult/shift */ - cs->maxadj = clocksource_max_adjustment(cs); - WARN_ONCE(cs->mult + cs->maxadj < cs->mult, - "Clocksource %s might overflow on 11%% adjustment\n", - cs->name); - - /* calculate max idle time permitted for this clocksource */ - cs->max_idle_ns = clocksource_max_deferment(cs); - - mutex_lock(&clocksource_mutex); - clocksource_enqueue(cs); - clocksource_enqueue_watchdog(cs); - clocksource_select(); - mutex_unlock(&clocksource_mutex); - return 0; -} -EXPORT_SYMBOL(clocksource_register); - static void __clocksource_change_rating(struct clocksource *cs, int rating) { list_del(&cs->list); diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index bee0c1f78091..76d4bd962b19 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -54,7 +54,7 @@ #include <trace/events/timer.h> -#include "timekeeping.h" +#include "tick-internal.h" /* * The timer bases: @@ -1707,17 +1707,10 @@ static int hrtimer_cpu_notify(struct notifier_block *self, break; #ifdef CONFIG_HOTPLUG_CPU - case CPU_DYING: - case CPU_DYING_FROZEN: - clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DYING, &scpu); - break; case CPU_DEAD: case CPU_DEAD_FROZEN: - { - clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DEAD, &scpu); migrate_hrtimers(scpu); break; - } #endif default: diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c index a6a5bf53e86d..347fecf86a3f 100644 --- a/kernel/time/jiffies.c +++ b/kernel/time/jiffies.c @@ -25,7 +25,7 @@ #include <linux/module.h> #include <linux/init.h> -#include "tick-internal.h" +#include "timekeeping.h" /* The Jiffies based clocksource is the lowest common * denominator clock source which should function on @@ -71,6 +71,7 @@ static struct clocksource clocksource_jiffies = { .mask = 0xffffffff, /*32bits*/ .mult = NSEC_PER_JIFFY << JIFFIES_SHIFT, /* details above */ .shift = JIFFIES_SHIFT, + .max_cycles = 10, }; __cacheline_aligned_in_smp DEFINE_SEQLOCK(jiffies_lock); @@ -94,7 +95,7 @@ EXPORT_SYMBOL(jiffies); static int __init init_jiffies_clocksource(void) { - return clocksource_register(&clocksource_jiffies); + return __clocksource_register(&clocksource_jiffies); } core_initcall(init_jiffies_clocksource); @@ -130,6 +131,6 @@ int register_refined_jiffies(long cycles_per_second) refined_jiffies.mult = ((u32)nsec_per_tick) << JIFFIES_SHIFT; - clocksource_register(&refined_jiffies); + __clocksource_register(&refined_jiffies); return 0; } diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 0f60b08a4f07..7a681003001c 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -17,7 +17,6 @@ #include <linux/module.h> #include <linux/rtc.h> -#include "tick-internal.h" #include "ntp_internal.h" /* @@ -459,6 +458,16 @@ out: return leap; } +#ifdef CONFIG_GENERIC_CMOS_UPDATE +int __weak update_persistent_clock64(struct timespec64 now64) +{ + struct timespec now; + + now = timespec64_to_timespec(now64); + return update_persistent_clock(now); +} +#endif + #if defined(CONFIG_GENERIC_CMOS_UPDATE) || defined(CONFIG_RTC_SYSTOHC) static void sync_cmos_clock(struct work_struct *work); @@ -494,8 +503,9 @@ static void sync_cmos_clock(struct work_struct *work) if (persistent_clock_is_local) adjust.tv_sec -= (sys_tz.tz_minuteswest * 60); #ifdef CONFIG_GENERIC_CMOS_UPDATE - fail = update_persistent_clock(timespec64_to_timespec(adjust)); + fail = update_persistent_clock64(adjust); #endif + #ifdef CONFIG_RTC_SYSTOHC if (fail == -ENODEV) fail = rtc_set_ntp_time(adjust); diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c index 01d2d15aa662..a26036d37a38 100644 --- a/kernel/time/sched_clock.c +++ b/kernel/time/sched_clock.c @@ -1,5 +1,6 @@ /* - * sched_clock.c: support for extending counters to full 64-bit ns counter + * sched_clock.c: Generic sched_clock() support, to extend low level + * hardware time counters to full 64-bit ns values. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -18,15 +19,53 @@ #include <linux/seqlock.h> #include <linux/bitops.h> -struct clock_data { - ktime_t wrap_kt; +/** + * struct clock_read_data - data required to read from sched_clock() + * + * @epoch_ns: sched_clock() value at last update + * @epoch_cyc: Clock cycle value at last update. + * @sched_clock_mask: Bitmask for two's complement subtraction of non 64bit + * clocks. + * @read_sched_clock: Current clock source (or dummy source when suspended). + * @mult: Multipler for scaled math conversion. + * @shift: Shift value for scaled math conversion. + * + * Care must be taken when updating this structure; it is read by + * some very hot code paths. It occupies <=40 bytes and, when combined + * with the seqcount used to synchronize access, comfortably fits into + * a 64 byte cache line. + */ +struct clock_read_data { u64 epoch_ns; u64 epoch_cyc; - seqcount_t seq; - unsigned long rate; + u64 sched_clock_mask; + u64 (*read_sched_clock)(void); u32 mult; u32 shift; - bool suspended; +}; + +/** + * struct clock_data - all data needed for sched_clock() (including + * registration of a new clock source) + * + * @seq: Sequence counter for protecting updates. The lowest + * bit is the index for @read_data. + * @read_data: Data required to read from sched_clock. + * @wrap_kt: Duration for which clock can run before wrapping. + * @rate: Tick rate of the registered clock. + * @actual_read_sched_clock: Registered hardware level clock read function. + * + * The ordering of this structure has been chosen to optimize cache + * performance. In particular 'seq' and 'read_data[0]' (combined) should fit + * into a single 64-byte cache line. + */ +struct clock_data { + seqcount_t seq; + struct clock_read_data read_data[2]; + ktime_t wrap_kt; + unsigned long rate; + + u64 (*actual_read_sched_clock)(void); }; static struct hrtimer sched_clock_timer; @@ -34,12 +73,6 @@ static int irqtime = -1; core_param(irqtime, irqtime, int, 0400); -static struct clock_data cd = { - .mult = NSEC_PER_SEC / HZ, -}; - -static u64 __read_mostly sched_clock_mask; - static u64 notrace jiffy_sched_clock_read(void) { /* @@ -49,7 +82,11 @@ static u64 notrace jiffy_sched_clock_read(void) return (u64)(jiffies - INITIAL_JIFFIES); } -static u64 __read_mostly (*read_sched_clock)(void) = jiffy_sched_clock_read; +static struct clock_data cd ____cacheline_aligned = { + .read_data[0] = { .mult = NSEC_PER_SEC / HZ, + .read_sched_clock = jiffy_sched_clock_read, }, + .actual_read_sched_clock = jiffy_sched_clock_read, +}; static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift) { @@ -58,111 +95,136 @@ static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift) unsigned long long notrace sched_clock(void) { - u64 epoch_ns; - u64 epoch_cyc; - u64 cyc; + u64 cyc, res; unsigned long seq; - - if (cd.suspended) - return cd.epoch_ns; + struct clock_read_data *rd; do { - seq = raw_read_seqcount_begin(&cd.seq); - epoch_cyc = cd.epoch_cyc; - epoch_ns = cd.epoch_ns; + seq = raw_read_seqcount(&cd.seq); + rd = cd.read_data + (seq & 1); + + cyc = (rd->read_sched_clock() - rd->epoch_cyc) & + rd->sched_clock_mask; + res = rd->epoch_ns + cyc_to_ns(cyc, rd->mult, rd->shift); } while (read_seqcount_retry(&cd.seq, seq)); - cyc = read_sched_clock(); - cyc = (cyc - epoch_cyc) & sched_clock_mask; - return epoch_ns + cyc_to_ns(cyc, cd.mult, cd.shift); + return res; +} + +/* + * Updating the data required to read the clock. + * + * sched_clock() will never observe mis-matched data even if called from + * an NMI. We do this by maintaining an odd/even copy of the data and + * steering sched_clock() to one or the other using a sequence counter. + * In order to preserve the data cache profile of sched_clock() as much + * as possible the system reverts back to the even copy when the update + * completes; the odd copy is used *only* during an update. + */ +static void update_clock_read_data(struct clock_read_data *rd) +{ + /* update the backup (odd) copy with the new data */ + cd.read_data[1] = *rd; + + /* steer readers towards the odd copy */ + raw_write_seqcount_latch(&cd.seq); + + /* now its safe for us to update the normal (even) copy */ + cd.read_data[0] = *rd; + + /* switch readers back to the even copy */ + raw_write_seqcount_latch(&cd.seq); } /* - * Atomically update the sched_clock epoch. + * Atomically update the sched_clock() epoch. */ -static void notrace update_sched_clock(void) +static void update_sched_clock(void) { - unsigned long flags; u64 cyc; u64 ns; + struct clock_read_data rd; + + rd = cd.read_data[0]; + + cyc = cd.actual_read_sched_clock(); + ns = rd.epoch_ns + cyc_to_ns((cyc - rd.epoch_cyc) & rd.sched_clock_mask, rd.mult, rd.shift); + + rd.epoch_ns = ns; + rd.epoch_cyc = cyc; - cyc = read_sched_clock(); - ns = cd.epoch_ns + - cyc_to_ns((cyc - cd.epoch_cyc) & sched_clock_mask, - cd.mult, cd.shift); - - raw_local_irq_save(flags); - raw_write_seqcount_begin(&cd.seq); - cd.epoch_ns = ns; - cd.epoch_cyc = cyc; - raw_write_seqcount_end(&cd.seq); - raw_local_irq_restore(flags); + update_clock_read_data(&rd); } static enum hrtimer_restart sched_clock_poll(struct hrtimer *hrt) { update_sched_clock(); hrtimer_forward_now(hrt, cd.wrap_kt); + return HRTIMER_RESTART; } -void __init sched_clock_register(u64 (*read)(void), int bits, - unsigned long rate) +void __init +sched_clock_register(u64 (*read)(void), int bits, unsigned long rate) { u64 res, wrap, new_mask, new_epoch, cyc, ns; u32 new_mult, new_shift; - ktime_t new_wrap_kt; unsigned long r; char r_unit; + struct clock_read_data rd; if (cd.rate > rate) return; WARN_ON(!irqs_disabled()); - /* calculate the mult/shift to convert counter ticks to ns. */ + /* Calculate the mult/shift to convert counter ticks to ns. */ clocks_calc_mult_shift(&new_mult, &new_shift, rate, NSEC_PER_SEC, 3600); new_mask = CLOCKSOURCE_MASK(bits); + cd.rate = rate; + + /* Calculate how many nanosecs until we risk wrapping */ + wrap = clocks_calc_max_nsecs(new_mult, new_shift, 0, new_mask, NULL); + cd.wrap_kt = ns_to_ktime(wrap); - /* calculate how many ns until we wrap */ - wrap = clocks_calc_max_nsecs(new_mult, new_shift, 0, new_mask); - new_wrap_kt = ns_to_ktime(wrap - (wrap >> 3)); + rd = cd.read_data[0]; - /* update epoch for new counter and update epoch_ns from old counter*/ + /* Update epoch for new counter and update 'epoch_ns' from old counter*/ new_epoch = read(); - cyc = read_sched_clock(); - ns = cd.epoch_ns + cyc_to_ns((cyc - cd.epoch_cyc) & sched_clock_mask, - cd.mult, cd.shift); + cyc = cd.actual_read_sched_clock(); + ns = rd.epoch_ns + cyc_to_ns((cyc - rd.epoch_cyc) & rd.sched_clock_mask, rd.mult, rd.shift); + cd.actual_read_sched_clock = read; - raw_write_seqcount_begin(&cd.seq); - read_sched_clock = read; - sched_clock_mask = new_mask; - cd.rate = rate; - cd.wrap_kt = new_wrap_kt; - cd.mult = new_mult; - cd.shift = new_shift; - cd.epoch_cyc = new_epoch; - cd.epoch_ns = ns; - raw_write_seqcount_end(&cd.seq); + rd.read_sched_clock = read; + rd.sched_clock_mask = new_mask; + rd.mult = new_mult; + rd.shift = new_shift; + rd.epoch_cyc = new_epoch; + rd.epoch_ns = ns; + + update_clock_read_data(&rd); r = rate; if (r >= 4000000) { r /= 1000000; r_unit = 'M'; - } else if (r >= 1000) { - r /= 1000; - r_unit = 'k'; - } else - r_unit = ' '; - - /* calculate the ns resolution of this counter */ + } else { + if (r >= 1000) { + r /= 1000; + r_unit = 'k'; + } else { + r_unit = ' '; + } + } + + /* Calculate the ns resolution of this counter */ res = cyc_to_ns(1ULL, new_mult, new_shift); pr_info("sched_clock: %u bits at %lu%cHz, resolution %lluns, wraps every %lluns\n", bits, r, r_unit, res, wrap); - /* Enable IRQ time accounting if we have a fast enough sched_clock */ + /* Enable IRQ time accounting if we have a fast enough sched_clock() */ if (irqtime > 0 || (irqtime == -1 && rate >= 1000000)) enable_sched_clock_irqtime(); @@ -172,10 +234,10 @@ void __init sched_clock_register(u64 (*read)(void), int bits, void __init sched_clock_postinit(void) { /* - * If no sched_clock function has been provided at that point, + * If no sched_clock() function has been provided at that point, * make it the final one one. */ - if (read_sched_clock == jiffy_sched_clock_read) + if (cd.actual_read_sched_clock == jiffy_sched_clock_read) sched_clock_register(jiffy_sched_clock_read, BITS_PER_LONG, HZ); update_sched_clock(); @@ -189,29 +251,53 @@ void __init sched_clock_postinit(void) hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL); } +/* + * Clock read function for use when the clock is suspended. + * + * This function makes it appear to sched_clock() as if the clock + * stopped counting at its last update. + * + * This function must only be called from the critical + * section in sched_clock(). It relies on the read_seqcount_retry() + * at the end of the critical section to be sure we observe the + * correct copy of 'epoch_cyc'. + */ +static u64 notrace suspended_sched_clock_read(void) +{ + unsigned long seq = raw_read_seqcount(&cd.seq); + + return cd.read_data[seq & 1].epoch_cyc; +} + static int sched_clock_suspend(void) { + struct clock_read_data *rd = &cd.read_data[0]; + update_sched_clock(); hrtimer_cancel(&sched_clock_timer); - cd.suspended = true; + rd->read_sched_clock = suspended_sched_clock_read; + return 0; } static void sched_clock_resume(void) { - cd.epoch_cyc = read_sched_clock(); + struct clock_read_data *rd = &cd.read_data[0]; + + rd->epoch_cyc = cd.actual_read_sched_clock(); hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL); - cd.suspended = false; + rd->read_sched_clock = cd.actual_read_sched_clock; } static struct syscore_ops sched_clock_ops = { - .suspend = sched_clock_suspend, - .resume = sched_clock_resume, + .suspend = sched_clock_suspend, + .resume = sched_clock_resume, }; static int __init sched_clock_syscore_init(void) { register_syscore_ops(&sched_clock_ops); + return 0; } device_initcall(sched_clock_syscore_init); diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index 066f0ec05e48..7e8ca4f448a8 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -33,12 +33,14 @@ static cpumask_var_t tick_broadcast_mask; static cpumask_var_t tick_broadcast_on; static cpumask_var_t tmpmask; static DEFINE_RAW_SPINLOCK(tick_broadcast_lock); -static int tick_broadcast_force; +static int tick_broadcast_forced; #ifdef CONFIG_TICK_ONESHOT static void tick_broadcast_clear_oneshot(int cpu); +static void tick_resume_broadcast_oneshot(struct clock_event_device *bc); #else static inline void tick_broadcast_clear_oneshot(int cpu) { } +static inline void tick_resume_broadcast_oneshot(struct clock_event_device *bc) { } #endif /* @@ -303,7 +305,7 @@ static void tick_handle_periodic_broadcast(struct clock_event_device *dev) /* * The device is in periodic mode. No reprogramming necessary: */ - if (dev->mode == CLOCK_EVT_MODE_PERIODIC) + if (dev->state == CLOCK_EVT_STATE_PERIODIC) goto unlock; /* @@ -324,49 +326,54 @@ unlock: raw_spin_unlock(&tick_broadcast_lock); } -/* - * Powerstate information: The system enters/leaves a state, where - * affected devices might stop +/** + * tick_broadcast_control - Enable/disable or force broadcast mode + * @mode: The selected broadcast mode + * + * Called when the system enters a state where affected tick devices + * might stop. Note: TICK_BROADCAST_FORCE cannot be undone. + * + * Called with interrupts disabled, so clockevents_lock is not + * required here because the local clock event device cannot go away + * under us. */ -static void tick_do_broadcast_on_off(unsigned long *reason) +void tick_broadcast_control(enum tick_broadcast_mode mode) { struct clock_event_device *bc, *dev; struct tick_device *td; - unsigned long flags; int cpu, bc_stopped; - raw_spin_lock_irqsave(&tick_broadcast_lock, flags); - - cpu = smp_processor_id(); - td = &per_cpu(tick_cpu_device, cpu); + td = this_cpu_ptr(&tick_cpu_device); dev = td->evtdev; - bc = tick_broadcast_device.evtdev; /* * Is the device not affected by the powerstate ? */ if (!dev || !(dev->features & CLOCK_EVT_FEAT_C3STOP)) - goto out; + return; if (!tick_device_is_functional(dev)) - goto out; + return; + raw_spin_lock(&tick_broadcast_lock); + cpu = smp_processor_id(); + bc = tick_broadcast_device.evtdev; bc_stopped = cpumask_empty(tick_broadcast_mask); - switch (*reason) { - case CLOCK_EVT_NOTIFY_BROADCAST_ON: - case CLOCK_EVT_NOTIFY_BROADCAST_FORCE: + switch (mode) { + case TICK_BROADCAST_FORCE: + tick_broadcast_forced = 1; + case TICK_BROADCAST_ON: cpumask_set_cpu(cpu, tick_broadcast_on); if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_mask)) { if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) clockevents_shutdown(dev); } - if (*reason == CLOCK_EVT_NOTIFY_BROADCAST_FORCE) - tick_broadcast_force = 1; break; - case CLOCK_EVT_NOTIFY_BROADCAST_OFF: - if (tick_broadcast_force) + + case TICK_BROADCAST_OFF: + if (tick_broadcast_forced) break; cpumask_clear_cpu(cpu, tick_broadcast_on); if (!tick_device_is_functional(dev)) @@ -388,22 +395,9 @@ static void tick_do_broadcast_on_off(unsigned long *reason) else tick_broadcast_setup_oneshot(bc); } -out: - raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); -} - -/* - * Powerstate information: The system enters/leaves a state, where - * affected devices might stop. - */ -void tick_broadcast_on_off(unsigned long reason, int *oncpu) -{ - if (!cpumask_test_cpu(*oncpu, cpu_online_mask)) - printk(KERN_ERR "tick-broadcast: ignoring broadcast for " - "offline CPU #%d\n", *oncpu); - else - tick_do_broadcast_on_off(&reason); + raw_spin_unlock(&tick_broadcast_lock); } +EXPORT_SYMBOL_GPL(tick_broadcast_control); /* * Set the periodic handler depending on broadcast on/off @@ -416,14 +410,14 @@ void tick_set_periodic_handler(struct clock_event_device *dev, int broadcast) dev->event_handler = tick_handle_periodic_broadcast; } +#ifdef CONFIG_HOTPLUG_CPU /* * Remove a CPU from broadcasting */ -void tick_shutdown_broadcast(unsigned int *cpup) +void tick_shutdown_broadcast(unsigned int cpu) { struct clock_event_device *bc; unsigned long flags; - unsigned int cpu = *cpup; raw_spin_lock_irqsave(&tick_broadcast_lock, flags); @@ -438,6 +432,7 @@ void tick_shutdown_broadcast(unsigned int *cpup) raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); } +#endif void tick_suspend_broadcast(void) { @@ -453,38 +448,48 @@ void tick_suspend_broadcast(void) raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); } -int tick_resume_broadcast(void) +/* + * This is called from tick_resume_local() on a resuming CPU. That's + * called from the core resume function, tick_unfreeze() and the magic XEN + * resume hackery. + * + * In none of these cases the broadcast device mode can change and the + * bit of the resuming CPU in the broadcast mask is safe as well. + */ +bool tick_resume_check_broadcast(void) +{ + if (tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT) + return false; + else + return cpumask_test_cpu(smp_processor_id(), tick_broadcast_mask); +} + +void tick_resume_broadcast(void) { struct clock_event_device *bc; unsigned long flags; - int broadcast = 0; raw_spin_lock_irqsave(&tick_broadcast_lock, flags); bc = tick_broadcast_device.evtdev; if (bc) { - clockevents_set_mode(bc, CLOCK_EVT_MODE_RESUME); + clockevents_tick_resume(bc); switch (tick_broadcast_device.mode) { case TICKDEV_MODE_PERIODIC: if (!cpumask_empty(tick_broadcast_mask)) tick_broadcast_start_periodic(bc); - broadcast = cpumask_test_cpu(smp_processor_id(), - tick_broadcast_mask); break; case TICKDEV_MODE_ONESHOT: if (!cpumask_empty(tick_broadcast_mask)) - broadcast = tick_resume_broadcast_oneshot(bc); + tick_resume_broadcast_oneshot(bc); break; } } raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); - - return broadcast; } - #ifdef CONFIG_TICK_ONESHOT static cpumask_var_t tick_broadcast_oneshot_mask; @@ -532,8 +537,8 @@ static int tick_broadcast_set_event(struct clock_event_device *bc, int cpu, { int ret; - if (bc->mode != CLOCK_EVT_MODE_ONESHOT) - clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT); + if (bc->state != CLOCK_EVT_STATE_ONESHOT) + clockevents_set_state(bc, CLOCK_EVT_STATE_ONESHOT); ret = clockevents_program_event(bc, expires, force); if (!ret) @@ -541,10 +546,9 @@ static int tick_broadcast_set_event(struct clock_event_device *bc, int cpu, return ret; } -int tick_resume_broadcast_oneshot(struct clock_event_device *bc) +static void tick_resume_broadcast_oneshot(struct clock_event_device *bc) { - clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT); - return 0; + clockevents_set_state(bc, CLOCK_EVT_STATE_ONESHOT); } /* @@ -562,8 +566,8 @@ void tick_check_oneshot_broadcast_this_cpu(void) * switched over, leave the device alone. */ if (td->mode == TICKDEV_MODE_ONESHOT) { - clockevents_set_mode(td->evtdev, - CLOCK_EVT_MODE_ONESHOT); + clockevents_set_state(td->evtdev, + CLOCK_EVT_STATE_ONESHOT); } } } @@ -666,31 +670,26 @@ static void broadcast_shutdown_local(struct clock_event_device *bc, if (dev->next_event.tv64 < bc->next_event.tv64) return; } - clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN); + clockevents_set_state(dev, CLOCK_EVT_STATE_SHUTDOWN); } -static void broadcast_move_bc(int deadcpu) -{ - struct clock_event_device *bc = tick_broadcast_device.evtdev; - - if (!bc || !broadcast_needs_cpu(bc, deadcpu)) - return; - /* This moves the broadcast assignment to this cpu */ - clockevents_program_event(bc, bc->next_event, 1); -} - -/* - * Powerstate information: The system enters/leaves a state, where - * affected devices might stop +/** + * tick_broadcast_oneshot_control - Enter/exit broadcast oneshot mode + * @state: The target state (enter/exit) + * + * The system enters/leaves a state, where affected devices might stop * Returns 0 on success, -EBUSY if the cpu is used to broadcast wakeups. + * + * Called with interrupts disabled, so clockevents_lock is not + * required here because the local clock event device cannot go away + * under us. */ -int tick_broadcast_oneshot_control(unsigned long reason) +int tick_broadcast_oneshot_control(enum tick_broadcast_state state) { struct clock_event_device *bc, *dev; struct tick_device *td; - unsigned long flags; - ktime_t now; int cpu, ret = 0; + ktime_t now; /* * Periodic mode does not care about the enter/exit of power @@ -703,17 +702,17 @@ int tick_broadcast_oneshot_control(unsigned long reason) * We are called with preemtion disabled from the depth of the * idle code, so we can't be moved away. */ - cpu = smp_processor_id(); - td = &per_cpu(tick_cpu_device, cpu); + td = this_cpu_ptr(&tick_cpu_device); dev = td->evtdev; if (!(dev->features & CLOCK_EVT_FEAT_C3STOP)) return 0; + raw_spin_lock(&tick_broadcast_lock); bc = tick_broadcast_device.evtdev; + cpu = smp_processor_id(); - raw_spin_lock_irqsave(&tick_broadcast_lock, flags); - if (reason == CLOCK_EVT_NOTIFY_BROADCAST_ENTER) { + if (state == TICK_BROADCAST_ENTER) { if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_oneshot_mask)) { WARN_ON_ONCE(cpumask_test_cpu(cpu, tick_broadcast_pending_mask)); broadcast_shutdown_local(bc, dev); @@ -741,7 +740,7 @@ int tick_broadcast_oneshot_control(unsigned long reason) cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask); } else { if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_oneshot_mask)) { - clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT); + clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT); /* * The cpu which was handling the broadcast * timer marked this cpu in the broadcast @@ -805,9 +804,10 @@ int tick_broadcast_oneshot_control(unsigned long reason) } } out: - raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); + raw_spin_unlock(&tick_broadcast_lock); return ret; } +EXPORT_SYMBOL_GPL(tick_broadcast_oneshot_control); /* * Reset the one shot broadcast for a cpu @@ -842,7 +842,7 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc) /* Set it up only once ! */ if (bc->event_handler != tick_handle_oneshot_broadcast) { - int was_periodic = bc->mode == CLOCK_EVT_MODE_PERIODIC; + int was_periodic = bc->state == CLOCK_EVT_STATE_PERIODIC; bc->event_handler = tick_handle_oneshot_broadcast; @@ -858,7 +858,7 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc) tick_broadcast_oneshot_mask, tmpmask); if (was_periodic && !cpumask_empty(tmpmask)) { - clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT); + clockevents_set_state(bc, CLOCK_EVT_STATE_ONESHOT); tick_broadcast_init_next_event(tmpmask, tick_next_period); tick_broadcast_set_event(bc, cpu, tick_next_period, 1); @@ -894,14 +894,28 @@ void tick_broadcast_switch_to_oneshot(void) raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); } +#ifdef CONFIG_HOTPLUG_CPU +void hotplug_cpu__broadcast_tick_pull(int deadcpu) +{ + struct clock_event_device *bc; + unsigned long flags; + + raw_spin_lock_irqsave(&tick_broadcast_lock, flags); + bc = tick_broadcast_device.evtdev; + + if (bc && broadcast_needs_cpu(bc, deadcpu)) { + /* This moves the broadcast assignment to this CPU: */ + clockevents_program_event(bc, bc->next_event, 1); + } + raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); +} /* * Remove a dead CPU from broadcasting */ -void tick_shutdown_broadcast_oneshot(unsigned int *cpup) +void tick_shutdown_broadcast_oneshot(unsigned int cpu) { unsigned long flags; - unsigned int cpu = *cpup; raw_spin_lock_irqsave(&tick_broadcast_lock, flags); @@ -913,10 +927,9 @@ void tick_shutdown_broadcast_oneshot(unsigned int *cpup) cpumask_clear_cpu(cpu, tick_broadcast_pending_mask); cpumask_clear_cpu(cpu, tick_broadcast_force_mask); - broadcast_move_bc(cpu); - raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); } +#endif /* * Check, whether the broadcast device is in one shot mode diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index f7c515595b42..3ae6afa1eb98 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -102,7 +102,7 @@ void tick_handle_periodic(struct clock_event_device *dev) tick_periodic(cpu); - if (dev->mode != CLOCK_EVT_MODE_ONESHOT) + if (dev->state != CLOCK_EVT_STATE_ONESHOT) return; for (;;) { /* @@ -140,7 +140,7 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast) if ((dev->features & CLOCK_EVT_FEAT_PERIODIC) && !tick_broadcast_oneshot_active()) { - clockevents_set_mode(dev, CLOCK_EVT_MODE_PERIODIC); + clockevents_set_state(dev, CLOCK_EVT_STATE_PERIODIC); } else { unsigned long seq; ktime_t next; @@ -150,7 +150,7 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast) next = tick_next_period; } while (read_seqretry(&jiffies_lock, seq)); - clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT); + clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT); for (;;) { if (!clockevents_program_event(dev, next, false)) @@ -332,14 +332,16 @@ out_bc: tick_install_broadcast_device(newdev); } +#ifdef CONFIG_HOTPLUG_CPU /* * Transfer the do_timer job away from a dying cpu. * - * Called with interrupts disabled. + * Called with interrupts disabled. Not locking required. If + * tick_do_timer_cpu is owned by this cpu, nothing can change it. */ -void tick_handover_do_timer(int *cpup) +void tick_handover_do_timer(void) { - if (*cpup == tick_do_timer_cpu) { + if (tick_do_timer_cpu == smp_processor_id()) { int cpu = cpumask_first(cpu_online_mask); tick_do_timer_cpu = (cpu < nr_cpu_ids) ? cpu : @@ -354,9 +356,9 @@ void tick_handover_do_timer(int *cpup) * access the hardware device itself. * We just set the mode and remove it from the lists. */ -void tick_shutdown(unsigned int *cpup) +void tick_shutdown(unsigned int cpu) { - struct tick_device *td = &per_cpu(tick_cpu_device, *cpup); + struct tick_device *td = &per_cpu(tick_cpu_device, cpu); struct clock_event_device *dev = td->evtdev; td->mode = TICKDEV_MODE_PERIODIC; @@ -365,27 +367,42 @@ void tick_shutdown(unsigned int *cpup) * Prevent that the clock events layer tries to call * the set mode function! */ + dev->state = CLOCK_EVT_STATE_DETACHED; dev->mode = CLOCK_EVT_MODE_UNUSED; clockevents_exchange_device(dev, NULL); dev->event_handler = clockevents_handle_noop; td->evtdev = NULL; } } +#endif -void tick_suspend(void) +/** + * tick_suspend_local - Suspend the local tick device + * + * Called from the local cpu for freeze with interrupts disabled. + * + * No locks required. Nothing can change the per cpu device. + */ +void tick_suspend_local(void) { struct tick_device *td = this_cpu_ptr(&tick_cpu_device); clockevents_shutdown(td->evtdev); } -void tick_resume(void) +/** + * tick_resume_local - Resume the local tick device + * + * Called from the local CPU for unfreeze or XEN resume magic. + * + * No locks required. Nothing can change the per cpu device. + */ +void tick_resume_local(void) { struct tick_device *td = this_cpu_ptr(&tick_cpu_device); - int broadcast = tick_resume_broadcast(); - - clockevents_set_mode(td->evtdev, CLOCK_EVT_MODE_RESUME); + bool broadcast = tick_resume_check_broadcast(); + clockevents_tick_resume(td->evtdev); if (!broadcast) { if (td->mode == TICKDEV_MODE_PERIODIC) tick_setup_periodic(td->evtdev, 0); @@ -394,6 +411,35 @@ void tick_resume(void) } } +/** + * tick_suspend - Suspend the tick and the broadcast device + * + * Called from syscore_suspend() via timekeeping_suspend with only one + * CPU online and interrupts disabled or from tick_unfreeze() under + * tick_freeze_lock. + * + * No locks required. Nothing can change the per cpu device. + */ +void tick_suspend(void) +{ + tick_suspend_local(); + tick_suspend_broadcast(); +} + +/** + * tick_resume - Resume the tick and the broadcast device + * + * Called from syscore_resume() via timekeeping_resume with only one + * CPU online and interrupts disabled. + * + * No locks required. Nothing can change the per cpu device. + */ +void tick_resume(void) +{ + tick_resume_broadcast(); + tick_resume_local(); +} + static DEFINE_RAW_SPINLOCK(tick_freeze_lock); static unsigned int tick_freeze_depth; @@ -411,12 +457,10 @@ void tick_freeze(void) raw_spin_lock(&tick_freeze_lock); tick_freeze_depth++; - if (tick_freeze_depth == num_online_cpus()) { + if (tick_freeze_depth == num_online_cpus()) timekeeping_suspend(); - } else { - tick_suspend(); - tick_suspend_broadcast(); - } + else + tick_suspend_local(); raw_spin_unlock(&tick_freeze_lock); } @@ -437,7 +481,7 @@ void tick_unfreeze(void) if (tick_freeze_depth == num_online_cpus()) timekeeping_resume(); else - tick_resume(); + tick_resume_local(); tick_freeze_depth--; diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index 366aeb4f2c66..b64fdd8054c5 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -5,15 +5,12 @@ #include <linux/tick.h> #include "timekeeping.h" +#include "tick-sched.h" -extern seqlock_t jiffies_lock; +#ifdef CONFIG_GENERIC_CLOCKEVENTS -#define CS_NAME_LEN 32 - -#ifdef CONFIG_GENERIC_CLOCKEVENTS_BUILD - -#define TICK_DO_TIMER_NONE -1 -#define TICK_DO_TIMER_BOOT -2 +# define TICK_DO_TIMER_NONE -1 +# define TICK_DO_TIMER_BOOT -2 DECLARE_PER_CPU(struct tick_device, tick_cpu_device); extern ktime_t tick_next_period; @@ -23,21 +20,72 @@ extern int tick_do_timer_cpu __read_mostly; extern void tick_setup_periodic(struct clock_event_device *dev, int broadcast); extern void tick_handle_periodic(struct clock_event_device *dev); extern void tick_check_new_device(struct clock_event_device *dev); -extern void tick_handover_do_timer(int *cpup); -extern void tick_shutdown(unsigned int *cpup); +extern void tick_shutdown(unsigned int cpu); extern void tick_suspend(void); extern void tick_resume(void); extern bool tick_check_replacement(struct clock_event_device *curdev, struct clock_event_device *newdev); extern void tick_install_replacement(struct clock_event_device *dev); +extern int tick_is_oneshot_available(void); +extern struct tick_device *tick_get_device(int cpu); -extern void clockevents_shutdown(struct clock_event_device *dev); +extern int clockevents_tick_resume(struct clock_event_device *dev); +/* Check, if the device is functional or a dummy for broadcast */ +static inline int tick_device_is_functional(struct clock_event_device *dev) +{ + return !(dev->features & CLOCK_EVT_FEAT_DUMMY); +} +extern void clockevents_shutdown(struct clock_event_device *dev); +extern void clockevents_exchange_device(struct clock_event_device *old, + struct clock_event_device *new); +extern void clockevents_set_state(struct clock_event_device *dev, + enum clock_event_state state); +extern int clockevents_program_event(struct clock_event_device *dev, + ktime_t expires, bool force); +extern void clockevents_handle_noop(struct clock_event_device *dev); +extern int __clockevents_update_freq(struct clock_event_device *dev, u32 freq); extern ssize_t sysfs_get_uname(const char *buf, char *dst, size_t cnt); -/* - * NO_HZ / high resolution timer shared code - */ +/* Broadcasting support */ +# ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST +extern int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu); +extern void tick_install_broadcast_device(struct clock_event_device *dev); +extern int tick_is_broadcast_device(struct clock_event_device *dev); +extern void tick_shutdown_broadcast(unsigned int cpu); +extern void tick_suspend_broadcast(void); +extern void tick_resume_broadcast(void); +extern bool tick_resume_check_broadcast(void); +extern void tick_broadcast_init(void); +extern void tick_set_periodic_handler(struct clock_event_device *dev, int broadcast); +extern int tick_broadcast_update_freq(struct clock_event_device *dev, u32 freq); +extern struct tick_device *tick_get_broadcast_device(void); +extern struct cpumask *tick_get_broadcast_mask(void); +# else /* !CONFIG_GENERIC_CLOCKEVENTS_BROADCAST: */ +static inline void tick_install_broadcast_device(struct clock_event_device *dev) { } +static inline int tick_is_broadcast_device(struct clock_event_device *dev) { return 0; } +static inline int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu) { return 0; } +static inline void tick_do_periodic_broadcast(struct clock_event_device *d) { } +static inline void tick_shutdown_broadcast(unsigned int cpu) { } +static inline void tick_suspend_broadcast(void) { } +static inline void tick_resume_broadcast(void) { } +static inline bool tick_resume_check_broadcast(void) { return false; } +static inline void tick_broadcast_init(void) { } +static inline int tick_broadcast_update_freq(struct clock_event_device *dev, u32 freq) { return -ENODEV; } + +/* Set the periodic handler in non broadcast mode */ +static inline void tick_set_periodic_handler(struct clock_event_device *dev, int broadcast) +{ + dev->event_handler = tick_handle_periodic; +} +# endif /* !CONFIG_GENERIC_CLOCKEVENTS_BROADCAST */ + +#else /* !GENERIC_CLOCKEVENTS: */ +static inline void tick_suspend(void) { } +static inline void tick_resume(void) { } +#endif /* !GENERIC_CLOCKEVENTS */ + +/* Oneshot related functions */ #ifdef CONFIG_TICK_ONESHOT extern void tick_setup_oneshot(struct clock_event_device *newdev, void (*handler)(struct clock_event_device *), @@ -46,58 +94,42 @@ extern int tick_program_event(ktime_t expires, int force); extern void tick_oneshot_notify(void); extern int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *)); extern void tick_resume_oneshot(void); -# ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST +static inline bool tick_oneshot_possible(void) { return true; } +extern int tick_oneshot_mode_active(void); +extern void tick_clock_notify(void); +extern int tick_check_oneshot_change(int allow_nohz); +extern int tick_init_highres(void); +#else /* !CONFIG_TICK_ONESHOT: */ +static inline +void tick_setup_oneshot(struct clock_event_device *newdev, + void (*handler)(struct clock_event_device *), + ktime_t nextevt) { BUG(); } +static inline void tick_resume_oneshot(void) { BUG(); } +static inline int tick_program_event(ktime_t expires, int force) { return 0; } +static inline void tick_oneshot_notify(void) { } +static inline bool tick_oneshot_possible(void) { return false; } +static inline int tick_oneshot_mode_active(void) { return 0; } +static inline void tick_clock_notify(void) { } +static inline int tick_check_oneshot_change(int allow_nohz) { return 0; } +#endif /* !CONFIG_TICK_ONESHOT */ + +/* Functions related to oneshot broadcasting */ +#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT) extern void tick_broadcast_setup_oneshot(struct clock_event_device *bc); -extern int tick_broadcast_oneshot_control(unsigned long reason); extern void tick_broadcast_switch_to_oneshot(void); -extern void tick_shutdown_broadcast_oneshot(unsigned int *cpup); -extern int tick_resume_broadcast_oneshot(struct clock_event_device *bc); +extern void tick_shutdown_broadcast_oneshot(unsigned int cpu); extern int tick_broadcast_oneshot_active(void); extern void tick_check_oneshot_broadcast_this_cpu(void); bool tick_broadcast_oneshot_available(void); -# else /* BROADCAST */ -static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc) -{ - BUG(); -} -static inline int tick_broadcast_oneshot_control(unsigned long reason) { return 0; } +extern struct cpumask *tick_get_broadcast_oneshot_mask(void); +#else /* !(BROADCAST && ONESHOT): */ +static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc) { BUG(); } static inline void tick_broadcast_switch_to_oneshot(void) { } -static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { } +static inline void tick_shutdown_broadcast_oneshot(unsigned int cpu) { } static inline int tick_broadcast_oneshot_active(void) { return 0; } static inline void tick_check_oneshot_broadcast_this_cpu(void) { } -static inline bool tick_broadcast_oneshot_available(void) { return true; } -# endif /* !BROADCAST */ - -#else /* !ONESHOT */ -static inline -void tick_setup_oneshot(struct clock_event_device *newdev, - void (*handler)(struct clock_event_device *), - ktime_t nextevt) -{ - BUG(); -} -static inline void tick_resume_oneshot(void) -{ - BUG(); -} -static inline int tick_program_event(ktime_t expires, int force) -{ - return 0; -} -static inline void tick_oneshot_notify(void) { } -static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc) -{ - BUG(); -} -static inline int tick_broadcast_oneshot_control(unsigned long reason) { return 0; } -static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { } -static inline int tick_resume_broadcast_oneshot(struct clock_event_device *bc) -{ - return 0; -} -static inline int tick_broadcast_oneshot_active(void) { return 0; } -static inline bool tick_broadcast_oneshot_available(void) { return false; } -#endif /* !TICK_ONESHOT */ +static inline bool tick_broadcast_oneshot_available(void) { return tick_oneshot_possible(); } +#endif /* !(BROADCAST && ONESHOT) */ /* NO_HZ_FULL internal */ #ifdef CONFIG_NO_HZ_FULL @@ -105,68 +137,3 @@ extern void tick_nohz_init(void); # else static inline void tick_nohz_init(void) { } #endif - -/* - * Broadcasting support - */ -#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST -extern int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu); -extern void tick_install_broadcast_device(struct clock_event_device *dev); -extern int tick_is_broadcast_device(struct clock_event_device *dev); -extern void tick_broadcast_on_off(unsigned long reason, int *oncpu); -extern void tick_shutdown_broadcast(unsigned int *cpup); -extern void tick_suspend_broadcast(void); -extern int tick_resume_broadcast(void); -extern void tick_broadcast_init(void); -extern void -tick_set_periodic_handler(struct clock_event_device *dev, int broadcast); -int tick_broadcast_update_freq(struct clock_event_device *dev, u32 freq); - -#else /* !BROADCAST */ - -static inline void tick_install_broadcast_device(struct clock_event_device *dev) -{ -} - -static inline int tick_is_broadcast_device(struct clock_event_device *dev) -{ - return 0; -} -static inline int tick_device_uses_broadcast(struct clock_event_device *dev, - int cpu) -{ - return 0; -} -static inline void tick_do_periodic_broadcast(struct clock_event_device *d) { } -static inline void tick_broadcast_on_off(unsigned long reason, int *oncpu) { } -static inline void tick_shutdown_broadcast(unsigned int *cpup) { } -static inline void tick_suspend_broadcast(void) { } -static inline int tick_resume_broadcast(void) { return 0; } -static inline void tick_broadcast_init(void) { } -static inline int tick_broadcast_update_freq(struct clock_event_device *dev, - u32 freq) { return -ENODEV; } - -/* - * Set the periodic handler in non broadcast mode - */ -static inline void tick_set_periodic_handler(struct clock_event_device *dev, - int broadcast) -{ - dev->event_handler = tick_handle_periodic; -} -#endif /* !BROADCAST */ - -/* - * Check, if the device is functional or a dummy for broadcast - */ -static inline int tick_device_is_functional(struct clock_event_device *dev) -{ - return !(dev->features & CLOCK_EVT_FEAT_DUMMY); -} - -int __clockevents_update_freq(struct clock_event_device *dev, u32 freq); - -#endif - -extern void do_timer(unsigned long ticks); -extern void update_wall_time(void); diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c index 7ce740e78e1b..67a64b1670bf 100644 --- a/kernel/time/tick-oneshot.c +++ b/kernel/time/tick-oneshot.c @@ -38,7 +38,7 @@ void tick_resume_oneshot(void) { struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev); - clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT); + clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT); clockevents_program_event(dev, ktime_get(), true); } @@ -50,7 +50,7 @@ void tick_setup_oneshot(struct clock_event_device *newdev, ktime_t next_event) { newdev->event_handler = handler; - clockevents_set_mode(newdev, CLOCK_EVT_MODE_ONESHOT); + clockevents_set_state(newdev, CLOCK_EVT_STATE_ONESHOT); clockevents_program_event(newdev, next_event, true); } @@ -81,7 +81,7 @@ int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *)) td->mode = TICKDEV_MODE_ONESHOT; dev->event_handler = handler; - clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT); + clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT); tick_broadcast_switch_to_oneshot(); return 0; } diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index a4c4edac4528..914259128145 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -34,7 +34,7 @@ /* * Per cpu nohz control structure */ -DEFINE_PER_CPU(struct tick_sched, tick_cpu_sched); +static DEFINE_PER_CPU(struct tick_sched, tick_cpu_sched); /* * The time, when the last jiffy update happened. Protected by jiffies_lock. @@ -416,6 +416,11 @@ static int __init setup_tick_nohz(char *str) __setup("nohz=", setup_tick_nohz); +int tick_nohz_tick_stopped(void) +{ + return __this_cpu_read(tick_cpu_sched.tick_stopped); +} + /** * tick_nohz_update_jiffies - update jiffies when idle was interrupted * diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h new file mode 100644 index 000000000000..28b5da3e1a17 --- /dev/null +++ b/kernel/time/tick-sched.h @@ -0,0 +1,74 @@ +#ifndef _TICK_SCHED_H +#define _TICK_SCHED_H + +#include <linux/hrtimer.h> + +enum tick_device_mode { + TICKDEV_MODE_PERIODIC, + TICKDEV_MODE_ONESHOT, +}; + +struct tick_device { + struct clock_event_device *evtdev; + enum tick_device_mode mode; +}; + +enum tick_nohz_mode { + NOHZ_MODE_INACTIVE, + NOHZ_MODE_LOWRES, + NOHZ_MODE_HIGHRES, +}; + +/** + * struct tick_sched - sched tick emulation and no idle tick control/stats + * @sched_timer: hrtimer to schedule the periodic tick in high + * resolution mode + * @last_tick: Store the last tick expiry time when the tick + * timer is modified for nohz sleeps. This is necessary + * to resume the tick timer operation in the timeline + * when the CPU returns from nohz sleep. + * @tick_stopped: Indicator that the idle tick has been stopped + * @idle_jiffies: jiffies at the entry to idle for idle time accounting + * @idle_calls: Total number of idle calls + * @idle_sleeps: Number of idle calls, where the sched tick was stopped + * @idle_entrytime: Time when the idle call was entered + * @idle_waketime: Time when the idle was interrupted + * @idle_exittime: Time when the idle state was left + * @idle_sleeptime: Sum of the time slept in idle with sched tick stopped + * @iowait_sleeptime: Sum of the time slept in idle with sched tick stopped, with IO outstanding + * @sleep_length: Duration of the current idle sleep + * @do_timer_lst: CPU was the last one doing do_timer before going idle + */ +struct tick_sched { + struct hrtimer sched_timer; + unsigned long check_clocks; + enum tick_nohz_mode nohz_mode; + ktime_t last_tick; + int inidle; + int tick_stopped; + unsigned long idle_jiffies; + unsigned long idle_calls; + unsigned long idle_sleeps; + int idle_active; + ktime_t idle_entrytime; + ktime_t idle_waketime; + ktime_t idle_exittime; + ktime_t idle_sleeptime; + ktime_t iowait_sleeptime; + ktime_t sleep_length; + unsigned long last_jiffies; + unsigned long next_jiffies; + ktime_t idle_expires; + int do_timer_last; +}; + +extern struct tick_sched *tick_get_tick_sched(int cpu); + +extern void tick_setup_sched_timer(void); +#if defined CONFIG_NO_HZ_COMMON || defined CONFIG_HIGH_RES_TIMERS +extern void tick_cancel_sched_timer(int cpu); +#else +static inline void tick_cancel_sched_timer(int cpu) { } +#endif + +#endif diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 91db94136c10..946acb72179f 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -59,17 +59,15 @@ struct tk_fast { }; static struct tk_fast tk_fast_mono ____cacheline_aligned; +static struct tk_fast tk_fast_raw ____cacheline_aligned; /* flag for if timekeeping is suspended */ int __read_mostly timekeeping_suspended; -/* Flag for if there is a persistent clock on this platform */ -bool __read_mostly persistent_clock_exist = false; - static inline void tk_normalize_xtime(struct timekeeper *tk) { - while (tk->tkr.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr.shift)) { - tk->tkr.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr.shift; + while (tk->tkr_mono.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr_mono.shift)) { + tk->tkr_mono.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr_mono.shift; tk->xtime_sec++; } } @@ -79,20 +77,20 @@ static inline struct timespec64 tk_xtime(struct timekeeper *tk) struct timespec64 ts; ts.tv_sec = tk->xtime_sec; - ts.tv_nsec = (long)(tk->tkr.xtime_nsec >> tk->tkr.shift); + ts.tv_nsec = (long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift); return ts; } static void tk_set_xtime(struct timekeeper *tk, const struct timespec64 *ts) { tk->xtime_sec = ts->tv_sec; - tk->tkr.xtime_nsec = (u64)ts->tv_nsec << tk->tkr.shift; + tk->tkr_mono.xtime_nsec = (u64)ts->tv_nsec << tk->tkr_mono.shift; } static void tk_xtime_add(struct timekeeper *tk, const struct timespec64 *ts) { tk->xtime_sec += ts->tv_sec; - tk->tkr.xtime_nsec += (u64)ts->tv_nsec << tk->tkr.shift; + tk->tkr_mono.xtime_nsec += (u64)ts->tv_nsec << tk->tkr_mono.shift; tk_normalize_xtime(tk); } @@ -118,6 +116,117 @@ static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta) tk->offs_boot = ktime_add(tk->offs_boot, delta); } +#ifdef CONFIG_DEBUG_TIMEKEEPING +#define WARNING_FREQ (HZ*300) /* 5 minute rate-limiting */ +/* + * These simple flag variables are managed + * without locks, which is racy, but ok since + * we don't really care about being super + * precise about how many events were seen, + * just that a problem was observed. + */ +static int timekeeping_underflow_seen; +static int timekeeping_overflow_seen; + +/* last_warning is only modified under the timekeeping lock */ +static long timekeeping_last_warning; + +static void timekeeping_check_update(struct timekeeper *tk, cycle_t offset) +{ + + cycle_t max_cycles = tk->tkr_mono.clock->max_cycles; + const char *name = tk->tkr_mono.clock->name; + + if (offset > max_cycles) { + printk_deferred("WARNING: timekeeping: Cycle offset (%lld) is larger than allowed by the '%s' clock's max_cycles value (%lld): time overflow danger\n", + offset, name, max_cycles); + printk_deferred(" timekeeping: Your kernel is sick, but tries to cope by capping time updates\n"); + } else { + if (offset > (max_cycles >> 1)) { + printk_deferred("INFO: timekeeping: Cycle offset (%lld) is larger than the the '%s' clock's 50%% safety margin (%lld)\n", + offset, name, max_cycles >> 1); + printk_deferred(" timekeeping: Your kernel is still fine, but is feeling a bit nervous\n"); + } + } + + if (timekeeping_underflow_seen) { + if (jiffies - timekeeping_last_warning > WARNING_FREQ) { + printk_deferred("WARNING: Underflow in clocksource '%s' observed, time update ignored.\n", name); + printk_deferred(" Please report this, consider using a different clocksource, if possible.\n"); + printk_deferred(" Your kernel is probably still fine.\n"); + timekeeping_last_warning = jiffies; + } + timekeeping_underflow_seen = 0; + } + + if (timekeeping_overflow_seen) { + if (jiffies - timekeeping_last_warning > WARNING_FREQ) { + printk_deferred("WARNING: Overflow in clocksource '%s' observed, time update capped.\n", name); + printk_deferred(" Please report this, consider using a different clocksource, if possible.\n"); + printk_deferred(" Your kernel is probably still fine.\n"); + timekeeping_last_warning = jiffies; + } + timekeeping_overflow_seen = 0; + } +} + +static inline cycle_t timekeeping_get_delta(struct tk_read_base *tkr) +{ + cycle_t now, last, mask, max, delta; + unsigned int seq; + + /* + * Since we're called holding a seqlock, the data may shift + * under us while we're doing the calculation. This can cause + * false positives, since we'd note a problem but throw the + * results away. So nest another seqlock here to atomically + * grab the points we are checking with. + */ + do { + seq = read_seqcount_begin(&tk_core.seq); + now = tkr->read(tkr->clock); + last = tkr->cycle_last; + mask = tkr->mask; + max = tkr->clock->max_cycles; + } while (read_seqcount_retry(&tk_core.seq, seq)); + + delta = clocksource_delta(now, last, mask); + + /* + * Try to catch underflows by checking if we are seeing small + * mask-relative negative values. + */ + if (unlikely((~delta & mask) < (mask >> 3))) { + timekeeping_underflow_seen = 1; + delta = 0; + } + + /* Cap delta value to the max_cycles values to avoid mult overflows */ + if (unlikely(delta > max)) { + timekeeping_overflow_seen = 1; + delta = tkr->clock->max_cycles; + } + + return delta; +} +#else +static inline void timekeeping_check_update(struct timekeeper *tk, cycle_t offset) +{ +} +static inline cycle_t timekeeping_get_delta(struct tk_read_base *tkr) +{ + cycle_t cycle_now, delta; + + /* read clocksource */ + cycle_now = tkr->read(tkr->clock); + + /* calculate the delta since the last update_wall_time */ + delta = clocksource_delta(cycle_now, tkr->cycle_last, tkr->mask); + + return delta; +} +#endif + /** * tk_setup_internals - Set up internals to use clocksource clock. * @@ -135,11 +244,16 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) u64 tmp, ntpinterval; struct clocksource *old_clock; - old_clock = tk->tkr.clock; - tk->tkr.clock = clock; - tk->tkr.read = clock->read; - tk->tkr.mask = clock->mask; - tk->tkr.cycle_last = tk->tkr.read(clock); + old_clock = tk->tkr_mono.clock; + tk->tkr_mono.clock = clock; + tk->tkr_mono.read = clock->read; + tk->tkr_mono.mask = clock->mask; + tk->tkr_mono.cycle_last = tk->tkr_mono.read(clock); + + tk->tkr_raw.clock = clock; + tk->tkr_raw.read = clock->read; + tk->tkr_raw.mask = clock->mask; + tk->tkr_raw.cycle_last = tk->tkr_mono.cycle_last; /* Do the ns -> cycle conversion first, using original mult */ tmp = NTP_INTERVAL_LENGTH; @@ -163,11 +277,14 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) if (old_clock) { int shift_change = clock->shift - old_clock->shift; if (shift_change < 0) - tk->tkr.xtime_nsec >>= -shift_change; + tk->tkr_mono.xtime_nsec >>= -shift_change; else - tk->tkr.xtime_nsec <<= shift_change; + tk->tkr_mono.xtime_nsec <<= shift_change; } - tk->tkr.shift = clock->shift; + tk->tkr_raw.xtime_nsec = 0; + + tk->tkr_mono.shift = clock->shift; + tk->tkr_raw.shift = clock->shift; tk->ntp_error = 0; tk->ntp_error_shift = NTP_SCALE_SHIFT - clock->shift; @@ -178,7 +295,8 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) * active clocksource. These value will be adjusted via NTP * to counteract clock drifting. */ - tk->tkr.mult = clock->mult; + tk->tkr_mono.mult = clock->mult; + tk->tkr_raw.mult = clock->mult; tk->ntp_err_mult = 0; } @@ -193,14 +311,10 @@ static inline u32 arch_gettimeoffset(void) { return 0; } static inline s64 timekeeping_get_ns(struct tk_read_base *tkr) { - cycle_t cycle_now, delta; + cycle_t delta; s64 nsec; - /* read clocksource: */ - cycle_now = tkr->read(tkr->clock); - - /* calculate the delta since the last update_wall_time: */ - delta = clocksource_delta(cycle_now, tkr->cycle_last, tkr->mask); + delta = timekeeping_get_delta(tkr); nsec = delta * tkr->mult + tkr->xtime_nsec; nsec >>= tkr->shift; @@ -209,25 +323,6 @@ static inline s64 timekeeping_get_ns(struct tk_read_base *tkr) return nsec + arch_gettimeoffset(); } -static inline s64 timekeeping_get_ns_raw(struct timekeeper *tk) -{ - struct clocksource *clock = tk->tkr.clock; - cycle_t cycle_now, delta; - s64 nsec; - - /* read clocksource: */ - cycle_now = tk->tkr.read(clock); - - /* calculate the delta since the last update_wall_time: */ - delta = clocksource_delta(cycle_now, tk->tkr.cycle_last, tk->tkr.mask); - - /* convert delta to nanoseconds. */ - nsec = clocksource_cyc2ns(delta, clock->mult, clock->shift); - - /* If arch requires, add in get_arch_timeoffset() */ - return nsec + arch_gettimeoffset(); -} - /** * update_fast_timekeeper - Update the fast and NMI safe monotonic timekeeper. * @tkr: Timekeeping readout base from which we take the update @@ -267,18 +362,18 @@ static inline s64 timekeeping_get_ns_raw(struct timekeeper *tk) * slightly wrong timestamp (a few nanoseconds). See * @ktime_get_mono_fast_ns. */ -static void update_fast_timekeeper(struct tk_read_base *tkr) +static void update_fast_timekeeper(struct tk_read_base *tkr, struct tk_fast *tkf) { - struct tk_read_base *base = tk_fast_mono.base; + struct tk_read_base *base = tkf->base; /* Force readers off to base[1] */ - raw_write_seqcount_latch(&tk_fast_mono.seq); + raw_write_seqcount_latch(&tkf->seq); /* Update base[0] */ memcpy(base, tkr, sizeof(*base)); /* Force readers back to base[0] */ - raw_write_seqcount_latch(&tk_fast_mono.seq); + raw_write_seqcount_latch(&tkf->seq); /* Update base[1] */ memcpy(base + 1, base, sizeof(*base)); @@ -316,22 +411,33 @@ static void update_fast_timekeeper(struct tk_read_base *tkr) * of the following timestamps. Callers need to be aware of that and * deal with it. */ -u64 notrace ktime_get_mono_fast_ns(void) +static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf) { struct tk_read_base *tkr; unsigned int seq; u64 now; do { - seq = raw_read_seqcount(&tk_fast_mono.seq); - tkr = tk_fast_mono.base + (seq & 0x01); - now = ktime_to_ns(tkr->base_mono) + timekeeping_get_ns(tkr); + seq = raw_read_seqcount(&tkf->seq); + tkr = tkf->base + (seq & 0x01); + now = ktime_to_ns(tkr->base) + timekeeping_get_ns(tkr); + } while (read_seqcount_retry(&tkf->seq, seq)); - } while (read_seqcount_retry(&tk_fast_mono.seq, seq)); return now; } + +u64 ktime_get_mono_fast_ns(void) +{ + return __ktime_get_fast_ns(&tk_fast_mono); +} EXPORT_SYMBOL_GPL(ktime_get_mono_fast_ns); +u64 ktime_get_raw_fast_ns(void) +{ + return __ktime_get_fast_ns(&tk_fast_raw); +} +EXPORT_SYMBOL_GPL(ktime_get_raw_fast_ns); + /* Suspend-time cycles value for halted fast timekeeper. */ static cycle_t cycles_at_suspend; @@ -353,12 +459,17 @@ static cycle_t dummy_clock_read(struct clocksource *cs) static void halt_fast_timekeeper(struct timekeeper *tk) { static struct tk_read_base tkr_dummy; - struct tk_read_base *tkr = &tk->tkr; + struct tk_read_base *tkr = &tk->tkr_mono; memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); cycles_at_suspend = tkr->read(tkr->clock); tkr_dummy.read = dummy_clock_read; - update_fast_timekeeper(&tkr_dummy); + update_fast_timekeeper(&tkr_dummy, &tk_fast_mono); + + tkr = &tk->tkr_raw; + memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); + tkr_dummy.read = dummy_clock_read; + update_fast_timekeeper(&tkr_dummy, &tk_fast_raw); } #ifdef CONFIG_GENERIC_TIME_VSYSCALL_OLD @@ -369,8 +480,8 @@ static inline void update_vsyscall(struct timekeeper *tk) xt = timespec64_to_timespec(tk_xtime(tk)); wm = timespec64_to_timespec(tk->wall_to_monotonic); - update_vsyscall_old(&xt, &wm, tk->tkr.clock, tk->tkr.mult, - tk->tkr.cycle_last); + update_vsyscall_old(&xt, &wm, tk->tkr_mono.clock, tk->tkr_mono.mult, + tk->tkr_mono.cycle_last); } static inline void old_vsyscall_fixup(struct timekeeper *tk) @@ -387,11 +498,11 @@ static inline void old_vsyscall_fixup(struct timekeeper *tk) * (shifted nanoseconds), and CONFIG_GENERIC_TIME_VSYSCALL_OLD * users are removed, this can be killed. */ - remainder = tk->tkr.xtime_nsec & ((1ULL << tk->tkr.shift) - 1); - tk->tkr.xtime_nsec -= remainder; - tk->tkr.xtime_nsec += 1ULL << tk->tkr.shift; + remainder = tk->tkr_mono.xtime_nsec & ((1ULL << tk->tkr_mono.shift) - 1); + tk->tkr_mono.xtime_nsec -= remainder; + tk->tkr_mono.xtime_nsec += 1ULL << tk->tkr_mono.shift; tk->ntp_error += remainder << tk->ntp_error_shift; - tk->ntp_error -= (1ULL << tk->tkr.shift) << tk->ntp_error_shift; + tk->ntp_error -= (1ULL << tk->tkr_mono.shift) << tk->ntp_error_shift; } #else #define old_vsyscall_fixup(tk) @@ -456,17 +567,17 @@ static inline void tk_update_ktime_data(struct timekeeper *tk) */ seconds = (u64)(tk->xtime_sec + tk->wall_to_monotonic.tv_sec); nsec = (u32) tk->wall_to_monotonic.tv_nsec; - tk->tkr.base_mono = ns_to_ktime(seconds * NSEC_PER_SEC + nsec); + tk->tkr_mono.base = ns_to_ktime(seconds * NSEC_PER_SEC + nsec); /* Update the monotonic raw base */ - tk->base_raw = timespec64_to_ktime(tk->raw_time); + tk->tkr_raw.base = timespec64_to_ktime(tk->raw_time); /* * The sum of the nanoseconds portions of xtime and * wall_to_monotonic can be greater/equal one second. Take * this into account before updating tk->ktime_sec. */ - nsec += (u32)(tk->tkr.xtime_nsec >> tk->tkr.shift); + nsec += (u32)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift); if (nsec >= NSEC_PER_SEC) seconds++; tk->ktime_sec = seconds; @@ -489,7 +600,8 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action) memcpy(&shadow_timekeeper, &tk_core.timekeeper, sizeof(tk_core.timekeeper)); - update_fast_timekeeper(&tk->tkr); + update_fast_timekeeper(&tk->tkr_mono, &tk_fast_mono); + update_fast_timekeeper(&tk->tkr_raw, &tk_fast_raw); } /** @@ -501,22 +613,23 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action) */ static void timekeeping_forward_now(struct timekeeper *tk) { - struct clocksource *clock = tk->tkr.clock; + struct clocksource *clock = tk->tkr_mono.clock; cycle_t cycle_now, delta; s64 nsec; - cycle_now = tk->tkr.read(clock); - delta = clocksource_delta(cycle_now, tk->tkr.cycle_last, tk->tkr.mask); - tk->tkr.cycle_last = cycle_now; + cycle_now = tk->tkr_mono.read(clock); + delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask); + tk->tkr_mono.cycle_last = cycle_now; + tk->tkr_raw.cycle_last = cycle_now; - tk->tkr.xtime_nsec += delta * tk->tkr.mult; + tk->tkr_mono.xtime_nsec += delta * tk->tkr_mono.mult; /* If arch requires, add in get_arch_timeoffset() */ - tk->tkr.xtime_nsec += (u64)arch_gettimeoffset() << tk->tkr.shift; + tk->tkr_mono.xtime_nsec += (u64)arch_gettimeoffset() << tk->tkr_mono.shift; tk_normalize_xtime(tk); - nsec = clocksource_cyc2ns(delta, clock->mult, clock->shift); + nsec = clocksource_cyc2ns(delta, tk->tkr_raw.mult, tk->tkr_raw.shift); timespec64_add_ns(&tk->raw_time, nsec); } @@ -537,7 +650,7 @@ int __getnstimeofday64(struct timespec64 *ts) seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->xtime_sec; - nsecs = timekeeping_get_ns(&tk->tkr); + nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); @@ -577,8 +690,8 @@ ktime_t ktime_get(void) do { seq = read_seqcount_begin(&tk_core.seq); - base = tk->tkr.base_mono; - nsecs = timekeeping_get_ns(&tk->tkr); + base = tk->tkr_mono.base; + nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); @@ -603,8 +716,8 @@ ktime_t ktime_get_with_offset(enum tk_offsets offs) do { seq = read_seqcount_begin(&tk_core.seq); - base = ktime_add(tk->tkr.base_mono, *offset); - nsecs = timekeeping_get_ns(&tk->tkr); + base = ktime_add(tk->tkr_mono.base, *offset); + nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); @@ -645,8 +758,8 @@ ktime_t ktime_get_raw(void) do { seq = read_seqcount_begin(&tk_core.seq); - base = tk->base_raw; - nsecs = timekeeping_get_ns_raw(tk); + base = tk->tkr_raw.base; + nsecs = timekeeping_get_ns(&tk->tkr_raw); } while (read_seqcount_retry(&tk_core.seq, seq)); @@ -674,7 +787,7 @@ void ktime_get_ts64(struct timespec64 *ts) do { seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->xtime_sec; - nsec = timekeeping_get_ns(&tk->tkr); + nsec = timekeeping_get_ns(&tk->tkr_mono); tomono = tk->wall_to_monotonic; } while (read_seqcount_retry(&tk_core.seq, seq)); @@ -759,8 +872,8 @@ void getnstime_raw_and_real(struct timespec *ts_raw, struct timespec *ts_real) ts_real->tv_sec = tk->xtime_sec; ts_real->tv_nsec = 0; - nsecs_raw = timekeeping_get_ns_raw(tk); - nsecs_real = timekeeping_get_ns(&tk->tkr); + nsecs_raw = timekeeping_get_ns(&tk->tkr_raw); + nsecs_real = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); @@ -943,7 +1056,7 @@ static int change_clocksource(void *data) */ if (try_module_get(new->owner)) { if (!new->enable || new->enable(new) == 0) { - old = tk->tkr.clock; + old = tk->tkr_mono.clock; tk_setup_internals(tk, new); if (old->disable) old->disable(old); @@ -971,11 +1084,11 @@ int timekeeping_notify(struct clocksource *clock) { struct timekeeper *tk = &tk_core.timekeeper; - if (tk->tkr.clock == clock) + if (tk->tkr_mono.clock == clock) return 0; stop_machine(change_clocksource, clock, NULL); tick_clock_notify(); - return tk->tkr.clock == clock ? 0 : -1; + return tk->tkr_mono.clock == clock ? 0 : -1; } /** @@ -993,7 +1106,7 @@ void getrawmonotonic64(struct timespec64 *ts) do { seq = read_seqcount_begin(&tk_core.seq); - nsecs = timekeeping_get_ns_raw(tk); + nsecs = timekeeping_get_ns(&tk->tkr_raw); ts64 = tk->raw_time; } while (read_seqcount_retry(&tk_core.seq, seq)); @@ -1016,7 +1129,7 @@ int timekeeping_valid_for_hres(void) do { seq = read_seqcount_begin(&tk_core.seq); - ret = tk->tkr.clock->flags & CLOCK_SOURCE_VALID_FOR_HRES; + ret = tk->tkr_mono.clock->flags & CLOCK_SOURCE_VALID_FOR_HRES; } while (read_seqcount_retry(&tk_core.seq, seq)); @@ -1035,7 +1148,7 @@ u64 timekeeping_max_deferment(void) do { seq = read_seqcount_begin(&tk_core.seq); - ret = tk->tkr.clock->max_idle_ns; + ret = tk->tkr_mono.clock->max_idle_ns; } while (read_seqcount_retry(&tk_core.seq, seq)); @@ -1057,6 +1170,14 @@ void __weak read_persistent_clock(struct timespec *ts) ts->tv_nsec = 0; } +void __weak read_persistent_clock64(struct timespec64 *ts64) +{ + struct timespec ts; + + read_persistent_clock(&ts); + *ts64 = timespec_to_timespec64(ts); +} + /** * read_boot_clock - Return time of the system start. * @@ -1072,6 +1193,20 @@ void __weak read_boot_clock(struct timespec *ts) ts->tv_nsec = 0; } +void __weak read_boot_clock64(struct timespec64 *ts64) +{ + struct timespec ts; + + read_boot_clock(&ts); + *ts64 = timespec_to_timespec64(ts); +} + +/* Flag for if timekeeping_resume() has injected sleeptime */ +static bool sleeptime_injected; + +/* Flag for if there is a persistent clock on this platform */ +static bool persistent_clock_exists; + /* * timekeeping_init - Initializes the clocksource and common timekeeping values */ @@ -1081,20 +1216,17 @@ void __init timekeeping_init(void) struct clocksource *clock; unsigned long flags; struct timespec64 now, boot, tmp; - struct timespec ts; - read_persistent_clock(&ts); - now = timespec_to_timespec64(ts); + read_persistent_clock64(&now); if (!timespec64_valid_strict(&now)) { pr_warn("WARNING: Persistent clock returned invalid value!\n" " Check your CMOS/BIOS settings.\n"); now.tv_sec = 0; now.tv_nsec = 0; } else if (now.tv_sec || now.tv_nsec) - persistent_clock_exist = true; + persistent_clock_exists = true; - read_boot_clock(&ts); - boot = timespec_to_timespec64(ts); + read_boot_clock64(&boot); if (!timespec64_valid_strict(&boot)) { pr_warn("WARNING: Boot clock returned invalid value!\n" " Check your CMOS/BIOS settings.\n"); @@ -1114,7 +1246,6 @@ void __init timekeeping_init(void) tk_set_xtime(tk, &now); tk->raw_time.tv_sec = 0; tk->raw_time.tv_nsec = 0; - tk->base_raw.tv64 = 0; if (boot.tv_sec == 0 && boot.tv_nsec == 0) boot = tk_xtime(tk); @@ -1127,7 +1258,7 @@ void __init timekeeping_init(void) raw_spin_unlock_irqrestore(&timekeeper_lock, flags); } -/* time in seconds when suspend began */ +/* time in seconds when suspend began for persistent clock */ static struct timespec64 timekeeping_suspend_time; /** @@ -1152,12 +1283,49 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk, tk_debug_account_sleep_time(delta); } +#if defined(CONFIG_PM_SLEEP) && defined(CONFIG_RTC_HCTOSYS_DEVICE) +/** + * We have three kinds of time sources to use for sleep time + * injection, the preference order is: + * 1) non-stop clocksource + * 2) persistent clock (ie: RTC accessible when irqs are off) + * 3) RTC + * + * 1) and 2) are used by timekeeping, 3) by RTC subsystem. + * If system has neither 1) nor 2), 3) will be used finally. + * + * + * If timekeeping has injected sleeptime via either 1) or 2), + * 3) becomes needless, so in this case we don't need to call + * rtc_resume(), and this is what timekeeping_rtc_skipresume() + * means. + */ +bool timekeeping_rtc_skipresume(void) +{ + return sleeptime_injected; +} + +/** + * 1) can be determined whether to use or not only when doing + * timekeeping_resume() which is invoked after rtc_suspend(), + * so we can't skip rtc_suspend() surely if system has 1). + * + * But if system has 2), 2) will definitely be used, so in this + * case we don't need to call rtc_suspend(), and this is what + * timekeeping_rtc_skipsuspend() means. + */ +bool timekeeping_rtc_skipsuspend(void) +{ + return persistent_clock_exists; +} + /** * timekeeping_inject_sleeptime64 - Adds suspend interval to timeekeeping values * @delta: pointer to a timespec64 delta value * - * This hook is for architectures that cannot support read_persistent_clock + * This hook is for architectures that cannot support read_persistent_clock64 * because their RTC/persistent clock is only accessible when irqs are enabled. + * and also don't have an effective nonstop clocksource. * * This function should only be called by rtc_resume(), and allows * a suspend offset to be injected into the timekeeping values. @@ -1167,13 +1335,6 @@ void timekeeping_inject_sleeptime64(struct timespec64 *delta) struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; - /* - * Make sure we don't set the clock twice, as timekeeping_resume() - * already did it - */ - if (has_persistent_clock()) - return; - raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); @@ -1189,26 +1350,21 @@ void timekeeping_inject_sleeptime64(struct timespec64 *delta) /* signal hrtimers about time change */ clock_was_set(); } +#endif /** * timekeeping_resume - Resumes the generic timekeeping subsystem. - * - * This is for the generic clocksource timekeeping. - * xtime/wall_to_monotonic/jiffies/etc are - * still managed by arch specific suspend/resume code. */ void timekeeping_resume(void) { struct timekeeper *tk = &tk_core.timekeeper; - struct clocksource *clock = tk->tkr.clock; + struct clocksource *clock = tk->tkr_mono.clock; unsigned long flags; struct timespec64 ts_new, ts_delta; - struct timespec tmp; cycle_t cycle_now, cycle_delta; - bool suspendtime_found = false; - read_persistent_clock(&tmp); - ts_new = timespec_to_timespec64(tmp); + sleeptime_injected = false; + read_persistent_clock64(&ts_new); clockevents_resume(); clocksource_resume(); @@ -1228,16 +1384,16 @@ void timekeeping_resume(void) * The less preferred source will only be tried if there is no better * usable source. The rtc part is handled separately in rtc core code. */ - cycle_now = tk->tkr.read(clock); + cycle_now = tk->tkr_mono.read(clock); if ((clock->flags & CLOCK_SOURCE_SUSPEND_NONSTOP) && - cycle_now > tk->tkr.cycle_last) { + cycle_now > tk->tkr_mono.cycle_last) { u64 num, max = ULLONG_MAX; u32 mult = clock->mult; u32 shift = clock->shift; s64 nsec = 0; - cycle_delta = clocksource_delta(cycle_now, tk->tkr.cycle_last, - tk->tkr.mask); + cycle_delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, + tk->tkr_mono.mask); /* * "cycle_delta * mutl" may cause 64 bits overflow, if the @@ -1253,17 +1409,19 @@ void timekeeping_resume(void) nsec += ((u64) cycle_delta * mult) >> shift; ts_delta = ns_to_timespec64(nsec); - suspendtime_found = true; + sleeptime_injected = true; } else if (timespec64_compare(&ts_new, &timekeeping_suspend_time) > 0) { ts_delta = timespec64_sub(ts_new, timekeeping_suspend_time); - suspendtime_found = true; + sleeptime_injected = true; } - if (suspendtime_found) + if (sleeptime_injected) __timekeeping_inject_sleeptime(tk, &ts_delta); /* Re-base the last cycle value */ - tk->tkr.cycle_last = cycle_now; + tk->tkr_mono.cycle_last = cycle_now; + tk->tkr_raw.cycle_last = cycle_now; + tk->ntp_error = 0; timekeeping_suspended = 0; timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); @@ -1272,9 +1430,7 @@ void timekeeping_resume(void) touch_softlockup_watchdog(); - clockevents_notify(CLOCK_EVT_NOTIFY_RESUME, NULL); - - /* Resume hrtimers */ + tick_resume(); hrtimers_resume(); } @@ -1284,10 +1440,8 @@ int timekeeping_suspend(void) unsigned long flags; struct timespec64 delta, delta_delta; static struct timespec64 old_delta; - struct timespec tmp; - read_persistent_clock(&tmp); - timekeeping_suspend_time = timespec_to_timespec64(tmp); + read_persistent_clock64(&timekeeping_suspend_time); /* * On some systems the persistent_clock can not be detected at @@ -1295,31 +1449,33 @@ int timekeeping_suspend(void) * value returned, update the persistent_clock_exists flag. */ if (timekeeping_suspend_time.tv_sec || timekeeping_suspend_time.tv_nsec) - persistent_clock_exist = true; + persistent_clock_exists = true; raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); timekeeping_suspended = 1; - /* - * To avoid drift caused by repeated suspend/resumes, - * which each can add ~1 second drift error, - * try to compensate so the difference in system time - * and persistent_clock time stays close to constant. - */ - delta = timespec64_sub(tk_xtime(tk), timekeeping_suspend_time); - delta_delta = timespec64_sub(delta, old_delta); - if (abs(delta_delta.tv_sec) >= 2) { + if (persistent_clock_exists) { /* - * if delta_delta is too large, assume time correction - * has occured and set old_delta to the current delta. + * To avoid drift caused by repeated suspend/resumes, + * which each can add ~1 second drift error, + * try to compensate so the difference in system time + * and persistent_clock time stays close to constant. */ - old_delta = delta; - } else { - /* Otherwise try to adjust old_system to compensate */ - timekeeping_suspend_time = - timespec64_add(timekeeping_suspend_time, delta_delta); + delta = timespec64_sub(tk_xtime(tk), timekeeping_suspend_time); + delta_delta = timespec64_sub(delta, old_delta); + if (abs(delta_delta.tv_sec) >= 2) { + /* + * if delta_delta is too large, assume time correction + * has occurred and set old_delta to the current delta. + */ + old_delta = delta; + } else { + /* Otherwise try to adjust old_system to compensate */ + timekeeping_suspend_time = + timespec64_add(timekeeping_suspend_time, delta_delta); + } } timekeeping_update(tk, TK_MIRROR); @@ -1327,7 +1483,7 @@ int timekeeping_suspend(void) write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); - clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL); + tick_suspend(); clocksource_suspend(); clockevents_suspend(); @@ -1416,15 +1572,15 @@ static __always_inline void timekeeping_apply_adjustment(struct timekeeper *tk, * * XXX - TODO: Doc ntp_error calculation. */ - if ((mult_adj > 0) && (tk->tkr.mult + mult_adj < mult_adj)) { + if ((mult_adj > 0) && (tk->tkr_mono.mult + mult_adj < mult_adj)) { /* NTP adjustment caused clocksource mult overflow */ WARN_ON_ONCE(1); return; } - tk->tkr.mult += mult_adj; + tk->tkr_mono.mult += mult_adj; tk->xtime_interval += interval; - tk->tkr.xtime_nsec -= offset; + tk->tkr_mono.xtime_nsec -= offset; tk->ntp_error -= (interval - offset) << tk->ntp_error_shift; } @@ -1486,13 +1642,13 @@ static void timekeeping_adjust(struct timekeeper *tk, s64 offset) tk->ntp_err_mult = 0; } - if (unlikely(tk->tkr.clock->maxadj && - (abs(tk->tkr.mult - tk->tkr.clock->mult) - > tk->tkr.clock->maxadj))) { + if (unlikely(tk->tkr_mono.clock->maxadj && + (abs(tk->tkr_mono.mult - tk->tkr_mono.clock->mult) + > tk->tkr_mono.clock->maxadj))) { printk_once(KERN_WARNING "Adjusting %s more than 11%% (%ld vs %ld)\n", - tk->tkr.clock->name, (long)tk->tkr.mult, - (long)tk->tkr.clock->mult + tk->tkr.clock->maxadj); + tk->tkr_mono.clock->name, (long)tk->tkr_mono.mult, + (long)tk->tkr_mono.clock->mult + tk->tkr_mono.clock->maxadj); } /* @@ -1509,9 +1665,9 @@ static void timekeeping_adjust(struct timekeeper *tk, s64 offset) * We'll correct this error next time through this function, when * xtime_nsec is not as small. */ - if (unlikely((s64)tk->tkr.xtime_nsec < 0)) { - s64 neg = -(s64)tk->tkr.xtime_nsec; - tk->tkr.xtime_nsec = 0; + if (unlikely((s64)tk->tkr_mono.xtime_nsec < 0)) { + s64 neg = -(s64)tk->tkr_mono.xtime_nsec; + tk->tkr_mono.xtime_nsec = 0; tk->ntp_error += neg << tk->ntp_error_shift; } } @@ -1526,13 +1682,13 @@ static void timekeeping_adjust(struct timekeeper *tk, s64 offset) */ static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk) { - u64 nsecps = (u64)NSEC_PER_SEC << tk->tkr.shift; + u64 nsecps = (u64)NSEC_PER_SEC << tk->tkr_mono.shift; unsigned int clock_set = 0; - while (tk->tkr.xtime_nsec >= nsecps) { + while (tk->tkr_mono.xtime_nsec >= nsecps) { int leap; - tk->tkr.xtime_nsec -= nsecps; + tk->tkr_mono.xtime_nsec -= nsecps; tk->xtime_sec++; /* Figure out if its a leap sec and apply if needed */ @@ -1577,9 +1733,10 @@ static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset, /* Accumulate one shifted interval */ offset -= interval; - tk->tkr.cycle_last += interval; + tk->tkr_mono.cycle_last += interval; + tk->tkr_raw.cycle_last += interval; - tk->tkr.xtime_nsec += tk->xtime_interval << shift; + tk->tkr_mono.xtime_nsec += tk->xtime_interval << shift; *clock_set |= accumulate_nsecs_to_secs(tk); /* Accumulate raw time */ @@ -1622,14 +1779,17 @@ void update_wall_time(void) #ifdef CONFIG_ARCH_USES_GETTIMEOFFSET offset = real_tk->cycle_interval; #else - offset = clocksource_delta(tk->tkr.read(tk->tkr.clock), - tk->tkr.cycle_last, tk->tkr.mask); + offset = clocksource_delta(tk->tkr_mono.read(tk->tkr_mono.clock), + tk->tkr_mono.cycle_last, tk->tkr_mono.mask); #endif /* Check if there's really nothing to do */ if (offset < real_tk->cycle_interval) goto out; + /* Do some additional sanity checking */ + timekeeping_check_update(real_tk, offset); + /* * With NO_HZ we may have to accumulate many cycle_intervals * (think "ticks") worth of time at once. To do this efficiently, @@ -1784,8 +1944,8 @@ ktime_t ktime_get_update_offsets_tick(ktime_t *offs_real, ktime_t *offs_boot, do { seq = read_seqcount_begin(&tk_core.seq); - base = tk->tkr.base_mono; - nsecs = tk->tkr.xtime_nsec >> tk->tkr.shift; + base = tk->tkr_mono.base; + nsecs = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift; *offs_real = tk->offs_real; *offs_boot = tk->offs_boot; @@ -1816,8 +1976,8 @@ ktime_t ktime_get_update_offsets_now(ktime_t *offs_real, ktime_t *offs_boot, do { seq = read_seqcount_begin(&tk_core.seq); - base = tk->tkr.base_mono; - nsecs = timekeeping_get_ns(&tk->tkr); + base = tk->tkr_mono.base; + nsecs = timekeeping_get_ns(&tk->tkr_mono); *offs_real = tk->offs_real; *offs_boot = tk->offs_boot; diff --git a/kernel/time/timekeeping.h b/kernel/time/timekeeping.h index 1d91416055d5..ead8794b9a4e 100644 --- a/kernel/time/timekeeping.h +++ b/kernel/time/timekeeping.h @@ -19,4 +19,11 @@ extern void timekeeping_clocktai(struct timespec *ts); extern int timekeeping_suspend(void); extern void timekeeping_resume(void); +extern void do_timer(unsigned long ticks); +extern void update_wall_time(void); + +extern seqlock_t jiffies_lock; + +#define CS_NAME_LEN 32 + #endif diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 2d3f5c504939..2ece3aa5069c 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -90,8 +90,18 @@ struct tvec_base { struct tvec tv5; } ____cacheline_aligned; +/* + * __TIMER_INITIALIZER() needs to set ->base to a valid pointer (because we've + * made NULL special, hint: lock_timer_base()) and we cannot get a compile time + * pointer to per-cpu entries because we don't know where we'll map the section, + * even for the boot cpu. + * + * And so we use boot_tvec_bases for boot CPU and per-cpu __tvec_bases for the + * rest of them. + */ struct tvec_base boot_tvec_bases; EXPORT_SYMBOL(boot_tvec_bases); + static DEFINE_PER_CPU(struct tvec_base *, tvec_bases) = &boot_tvec_bases; /* Functions below help us manage 'deferrable' flag */ @@ -1027,6 +1037,8 @@ int try_to_del_timer_sync(struct timer_list *timer) EXPORT_SYMBOL(try_to_del_timer_sync); #ifdef CONFIG_SMP +static DEFINE_PER_CPU(struct tvec_base, __tvec_bases); + /** * del_timer_sync - deactivate a timer and wait for the handler to finish. * @timer: the timer to be deactivated @@ -1532,64 +1544,6 @@ signed long __sched schedule_timeout_uninterruptible(signed long timeout) } EXPORT_SYMBOL(schedule_timeout_uninterruptible); -static int init_timers_cpu(int cpu) -{ - int j; - struct tvec_base *base; - static char tvec_base_done[NR_CPUS]; - - if (!tvec_base_done[cpu]) { - static char boot_done; - - if (boot_done) { - /* - * The APs use this path later in boot - */ - base = kzalloc_node(sizeof(*base), GFP_KERNEL, - cpu_to_node(cpu)); - if (!base) - return -ENOMEM; - - /* Make sure tvec_base has TIMER_FLAG_MASK bits free */ - if (WARN_ON(base != tbase_get_base(base))) { - kfree(base); - return -ENOMEM; - } - per_cpu(tvec_bases, cpu) = base; - } else { - /* - * This is for the boot CPU - we use compile-time - * static initialisation because per-cpu memory isn't - * ready yet and because the memory allocators are not - * initialised either. - */ - boot_done = 1; - base = &boot_tvec_bases; - } - spin_lock_init(&base->lock); - tvec_base_done[cpu] = 1; - base->cpu = cpu; - } else { - base = per_cpu(tvec_bases, cpu); - } - - - for (j = 0; j < TVN_SIZE; j++) { - INIT_LIST_HEAD(base->tv5.vec + j); - INIT_LIST_HEAD(base->tv4.vec + j); - INIT_LIST_HEAD(base->tv3.vec + j); - INIT_LIST_HEAD(base->tv2.vec + j); - } - for (j = 0; j < TVR_SIZE; j++) - INIT_LIST_HEAD(base->tv1.vec + j); - - base->timer_jiffies = jiffies; - base->next_timer = base->timer_jiffies; - base->active_timers = 0; - base->all_timers = 0; - return 0; -} - #ifdef CONFIG_HOTPLUG_CPU static void migrate_timer_list(struct tvec_base *new_base, struct list_head *head) { @@ -1631,55 +1585,86 @@ static void migrate_timers(int cpu) migrate_timer_list(new_base, old_base->tv5.vec + i); } + old_base->active_timers = 0; + old_base->all_timers = 0; + spin_unlock(&old_base->lock); spin_unlock_irq(&new_base->lock); put_cpu_var(tvec_bases); } -#endif /* CONFIG_HOTPLUG_CPU */ static int timer_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) { - long cpu = (long)hcpu; - int err; - - switch(action) { - case CPU_UP_PREPARE: - case CPU_UP_PREPARE_FROZEN: - err = init_timers_cpu(cpu); - if (err < 0) - return notifier_from_errno(err); - break; -#ifdef CONFIG_HOTPLUG_CPU + switch (action) { case CPU_DEAD: case CPU_DEAD_FROZEN: - migrate_timers(cpu); + migrate_timers((long)hcpu); break; -#endif default: break; } + return NOTIFY_OK; } -static struct notifier_block timers_nb = { - .notifier_call = timer_cpu_notify, -}; +static inline void timer_register_cpu_notifier(void) +{ + cpu_notifier(timer_cpu_notify, 0); +} +#else +static inline void timer_register_cpu_notifier(void) { } +#endif /* CONFIG_HOTPLUG_CPU */ +static void __init init_timer_cpu(struct tvec_base *base, int cpu) +{ + int j; -void __init init_timers(void) + BUG_ON(base != tbase_get_base(base)); + + base->cpu = cpu; + per_cpu(tvec_bases, cpu) = base; + spin_lock_init(&base->lock); + + for (j = 0; j < TVN_SIZE; j++) { + INIT_LIST_HEAD(base->tv5.vec + j); + INIT_LIST_HEAD(base->tv4.vec + j); + INIT_LIST_HEAD(base->tv3.vec + j); + INIT_LIST_HEAD(base->tv2.vec + j); + } + for (j = 0; j < TVR_SIZE; j++) + INIT_LIST_HEAD(base->tv1.vec + j); + + base->timer_jiffies = jiffies; + base->next_timer = base->timer_jiffies; +} + +static void __init init_timer_cpus(void) { - int err; + struct tvec_base *base; + int local_cpu = smp_processor_id(); + int cpu; + for_each_possible_cpu(cpu) { + if (cpu == local_cpu) + base = &boot_tvec_bases; +#ifdef CONFIG_SMP + else + base = per_cpu_ptr(&__tvec_bases, cpu); +#endif + + init_timer_cpu(base, cpu); + } +} + +void __init init_timers(void) +{ /* ensure there are enough low bits for flags in timer->base pointer */ BUILD_BUG_ON(__alignof__(struct tvec_base) & TIMER_FLAG_MASK); - err = timer_cpu_notify(&timers_nb, (unsigned long)CPU_UP_PREPARE, - (void *)(long)smp_processor_id()); - BUG_ON(err != NOTIFY_OK); - + init_timer_cpus(); init_timer_stats(); - register_cpu_notifier(&timers_nb); + timer_register_cpu_notifier(); open_softirq(TIMER_SOFTIRQ, run_timer_softirq); } diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index 61ed862cdd37..e878c2e0ba45 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -16,10 +16,10 @@ #include <linux/sched.h> #include <linux/seq_file.h> #include <linux/kallsyms.h> -#include <linux/tick.h> #include <asm/uaccess.h> +#include "tick-internal.h" struct timer_list_iter { int cpu; @@ -228,9 +228,35 @@ print_tickdevice(struct seq_file *m, struct tick_device *td, int cpu) print_name_offset(m, dev->set_next_event); SEQ_printf(m, "\n"); - SEQ_printf(m, " set_mode: "); - print_name_offset(m, dev->set_mode); - SEQ_printf(m, "\n"); + if (dev->set_mode) { + SEQ_printf(m, " set_mode: "); + print_name_offset(m, dev->set_mode); + SEQ_printf(m, "\n"); + } else { + if (dev->set_state_shutdown) { + SEQ_printf(m, " shutdown: "); + print_name_offset(m, dev->set_state_shutdown); + SEQ_printf(m, "\n"); + } + + if (dev->set_state_periodic) { + SEQ_printf(m, " periodic: "); + print_name_offset(m, dev->set_state_periodic); + SEQ_printf(m, "\n"); + } + + if (dev->set_state_oneshot) { + SEQ_printf(m, " oneshot: "); + print_name_offset(m, dev->set_state_oneshot); + SEQ_printf(m, "\n"); + } + + if (dev->tick_resume) { + SEQ_printf(m, " resume: "); + print_name_offset(m, dev->tick_resume); + SEQ_printf(m, "\n"); + } + } SEQ_printf(m, " event_handler: "); print_name_offset(m, dev->event_handler); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index c5cefb3c009c..36b6fa88ce5b 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -865,6 +865,19 @@ config SCHED_STACK_END_CHECK data corruption or a sporadic crash at a later stage once the region is examined. The runtime overhead introduced is minimal. +config DEBUG_TIMEKEEPING + bool "Enable extra timekeeping sanity checking" + help + This option will enable additional timekeeping sanity checks + which may be helpful when diagnosing issues where timekeeping + problems are suspected. + + This may include checks in the timekeeping hotpaths, so this + option may have a (very small) performance impact to some + workloads. + + If unsure, say N. + config TIMER_STATS bool "Collect kernel timers statistics" depends on DEBUG_KERNEL && PROC_FS diff --git a/lib/lockref.c b/lib/lockref.c index ecb9a665ec19..494994bf17c8 100644 --- a/lib/lockref.c +++ b/lib/lockref.c @@ -18,7 +18,7 @@ #define CMPXCHG_LOOP(CODE, SUCCESS) do { \ struct lockref old; \ BUILD_BUG_ON(sizeof(old) != 8); \ - old.lock_count = ACCESS_ONCE(lockref->lock_count); \ + old.lock_count = READ_ONCE(lockref->lock_count); \ while (likely(arch_spin_value_unlocked(old.lock.rlock.raw_lock))) { \ struct lockref new = old, prev = old; \ CODE \ diff --git a/mm/mremap.c b/mm/mremap.c index 57dadc025c64..2dc44b1cb1df 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -286,8 +286,14 @@ static unsigned long move_vma(struct vm_area_struct *vma, old_len = new_len; old_addr = new_addr; new_addr = -ENOMEM; - } else if (vma->vm_file && vma->vm_file->f_op->mremap) - vma->vm_file->f_op->mremap(vma->vm_file, new_vma); + } else if (vma->vm_file && vma->vm_file->f_op->mremap) { + err = vma->vm_file->f_op->mremap(vma->vm_file, new_vma); + if (err < 0) { + move_page_tables(new_vma, new_addr, vma, old_addr, + moved_len, true); + return err; + } + } /* Conceal VM_ACCOUNT so old reservation is not undone */ if (vm_flags & VM_ACCOUNT) { diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 6b3f54ed65ba..a9f4ae45b7fb 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -484,7 +484,7 @@ static int ceph_tcp_connect(struct ceph_connection *con) IPPROTO_TCP, &sock); if (ret) return ret; - sock->sk->sk_allocation = GFP_NOFS | __GFP_MEMALLOC; + sock->sk->sk_allocation = GFP_NOFS; #ifdef CONFIG_LOCKDEP lockdep_set_class(&sock->sk->sk_lock, &socket_class); @@ -520,8 +520,6 @@ static int ceph_tcp_connect(struct ceph_connection *con) ret); } - sk_set_memalloc(sock->sk); - con->sock = sock; return 0; } @@ -2808,11 +2806,8 @@ static void con_work(struct work_struct *work) { struct ceph_connection *con = container_of(work, struct ceph_connection, work.work); - unsigned long pflags = current->flags; bool fault; - current->flags |= PF_MEMALLOC; - mutex_lock(&con->mutex); while (true) { int ret; @@ -2866,8 +2861,6 @@ static void con_work(struct work_struct *work) con_fault_finish(con); con->ops->put(con); - - tsk_restore_flags(current, pflags, PF_MEMALLOC); } /* diff --git a/sound/firewire/bebob/bebob_maudio.c b/sound/firewire/bebob/bebob_maudio.c index a422aaa3bb0c..9ee25a63f684 100644 --- a/sound/firewire/bebob/bebob_maudio.c +++ b/sound/firewire/bebob/bebob_maudio.c @@ -96,10 +96,10 @@ int snd_bebob_maudio_load_firmware(struct fw_unit *unit) struct fw_device *device = fw_parent_device(unit); int err, rcode; u64 date; - __be32 cues[3] = { - MAUDIO_BOOTLOADER_CUE1, - MAUDIO_BOOTLOADER_CUE2, - MAUDIO_BOOTLOADER_CUE3 + __le32 cues[3] = { + cpu_to_le32(MAUDIO_BOOTLOADER_CUE1), + cpu_to_le32(MAUDIO_BOOTLOADER_CUE2), + cpu_to_le32(MAUDIO_BOOTLOADER_CUE3) }; /* check date of software used to build */ diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 74382137b9f5..f9d12c0a7e5a 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -2912,6 +2912,8 @@ static void alc283_init(struct hda_codec *codec) if (!hp_pin) return; + + msleep(30); hp_pin_sense = snd_hda_jack_detect(codec, hp_pin); /* Index 0x43 Direct Drive HP AMP LPM Control 1 */ @@ -3607,6 +3609,7 @@ static void alc_headset_mode_unplugged(struct hda_codec *codec) switch (codec->vendor_id) { case 0x10ec0255: + case 0x10ec0256: alc_process_coef_fw(codec, coef0255); break; case 0x10ec0233: @@ -3662,6 +3665,7 @@ static void alc_headset_mode_mic_in(struct hda_codec *codec, hda_nid_t hp_pin, switch (codec->vendor_id) { case 0x10ec0255: + case 0x10ec0256: alc_write_coef_idx(codec, 0x45, 0xc489); snd_hda_set_pin_ctl_cache(codec, hp_pin, 0); alc_process_coef_fw(codec, coef0255); @@ -3731,6 +3735,7 @@ static void alc_headset_mode_default(struct hda_codec *codec) switch (codec->vendor_id) { case 0x10ec0255: + case 0x10ec0256: alc_process_coef_fw(codec, coef0255); break; case 0x10ec0233: @@ -3785,6 +3790,7 @@ static void alc_headset_mode_ctia(struct hda_codec *codec) switch (codec->vendor_id) { case 0x10ec0255: + case 0x10ec0256: alc_process_coef_fw(codec, coef0255); break; case 0x10ec0233: @@ -3839,6 +3845,7 @@ static void alc_headset_mode_omtp(struct hda_codec *codec) switch (codec->vendor_id) { case 0x10ec0255: + case 0x10ec0256: alc_process_coef_fw(codec, coef0255); break; case 0x10ec0233: @@ -3884,6 +3891,7 @@ static void alc_determine_headset_type(struct hda_codec *codec) switch (codec->vendor_id) { case 0x10ec0255: + case 0x10ec0256: alc_process_coef_fw(codec, coef0255); msleep(300); val = alc_read_coef_idx(codec, 0x46); @@ -4364,6 +4372,7 @@ enum { ALC269_FIXUP_QUANTA_MUTE, ALC269_FIXUP_LIFEBOOK, ALC269_FIXUP_LIFEBOOK_EXTMIC, + ALC269_FIXUP_LIFEBOOK_HP_PIN, ALC269_FIXUP_AMIC, ALC269_FIXUP_DMIC, ALC269VB_FIXUP_AMIC, @@ -4517,6 +4526,13 @@ static const struct hda_fixup alc269_fixups[] = { { } }, }, + [ALC269_FIXUP_LIFEBOOK_HP_PIN] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x21, 0x0221102f }, /* HP out */ + { } + }, + }, [ALC269_FIXUP_AMIC] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { @@ -5010,6 +5026,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x104d, 0x9084, "Sony VAIO", ALC275_FIXUP_SONY_HWEQ), SND_PCI_QUIRK(0x104d, 0x9099, "Sony VAIO S13", ALC275_FIXUP_SONY_DISABLE_AAMIX), SND_PCI_QUIRK(0x10cf, 0x1475, "Lifebook", ALC269_FIXUP_LIFEBOOK), + SND_PCI_QUIRK(0x10cf, 0x15dc, "Lifebook T731", ALC269_FIXUP_LIFEBOOK_HP_PIN), SND_PCI_QUIRK(0x10cf, 0x1845, "Lifebook U904", ALC269_FIXUP_LIFEBOOK_EXTMIC), SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC), SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_BXBT2807_MIC), @@ -5217,6 +5234,16 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x17, 0x40000000}, {0x1d, 0x40700001}, {0x21, 0x02211050}), + SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, + {0x12, 0x90a60140}, + {0x13, 0x40000000}, + {0x14, 0x90170110}, + {0x19, 0x411111f0}, + {0x1a, 0x411111f0}, + {0x1b, 0x411111f0}, + {0x1d, 0x40700001}, + {0x1e, 0x411111f0}, + {0x21, 0x02211020}), SND_HDA_PIN_QUIRK(0x10ec0280, 0x103c, "HP", ALC280_FIXUP_HP_GPIO4, {0x12, 0x90a60130}, {0x13, 0x40000000}, diff --git a/sound/soc/codecs/pcm512x.c b/sound/soc/codecs/pcm512x.c index 9974f201a08f..474cae82a874 100644 --- a/sound/soc/codecs/pcm512x.c +++ b/sound/soc/codecs/pcm512x.c @@ -1156,25 +1156,6 @@ static int pcm512x_hw_params(struct snd_pcm_substream *substream, ret, pcm512x->pll_out); return ret; } - - gpio = PCM512x_G1OE << (4 - 1); - ret = regmap_update_bits(pcm512x->regmap, PCM512x_GPIO_EN, - gpio, gpio); - if (ret != 0) { - dev_err(codec->dev, "Failed to enable gpio %d: %d\n", - 4, ret); - return ret; - } - - gpio = PCM512x_GPIO_OUTPUT_1 + 4 - 1; - ret = regmap_update_bits(pcm512x->regmap, gpio, - PCM512x_GxSL, PCM512x_GxSL_PLLLK); - if (ret != 0) { - dev_err(codec->dev, - "Failed to output pll lock on %d: %d\n", - ret, 4); - return ret; - } } ret = regmap_update_bits(pcm512x->regmap, PCM512x_SYNCHRONIZE, diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c index dc9df007d3e3..337c317ead6f 100644 --- a/sound/usb/mixer_quirks.c +++ b/sound/usb/mixer_quirks.c @@ -192,6 +192,7 @@ static const struct rc_config { { USB_ID(0x041e, 0x3040), 2, 2, 6, 6, 2, 0x6e91 }, /* Live! 24-bit */ { USB_ID(0x041e, 0x3042), 0, 1, 1, 1, 1, 0x000d }, /* Usb X-Fi S51 */ { USB_ID(0x041e, 0x30df), 0, 1, 1, 1, 1, 0x000d }, /* Usb X-Fi S51 Pro */ + { USB_ID(0x041e, 0x3237), 0, 1, 1, 1, 1, 0x000d }, /* Usb X-Fi S51 Pro */ { USB_ID(0x041e, 0x3048), 2, 2, 6, 6, 2, 0x6e91 }, /* Toshiba SB0500 */ }; diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 753a47de8459..9a28365126f9 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1113,8 +1113,13 @@ void snd_usb_set_format_quirk(struct snd_usb_substream *subs, bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip) { - /* MS Lifecam HD-5000 doesn't support reading the sample rate. */ - return chip->usb_id == USB_ID(0x045E, 0x076D); + /* devices which do not support reading the sample rate. */ + switch (chip->usb_id) { + case USB_ID(0x045E, 0x076D): /* MS Lifecam HD-5000 */ + case USB_ID(0x04D8, 0xFEEA): /* Benchmark DAC1 Pre */ + return true; + } + return false; } /* Marantz/Denon USB DACs need a vendor cmd to switch diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 67360e43852c..95abddcd7839 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -56,7 +56,40 @@ clean_hotplug: make -C $$TARGET clean; \ done; +INSTALL_PATH ?= install +INSTALL_PATH := $(abspath $(INSTALL_PATH)) +ALL_SCRIPT := $(INSTALL_PATH)/run_kselftest.sh + +install: +ifdef INSTALL_PATH + @# Ask all targets to install their files + mkdir -p $(INSTALL_PATH) + for TARGET in $(TARGETS); do \ + mkdir -p $(INSTALL_PATH)/$$TARGET ; \ + make -C $$TARGET INSTALL_PATH=$(INSTALL_PATH)/$$TARGET install; \ + done; + + @# Ask all targets to emit their test scripts + echo "#!/bin/bash" > $(ALL_SCRIPT) + echo "cd \$$(dirname \$$0)" >> $(ALL_SCRIPT) + echo "ROOT=\$$PWD" >> $(ALL_SCRIPT) + + for TARGET in $(TARGETS); do \ + echo "echo ; echo Running tests in $$TARGET" >> $(ALL_SCRIPT); \ + echo "echo ========================================" >> $(ALL_SCRIPT); \ + echo "cd $$TARGET" >> $(ALL_SCRIPT); \ + make -s --no-print-directory -C $$TARGET emit_tests >> $(ALL_SCRIPT); \ + echo "cd \$$ROOT" >> $(ALL_SCRIPT); \ + done; + + chmod u+x $(ALL_SCRIPT) +else + $(error Error: set INSTALL_PATH to use install) +endif + clean: for TARGET in $(TARGETS); do \ make -C $$TARGET clean; \ done; + +.PHONY: install diff --git a/tools/testing/selftests/breakpoints/Makefile b/tools/testing/selftests/breakpoints/Makefile index e18b42b254af..182235640209 100644 --- a/tools/testing/selftests/breakpoints/Makefile +++ b/tools/testing/selftests/breakpoints/Makefile @@ -16,8 +16,9 @@ else echo "Not an x86 target, can't build breakpoints selftests" endif -run_tests: - @./breakpoint_test || echo "breakpoints selftests: [FAIL]" +TEST_PROGS := breakpoint_test + +include ../lib.mk clean: rm -fr breakpoint_test diff --git a/tools/testing/selftests/cpu-hotplug/Makefile b/tools/testing/selftests/cpu-hotplug/Makefile index e9c28d8dc84b..fe1f99101c5d 100644 --- a/tools/testing/selftests/cpu-hotplug/Makefile +++ b/tools/testing/selftests/cpu-hotplug/Makefile @@ -1,9 +1,10 @@ all: -run_tests: - @/bin/bash ./on-off-test.sh || echo "cpu-hotplug selftests: [FAIL]" +TEST_PROGS := cpu-on-off-test.sh + +include ../lib.mk run_full_test: - @/bin/bash ./on-off-test.sh -a || echo "cpu-hotplug selftests: [FAIL]" + @/bin/bash ./cpu-on-off-test.sh -a || echo "cpu-hotplug selftests: [FAIL]" clean: diff --git a/tools/testing/selftests/cpu-hotplug/on-off-test.sh b/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh index 98b1d6565f2c..98b1d6565f2c 100644..100755 --- a/tools/testing/selftests/cpu-hotplug/on-off-test.sh +++ b/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh diff --git a/tools/testing/selftests/efivarfs/Makefile b/tools/testing/selftests/efivarfs/Makefile index 29e8c6bc81b0..736c3ddfc787 100644 --- a/tools/testing/selftests/efivarfs/Makefile +++ b/tools/testing/selftests/efivarfs/Makefile @@ -1,12 +1,13 @@ -CC = $(CROSS_COMPILE)gcc CFLAGS = -Wall test_objs = open-unlink create-read all: $(test_objs) -run_tests: all - @/bin/bash ./efivarfs.sh || echo "efivarfs selftests: [FAIL]" +TEST_PROGS := efivarfs.sh +TEST_FILES := $(test_objs) + +include ../lib.mk clean: rm -f $(test_objs) diff --git a/tools/testing/selftests/efivarfs/efivarfs.sh b/tools/testing/selftests/efivarfs/efivarfs.sh index 77edcdcc016b..77edcdcc016b 100644..100755 --- a/tools/testing/selftests/efivarfs/efivarfs.sh +++ b/tools/testing/selftests/efivarfs/efivarfs.sh diff --git a/tools/testing/selftests/exec/Makefile b/tools/testing/selftests/exec/Makefile index 66dfc2ce1788..4edb7d0da29b 100644 --- a/tools/testing/selftests/exec/Makefile +++ b/tools/testing/selftests/exec/Makefile @@ -1,4 +1,3 @@ -CC = $(CROSS_COMPILE)gcc CFLAGS = -Wall BINARIES = execveat DEPS = execveat.symlink execveat.denatured script subdir @@ -18,8 +17,12 @@ execveat.denatured: execveat %: %.c $(CC) $(CFLAGS) -o $@ $^ -run_tests: all - ./execveat +TEST_PROGS := execveat +TEST_FILES := $(DEPS) + +include ../lib.mk + +override EMIT_TESTS := echo "mkdir -p subdir; (./execveat && echo \"selftests: execveat [PASS]\") || echo \"selftests: execveat [FAIL]\"" clean: rm -rf $(BINARIES) $(DEPS) subdir.moved execveat.moved xxxxx* diff --git a/tools/testing/selftests/firmware/Makefile b/tools/testing/selftests/firmware/Makefile index e23cce0bbc3a..9bf82234855b 100644 --- a/tools/testing/selftests/firmware/Makefile +++ b/tools/testing/selftests/firmware/Makefile @@ -3,25 +3,9 @@ # No binaries, but make sure arg-less "make" doesn't trigger "run_tests" all: -fw_filesystem: - @if /bin/sh ./fw_filesystem.sh ; then \ - echo "fw_filesystem: ok"; \ - else \ - echo "fw_filesystem: [FAIL]"; \ - exit 1; \ - fi +TEST_PROGS := fw_filesystem.sh fw_userhelper.sh -fw_userhelper: - @if /bin/sh ./fw_userhelper.sh ; then \ - echo "fw_userhelper: ok"; \ - else \ - echo "fw_userhelper: [FAIL]"; \ - exit 1; \ - fi - -run_tests: all fw_filesystem fw_userhelper +include ../lib.mk # Nothing to clean up. clean: - -.PHONY: all clean run_tests fw_filesystem fw_userhelper diff --git a/tools/testing/selftests/firmware/fw_filesystem.sh b/tools/testing/selftests/firmware/fw_filesystem.sh index 3fc6c10c2479..3fc6c10c2479 100644..100755 --- a/tools/testing/selftests/firmware/fw_filesystem.sh +++ b/tools/testing/selftests/firmware/fw_filesystem.sh diff --git a/tools/testing/selftests/firmware/fw_userhelper.sh b/tools/testing/selftests/firmware/fw_userhelper.sh index 6efbade12139..6efbade12139 100644..100755 --- a/tools/testing/selftests/firmware/fw_userhelper.sh +++ b/tools/testing/selftests/firmware/fw_userhelper.sh diff --git a/tools/testing/selftests/ftrace/Makefile b/tools/testing/selftests/ftrace/Makefile index 76cc9f156267..346720639d1d 100644 --- a/tools/testing/selftests/ftrace/Makefile +++ b/tools/testing/selftests/ftrace/Makefile @@ -1,7 +1,8 @@ all: -run_tests: - @/bin/sh ./ftracetest || echo "ftrace selftests: [FAIL]" +TEST_PROGS := ftracetest + +include ../lib.mk clean: rm -rf logs/* diff --git a/tools/testing/selftests/ftrace/test.d/00basic/basic4.tc b/tools/testing/selftests/ftrace/test.d/00basic/basic4.tc index fd9c49a13612..aa51f6c17359 100644 --- a/tools/testing/selftests/ftrace/test.d/00basic/basic4.tc +++ b/tools/testing/selftests/ftrace/test.d/00basic/basic4.tc @@ -2,4 +2,4 @@ # description: Basic event tracing check test -f available_events -a -f set_event -a -d events # check scheduler events are available -grep -q sched available_events && exit 0 || exit -1
\ No newline at end of file +grep -q sched available_events && exit 0 || exit $FAIL diff --git a/tools/testing/selftests/ftrace/test.d/event/event-enable.tc b/tools/testing/selftests/ftrace/test.d/event/event-enable.tc index 668616d9bb03..87eb9d6dd4ca 100644 --- a/tools/testing/selftests/ftrace/test.d/event/event-enable.tc +++ b/tools/testing/selftests/ftrace/test.d/event/event-enable.tc @@ -9,7 +9,11 @@ do_reset() { fail() { #msg do_reset echo $1 - exit -1 + exit $FAIL +} + +yield() { + ping localhost -c 1 || sleep .001 || usleep 1 || sleep 1 } if [ ! -f set_event -o ! -d events/sched ]; then @@ -21,7 +25,8 @@ reset_tracer do_reset echo 'sched:sched_switch' > set_event -usleep 1 + +yield count=`cat trace | grep sched_switch | wc -l` if [ $count -eq 0 ]; then @@ -31,7 +36,8 @@ fi do_reset echo 1 > events/sched/sched_switch/enable -usleep 1 + +yield count=`cat trace | grep sched_switch | wc -l` if [ $count -eq 0 ]; then @@ -41,7 +47,8 @@ fi do_reset echo 0 > events/sched/sched_switch/enable -usleep 1 + +yield count=`cat trace | grep sched_switch | wc -l` if [ $count -ne 0 ]; then diff --git a/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc b/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc index 655c415b6e7f..ced27ef0638f 100644 --- a/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc +++ b/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc @@ -9,7 +9,11 @@ do_reset() { fail() { #msg do_reset echo $1 - exit -1 + exit $FAIL +} + +yield() { + ping localhost -c 1 || sleep .001 || usleep 1 || sleep 1 } if [ ! -f set_event -o ! -d events/sched ]; then @@ -21,7 +25,8 @@ reset_tracer do_reset echo 'sched:*' > set_event -usleep 1 + +yield count=`cat trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` if [ $count -lt 3 ]; then @@ -31,7 +36,8 @@ fi do_reset echo 1 > events/sched/enable -usleep 1 + +yield count=`cat trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` if [ $count -lt 3 ]; then @@ -41,7 +47,8 @@ fi do_reset echo 0 > events/sched/enable -usleep 1 + +yield count=`cat trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` if [ $count -ne 0 ]; then diff --git a/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc b/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc index 480845774007..0bb5df3c00d4 100644 --- a/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc +++ b/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc @@ -9,7 +9,11 @@ do_reset() { fail() { #msg do_reset echo $1 - exit -1 + exit $FAIL +} + +yield() { + ping localhost -c 1 || sleep .001 || usleep 1 || sleep 1 } if [ ! -f available_events -o ! -f set_event -o ! -d events ]; then @@ -21,6 +25,9 @@ reset_tracer do_reset echo '*:*' > set_event + +yield + count=`cat trace | grep -v ^# | wc -l` if [ $count -eq 0 ]; then fail "none of events are recorded" @@ -29,6 +36,9 @@ fi do_reset echo 1 > events/enable + +yield + count=`cat trace | grep -v ^# | wc -l` if [ $count -eq 0 ]; then fail "none of events are recorded" @@ -37,6 +47,9 @@ fi do_reset echo 0 > events/enable + +yield + count=`cat trace | grep -v ^# | wc -l` if [ $count -ne 0 ]; then fail "any of events should not be recorded" diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter-stack.tc b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter-stack.tc index c15e018e0220..15c2dba06ea2 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter-stack.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter-stack.tc @@ -16,7 +16,9 @@ fi do_reset() { reset_tracer - echo 0 > /proc/sys/kernel/stack_tracer_enabled + if [ -e /proc/sys/kernel/stack_tracer_enabled ]; then + echo 0 > /proc/sys/kernel/stack_tracer_enabled + fi enable_tracing clear_trace echo > set_ftrace_filter @@ -25,7 +27,7 @@ do_reset() { fail() { # msg do_reset echo $1 - exit -1 + exit $FAIL } disable_tracing diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc index 6af5f6360b18..0ab2189613ef 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc @@ -17,7 +17,7 @@ do_reset() { fail() { # msg do_reset echo $1 - exit -1 + exit $FAIL } disable_tracing diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc index 2e719cb1fc4d..7808336d6f50 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc @@ -31,7 +31,7 @@ fail() { # mesg reset_tracer echo > set_ftrace_filter echo $1 - exit -1 + exit $FAIL } echo "Testing function tracer with profiler:" diff --git a/tools/testing/selftests/gen_kselftest_tar.sh b/tools/testing/selftests/gen_kselftest_tar.sh new file mode 100755 index 000000000000..17d5bd0c0936 --- /dev/null +++ b/tools/testing/selftests/gen_kselftest_tar.sh @@ -0,0 +1,55 @@ +#!/bin/bash +# +# gen_kselftest_tar +# Generate kselftest tarball +# Author: Shuah Khan <shuahkh@osg.samsung.com> +# Copyright (C) 2015 Samsung Electronics Co., Ltd. + +# This software may be freely redistributed under the terms of the GNU +# General Public License (GPLv2). + +# main +main() +{ + if [ "$#" -eq 0 ]; then + echo "$0: Generating default compression gzip" + copts="cvzf" + ext=".tar.gz" + else + case "$1" in + tar) + copts="cvf" + ext=".tar" + ;; + targz) + copts="cvzf" + ext=".tar.gz" + ;; + tarbz2) + copts="cvjf" + ext=".tar.bz2" + ;; + tarxz) + copts="cvJf" + ext=".tar.xz" + ;; + *) + echo "Unknown tarball format $1" + exit 1 + ;; + esac + fi + + install_dir=./kselftest + +# Run install using INSTALL_KSFT_PATH override to generate install +# directory +./kselftest_install.sh +tar $copts kselftest${ext} $install_dir +echo "Kselftest archive kselftest${ext} created!" + +# clean up install directory +rm -rf kselftest +} + +main "$@" diff --git a/tools/testing/selftests/ipc/Makefile b/tools/testing/selftests/ipc/Makefile index 74bbefdeaf4c..25d2e702c68a 100644 --- a/tools/testing/selftests/ipc/Makefile +++ b/tools/testing/selftests/ipc/Makefile @@ -12,14 +12,11 @@ endif CFLAGS += -I../../../../usr/include/ all: -ifeq ($(ARCH),x86) - gcc $(CFLAGS) msgque.c -o msgque_test -else - echo "Not an x86 target, can't build msgque selftest" -endif + $(CC) $(CFLAGS) msgque.c -o msgque_test + +TEST_PROGS := msgque_test -run_tests: all - ./msgque_test +include ../lib.mk clean: rm -fr ./msgque_test diff --git a/tools/testing/selftests/kcmp/Makefile b/tools/testing/selftests/kcmp/Makefile index ff0eefdc6ceb..2ae7450a9a89 100644 --- a/tools/testing/selftests/kcmp/Makefile +++ b/tools/testing/selftests/kcmp/Makefile @@ -1,10 +1,10 @@ -CC := $(CROSS_COMPILE)$(CC) CFLAGS += -I../../../../usr/include/ all: kcmp_test -run_tests: all - @./kcmp_test || echo "kcmp_test: [FAIL]" +TEST_PROGS := kcmp_test + +include ../lib.mk clean: $(RM) kcmp_test kcmp-test-file diff --git a/tools/testing/selftests/kselftest_install.sh b/tools/testing/selftests/kselftest_install.sh new file mode 100755 index 000000000000..1555fbdb08da --- /dev/null +++ b/tools/testing/selftests/kselftest_install.sh @@ -0,0 +1,37 @@ +#!/bin/bash +# +# Kselftest Install +# Install kselftest tests +# Author: Shuah Khan <shuahkh@osg.samsung.com> +# Copyright (C) 2015 Samsung Electronics Co., Ltd. + +# This software may be freely redistributed under the terms of the GNU +# General Public License (GPLv2). + +install_loc=`pwd` + +main() +{ + if [ $(basename $install_loc) != "selftests" ]; then + echo "$0: Please run it in selftests directory ..." + exit 1; + fi + if [ "$#" -eq 0 ]; then + echo "$0: Installing in default location - $install_loc ..." + elif [ ! -d "$1" ]; then + echo "$0: $1 doesn't exist!!" + exit 1; + else + install_loc=$1 + echo "$0: Installing in specified location - $install_loc ..." + fi + + install_dir=$install_loc/kselftest + +# Create install directory + mkdir -p $install_dir +# Build tests + INSTALL_PATH=$install_dir make install +} + +main "$@" diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk new file mode 100644 index 000000000000..2194155ae62a --- /dev/null +++ b/tools/testing/selftests/lib.mk @@ -0,0 +1,35 @@ +# This mimics the top-level Makefile. We do it explicitly here so that this +# Makefile can operate with or without the kbuild infrastructure. +CC := $(CROSS_COMPILE)gcc + +define RUN_TESTS + @for TEST in $(TEST_PROGS); do \ + (./$$TEST && echo "selftests: $$TEST [PASS]") || echo "selftests: $$TEST [FAIL]"; \ + done; +endef + +run_tests: all + $(RUN_TESTS) + +define INSTALL_RULE + mkdir -p $(INSTALL_PATH) + install -t $(INSTALL_PATH) $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) +endef + +install: all +ifdef INSTALL_PATH + $(INSTALL_RULE) +else + $(error Error: set INSTALL_PATH to use install) +endif + +define EMIT_TESTS + @for TEST in $(TEST_PROGS); do \ + echo "(./$$TEST && echo \"selftests: $$TEST [PASS]\") || echo \"selftests: $$TEST [FAIL]\""; \ + done; +endef + +emit_tests: + $(EMIT_TESTS) + +.PHONY: run_tests all clean install emit_tests diff --git a/tools/testing/selftests/memfd/Makefile b/tools/testing/selftests/memfd/Makefile index b80cd10d53ba..3e7eb7972511 100644 --- a/tools/testing/selftests/memfd/Makefile +++ b/tools/testing/selftests/memfd/Makefile @@ -1,17 +1,19 @@ +CC = $(CROSS_COMPILE)gcc CFLAGS += -D_FILE_OFFSET_BITS=64 CFLAGS += -I../../../../include/uapi/ CFLAGS += -I../../../../include/ +CFLAGS += -I../../../../usr/include/ all: - gcc $(CFLAGS) memfd_test.c -o memfd_test + $(CC) $(CFLAGS) memfd_test.c -o memfd_test -run_tests: all - gcc $(CFLAGS) memfd_test.c -o memfd_test - @./memfd_test || echo "memfd_test: [FAIL]" +TEST_PROGS := memfd_test + +include ../lib.mk build_fuse: - gcc $(CFLAGS) fuse_mnt.c `pkg-config fuse --cflags --libs` -o fuse_mnt - gcc $(CFLAGS) fuse_test.c -o fuse_test + $(CC) $(CFLAGS) fuse_mnt.c `pkg-config fuse --cflags --libs` -o fuse_mnt + $(CC) $(CFLAGS) fuse_test.c -o fuse_test run_fuse: build_fuse @./run_fuse_test.sh || echo "fuse_test: [FAIL]" diff --git a/tools/testing/selftests/memory-hotplug/Makefile b/tools/testing/selftests/memory-hotplug/Makefile index d46b8d489cd2..afb2624c7048 100644 --- a/tools/testing/selftests/memory-hotplug/Makefile +++ b/tools/testing/selftests/memory-hotplug/Makefile @@ -1,9 +1,12 @@ all: -run_tests: - @/bin/bash ./on-off-test.sh -r 2 || echo "memory-hotplug selftests: [FAIL]" +include ../lib.mk + +TEST_PROGS := mem-on-off-test.sh +override RUN_TESTS := ./mem-on-off-test.sh -r 2 || echo "selftests: memory-hotplug [FAIL]" +override EMIT_TESTS := echo "$(RUN_TESTS)" run_full_test: - @/bin/bash ./on-off-test.sh || echo "memory-hotplug selftests: [FAIL]" + @/bin/bash ./mem-on-off-test.sh || echo "memory-hotplug selftests: [FAIL]" clean: diff --git a/tools/testing/selftests/memory-hotplug/on-off-test.sh b/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh index 6cddde0b96f8..6cddde0b96f8 100644..100755 --- a/tools/testing/selftests/memory-hotplug/on-off-test.sh +++ b/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh diff --git a/tools/testing/selftests/mount/.gitignore b/tools/testing/selftests/mount/.gitignore new file mode 100644 index 000000000000..856ad4107eb3 --- /dev/null +++ b/tools/testing/selftests/mount/.gitignore @@ -0,0 +1 @@ +unprivileged-remount-test diff --git a/tools/testing/selftests/mount/Makefile b/tools/testing/selftests/mount/Makefile index 337d853c2b72..95580a97326e 100644 --- a/tools/testing/selftests/mount/Makefile +++ b/tools/testing/selftests/mount/Makefile @@ -1,17 +1,16 @@ # Makefile for mount selftests. - +CFLAGS = -Wall \ + -O2 all: unprivileged-remount-test unprivileged-remount-test: unprivileged-remount-test.c - gcc -Wall -O2 unprivileged-remount-test.c -o unprivileged-remount-test + $(CC) $(CFLAGS) unprivileged-remount-test.c -o unprivileged-remount-test -# Allow specific tests to be selected. -test_unprivileged_remount: unprivileged-remount-test - @if [ -f /proc/self/uid_map ] ; then ./unprivileged-remount-test ; fi +include ../lib.mk -run_tests: all test_unprivileged_remount +TEST_PROGS := unprivileged-remount-test +override RUN_TESTS := if [ -f /proc/self/uid_map ] ; then ./unprivileged-remount-test ; fi +override EMIT_TESTS := echo "$(RUN_TESTS)" clean: rm -f unprivileged-remount-test - -.PHONY: all test_unprivileged_remount diff --git a/tools/testing/selftests/mqueue/Makefile b/tools/testing/selftests/mqueue/Makefile index 8056e2e68fa4..0e3b41eb85cd 100644 --- a/tools/testing/selftests/mqueue/Makefile +++ b/tools/testing/selftests/mqueue/Makefile @@ -1,10 +1,22 @@ +CFLAGS = -O2 + all: - gcc -O2 mq_open_tests.c -o mq_open_tests -lrt - gcc -O2 -o mq_perf_tests mq_perf_tests.c -lrt -lpthread -lpopt + $(CC) $(CFLAGS) mq_open_tests.c -o mq_open_tests -lrt + $(CC) $(CFLAGS) -o mq_perf_tests mq_perf_tests.c -lrt -lpthread -lpopt + +include ../lib.mk + +override define RUN_TESTS + @./mq_open_tests /test1 || echo "selftests: mq_open_tests [FAIL]" + @./mq_perf_tests || echo "selftests: mq_perf_tests [FAIL]" +endef + +TEST_PROGS := mq_open_tests mq_perf_tests -run_tests: - @./mq_open_tests /test1 || echo "mq_open_tests: [FAIL]" - @./mq_perf_tests || echo "mq_perf_tests: [FAIL]" +override define EMIT_TESTS + echo "./mq_open_tests /test1 || echo \"selftests: mq_open_tests [FAIL]\"" + echo "./mq_perf_tests || echo \"selftests: mq_perf_tests [FAIL]\"" +endef clean: rm -f mq_open_tests mq_perf_tests diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 62f22cc9941c..fac4782c51d8 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -1,6 +1,5 @@ # Makefile for net selftests -CC = $(CROSS_COMPILE)gcc CFLAGS = -Wall -O2 -g CFLAGS += -I../../../../usr/include/ @@ -11,9 +10,10 @@ all: $(NET_PROGS) %: %.c $(CC) $(CFLAGS) -o $@ $^ -run_tests: all - @/bin/sh ./run_netsocktests || echo "sockettests: [FAIL]" - @/bin/sh ./run_afpackettests || echo "afpackettests: [FAIL]" - ./test_bpf.sh +TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh +TEST_FILES := $(NET_PROGS) + +include ../lib.mk + clean: $(RM) $(NET_PROGS) diff --git a/tools/testing/selftests/net/run_afpackettests b/tools/testing/selftests/net/run_afpackettests index 5246e782d6e8..5246e782d6e8 100644..100755 --- a/tools/testing/selftests/net/run_afpackettests +++ b/tools/testing/selftests/net/run_afpackettests diff --git a/tools/testing/selftests/net/run_netsocktests b/tools/testing/selftests/net/run_netsocktests index c09a682df56a..c09a682df56a 100644..100755 --- a/tools/testing/selftests/net/run_netsocktests +++ b/tools/testing/selftests/net/run_netsocktests diff --git a/tools/testing/selftests/powerpc/Makefile b/tools/testing/selftests/powerpc/Makefile index 1d5e7ad2c460..2958fe9a74e9 100644 --- a/tools/testing/selftests/powerpc/Makefile +++ b/tools/testing/selftests/powerpc/Makefile @@ -8,10 +8,9 @@ ifeq ($(ARCH),powerpc) GIT_VERSION = $(shell git describe --always --long --dirty || echo "unknown") -CC := $(CROSS_COMPILE)$(CC) CFLAGS := -Wall -O2 -flto -Wall -Werror -DGIT_VERSION='"$(GIT_VERSION)"' -I$(CURDIR) $(CFLAGS) -export CC CFLAGS +export CFLAGS TARGETS = pmu copyloops mm tm primitives stringloops @@ -22,10 +21,25 @@ all: $(TARGETS) $(TARGETS): $(MAKE) -k -C $@ all -run_tests: all +include ../lib.mk + +override define RUN_TESTS @for TARGET in $(TARGETS); do \ $(MAKE) -C $$TARGET run_tests; \ done; +endef + +override define INSTALL_RULE + @for TARGET in $(TARGETS); do \ + $(MAKE) -C $$TARGET install; \ + done; +endef + +override define EMIT_TESTS + @for TARGET in $(TARGETS); do \ + $(MAKE) -s -C $$TARGET emit_tests; \ + done; +endef clean: @for TARGET in $(TARGETS); do \ @@ -36,4 +50,4 @@ clean: tags: find . -name '*.c' -o -name '*.h' | xargs ctags -.PHONY: all run_tests clean tags $(TARGETS) +.PHONY: tags $(TARGETS) diff --git a/tools/testing/selftests/powerpc/copyloops/Makefile b/tools/testing/selftests/powerpc/copyloops/Makefile index 6f2d3be227f9..c05023514ce8 100644 --- a/tools/testing/selftests/powerpc/copyloops/Makefile +++ b/tools/testing/selftests/powerpc/copyloops/Makefile @@ -6,24 +6,19 @@ CFLAGS += -D SELFTEST # Use our CFLAGS for the implicit .S rule ASFLAGS = $(CFLAGS) -PROGS := copyuser_64 copyuser_power7 memcpy_64 memcpy_power7 +TEST_PROGS := copyuser_64 copyuser_power7 memcpy_64 memcpy_power7 EXTRA_SOURCES := validate.c ../harness.c -all: $(PROGS) +all: $(TEST_PROGS) copyuser_64: CPPFLAGS += -D COPY_LOOP=test___copy_tofrom_user_base copyuser_power7: CPPFLAGS += -D COPY_LOOP=test___copy_tofrom_user_power7 memcpy_64: CPPFLAGS += -D COPY_LOOP=test_memcpy memcpy_power7: CPPFLAGS += -D COPY_LOOP=test_memcpy_power7 -$(PROGS): $(EXTRA_SOURCES) +$(TEST_PROGS): $(EXTRA_SOURCES) -run_tests: all - @-for PROG in $(PROGS); do \ - ./$$PROG; \ - done; +include ../../lib.mk clean: - rm -f $(PROGS) *.o - -.PHONY: all run_tests clean + rm -f $(TEST_PROGS) *.o diff --git a/tools/testing/selftests/powerpc/mm/Makefile b/tools/testing/selftests/powerpc/mm/Makefile index a14c538dd7f8..41cc3ed66818 100644 --- a/tools/testing/selftests/powerpc/mm/Makefile +++ b/tools/testing/selftests/powerpc/mm/Makefile @@ -1,21 +1,16 @@ noarg: $(MAKE) -C ../ -PROGS := hugetlb_vs_thp_test subpage_prot +TEST_PROGS := hugetlb_vs_thp_test subpage_prot -all: $(PROGS) tempfile +all: $(TEST_PROGS) tempfile -$(PROGS): ../harness.c +$(TEST_PROGS): ../harness.c -run_tests: all - @-for PROG in $(PROGS); do \ - ./$$PROG; \ - done; +include ../../lib.mk tempfile: dd if=/dev/zero of=tempfile bs=64k count=1 clean: - rm -f $(PROGS) tempfile - -.PHONY: all run_tests clean + rm -f $(TEST_PROGS) tempfile diff --git a/tools/testing/selftests/powerpc/pmu/Makefile b/tools/testing/selftests/powerpc/pmu/Makefile index c9f4263906a5..5a161175bbd4 100644 --- a/tools/testing/selftests/powerpc/pmu/Makefile +++ b/tools/testing/selftests/powerpc/pmu/Makefile @@ -1,38 +1,42 @@ noarg: $(MAKE) -C ../ -PROGS := count_instructions l3_bank_test per_event_excludes +TEST_PROGS := count_instructions l3_bank_test per_event_excludes EXTRA_SOURCES := ../harness.c event.c lib.c -SUB_TARGETS = ebb +all: $(TEST_PROGS) ebb -all: $(PROGS) $(SUB_TARGETS) - -$(PROGS): $(EXTRA_SOURCES) +$(TEST_PROGS): $(EXTRA_SOURCES) # loop.S can only be built 64-bit count_instructions: loop.S count_instructions.c $(EXTRA_SOURCES) $(CC) $(CFLAGS) -m64 -o $@ $^ -run_tests: all sub_run_tests - @-for PROG in $(PROGS); do \ - ./$$PROG; \ - done; +include ../../lib.mk -clean: sub_clean - rm -f $(PROGS) loop.o +DEFAULT_RUN_TESTS := $(RUN_TESTS) +override define RUN_TESTS + $(DEFAULT_RUN_TESTS) + $(MAKE) -C ebb run_tests +endef -$(SUB_TARGETS): - $(MAKE) -k -C $@ all +DEFAULT_EMIT_TESTS := $(EMIT_TESTS) +override define EMIT_TESTS + $(DEFAULT_EMIT_TESTS) + $(MAKE) -s -C ebb emit_tests +endef -sub_run_tests: all - @for TARGET in $(SUB_TARGETS); do \ - $(MAKE) -C $$TARGET run_tests; \ - done; +DEFAULT_INSTALL := $(INSTALL_RULE) +override define INSTALL_RULE + $(DEFAULT_INSTALL_RULE) + $(MAKE) -C ebb install +endef -sub_clean: - @for TARGET in $(SUB_TARGETS); do \ - $(MAKE) -C $$TARGET clean; \ - done; +clean: + rm -f $(TEST_PROGS) loop.o + $(MAKE) -C ebb clean + +ebb: + $(MAKE) -k -C $@ all -.PHONY: all run_tests clean sub_run_tests sub_clean $(SUB_TARGETS) +.PHONY: all run_tests clean ebb diff --git a/tools/testing/selftests/powerpc/pmu/ebb/Makefile b/tools/testing/selftests/powerpc/pmu/ebb/Makefile index 3dc4332698cb..5cdc9dbf2b27 100644 --- a/tools/testing/selftests/powerpc/pmu/ebb/Makefile +++ b/tools/testing/selftests/powerpc/pmu/ebb/Makefile @@ -4,7 +4,7 @@ noarg: # The EBB handler is 64-bit code and everything links against it CFLAGS += -m64 -PROGS := reg_access_test event_attributes_test cycles_test \ +TEST_PROGS := reg_access_test event_attributes_test cycles_test \ cycles_with_freeze_test pmc56_overflow_test \ ebb_vs_cpu_event_test cpu_event_vs_ebb_test \ cpu_event_pinned_vs_ebb_test task_event_vs_ebb_test \ @@ -16,18 +16,15 @@ PROGS := reg_access_test event_attributes_test cycles_test \ lost_exception_test no_handler_test \ cycles_with_mmcr2_test -all: $(PROGS) +all: $(TEST_PROGS) -$(PROGS): ../../harness.c ../event.c ../lib.c ebb.c ebb_handler.S trace.c busy_loop.S +$(TEST_PROGS): ../../harness.c ../event.c ../lib.c ebb.c ebb_handler.S trace.c busy_loop.S instruction_count_test: ../loop.S lost_exception_test: ../lib.c -run_tests: all - @-for PROG in $(PROGS); do \ - ./$$PROG; \ - done; +include ../../../lib.mk clean: - rm -f $(PROGS) + rm -f $(TEST_PROGS) diff --git a/tools/testing/selftests/powerpc/primitives/Makefile b/tools/testing/selftests/powerpc/primitives/Makefile index ea737ca01732..b68c6221d3d1 100644 --- a/tools/testing/selftests/powerpc/primitives/Makefile +++ b/tools/testing/selftests/powerpc/primitives/Makefile @@ -1,17 +1,12 @@ CFLAGS += -I$(CURDIR) -PROGS := load_unaligned_zeropad +TEST_PROGS := load_unaligned_zeropad -all: $(PROGS) +all: $(TEST_PROGS) -$(PROGS): ../harness.c +$(TEST_PROGS): ../harness.c -run_tests: all - @-for PROG in $(PROGS); do \ - ./$$PROG; \ - done; +include ../../lib.mk clean: - rm -f $(PROGS) *.o - -.PHONY: all run_tests clean + rm -f $(TEST_PROGS) *.o diff --git a/tools/testing/selftests/powerpc/stringloops/Makefile b/tools/testing/selftests/powerpc/stringloops/Makefile index 506d77346477..2a728f4d2873 100644 --- a/tools/testing/selftests/powerpc/stringloops/Makefile +++ b/tools/testing/selftests/powerpc/stringloops/Makefile @@ -2,19 +2,14 @@ CFLAGS += -m64 CFLAGS += -I$(CURDIR) -PROGS := memcmp +TEST_PROGS := memcmp EXTRA_SOURCES := memcmp_64.S ../harness.c -all: $(PROGS) +all: $(TEST_PROGS) -$(PROGS): $(EXTRA_SOURCES) +$(TEST_PROGS): $(EXTRA_SOURCES) -run_tests: all - @-for PROG in $(PROGS); do \ - ./$$PROG; \ - done; +include ../../lib.mk clean: - rm -f $(PROGS) *.o - -.PHONY: all run_tests clean + rm -f $(TEST_PROGS) *.o diff --git a/tools/testing/selftests/powerpc/tm/Makefile b/tools/testing/selftests/powerpc/tm/Makefile index 2cede239a074..34f2ec634b40 100644 --- a/tools/testing/selftests/powerpc/tm/Makefile +++ b/tools/testing/selftests/powerpc/tm/Makefile @@ -1,15 +1,10 @@ -PROGS := tm-resched-dscr +TEST_PROGS := tm-resched-dscr -all: $(PROGS) +all: $(TEST_PROGS) -$(PROGS): ../harness.c +$(TEST_PROGS): ../harness.c -run_tests: all - @-for PROG in $(PROGS); do \ - ./$$PROG; \ - done; +include ../../lib.mk clean: - rm -f $(PROGS) *.o - -.PHONY: all run_tests clean + rm -f $(TEST_PROGS) *.o diff --git a/tools/testing/selftests/ptrace/Makefile b/tools/testing/selftests/ptrace/Makefile index 47ae2d385ce8..453927fea90c 100644 --- a/tools/testing/selftests/ptrace/Makefile +++ b/tools/testing/selftests/ptrace/Makefile @@ -6,5 +6,6 @@ all: peeksiginfo clean: rm -f peeksiginfo -run_tests: all - @./peeksiginfo || echo "peeksiginfo selftests: [FAIL]" +TEST_PROGS := peeksiginfo + +include ../lib.mk diff --git a/tools/testing/selftests/size/Makefile b/tools/testing/selftests/size/Makefile index 04dc25e4fa92..bbd0b5398b61 100644 --- a/tools/testing/selftests/size/Makefile +++ b/tools/testing/selftests/size/Makefile @@ -1,12 +1,11 @@ -CC = $(CROSS_COMPILE)gcc - all: get_size get_size: get_size.c $(CC) -static -ffreestanding -nostartfiles -s $< -o $@ -run_tests: all - ./get_size +TEST_PROGS := get_size + +include ../lib.mk clean: $(RM) get_size diff --git a/tools/testing/selftests/sysctl/Makefile b/tools/testing/selftests/sysctl/Makefile index 0a92adaf0865..b3c33e071f10 100644 --- a/tools/testing/selftests/sysctl/Makefile +++ b/tools/testing/selftests/sysctl/Makefile @@ -4,16 +4,10 @@ # No binaries, but make sure arg-less "make" doesn't trigger "run_tests". all: -# Allow specific tests to be selected. -test_num: - @/bin/sh ./run_numerictests +TEST_PROGS := run_numerictests run_stringtests +TEST_FILES := common_tests -test_string: - @/bin/sh ./run_stringtests - -run_tests: all test_num test_string +include ../lib.mk # Nothing to clean up. clean: - -.PHONY: all run_tests clean test_num test_string diff --git a/tools/testing/selftests/sysctl/run_numerictests b/tools/testing/selftests/sysctl/run_numerictests index 8510f93f2d14..8510f93f2d14 100644..100755 --- a/tools/testing/selftests/sysctl/run_numerictests +++ b/tools/testing/selftests/sysctl/run_numerictests diff --git a/tools/testing/selftests/sysctl/run_stringtests b/tools/testing/selftests/sysctl/run_stringtests index 90a9293d520c..90a9293d520c 100644..100755 --- a/tools/testing/selftests/sysctl/run_stringtests +++ b/tools/testing/selftests/sysctl/run_stringtests diff --git a/tools/testing/selftests/timers/Makefile b/tools/testing/selftests/timers/Makefile index eb2859f4ad21..89a3f44bf355 100644 --- a/tools/testing/selftests/timers/Makefile +++ b/tools/testing/selftests/timers/Makefile @@ -1,8 +1,36 @@ -all: - gcc posix_timers.c -o posix_timers -lrt +CC = $(CROSS_COMPILE)gcc +BUILD_FLAGS = -DKTEST +CFLAGS += -O3 -Wl,-no-as-needed -Wall $(BUILD_FLAGS) +LDFLAGS += -lrt -lpthread -run_tests: all - ./posix_timers +# these are all "safe" tests that don't modify +# system time or require escalated privledges +TEST_PROGS = posix_timers nanosleep nsleep-lat set-timer-lat mqueue-lat \ + inconsistency-check raw_skew threadtest rtctest + +TEST_PROGS_EXTENDED = alarmtimer-suspend valid-adjtimex change_skew \ + skew_consistency clocksource-switch leap-a-day \ + leapcrash set-tai set-2038 + +bins = $(TEST_PROGS) $(TEST_PROGS_EXTENDED) + +all: ${bins} + +include ../lib.mk + +# these tests require escalated privledges +# and may modify the system time or trigger +# other behavior like suspend +run_destructive_tests: run_tests + ./alarmtimer-suspend + ./valid-adjtimex + ./change_skew + ./skew_consistency + ./clocksource-switch + ./leap-a-day -s -i 10 + ./leapcrash + ./set-tai + ./set-2038 clean: - rm -f ./posix_timers + rm -f ${bins} diff --git a/tools/testing/selftests/timers/alarmtimer-suspend.c b/tools/testing/selftests/timers/alarmtimer-suspend.c new file mode 100644 index 000000000000..aaffbde1d5ee --- /dev/null +++ b/tools/testing/selftests/timers/alarmtimer-suspend.c @@ -0,0 +1,185 @@ +/* alarmtimer suspend test + * John Stultz (john.stultz@linaro.org) + * (C) Copyright Linaro 2013 + * Licensed under the GPLv2 + * + * This test makes sure the alarmtimer & RTC wakeup code is + * functioning. + * + * To build: + * $ gcc alarmtimer-suspend.c -o alarmtimer-suspend -lrt + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + + +#include <stdio.h> +#include <unistd.h> +#include <time.h> +#include <string.h> +#include <signal.h> +#include <stdlib.h> +#include <pthread.h> +#ifdef KTEST +#include "../kselftest.h" +#else +static inline int ksft_exit_pass(void) +{ + exit(0); +} +static inline int ksft_exit_fail(void) +{ + exit(1); +} +#endif + +#define CLOCK_REALTIME 0 +#define CLOCK_MONOTONIC 1 +#define CLOCK_PROCESS_CPUTIME_ID 2 +#define CLOCK_THREAD_CPUTIME_ID 3 +#define CLOCK_MONOTONIC_RAW 4 +#define CLOCK_REALTIME_COARSE 5 +#define CLOCK_MONOTONIC_COARSE 6 +#define CLOCK_BOOTTIME 7 +#define CLOCK_REALTIME_ALARM 8 +#define CLOCK_BOOTTIME_ALARM 9 +#define CLOCK_HWSPECIFIC 10 +#define CLOCK_TAI 11 +#define NR_CLOCKIDS 12 + + +#define NSEC_PER_SEC 1000000000ULL +#define UNREASONABLE_LAT (NSEC_PER_SEC * 4) /* hopefully we resume in 4secs */ + +#define SUSPEND_SECS 15 +int alarmcount; +int alarm_clock_id; +struct timespec start_time; + + +char *clockstring(int clockid) +{ + switch (clockid) { + case CLOCK_REALTIME: + return "CLOCK_REALTIME"; + case CLOCK_MONOTONIC: + return "CLOCK_MONOTONIC"; + case CLOCK_PROCESS_CPUTIME_ID: + return "CLOCK_PROCESS_CPUTIME_ID"; + case CLOCK_THREAD_CPUTIME_ID: + return "CLOCK_THREAD_CPUTIME_ID"; + case CLOCK_MONOTONIC_RAW: + return "CLOCK_MONOTONIC_RAW"; + case CLOCK_REALTIME_COARSE: + return "CLOCK_REALTIME_COARSE"; + case CLOCK_MONOTONIC_COARSE: + return "CLOCK_MONOTONIC_COARSE"; + case CLOCK_BOOTTIME: + return "CLOCK_BOOTTIME"; + case CLOCK_REALTIME_ALARM: + return "CLOCK_REALTIME_ALARM"; + case CLOCK_BOOTTIME_ALARM: + return "CLOCK_BOOTTIME_ALARM"; + case CLOCK_TAI: + return "CLOCK_TAI"; + }; + return "UNKNOWN_CLOCKID"; +} + + +long long timespec_sub(struct timespec a, struct timespec b) +{ + long long ret = NSEC_PER_SEC * b.tv_sec + b.tv_nsec; + + ret -= NSEC_PER_SEC * a.tv_sec + a.tv_nsec; + return ret; +} + +int final_ret = 0; + +void sigalarm(int signo) +{ + long long delta_ns; + struct timespec ts; + + clock_gettime(alarm_clock_id, &ts); + alarmcount++; + + delta_ns = timespec_sub(start_time, ts); + delta_ns -= NSEC_PER_SEC * SUSPEND_SECS * alarmcount; + + printf("ALARM(%i): %ld:%ld latency: %lld ns ", alarmcount, ts.tv_sec, + ts.tv_nsec, delta_ns); + + if (delta_ns > UNREASONABLE_LAT) { + printf("[FAIL]\n"); + final_ret = -1; + } else + printf("[OK]\n"); + +} + +int main(void) +{ + timer_t tm1; + struct itimerspec its1, its2; + struct sigevent se; + struct sigaction act; + int signum = SIGRTMAX; + + /* Set up signal handler: */ + sigfillset(&act.sa_mask); + act.sa_flags = 0; + act.sa_handler = sigalarm; + sigaction(signum, &act, NULL); + + /* Set up timer: */ + memset(&se, 0, sizeof(se)); + se.sigev_notify = SIGEV_SIGNAL; + se.sigev_signo = signum; + se.sigev_value.sival_int = 0; + + for (alarm_clock_id = CLOCK_REALTIME_ALARM; + alarm_clock_id <= CLOCK_BOOTTIME_ALARM; + alarm_clock_id++) { + + alarmcount = 0; + timer_create(alarm_clock_id, &se, &tm1); + + clock_gettime(alarm_clock_id, &start_time); + printf("Start time (%s): %ld:%ld\n", clockstring(alarm_clock_id), + start_time.tv_sec, start_time.tv_nsec); + printf("Setting alarm for every %i seconds\n", SUSPEND_SECS); + its1.it_value = start_time; + its1.it_value.tv_sec += SUSPEND_SECS; + its1.it_interval.tv_sec = SUSPEND_SECS; + its1.it_interval.tv_nsec = 0; + + timer_settime(tm1, TIMER_ABSTIME, &its1, &its2); + + while (alarmcount < 5) + sleep(1); /* First 5 alarms, do nothing */ + + printf("Starting suspend loops\n"); + while (alarmcount < 10) { + int ret; + + sleep(1); + ret = system("echo mem > /sys/power/state"); + if (ret) + break; + } + timer_delete(tm1); + } + if (final_ret) + return ksft_exit_fail(); + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/timers/change_skew.c b/tools/testing/selftests/timers/change_skew.c new file mode 100644 index 000000000000..cb1968977c04 --- /dev/null +++ b/tools/testing/selftests/timers/change_skew.c @@ -0,0 +1,107 @@ +/* ADJ_FREQ Skew change test + * by: john stultz (johnstul@us.ibm.com) + * (C) Copyright IBM 2012 + * Licensed under the GPLv2 + * + * NOTE: This is a meta-test which cranks the ADJ_FREQ knob and + * then uses other tests to detect problems. Thus this test requires + * that the raw_skew, inconsistency-check and nanosleep tests be + * present in the same directory it is run from. + * + * To build: + * $ gcc change_skew.c -o change_skew -lrt + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + + +#include <stdio.h> +#include <stdlib.h> +#include <sys/time.h> +#include <sys/timex.h> +#include <time.h> +#ifdef KTEST +#include "../kselftest.h" +#else +static inline int ksft_exit_pass(void) +{ + exit(0); +} +static inline int ksft_exit_fail(void) +{ + exit(1); +} +#endif + +#define NSEC_PER_SEC 1000000000LL + + +int change_skew_test(int ppm) +{ + struct timex tx; + int ret; + + tx.modes = ADJ_FREQUENCY; + tx.freq = ppm << 16; + + ret = adjtimex(&tx); + if (ret < 0) { + printf("Error adjusting freq\n"); + return ret; + } + + ret = system("./raw_skew"); + ret |= system("./inconsistency-check"); + ret |= system("./nanosleep"); + + return ret; +} + + +int main(int argv, char **argc) +{ + struct timex tx; + int i, ret; + + int ppm[5] = {0, 250, 500, -250, -500}; + + /* Kill ntpd */ + ret = system("killall -9 ntpd"); + + /* Make sure there's no offset adjustment going on */ + tx.modes = ADJ_OFFSET; + tx.offset = 0; + ret = adjtimex(&tx); + + if (ret < 0) { + printf("Maybe you're not running as root?\n"); + return -1; + } + + for (i = 0; i < 5; i++) { + printf("Using %i ppm adjustment\n", ppm[i]); + ret = change_skew_test(ppm[i]); + if (ret) + break; + } + + /* Set things back */ + tx.modes = ADJ_FREQUENCY; + tx.offset = 0; + adjtimex(&tx); + + if (ret) { + printf("[FAIL]"); + return ksft_exit_fail(); + } + printf("[OK]"); + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/timers/clocksource-switch.c b/tools/testing/selftests/timers/clocksource-switch.c new file mode 100644 index 000000000000..627ec7425f78 --- /dev/null +++ b/tools/testing/selftests/timers/clocksource-switch.c @@ -0,0 +1,179 @@ +/* Clocksource change test + * by: john stultz (johnstul@us.ibm.com) + * (C) Copyright IBM 2012 + * Licensed under the GPLv2 + * + * NOTE: This is a meta-test which quickly changes the clocksourc and + * then uses other tests to detect problems. Thus this test requires + * that the inconsistency-check and nanosleep tests be present in the + * same directory it is run from. + * + * To build: + * $ gcc clocksource-switch.c -o clocksource-switch -lrt + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + + +#include <stdio.h> +#include <unistd.h> +#include <stdlib.h> +#include <sys/time.h> +#include <sys/timex.h> +#include <time.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <string.h> +#include <sys/wait.h> +#ifdef KTEST +#include "../kselftest.h" +#else +static inline int ksft_exit_pass(void) +{ + exit(0); +} +static inline int ksft_exit_fail(void) +{ + exit(1); +} +#endif + + +int get_clocksources(char list[][30]) +{ + int fd, i; + size_t size; + char buf[512]; + char *head, *tmp; + + fd = open("/sys/devices/system/clocksource/clocksource0/available_clocksource", O_RDONLY); + + size = read(fd, buf, 512); + + close(fd); + + for (i = 0; i < 30; i++) + list[i][0] = '\0'; + + head = buf; + i = 0; + while (head - buf < size) { + /* Find the next space */ + for (tmp = head; *tmp != ' '; tmp++) { + if (*tmp == '\n') + break; + if (*tmp == '\0') + break; + } + *tmp = '\0'; + strcpy(list[i], head); + head = tmp + 1; + i++; + } + + return i-1; +} + +int get_cur_clocksource(char *buf, size_t size) +{ + int fd; + + fd = open("/sys/devices/system/clocksource/clocksource0/current_clocksource", O_RDONLY); + + size = read(fd, buf, size); + + return 0; +} + +int change_clocksource(char *clocksource) +{ + int fd; + size_t size; + + fd = open("/sys/devices/system/clocksource/clocksource0/current_clocksource", O_WRONLY); + + if (fd < 0) + return -1; + + size = write(fd, clocksource, strlen(clocksource)); + + if (size < 0) + return -1; + + close(fd); + return 0; +} + + +int run_tests(int secs) +{ + int ret; + char buf[255]; + + sprintf(buf, "./inconsistency-check -t %i", secs); + ret = system(buf); + if (ret) + return ret; + ret = system("./nanosleep"); + return ret; +} + + +char clocksource_list[10][30]; + +int main(int argv, char **argc) +{ + char orig_clk[512]; + int count, i, status; + pid_t pid; + + get_cur_clocksource(orig_clk, 512); + + count = get_clocksources(clocksource_list); + + if (change_clocksource(clocksource_list[0])) { + printf("Error: You probably need to run this as root\n"); + return -1; + } + + /* Check everything is sane before we start switching asyncrhonously */ + for (i = 0; i < count; i++) { + printf("Validating clocksource %s\n", clocksource_list[i]); + if (change_clocksource(clocksource_list[i])) { + status = -1; + goto out; + } + if (run_tests(5)) { + status = -1; + goto out; + } + } + + + printf("Running Asyncrhonous Switching Tests...\n"); + pid = fork(); + if (!pid) + return run_tests(60); + + while (pid != waitpid(pid, &status, WNOHANG)) + for (i = 0; i < count; i++) + if (change_clocksource(clocksource_list[i])) { + status = -1; + goto out; + } +out: + change_clocksource(orig_clk); + + if (status) + return ksft_exit_fail(); + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/timers/inconsistency-check.c b/tools/testing/selftests/timers/inconsistency-check.c new file mode 100644 index 000000000000..caf1bc9257c4 --- /dev/null +++ b/tools/testing/selftests/timers/inconsistency-check.c @@ -0,0 +1,204 @@ +/* Time inconsistency check test + * by: john stultz (johnstul@us.ibm.com) + * (C) Copyright IBM 2003, 2004, 2005, 2012 + * (C) Copyright Linaro Limited 2015 + * Licensed under the GPLv2 + * + * To build: + * $ gcc inconsistency-check.c -o inconsistency-check -lrt + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + + + +#include <stdio.h> +#include <unistd.h> +#include <stdlib.h> +#include <time.h> +#include <sys/time.h> +#include <sys/timex.h> +#include <string.h> +#include <signal.h> +#ifdef KTEST +#include "../kselftest.h" +#else +static inline int ksft_exit_pass(void) +{ + exit(0); +} +static inline int ksft_exit_fail(void) +{ + exit(1); +} +#endif + +#define CALLS_PER_LOOP 64 +#define NSEC_PER_SEC 1000000000ULL + +#define CLOCK_REALTIME 0 +#define CLOCK_MONOTONIC 1 +#define CLOCK_PROCESS_CPUTIME_ID 2 +#define CLOCK_THREAD_CPUTIME_ID 3 +#define CLOCK_MONOTONIC_RAW 4 +#define CLOCK_REALTIME_COARSE 5 +#define CLOCK_MONOTONIC_COARSE 6 +#define CLOCK_BOOTTIME 7 +#define CLOCK_REALTIME_ALARM 8 +#define CLOCK_BOOTTIME_ALARM 9 +#define CLOCK_HWSPECIFIC 10 +#define CLOCK_TAI 11 +#define NR_CLOCKIDS 12 + +char *clockstring(int clockid) +{ + switch (clockid) { + case CLOCK_REALTIME: + return "CLOCK_REALTIME"; + case CLOCK_MONOTONIC: + return "CLOCK_MONOTONIC"; + case CLOCK_PROCESS_CPUTIME_ID: + return "CLOCK_PROCESS_CPUTIME_ID"; + case CLOCK_THREAD_CPUTIME_ID: + return "CLOCK_THREAD_CPUTIME_ID"; + case CLOCK_MONOTONIC_RAW: + return "CLOCK_MONOTONIC_RAW"; + case CLOCK_REALTIME_COARSE: + return "CLOCK_REALTIME_COARSE"; + case CLOCK_MONOTONIC_COARSE: + return "CLOCK_MONOTONIC_COARSE"; + case CLOCK_BOOTTIME: + return "CLOCK_BOOTTIME"; + case CLOCK_REALTIME_ALARM: + return "CLOCK_REALTIME_ALARM"; + case CLOCK_BOOTTIME_ALARM: + return "CLOCK_BOOTTIME_ALARM"; + case CLOCK_TAI: + return "CLOCK_TAI"; + }; + return "UNKNOWN_CLOCKID"; +} + +/* returns 1 if a <= b, 0 otherwise */ +static inline int in_order(struct timespec a, struct timespec b) +{ + /* use unsigned to avoid false positives on 2038 rollover */ + if ((unsigned long)a.tv_sec < (unsigned long)b.tv_sec) + return 1; + if ((unsigned long)a.tv_sec > (unsigned long)b.tv_sec) + return 0; + if (a.tv_nsec > b.tv_nsec) + return 0; + return 1; +} + + + +int consistency_test(int clock_type, unsigned long seconds) +{ + struct timespec list[CALLS_PER_LOOP]; + int i, inconsistent; + long now, then; + time_t t; + char *start_str; + + clock_gettime(clock_type, &list[0]); + now = then = list[0].tv_sec; + + /* timestamp start of test */ + t = time(0); + start_str = ctime(&t); + + while (seconds == -1 || now - then < seconds) { + inconsistent = 0; + + /* Fill list */ + for (i = 0; i < CALLS_PER_LOOP; i++) + clock_gettime(clock_type, &list[i]); + + /* Check for inconsistencies */ + for (i = 0; i < CALLS_PER_LOOP - 1; i++) + if (!in_order(list[i], list[i+1])) + inconsistent = i; + + /* display inconsistency */ + if (inconsistent) { + unsigned long long delta; + + printf("\%s\n", start_str); + for (i = 0; i < CALLS_PER_LOOP; i++) { + if (i == inconsistent) + printf("--------------------\n"); + printf("%lu:%lu\n", list[i].tv_sec, + list[i].tv_nsec); + if (i == inconsistent + 1) + printf("--------------------\n"); + } + delta = list[inconsistent].tv_sec * NSEC_PER_SEC; + delta += list[inconsistent].tv_nsec; + delta -= list[inconsistent+1].tv_sec * NSEC_PER_SEC; + delta -= list[inconsistent+1].tv_nsec; + printf("Delta: %llu ns\n", delta); + fflush(0); + /* timestamp inconsistency*/ + t = time(0); + printf("%s\n", ctime(&t)); + printf("[FAILED]\n"); + return -1; + } + now = list[0].tv_sec; + } + printf("[OK]\n"); + return 0; +} + + +int main(int argc, char *argv[]) +{ + int clockid, opt; + int userclock = CLOCK_REALTIME; + int maxclocks = NR_CLOCKIDS; + int runtime = 10; + struct timespec ts; + + /* Process arguments */ + while ((opt = getopt(argc, argv, "t:c:")) != -1) { + switch (opt) { + case 't': + runtime = atoi(optarg); + break; + case 'c': + userclock = atoi(optarg); + maxclocks = userclock + 1; + break; + default: + printf("Usage: %s [-t <secs>] [-c <clockid>]\n", argv[0]); + printf(" -t: Number of seconds to run\n"); + printf(" -c: clockid to use (default, all clockids)\n"); + exit(-1); + } + } + + setbuf(stdout, NULL); + + for (clockid = userclock; clockid < maxclocks; clockid++) { + + if (clockid == CLOCK_HWSPECIFIC) + continue; + + if (!clock_gettime(clockid, &ts)) { + printf("Consistent %-30s ", clockstring(clockid)); + if (consistency_test(clockid, runtime)) + return ksft_exit_fail(); + } + } + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/timers/leap-a-day.c b/tools/testing/selftests/timers/leap-a-day.c new file mode 100644 index 000000000000..b8272e6c4b3b --- /dev/null +++ b/tools/testing/selftests/timers/leap-a-day.c @@ -0,0 +1,319 @@ +/* Leap second stress test + * by: John Stultz (john.stultz@linaro.org) + * (C) Copyright IBM 2012 + * (C) Copyright 2013, 2015 Linaro Limited + * Licensed under the GPLv2 + * + * This test signals the kernel to insert a leap second + * every day at midnight GMT. This allows for stessing the + * kernel's leap-second behavior, as well as how well applications + * handle the leap-second discontinuity. + * + * Usage: leap-a-day [-s] [-i <num>] + * + * Options: + * -s: Each iteration, set the date to 10 seconds before midnight GMT. + * This speeds up the number of leapsecond transitions tested, + * but because it calls settimeofday frequently, advancing the + * time by 24 hours every ~16 seconds, it may cause application + * disruption. + * + * -i: Number of iterations to run (default: infinite) + * + * Other notes: Disabling NTP prior to running this is advised, as the two + * may conflict in their commands to the kernel. + * + * To build: + * $ gcc leap-a-day.c -o leap-a-day -lrt + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + + + +#include <stdio.h> +#include <stdlib.h> +#include <time.h> +#include <sys/time.h> +#include <sys/timex.h> +#include <string.h> +#include <signal.h> +#include <unistd.h> +#ifdef KTEST +#include "../kselftest.h" +#else +static inline int ksft_exit_pass(void) +{ + exit(0); +} +static inline int ksft_exit_fail(void) +{ + exit(1); +} +#endif + +#define NSEC_PER_SEC 1000000000ULL +#define CLOCK_TAI 11 + +/* returns 1 if a <= b, 0 otherwise */ +static inline int in_order(struct timespec a, struct timespec b) +{ + if (a.tv_sec < b.tv_sec) + return 1; + if (a.tv_sec > b.tv_sec) + return 0; + if (a.tv_nsec > b.tv_nsec) + return 0; + return 1; +} + +struct timespec timespec_add(struct timespec ts, unsigned long long ns) +{ + ts.tv_nsec += ns; + while (ts.tv_nsec >= NSEC_PER_SEC) { + ts.tv_nsec -= NSEC_PER_SEC; + ts.tv_sec++; + } + return ts; +} + +char *time_state_str(int state) +{ + switch (state) { + case TIME_OK: return "TIME_OK"; + case TIME_INS: return "TIME_INS"; + case TIME_DEL: return "TIME_DEL"; + case TIME_OOP: return "TIME_OOP"; + case TIME_WAIT: return "TIME_WAIT"; + case TIME_BAD: return "TIME_BAD"; + } + return "ERROR"; +} + +/* clear NTP time_status & time_state */ +int clear_time_state(void) +{ + struct timex tx; + int ret; + + /* + * We have to call adjtime twice here, as kernels + * prior to 6b1859dba01c7 (included in 3.5 and + * -stable), had an issue with the state machine + * and wouldn't clear the STA_INS/DEL flag directly. + */ + tx.modes = ADJ_STATUS; + tx.status = STA_PLL; + ret = adjtimex(&tx); + + /* Clear maxerror, as it can cause UNSYNC to be set */ + tx.modes = ADJ_MAXERROR; + tx.maxerror = 0; + ret = adjtimex(&tx); + + /* Clear the status */ + tx.modes = ADJ_STATUS; + tx.status = 0; + ret = adjtimex(&tx); + + return ret; +} + +/* Make sure we cleanup on ctrl-c */ +void handler(int unused) +{ + clear_time_state(); + exit(0); +} + +/* Test for known hrtimer failure */ +void test_hrtimer_failure(void) +{ + struct timespec now, target; + + clock_gettime(CLOCK_REALTIME, &now); + target = timespec_add(now, NSEC_PER_SEC/2); + clock_nanosleep(CLOCK_REALTIME, TIMER_ABSTIME, &target, NULL); + clock_gettime(CLOCK_REALTIME, &now); + + if (!in_order(target, now)) + printf("ERROR: hrtimer early expiration failure observed.\n"); +} + +int main(int argc, char **argv) +{ + int settime = 0; + int tai_time = 0; + int insert = 1; + int iterations = -1; + int opt; + + /* Process arguments */ + while ((opt = getopt(argc, argv, "sti:")) != -1) { + switch (opt) { + case 's': + printf("Setting time to speed up testing\n"); + settime = 1; + break; + case 'i': + iterations = atoi(optarg); + break; + case 't': + tai_time = 1; + break; + default: + printf("Usage: %s [-s] [-i <iterations>]\n", argv[0]); + printf(" -s: Set time to right before leap second each iteration\n"); + printf(" -i: Number of iterations\n"); + printf(" -t: Print TAI time\n"); + exit(-1); + } + } + + /* Make sure TAI support is present if -t was used */ + if (tai_time) { + struct timespec ts; + + if (clock_gettime(CLOCK_TAI, &ts)) { + printf("System doesn't support CLOCK_TAI\n"); + ksft_exit_fail(); + } + } + + signal(SIGINT, handler); + signal(SIGKILL, handler); + + if (iterations < 0) + printf("This runs continuously. Press ctrl-c to stop\n"); + else + printf("Running for %i iterations. Press ctrl-c to stop\n", iterations); + + printf("\n"); + while (1) { + int ret; + struct timespec ts; + struct timex tx; + time_t now, next_leap; + + /* Get the current time */ + clock_gettime(CLOCK_REALTIME, &ts); + + /* Calculate the next possible leap second 23:59:60 GMT */ + next_leap = ts.tv_sec; + next_leap += 86400 - (next_leap % 86400); + + if (settime) { + struct timeval tv; + + tv.tv_sec = next_leap - 10; + tv.tv_usec = 0; + settimeofday(&tv, NULL); + printf("Setting time to %s", ctime(&tv.tv_sec)); + } + + /* Reset NTP time state */ + clear_time_state(); + + /* Set the leap second insert flag */ + tx.modes = ADJ_STATUS; + if (insert) + tx.status = STA_INS; + else + tx.status = STA_DEL; + ret = adjtimex(&tx); + if (ret < 0) { + printf("Error: Problem setting STA_INS/STA_DEL!: %s\n", + time_state_str(ret)); + return ksft_exit_fail(); + } + + /* Validate STA_INS was set */ + tx.modes = 0; + ret = adjtimex(&tx); + if (tx.status != STA_INS && tx.status != STA_DEL) { + printf("Error: STA_INS/STA_DEL not set!: %s\n", + time_state_str(ret)); + return ksft_exit_fail(); + } + + if (tai_time) { + printf("Using TAI time," + " no inconsistencies should be seen!\n"); + } + + printf("Scheduling leap second for %s", ctime(&next_leap)); + + /* Wake up 3 seconds before leap */ + ts.tv_sec = next_leap - 3; + ts.tv_nsec = 0; + + while (clock_nanosleep(CLOCK_REALTIME, TIMER_ABSTIME, &ts, NULL)) + printf("Something woke us up, returning to sleep\n"); + + /* Validate STA_INS is still set */ + tx.modes = 0; + ret = adjtimex(&tx); + if (tx.status != STA_INS && tx.status != STA_DEL) { + printf("Something cleared STA_INS/STA_DEL, setting it again.\n"); + tx.modes = ADJ_STATUS; + if (insert) + tx.status = STA_INS; + else + tx.status = STA_DEL; + ret = adjtimex(&tx); + } + + /* Check adjtimex output every half second */ + now = tx.time.tv_sec; + while (now < next_leap + 2) { + char buf[26]; + struct timespec tai; + + tx.modes = 0; + ret = adjtimex(&tx); + + if (tai_time) { + clock_gettime(CLOCK_TAI, &tai); + printf("%ld sec, %9ld ns\t%s\n", + tai.tv_sec, + tai.tv_nsec, + time_state_str(ret)); + } else { + ctime_r(&tx.time.tv_sec, buf); + buf[strlen(buf)-1] = 0; /*remove trailing\n */ + + printf("%s + %6ld us (%i)\t%s\n", + buf, + tx.time.tv_usec, + tx.tai, + time_state_str(ret)); + } + now = tx.time.tv_sec; + /* Sleep for another half second */ + ts.tv_sec = 0; + ts.tv_nsec = NSEC_PER_SEC / 2; + clock_nanosleep(CLOCK_MONOTONIC, 0, &ts, NULL); + } + /* Switch to using other mode */ + insert = !insert; + + /* Note if kernel has known hrtimer failure */ + test_hrtimer_failure(); + + printf("Leap complete\n\n"); + + if ((iterations != -1) && !(--iterations)) + break; + } + + clear_time_state(); + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/timers/leapcrash.c b/tools/testing/selftests/timers/leapcrash.c new file mode 100644 index 000000000000..a1071bdbdeb7 --- /dev/null +++ b/tools/testing/selftests/timers/leapcrash.c @@ -0,0 +1,120 @@ +/* Demo leapsecond deadlock + * by: John Stultz (john.stultz@linaro.org) + * (C) Copyright IBM 2012 + * (C) Copyright 2013, 2015 Linaro Limited + * Licensed under the GPL + * + * This test demonstrates leapsecond deadlock that is possibe + * on kernels from 2.6.26 to 3.3. + * + * WARNING: THIS WILL LIKELY HARDHANG SYSTEMS AND MAY LOSE DATA + * RUN AT YOUR OWN RISK! + * To build: + * $ gcc leapcrash.c -o leapcrash -lrt + */ + + + +#include <stdio.h> +#include <stdlib.h> +#include <time.h> +#include <sys/time.h> +#include <sys/timex.h> +#include <string.h> +#include <signal.h> +#ifdef KTEST +#include "../kselftest.h" +#else +static inline int ksft_exit_pass(void) +{ + exit(0); +} +static inline int ksft_exit_fail(void) +{ + exit(1); +} +#endif + + + +/* clear NTP time_status & time_state */ +int clear_time_state(void) +{ + struct timex tx; + int ret; + + /* + * We have to call adjtime twice here, as kernels + * prior to 6b1859dba01c7 (included in 3.5 and + * -stable), had an issue with the state machine + * and wouldn't clear the STA_INS/DEL flag directly. + */ + tx.modes = ADJ_STATUS; + tx.status = STA_PLL; + ret = adjtimex(&tx); + + tx.modes = ADJ_STATUS; + tx.status = 0; + ret = adjtimex(&tx); + + return ret; +} + +/* Make sure we cleanup on ctrl-c */ +void handler(int unused) +{ + clear_time_state(); + exit(0); +} + + +int main(void) +{ + struct timex tx; + struct timespec ts; + time_t next_leap; + int count = 0; + + setbuf(stdout, NULL); + + signal(SIGINT, handler); + signal(SIGKILL, handler); + printf("This runs for a few minutes. Press ctrl-c to stop\n"); + + clear_time_state(); + + + /* Get the current time */ + clock_gettime(CLOCK_REALTIME, &ts); + + /* Calculate the next possible leap second 23:59:60 GMT */ + next_leap = ts.tv_sec; + next_leap += 86400 - (next_leap % 86400); + + for (count = 0; count < 20; count++) { + struct timeval tv; + + + /* set the time to 2 seconds before the leap */ + tv.tv_sec = next_leap - 2; + tv.tv_usec = 0; + if (settimeofday(&tv, NULL)) { + printf("Error: You're likely not running with proper (ie: root) permissions\n"); + return ksft_exit_fail(); + } + tx.modes = 0; + adjtimex(&tx); + + /* hammer on adjtime w/ STA_INS */ + while (tx.time.tv_sec < next_leap + 1) { + /* Set the leap second insert flag */ + tx.modes = ADJ_STATUS; + tx.status = STA_INS; + adjtimex(&tx); + } + clear_time_state(); + printf("."); + } + printf("[OK]\n"); + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/timers/mqueue-lat.c b/tools/testing/selftests/timers/mqueue-lat.c new file mode 100644 index 000000000000..a2a3924d0b41 --- /dev/null +++ b/tools/testing/selftests/timers/mqueue-lat.c @@ -0,0 +1,124 @@ +/* Measure mqueue timeout latency + * by: john stultz (john.stultz@linaro.org) + * (C) Copyright Linaro 2013 + * + * Inspired with permission from example test by: + * Romain Francoise <romain@orebokech.com> + * Licensed under the GPLv2 + * + * To build: + * $ gcc mqueue-lat.c -o mqueue-lat -lrt + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <stdio.h> +#include <stdlib.h> +#include <time.h> +#include <sys/time.h> +#include <sys/timex.h> +#include <string.h> +#include <signal.h> +#include <errno.h> +#include <mqueue.h> +#ifdef KTEST +#include "../kselftest.h" +#else +static inline int ksft_exit_pass(void) +{ + exit(0); +} +static inline int ksft_exit_fail(void) +{ + exit(1); +} +#endif + +#define NSEC_PER_SEC 1000000000ULL + +#define TARGET_TIMEOUT 100000000 /* 100ms in nanoseconds */ +#define UNRESONABLE_LATENCY 40000000 /* 40ms in nanosecs */ + + +long long timespec_sub(struct timespec a, struct timespec b) +{ + long long ret = NSEC_PER_SEC * b.tv_sec + b.tv_nsec; + + ret -= NSEC_PER_SEC * a.tv_sec + a.tv_nsec; + return ret; +} + +struct timespec timespec_add(struct timespec ts, unsigned long long ns) +{ + ts.tv_nsec += ns; + while (ts.tv_nsec >= NSEC_PER_SEC) { + ts.tv_nsec -= NSEC_PER_SEC; + ts.tv_sec++; + } + return ts; +} + +int mqueue_lat_test(void) +{ + + mqd_t q; + struct mq_attr attr; + struct timespec start, end, now, target; + int i, count, ret; + + q = mq_open("/foo", O_CREAT | O_RDONLY, 0666, NULL); + if (q < 0) { + perror("mq_open"); + return -1; + } + mq_getattr(q, &attr); + + + count = 100; + clock_gettime(CLOCK_MONOTONIC, &start); + + for (i = 0; i < count; i++) { + char buf[attr.mq_msgsize]; + + clock_gettime(CLOCK_REALTIME, &now); + target = now; + target = timespec_add(now, TARGET_TIMEOUT); /* 100ms */ + + ret = mq_timedreceive(q, buf, sizeof(buf), NULL, &target); + if (ret < 0 && errno != ETIMEDOUT) { + perror("mq_timedreceive"); + return -1; + } + } + clock_gettime(CLOCK_MONOTONIC, &end); + + mq_close(q); + + if ((timespec_sub(start, end)/count) > TARGET_TIMEOUT + UNRESONABLE_LATENCY) + return -1; + + return 0; +} + +int main(int argc, char **argv) +{ + int ret; + + printf("Mqueue latency : "); + + ret = mqueue_lat_test(); + if (ret < 0) { + printf("[FAILED]\n"); + return ksft_exit_fail(); + } + printf("[OK]\n"); + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/timers/nanosleep.c b/tools/testing/selftests/timers/nanosleep.c new file mode 100644 index 000000000000..8a3c29de7d49 --- /dev/null +++ b/tools/testing/selftests/timers/nanosleep.c @@ -0,0 +1,174 @@ +/* Make sure timers don't return early + * by: john stultz (johnstul@us.ibm.com) + * John Stultz (john.stultz@linaro.org) + * (C) Copyright IBM 2012 + * (C) Copyright Linaro 2013 2015 + * Licensed under the GPLv2 + * + * To build: + * $ gcc nanosleep.c -o nanosleep -lrt + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <stdio.h> +#include <stdlib.h> +#include <time.h> +#include <sys/time.h> +#include <sys/timex.h> +#include <string.h> +#include <signal.h> +#ifdef KTEST +#include "../kselftest.h" +#else +static inline int ksft_exit_pass(void) +{ + exit(0); +} +static inline int ksft_exit_fail(void) +{ + exit(1); +} +#endif + +#define NSEC_PER_SEC 1000000000ULL + +#define CLOCK_REALTIME 0 +#define CLOCK_MONOTONIC 1 +#define CLOCK_PROCESS_CPUTIME_ID 2 +#define CLOCK_THREAD_CPUTIME_ID 3 +#define CLOCK_MONOTONIC_RAW 4 +#define CLOCK_REALTIME_COARSE 5 +#define CLOCK_MONOTONIC_COARSE 6 +#define CLOCK_BOOTTIME 7 +#define CLOCK_REALTIME_ALARM 8 +#define CLOCK_BOOTTIME_ALARM 9 +#define CLOCK_HWSPECIFIC 10 +#define CLOCK_TAI 11 +#define NR_CLOCKIDS 12 + +#define UNSUPPORTED 0xf00f + +char *clockstring(int clockid) +{ + switch (clockid) { + case CLOCK_REALTIME: + return "CLOCK_REALTIME"; + case CLOCK_MONOTONIC: + return "CLOCK_MONOTONIC"; + case CLOCK_PROCESS_CPUTIME_ID: + return "CLOCK_PROCESS_CPUTIME_ID"; + case CLOCK_THREAD_CPUTIME_ID: + return "CLOCK_THREAD_CPUTIME_ID"; + case CLOCK_MONOTONIC_RAW: + return "CLOCK_MONOTONIC_RAW"; + case CLOCK_REALTIME_COARSE: + return "CLOCK_REALTIME_COARSE"; + case CLOCK_MONOTONIC_COARSE: + return "CLOCK_MONOTONIC_COARSE"; + case CLOCK_BOOTTIME: + return "CLOCK_BOOTTIME"; + case CLOCK_REALTIME_ALARM: + return "CLOCK_REALTIME_ALARM"; + case CLOCK_BOOTTIME_ALARM: + return "CLOCK_BOOTTIME_ALARM"; + case CLOCK_TAI: + return "CLOCK_TAI"; + }; + return "UNKNOWN_CLOCKID"; +} + +/* returns 1 if a <= b, 0 otherwise */ +static inline int in_order(struct timespec a, struct timespec b) +{ + if (a.tv_sec < b.tv_sec) + return 1; + if (a.tv_sec > b.tv_sec) + return 0; + if (a.tv_nsec > b.tv_nsec) + return 0; + return 1; +} + +struct timespec timespec_add(struct timespec ts, unsigned long long ns) +{ + ts.tv_nsec += ns; + while (ts.tv_nsec >= NSEC_PER_SEC) { + ts.tv_nsec -= NSEC_PER_SEC; + ts.tv_sec++; + } + return ts; +} + +int nanosleep_test(int clockid, long long ns) +{ + struct timespec now, target, rel; + + /* First check abs time */ + if (clock_gettime(clockid, &now)) + return UNSUPPORTED; + target = timespec_add(now, ns); + + if (clock_nanosleep(clockid, TIMER_ABSTIME, &target, NULL)) + return UNSUPPORTED; + clock_gettime(clockid, &now); + + if (!in_order(target, now)) + return -1; + + /* Second check reltime */ + clock_gettime(clockid, &now); + rel.tv_sec = 0; + rel.tv_nsec = 0; + rel = timespec_add(rel, ns); + target = timespec_add(now, ns); + clock_nanosleep(clockid, 0, &rel, NULL); + clock_gettime(clockid, &now); + + if (!in_order(target, now)) + return -1; + return 0; +} + +int main(int argc, char **argv) +{ + long long length; + int clockid, ret; + + for (clockid = CLOCK_REALTIME; clockid < NR_CLOCKIDS; clockid++) { + + /* Skip cputime clockids since nanosleep won't increment cputime */ + if (clockid == CLOCK_PROCESS_CPUTIME_ID || + clockid == CLOCK_THREAD_CPUTIME_ID || + clockid == CLOCK_HWSPECIFIC) + continue; + + printf("Nanosleep %-31s ", clockstring(clockid)); + + length = 10; + while (length <= (NSEC_PER_SEC * 10)) { + ret = nanosleep_test(clockid, length); + if (ret == UNSUPPORTED) { + printf("[UNSUPPORTED]\n"); + goto next; + } + if (ret < 0) { + printf("[FAILED]\n"); + return ksft_exit_fail(); + } + length *= 100; + } + printf("[OK]\n"); +next: + ret = 0; + } + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/timers/nsleep-lat.c b/tools/testing/selftests/timers/nsleep-lat.c new file mode 100644 index 000000000000..2d7898fda0f1 --- /dev/null +++ b/tools/testing/selftests/timers/nsleep-lat.c @@ -0,0 +1,190 @@ +/* Measure nanosleep timer latency + * by: john stultz (john.stultz@linaro.org) + * (C) Copyright Linaro 2013 + * Licensed under the GPLv2 + * + * To build: + * $ gcc nsleep-lat.c -o nsleep-lat -lrt + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <stdio.h> +#include <stdlib.h> +#include <time.h> +#include <sys/time.h> +#include <sys/timex.h> +#include <string.h> +#include <signal.h> +#ifdef KTEST +#include "../kselftest.h" +#else +static inline int ksft_exit_pass(void) +{ + exit(0); +} +static inline int ksft_exit_fail(void) +{ + exit(1); +} +#endif + +#define NSEC_PER_SEC 1000000000ULL + +#define UNRESONABLE_LATENCY 40000000 /* 40ms in nanosecs */ + + +#define CLOCK_REALTIME 0 +#define CLOCK_MONOTONIC 1 +#define CLOCK_PROCESS_CPUTIME_ID 2 +#define CLOCK_THREAD_CPUTIME_ID 3 +#define CLOCK_MONOTONIC_RAW 4 +#define CLOCK_REALTIME_COARSE 5 +#define CLOCK_MONOTONIC_COARSE 6 +#define CLOCK_BOOTTIME 7 +#define CLOCK_REALTIME_ALARM 8 +#define CLOCK_BOOTTIME_ALARM 9 +#define CLOCK_HWSPECIFIC 10 +#define CLOCK_TAI 11 +#define NR_CLOCKIDS 12 + +#define UNSUPPORTED 0xf00f + +char *clockstring(int clockid) +{ + switch (clockid) { + case CLOCK_REALTIME: + return "CLOCK_REALTIME"; + case CLOCK_MONOTONIC: + return "CLOCK_MONOTONIC"; + case CLOCK_PROCESS_CPUTIME_ID: + return "CLOCK_PROCESS_CPUTIME_ID"; + case CLOCK_THREAD_CPUTIME_ID: + return "CLOCK_THREAD_CPUTIME_ID"; + case CLOCK_MONOTONIC_RAW: + return "CLOCK_MONOTONIC_RAW"; + case CLOCK_REALTIME_COARSE: + return "CLOCK_REALTIME_COARSE"; + case CLOCK_MONOTONIC_COARSE: + return "CLOCK_MONOTONIC_COARSE"; + case CLOCK_BOOTTIME: + return "CLOCK_BOOTTIME"; + case CLOCK_REALTIME_ALARM: + return "CLOCK_REALTIME_ALARM"; + case CLOCK_BOOTTIME_ALARM: + return "CLOCK_BOOTTIME_ALARM"; + case CLOCK_TAI: + return "CLOCK_TAI"; + }; + return "UNKNOWN_CLOCKID"; +} + +struct timespec timespec_add(struct timespec ts, unsigned long long ns) +{ + ts.tv_nsec += ns; + while (ts.tv_nsec >= NSEC_PER_SEC) { + ts.tv_nsec -= NSEC_PER_SEC; + ts.tv_sec++; + } + return ts; +} + + +long long timespec_sub(struct timespec a, struct timespec b) +{ + long long ret = NSEC_PER_SEC * b.tv_sec + b.tv_nsec; + + ret -= NSEC_PER_SEC * a.tv_sec + a.tv_nsec; + return ret; +} + +int nanosleep_lat_test(int clockid, long long ns) +{ + struct timespec start, end, target; + long long latency = 0; + int i, count; + + target.tv_sec = ns/NSEC_PER_SEC; + target.tv_nsec = ns%NSEC_PER_SEC; + + if (clock_gettime(clockid, &start)) + return UNSUPPORTED; + if (clock_nanosleep(clockid, 0, &target, NULL)) + return UNSUPPORTED; + + count = 10; + + /* First check relative latency */ + clock_gettime(clockid, &start); + for (i = 0; i < count; i++) + clock_nanosleep(clockid, 0, &target, NULL); + clock_gettime(clockid, &end); + + if (((timespec_sub(start, end)/count)-ns) > UNRESONABLE_LATENCY) { + printf("Large rel latency: %lld ns :", (timespec_sub(start, end)/count)-ns); + return -1; + } + + /* Next check absolute latency */ + for (i = 0; i < count; i++) { + clock_gettime(clockid, &start); + target = timespec_add(start, ns); + clock_nanosleep(clockid, TIMER_ABSTIME, &target, NULL); + clock_gettime(clockid, &end); + latency += timespec_sub(target, end); + } + + if (latency/count > UNRESONABLE_LATENCY) { + printf("Large abs latency: %lld ns :", latency/count); + return -1; + } + + return 0; +} + + + +int main(int argc, char **argv) +{ + long long length; + int clockid, ret; + + for (clockid = CLOCK_REALTIME; clockid < NR_CLOCKIDS; clockid++) { + + /* Skip cputime clockids since nanosleep won't increment cputime */ + if (clockid == CLOCK_PROCESS_CPUTIME_ID || + clockid == CLOCK_THREAD_CPUTIME_ID || + clockid == CLOCK_HWSPECIFIC) + continue; + + printf("nsleep latency %-26s ", clockstring(clockid)); + + length = 10; + while (length <= (NSEC_PER_SEC * 10)) { + ret = nanosleep_lat_test(clockid, length); + if (ret) + break; + length *= 100; + + } + + if (ret == UNSUPPORTED) { + printf("[UNSUPPORTED]\n"); + continue; + } + if (ret < 0) { + printf("[FAILED]\n"); + return ksft_exit_fail(); + } + printf("[OK]\n"); + } + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/timers/posix_timers.c b/tools/testing/selftests/timers/posix_timers.c index f87d970a485c..5a246a02dff3 100644 --- a/tools/testing/selftests/timers/posix_timers.c +++ b/tools/testing/selftests/timers/posix_timers.c @@ -35,10 +35,11 @@ static void user_loop(void) static void kernel_loop(void) { void *addr = sbrk(0); + int err = 0; - while (!done) { - brk(addr + 4096); - brk(addr); + while (!done && !err) { + err = brk(addr + 4096); + err |= brk(addr); } } @@ -190,8 +191,6 @@ static int check_timer_create(int which) int main(int argc, char **argv) { - int err; - printf("Testing posix timers. False negative may happen on CPU execution \n"); printf("based timers if other threads run on the CPU...\n"); diff --git a/tools/testing/selftests/timers/raw_skew.c b/tools/testing/selftests/timers/raw_skew.c new file mode 100644 index 000000000000..30906bfd9c1b --- /dev/null +++ b/tools/testing/selftests/timers/raw_skew.c @@ -0,0 +1,154 @@ +/* CLOCK_MONOTONIC vs CLOCK_MONOTONIC_RAW skew test + * by: john stultz (johnstul@us.ibm.com) + * John Stultz <john.stultz@linaro.org> + * (C) Copyright IBM 2012 + * (C) Copyright Linaro Limited 2015 + * Licensed under the GPLv2 + * + * To build: + * $ gcc raw_skew.c -o raw_skew -lrt + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <stdio.h> +#include <unistd.h> +#include <stdlib.h> +#include <sys/time.h> +#include <sys/timex.h> +#include <time.h> +#ifdef KTEST +#include "../kselftest.h" +#else +static inline int ksft_exit_pass(void) +{ + exit(0); +} +static inline int ksft_exit_fail(void) +{ + exit(1); +} +#endif + + +#define CLOCK_MONOTONIC_RAW 4 +#define NSEC_PER_SEC 1000000000LL + +#define shift_right(x, s) ({ \ + __typeof__(x) __x = (x); \ + __typeof__(s) __s = (s); \ + __x < 0 ? -(-__x >> __s) : __x >> __s; \ +}) + +long long llabs(long long val) +{ + if (val < 0) + val = -val; + return val; +} + +unsigned long long ts_to_nsec(struct timespec ts) +{ + return ts.tv_sec * NSEC_PER_SEC + ts.tv_nsec; +} + +struct timespec nsec_to_ts(long long ns) +{ + struct timespec ts; + + ts.tv_sec = ns/NSEC_PER_SEC; + ts.tv_nsec = ns%NSEC_PER_SEC; + return ts; +} + +long long diff_timespec(struct timespec start, struct timespec end) +{ + long long start_ns, end_ns; + + start_ns = ts_to_nsec(start); + end_ns = ts_to_nsec(end); + return end_ns - start_ns; +} + +void get_monotonic_and_raw(struct timespec *mon, struct timespec *raw) +{ + struct timespec start, mid, end; + long long diff = 0, tmp; + int i; + + for (i = 0; i < 3; i++) { + long long newdiff; + + clock_gettime(CLOCK_MONOTONIC, &start); + clock_gettime(CLOCK_MONOTONIC_RAW, &mid); + clock_gettime(CLOCK_MONOTONIC, &end); + + newdiff = diff_timespec(start, end); + if (diff == 0 || newdiff < diff) { + diff = newdiff; + *raw = mid; + tmp = (ts_to_nsec(start) + ts_to_nsec(end))/2; + *mon = nsec_to_ts(tmp); + } + } +} + +int main(int argv, char **argc) +{ + struct timespec mon, raw, start, end; + long long delta1, delta2, interval, eppm, ppm; + struct timex tx1, tx2; + + setbuf(stdout, NULL); + + if (clock_gettime(CLOCK_MONOTONIC_RAW, &raw)) { + printf("ERR: NO CLOCK_MONOTONIC_RAW\n"); + return -1; + } + + tx1.modes = 0; + adjtimex(&tx1); + get_monotonic_and_raw(&mon, &raw); + start = mon; + delta1 = diff_timespec(mon, raw); + + if (tx1.offset) + printf("WARNING: ADJ_OFFSET in progress, this will cause inaccurate results\n"); + + printf("Estimating clock drift: "); + sleep(120); + + get_monotonic_and_raw(&mon, &raw); + end = mon; + tx2.modes = 0; + adjtimex(&tx2); + delta2 = diff_timespec(mon, raw); + + interval = diff_timespec(start, end); + + /* calculate measured ppm between MONOTONIC and MONOTONIC_RAW */ + eppm = ((delta2-delta1)*NSEC_PER_SEC)/interval; + eppm = -eppm; + printf("%lld.%i(est)", eppm/1000, abs((int)(eppm%1000))); + + /* Avg the two actual freq samples adjtimex gave us */ + ppm = (tx1.freq + tx2.freq) * 1000 / 2; + ppm = (long long)tx1.freq * 1000; + ppm = shift_right(ppm, 16); + printf(" %lld.%i(act)", ppm/1000, abs((int)(ppm%1000))); + + if (llabs(eppm - ppm) > 1000) { + printf(" [FAILED]\n"); + return ksft_exit_fail(); + } + printf(" [OK]\n"); + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/timers/rtctest.c b/tools/testing/selftests/timers/rtctest.c new file mode 100644 index 000000000000..d80ae852334d --- /dev/null +++ b/tools/testing/selftests/timers/rtctest.c @@ -0,0 +1,271 @@ +/* + * Real Time Clock Driver Test/Example Program + * + * Compile with: + * gcc -s -Wall -Wstrict-prototypes rtctest.c -o rtctest + * + * Copyright (C) 1996, Paul Gortmaker. + * + * Released under the GNU General Public License, version 2, + * included herein by reference. + * + */ + +#include <stdio.h> +#include <linux/rtc.h> +#include <sys/ioctl.h> +#include <sys/time.h> +#include <sys/types.h> +#include <fcntl.h> +#include <unistd.h> +#include <stdlib.h> +#include <errno.h> + + +/* + * This expects the new RTC class driver framework, working with + * clocks that will often not be clones of what the PC-AT had. + * Use the command line to specify another RTC if you need one. + */ +static const char default_rtc[] = "/dev/rtc0"; + + +int main(int argc, char **argv) +{ + int i, fd, retval, irqcount = 0; + unsigned long tmp, data; + struct rtc_time rtc_tm; + const char *rtc = default_rtc; + struct timeval start, end, diff; + + switch (argc) { + case 2: + rtc = argv[1]; + /* FALLTHROUGH */ + case 1: + break; + default: + fprintf(stderr, "usage: rtctest [rtcdev]\n"); + return 1; + } + + fd = open(rtc, O_RDONLY); + + if (fd == -1) { + perror(rtc); + exit(errno); + } + + fprintf(stderr, "\n\t\t\tRTC Driver Test Example.\n\n"); + + /* Turn on update interrupts (one per second) */ + retval = ioctl(fd, RTC_UIE_ON, 0); + if (retval == -1) { + if (errno == ENOTTY) { + fprintf(stderr, + "\n...Update IRQs not supported.\n"); + goto test_READ; + } + perror("RTC_UIE_ON ioctl"); + exit(errno); + } + + fprintf(stderr, "Counting 5 update (1/sec) interrupts from reading %s:", + rtc); + fflush(stderr); + for (i=1; i<6; i++) { + /* This read will block */ + retval = read(fd, &data, sizeof(unsigned long)); + if (retval == -1) { + perror("read"); + exit(errno); + } + fprintf(stderr, " %d",i); + fflush(stderr); + irqcount++; + } + + fprintf(stderr, "\nAgain, from using select(2) on /dev/rtc:"); + fflush(stderr); + for (i=1; i<6; i++) { + struct timeval tv = {5, 0}; /* 5 second timeout on select */ + fd_set readfds; + + FD_ZERO(&readfds); + FD_SET(fd, &readfds); + /* The select will wait until an RTC interrupt happens. */ + retval = select(fd+1, &readfds, NULL, NULL, &tv); + if (retval == -1) { + perror("select"); + exit(errno); + } + /* This read won't block unlike the select-less case above. */ + retval = read(fd, &data, sizeof(unsigned long)); + if (retval == -1) { + perror("read"); + exit(errno); + } + fprintf(stderr, " %d",i); + fflush(stderr); + irqcount++; + } + + /* Turn off update interrupts */ + retval = ioctl(fd, RTC_UIE_OFF, 0); + if (retval == -1) { + perror("RTC_UIE_OFF ioctl"); + exit(errno); + } + +test_READ: + /* Read the RTC time/date */ + retval = ioctl(fd, RTC_RD_TIME, &rtc_tm); + if (retval == -1) { + perror("RTC_RD_TIME ioctl"); + exit(errno); + } + + fprintf(stderr, "\n\nCurrent RTC date/time is %d-%d-%d, %02d:%02d:%02d.\n", + rtc_tm.tm_mday, rtc_tm.tm_mon + 1, rtc_tm.tm_year + 1900, + rtc_tm.tm_hour, rtc_tm.tm_min, rtc_tm.tm_sec); + + /* Set the alarm to 5 sec in the future, and check for rollover */ + rtc_tm.tm_sec += 5; + if (rtc_tm.tm_sec >= 60) { + rtc_tm.tm_sec %= 60; + rtc_tm.tm_min++; + } + if (rtc_tm.tm_min == 60) { + rtc_tm.tm_min = 0; + rtc_tm.tm_hour++; + } + if (rtc_tm.tm_hour == 24) + rtc_tm.tm_hour = 0; + + retval = ioctl(fd, RTC_ALM_SET, &rtc_tm); + if (retval == -1) { + if (errno == ENOTTY) { + fprintf(stderr, + "\n...Alarm IRQs not supported.\n"); + goto test_PIE; + } + perror("RTC_ALM_SET ioctl"); + exit(errno); + } + + /* Read the current alarm settings */ + retval = ioctl(fd, RTC_ALM_READ, &rtc_tm); + if (retval == -1) { + perror("RTC_ALM_READ ioctl"); + exit(errno); + } + + fprintf(stderr, "Alarm time now set to %02d:%02d:%02d.\n", + rtc_tm.tm_hour, rtc_tm.tm_min, rtc_tm.tm_sec); + + /* Enable alarm interrupts */ + retval = ioctl(fd, RTC_AIE_ON, 0); + if (retval == -1) { + perror("RTC_AIE_ON ioctl"); + exit(errno); + } + + fprintf(stderr, "Waiting 5 seconds for alarm..."); + fflush(stderr); + /* This blocks until the alarm ring causes an interrupt */ + retval = read(fd, &data, sizeof(unsigned long)); + if (retval == -1) { + perror("read"); + exit(errno); + } + irqcount++; + fprintf(stderr, " okay. Alarm rang.\n"); + + /* Disable alarm interrupts */ + retval = ioctl(fd, RTC_AIE_OFF, 0); + if (retval == -1) { + perror("RTC_AIE_OFF ioctl"); + exit(errno); + } + +test_PIE: + /* Read periodic IRQ rate */ + retval = ioctl(fd, RTC_IRQP_READ, &tmp); + if (retval == -1) { + /* not all RTCs support periodic IRQs */ + if (errno == ENOTTY) { + fprintf(stderr, "\nNo periodic IRQ support\n"); + goto done; + } + perror("RTC_IRQP_READ ioctl"); + exit(errno); + } + fprintf(stderr, "\nPeriodic IRQ rate is %ldHz.\n", tmp); + + fprintf(stderr, "Counting 20 interrupts at:"); + fflush(stderr); + + /* The frequencies 128Hz, 256Hz, ... 8192Hz are only allowed for root. */ + for (tmp=2; tmp<=64; tmp*=2) { + + retval = ioctl(fd, RTC_IRQP_SET, tmp); + if (retval == -1) { + /* not all RTCs can change their periodic IRQ rate */ + if (errno == ENOTTY) { + fprintf(stderr, + "\n...Periodic IRQ rate is fixed\n"); + goto done; + } + perror("RTC_IRQP_SET ioctl"); + exit(errno); + } + + fprintf(stderr, "\n%ldHz:\t", tmp); + fflush(stderr); + + /* Enable periodic interrupts */ + retval = ioctl(fd, RTC_PIE_ON, 0); + if (retval == -1) { + perror("RTC_PIE_ON ioctl"); + exit(errno); + } + + for (i=1; i<21; i++) { + gettimeofday(&start, NULL); + /* This blocks */ + retval = read(fd, &data, sizeof(unsigned long)); + if (retval == -1) { + perror("read"); + exit(errno); + } + gettimeofday(&end, NULL); + timersub(&end, &start, &diff); + if (diff.tv_sec > 0 || + diff.tv_usec > ((1000000L / tmp) * 1.10)) { + fprintf(stderr, "\nPIE delta error: %ld.%06ld should be close to 0.%06ld\n", + diff.tv_sec, diff.tv_usec, + (1000000L / tmp)); + fflush(stdout); + exit(-1); + } + + fprintf(stderr, " %d",i); + fflush(stderr); + irqcount++; + } + + /* Disable periodic interrupts */ + retval = ioctl(fd, RTC_PIE_OFF, 0); + if (retval == -1) { + perror("RTC_PIE_OFF ioctl"); + exit(errno); + } + } + +done: + fprintf(stderr, "\n\n\t\t\t *** Test complete ***\n"); + + close(fd); + + return 0; +} diff --git a/tools/testing/selftests/timers/set-2038.c b/tools/testing/selftests/timers/set-2038.c new file mode 100644 index 000000000000..c8a7e14446b1 --- /dev/null +++ b/tools/testing/selftests/timers/set-2038.c @@ -0,0 +1,144 @@ +/* Time bounds setting test + * by: john stultz (johnstul@us.ibm.com) + * (C) Copyright IBM 2012 + * Licensed under the GPLv2 + * + * NOTE: This is a meta-test which sets the time to edge cases then + * uses other tests to detect problems. Thus this test requires that + * the inconsistency-check and nanosleep tests be present in the same + * directory it is run from. + * + * To build: + * $ gcc set-2038.c -o set-2038 -lrt + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <time.h> +#include <sys/time.h> +#ifdef KTEST +#include "../kselftest.h" +#else +static inline int ksft_exit_pass(void) +{ + exit(0); +} +static inline int ksft_exit_fail(void) +{ + exit(1); +} +#endif + +#define NSEC_PER_SEC 1000000000LL + +#define KTIME_MAX ((long long)~((unsigned long long)1 << 63)) +#define KTIME_SEC_MAX (KTIME_MAX / NSEC_PER_SEC) + +#define YEAR_1901 (-0x7fffffffL) +#define YEAR_1970 1 +#define YEAR_2038 0x7fffffffL /*overflows 32bit time_t */ +#define YEAR_2262 KTIME_SEC_MAX /*overflows 64bit ktime_t */ +#define YEAR_MAX ((long long)((1ULL<<63)-1)) /*overflows 64bit time_t */ + +int is32bits(void) +{ + return (sizeof(long) == 4); +} + +int settime(long long time) +{ + struct timeval now; + int ret; + + now.tv_sec = (time_t)time; + now.tv_usec = 0; + + ret = settimeofday(&now, NULL); + + printf("Setting time to 0x%lx: %d\n", (long)time, ret); + return ret; +} + +int do_tests(void) +{ + int ret; + + ret = system("date"); + ret = system("./inconsistency-check -c 0 -t 20"); + ret |= system("./nanosleep"); + ret |= system("./nsleep-lat"); + return ret; + +} + +int main(int argc, char *argv[]) +{ + int ret = 0; + int opt, dangerous = 0; + time_t start; + + /* Process arguments */ + while ((opt = getopt(argc, argv, "d")) != -1) { + switch (opt) { + case 'd': + dangerous = 1; + } + } + + start = time(0); + + /* First test that crazy values don't work */ + if (!settime(YEAR_1901)) { + ret = -1; + goto out; + } + if (!settime(YEAR_MAX)) { + ret = -1; + goto out; + } + if (!is32bits() && !settime(YEAR_2262)) { + ret = -1; + goto out; + } + + /* Now test behavior near edges */ + settime(YEAR_1970); + ret = do_tests(); + if (ret) + goto out; + + settime(YEAR_2038 - 600); + ret = do_tests(); + if (ret) + goto out; + + /* The rest of the tests can blowup on 32bit systems */ + if (is32bits() && !dangerous) + goto out; + /* Test rollover behavior 32bit edge */ + settime(YEAR_2038 - 10); + ret = do_tests(); + if (ret) + goto out; + + settime(YEAR_2262 - 600); + ret = do_tests(); + +out: + /* restore clock */ + settime(start); + if (ret) + return ksft_exit_fail(); + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/timers/set-tai.c b/tools/testing/selftests/timers/set-tai.c new file mode 100644 index 000000000000..dc88dbc8831f --- /dev/null +++ b/tools/testing/selftests/timers/set-tai.c @@ -0,0 +1,79 @@ +/* Set tai offset + * by: John Stultz <john.stultz@linaro.org> + * (C) Copyright Linaro 2013 + * Licensed under the GPLv2 + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + + +#include <stdio.h> +#include <stdlib.h> +#include <time.h> +#include <sys/time.h> +#include <sys/timex.h> +#include <string.h> +#include <signal.h> +#include <unistd.h> +#ifdef KTEST +#include "../kselftest.h" +#else +static inline int ksft_exit_pass(void) +{ + exit(0); +} +static inline int ksft_exit_fail(void) +{ + exit(1); +} +#endif + +int set_tai(int offset) +{ + struct timex tx; + + memset(&tx, 0, sizeof(tx)); + + tx.modes = ADJ_TAI; + tx.constant = offset; + + return adjtimex(&tx); +} + +int get_tai(void) +{ + struct timex tx; + + memset(&tx, 0, sizeof(tx)); + + adjtimex(&tx); + return tx.tai; +} + +int main(int argc, char **argv) +{ + int i, ret; + + ret = get_tai(); + printf("tai offset started at %i\n", ret); + + printf("Checking tai offsets can be properly set: "); + for (i = 1; i <= 60; i++) { + ret = set_tai(i); + ret = get_tai(); + if (ret != i) { + printf("[FAILED] expected: %i got %i\n", i, ret); + return ksft_exit_fail(); + } + } + printf("[OK]\n"); + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/timers/set-timer-lat.c b/tools/testing/selftests/timers/set-timer-lat.c new file mode 100644 index 000000000000..4fc98c5b0899 --- /dev/null +++ b/tools/testing/selftests/timers/set-timer-lat.c @@ -0,0 +1,216 @@ +/* set_timer latency test + * John Stultz (john.stultz@linaro.org) + * (C) Copyright Linaro 2014 + * Licensed under the GPLv2 + * + * This test makes sure the set_timer api is correct + * + * To build: + * $ gcc set-timer-lat.c -o set-timer-lat -lrt + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + + +#include <stdio.h> +#include <unistd.h> +#include <time.h> +#include <string.h> +#include <signal.h> +#include <stdlib.h> +#include <pthread.h> +#ifdef KTEST +#include "../kselftest.h" +#else +static inline int ksft_exit_pass(void) +{ + exit(0); +} +static inline int ksft_exit_fail(void) +{ + exit(1); +} +#endif + +#define CLOCK_REALTIME 0 +#define CLOCK_MONOTONIC 1 +#define CLOCK_PROCESS_CPUTIME_ID 2 +#define CLOCK_THREAD_CPUTIME_ID 3 +#define CLOCK_MONOTONIC_RAW 4 +#define CLOCK_REALTIME_COARSE 5 +#define CLOCK_MONOTONIC_COARSE 6 +#define CLOCK_BOOTTIME 7 +#define CLOCK_REALTIME_ALARM 8 +#define CLOCK_BOOTTIME_ALARM 9 +#define CLOCK_HWSPECIFIC 10 +#define CLOCK_TAI 11 +#define NR_CLOCKIDS 12 + + +#define NSEC_PER_SEC 1000000000ULL +#define UNRESONABLE_LATENCY 40000000 /* 40ms in nanosecs */ + +#define TIMER_SECS 1 +int alarmcount; +int clock_id; +struct timespec start_time; +long long max_latency_ns; + +char *clockstring(int clockid) +{ + switch (clockid) { + case CLOCK_REALTIME: + return "CLOCK_REALTIME"; + case CLOCK_MONOTONIC: + return "CLOCK_MONOTONIC"; + case CLOCK_PROCESS_CPUTIME_ID: + return "CLOCK_PROCESS_CPUTIME_ID"; + case CLOCK_THREAD_CPUTIME_ID: + return "CLOCK_THREAD_CPUTIME_ID"; + case CLOCK_MONOTONIC_RAW: + return "CLOCK_MONOTONIC_RAW"; + case CLOCK_REALTIME_COARSE: + return "CLOCK_REALTIME_COARSE"; + case CLOCK_MONOTONIC_COARSE: + return "CLOCK_MONOTONIC_COARSE"; + case CLOCK_BOOTTIME: + return "CLOCK_BOOTTIME"; + case CLOCK_REALTIME_ALARM: + return "CLOCK_REALTIME_ALARM"; + case CLOCK_BOOTTIME_ALARM: + return "CLOCK_BOOTTIME_ALARM"; + case CLOCK_TAI: + return "CLOCK_TAI"; + }; + return "UNKNOWN_CLOCKID"; +} + + +long long timespec_sub(struct timespec a, struct timespec b) +{ + long long ret = NSEC_PER_SEC * b.tv_sec + b.tv_nsec; + + ret -= NSEC_PER_SEC * a.tv_sec + a.tv_nsec; + return ret; +} + + +void sigalarm(int signo) +{ + long long delta_ns; + struct timespec ts; + + clock_gettime(clock_id, &ts); + alarmcount++; + + delta_ns = timespec_sub(start_time, ts); + delta_ns -= NSEC_PER_SEC * TIMER_SECS * alarmcount; + + if (delta_ns < 0) + printf("%s timer fired early: FAIL\n", clockstring(clock_id)); + + if (delta_ns > max_latency_ns) + max_latency_ns = delta_ns; +} + +int do_timer(int clock_id, int flags) +{ + struct sigevent se; + timer_t tm1; + struct itimerspec its1, its2; + int err; + + /* Set up timer: */ + memset(&se, 0, sizeof(se)); + se.sigev_notify = SIGEV_SIGNAL; + se.sigev_signo = SIGRTMAX; + se.sigev_value.sival_int = 0; + + max_latency_ns = 0; + alarmcount = 0; + + err = timer_create(clock_id, &se, &tm1); + if (err) { + if ((clock_id == CLOCK_REALTIME_ALARM) || + (clock_id == CLOCK_BOOTTIME_ALARM)) { + printf("%-22s %s missing CAP_WAKE_ALARM? : [UNSUPPORTED]\n", + clockstring(clock_id), + flags ? "ABSTIME":"RELTIME"); + return 0; + } + printf("%s - timer_create() failed\n", clockstring(clock_id)); + return -1; + } + + clock_gettime(clock_id, &start_time); + if (flags) { + its1.it_value = start_time; + its1.it_value.tv_sec += TIMER_SECS; + } else { + its1.it_value.tv_sec = TIMER_SECS; + its1.it_value.tv_nsec = 0; + } + its1.it_interval.tv_sec = TIMER_SECS; + its1.it_interval.tv_nsec = 0; + + err = timer_settime(tm1, flags, &its1, &its2); + if (err) { + printf("%s - timer_settime() failed\n", clockstring(clock_id)); + return -1; + } + + while (alarmcount < 5) + sleep(1); + + printf("%-22s %s max latency: %10lld ns : ", + clockstring(clock_id), + flags ? "ABSTIME":"RELTIME", + max_latency_ns); + + timer_delete(tm1); + if (max_latency_ns < UNRESONABLE_LATENCY) { + printf("[OK]\n"); + return 0; + } + printf("[FAILED]\n"); + return -1; +} + +int main(void) +{ + struct sigaction act; + int signum = SIGRTMAX; + int ret = 0; + + /* Set up signal handler: */ + sigfillset(&act.sa_mask); + act.sa_flags = 0; + act.sa_handler = sigalarm; + sigaction(signum, &act, NULL); + + printf("Setting timers for every %i seconds\n", TIMER_SECS); + for (clock_id = 0; clock_id < NR_CLOCKIDS; clock_id++) { + + if ((clock_id == CLOCK_PROCESS_CPUTIME_ID) || + (clock_id == CLOCK_THREAD_CPUTIME_ID) || + (clock_id == CLOCK_MONOTONIC_RAW) || + (clock_id == CLOCK_REALTIME_COARSE) || + (clock_id == CLOCK_MONOTONIC_COARSE) || + (clock_id == CLOCK_HWSPECIFIC)) + continue; + + ret |= do_timer(clock_id, TIMER_ABSTIME); + ret |= do_timer(clock_id, 0); + } + if (ret) + return ksft_exit_fail(); + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/timers/skew_consistency.c b/tools/testing/selftests/timers/skew_consistency.c new file mode 100644 index 000000000000..5562f84ee07c --- /dev/null +++ b/tools/testing/selftests/timers/skew_consistency.c @@ -0,0 +1,89 @@ +/* ADJ_FREQ Skew consistency test + * by: john stultz (johnstul@us.ibm.com) + * (C) Copyright IBM 2012 + * Licensed under the GPLv2 + * + * NOTE: This is a meta-test which cranks the ADJ_FREQ knob back + * and forth and watches for consistency problems. Thus this test requires + * that the inconsistency-check tests be present in the same directory it + * is run from. + * + * To build: + * $ gcc skew_consistency.c -o skew_consistency -lrt + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + + +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <sys/time.h> +#include <sys/timex.h> +#include <time.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <stdlib.h> +#include <string.h> +#include <sys/wait.h> +#ifdef KTEST +#include "../kselftest.h" +#else +static inline int ksft_exit_pass(void) +{ + exit(0); +} +static inline int ksft_exit_fail(void) +{ + exit(1); +} +#endif + +#define NSEC_PER_SEC 1000000000LL + +int main(int argv, char **argc) +{ + struct timex tx; + int ret, ppm; + pid_t pid; + + + printf("Running Asyncrhonous Frequency Changing Tests...\n"); + + pid = fork(); + if (!pid) + return system("./inconsistency-check -c 1 -t 600"); + + ppm = 500; + ret = 0; + + while (pid != waitpid(pid, &ret, WNOHANG)) { + ppm = -ppm; + tx.modes = ADJ_FREQUENCY; + tx.freq = ppm << 16; + adjtimex(&tx); + usleep(500000); + } + + /* Set things back */ + tx.modes = ADJ_FREQUENCY; + tx.offset = 0; + adjtimex(&tx); + + + if (ret) { + printf("[FAILED]\n"); + return ksft_exit_fail(); + } + printf("[OK]\n"); + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/timers/threadtest.c b/tools/testing/selftests/timers/threadtest.c new file mode 100644 index 000000000000..e632e116f05e --- /dev/null +++ b/tools/testing/selftests/timers/threadtest.c @@ -0,0 +1,204 @@ +/* threadtest.c + * by: john stultz (johnstul@us.ibm.com) + * (C) Copyright IBM 2004, 2005, 2006, 2012 + * Licensed under the GPLv2 + * + * To build: + * $ gcc threadtest.c -o threadtest -lrt + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ +#include <stdio.h> +#include <unistd.h> +#include <stdlib.h> +#include <sys/time.h> +#include <pthread.h> +#ifdef KTEST +#include "../kselftest.h" +#else +static inline int ksft_exit_pass(void) +{ + exit(0); +} +static inline int ksft_exit_fail(void) +{ + exit(1); +} +#endif + + +/* serializes shared list access */ +pthread_mutex_t list_lock = PTHREAD_MUTEX_INITIALIZER; +/* serializes console output */ +pthread_mutex_t print_lock = PTHREAD_MUTEX_INITIALIZER; + + +#define MAX_THREADS 128 +#define LISTSIZE 128 + +int done = 0; + +struct timespec global_list[LISTSIZE]; +int listcount = 0; + + +void checklist(struct timespec *list, int size) +{ + int i, j; + struct timespec *a, *b; + + /* scan the list */ + for (i = 0; i < size-1; i++) { + a = &list[i]; + b = &list[i+1]; + + /* look for any time inconsistencies */ + if ((b->tv_sec <= a->tv_sec) && + (b->tv_nsec < a->tv_nsec)) { + + /* flag other threads */ + done = 1; + + /*serialize printing to avoid junky output*/ + pthread_mutex_lock(&print_lock); + + /* dump the list */ + printf("\n"); + for (j = 0; j < size; j++) { + if (j == i) + printf("---------------\n"); + printf("%lu:%lu\n", list[j].tv_sec, list[j].tv_nsec); + if (j == i+1) + printf("---------------\n"); + } + printf("[FAILED]\n"); + + pthread_mutex_unlock(&print_lock); + } + } +} + +/* The shared thread shares a global list + * that each thread fills while holding the lock. + * This stresses clock syncronization across cpus. + */ +void *shared_thread(void *arg) +{ + while (!done) { + /* protect the list */ + pthread_mutex_lock(&list_lock); + + /* see if we're ready to check the list */ + if (listcount >= LISTSIZE) { + checklist(global_list, LISTSIZE); + listcount = 0; + } + clock_gettime(CLOCK_MONOTONIC, &global_list[listcount++]); + + pthread_mutex_unlock(&list_lock); + } + return NULL; +} + + +/* Each independent thread fills in its own + * list. This stresses clock_gettime() lock contention. + */ +void *independent_thread(void *arg) +{ + struct timespec my_list[LISTSIZE]; + int count; + + while (!done) { + /* fill the list */ + for (count = 0; count < LISTSIZE; count++) + clock_gettime(CLOCK_MONOTONIC, &my_list[count]); + checklist(my_list, LISTSIZE); + } + return NULL; +} + +#define DEFAULT_THREAD_COUNT 8 +#define DEFAULT_RUNTIME 30 + +int main(int argc, char **argv) +{ + int thread_count, i; + time_t start, now, runtime; + char buf[255]; + pthread_t pth[MAX_THREADS]; + int opt; + void *tret; + int ret = 0; + void *(*thread)(void *) = shared_thread; + + thread_count = DEFAULT_THREAD_COUNT; + runtime = DEFAULT_RUNTIME; + + /* Process arguments */ + while ((opt = getopt(argc, argv, "t:n:i")) != -1) { + switch (opt) { + case 't': + runtime = atoi(optarg); + break; + case 'n': + thread_count = atoi(optarg); + break; + case 'i': + thread = independent_thread; + printf("using independent threads\n"); + break; + default: + printf("Usage: %s [-t <secs>] [-n <numthreads>] [-i]\n", argv[0]); + printf(" -t: time to run\n"); + printf(" -n: number of threads\n"); + printf(" -i: use independent threads\n"); + return -1; + } + } + + if (thread_count > MAX_THREADS) + thread_count = MAX_THREADS; + + + setbuf(stdout, NULL); + + start = time(0); + strftime(buf, 255, "%a, %d %b %Y %T %z", localtime(&start)); + printf("%s\n", buf); + printf("Testing consistency with %i threads for %ld seconds: ", thread_count, runtime); + + /* spawn */ + for (i = 0; i < thread_count; i++) + pthread_create(&pth[i], 0, thread, 0); + + while (time(&now) < start + runtime) { + sleep(1); + if (done) { + ret = 1; + strftime(buf, 255, "%a, %d %b %Y %T %z", localtime(&now)); + printf("%s\n", buf); + goto out; + } + } + printf("[OK]\n"); + done = 1; + +out: + /* wait */ + for (i = 0; i < thread_count; i++) + pthread_join(pth[i], &tret); + + /* die */ + if (ret) + ksft_exit_fail(); + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/timers/valid-adjtimex.c b/tools/testing/selftests/timers/valid-adjtimex.c new file mode 100644 index 000000000000..e86d937cc22c --- /dev/null +++ b/tools/testing/selftests/timers/valid-adjtimex.c @@ -0,0 +1,202 @@ +/* valid adjtimex test + * by: John Stultz <john.stultz@linaro.org> + * (C) Copyright Linaro 2015 + * Licensed under the GPLv2 + * + * This test validates adjtimex interface with valid + * and invalid test data. + * + * Usage: valid-adjtimex + * + * To build: + * $ gcc valid-adjtimex.c -o valid-adjtimex -lrt + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + + + +#include <stdio.h> +#include <stdlib.h> +#include <time.h> +#include <sys/time.h> +#include <sys/timex.h> +#include <string.h> +#include <signal.h> +#include <unistd.h> +#ifdef KTEST +#include "../kselftest.h" +#else +static inline int ksft_exit_pass(void) +{ + exit(0); +} +static inline int ksft_exit_fail(void) +{ + exit(1); +} +#endif + +#define NSEC_PER_SEC 1000000000L + +/* clear NTP time_status & time_state */ +int clear_time_state(void) +{ + struct timex tx; + int ret; + + tx.modes = ADJ_STATUS; + tx.status = 0; + ret = adjtimex(&tx); + return ret; +} + +#define NUM_FREQ_VALID 32 +#define NUM_FREQ_OUTOFRANGE 4 +#define NUM_FREQ_INVALID 2 + +long valid_freq[NUM_FREQ_VALID] = { + -499<<16, + -450<<16, + -400<<16, + -350<<16, + -300<<16, + -250<<16, + -200<<16, + -150<<16, + -100<<16, + -75<<16, + -50<<16, + -25<<16, + -10<<16, + -5<<16, + -1<<16, + -1000, + 1<<16, + 5<<16, + 10<<16, + 25<<16, + 50<<16, + 75<<16, + 100<<16, + 150<<16, + 200<<16, + 250<<16, + 300<<16, + 350<<16, + 400<<16, + 450<<16, + 499<<16, +}; + +long outofrange_freq[NUM_FREQ_OUTOFRANGE] = { + -1000<<16, + -550<<16, + 550<<16, + 1000<<16, +}; + +#define LONG_MAX (~0UL>>1) +#define LONG_MIN (-LONG_MAX - 1) + +long invalid_freq[NUM_FREQ_INVALID] = { + LONG_MAX, + LONG_MIN, +}; + +int validate_freq(void) +{ + struct timex tx; + int ret, pass = 0; + int i; + + clear_time_state(); + + memset(&tx, 0, sizeof(struct timex)); + /* Set the leap second insert flag */ + + printf("Testing ADJ_FREQ... "); + for (i = 0; i < NUM_FREQ_VALID; i++) { + tx.modes = ADJ_FREQUENCY; + tx.freq = valid_freq[i]; + + ret = adjtimex(&tx); + if (ret < 0) { + printf("[FAIL]\n"); + printf("Error: adjtimex(ADJ_FREQ, %ld - %ld ppm\n", + valid_freq[i], valid_freq[i]>>16); + pass = -1; + goto out; + } + tx.modes = 0; + ret = adjtimex(&tx); + if (tx.freq != valid_freq[i]) { + printf("Warning: freq value %ld not what we set it (%ld)!\n", + tx.freq, valid_freq[i]); + } + } + for (i = 0; i < NUM_FREQ_OUTOFRANGE; i++) { + tx.modes = ADJ_FREQUENCY; + tx.freq = outofrange_freq[i]; + + ret = adjtimex(&tx); + if (ret < 0) { + printf("[FAIL]\n"); + printf("Error: adjtimex(ADJ_FREQ, %ld - %ld ppm\n", + outofrange_freq[i], outofrange_freq[i]>>16); + pass = -1; + goto out; + } + tx.modes = 0; + ret = adjtimex(&tx); + if (tx.freq == outofrange_freq[i]) { + printf("[FAIL]\n"); + printf("ERROR: out of range value %ld actually set!\n", + tx.freq); + pass = -1; + goto out; + } + } + + + if (sizeof(long) == 8) { /* this case only applies to 64bit systems */ + for (i = 0; i < NUM_FREQ_INVALID; i++) { + tx.modes = ADJ_FREQUENCY; + tx.freq = invalid_freq[i]; + ret = adjtimex(&tx); + if (ret >= 0) { + printf("[FAIL]\n"); + printf("Error: No failure on invalid ADJ_FREQUENCY %ld\n", + invalid_freq[i]); + pass = -1; + goto out; + } + } + } + + printf("[OK]\n"); +out: + /* reset freq to zero */ + tx.modes = ADJ_FREQUENCY; + tx.freq = 0; + ret = adjtimex(&tx); + + return pass; +} + + +int main(int argc, char **argv) +{ + if (validate_freq()) + return ksft_exit_fail(); + + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/user/Makefile b/tools/testing/selftests/user/Makefile index 12c9d15bab07..d401b63c5b1a 100644 --- a/tools/testing/selftests/user/Makefile +++ b/tools/testing/selftests/user/Makefile @@ -3,5 +3,6 @@ # No binaries, but make sure arg-less "make" doesn't trigger "run_tests" all: -run_tests: all - ./test_user_copy.sh +TEST_PROGS := test_user_copy.sh + +include ../lib.mk diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index 077828c889f1..a5ce9534eb15 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -1,6 +1,5 @@ # Makefile for vm selftests -CC = $(CROSS_COMPILE)gcc CFLAGS = -Wall BINARIES = hugepage-mmap hugepage-shm map_hugetlb thuge-gen hugetlbfstest BINARIES += transhuge-stress @@ -9,8 +8,10 @@ all: $(BINARIES) %: %.c $(CC) $(CFLAGS) -o $@ $^ -lrt -run_tests: all - @/bin/sh ./run_vmtests || (echo "vmtests: [FAIL]"; exit 1) +TEST_PROGS := run_vmtests +TEST_FILES := $(BINARIES) + +include ../lib.mk clean: $(RM) $(BINARIES) diff --git a/tools/testing/selftests/vm/run_vmtests b/tools/testing/selftests/vm/run_vmtests index c87b6812300d..c87b6812300d 100644..100755 --- a/tools/testing/selftests/vm/run_vmtests +++ b/tools/testing/selftests/vm/run_vmtests diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c index 6e54f3542126..98c95f2fcba4 100644 --- a/virt/kvm/arm/arch_timer.c +++ b/virt/kvm/arm/arch_timer.c @@ -85,13 +85,22 @@ static irqreturn_t kvm_arch_timer_handler(int irq, void *dev_id) return IRQ_HANDLED; } +/* + * Work function for handling the backup timer that we schedule when a vcpu is + * no longer running, but had a timer programmed to fire in the future. + */ static void kvm_timer_inject_irq_work(struct work_struct *work) { struct kvm_vcpu *vcpu; vcpu = container_of(work, struct kvm_vcpu, arch.timer_cpu.expired); vcpu->arch.timer_cpu.armed = false; - kvm_timer_inject_irq(vcpu); + + /* + * If the vcpu is blocked we want to wake it up so that it will see + * the timer has expired when entering the guest. + */ + kvm_vcpu_kick(vcpu); } static enum hrtimer_restart kvm_timer_expire(struct hrtimer *hrt) @@ -102,6 +111,21 @@ static enum hrtimer_restart kvm_timer_expire(struct hrtimer *hrt) return HRTIMER_NORESTART; } +bool kvm_timer_should_fire(struct kvm_vcpu *vcpu) +{ + struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; + cycle_t cval, now; + + if ((timer->cntv_ctl & ARCH_TIMER_CTRL_IT_MASK) || + !(timer->cntv_ctl & ARCH_TIMER_CTRL_ENABLE)) + return false; + + cval = timer->cntv_cval; + now = kvm_phys_timer_read() - vcpu->kvm->arch.timer.cntvoff; + + return cval <= now; +} + /** * kvm_timer_flush_hwstate - prepare to move the virt timer to the cpu * @vcpu: The vcpu pointer @@ -119,6 +143,13 @@ void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu) * populate the CPU timer again. */ timer_disarm(timer); + + /* + * If the timer expired while we were not scheduled, now is the time + * to inject it. + */ + if (kvm_timer_should_fire(vcpu)) + kvm_timer_inject_irq(vcpu); } /** @@ -134,16 +165,9 @@ void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu) cycle_t cval, now; u64 ns; - if ((timer->cntv_ctl & ARCH_TIMER_CTRL_IT_MASK) || - !(timer->cntv_ctl & ARCH_TIMER_CTRL_ENABLE)) - return; - - cval = timer->cntv_cval; - now = kvm_phys_timer_read() - vcpu->kvm->arch.timer.cntvoff; - BUG_ON(timer_is_armed(timer)); - if (cval <= now) { + if (kvm_timer_should_fire(vcpu)) { /* * Timer has already expired while we were not * looking. Inject the interrupt and carry on. @@ -152,6 +176,9 @@ void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu) return; } + cval = timer->cntv_cval; + now = kvm_phys_timer_read() - vcpu->kvm->arch.timer.cntvoff; + ns = cyclecounter_cyc2ns(timecounter->cc, cval - now, timecounter->mask, &timecounter->frac); timer_arm(timer, ns); diff --git a/virt/kvm/arm/vgic-v2-emul.c b/virt/kvm/arm/vgic-v2-emul.c index 19c6210f02cf..13907970d11c 100644 --- a/virt/kvm/arm/vgic-v2-emul.c +++ b/virt/kvm/arm/vgic-v2-emul.c @@ -107,6 +107,22 @@ static bool handle_mmio_clear_pending_reg(struct kvm_vcpu *vcpu, vcpu->vcpu_id); } +static bool handle_mmio_set_active_reg(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, + phys_addr_t offset) +{ + return vgic_handle_set_active_reg(vcpu->kvm, mmio, offset, + vcpu->vcpu_id); +} + +static bool handle_mmio_clear_active_reg(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, + phys_addr_t offset) +{ + return vgic_handle_clear_active_reg(vcpu->kvm, mmio, offset, + vcpu->vcpu_id); +} + static bool handle_mmio_priority_reg(struct kvm_vcpu *vcpu, struct kvm_exit_mmio *mmio, phys_addr_t offset) @@ -303,7 +319,7 @@ static bool handle_mmio_sgi_clear(struct kvm_vcpu *vcpu, return write_set_clear_sgi_pend_reg(vcpu, mmio, offset, false); } -static const struct kvm_mmio_range vgic_dist_ranges[] = { +static const struct vgic_io_range vgic_dist_ranges[] = { { .base = GIC_DIST_CTRL, .len = 12, @@ -344,13 +360,13 @@ static const struct kvm_mmio_range vgic_dist_ranges[] = { .base = GIC_DIST_ACTIVE_SET, .len = VGIC_MAX_IRQS / 8, .bits_per_irq = 1, - .handle_mmio = handle_mmio_raz_wi, + .handle_mmio = handle_mmio_set_active_reg, }, { .base = GIC_DIST_ACTIVE_CLEAR, .len = VGIC_MAX_IRQS / 8, .bits_per_irq = 1, - .handle_mmio = handle_mmio_raz_wi, + .handle_mmio = handle_mmio_clear_active_reg, }, { .base = GIC_DIST_PRI, @@ -388,24 +404,6 @@ static const struct kvm_mmio_range vgic_dist_ranges[] = { {} }; -static bool vgic_v2_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run, - struct kvm_exit_mmio *mmio) -{ - unsigned long base = vcpu->kvm->arch.vgic.vgic_dist_base; - - if (!is_in_range(mmio->phys_addr, mmio->len, base, - KVM_VGIC_V2_DIST_SIZE)) - return false; - - /* GICv2 does not support accesses wider than 32 bits */ - if (mmio->len > 4) { - kvm_inject_dabt(vcpu, mmio->phys_addr); - return true; - } - - return vgic_handle_mmio_range(vcpu, run, mmio, vgic_dist_ranges, base); -} - static void vgic_dispatch_sgi(struct kvm_vcpu *vcpu, u32 reg) { struct kvm *kvm = vcpu->kvm; @@ -490,6 +488,7 @@ static bool vgic_v2_queue_sgi(struct kvm_vcpu *vcpu, int irq) static int vgic_v2_map_resources(struct kvm *kvm, const struct vgic_params *params) { + struct vgic_dist *dist = &kvm->arch.vgic; int ret = 0; if (!irqchip_in_kernel(kvm)) @@ -500,13 +499,17 @@ static int vgic_v2_map_resources(struct kvm *kvm, if (vgic_ready(kvm)) goto out; - if (IS_VGIC_ADDR_UNDEF(kvm->arch.vgic.vgic_dist_base) || - IS_VGIC_ADDR_UNDEF(kvm->arch.vgic.vgic_cpu_base)) { + if (IS_VGIC_ADDR_UNDEF(dist->vgic_dist_base) || + IS_VGIC_ADDR_UNDEF(dist->vgic_cpu_base)) { kvm_err("Need to set vgic cpu and dist addresses first\n"); ret = -ENXIO; goto out; } + vgic_register_kvm_io_dev(kvm, dist->vgic_dist_base, + KVM_VGIC_V2_DIST_SIZE, + vgic_dist_ranges, -1, &dist->dist_iodev); + /* * Initialize the vgic if this hasn't already been done on demand by * accessing the vgic state from userspace. @@ -514,18 +517,23 @@ static int vgic_v2_map_resources(struct kvm *kvm, ret = vgic_init(kvm); if (ret) { kvm_err("Unable to allocate maps\n"); - goto out; + goto out_unregister; } - ret = kvm_phys_addr_ioremap(kvm, kvm->arch.vgic.vgic_cpu_base, + ret = kvm_phys_addr_ioremap(kvm, dist->vgic_cpu_base, params->vcpu_base, KVM_VGIC_V2_CPU_SIZE, true); if (ret) { kvm_err("Unable to remap VGIC CPU to VCPU\n"); - goto out; + goto out_unregister; } - kvm->arch.vgic.ready = true; + dist->ready = true; + goto out; + +out_unregister: + kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &dist->dist_iodev.dev); + out: if (ret) kvm_vgic_destroy(kvm); @@ -554,7 +562,6 @@ void vgic_v2_init_emulation(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; - dist->vm_ops.handle_mmio = vgic_v2_handle_mmio; dist->vm_ops.queue_sgi = vgic_v2_queue_sgi; dist->vm_ops.add_sgi_source = vgic_v2_add_sgi_source; dist->vm_ops.init_model = vgic_v2_init_model; @@ -631,7 +638,7 @@ static bool handle_cpu_mmio_ident(struct kvm_vcpu *vcpu, * CPU Interface Register accesses - these are not accessed by the VM, but by * user space for saving and restoring VGIC state. */ -static const struct kvm_mmio_range vgic_cpu_ranges[] = { +static const struct vgic_io_range vgic_cpu_ranges[] = { { .base = GIC_CPU_CTRL, .len = 12, @@ -658,12 +665,13 @@ static int vgic_attr_regs_access(struct kvm_device *dev, struct kvm_device_attr *attr, u32 *reg, bool is_write) { - const struct kvm_mmio_range *r = NULL, *ranges; + const struct vgic_io_range *r = NULL, *ranges; phys_addr_t offset; int ret, cpuid, c; struct kvm_vcpu *vcpu, *tmp_vcpu; struct vgic_dist *vgic; struct kvm_exit_mmio mmio; + u32 data; offset = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK; cpuid = (attr->attr & KVM_DEV_ARM_VGIC_CPUID_MASK) >> @@ -685,6 +693,7 @@ static int vgic_attr_regs_access(struct kvm_device *dev, mmio.len = 4; mmio.is_write = is_write; + mmio.data = &data; if (is_write) mmio_data_write(&mmio, ~0, *reg); switch (attr->group) { @@ -699,7 +708,7 @@ static int vgic_attr_regs_access(struct kvm_device *dev, default: BUG(); } - r = vgic_find_range(ranges, &mmio, offset); + r = vgic_find_range(ranges, 4, offset); if (unlikely(!r || !r->handle_mmio)) { ret = -ENXIO; diff --git a/virt/kvm/arm/vgic-v3-emul.c b/virt/kvm/arm/vgic-v3-emul.c index b3f154631515..e9c3a7a83833 100644 --- a/virt/kvm/arm/vgic-v3-emul.c +++ b/virt/kvm/arm/vgic-v3-emul.c @@ -340,7 +340,7 @@ static bool handle_mmio_idregs(struct kvm_vcpu *vcpu, return false; } -static const struct kvm_mmio_range vgic_v3_dist_ranges[] = { +static const struct vgic_io_range vgic_v3_dist_ranges[] = { { .base = GICD_CTLR, .len = 0x04, @@ -502,6 +502,43 @@ static const struct kvm_mmio_range vgic_v3_dist_ranges[] = { {}, }; +static bool handle_mmio_ctlr_redist(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, + phys_addr_t offset) +{ + /* since we don't support LPIs, this register is zero for now */ + vgic_reg_access(mmio, NULL, offset, + ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED); + return false; +} + +static bool handle_mmio_typer_redist(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, + phys_addr_t offset) +{ + u32 reg; + u64 mpidr; + struct kvm_vcpu *redist_vcpu = mmio->private; + int target_vcpu_id = redist_vcpu->vcpu_id; + + /* the upper 32 bits contain the affinity value */ + if ((offset & ~3) == 4) { + mpidr = kvm_vcpu_get_mpidr_aff(redist_vcpu); + reg = compress_mpidr(mpidr); + + vgic_reg_access(mmio, ®, offset, + ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED); + return false; + } + + reg = redist_vcpu->vcpu_id << 8; + if (target_vcpu_id == atomic_read(&vcpu->kvm->online_vcpus) - 1) + reg |= GICR_TYPER_LAST; + vgic_reg_access(mmio, ®, offset, + ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED); + return false; +} + static bool handle_mmio_set_enable_reg_redist(struct kvm_vcpu *vcpu, struct kvm_exit_mmio *mmio, phys_addr_t offset) @@ -570,186 +607,107 @@ static bool handle_mmio_cfg_reg_redist(struct kvm_vcpu *vcpu, return vgic_handle_cfg_reg(reg, mmio, offset); } -static const struct kvm_mmio_range vgic_redist_sgi_ranges[] = { +#define SGI_base(x) ((x) + SZ_64K) + +static const struct vgic_io_range vgic_redist_ranges[] = { + { + .base = GICR_CTLR, + .len = 0x04, + .bits_per_irq = 0, + .handle_mmio = handle_mmio_ctlr_redist, + }, + { + .base = GICR_TYPER, + .len = 0x08, + .bits_per_irq = 0, + .handle_mmio = handle_mmio_typer_redist, + }, + { + .base = GICR_IIDR, + .len = 0x04, + .bits_per_irq = 0, + .handle_mmio = handle_mmio_iidr, + }, + { + .base = GICR_WAKER, + .len = 0x04, + .bits_per_irq = 0, + .handle_mmio = handle_mmio_raz_wi, + }, { - .base = GICR_IGROUPR0, + .base = GICR_IDREGS, + .len = 0x30, + .bits_per_irq = 0, + .handle_mmio = handle_mmio_idregs, + }, + { + .base = SGI_base(GICR_IGROUPR0), .len = 0x04, .bits_per_irq = 1, .handle_mmio = handle_mmio_rao_wi, }, { - .base = GICR_ISENABLER0, + .base = SGI_base(GICR_ISENABLER0), .len = 0x04, .bits_per_irq = 1, .handle_mmio = handle_mmio_set_enable_reg_redist, }, { - .base = GICR_ICENABLER0, + .base = SGI_base(GICR_ICENABLER0), .len = 0x04, .bits_per_irq = 1, .handle_mmio = handle_mmio_clear_enable_reg_redist, }, { - .base = GICR_ISPENDR0, + .base = SGI_base(GICR_ISPENDR0), .len = 0x04, .bits_per_irq = 1, .handle_mmio = handle_mmio_set_pending_reg_redist, }, { - .base = GICR_ICPENDR0, + .base = SGI_base(GICR_ICPENDR0), .len = 0x04, .bits_per_irq = 1, .handle_mmio = handle_mmio_clear_pending_reg_redist, }, { - .base = GICR_ISACTIVER0, + .base = SGI_base(GICR_ISACTIVER0), .len = 0x04, .bits_per_irq = 1, .handle_mmio = handle_mmio_raz_wi, }, { - .base = GICR_ICACTIVER0, + .base = SGI_base(GICR_ICACTIVER0), .len = 0x04, .bits_per_irq = 1, .handle_mmio = handle_mmio_raz_wi, }, { - .base = GICR_IPRIORITYR0, + .base = SGI_base(GICR_IPRIORITYR0), .len = 0x20, .bits_per_irq = 8, .handle_mmio = handle_mmio_priority_reg_redist, }, { - .base = GICR_ICFGR0, + .base = SGI_base(GICR_ICFGR0), .len = 0x08, .bits_per_irq = 2, .handle_mmio = handle_mmio_cfg_reg_redist, }, { - .base = GICR_IGRPMODR0, + .base = SGI_base(GICR_IGRPMODR0), .len = 0x04, .bits_per_irq = 1, .handle_mmio = handle_mmio_raz_wi, }, { - .base = GICR_NSACR, + .base = SGI_base(GICR_NSACR), .len = 0x04, .handle_mmio = handle_mmio_raz_wi, }, {}, }; -static bool handle_mmio_ctlr_redist(struct kvm_vcpu *vcpu, - struct kvm_exit_mmio *mmio, - phys_addr_t offset) -{ - /* since we don't support LPIs, this register is zero for now */ - vgic_reg_access(mmio, NULL, offset, - ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED); - return false; -} - -static bool handle_mmio_typer_redist(struct kvm_vcpu *vcpu, - struct kvm_exit_mmio *mmio, - phys_addr_t offset) -{ - u32 reg; - u64 mpidr; - struct kvm_vcpu *redist_vcpu = mmio->private; - int target_vcpu_id = redist_vcpu->vcpu_id; - - /* the upper 32 bits contain the affinity value */ - if ((offset & ~3) == 4) { - mpidr = kvm_vcpu_get_mpidr_aff(redist_vcpu); - reg = compress_mpidr(mpidr); - - vgic_reg_access(mmio, ®, offset, - ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED); - return false; - } - - reg = redist_vcpu->vcpu_id << 8; - if (target_vcpu_id == atomic_read(&vcpu->kvm->online_vcpus) - 1) - reg |= GICR_TYPER_LAST; - vgic_reg_access(mmio, ®, offset, - ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED); - return false; -} - -static const struct kvm_mmio_range vgic_redist_ranges[] = { - { - .base = GICR_CTLR, - .len = 0x04, - .bits_per_irq = 0, - .handle_mmio = handle_mmio_ctlr_redist, - }, - { - .base = GICR_TYPER, - .len = 0x08, - .bits_per_irq = 0, - .handle_mmio = handle_mmio_typer_redist, - }, - { - .base = GICR_IIDR, - .len = 0x04, - .bits_per_irq = 0, - .handle_mmio = handle_mmio_iidr, - }, - { - .base = GICR_WAKER, - .len = 0x04, - .bits_per_irq = 0, - .handle_mmio = handle_mmio_raz_wi, - }, - { - .base = GICR_IDREGS, - .len = 0x30, - .bits_per_irq = 0, - .handle_mmio = handle_mmio_idregs, - }, - {}, -}; - -/* - * This function splits accesses between the distributor and the two - * redistributor parts (private/SPI). As each redistributor is accessible - * from any CPU, we have to determine the affected VCPU by taking the faulting - * address into account. We then pass this VCPU to the handler function via - * the private parameter. - */ -#define SGI_BASE_OFFSET SZ_64K -static bool vgic_v3_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run, - struct kvm_exit_mmio *mmio) -{ - struct vgic_dist *dist = &vcpu->kvm->arch.vgic; - unsigned long dbase = dist->vgic_dist_base; - unsigned long rdbase = dist->vgic_redist_base; - int nrcpus = atomic_read(&vcpu->kvm->online_vcpus); - int vcpu_id; - const struct kvm_mmio_range *mmio_range; - - if (is_in_range(mmio->phys_addr, mmio->len, dbase, GIC_V3_DIST_SIZE)) { - return vgic_handle_mmio_range(vcpu, run, mmio, - vgic_v3_dist_ranges, dbase); - } - - if (!is_in_range(mmio->phys_addr, mmio->len, rdbase, - GIC_V3_REDIST_SIZE * nrcpus)) - return false; - - vcpu_id = (mmio->phys_addr - rdbase) / GIC_V3_REDIST_SIZE; - rdbase += (vcpu_id * GIC_V3_REDIST_SIZE); - mmio->private = kvm_get_vcpu(vcpu->kvm, vcpu_id); - - if (mmio->phys_addr >= rdbase + SGI_BASE_OFFSET) { - rdbase += SGI_BASE_OFFSET; - mmio_range = vgic_redist_sgi_ranges; - } else { - mmio_range = vgic_redist_ranges; - } - return vgic_handle_mmio_range(vcpu, run, mmio, mmio_range, rdbase); -} - static bool vgic_v3_queue_sgi(struct kvm_vcpu *vcpu, int irq) { if (vgic_queue_irq(vcpu, 0, irq)) { @@ -766,6 +724,9 @@ static int vgic_v3_map_resources(struct kvm *kvm, { int ret = 0; struct vgic_dist *dist = &kvm->arch.vgic; + gpa_t rdbase = dist->vgic_redist_base; + struct vgic_io_device *iodevs = NULL; + int i; if (!irqchip_in_kernel(kvm)) return 0; @@ -791,7 +752,41 @@ static int vgic_v3_map_resources(struct kvm *kvm, goto out; } - kvm->arch.vgic.ready = true; + ret = vgic_register_kvm_io_dev(kvm, dist->vgic_dist_base, + GIC_V3_DIST_SIZE, vgic_v3_dist_ranges, + -1, &dist->dist_iodev); + if (ret) + goto out; + + iodevs = kcalloc(dist->nr_cpus, sizeof(iodevs[0]), GFP_KERNEL); + if (!iodevs) { + ret = -ENOMEM; + goto out_unregister; + } + + for (i = 0; i < dist->nr_cpus; i++) { + ret = vgic_register_kvm_io_dev(kvm, rdbase, + SZ_128K, vgic_redist_ranges, + i, &iodevs[i]); + if (ret) + goto out_unregister; + rdbase += GIC_V3_REDIST_SIZE; + } + + dist->redist_iodevs = iodevs; + dist->ready = true; + goto out; + +out_unregister: + kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &dist->dist_iodev.dev); + if (iodevs) { + for (i = 0; i < dist->nr_cpus; i++) { + if (iodevs[i].dev.ops) + kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, + &iodevs[i].dev); + } + } + out: if (ret) kvm_vgic_destroy(kvm); @@ -832,7 +827,6 @@ void vgic_v3_init_emulation(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; - dist->vm_ops.handle_mmio = vgic_v3_handle_mmio; dist->vm_ops.queue_sgi = vgic_v3_queue_sgi; dist->vm_ops.add_sgi_source = vgic_v3_add_sgi_source; dist->vm_ops.init_model = vgic_v3_init_model; diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c index c9f60f524588..8d550ff14700 100644 --- a/virt/kvm/arm/vgic.c +++ b/virt/kvm/arm/vgic.c @@ -31,6 +31,9 @@ #include <asm/kvm_emulate.h> #include <asm/kvm_arm.h> #include <asm/kvm_mmu.h> +#include <trace/events/kvm.h> +#include <asm/kvm.h> +#include <kvm/iodev.h> /* * How the whole thing works (courtesy of Christoffer Dall): @@ -263,6 +266,13 @@ static int vgic_irq_is_queued(struct kvm_vcpu *vcpu, int irq) return vgic_bitmap_get_irq_val(&dist->irq_queued, vcpu->vcpu_id, irq); } +static int vgic_irq_is_active(struct kvm_vcpu *vcpu, int irq) +{ + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + + return vgic_bitmap_get_irq_val(&dist->irq_active, vcpu->vcpu_id, irq); +} + static void vgic_irq_set_queued(struct kvm_vcpu *vcpu, int irq) { struct vgic_dist *dist = &vcpu->kvm->arch.vgic; @@ -277,6 +287,20 @@ static void vgic_irq_clear_queued(struct kvm_vcpu *vcpu, int irq) vgic_bitmap_set_irq_val(&dist->irq_queued, vcpu->vcpu_id, irq, 0); } +static void vgic_irq_set_active(struct kvm_vcpu *vcpu, int irq) +{ + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + + vgic_bitmap_set_irq_val(&dist->irq_active, vcpu->vcpu_id, irq, 1); +} + +static void vgic_irq_clear_active(struct kvm_vcpu *vcpu, int irq) +{ + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + + vgic_bitmap_set_irq_val(&dist->irq_active, vcpu->vcpu_id, irq, 0); +} + static int vgic_dist_irq_get_level(struct kvm_vcpu *vcpu, int irq) { struct vgic_dist *dist = &vcpu->kvm->arch.vgic; @@ -520,6 +544,44 @@ bool vgic_handle_clear_pending_reg(struct kvm *kvm, return false; } +bool vgic_handle_set_active_reg(struct kvm *kvm, + struct kvm_exit_mmio *mmio, + phys_addr_t offset, int vcpu_id) +{ + u32 *reg; + struct vgic_dist *dist = &kvm->arch.vgic; + + reg = vgic_bitmap_get_reg(&dist->irq_active, vcpu_id, offset); + vgic_reg_access(mmio, reg, offset, + ACCESS_READ_VALUE | ACCESS_WRITE_SETBIT); + + if (mmio->is_write) { + vgic_update_state(kvm); + return true; + } + + return false; +} + +bool vgic_handle_clear_active_reg(struct kvm *kvm, + struct kvm_exit_mmio *mmio, + phys_addr_t offset, int vcpu_id) +{ + u32 *reg; + struct vgic_dist *dist = &kvm->arch.vgic; + + reg = vgic_bitmap_get_reg(&dist->irq_active, vcpu_id, offset); + vgic_reg_access(mmio, reg, offset, + ACCESS_READ_VALUE | ACCESS_WRITE_CLEARBIT); + + if (mmio->is_write) { + vgic_update_state(kvm); + return true; + } + + return false; +} + static u32 vgic_cfg_expand(u16 val) { u32 res = 0; @@ -588,16 +650,12 @@ bool vgic_handle_cfg_reg(u32 *reg, struct kvm_exit_mmio *mmio, } /** - * vgic_unqueue_irqs - move pending IRQs from LRs to the distributor + * vgic_unqueue_irqs - move pending/active IRQs from LRs to the distributor * @vgic_cpu: Pointer to the vgic_cpu struct holding the LRs * - * Move any pending IRQs that have already been assigned to LRs back to the + * Move any IRQs that have already been assigned to LRs back to the * emulated distributor state so that the complete emulated state can be read * from the main emulation structures without investigating the LRs. - * - * Note that IRQs in the active state in the LRs get their pending state moved - * to the distributor but the active state stays in the LRs, because we don't - * track the active state on the distributor side. */ void vgic_unqueue_irqs(struct kvm_vcpu *vcpu) { @@ -613,12 +671,22 @@ void vgic_unqueue_irqs(struct kvm_vcpu *vcpu) * 01: pending * 10: active * 11: pending and active - * - * If the LR holds only an active interrupt (not pending) then - * just leave it alone. */ - if ((lr.state & LR_STATE_MASK) == LR_STATE_ACTIVE) - continue; + BUG_ON(!(lr.state & LR_STATE_MASK)); + + /* Reestablish SGI source for pending and active IRQs */ + if (lr.irq < VGIC_NR_SGIS) + add_sgi_source(vcpu, lr.irq, lr.source); + + /* + * If the LR holds an active (10) or a pending and active (11) + * interrupt then move the active state to the + * distributor tracking bit. + */ + if (lr.state & LR_STATE_ACTIVE) { + vgic_irq_set_active(vcpu, lr.irq); + lr.state &= ~LR_STATE_ACTIVE; + } /* * Reestablish the pending state on the distributor and the @@ -626,21 +694,19 @@ void vgic_unqueue_irqs(struct kvm_vcpu *vcpu) * is fine, then we are only setting a few bits that were * already set. */ - vgic_dist_irq_set_pending(vcpu, lr.irq); - if (lr.irq < VGIC_NR_SGIS) - add_sgi_source(vcpu, lr.irq, lr.source); - lr.state &= ~LR_STATE_PENDING; + if (lr.state & LR_STATE_PENDING) { + vgic_dist_irq_set_pending(vcpu, lr.irq); + lr.state &= ~LR_STATE_PENDING; + } + vgic_set_lr(vcpu, i, lr); /* - * If there's no state left on the LR (it could still be - * active), then the LR does not hold any useful info and can - * be marked as free for other use. + * Mark the LR as free for other use. */ - if (!(lr.state & LR_STATE_MASK)) { - vgic_retire_lr(i, lr.irq, vcpu); - vgic_irq_clear_queued(vcpu, lr.irq); - } + BUG_ON(lr.state & LR_STATE_MASK); + vgic_retire_lr(i, lr.irq, vcpu); + vgic_irq_clear_queued(vcpu, lr.irq); /* Finally update the VGIC state. */ vgic_update_state(vcpu->kvm); @@ -648,24 +714,21 @@ void vgic_unqueue_irqs(struct kvm_vcpu *vcpu) } const -struct kvm_mmio_range *vgic_find_range(const struct kvm_mmio_range *ranges, - struct kvm_exit_mmio *mmio, - phys_addr_t offset) -{ - const struct kvm_mmio_range *r = ranges; - - while (r->len) { - if (offset >= r->base && - (offset + mmio->len) <= (r->base + r->len)) - return r; - r++; +struct vgic_io_range *vgic_find_range(const struct vgic_io_range *ranges, + int len, gpa_t offset) +{ + while (ranges->len) { + if (offset >= ranges->base && + (offset + len) <= (ranges->base + ranges->len)) + return ranges; + ranges++; } return NULL; } static bool vgic_validate_access(const struct vgic_dist *dist, - const struct kvm_mmio_range *range, + const struct vgic_io_range *range, unsigned long offset) { int irq; @@ -693,9 +756,8 @@ static bool vgic_validate_access(const struct vgic_dist *dist, static bool call_range_handler(struct kvm_vcpu *vcpu, struct kvm_exit_mmio *mmio, unsigned long offset, - const struct kvm_mmio_range *range) + const struct vgic_io_range *range) { - u32 *data32 = (void *)mmio->data; struct kvm_exit_mmio mmio32; bool ret; @@ -712,91 +774,142 @@ static bool call_range_handler(struct kvm_vcpu *vcpu, mmio32.private = mmio->private; mmio32.phys_addr = mmio->phys_addr + 4; - if (mmio->is_write) - *(u32 *)mmio32.data = data32[1]; + mmio32.data = &((u32 *)mmio->data)[1]; ret = range->handle_mmio(vcpu, &mmio32, offset + 4); - if (!mmio->is_write) - data32[1] = *(u32 *)mmio32.data; mmio32.phys_addr = mmio->phys_addr; - if (mmio->is_write) - *(u32 *)mmio32.data = data32[0]; + mmio32.data = &((u32 *)mmio->data)[0]; ret |= range->handle_mmio(vcpu, &mmio32, offset); - if (!mmio->is_write) - data32[0] = *(u32 *)mmio32.data; return ret; } /** - * vgic_handle_mmio_range - handle an in-kernel MMIO access + * vgic_handle_mmio_access - handle an in-kernel MMIO access + * This is called by the read/write KVM IO device wrappers below. * @vcpu: pointer to the vcpu performing the access - * @run: pointer to the kvm_run structure - * @mmio: pointer to the data describing the access - * @ranges: array of MMIO ranges in a given region - * @mmio_base: base address of that region + * @this: pointer to the KVM IO device in charge + * @addr: guest physical address of the access + * @len: size of the access + * @val: pointer to the data region + * @is_write: read or write access * * returns true if the MMIO access could be performed */ -bool vgic_handle_mmio_range(struct kvm_vcpu *vcpu, struct kvm_run *run, - struct kvm_exit_mmio *mmio, - const struct kvm_mmio_range *ranges, - unsigned long mmio_base) +static int vgic_handle_mmio_access(struct kvm_vcpu *vcpu, + struct kvm_io_device *this, gpa_t addr, + int len, void *val, bool is_write) { - const struct kvm_mmio_range *range; struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + struct vgic_io_device *iodev = container_of(this, + struct vgic_io_device, dev); + struct kvm_run *run = vcpu->run; + const struct vgic_io_range *range; + struct kvm_exit_mmio mmio; bool updated_state; - unsigned long offset; + gpa_t offset; - offset = mmio->phys_addr - mmio_base; - range = vgic_find_range(ranges, mmio, offset); + offset = addr - iodev->addr; + range = vgic_find_range(iodev->reg_ranges, len, offset); if (unlikely(!range || !range->handle_mmio)) { - pr_warn("Unhandled access %d %08llx %d\n", - mmio->is_write, mmio->phys_addr, mmio->len); - return false; + pr_warn("Unhandled access %d %08llx %d\n", is_write, addr, len); + return -ENXIO; } - spin_lock(&vcpu->kvm->arch.vgic.lock); + mmio.phys_addr = addr; + mmio.len = len; + mmio.is_write = is_write; + mmio.data = val; + mmio.private = iodev->redist_vcpu; + + spin_lock(&dist->lock); offset -= range->base; if (vgic_validate_access(dist, range, offset)) { - updated_state = call_range_handler(vcpu, mmio, offset, range); + updated_state = call_range_handler(vcpu, &mmio, offset, range); } else { - if (!mmio->is_write) - memset(mmio->data, 0, mmio->len); + if (!is_write) + memset(val, 0, len); updated_state = false; } - spin_unlock(&vcpu->kvm->arch.vgic.lock); - kvm_prepare_mmio(run, mmio); + spin_unlock(&dist->lock); + run->mmio.is_write = is_write; + run->mmio.len = len; + run->mmio.phys_addr = addr; + memcpy(run->mmio.data, val, len); + kvm_handle_mmio_return(vcpu, run); if (updated_state) vgic_kick_vcpus(vcpu->kvm); - return true; + return 0; +} + +static int vgic_handle_mmio_read(struct kvm_vcpu *vcpu, + struct kvm_io_device *this, + gpa_t addr, int len, void *val) +{ + return vgic_handle_mmio_access(vcpu, this, addr, len, val, false); } +static int vgic_handle_mmio_write(struct kvm_vcpu *vcpu, + struct kvm_io_device *this, + gpa_t addr, int len, const void *val) +{ + return vgic_handle_mmio_access(vcpu, this, addr, len, (void *)val, + true); +} + +struct kvm_io_device_ops vgic_io_ops = { + .read = vgic_handle_mmio_read, + .write = vgic_handle_mmio_write, +}; + /** - * vgic_handle_mmio - handle an in-kernel MMIO access for the GIC emulation - * @vcpu: pointer to the vcpu performing the access - * @run: pointer to the kvm_run structure - * @mmio: pointer to the data describing the access + * vgic_register_kvm_io_dev - register VGIC register frame on the KVM I/O bus + * @kvm: The VM structure pointer + * @base: The (guest) base address for the register frame + * @len: Length of the register frame window + * @ranges: Describing the handler functions for each register + * @redist_vcpu_id: The VCPU ID to pass on to the handlers on call + * @iodev: Points to memory to be passed on to the handler * - * returns true if the MMIO access has been performed in kernel space, - * and false if it needs to be emulated in user space. - * Calls the actual handling routine for the selected VGIC model. + * @iodev stores the parameters of this function to be usable by the handler + * respectively the dispatcher function (since the KVM I/O bus framework lacks + * an opaque parameter). Initialization is done in this function, but the + * reference should be valid and unique for the whole VGIC lifetime. + * If the register frame is not mapped for a specific VCPU, pass -1 to + * @redist_vcpu_id. */ -bool vgic_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run, - struct kvm_exit_mmio *mmio) +int vgic_register_kvm_io_dev(struct kvm *kvm, gpa_t base, int len, + const struct vgic_io_range *ranges, + int redist_vcpu_id, + struct vgic_io_device *iodev) { - if (!irqchip_in_kernel(vcpu->kvm)) - return false; + struct kvm_vcpu *vcpu = NULL; + int ret; - /* - * This will currently call either vgic_v2_handle_mmio() or - * vgic_v3_handle_mmio(), which in turn will call - * vgic_handle_mmio_range() defined above. - */ - return vcpu->kvm->arch.vgic.vm_ops.handle_mmio(vcpu, run, mmio); + if (redist_vcpu_id >= 0) + vcpu = kvm_get_vcpu(kvm, redist_vcpu_id); + + iodev->addr = base; + iodev->len = len; + iodev->reg_ranges = ranges; + iodev->redist_vcpu = vcpu; + + kvm_iodevice_init(&iodev->dev, &vgic_io_ops); + + mutex_lock(&kvm->slots_lock); + + ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, base, len, + &iodev->dev); + mutex_unlock(&kvm->slots_lock); + + /* Mark the iodev as invalid if registration fails. */ + if (ret) + iodev->dev.ops = NULL; + + return ret; } static int vgic_nr_shared_irqs(struct vgic_dist *dist) @@ -804,6 +917,36 @@ static int vgic_nr_shared_irqs(struct vgic_dist *dist) return dist->nr_irqs - VGIC_NR_PRIVATE_IRQS; } +static int compute_active_for_cpu(struct kvm_vcpu *vcpu) +{ + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + unsigned long *active, *enabled, *act_percpu, *act_shared; + unsigned long active_private, active_shared; + int nr_shared = vgic_nr_shared_irqs(dist); + int vcpu_id; + + vcpu_id = vcpu->vcpu_id; + act_percpu = vcpu->arch.vgic_cpu.active_percpu; + act_shared = vcpu->arch.vgic_cpu.active_shared; + + active = vgic_bitmap_get_cpu_map(&dist->irq_active, vcpu_id); + enabled = vgic_bitmap_get_cpu_map(&dist->irq_enabled, vcpu_id); + bitmap_and(act_percpu, active, enabled, VGIC_NR_PRIVATE_IRQS); + + active = vgic_bitmap_get_shared_map(&dist->irq_active); + enabled = vgic_bitmap_get_shared_map(&dist->irq_enabled); + bitmap_and(act_shared, active, enabled, nr_shared); + bitmap_and(act_shared, act_shared, + vgic_bitmap_get_shared_map(&dist->irq_spi_target[vcpu_id]), + nr_shared); + + active_private = find_first_bit(act_percpu, VGIC_NR_PRIVATE_IRQS); + active_shared = find_first_bit(act_shared, nr_shared); + + return (active_private < VGIC_NR_PRIVATE_IRQS || + active_shared < nr_shared); +} + static int compute_pending_for_cpu(struct kvm_vcpu *vcpu) { struct vgic_dist *dist = &vcpu->kvm->arch.vgic; @@ -835,7 +978,7 @@ static int compute_pending_for_cpu(struct kvm_vcpu *vcpu) /* * Update the interrupt state and determine which CPUs have pending - * interrupts. Must be called with distributor lock held. + * or active interrupts. Must be called with distributor lock held. */ void vgic_update_state(struct kvm *kvm) { @@ -849,10 +992,13 @@ void vgic_update_state(struct kvm *kvm) } kvm_for_each_vcpu(c, vcpu, kvm) { - if (compute_pending_for_cpu(vcpu)) { - pr_debug("CPU%d has pending interrupts\n", c); + if (compute_pending_for_cpu(vcpu)) set_bit(c, dist->irq_pending_on_cpu); - } + + if (compute_active_for_cpu(vcpu)) + set_bit(c, dist->irq_active_on_cpu); + else + clear_bit(c, dist->irq_active_on_cpu); } } @@ -955,6 +1101,26 @@ static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu) } } +static void vgic_queue_irq_to_lr(struct kvm_vcpu *vcpu, int irq, + int lr_nr, struct vgic_lr vlr) +{ + if (vgic_irq_is_active(vcpu, irq)) { + vlr.state |= LR_STATE_ACTIVE; + kvm_debug("Set active, clear distributor: 0x%x\n", vlr.state); + vgic_irq_clear_active(vcpu, irq); + vgic_update_state(vcpu->kvm); + } else if (vgic_dist_irq_is_pending(vcpu, irq)) { + vlr.state |= LR_STATE_PENDING; + kvm_debug("Set pending: 0x%x\n", vlr.state); + } + + if (!vgic_irq_is_edge(vcpu, irq)) + vlr.state |= LR_EOI_INT; + + vgic_set_lr(vcpu, lr_nr, vlr); + vgic_sync_lr_elrsr(vcpu, lr_nr, vlr); +} + /* * Queue an interrupt to a CPU virtual interface. Return true on success, * or false if it wasn't possible to queue it. @@ -982,9 +1148,7 @@ bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq) if (vlr.source == sgi_source_id) { kvm_debug("LR%d piggyback for IRQ%d\n", lr, vlr.irq); BUG_ON(!test_bit(lr, vgic_cpu->lr_used)); - vlr.state |= LR_STATE_PENDING; - vgic_set_lr(vcpu, lr, vlr); - vgic_sync_lr_elrsr(vcpu, lr, vlr); + vgic_queue_irq_to_lr(vcpu, irq, lr, vlr); return true; } } @@ -1001,12 +1165,8 @@ bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq) vlr.irq = irq; vlr.source = sgi_source_id; - vlr.state = LR_STATE_PENDING; - if (!vgic_irq_is_edge(vcpu, irq)) - vlr.state |= LR_EOI_INT; - - vgic_set_lr(vcpu, lr, vlr); - vgic_sync_lr_elrsr(vcpu, lr, vlr); + vlr.state = 0; + vgic_queue_irq_to_lr(vcpu, irq, lr, vlr); return true; } @@ -1038,39 +1198,49 @@ static void __kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + unsigned long *pa_percpu, *pa_shared; int i, vcpu_id; int overflow = 0; + int nr_shared = vgic_nr_shared_irqs(dist); vcpu_id = vcpu->vcpu_id; + pa_percpu = vcpu->arch.vgic_cpu.pend_act_percpu; + pa_shared = vcpu->arch.vgic_cpu.pend_act_shared; + + bitmap_or(pa_percpu, vgic_cpu->pending_percpu, vgic_cpu->active_percpu, + VGIC_NR_PRIVATE_IRQS); + bitmap_or(pa_shared, vgic_cpu->pending_shared, vgic_cpu->active_shared, + nr_shared); /* * We may not have any pending interrupt, or the interrupts * may have been serviced from another vcpu. In all cases, * move along. */ - if (!kvm_vgic_vcpu_pending_irq(vcpu)) { - pr_debug("CPU%d has no pending interrupt\n", vcpu_id); + if (!kvm_vgic_vcpu_pending_irq(vcpu) && !kvm_vgic_vcpu_active_irq(vcpu)) goto epilog; - } /* SGIs */ - for_each_set_bit(i, vgic_cpu->pending_percpu, VGIC_NR_SGIS) { + for_each_set_bit(i, pa_percpu, VGIC_NR_SGIS) { if (!queue_sgi(vcpu, i)) overflow = 1; } /* PPIs */ - for_each_set_bit_from(i, vgic_cpu->pending_percpu, VGIC_NR_PRIVATE_IRQS) { + for_each_set_bit_from(i, pa_percpu, VGIC_NR_PRIVATE_IRQS) { if (!vgic_queue_hwirq(vcpu, i)) overflow = 1; } /* SPIs */ - for_each_set_bit(i, vgic_cpu->pending_shared, vgic_nr_shared_irqs(dist)) { + for_each_set_bit(i, pa_shared, nr_shared) { if (!vgic_queue_hwirq(vcpu, i + VGIC_NR_PRIVATE_IRQS)) overflow = 1; } + + + epilog: if (overflow) { vgic_enable_underflow(vcpu); @@ -1089,7 +1259,9 @@ epilog: static bool vgic_process_maintenance(struct kvm_vcpu *vcpu) { u32 status = vgic_get_interrupt_status(vcpu); + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; bool level_pending = false; + struct kvm *kvm = vcpu->kvm; kvm_debug("STATUS = %08x\n", status); @@ -1106,6 +1278,7 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu) struct vgic_lr vlr = vgic_get_lr(vcpu, lr); WARN_ON(vgic_irq_is_edge(vcpu, vlr.irq)); + spin_lock(&dist->lock); vgic_irq_clear_queued(vcpu, vlr.irq); WARN_ON(vlr.state & LR_STATE_MASK); vlr.state = 0; @@ -1124,6 +1297,17 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu) */ vgic_dist_irq_clear_soft_pend(vcpu, vlr.irq); + /* + * kvm_notify_acked_irq calls kvm_set_irq() + * to reset the IRQ level. Need to release the + * lock for kvm_set_irq to grab it. + */ + spin_unlock(&dist->lock); + + kvm_notify_acked_irq(kvm, 0, + vlr.irq - VGIC_NR_PRIVATE_IRQS); + spin_lock(&dist->lock); + /* Any additional pending interrupt? */ if (vgic_dist_irq_get_level(vcpu, vlr.irq)) { vgic_cpu_irq_set(vcpu, vlr.irq); @@ -1133,6 +1317,8 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu) vgic_cpu_irq_clear(vcpu, vlr.irq); } + spin_unlock(&dist->lock); + /* * Despite being EOIed, the LR may not have * been marked as empty. @@ -1155,10 +1341,7 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu) return level_pending; } -/* - * Sync back the VGIC state after a guest run. The distributor lock is - * needed so we don't get preempted in the middle of the state processing. - */ +/* Sync back the VGIC state after a guest run */ static void __kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; @@ -1205,14 +1388,10 @@ void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu) void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu) { - struct vgic_dist *dist = &vcpu->kvm->arch.vgic; - if (!irqchip_in_kernel(vcpu->kvm)) return; - spin_lock(&dist->lock); __kvm_vgic_sync_hwstate(vcpu); - spin_unlock(&dist->lock); } int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu) @@ -1225,6 +1404,17 @@ int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu) return test_bit(vcpu->vcpu_id, dist->irq_pending_on_cpu); } +int kvm_vgic_vcpu_active_irq(struct kvm_vcpu *vcpu) +{ + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + + if (!irqchip_in_kernel(vcpu->kvm)) + return 0; + + return test_bit(vcpu->vcpu_id, dist->irq_active_on_cpu); +} + + void vgic_kick_vcpus(struct kvm *kvm) { struct kvm_vcpu *vcpu; @@ -1397,8 +1587,12 @@ void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; kfree(vgic_cpu->pending_shared); + kfree(vgic_cpu->active_shared); + kfree(vgic_cpu->pend_act_shared); kfree(vgic_cpu->vgic_irq_lr_map); vgic_cpu->pending_shared = NULL; + vgic_cpu->active_shared = NULL; + vgic_cpu->pend_act_shared = NULL; vgic_cpu->vgic_irq_lr_map = NULL; } @@ -1408,9 +1602,14 @@ static int vgic_vcpu_init_maps(struct kvm_vcpu *vcpu, int nr_irqs) int sz = (nr_irqs - VGIC_NR_PRIVATE_IRQS) / 8; vgic_cpu->pending_shared = kzalloc(sz, GFP_KERNEL); + vgic_cpu->active_shared = kzalloc(sz, GFP_KERNEL); + vgic_cpu->pend_act_shared = kzalloc(sz, GFP_KERNEL); vgic_cpu->vgic_irq_lr_map = kmalloc(nr_irqs, GFP_KERNEL); - if (!vgic_cpu->pending_shared || !vgic_cpu->vgic_irq_lr_map) { + if (!vgic_cpu->pending_shared + || !vgic_cpu->active_shared + || !vgic_cpu->pend_act_shared + || !vgic_cpu->vgic_irq_lr_map) { kvm_vgic_vcpu_destroy(vcpu); return -ENOMEM; } @@ -1463,10 +1662,12 @@ void kvm_vgic_destroy(struct kvm *kvm) kfree(dist->irq_spi_mpidr); kfree(dist->irq_spi_target); kfree(dist->irq_pending_on_cpu); + kfree(dist->irq_active_on_cpu); dist->irq_sgi_sources = NULL; dist->irq_spi_cpu = NULL; dist->irq_spi_target = NULL; dist->irq_pending_on_cpu = NULL; + dist->irq_active_on_cpu = NULL; dist->nr_cpus = 0; } @@ -1502,6 +1703,7 @@ int vgic_init(struct kvm *kvm) ret |= vgic_init_bitmap(&dist->irq_pending, nr_cpus, nr_irqs); ret |= vgic_init_bitmap(&dist->irq_soft_pend, nr_cpus, nr_irqs); ret |= vgic_init_bitmap(&dist->irq_queued, nr_cpus, nr_irqs); + ret |= vgic_init_bitmap(&dist->irq_active, nr_cpus, nr_irqs); ret |= vgic_init_bitmap(&dist->irq_cfg, nr_cpus, nr_irqs); ret |= vgic_init_bytemap(&dist->irq_priority, nr_cpus, nr_irqs); @@ -1514,10 +1716,13 @@ int vgic_init(struct kvm *kvm) GFP_KERNEL); dist->irq_pending_on_cpu = kzalloc(BITS_TO_LONGS(nr_cpus) * sizeof(long), GFP_KERNEL); + dist->irq_active_on_cpu = kzalloc(BITS_TO_LONGS(nr_cpus) * sizeof(long), + GFP_KERNEL); if (!dist->irq_sgi_sources || !dist->irq_spi_cpu || !dist->irq_spi_target || - !dist->irq_pending_on_cpu) { + !dist->irq_pending_on_cpu || + !dist->irq_active_on_cpu) { ret = -ENOMEM; goto out; } @@ -1845,12 +2050,9 @@ int vgic_get_common_attr(struct kvm_device *dev, struct kvm_device_attr *attr) return r; } -int vgic_has_attr_regs(const struct kvm_mmio_range *ranges, phys_addr_t offset) +int vgic_has_attr_regs(const struct vgic_io_range *ranges, phys_addr_t offset) { - struct kvm_exit_mmio dev_attr_mmio; - - dev_attr_mmio.len = 4; - if (vgic_find_range(ranges, &dev_attr_mmio, offset)) + if (vgic_find_range(ranges, 4, offset)) return 0; else return -ENXIO; @@ -1883,8 +2085,10 @@ static struct notifier_block vgic_cpu_nb = { }; static const struct of_device_id vgic_ids[] = { - { .compatible = "arm,cortex-a15-gic", .data = vgic_v2_probe, }, - { .compatible = "arm,gic-v3", .data = vgic_v3_probe, }, + { .compatible = "arm,cortex-a15-gic", .data = vgic_v2_probe, }, + { .compatible = "arm,cortex-a7-gic", .data = vgic_v2_probe, }, + { .compatible = "arm,gic-400", .data = vgic_v2_probe, }, + { .compatible = "arm,gic-v3", .data = vgic_v3_probe, }, {}, }; @@ -1932,3 +2136,38 @@ out_free_irq: free_percpu_irq(vgic->maint_irq, kvm_get_running_vcpus()); return ret; } + +int kvm_irq_map_gsi(struct kvm *kvm, + struct kvm_kernel_irq_routing_entry *entries, + int gsi) +{ + return gsi; +} + +int kvm_irq_map_chip_pin(struct kvm *kvm, unsigned irqchip, unsigned pin) +{ + return pin; +} + +int kvm_set_irq(struct kvm *kvm, int irq_source_id, + u32 irq, int level, bool line_status) +{ + unsigned int spi = irq + VGIC_NR_PRIVATE_IRQS; + + trace_kvm_set_irq(irq, level, irq_source_id); + + BUG_ON(!vgic_initialized(kvm)); + + if (spi > kvm->arch.vgic.nr_irqs) + return -EINVAL; + return kvm_vgic_inject_irq(kvm, 0, spi, level); + +} + +/* MSI not implemented yet */ +int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, + struct kvm *kvm, int irq_source_id, + int level, bool line_status) +{ + return 0; +} diff --git a/virt/kvm/arm/vgic.h b/virt/kvm/arm/vgic.h index 1e83bdf5f499..0df74cbb6200 100644 --- a/virt/kvm/arm/vgic.h +++ b/virt/kvm/arm/vgic.h @@ -20,6 +20,8 @@ #ifndef __KVM_VGIC_H__ #define __KVM_VGIC_H__ +#include <kvm/iodev.h> + #define VGIC_ADDR_UNDEF (-1) #define IS_VGIC_ADDR_UNDEF(_x) ((_x) == VGIC_ADDR_UNDEF) @@ -57,6 +59,14 @@ void vgic_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr); bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq); void vgic_unqueue_irqs(struct kvm_vcpu *vcpu); +struct kvm_exit_mmio { + phys_addr_t phys_addr; + void *data; + u32 len; + bool is_write; + void *private; +}; + void vgic_reg_access(struct kvm_exit_mmio *mmio, u32 *reg, phys_addr_t offset, int mode); bool handle_mmio_raz_wi(struct kvm_vcpu *vcpu, struct kvm_exit_mmio *mmio, @@ -74,7 +84,7 @@ void mmio_data_write(struct kvm_exit_mmio *mmio, u32 mask, u32 value) *((u32 *)mmio->data) = cpu_to_le32(value) & mask; } -struct kvm_mmio_range { +struct vgic_io_range { phys_addr_t base; unsigned long len; int bits_per_irq; @@ -82,6 +92,11 @@ struct kvm_mmio_range { phys_addr_t offset); }; +int vgic_register_kvm_io_dev(struct kvm *kvm, gpa_t base, int len, + const struct vgic_io_range *ranges, + int redist_id, + struct vgic_io_device *iodev); + static inline bool is_in_range(phys_addr_t addr, unsigned long len, phys_addr_t baseaddr, unsigned long size) { @@ -89,14 +104,8 @@ static inline bool is_in_range(phys_addr_t addr, unsigned long len, } const -struct kvm_mmio_range *vgic_find_range(const struct kvm_mmio_range *ranges, - struct kvm_exit_mmio *mmio, - phys_addr_t offset); - -bool vgic_handle_mmio_range(struct kvm_vcpu *vcpu, struct kvm_run *run, - struct kvm_exit_mmio *mmio, - const struct kvm_mmio_range *ranges, - unsigned long mmio_base); +struct vgic_io_range *vgic_find_range(const struct vgic_io_range *ranges, + int len, gpa_t offset); bool vgic_handle_enable_reg(struct kvm *kvm, struct kvm_exit_mmio *mmio, phys_addr_t offset, int vcpu_id, int access); @@ -107,12 +116,20 @@ bool vgic_handle_set_pending_reg(struct kvm *kvm, struct kvm_exit_mmio *mmio, bool vgic_handle_clear_pending_reg(struct kvm *kvm, struct kvm_exit_mmio *mmio, phys_addr_t offset, int vcpu_id); +bool vgic_handle_set_active_reg(struct kvm *kvm, + struct kvm_exit_mmio *mmio, + phys_addr_t offset, int vcpu_id); + +bool vgic_handle_clear_active_reg(struct kvm *kvm, + struct kvm_exit_mmio *mmio, + phys_addr_t offset, int vcpu_id); + bool vgic_handle_cfg_reg(u32 *reg, struct kvm_exit_mmio *mmio, phys_addr_t offset); void vgic_kick_vcpus(struct kvm *kvm); -int vgic_has_attr_regs(const struct kvm_mmio_range *ranges, phys_addr_t offset); +int vgic_has_attr_regs(const struct vgic_io_range *ranges, phys_addr_t offset); int vgic_set_common_attr(struct kvm_device *dev, struct kvm_device_attr *attr); int vgic_get_common_attr(struct kvm_device *dev, struct kvm_device_attr *attr); diff --git a/virt/kvm/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c index 00d86427af0f..571c1ce37d15 100644 --- a/virt/kvm/coalesced_mmio.c +++ b/virt/kvm/coalesced_mmio.c @@ -8,7 +8,7 @@ * */ -#include "iodev.h" +#include <kvm/iodev.h> #include <linux/kvm_host.h> #include <linux/slab.h> @@ -60,8 +60,9 @@ static int coalesced_mmio_has_room(struct kvm_coalesced_mmio_dev *dev) return 1; } -static int coalesced_mmio_write(struct kvm_io_device *this, - gpa_t addr, int len, const void *val) +static int coalesced_mmio_write(struct kvm_vcpu *vcpu, + struct kvm_io_device *this, gpa_t addr, + int len, const void *val) { struct kvm_coalesced_mmio_dev *dev = to_mmio(this); struct kvm_coalesced_mmio_ring *ring = dev->kvm->coalesced_mmio_ring; diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index 148b2392c762..9ff4193dfa49 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -36,7 +36,7 @@ #include <linux/seqlock.h> #include <trace/events/kvm.h> -#include "iodev.h" +#include <kvm/iodev.h> #ifdef CONFIG_HAVE_KVM_IRQFD /* @@ -311,6 +311,9 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args) unsigned int events; int idx; + if (!kvm_arch_intc_initialized(kvm)) + return -EAGAIN; + irqfd = kzalloc(sizeof(*irqfd), GFP_KERNEL); if (!irqfd) return -ENOMEM; @@ -712,8 +715,8 @@ ioeventfd_in_range(struct _ioeventfd *p, gpa_t addr, int len, const void *val) /* MMIO/PIO writes trigger an event if the addr/val match */ static int -ioeventfd_write(struct kvm_io_device *this, gpa_t addr, int len, - const void *val) +ioeventfd_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this, gpa_t addr, + int len, const void *val) { struct _ioeventfd *p = to_ioeventfd(this); diff --git a/virt/kvm/irqchip.c b/virt/kvm/irqchip.c index 7f256f31df10..1d56a901e791 100644 --- a/virt/kvm/irqchip.c +++ b/virt/kvm/irqchip.c @@ -105,7 +105,7 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level, i = kvm_irq_map_gsi(kvm, irq_set, irq); srcu_read_unlock(&kvm->irq_srcu, idx); - while(i--) { + while (i--) { int r; r = irq_set[i].set(&irq_set[i], kvm, irq_source_id, level, line_status); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index cc6a25d95fbf..d3fc9399062a 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -16,7 +16,7 @@ * */ -#include "iodev.h" +#include <kvm/iodev.h> #include <linux/kvm_host.h> #include <linux/kvm.h> @@ -66,13 +66,13 @@ MODULE_AUTHOR("Qumranet"); MODULE_LICENSE("GPL"); -unsigned int halt_poll_ns = 0; +static unsigned int halt_poll_ns; module_param(halt_poll_ns, uint, S_IRUGO | S_IWUSR); /* * Ordering of locks: * - * kvm->lock --> kvm->slots_lock --> kvm->irq_lock + * kvm->lock --> kvm->slots_lock --> kvm->irq_lock */ DEFINE_SPINLOCK(kvm_lock); @@ -80,7 +80,7 @@ static DEFINE_RAW_SPINLOCK(kvm_count_lock); LIST_HEAD(vm_list); static cpumask_var_t cpus_hardware_enabled; -static int kvm_usage_count = 0; +static int kvm_usage_count; static atomic_t hardware_enable_failed; struct kmem_cache *kvm_vcpu_cache; @@ -539,20 +539,12 @@ void *kvm_kvzalloc(unsigned long size) return kzalloc(size, GFP_KERNEL); } -void kvm_kvfree(const void *addr) -{ - if (is_vmalloc_addr(addr)) - vfree(addr); - else - kfree(addr); -} - static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot) { if (!memslot->dirty_bitmap) return; - kvm_kvfree(memslot->dirty_bitmap); + kvfree(memslot->dirty_bitmap); memslot->dirty_bitmap = NULL; } @@ -888,8 +880,8 @@ int __kvm_set_memory_region(struct kvm *kvm, * or moved, memslot will be created. * * validation of sp->gfn happens in: - * - gfn_to_hva (kvm_read_guest, gfn_to_pfn) - * - kvm_is_visible_gfn (mmu_check_roots) + * - gfn_to_hva (kvm_read_guest, gfn_to_pfn) + * - kvm_is_visible_gfn (mmu_check_roots) */ kvm_arch_flush_shadow_memslot(kvm, slot); @@ -1061,9 +1053,11 @@ int kvm_get_dirty_log_protect(struct kvm *kvm, mask = xchg(&dirty_bitmap[i], 0); dirty_bitmap_buffer[i] = mask; - offset = i * BITS_PER_LONG; - kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot, offset, - mask); + if (mask) { + offset = i * BITS_PER_LONG; + kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot, + offset, mask); + } } spin_unlock(&kvm->mmu_lock); @@ -1193,16 +1187,6 @@ unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable) return gfn_to_hva_memslot_prot(slot, gfn, writable); } -static int kvm_read_hva(void *data, void __user *hva, int len) -{ - return __copy_from_user(data, hva, len); -} - -static int kvm_read_hva_atomic(void *data, void __user *hva, int len) -{ - return __copy_from_user_inatomic(data, hva, len); -} - static int get_user_page_nowait(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, int write, struct page **page) { @@ -1481,7 +1465,6 @@ struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn) return kvm_pfn_to_page(pfn); } - EXPORT_SYMBOL_GPL(gfn_to_page); void kvm_release_page_clean(struct page *page) @@ -1517,6 +1500,7 @@ void kvm_set_pfn_dirty(pfn_t pfn) { if (!kvm_is_reserved_pfn(pfn)) { struct page *page = pfn_to_page(pfn); + if (!PageReserved(page)) SetPageDirty(page); } @@ -1554,7 +1538,7 @@ int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, addr = gfn_to_hva_prot(kvm, gfn, NULL); if (kvm_is_error_hva(addr)) return -EFAULT; - r = kvm_read_hva(data, (void __user *)addr + offset, len); + r = __copy_from_user(data, (void __user *)addr + offset, len); if (r) return -EFAULT; return 0; @@ -1593,7 +1577,7 @@ int kvm_read_guest_atomic(struct kvm *kvm, gpa_t gpa, void *data, if (kvm_is_error_hva(addr)) return -EFAULT; pagefault_disable(); - r = kvm_read_hva_atomic(data, (void __user *)addr + offset, len); + r = __copy_from_user_inatomic(data, (void __user *)addr + offset, len); pagefault_enable(); if (r) return -EFAULT; @@ -1653,8 +1637,8 @@ int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc, ghc->generation = slots->generation; ghc->len = len; ghc->memslot = gfn_to_memslot(kvm, start_gfn); - ghc->hva = gfn_to_hva_many(ghc->memslot, start_gfn, &nr_pages_avail); - if (!kvm_is_error_hva(ghc->hva) && nr_pages_avail >= nr_pages_needed) { + ghc->hva = gfn_to_hva_many(ghc->memslot, start_gfn, NULL); + if (!kvm_is_error_hva(ghc->hva) && nr_pages_needed <= 1) { ghc->hva += offset; } else { /* @@ -1742,7 +1726,7 @@ int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len) int offset = offset_in_page(gpa); int ret; - while ((seg = next_segment(len, offset)) != 0) { + while ((seg = next_segment(len, offset)) != 0) { ret = kvm_clear_guest_page(kvm, gfn, offset, seg); if (ret < 0) return ret; @@ -1800,6 +1784,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) start = cur = ktime_get(); if (halt_poll_ns) { ktime_t stop = ktime_add_ns(ktime_get(), halt_poll_ns); + do { /* * This sets KVM_REQ_UNHALT if an interrupt @@ -2118,7 +2103,7 @@ static long kvm_vcpu_ioctl(struct file *filp, * Special cases: vcpu ioctls that are asynchronous to vcpu execution, * so vcpu_load() would break it. */ - if (ioctl == KVM_S390_INTERRUPT || ioctl == KVM_INTERRUPT) + if (ioctl == KVM_S390_INTERRUPT || ioctl == KVM_S390_IRQ || ioctl == KVM_INTERRUPT) return kvm_arch_vcpu_ioctl(filp, ioctl, arg); #endif @@ -2135,6 +2120,7 @@ static long kvm_vcpu_ioctl(struct file *filp, /* The thread running this VCPU changed. */ struct pid *oldpid = vcpu->pid; struct pid *newpid = get_task_pid(current, PIDTYPE_PID); + rcu_assign_pointer(vcpu->pid, newpid); if (oldpid) synchronize_rcu(); @@ -2205,7 +2191,7 @@ out_free1: if (r) goto out; r = -EFAULT; - if (copy_to_user(argp, &mp_state, sizeof mp_state)) + if (copy_to_user(argp, &mp_state, sizeof(mp_state))) goto out; r = 0; break; @@ -2214,7 +2200,7 @@ out_free1: struct kvm_mp_state mp_state; r = -EFAULT; - if (copy_from_user(&mp_state, argp, sizeof mp_state)) + if (copy_from_user(&mp_state, argp, sizeof(mp_state))) goto out; r = kvm_arch_vcpu_ioctl_set_mpstate(vcpu, &mp_state); break; @@ -2223,13 +2209,13 @@ out_free1: struct kvm_translation tr; r = -EFAULT; - if (copy_from_user(&tr, argp, sizeof tr)) + if (copy_from_user(&tr, argp, sizeof(tr))) goto out; r = kvm_arch_vcpu_ioctl_translate(vcpu, &tr); if (r) goto out; r = -EFAULT; - if (copy_to_user(argp, &tr, sizeof tr)) + if (copy_to_user(argp, &tr, sizeof(tr))) goto out; r = 0; break; @@ -2238,7 +2224,7 @@ out_free1: struct kvm_guest_debug dbg; r = -EFAULT; - if (copy_from_user(&dbg, argp, sizeof dbg)) + if (copy_from_user(&dbg, argp, sizeof(dbg))) goto out; r = kvm_arch_vcpu_ioctl_set_guest_debug(vcpu, &dbg); break; @@ -2252,14 +2238,14 @@ out_free1: if (argp) { r = -EFAULT; if (copy_from_user(&kvm_sigmask, argp, - sizeof kvm_sigmask)) + sizeof(kvm_sigmask))) goto out; r = -EINVAL; - if (kvm_sigmask.len != sizeof sigset) + if (kvm_sigmask.len != sizeof(sigset)) goto out; r = -EFAULT; if (copy_from_user(&sigset, sigmask_arg->sigset, - sizeof sigset)) + sizeof(sigset))) goto out; p = &sigset; } @@ -2321,14 +2307,14 @@ static long kvm_vcpu_compat_ioctl(struct file *filp, if (argp) { r = -EFAULT; if (copy_from_user(&kvm_sigmask, argp, - sizeof kvm_sigmask)) + sizeof(kvm_sigmask))) goto out; r = -EINVAL; - if (kvm_sigmask.len != sizeof csigset) + if (kvm_sigmask.len != sizeof(csigset)) goto out; r = -EFAULT; if (copy_from_user(&csigset, sigmask_arg->sigset, - sizeof csigset)) + sizeof(csigset))) goto out; sigset_from_compat(&sigset, &csigset); r = kvm_vcpu_ioctl_set_sigmask(vcpu, &sigset); @@ -2525,7 +2511,7 @@ static long kvm_vm_ioctl(struct file *filp, r = -EFAULT; if (copy_from_user(&kvm_userspace_mem, argp, - sizeof kvm_userspace_mem)) + sizeof(kvm_userspace_mem))) goto out; r = kvm_vm_ioctl_set_memory_region(kvm, &kvm_userspace_mem); @@ -2535,7 +2521,7 @@ static long kvm_vm_ioctl(struct file *filp, struct kvm_dirty_log log; r = -EFAULT; - if (copy_from_user(&log, argp, sizeof log)) + if (copy_from_user(&log, argp, sizeof(log))) goto out; r = kvm_vm_ioctl_get_dirty_log(kvm, &log); break; @@ -2543,16 +2529,18 @@ static long kvm_vm_ioctl(struct file *filp, #ifdef KVM_COALESCED_MMIO_PAGE_OFFSET case KVM_REGISTER_COALESCED_MMIO: { struct kvm_coalesced_mmio_zone zone; + r = -EFAULT; - if (copy_from_user(&zone, argp, sizeof zone)) + if (copy_from_user(&zone, argp, sizeof(zone))) goto out; r = kvm_vm_ioctl_register_coalesced_mmio(kvm, &zone); break; } case KVM_UNREGISTER_COALESCED_MMIO: { struct kvm_coalesced_mmio_zone zone; + r = -EFAULT; - if (copy_from_user(&zone, argp, sizeof zone)) + if (copy_from_user(&zone, argp, sizeof(zone))) goto out; r = kvm_vm_ioctl_unregister_coalesced_mmio(kvm, &zone); break; @@ -2562,7 +2550,7 @@ static long kvm_vm_ioctl(struct file *filp, struct kvm_irqfd data; r = -EFAULT; - if (copy_from_user(&data, argp, sizeof data)) + if (copy_from_user(&data, argp, sizeof(data))) goto out; r = kvm_irqfd(kvm, &data); break; @@ -2571,7 +2559,7 @@ static long kvm_vm_ioctl(struct file *filp, struct kvm_ioeventfd data; r = -EFAULT; - if (copy_from_user(&data, argp, sizeof data)) + if (copy_from_user(&data, argp, sizeof(data))) goto out; r = kvm_ioeventfd(kvm, &data); break; @@ -2592,7 +2580,7 @@ static long kvm_vm_ioctl(struct file *filp, struct kvm_msi msi; r = -EFAULT; - if (copy_from_user(&msi, argp, sizeof msi)) + if (copy_from_user(&msi, argp, sizeof(msi))) goto out; r = kvm_send_userspace_msi(kvm, &msi); break; @@ -2604,7 +2592,7 @@ static long kvm_vm_ioctl(struct file *filp, struct kvm_irq_level irq_event; r = -EFAULT; - if (copy_from_user(&irq_event, argp, sizeof irq_event)) + if (copy_from_user(&irq_event, argp, sizeof(irq_event))) goto out; r = kvm_vm_ioctl_irq_line(kvm, &irq_event, @@ -2614,7 +2602,7 @@ static long kvm_vm_ioctl(struct file *filp, r = -EFAULT; if (ioctl == KVM_IRQ_LINE_STATUS) { - if (copy_to_user(argp, &irq_event, sizeof irq_event)) + if (copy_to_user(argp, &irq_event, sizeof(irq_event))) goto out; } @@ -2647,7 +2635,7 @@ static long kvm_vm_ioctl(struct file *filp, goto out_free_irq_routing; r = kvm_set_irq_routing(kvm, entries, routing.nr, routing.flags); - out_free_irq_routing: +out_free_irq_routing: vfree(entries); break; } @@ -2822,8 +2810,7 @@ static void hardware_enable_nolock(void *junk) if (r) { cpumask_clear_cpu(cpu, cpus_hardware_enabled); atomic_inc(&hardware_enable_failed); - printk(KERN_INFO "kvm: enabling virtualization on " - "CPU%d failed\n", cpu); + pr_info("kvm: enabling virtualization on CPU%d failed\n", cpu); } } @@ -2899,12 +2886,12 @@ static int kvm_cpu_hotplug(struct notifier_block *notifier, unsigned long val, val &= ~CPU_TASKS_FROZEN; switch (val) { case CPU_DYING: - printk(KERN_INFO "kvm: disabling virtualization on CPU%d\n", + pr_info("kvm: disabling virtualization on CPU%d\n", cpu); hardware_disable(); break; case CPU_STARTING: - printk(KERN_INFO "kvm: enabling virtualization on CPU%d\n", + pr_info("kvm: enabling virtualization on CPU%d\n", cpu); hardware_enable(); break; @@ -2921,7 +2908,7 @@ static int kvm_reboot(struct notifier_block *notifier, unsigned long val, * * And Intel TXT required VMX off for all cpu when system shutdown. */ - printk(KERN_INFO "kvm: exiting hardware virtualization\n"); + pr_info("kvm: exiting hardware virtualization\n"); kvm_rebooting = true; on_each_cpu(hardware_disable_nolock, NULL, 1); return NOTIFY_OK; @@ -2945,7 +2932,7 @@ static void kvm_io_bus_destroy(struct kvm_io_bus *bus) } static inline int kvm_io_bus_cmp(const struct kvm_io_range *r1, - const struct kvm_io_range *r2) + const struct kvm_io_range *r2) { if (r1->addr < r2->addr) return -1; @@ -2998,7 +2985,7 @@ static int kvm_io_bus_get_first_dev(struct kvm_io_bus *bus, return off; } -static int __kvm_io_bus_write(struct kvm_io_bus *bus, +static int __kvm_io_bus_write(struct kvm_vcpu *vcpu, struct kvm_io_bus *bus, struct kvm_io_range *range, const void *val) { int idx; @@ -3009,7 +2996,7 @@ static int __kvm_io_bus_write(struct kvm_io_bus *bus, while (idx < bus->dev_count && kvm_io_bus_cmp(range, &bus->range[idx]) == 0) { - if (!kvm_iodevice_write(bus->range[idx].dev, range->addr, + if (!kvm_iodevice_write(vcpu, bus->range[idx].dev, range->addr, range->len, val)) return idx; idx++; @@ -3019,7 +3006,7 @@ static int __kvm_io_bus_write(struct kvm_io_bus *bus, } /* kvm_io_bus_write - called under kvm->slots_lock */ -int kvm_io_bus_write(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, +int kvm_io_bus_write(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, int len, const void *val) { struct kvm_io_bus *bus; @@ -3031,14 +3018,14 @@ int kvm_io_bus_write(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, .len = len, }; - bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu); - r = __kvm_io_bus_write(bus, &range, val); + bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu); + r = __kvm_io_bus_write(vcpu, bus, &range, val); return r < 0 ? r : 0; } /* kvm_io_bus_write_cookie - called under kvm->slots_lock */ -int kvm_io_bus_write_cookie(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, - int len, const void *val, long cookie) +int kvm_io_bus_write_cookie(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, + gpa_t addr, int len, const void *val, long cookie) { struct kvm_io_bus *bus; struct kvm_io_range range; @@ -3048,12 +3035,12 @@ int kvm_io_bus_write_cookie(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, .len = len, }; - bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu); + bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu); /* First try the device referenced by cookie. */ if ((cookie >= 0) && (cookie < bus->dev_count) && (kvm_io_bus_cmp(&range, &bus->range[cookie]) == 0)) - if (!kvm_iodevice_write(bus->range[cookie].dev, addr, len, + if (!kvm_iodevice_write(vcpu, bus->range[cookie].dev, addr, len, val)) return cookie; @@ -3061,11 +3048,11 @@ int kvm_io_bus_write_cookie(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, * cookie contained garbage; fall back to search and return the * correct cookie value. */ - return __kvm_io_bus_write(bus, &range, val); + return __kvm_io_bus_write(vcpu, bus, &range, val); } -static int __kvm_io_bus_read(struct kvm_io_bus *bus, struct kvm_io_range *range, - void *val) +static int __kvm_io_bus_read(struct kvm_vcpu *vcpu, struct kvm_io_bus *bus, + struct kvm_io_range *range, void *val) { int idx; @@ -3075,7 +3062,7 @@ static int __kvm_io_bus_read(struct kvm_io_bus *bus, struct kvm_io_range *range, while (idx < bus->dev_count && kvm_io_bus_cmp(range, &bus->range[idx]) == 0) { - if (!kvm_iodevice_read(bus->range[idx].dev, range->addr, + if (!kvm_iodevice_read(vcpu, bus->range[idx].dev, range->addr, range->len, val)) return idx; idx++; @@ -3086,7 +3073,7 @@ static int __kvm_io_bus_read(struct kvm_io_bus *bus, struct kvm_io_range *range, EXPORT_SYMBOL_GPL(kvm_io_bus_write); /* kvm_io_bus_read - called under kvm->slots_lock */ -int kvm_io_bus_read(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, +int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, int len, void *val) { struct kvm_io_bus *bus; @@ -3098,8 +3085,8 @@ int kvm_io_bus_read(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, .len = len, }; - bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu); - r = __kvm_io_bus_read(bus, &range, val); + bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu); + r = __kvm_io_bus_read(vcpu, bus, &range, val); return r < 0 ? r : 0; } @@ -3269,6 +3256,7 @@ struct kvm_vcpu *preempt_notifier_to_vcpu(struct preempt_notifier *pn) static void kvm_sched_in(struct preempt_notifier *pn, int cpu) { struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn); + if (vcpu->preempted) vcpu->preempted = false; @@ -3350,7 +3338,7 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, r = misc_register(&kvm_dev); if (r) { - printk(KERN_ERR "kvm: misc device register failed\n"); + pr_err("kvm: misc device register failed\n"); goto out_unreg; } @@ -3361,7 +3349,7 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, r = kvm_init_debug(); if (r) { - printk(KERN_ERR "kvm: create debugfs files failed\n"); + pr_err("kvm: create debugfs files failed\n"); goto out_undebugfs; } |