diff options
79 files changed, 856 insertions, 503 deletions
diff --git a/Documentation/kbuild/makefiles.txt b/Documentation/kbuild/makefiles.txt index e63b446d973c..13f888a02a3d 100644 --- a/Documentation/kbuild/makefiles.txt +++ b/Documentation/kbuild/makefiles.txt @@ -952,6 +952,14 @@ When kbuild executes, the following steps are followed (roughly): $(KBUILD_ARFLAGS) set by the top level Makefile to "D" (deterministic mode) if this option is supported by $(AR). + ARCH_CPPFLAGS, ARCH_AFLAGS, ARCH_CFLAGS Overrides the kbuild defaults + + These variables are appended to the KBUILD_CPPFLAGS, + KBUILD_AFLAGS, and KBUILD_CFLAGS, respectively, after the + top-level Makefile has set any other flags. This provides a + means for an architecture to override the defaults. + + --- 6.2 Add prerequisites to archheaders: The archheaders: rule is used to generate header files that @@ -780,10 +780,11 @@ endif include scripts/Makefile.kasan include scripts/Makefile.extrawarn -# Add user supplied CPPFLAGS, AFLAGS and CFLAGS as the last assignments -KBUILD_CPPFLAGS += $(KCPPFLAGS) -KBUILD_AFLAGS += $(KAFLAGS) -KBUILD_CFLAGS += $(KCFLAGS) +# Add any arch overrides and user supplied CPPFLAGS, AFLAGS and CFLAGS as the +# last assignments +KBUILD_CPPFLAGS += $(ARCH_CPPFLAGS) $(KCPPFLAGS) +KBUILD_AFLAGS += $(ARCH_AFLAGS) $(KAFLAGS) +KBUILD_CFLAGS += $(ARCH_CFLAGS) $(KCFLAGS) # Use --build-id when available. LDFLAGS_BUILD_ID = $(patsubst -Wl$(comma)%,%,\ diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index e7cee0a5c56d..91cf4055acab 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -115,6 +115,7 @@ if ISA_ARCOMPACT config ARC_CPU_750D bool "ARC750D" + select ARC_CANT_LLSC help Support for ARC750 core @@ -362,7 +363,7 @@ config ARC_CANT_LLSC config ARC_HAS_LLSC bool "Insn: LLOCK/SCOND (efficient atomic ops)" default y - depends on !ARC_CPU_750D && !ARC_CANT_LLSC + depends on !ARC_CANT_LLSC config ARC_HAS_SWAPE bool "Insn: SWAPE (endian-swap)" diff --git a/arch/arc/Makefile b/arch/arc/Makefile index 6107062c0111..46d87310220d 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -49,7 +49,8 @@ endif ifndef CONFIG_CC_OPTIMIZE_FOR_SIZE # Generic build system uses -O2, we want -O3 -cflags-y += -O3 +# Note: No need to add to cflags-y as that happens anyways +ARCH_CFLAGS += -O3 endif # small data is default for elf32 tool-chain. If not usable, disable it diff --git a/arch/arc/boot/dts/axc003.dtsi b/arch/arc/boot/dts/axc003.dtsi index 15c8d6226c9d..1cd5e82f5dc2 100644 --- a/arch/arc/boot/dts/axc003.dtsi +++ b/arch/arc/boot/dts/axc003.dtsi @@ -12,7 +12,7 @@ / { compatible = "snps,arc"; - clock-frequency = <75000000>; + clock-frequency = <90000000>; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arc/boot/dts/axc003_idu.dtsi b/arch/arc/boot/dts/axc003_idu.dtsi index 199d42820eca..2f0b33257db2 100644 --- a/arch/arc/boot/dts/axc003_idu.dtsi +++ b/arch/arc/boot/dts/axc003_idu.dtsi @@ -12,7 +12,7 @@ / { compatible = "snps,arc"; - clock-frequency = <75000000>; + clock-frequency = <90000000>; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arc/include/asm/bitops.h b/arch/arc/include/asm/bitops.h index 99fe118d3730..57c1f33844d4 100644 --- a/arch/arc/include/asm/bitops.h +++ b/arch/arc/include/asm/bitops.h @@ -50,8 +50,7 @@ static inline void op##_bit(unsigned long nr, volatile unsigned long *m)\ * done for const @nr, but no code is generated due to gcc \ * const prop. \ */ \ - if (__builtin_constant_p(nr)) \ - nr &= 0x1f; \ + nr &= 0x1f; \ \ __asm__ __volatile__( \ "1: llock %0, [%1] \n" \ @@ -82,8 +81,7 @@ static inline int test_and_##op##_bit(unsigned long nr, volatile unsigned long * \ m += nr >> 5; \ \ - if (__builtin_constant_p(nr)) \ - nr &= 0x1f; \ + nr &= 0x1f; \ \ /* \ * Explicit full memory barrier needed before/after as \ @@ -129,16 +127,13 @@ static inline void op##_bit(unsigned long nr, volatile unsigned long *m)\ unsigned long temp, flags; \ m += nr >> 5; \ \ - if (__builtin_constant_p(nr)) \ - nr &= 0x1f; \ - \ /* \ * spin lock/unlock provide the needed smp_mb() before/after \ */ \ bitops_lock(flags); \ \ temp = *m; \ - *m = temp c_op (1UL << nr); \ + *m = temp c_op (1UL << (nr & 0x1f)); \ \ bitops_unlock(flags); \ } @@ -149,17 +144,14 @@ static inline int test_and_##op##_bit(unsigned long nr, volatile unsigned long * unsigned long old, flags; \ m += nr >> 5; \ \ - if (__builtin_constant_p(nr)) \ - nr &= 0x1f; \ - \ bitops_lock(flags); \ \ old = *m; \ - *m = old c_op (1 << nr); \ + *m = old c_op (1UL << (nr & 0x1f)); \ \ bitops_unlock(flags); \ \ - return (old & (1 << nr)) != 0; \ + return (old & (1UL << (nr & 0x1f))) != 0; \ } #endif /* CONFIG_ARC_HAS_LLSC */ @@ -174,11 +166,8 @@ static inline void __##op##_bit(unsigned long nr, volatile unsigned long *m) \ unsigned long temp; \ m += nr >> 5; \ \ - if (__builtin_constant_p(nr)) \ - nr &= 0x1f; \ - \ temp = *m; \ - *m = temp c_op (1UL << nr); \ + *m = temp c_op (1UL << (nr & 0x1f)); \ } #define __TEST_N_BIT_OP(op, c_op, asm_op) \ @@ -187,13 +176,10 @@ static inline int __test_and_##op##_bit(unsigned long nr, volatile unsigned long unsigned long old; \ m += nr >> 5; \ \ - if (__builtin_constant_p(nr)) \ - nr &= 0x1f; \ - \ old = *m; \ - *m = old c_op (1 << nr); \ + *m = old c_op (1UL << (nr & 0x1f)); \ \ - return (old & (1 << nr)) != 0; \ + return (old & (1UL << (nr & 0x1f))) != 0; \ } #define BIT_OPS(op, c_op, asm_op) \ @@ -224,10 +210,7 @@ test_bit(unsigned int nr, const volatile unsigned long *addr) addr += nr >> 5; - if (__builtin_constant_p(nr)) - nr &= 0x1f; - - mask = 1 << nr; + mask = 1UL << (nr & 0x1f); return ((mask & *addr) != 0); } diff --git a/arch/arc/include/asm/futex.h b/arch/arc/include/asm/futex.h index 05b5aaf5b0f9..70cfe16b742d 100644 --- a/arch/arc/include/asm/futex.h +++ b/arch/arc/include/asm/futex.h @@ -16,12 +16,40 @@ #include <linux/uaccess.h> #include <asm/errno.h> +#ifdef CONFIG_ARC_HAS_LLSC + +#define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)\ + \ + __asm__ __volatile__( \ + "1: llock %1, [%2] \n" \ + insn "\n" \ + "2: scond %0, [%2] \n" \ + " bnz 1b \n" \ + " mov %0, 0 \n" \ + "3: \n" \ + " .section .fixup,\"ax\" \n" \ + " .align 4 \n" \ + "4: mov %0, %4 \n" \ + " b 3b \n" \ + " .previous \n" \ + " .section __ex_table,\"a\" \n" \ + " .align 4 \n" \ + " .word 1b, 4b \n" \ + " .word 2b, 4b \n" \ + " .previous \n" \ + \ + : "=&r" (ret), "=&r" (oldval) \ + : "r" (uaddr), "r" (oparg), "ir" (-EFAULT) \ + : "cc", "memory") + +#else /* !CONFIG_ARC_HAS_LLSC */ + #define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)\ \ __asm__ __volatile__( \ - "1: ld %1, [%2] \n" \ + "1: ld %1, [%2] \n" \ insn "\n" \ - "2: st %0, [%2] \n" \ + "2: st %0, [%2] \n" \ " mov %0, 0 \n" \ "3: \n" \ " .section .fixup,\"ax\" \n" \ @@ -39,6 +67,8 @@ : "r" (uaddr), "r" (oparg), "ir" (-EFAULT) \ : "cc", "memory") +#endif + static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr) { int op = (encoded_op >> 28) & 7; @@ -123,11 +153,17 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval, pagefault_disable(); - /* TBD : can use llock/scond */ __asm__ __volatile__( - "1: ld %0, [%3] \n" - " brne %0, %1, 3f \n" - "2: st %2, [%3] \n" +#ifdef CONFIG_ARC_HAS_LLSC + "1: llock %0, [%3] \n" + " brne %0, %1, 3f \n" + "2: scond %2, [%3] \n" + " bnz 1b \n" +#else + "1: ld %0, [%3] \n" + " brne %0, %1, 3f \n" + "2: st %2, [%3] \n" +#endif "3: \n" " .section .fixup,\"ax\" \n" "4: mov %0, %4 \n" diff --git a/arch/arc/include/asm/ptrace.h b/arch/arc/include/asm/ptrace.h index 91755972b9a2..91694ec1ce95 100644 --- a/arch/arc/include/asm/ptrace.h +++ b/arch/arc/include/asm/ptrace.h @@ -106,7 +106,7 @@ struct callee_regs { long r25, r24, r23, r22, r21, r20, r19, r18, r17, r16, r15, r14, r13; }; -#define instruction_pointer(regs) ((regs)->ret) +#define instruction_pointer(regs) (unsigned long)((regs)->ret) #define profile_pc(regs) instruction_pointer(regs) /* return 1 if user mode or 0 if kernel mode */ diff --git a/arch/arc/kernel/intc-arcv2.c b/arch/arc/kernel/intc-arcv2.c index 6208c630abed..26c156827479 100644 --- a/arch/arc/kernel/intc-arcv2.c +++ b/arch/arc/kernel/intc-arcv2.c @@ -12,7 +12,6 @@ #include <linux/of.h> #include <linux/irqdomain.h> #include <linux/irqchip.h> -#include "../../drivers/irqchip/irqchip.h" #include <asm/irq.h> /* diff --git a/arch/arc/kernel/intc-compact.c b/arch/arc/kernel/intc-compact.c index fcdddb631766..039fac30b5c1 100644 --- a/arch/arc/kernel/intc-compact.c +++ b/arch/arc/kernel/intc-compact.c @@ -12,7 +12,6 @@ #include <linux/of.h> #include <linux/irqdomain.h> #include <linux/irqchip.h> -#include "../../drivers/irqchip/irqchip.h" #include <asm/irq.h> /* diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c index 30284e8de6ff..2fb86589054d 100644 --- a/arch/arc/kernel/mcip.c +++ b/arch/arc/kernel/mcip.c @@ -175,7 +175,6 @@ void mcip_init_early_smp(void) #include <linux/irqchip.h> #include <linux/of.h> #include <linux/of_irq.h> -#include "../../drivers/irqchip/irqchip.h" /* * Set the DEST for @cmn_irq to @cpu_mask (1 bit per core) @@ -218,11 +217,28 @@ static void idu_irq_unmask(struct irq_data *data) raw_spin_unlock_irqrestore(&mcip_lock, flags); } +#ifdef CONFIG_SMP static int -idu_irq_set_affinity(struct irq_data *d, const struct cpumask *cpumask, bool f) +idu_irq_set_affinity(struct irq_data *data, const struct cpumask *cpumask, + bool force) { + unsigned long flags; + cpumask_t online; + + /* errout if no online cpu per @cpumask */ + if (!cpumask_and(&online, cpumask, cpu_online_mask)) + return -EINVAL; + + raw_spin_lock_irqsave(&mcip_lock, flags); + + idu_set_dest(data->hwirq, cpumask_bits(&online)[0]); + idu_set_mode(data->hwirq, IDU_M_TRIG_LEVEL, IDU_M_DISTRI_RR); + + raw_spin_unlock_irqrestore(&mcip_lock, flags); + return IRQ_SET_MASK_OK; } +#endif static struct irq_chip idu_irq_chip = { .name = "MCIP IDU Intc", @@ -330,8 +346,7 @@ idu_of_init(struct device_node *intc, struct device_node *parent) if (!i) idu_first_irq = irq; - irq_set_handler_data(irq, domain); - irq_set_chained_handler(irq, idu_cascade_isr); + irq_set_chained_handler_and_data(irq, idu_cascade_isr, domain); } __mcip_cmd(CMD_IDU_ENABLE, 0); diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index a3d186211ed3..18cc01591c96 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -142,17 +142,22 @@ static void read_arc_build_cfg_regs(void) } static const struct cpuinfo_data arc_cpu_tbl[] = { +#ifdef CONFIG_ISA_ARCOMPACT { {0x20, "ARC 600" }, 0x2F}, { {0x30, "ARC 700" }, 0x33}, { {0x34, "ARC 700 R4.10"}, 0x34}, { {0x35, "ARC 700 R4.11"}, 0x35}, - { {0x50, "ARC HS38" }, 0x51}, +#else + { {0x50, "ARC HS38 R2.0"}, 0x51}, + { {0x52, "ARC HS38 R2.1"}, 0x52}, +#endif { {0x00, NULL } } }; -#define IS_AVAIL1(v, str) ((v) ? str : "") -#define IS_USED(cfg) (IS_ENABLED(cfg) ? "" : "(not used) ") -#define IS_AVAIL2(v, str, cfg) IS_AVAIL1(v, str), IS_AVAIL1(v, IS_USED(cfg)) +#define IS_AVAIL1(v, s) ((v) ? s : "") +#define IS_USED_RUN(v) ((v) ? "" : "(not used) ") +#define IS_USED_CFG(cfg) IS_USED_RUN(IS_ENABLED(cfg)) +#define IS_AVAIL2(v, s, cfg) IS_AVAIL1(v, s), IS_AVAIL1(v, IS_USED_CFG(cfg)) static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len) { @@ -226,7 +231,7 @@ static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len) n += scnprintf(buf + n, len - n, "mpy[opt %d] ", opt); } n += scnprintf(buf + n, len - n, "%s", - IS_USED(CONFIG_ARC_HAS_HW_MPY)); + IS_USED_CFG(CONFIG_ARC_HAS_HW_MPY)); } n += scnprintf(buf + n, len - n, "%s%s%s%s%s%s%s%s\n", diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c index 807f7d61d7a7..a6f91e88ce36 100644 --- a/arch/arc/kernel/troubleshoot.c +++ b/arch/arc/kernel/troubleshoot.c @@ -58,7 +58,6 @@ static void show_callee_regs(struct callee_regs *cregs) static void print_task_path_n_nm(struct task_struct *tsk, char *buf) { - struct path path; char *path_nm = NULL; struct mm_struct *mm; struct file *exe_file; diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c index b29d62ed4f7e..1cd6695b6ab5 100644 --- a/arch/arc/mm/cache.c +++ b/arch/arc/mm/cache.c @@ -468,10 +468,18 @@ static void __ic_line_inv_vaddr(unsigned long paddr, unsigned long vaddr, noinline void slc_op(unsigned long paddr, unsigned long sz, const int op) { #ifdef CONFIG_ISA_ARCV2 + /* + * SLC is shared between all cores and concurrent aux operations from + * multiple cores need to be serialized using a spinlock + * A concurrent operation can be silently ignored and/or the old/new + * operation can remain incomplete forever (lockup in SLC_CTRL_BUSY loop + * below) + */ + static DEFINE_SPINLOCK(lock); unsigned long flags; unsigned int ctrl; - local_irq_save(flags); + spin_lock_irqsave(&lock, flags); /* * The Region Flush operation is specified by CTRL.RGN_OP[11..9] @@ -504,7 +512,7 @@ noinline void slc_op(unsigned long paddr, unsigned long sz, const int op) while (read_aux_reg(ARC_REG_SLC_CTRL) & SLC_CTRL_BUSY); - local_irq_restore(flags); + spin_unlock_irqrestore(&lock, flags); #endif } diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c index 74a637a1cfc4..57706a9c6948 100644 --- a/arch/arc/mm/dma.c +++ b/arch/arc/mm/dma.c @@ -60,8 +60,8 @@ void *dma_alloc_coherent(struct device *dev, size_t size, /* This is kernel Virtual address (0x7000_0000 based) */ kvaddr = ioremap_nocache((unsigned long)paddr, size); - if (kvaddr != NULL) - memset(kvaddr, 0, size); + if (kvaddr == NULL) + return NULL; /* This is bus address, platform dependent */ *dma_handle = (dma_addr_t)paddr; diff --git a/arch/s390/include/asm/ctl_reg.h b/arch/s390/include/asm/ctl_reg.h index cfad7fca01d6..d7697ab802f6 100644 --- a/arch/s390/include/asm/ctl_reg.h +++ b/arch/s390/include/asm/ctl_reg.h @@ -57,7 +57,10 @@ union ctlreg0 { unsigned long lap : 1; /* Low-address-protection control */ unsigned long : 4; unsigned long edat : 1; /* Enhanced-DAT-enablement control */ - unsigned long : 23; + unsigned long : 4; + unsigned long afp : 1; /* AFP-register control */ + unsigned long vx : 1; /* Vector enablement control */ + unsigned long : 17; }; }; diff --git a/arch/s390/include/asm/perf_event.h b/arch/s390/include/asm/perf_event.h index 4cb19fe76dd9..f897ec73dc8c 100644 --- a/arch/s390/include/asm/perf_event.h +++ b/arch/s390/include/asm/perf_event.h @@ -87,7 +87,15 @@ struct sf_raw_sample { } __packed; /* Perf hardware reserve and release functions */ +#ifdef CONFIG_PERF_EVENTS int perf_reserve_sampling(void); void perf_release_sampling(void); +#else /* CONFIG_PERF_EVENTS */ +static inline int perf_reserve_sampling(void) +{ + return 0; +} +static inline void perf_release_sampling(void) {} +#endif /* CONFIG_PERF_EVENTS */ #endif /* _ASM_S390_PERF_EVENT_H */ diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c index 505c17c0ae1a..56b550893593 100644 --- a/arch/s390/kernel/nmi.c +++ b/arch/s390/kernel/nmi.c @@ -21,6 +21,7 @@ #include <asm/nmi.h> #include <asm/crw.h> #include <asm/switch_to.h> +#include <asm/ctl_reg.h> struct mcck_struct { int kill_task; @@ -129,26 +130,30 @@ static int notrace s390_revalidate_registers(struct mci *mci) } else asm volatile("lfpc 0(%0)" : : "a" (fpt_creg_save_area)); - asm volatile( - " ld 0,0(%0)\n" - " ld 1,8(%0)\n" - " ld 2,16(%0)\n" - " ld 3,24(%0)\n" - " ld 4,32(%0)\n" - " ld 5,40(%0)\n" - " ld 6,48(%0)\n" - " ld 7,56(%0)\n" - " ld 8,64(%0)\n" - " ld 9,72(%0)\n" - " ld 10,80(%0)\n" - " ld 11,88(%0)\n" - " ld 12,96(%0)\n" - " ld 13,104(%0)\n" - " ld 14,112(%0)\n" - " ld 15,120(%0)\n" - : : "a" (fpt_save_area)); - /* Revalidate vector registers */ - if (MACHINE_HAS_VX && current->thread.vxrs) { + if (!MACHINE_HAS_VX) { + /* Revalidate floating point registers */ + asm volatile( + " ld 0,0(%0)\n" + " ld 1,8(%0)\n" + " ld 2,16(%0)\n" + " ld 3,24(%0)\n" + " ld 4,32(%0)\n" + " ld 5,40(%0)\n" + " ld 6,48(%0)\n" + " ld 7,56(%0)\n" + " ld 8,64(%0)\n" + " ld 9,72(%0)\n" + " ld 10,80(%0)\n" + " ld 11,88(%0)\n" + " ld 12,96(%0)\n" + " ld 13,104(%0)\n" + " ld 14,112(%0)\n" + " ld 15,120(%0)\n" + : : "a" (fpt_save_area)); + } else { + /* Revalidate vector registers */ + union ctlreg0 cr0; + if (!mci->vr) { /* * Vector registers can't be restored and therefore @@ -156,8 +161,12 @@ static int notrace s390_revalidate_registers(struct mci *mci) */ kill_task = 1; } + cr0.val = S390_lowcore.cregs_save_area[0]; + cr0.afp = cr0.vx = 1; + __ctl_load(cr0.val, 0, 0); restore_vx_regs((__vector128 *) - S390_lowcore.vector_save_area_addr); + &S390_lowcore.vector_save_area); + __ctl_load(S390_lowcore.cregs_save_area[0], 0, 0); } /* Revalidate access registers */ asm volatile( diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index dc5edc29b73a..8f587d871b9f 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -163,7 +163,7 @@ int copy_thread(unsigned long clone_flags, unsigned long new_stackp, asmlinkage void execve_tail(void) { current->thread.fp_regs.fpc = 0; - asm volatile("sfpc %0,%0" : : "d" (0)); + asm volatile("sfpc %0" : : "d" (0)); } /* diff --git a/arch/s390/kernel/sclp.S b/arch/s390/kernel/sclp.S index 43c3169ea49c..ada0c07fe1a8 100644 --- a/arch/s390/kernel/sclp.S +++ b/arch/s390/kernel/sclp.S @@ -270,6 +270,8 @@ ENTRY(_sclp_print_early) jno .Lesa2 ahi %r15,-80 stmh %r6,%r15,96(%r15) # store upper register halves + basr %r13,0 + lmh %r0,%r15,.Lzeroes-.(%r13) # clear upper register halves .Lesa2: lr %r10,%r2 # save string pointer lhi %r2,0 @@ -291,6 +293,8 @@ ENTRY(_sclp_print_early) .Lesa3: lm %r6,%r15,120(%r15) # restore registers br %r14 +.Lzeroes: + .fill 64,4,0 .LwritedataS4: .long 0x00760005 # SCLP command for write data diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c index bc927a09a172..9cfa2ffaa9d6 100644 --- a/arch/s390/oprofile/init.c +++ b/arch/s390/oprofile/init.c @@ -16,6 +16,7 @@ #include <linux/fs.h> #include <linux/module.h> #include <asm/processor.h> +#include <asm/perf_event.h> #include "../../../drivers/oprofile/oprof.h" diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 2a7f5d782c33..49ec9038ec14 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -604,6 +604,8 @@ struct kvm_arch { bool iommu_noncoherent; #define __KVM_HAVE_ARCH_NONCOHERENT_DMA atomic_t noncoherent_dma_count; +#define __KVM_HAVE_ARCH_ASSIGNED_DEVICE + atomic_t assigned_device_count; struct kvm_pic *vpic; struct kvm_ioapic *vioapic; struct kvm_pit *vpit; diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h index 8fba544e9cc4..f36d56bd7632 100644 --- a/arch/x86/include/uapi/asm/hyperv.h +++ b/arch/x86/include/uapi/asm/hyperv.h @@ -108,6 +108,8 @@ #define HV_X64_HYPERCALL_PARAMS_XMM_AVAILABLE (1 << 4) /* Support for a virtual guest idle state is available */ #define HV_X64_GUEST_IDLE_STATE_AVAILABLE (1 << 5) +/* Guest crash data handler available */ +#define HV_X64_GUEST_CRASH_MSR_AVAILABLE (1 << 10) /* * Implementation recommendations. Indicates which behaviors the hypervisor diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 64dd46793099..2fbea2544f24 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -98,6 +98,8 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu) best->ebx = xstate_required_size(vcpu->arch.xcr0, true); vcpu->arch.eager_fpu = use_eager_fpu() || guest_cpuid_has_mpx(vcpu); + if (vcpu->arch.eager_fpu) + kvm_x86_ops->fpu_activate(vcpu); /* * The existing code assumes virtual address is 48-bit in the canonical diff --git a/arch/x86/kvm/iommu.c b/arch/x86/kvm/iommu.c index 7dbced309ddb..5c520ebf6343 100644 --- a/arch/x86/kvm/iommu.c +++ b/arch/x86/kvm/iommu.c @@ -200,6 +200,7 @@ int kvm_assign_device(struct kvm *kvm, struct pci_dev *pdev) goto out_unmap; } + kvm_arch_start_assignment(kvm); pci_set_dev_assigned(pdev); dev_info(&pdev->dev, "kvm assign device\n"); @@ -224,6 +225,7 @@ int kvm_deassign_device(struct kvm *kvm, struct pci_dev *pdev) iommu_detach_device(domain, &pdev->dev); pci_clear_dev_assigned(pdev); + kvm_arch_end_assignment(kvm); dev_info(&pdev->dev, "kvm deassign device\n"); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index f807496b62c2..44171462bd2a 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -2479,6 +2479,14 @@ static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn, return 0; } +static bool kvm_is_mmio_pfn(pfn_t pfn) +{ + if (pfn_valid(pfn)) + return !is_zero_pfn(pfn) && PageReserved(pfn_to_page(pfn)); + + return true; +} + static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, int level, gfn_t gfn, pfn_t pfn, bool speculative, @@ -2506,7 +2514,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, spte |= PT_PAGE_SIZE_MASK; if (tdp_enabled) spte |= kvm_x86_ops->get_mt_mask(vcpu, gfn, - kvm_is_reserved_pfn(pfn)); + kvm_is_mmio_pfn(pfn)); if (host_writable) spte |= SPTE_HOST_WRITEABLE; diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 602b974a60a6..bbc678a66b18 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -865,6 +865,64 @@ static void svm_disable_lbrv(struct vcpu_svm *svm) set_msr_interception(msrpm, MSR_IA32_LASTINTTOIP, 0, 0); } +#define MTRR_TYPE_UC_MINUS 7 +#define MTRR2PROTVAL_INVALID 0xff + +static u8 mtrr2protval[8]; + +static u8 fallback_mtrr_type(int mtrr) +{ + /* + * WT and WP aren't always available in the host PAT. Treat + * them as UC and UC- respectively. Everything else should be + * there. + */ + switch (mtrr) + { + case MTRR_TYPE_WRTHROUGH: + return MTRR_TYPE_UNCACHABLE; + case MTRR_TYPE_WRPROT: + return MTRR_TYPE_UC_MINUS; + default: + BUG(); + } +} + +static void build_mtrr2protval(void) +{ + int i; + u64 pat; + + for (i = 0; i < 8; i++) + mtrr2protval[i] = MTRR2PROTVAL_INVALID; + + /* Ignore the invalid MTRR types. */ + mtrr2protval[2] = 0; + mtrr2protval[3] = 0; + + /* + * Use host PAT value to figure out the mapping from guest MTRR + * values to nested page table PAT/PCD/PWT values. We do not + * want to change the host PAT value every time we enter the + * guest. + */ + rdmsrl(MSR_IA32_CR_PAT, pat); + for (i = 0; i < 8; i++) { + u8 mtrr = pat >> (8 * i); + + if (mtrr2protval[mtrr] == MTRR2PROTVAL_INVALID) + mtrr2protval[mtrr] = __cm_idx2pte(i); + } + + for (i = 0; i < 8; i++) { + if (mtrr2protval[i] == MTRR2PROTVAL_INVALID) { + u8 fallback = fallback_mtrr_type(i); + mtrr2protval[i] = mtrr2protval[fallback]; + BUG_ON(mtrr2protval[i] == MTRR2PROTVAL_INVALID); + } + } +} + static __init int svm_hardware_setup(void) { int cpu; @@ -931,6 +989,7 @@ static __init int svm_hardware_setup(void) } else kvm_disable_tdp(); + build_mtrr2protval(); return 0; err: @@ -1085,6 +1144,39 @@ static u64 svm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) return target_tsc - tsc; } +static void svm_set_guest_pat(struct vcpu_svm *svm, u64 *g_pat) +{ + struct kvm_vcpu *vcpu = &svm->vcpu; + + /* Unlike Intel, AMD takes the guest's CR0.CD into account. + * + * AMD does not have IPAT. To emulate it for the case of guests + * with no assigned devices, just set everything to WB. If guests + * have assigned devices, however, we cannot force WB for RAM + * pages only, so use the guest PAT directly. + */ + if (!kvm_arch_has_assigned_device(vcpu->kvm)) + *g_pat = 0x0606060606060606; + else + *g_pat = vcpu->arch.pat; +} + +static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) +{ + u8 mtrr; + + /* + * 1. MMIO: trust guest MTRR, so same as item 3. + * 2. No passthrough: always map as WB, and force guest PAT to WB as well + * 3. Passthrough: can't guarantee the result, try to trust guest. + */ + if (!is_mmio && !kvm_arch_has_assigned_device(vcpu->kvm)) + return 0; + + mtrr = kvm_mtrr_get_guest_memory_type(vcpu, gfn); + return mtrr2protval[mtrr]; +} + static void init_vmcb(struct vcpu_svm *svm, bool init_event) { struct vmcb_control_area *control = &svm->vmcb->control; @@ -1180,6 +1272,7 @@ static void init_vmcb(struct vcpu_svm *svm, bool init_event) clr_cr_intercept(svm, INTERCEPT_CR3_READ); clr_cr_intercept(svm, INTERCEPT_CR3_WRITE); save->g_pat = svm->vcpu.arch.pat; + svm_set_guest_pat(svm, &save->g_pat); save->cr3 = 0; save->cr4 = 0; } @@ -3254,6 +3347,16 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) case MSR_VM_IGNNE: vcpu_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data); break; + case MSR_IA32_CR_PAT: + if (npt_enabled) { + if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data)) + return 1; + vcpu->arch.pat = data; + svm_set_guest_pat(svm, &svm->vmcb->save.g_pat); + mark_dirty(svm->vmcb, VMCB_NPT); + break; + } + /* fall through */ default: return kvm_set_msr_common(vcpu, msr); } @@ -4088,11 +4191,6 @@ static bool svm_has_high_real_mode_segbase(void) return true; } -static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) -{ - return 0; -} - static void svm_cpuid_update(struct kvm_vcpu *vcpu) { } diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index e856dd566f4c..5b4e9384717a 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -8632,22 +8632,17 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) u64 ipat = 0; /* For VT-d and EPT combination - * 1. MMIO: always map as UC + * 1. MMIO: guest may want to apply WC, trust it. * 2. EPT with VT-d: * a. VT-d without snooping control feature: can't guarantee the - * result, try to trust guest. + * result, try to trust guest. So the same as item 1. * b. VT-d with snooping control feature: snooping control feature of * VT-d engine can guarantee the cache correctness. Just set it * to WB to keep consistent with host. So the same as item 3. * 3. EPT without VT-d: always map as WB and set IPAT=1 to keep * consistent with host MTRR */ - if (is_mmio) { - cache = MTRR_TYPE_UNCACHABLE; - goto exit; - } - - if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) { + if (!is_mmio && !kvm_arch_has_noncoherent_dma(vcpu->kvm)) { ipat = VMX_EPT_IPAT_BIT; cache = MTRR_TYPE_WRBACK; goto exit; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index bbaf44e8f0d3..5ef2560075bf 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3157,8 +3157,7 @@ static void load_xsave(struct kvm_vcpu *vcpu, u8 *src) cpuid_count(XSTATE_CPUID, index, &size, &offset, &ecx, &edx); memcpy(dest, src + offset, size); - } else - WARN_ON_ONCE(1); + } valid -= feature; } @@ -7315,11 +7314,6 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, vcpu = kvm_x86_ops->vcpu_create(kvm, id); - /* - * Activate fpu unconditionally in case the guest needs eager FPU. It will be - * deactivated soon if it doesn't. - */ - kvm_x86_ops->fpu_activate(vcpu); return vcpu; } @@ -8218,6 +8212,24 @@ bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu) kvm_x86_ops->interrupt_allowed(vcpu); } +void kvm_arch_start_assignment(struct kvm *kvm) +{ + atomic_inc(&kvm->arch.assigned_device_count); +} +EXPORT_SYMBOL_GPL(kvm_arch_start_assignment); + +void kvm_arch_end_assignment(struct kvm *kvm) +{ + atomic_dec(&kvm->arch.assigned_device_count); +} +EXPORT_SYMBOL_GPL(kvm_arch_end_assignment); + +bool kvm_arch_has_assigned_device(struct kvm *kvm) +{ + return atomic_read(&kvm->arch.assigned_device_count); +} +EXPORT_SYMBOL_GPL(kvm_arch_has_assigned_device); + void kvm_arch_register_noncoherent_dma(struct kvm *kvm) { atomic_inc(&kvm->arch.noncoherent_dma_count); diff --git a/drivers/infiniband/core/agent.c b/drivers/infiniband/core/agent.c index c7dcfe4ca5f1..0429040304fd 100644 --- a/drivers/infiniband/core/agent.c +++ b/drivers/infiniband/core/agent.c @@ -88,7 +88,7 @@ void agent_send_response(const struct ib_mad_hdr *mad_hdr, const struct ib_grh * struct ib_ah *ah; struct ib_mad_send_wr_private *mad_send_wr; - if (device->node_type == RDMA_NODE_IB_SWITCH) + if (rdma_cap_ib_switch(device)) port_priv = ib_get_agent_port(device, 0); else port_priv = ib_get_agent_port(device, port_num); @@ -122,7 +122,7 @@ void agent_send_response(const struct ib_mad_hdr *mad_hdr, const struct ib_grh * memcpy(send_buf->mad, mad_hdr, resp_mad_len); send_buf->ah = ah; - if (device->node_type == RDMA_NODE_IB_SWITCH) { + if (rdma_cap_ib_switch(device)) { mad_send_wr = container_of(send_buf, struct ib_mad_send_wr_private, send_buf); diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index dbddddd6fb5d..3a972ebf3c0d 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -169,6 +169,7 @@ struct cm_device { struct ib_device *ib_device; struct device *device; u8 ack_delay; + int going_down; struct cm_port *port[0]; }; @@ -805,6 +806,11 @@ static void cm_enter_timewait(struct cm_id_private *cm_id_priv) { int wait_time; unsigned long flags; + struct cm_device *cm_dev; + + cm_dev = ib_get_client_data(cm_id_priv->id.device, &cm_client); + if (!cm_dev) + return; spin_lock_irqsave(&cm.lock, flags); cm_cleanup_timewait(cm_id_priv->timewait_info); @@ -818,8 +824,14 @@ static void cm_enter_timewait(struct cm_id_private *cm_id_priv) */ cm_id_priv->id.state = IB_CM_TIMEWAIT; wait_time = cm_convert_to_ms(cm_id_priv->av.timeout); - queue_delayed_work(cm.wq, &cm_id_priv->timewait_info->work.work, - msecs_to_jiffies(wait_time)); + + /* Check if the device started its remove_one */ + spin_lock_irq(&cm.lock); + if (!cm_dev->going_down) + queue_delayed_work(cm.wq, &cm_id_priv->timewait_info->work.work, + msecs_to_jiffies(wait_time)); + spin_unlock_irq(&cm.lock); + cm_id_priv->timewait_info = NULL; } @@ -3305,6 +3317,11 @@ static int cm_establish(struct ib_cm_id *cm_id) struct cm_work *work; unsigned long flags; int ret = 0; + struct cm_device *cm_dev; + + cm_dev = ib_get_client_data(cm_id->device, &cm_client); + if (!cm_dev) + return -ENODEV; work = kmalloc(sizeof *work, GFP_ATOMIC); if (!work) @@ -3343,7 +3360,17 @@ static int cm_establish(struct ib_cm_id *cm_id) work->remote_id = cm_id->remote_id; work->mad_recv_wc = NULL; work->cm_event.event = IB_CM_USER_ESTABLISHED; - queue_delayed_work(cm.wq, &work->work, 0); + + /* Check if the device started its remove_one */ + spin_lock_irq(&cm.lock); + if (!cm_dev->going_down) { + queue_delayed_work(cm.wq, &work->work, 0); + } else { + kfree(work); + ret = -ENODEV; + } + spin_unlock_irq(&cm.lock); + out: return ret; } @@ -3394,6 +3421,7 @@ static void cm_recv_handler(struct ib_mad_agent *mad_agent, enum ib_cm_event_type event; u16 attr_id; int paths = 0; + int going_down = 0; switch (mad_recv_wc->recv_buf.mad->mad_hdr.attr_id) { case CM_REQ_ATTR_ID: @@ -3452,7 +3480,19 @@ static void cm_recv_handler(struct ib_mad_agent *mad_agent, work->cm_event.event = event; work->mad_recv_wc = mad_recv_wc; work->port = port; - queue_delayed_work(cm.wq, &work->work, 0); + + /* Check if the device started its remove_one */ + spin_lock_irq(&cm.lock); + if (!port->cm_dev->going_down) + queue_delayed_work(cm.wq, &work->work, 0); + else + going_down = 1; + spin_unlock_irq(&cm.lock); + + if (going_down) { + kfree(work); + ib_free_recv_mad(mad_recv_wc); + } } static int cm_init_qp_init_attr(struct cm_id_private *cm_id_priv, @@ -3771,7 +3811,7 @@ static void cm_add_one(struct ib_device *ib_device) cm_dev->ib_device = ib_device; cm_get_ack_delay(cm_dev); - + cm_dev->going_down = 0; cm_dev->device = device_create(&cm_class, &ib_device->dev, MKDEV(0, 0), NULL, "%s", ib_device->name); @@ -3864,14 +3904,23 @@ static void cm_remove_one(struct ib_device *ib_device) list_del(&cm_dev->list); write_unlock_irqrestore(&cm.device_lock, flags); + spin_lock_irq(&cm.lock); + cm_dev->going_down = 1; + spin_unlock_irq(&cm.lock); + for (i = 1; i <= ib_device->phys_port_cnt; i++) { if (!rdma_cap_ib_cm(ib_device, i)) continue; port = cm_dev->port[i-1]; ib_modify_port(ib_device, port->port_num, 0, &port_modify); - ib_unregister_mad_agent(port->mad_agent); + /* + * We flush the queue here after the going_down set, this + * verify that no new works will be queued in the recv handler, + * after that we can call the unregister_mad_agent + */ flush_workqueue(cm.wq); + ib_unregister_mad_agent(port->mad_agent); cm_remove_port_fs(port); } device_unregister(cm_dev->device); diff --git a/drivers/infiniband/core/iwpm_msg.c b/drivers/infiniband/core/iwpm_msg.c index e6ffa2e66c1a..22a3abee2a54 100644 --- a/drivers/infiniband/core/iwpm_msg.c +++ b/drivers/infiniband/core/iwpm_msg.c @@ -67,7 +67,8 @@ int iwpm_register_pid(struct iwpm_dev_data *pm_msg, u8 nl_client) err_str = "Invalid port mapper client"; goto pid_query_error; } - if (iwpm_registered_client(nl_client)) + if (iwpm_check_registration(nl_client, IWPM_REG_VALID) || + iwpm_user_pid == IWPM_PID_UNAVAILABLE) return 0; skb = iwpm_create_nlmsg(RDMA_NL_IWPM_REG_PID, &nlh, nl_client); if (!skb) { @@ -106,7 +107,6 @@ int iwpm_register_pid(struct iwpm_dev_data *pm_msg, u8 nl_client) ret = ibnl_multicast(skb, nlh, RDMA_NL_GROUP_IWPM, GFP_KERNEL); if (ret) { skb = NULL; /* skb is freed in the netlink send-op handling */ - iwpm_set_registered(nl_client, 1); iwpm_user_pid = IWPM_PID_UNAVAILABLE; err_str = "Unable to send a nlmsg"; goto pid_query_error; @@ -144,12 +144,12 @@ int iwpm_add_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client) err_str = "Invalid port mapper client"; goto add_mapping_error; } - if (!iwpm_registered_client(nl_client)) { + if (!iwpm_valid_pid()) + return 0; + if (!iwpm_check_registration(nl_client, IWPM_REG_VALID)) { err_str = "Unregistered port mapper client"; goto add_mapping_error; } - if (!iwpm_valid_pid()) - return 0; skb = iwpm_create_nlmsg(RDMA_NL_IWPM_ADD_MAPPING, &nlh, nl_client); if (!skb) { err_str = "Unable to create a nlmsg"; @@ -214,12 +214,12 @@ int iwpm_add_and_query_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client) err_str = "Invalid port mapper client"; goto query_mapping_error; } - if (!iwpm_registered_client(nl_client)) { + if (!iwpm_valid_pid()) + return 0; + if (!iwpm_check_registration(nl_client, IWPM_REG_VALID)) { err_str = "Unregistered port mapper client"; goto query_mapping_error; } - if (!iwpm_valid_pid()) - return 0; ret = -ENOMEM; skb = iwpm_create_nlmsg(RDMA_NL_IWPM_QUERY_MAPPING, &nlh, nl_client); if (!skb) { @@ -288,12 +288,12 @@ int iwpm_remove_mapping(struct sockaddr_storage *local_addr, u8 nl_client) err_str = "Invalid port mapper client"; goto remove_mapping_error; } - if (!iwpm_registered_client(nl_client)) { + if (!iwpm_valid_pid()) + return 0; + if (iwpm_check_registration(nl_client, IWPM_REG_UNDEF)) { err_str = "Unregistered port mapper client"; goto remove_mapping_error; } - if (!iwpm_valid_pid()) - return 0; skb = iwpm_create_nlmsg(RDMA_NL_IWPM_REMOVE_MAPPING, &nlh, nl_client); if (!skb) { ret = -ENOMEM; @@ -388,7 +388,7 @@ int iwpm_register_pid_cb(struct sk_buff *skb, struct netlink_callback *cb) pr_debug("%s: iWarp Port Mapper (pid = %d) is available!\n", __func__, iwpm_user_pid); if (iwpm_valid_client(nl_client)) - iwpm_set_registered(nl_client, 1); + iwpm_set_registration(nl_client, IWPM_REG_VALID); register_pid_response_exit: nlmsg_request->request_done = 1; /* always for found nlmsg_request */ @@ -644,7 +644,6 @@ int iwpm_mapping_info_cb(struct sk_buff *skb, struct netlink_callback *cb) { struct nlattr *nltb[IWPM_NLA_MAPINFO_REQ_MAX]; const char *msg_type = "Mapping Info response"; - int iwpm_pid; u8 nl_client; char *iwpm_name; u16 iwpm_version; @@ -669,14 +668,14 @@ int iwpm_mapping_info_cb(struct sk_buff *skb, struct netlink_callback *cb) __func__, nl_client); return ret; } - iwpm_set_registered(nl_client, 0); + iwpm_set_registration(nl_client, IWPM_REG_INCOMPL); atomic_set(&echo_nlmsg_seq, cb->nlh->nlmsg_seq); + iwpm_user_pid = cb->nlh->nlmsg_pid; if (!iwpm_mapinfo_available()) return 0; - iwpm_pid = cb->nlh->nlmsg_pid; pr_debug("%s: iWarp Port Mapper (pid = %d) is available!\n", - __func__, iwpm_pid); - ret = iwpm_send_mapinfo(nl_client, iwpm_pid); + __func__, iwpm_user_pid); + ret = iwpm_send_mapinfo(nl_client, iwpm_user_pid); return ret; } EXPORT_SYMBOL(iwpm_mapping_info_cb); diff --git a/drivers/infiniband/core/iwpm_util.c b/drivers/infiniband/core/iwpm_util.c index a626795bf9c7..5fb089e91353 100644 --- a/drivers/infiniband/core/iwpm_util.c +++ b/drivers/infiniband/core/iwpm_util.c @@ -78,6 +78,7 @@ init_exit: mutex_unlock(&iwpm_admin_lock); if (!ret) { iwpm_set_valid(nl_client, 1); + iwpm_set_registration(nl_client, IWPM_REG_UNDEF); pr_debug("%s: Mapinfo and reminfo tables are created\n", __func__); } @@ -106,6 +107,7 @@ int iwpm_exit(u8 nl_client) } mutex_unlock(&iwpm_admin_lock); iwpm_set_valid(nl_client, 0); + iwpm_set_registration(nl_client, IWPM_REG_UNDEF); return 0; } EXPORT_SYMBOL(iwpm_exit); @@ -397,17 +399,23 @@ void iwpm_set_valid(u8 nl_client, int valid) } /* valid client */ -int iwpm_registered_client(u8 nl_client) +u32 iwpm_get_registration(u8 nl_client) { return iwpm_admin.reg_list[nl_client]; } /* valid client */ -void iwpm_set_registered(u8 nl_client, int reg) +void iwpm_set_registration(u8 nl_client, u32 reg) { iwpm_admin.reg_list[nl_client] = reg; } +/* valid client */ +u32 iwpm_check_registration(u8 nl_client, u32 reg) +{ + return (iwpm_get_registration(nl_client) & reg); +} + int iwpm_compare_sockaddr(struct sockaddr_storage *a_sockaddr, struct sockaddr_storage *b_sockaddr) { diff --git a/drivers/infiniband/core/iwpm_util.h b/drivers/infiniband/core/iwpm_util.h index ee2d9ff095be..b7b9e194ce81 100644 --- a/drivers/infiniband/core/iwpm_util.h +++ b/drivers/infiniband/core/iwpm_util.h @@ -58,6 +58,10 @@ #define IWPM_PID_UNDEFINED -1 #define IWPM_PID_UNAVAILABLE -2 +#define IWPM_REG_UNDEF 0x01 +#define IWPM_REG_VALID 0x02 +#define IWPM_REG_INCOMPL 0x04 + struct iwpm_nlmsg_request { struct list_head inprocess_list; __u32 nlmsg_seq; @@ -88,7 +92,7 @@ struct iwpm_admin_data { atomic_t refcount; atomic_t nlmsg_seq; int client_list[RDMA_NL_NUM_CLIENTS]; - int reg_list[RDMA_NL_NUM_CLIENTS]; + u32 reg_list[RDMA_NL_NUM_CLIENTS]; }; /** @@ -159,19 +163,31 @@ int iwpm_valid_client(u8 nl_client); void iwpm_set_valid(u8 nl_client, int valid); /** - * iwpm_registered_client - Check if the port mapper client is registered + * iwpm_check_registration - Check if the client registration + * matches the given one * @nl_client: The index of the netlink client + * @reg: The given registration type to compare with * * Call iwpm_register_pid() to register a client + * Returns true if the client registration matches reg, + * otherwise returns false + */ +u32 iwpm_check_registration(u8 nl_client, u32 reg); + +/** + * iwpm_set_registration - Set the client registration + * @nl_client: The index of the netlink client + * @reg: Registration type to set */ -int iwpm_registered_client(u8 nl_client); +void iwpm_set_registration(u8 nl_client, u32 reg); /** - * iwpm_set_registered - Set the port mapper client to registered or not + * iwpm_get_registration * @nl_client: The index of the netlink client - * @reg: 1 if registered or 0 if not + * + * Returns the client registration type */ -void iwpm_set_registered(u8 nl_client, int reg); +u32 iwpm_get_registration(u8 nl_client); /** * iwpm_send_mapinfo - Send local and mapped IPv4/IPv6 address info of diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c index a4b1466c1bf6..786fc51bf04b 100644 --- a/drivers/infiniband/core/mad.c +++ b/drivers/infiniband/core/mad.c @@ -769,7 +769,7 @@ static int handle_outgoing_dr_smp(struct ib_mad_agent_private *mad_agent_priv, bool opa = rdma_cap_opa_mad(mad_agent_priv->qp_info->port_priv->device, mad_agent_priv->qp_info->port_priv->port_num); - if (device->node_type == RDMA_NODE_IB_SWITCH && + if (rdma_cap_ib_switch(device) && smp->mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE) port_num = send_wr->wr.ud.port_num; else @@ -787,14 +787,15 @@ static int handle_outgoing_dr_smp(struct ib_mad_agent_private *mad_agent_priv, if ((opa_get_smp_direction(opa_smp) ? opa_smp->route.dr.dr_dlid : opa_smp->route.dr.dr_slid) == OPA_LID_PERMISSIVE && - opa_smi_handle_dr_smp_send(opa_smp, device->node_type, + opa_smi_handle_dr_smp_send(opa_smp, + rdma_cap_ib_switch(device), port_num) == IB_SMI_DISCARD) { ret = -EINVAL; dev_err(&device->dev, "OPA Invalid directed route\n"); goto out; } opa_drslid = be32_to_cpu(opa_smp->route.dr.dr_slid); - if (opa_drslid != OPA_LID_PERMISSIVE && + if (opa_drslid != be32_to_cpu(OPA_LID_PERMISSIVE) && opa_drslid & 0xffff0000) { ret = -EINVAL; dev_err(&device->dev, "OPA Invalid dr_slid 0x%x\n", @@ -810,7 +811,7 @@ static int handle_outgoing_dr_smp(struct ib_mad_agent_private *mad_agent_priv, } else { if ((ib_get_smp_direction(smp) ? smp->dr_dlid : smp->dr_slid) == IB_LID_PERMISSIVE && - smi_handle_dr_smp_send(smp, device->node_type, port_num) == + smi_handle_dr_smp_send(smp, rdma_cap_ib_switch(device), port_num) == IB_SMI_DISCARD) { ret = -EINVAL; dev_err(&device->dev, "Invalid directed route\n"); @@ -2030,7 +2031,7 @@ static enum smi_action handle_ib_smi(const struct ib_mad_port_private *port_priv struct ib_smp *smp = (struct ib_smp *)recv->mad; if (smi_handle_dr_smp_recv(smp, - port_priv->device->node_type, + rdma_cap_ib_switch(port_priv->device), port_num, port_priv->device->phys_port_cnt) == IB_SMI_DISCARD) @@ -2042,13 +2043,13 @@ static enum smi_action handle_ib_smi(const struct ib_mad_port_private *port_priv if (retsmi == IB_SMI_SEND) { /* don't forward */ if (smi_handle_dr_smp_send(smp, - port_priv->device->node_type, + rdma_cap_ib_switch(port_priv->device), port_num) == IB_SMI_DISCARD) return IB_SMI_DISCARD; if (smi_check_local_smp(smp, port_priv->device) == IB_SMI_DISCARD) return IB_SMI_DISCARD; - } else if (port_priv->device->node_type == RDMA_NODE_IB_SWITCH) { + } else if (rdma_cap_ib_switch(port_priv->device)) { /* forward case for switches */ memcpy(response, recv, mad_priv_size(response)); response->header.recv_wc.wc = &response->header.wc; @@ -2115,7 +2116,7 @@ handle_opa_smi(struct ib_mad_port_private *port_priv, struct opa_smp *smp = (struct opa_smp *)recv->mad; if (opa_smi_handle_dr_smp_recv(smp, - port_priv->device->node_type, + rdma_cap_ib_switch(port_priv->device), port_num, port_priv->device->phys_port_cnt) == IB_SMI_DISCARD) @@ -2127,7 +2128,7 @@ handle_opa_smi(struct ib_mad_port_private *port_priv, if (retsmi == IB_SMI_SEND) { /* don't forward */ if (opa_smi_handle_dr_smp_send(smp, - port_priv->device->node_type, + rdma_cap_ib_switch(port_priv->device), port_num) == IB_SMI_DISCARD) return IB_SMI_DISCARD; @@ -2135,7 +2136,7 @@ handle_opa_smi(struct ib_mad_port_private *port_priv, IB_SMI_DISCARD) return IB_SMI_DISCARD; - } else if (port_priv->device->node_type == RDMA_NODE_IB_SWITCH) { + } else if (rdma_cap_ib_switch(port_priv->device)) { /* forward case for switches */ memcpy(response, recv, mad_priv_size(response)); response->header.recv_wc.wc = &response->header.wc; @@ -2235,7 +2236,7 @@ static void ib_mad_recv_done_handler(struct ib_mad_port_private *port_priv, goto out; } - if (port_priv->device->node_type == RDMA_NODE_IB_SWITCH) + if (rdma_cap_ib_switch(port_priv->device)) port_num = wc->port_num; else port_num = port_priv->port_num; @@ -3297,17 +3298,11 @@ static int ib_mad_port_close(struct ib_device *device, int port_num) static void ib_mad_init_device(struct ib_device *device) { - int start, end, i; + int start, i; - if (device->node_type == RDMA_NODE_IB_SWITCH) { - start = 0; - end = 0; - } else { - start = 1; - end = device->phys_port_cnt; - } + start = rdma_start_port(device); - for (i = start; i <= end; i++) { + for (i = start; i <= rdma_end_port(device); i++) { if (!rdma_cap_ib_mad(device, i)) continue; @@ -3342,17 +3337,9 @@ error: static void ib_mad_remove_device(struct ib_device *device) { - int start, end, i; - - if (device->node_type == RDMA_NODE_IB_SWITCH) { - start = 0; - end = 0; - } else { - start = 1; - end = device->phys_port_cnt; - } + int i; - for (i = start; i <= end; i++) { + for (i = rdma_start_port(device); i <= rdma_end_port(device); i++) { if (!rdma_cap_ib_mad(device, i)) continue; diff --git a/drivers/infiniband/core/multicast.c b/drivers/infiniband/core/multicast.c index 1244f02a5c6d..2cb865c7ce7a 100644 --- a/drivers/infiniband/core/multicast.c +++ b/drivers/infiniband/core/multicast.c @@ -812,12 +812,8 @@ static void mcast_add_one(struct ib_device *device) if (!dev) return; - if (device->node_type == RDMA_NODE_IB_SWITCH) - dev->start_port = dev->end_port = 0; - else { - dev->start_port = 1; - dev->end_port = device->phys_port_cnt; - } + dev->start_port = rdma_start_port(device); + dev->end_port = rdma_end_port(device); for (i = 0; i <= dev->end_port - dev->start_port; i++) { if (!rdma_cap_ib_mcast(device, dev->start_port + i)) diff --git a/drivers/infiniband/core/opa_smi.h b/drivers/infiniband/core/opa_smi.h index 62d91bfa4cb7..3bfab3505a29 100644 --- a/drivers/infiniband/core/opa_smi.h +++ b/drivers/infiniband/core/opa_smi.h @@ -39,12 +39,12 @@ #include "smi.h" -enum smi_action opa_smi_handle_dr_smp_recv(struct opa_smp *smp, u8 node_type, +enum smi_action opa_smi_handle_dr_smp_recv(struct opa_smp *smp, bool is_switch, int port_num, int phys_port_cnt); int opa_smi_get_fwd_port(struct opa_smp *smp); extern enum smi_forward_action opa_smi_check_forward_dr_smp(struct opa_smp *smp); extern enum smi_action opa_smi_handle_dr_smp_send(struct opa_smp *smp, - u8 node_type, int port_num); + bool is_switch, int port_num); /* * Return IB_SMI_HANDLE if the SMP should be handled by the local SMA/SM diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c index 0fae85062a65..ca919f429666 100644 --- a/drivers/infiniband/core/sa_query.c +++ b/drivers/infiniband/core/sa_query.c @@ -1156,12 +1156,8 @@ static void ib_sa_add_one(struct ib_device *device) int s, e, i; int count = 0; - if (device->node_type == RDMA_NODE_IB_SWITCH) - s = e = 0; - else { - s = 1; - e = device->phys_port_cnt; - } + s = rdma_start_port(device); + e = rdma_end_port(device); sa_dev = kzalloc(sizeof *sa_dev + (e - s + 1) * sizeof (struct ib_sa_port), diff --git a/drivers/infiniband/core/smi.c b/drivers/infiniband/core/smi.c index 368a561d1a5d..f19b23817c2b 100644 --- a/drivers/infiniband/core/smi.c +++ b/drivers/infiniband/core/smi.c @@ -41,7 +41,7 @@ #include "smi.h" #include "opa_smi.h" -static enum smi_action __smi_handle_dr_smp_send(u8 node_type, int port_num, +static enum smi_action __smi_handle_dr_smp_send(bool is_switch, int port_num, u8 *hop_ptr, u8 hop_cnt, const u8 *initial_path, const u8 *return_path, @@ -64,7 +64,7 @@ static enum smi_action __smi_handle_dr_smp_send(u8 node_type, int port_num, /* C14-9:2 */ if (*hop_ptr && *hop_ptr < hop_cnt) { - if (node_type != RDMA_NODE_IB_SWITCH) + if (!is_switch) return IB_SMI_DISCARD; /* return_path set when received */ @@ -77,7 +77,7 @@ static enum smi_action __smi_handle_dr_smp_send(u8 node_type, int port_num, if (*hop_ptr == hop_cnt) { /* return_path set when received */ (*hop_ptr)++; - return (node_type == RDMA_NODE_IB_SWITCH || + return (is_switch || dr_dlid_is_permissive ? IB_SMI_HANDLE : IB_SMI_DISCARD); } @@ -96,7 +96,7 @@ static enum smi_action __smi_handle_dr_smp_send(u8 node_type, int port_num, /* C14-13:2 */ if (2 <= *hop_ptr && *hop_ptr <= hop_cnt) { - if (node_type != RDMA_NODE_IB_SWITCH) + if (!is_switch) return IB_SMI_DISCARD; (*hop_ptr)--; @@ -108,7 +108,7 @@ static enum smi_action __smi_handle_dr_smp_send(u8 node_type, int port_num, if (*hop_ptr == 1) { (*hop_ptr)--; /* C14-13:3 -- SMPs destined for SM shouldn't be here */ - return (node_type == RDMA_NODE_IB_SWITCH || + return (is_switch || dr_slid_is_permissive ? IB_SMI_HANDLE : IB_SMI_DISCARD); } @@ -127,9 +127,9 @@ static enum smi_action __smi_handle_dr_smp_send(u8 node_type, int port_num, * Return IB_SMI_DISCARD if the SMP should be discarded */ enum smi_action smi_handle_dr_smp_send(struct ib_smp *smp, - u8 node_type, int port_num) + bool is_switch, int port_num) { - return __smi_handle_dr_smp_send(node_type, port_num, + return __smi_handle_dr_smp_send(is_switch, port_num, &smp->hop_ptr, smp->hop_cnt, smp->initial_path, smp->return_path, @@ -139,9 +139,9 @@ enum smi_action smi_handle_dr_smp_send(struct ib_smp *smp, } enum smi_action opa_smi_handle_dr_smp_send(struct opa_smp *smp, - u8 node_type, int port_num) + bool is_switch, int port_num) { - return __smi_handle_dr_smp_send(node_type, port_num, + return __smi_handle_dr_smp_send(is_switch, port_num, &smp->hop_ptr, smp->hop_cnt, smp->route.dr.initial_path, smp->route.dr.return_path, @@ -152,7 +152,7 @@ enum smi_action opa_smi_handle_dr_smp_send(struct opa_smp *smp, OPA_LID_PERMISSIVE); } -static enum smi_action __smi_handle_dr_smp_recv(u8 node_type, int port_num, +static enum smi_action __smi_handle_dr_smp_recv(bool is_switch, int port_num, int phys_port_cnt, u8 *hop_ptr, u8 hop_cnt, const u8 *initial_path, @@ -173,7 +173,7 @@ static enum smi_action __smi_handle_dr_smp_recv(u8 node_type, int port_num, /* C14-9:2 -- intermediate hop */ if (*hop_ptr && *hop_ptr < hop_cnt) { - if (node_type != RDMA_NODE_IB_SWITCH) + if (!is_switch) return IB_SMI_DISCARD; return_path[*hop_ptr] = port_num; @@ -188,7 +188,7 @@ static enum smi_action __smi_handle_dr_smp_recv(u8 node_type, int port_num, return_path[*hop_ptr] = port_num; /* hop_ptr updated when sending */ - return (node_type == RDMA_NODE_IB_SWITCH || + return (is_switch || dr_dlid_is_permissive ? IB_SMI_HANDLE : IB_SMI_DISCARD); } @@ -208,7 +208,7 @@ static enum smi_action __smi_handle_dr_smp_recv(u8 node_type, int port_num, /* C14-13:2 */ if (2 <= *hop_ptr && *hop_ptr <= hop_cnt) { - if (node_type != RDMA_NODE_IB_SWITCH) + if (!is_switch) return IB_SMI_DISCARD; /* hop_ptr updated when sending */ @@ -224,8 +224,7 @@ static enum smi_action __smi_handle_dr_smp_recv(u8 node_type, int port_num, return IB_SMI_HANDLE; } /* hop_ptr updated when sending */ - return (node_type == RDMA_NODE_IB_SWITCH ? - IB_SMI_HANDLE : IB_SMI_DISCARD); + return (is_switch ? IB_SMI_HANDLE : IB_SMI_DISCARD); } /* C14-13:4 -- hop_ptr = 0 -> give to SM */ @@ -238,10 +237,10 @@ static enum smi_action __smi_handle_dr_smp_recv(u8 node_type, int port_num, * Adjust information for a received SMP * Return IB_SMI_DISCARD if the SMP should be dropped */ -enum smi_action smi_handle_dr_smp_recv(struct ib_smp *smp, u8 node_type, +enum smi_action smi_handle_dr_smp_recv(struct ib_smp *smp, bool is_switch, int port_num, int phys_port_cnt) { - return __smi_handle_dr_smp_recv(node_type, port_num, phys_port_cnt, + return __smi_handle_dr_smp_recv(is_switch, port_num, phys_port_cnt, &smp->hop_ptr, smp->hop_cnt, smp->initial_path, smp->return_path, @@ -254,10 +253,10 @@ enum smi_action smi_handle_dr_smp_recv(struct ib_smp *smp, u8 node_type, * Adjust information for a received SMP * Return IB_SMI_DISCARD if the SMP should be dropped */ -enum smi_action opa_smi_handle_dr_smp_recv(struct opa_smp *smp, u8 node_type, +enum smi_action opa_smi_handle_dr_smp_recv(struct opa_smp *smp, bool is_switch, int port_num, int phys_port_cnt) { - return __smi_handle_dr_smp_recv(node_type, port_num, phys_port_cnt, + return __smi_handle_dr_smp_recv(is_switch, port_num, phys_port_cnt, &smp->hop_ptr, smp->hop_cnt, smp->route.dr.initial_path, smp->route.dr.return_path, diff --git a/drivers/infiniband/core/smi.h b/drivers/infiniband/core/smi.h index aff96bac49b4..33c91c8a16e9 100644 --- a/drivers/infiniband/core/smi.h +++ b/drivers/infiniband/core/smi.h @@ -51,12 +51,12 @@ enum smi_forward_action { IB_SMI_FORWARD /* SMP should be forwarded (for switches only) */ }; -enum smi_action smi_handle_dr_smp_recv(struct ib_smp *smp, u8 node_type, +enum smi_action smi_handle_dr_smp_recv(struct ib_smp *smp, bool is_switch, int port_num, int phys_port_cnt); int smi_get_fwd_port(struct ib_smp *smp); extern enum smi_forward_action smi_check_forward_dr_smp(struct ib_smp *smp); extern enum smi_action smi_handle_dr_smp_send(struct ib_smp *smp, - u8 node_type, int port_num); + bool is_switch, int port_num); /* * Return IB_SMI_HANDLE if the SMP should be handled by the local SMA/SM diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c index ed6b6c85c334..0b84a9cdfe5b 100644 --- a/drivers/infiniband/core/sysfs.c +++ b/drivers/infiniband/core/sysfs.c @@ -870,7 +870,7 @@ int ib_device_register_sysfs(struct ib_device *device, goto err_put; } - if (device->node_type == RDMA_NODE_IB_SWITCH) { + if (rdma_cap_ib_switch(device)) { ret = add_port(device, 0, port_callback); if (ret) goto err_put; diff --git a/drivers/infiniband/core/ucm.c b/drivers/infiniband/core/ucm.c index 62c24b1452b8..009481073644 100644 --- a/drivers/infiniband/core/ucm.c +++ b/drivers/infiniband/core/ucm.c @@ -1193,6 +1193,7 @@ static int ib_ucm_close(struct inode *inode, struct file *filp) return 0; } +static DECLARE_BITMAP(overflow_map, IB_UCM_MAX_DEVICES); static void ib_ucm_release_dev(struct device *dev) { struct ib_ucm_device *ucm_dev; @@ -1202,7 +1203,7 @@ static void ib_ucm_release_dev(struct device *dev) if (ucm_dev->devnum < IB_UCM_MAX_DEVICES) clear_bit(ucm_dev->devnum, dev_map); else - clear_bit(ucm_dev->devnum - IB_UCM_MAX_DEVICES, dev_map); + clear_bit(ucm_dev->devnum - IB_UCM_MAX_DEVICES, overflow_map); kfree(ucm_dev); } @@ -1226,7 +1227,6 @@ static ssize_t show_ibdev(struct device *dev, struct device_attribute *attr, static DEVICE_ATTR(ibdev, S_IRUGO, show_ibdev, NULL); static dev_t overflow_maj; -static DECLARE_BITMAP(overflow_map, IB_UCM_MAX_DEVICES); static int find_overflow_devnum(void) { int ret; diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index ad45469f7582..29b21213ea75 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -1354,10 +1354,10 @@ static void ucma_lock_files(struct ucma_file *file1, struct ucma_file *file2) /* Acquire mutex's based on pointer comparison to prevent deadlock. */ if (file1 < file2) { mutex_lock(&file1->mut); - mutex_lock(&file2->mut); + mutex_lock_nested(&file2->mut, SINGLE_DEPTH_NESTING); } else { mutex_lock(&file2->mut); - mutex_lock(&file1->mut); + mutex_lock_nested(&file1->mut, SINGLE_DEPTH_NESTING); } } @@ -1616,6 +1616,7 @@ static void __exit ucma_cleanup(void) device_remove_file(ucma_misc.this_device, &dev_attr_abi_version); misc_deregister(&ucma_misc); idr_destroy(&ctx_idr); + idr_destroy(&multicast_idr); } module_init(ucma_init); diff --git a/drivers/infiniband/hw/ehca/ehca_sqp.c b/drivers/infiniband/hw/ehca/ehca_sqp.c index 12b5bc23832b..376b031c2c7f 100644 --- a/drivers/infiniband/hw/ehca/ehca_sqp.c +++ b/drivers/infiniband/hw/ehca/ehca_sqp.c @@ -226,8 +226,9 @@ int ehca_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num, const struct ib_mad *in_mad = (const struct ib_mad *)in; struct ib_mad *out_mad = (struct ib_mad *)out; - BUG_ON(in_mad_size != sizeof(*in_mad) || - *out_mad_size != sizeof(*out_mad)); + if (WARN_ON_ONCE(in_mad_size != sizeof(*in_mad) || + *out_mad_size != sizeof(*out_mad))) + return IB_MAD_RESULT_FAILURE; if (!port_num || port_num > ibdev->phys_port_cnt || !in_wc) return IB_MAD_RESULT_FAILURE; diff --git a/drivers/infiniband/hw/ipath/ipath_mad.c b/drivers/infiniband/hw/ipath/ipath_mad.c index 948188e37f95..ad3a926ab3c5 100644 --- a/drivers/infiniband/hw/ipath/ipath_mad.c +++ b/drivers/infiniband/hw/ipath/ipath_mad.c @@ -1499,8 +1499,9 @@ int ipath_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num, const struct ib_mad *in_mad = (const struct ib_mad *)in; struct ib_mad *out_mad = (struct ib_mad *)out; - BUG_ON(in_mad_size != sizeof(*in_mad) || - *out_mad_size != sizeof(*out_mad)); + if (WARN_ON_ONCE(in_mad_size != sizeof(*in_mad) || + *out_mad_size != sizeof(*out_mad))) + return IB_MAD_RESULT_FAILURE; switch (in_mad->mad_hdr.mgmt_class) { case IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE: diff --git a/drivers/infiniband/hw/ipath/ipath_verbs.c b/drivers/infiniband/hw/ipath/ipath_verbs.c index 48253b839a6f..30ba49c4a98c 100644 --- a/drivers/infiniband/hw/ipath/ipath_verbs.c +++ b/drivers/infiniband/hw/ipath/ipath_verbs.c @@ -2044,9 +2044,9 @@ int ipath_register_ib_device(struct ipath_devdata *dd) spin_lock_init(&idev->qp_table.lock); spin_lock_init(&idev->lk_table.lock); - idev->sm_lid = __constant_be16_to_cpu(IB_LID_PERMISSIVE); + idev->sm_lid = be16_to_cpu(IB_LID_PERMISSIVE); /* Set the prefix to the default value (see ch. 4.1.1) */ - idev->gid_prefix = __constant_cpu_to_be64(0xfe80000000000000ULL); + idev->gid_prefix = cpu_to_be64(0xfe80000000000000ULL); ret = ipath_init_qp_table(idev, ib_ipath_qp_table_size); if (ret) diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c index 85a50df2f203..68b3dfa922bf 100644 --- a/drivers/infiniband/hw/mlx4/mad.c +++ b/drivers/infiniband/hw/mlx4/mad.c @@ -860,21 +860,31 @@ int mlx4_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num, struct mlx4_ib_dev *dev = to_mdev(ibdev); const struct ib_mad *in_mad = (const struct ib_mad *)in; struct ib_mad *out_mad = (struct ib_mad *)out; + enum rdma_link_layer link = rdma_port_get_link_layer(ibdev, port_num); - BUG_ON(in_mad_size != sizeof(*in_mad) || - *out_mad_size != sizeof(*out_mad)); + if (WARN_ON_ONCE(in_mad_size != sizeof(*in_mad) || + *out_mad_size != sizeof(*out_mad))) + return IB_MAD_RESULT_FAILURE; - switch (rdma_port_get_link_layer(ibdev, port_num)) { - case IB_LINK_LAYER_INFINIBAND: - if (!mlx4_is_slave(dev->dev)) - return ib_process_mad(ibdev, mad_flags, port_num, in_wc, - in_grh, in_mad, out_mad); - case IB_LINK_LAYER_ETHERNET: - return iboe_process_mad(ibdev, mad_flags, port_num, in_wc, - in_grh, in_mad, out_mad); - default: - return -EINVAL; + /* iboe_process_mad() which uses the HCA flow-counters to implement IB PMA + * queries, should be called only by VFs and for that specific purpose + */ + if (link == IB_LINK_LAYER_INFINIBAND) { + if (mlx4_is_slave(dev->dev) && + in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_PERF_MGMT && + in_mad->mad_hdr.attr_id == IB_PMA_PORT_COUNTERS) + return iboe_process_mad(ibdev, mad_flags, port_num, in_wc, + in_grh, in_mad, out_mad); + + return ib_process_mad(ibdev, mad_flags, port_num, in_wc, + in_grh, in_mad, out_mad); } + + if (link == IB_LINK_LAYER_ETHERNET) + return iboe_process_mad(ibdev, mad_flags, port_num, in_wc, + in_grh, in_mad, out_mad); + + return -EINVAL; } static void send_handler(struct ib_mad_agent *agent, diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index 067a691ecbed..8be6db816460 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -253,14 +253,15 @@ static int mlx4_ib_query_device(struct ib_device *ibdev, props->hca_core_clock = dev->dev->caps.hca_core_clock * 1000UL; props->timestamp_mask = 0xFFFFFFFFFFFFULL; - err = mlx4_get_internal_clock_params(dev->dev, &clock_params); - if (err) - goto out; + if (!mlx4_is_slave(dev->dev)) + err = mlx4_get_internal_clock_params(dev->dev, &clock_params); if (uhw->outlen >= resp.response_length + sizeof(resp.hca_core_clock_offset)) { - resp.hca_core_clock_offset = clock_params.offset % PAGE_SIZE; resp.response_length += sizeof(resp.hca_core_clock_offset); - resp.comp_mask |= QUERY_DEVICE_RESP_MASK_TIMESTAMP; + if (!err && !mlx4_is_slave(dev->dev)) { + resp.comp_mask |= QUERY_DEVICE_RESP_MASK_TIMESTAMP; + resp.hca_core_clock_offset = clock_params.offset % PAGE_SIZE; + } } if (uhw->outlen) { @@ -2669,31 +2670,33 @@ static void do_slave_init(struct mlx4_ib_dev *ibdev, int slave, int do_init) dm = kcalloc(ports, sizeof(*dm), GFP_ATOMIC); if (!dm) { pr_err("failed to allocate memory for tunneling qp update\n"); - goto out; + return; } for (i = 0; i < ports; i++) { dm[i] = kmalloc(sizeof (struct mlx4_ib_demux_work), GFP_ATOMIC); if (!dm[i]) { pr_err("failed to allocate memory for tunneling qp update work struct\n"); - for (i = 0; i < dev->caps.num_ports; i++) { - if (dm[i]) - kfree(dm[i]); - } + while (--i >= 0) + kfree(dm[i]); goto out; } - } - /* initialize or tear down tunnel QPs for the slave */ - for (i = 0; i < ports; i++) { INIT_WORK(&dm[i]->work, mlx4_ib_tunnels_update_work); dm[i]->port = first_port + i + 1; dm[i]->slave = slave; dm[i]->do_init = do_init; dm[i]->dev = ibdev; - spin_lock_irqsave(&ibdev->sriov.going_down_lock, flags); - if (!ibdev->sriov.is_going_down) + } + /* initialize or tear down tunnel QPs for the slave */ + spin_lock_irqsave(&ibdev->sriov.going_down_lock, flags); + if (!ibdev->sriov.is_going_down) { + for (i = 0; i < ports; i++) queue_work(ibdev->sriov.demux[i].ud_wq, &dm[i]->work); spin_unlock_irqrestore(&ibdev->sriov.going_down_lock, flags); + } else { + spin_unlock_irqrestore(&ibdev->sriov.going_down_lock, flags); + for (i = 0; i < ports; i++) + kfree(dm[i]); } out: kfree(dm); diff --git a/drivers/infiniband/hw/mlx5/mad.c b/drivers/infiniband/hw/mlx5/mad.c index 01fc97db45d6..b84d13a487cc 100644 --- a/drivers/infiniband/hw/mlx5/mad.c +++ b/drivers/infiniband/hw/mlx5/mad.c @@ -68,8 +68,9 @@ int mlx5_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num, const struct ib_mad *in_mad = (const struct ib_mad *)in; struct ib_mad *out_mad = (struct ib_mad *)out; - BUG_ON(in_mad_size != sizeof(*in_mad) || - *out_mad_size != sizeof(*out_mad)); + if (WARN_ON_ONCE(in_mad_size != sizeof(*in_mad) || + *out_mad_size != sizeof(*out_mad))) + return IB_MAD_RESULT_FAILURE; slid = in_wc ? in_wc->slid : be16_to_cpu(IB_LID_PERMISSIVE); diff --git a/drivers/infiniband/hw/mthca/mthca_mad.c b/drivers/infiniband/hw/mthca/mthca_mad.c index 6b2418b74c99..7c3f2fb44ba5 100644 --- a/drivers/infiniband/hw/mthca/mthca_mad.c +++ b/drivers/infiniband/hw/mthca/mthca_mad.c @@ -209,8 +209,9 @@ int mthca_process_mad(struct ib_device *ibdev, const struct ib_mad *in_mad = (const struct ib_mad *)in; struct ib_mad *out_mad = (struct ib_mad *)out; - BUG_ON(in_mad_size != sizeof(*in_mad) || - *out_mad_size != sizeof(*out_mad)); + if (WARN_ON_ONCE(in_mad_size != sizeof(*in_mad) || + *out_mad_size != sizeof(*out_mad))) + return IB_MAD_RESULT_FAILURE; /* Forward locally generated traps to the SM */ if (in_mad->mad_hdr.method == IB_MGMT_METHOD_TRAP && diff --git a/drivers/infiniband/hw/nes/nes_cm.c b/drivers/infiniband/hw/nes/nes_cm.c index 9047af429906..8a3ad170d790 100644 --- a/drivers/infiniband/hw/nes/nes_cm.c +++ b/drivers/infiniband/hw/nes/nes_cm.c @@ -1520,8 +1520,9 @@ static int nes_addr_resolve_neigh(struct nes_vnic *nesvnic, u32 dst_ip, int arpi int rc = arpindex; struct net_device *netdev; struct nes_adapter *nesadapter = nesvnic->nesdev->nesadapter; + __be32 dst_ipaddr = htonl(dst_ip); - rt = ip_route_output(&init_net, htonl(dst_ip), 0, 0, 0); + rt = ip_route_output(&init_net, dst_ipaddr, nesvnic->local_ipaddr, 0, 0); if (IS_ERR(rt)) { printk(KERN_ERR "%s: ip_route_output_key failed for 0x%08X\n", __func__, dst_ip); @@ -1533,7 +1534,7 @@ static int nes_addr_resolve_neigh(struct nes_vnic *nesvnic, u32 dst_ip, int arpi else netdev = nesvnic->netdev; - neigh = neigh_lookup(&arp_tbl, &rt->rt_gateway, netdev); + neigh = dst_neigh_lookup(&rt->dst, &dst_ipaddr); rcu_read_lock(); if (neigh) { diff --git a/drivers/infiniband/hw/nes/nes_hw.c b/drivers/infiniband/hw/nes/nes_hw.c index 02120d340d50..4713dd7ed764 100644 --- a/drivers/infiniband/hw/nes/nes_hw.c +++ b/drivers/infiniband/hw/nes/nes_hw.c @@ -3861,7 +3861,7 @@ void nes_manage_arp_cache(struct net_device *netdev, unsigned char *mac_addr, (((u32)mac_addr[2]) << 24) | (((u32)mac_addr[3]) << 16) | (((u32)mac_addr[4]) << 8) | (u32)mac_addr[5]); cqp_wqe->wqe_words[NES_CQP_ARP_WQE_MAC_HIGH_IDX] = cpu_to_le32( - (((u32)mac_addr[0]) << 16) | (u32)mac_addr[1]); + (((u32)mac_addr[0]) << 8) | (u32)mac_addr[1]); } else { cqp_wqe->wqe_words[NES_CQP_ARP_WQE_MAC_ADDR_LOW_IDX] = 0; cqp_wqe->wqe_words[NES_CQP_ARP_WQE_MAC_HIGH_IDX] = 0; diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_ah.c b/drivers/infiniband/hw/ocrdma/ocrdma_ah.c index 4bafa15708d0..29b27675dd70 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_ah.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_ah.c @@ -215,8 +215,9 @@ int ocrdma_process_mad(struct ib_device *ibdev, const struct ib_mad *in_mad = (const struct ib_mad *)in; struct ib_mad *out_mad = (struct ib_mad *)out; - BUG_ON(in_mad_size != sizeof(*in_mad) || - *out_mad_size != sizeof(*out_mad)); + if (WARN_ON_ONCE(in_mad_size != sizeof(*in_mad) || + *out_mad_size != sizeof(*out_mad))) + return IB_MAD_RESULT_FAILURE; switch (in_mad->mad_hdr.mgmt_class) { case IB_MGMT_CLASS_PERF_MGMT: diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_main.c b/drivers/infiniband/hw/ocrdma/ocrdma_main.c index 8a1398b253a2..d98a707a5eb9 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_main.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_main.c @@ -696,6 +696,7 @@ static void __exit ocrdma_exit_module(void) ocrdma_unregister_inet6addr_notifier(); ocrdma_unregister_inetaddr_notifier(); ocrdma_rem_debugfs(); + idr_destroy(&ocrdma_dev_id); } module_init(ocrdma_init_module); diff --git a/drivers/infiniband/hw/qib/qib_mad.c b/drivers/infiniband/hw/qib/qib_mad.c index 05e3242d8442..9625e7c438e5 100644 --- a/drivers/infiniband/hw/qib/qib_mad.c +++ b/drivers/infiniband/hw/qib/qib_mad.c @@ -2412,8 +2412,9 @@ int qib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port, const struct ib_mad *in_mad = (const struct ib_mad *)in; struct ib_mad *out_mad = (struct ib_mad *)out; - BUG_ON(in_mad_size != sizeof(*in_mad) || - *out_mad_size != sizeof(*out_mad)); + if (WARN_ON_ONCE(in_mad_size != sizeof(*in_mad) || + *out_mad_size != sizeof(*out_mad))) + return IB_MAD_RESULT_FAILURE; switch (in_mad->mad_hdr.mgmt_class) { case IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE: diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h index bd94b0a6e9e5..79859c4d43c9 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib.h +++ b/drivers/infiniband/ulp/ipoib/ipoib.h @@ -239,7 +239,7 @@ struct ipoib_cm_tx { struct net_device *dev; struct ipoib_neigh *neigh; struct ipoib_path *path; - struct ipoib_cm_tx_buf *tx_ring; + struct ipoib_tx_buf *tx_ring; unsigned tx_head; unsigned tx_tail; unsigned long flags; @@ -504,6 +504,33 @@ int ipoib_mcast_stop_thread(struct net_device *dev); void ipoib_mcast_dev_down(struct net_device *dev); void ipoib_mcast_dev_flush(struct net_device *dev); +int ipoib_dma_map_tx(struct ib_device *ca, struct ipoib_tx_buf *tx_req); +void ipoib_dma_unmap_tx(struct ipoib_dev_priv *priv, + struct ipoib_tx_buf *tx_req); + +static inline void ipoib_build_sge(struct ipoib_dev_priv *priv, + struct ipoib_tx_buf *tx_req) +{ + int i, off; + struct sk_buff *skb = tx_req->skb; + skb_frag_t *frags = skb_shinfo(skb)->frags; + int nr_frags = skb_shinfo(skb)->nr_frags; + u64 *mapping = tx_req->mapping; + + if (skb_headlen(skb)) { + priv->tx_sge[0].addr = mapping[0]; + priv->tx_sge[0].length = skb_headlen(skb); + off = 1; + } else + off = 0; + + for (i = 0; i < nr_frags; ++i) { + priv->tx_sge[i + off].addr = mapping[i + off]; + priv->tx_sge[i + off].length = skb_frag_size(&frags[i]); + } + priv->tx_wr.num_sge = nr_frags + off; +} + #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG struct ipoib_mcast_iter *ipoib_mcast_iter_init(struct net_device *dev); int ipoib_mcast_iter_next(struct ipoib_mcast_iter *iter); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c index cf32a778e7d0..ee39be6ccfb0 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c @@ -694,14 +694,12 @@ repost: static inline int post_send(struct ipoib_dev_priv *priv, struct ipoib_cm_tx *tx, unsigned int wr_id, - u64 addr, int len) + struct ipoib_tx_buf *tx_req) { struct ib_send_wr *bad_wr; - priv->tx_sge[0].addr = addr; - priv->tx_sge[0].length = len; + ipoib_build_sge(priv, tx_req); - priv->tx_wr.num_sge = 1; priv->tx_wr.wr_id = wr_id | IPOIB_OP_CM; return ib_post_send(tx->qp, &priv->tx_wr, &bad_wr); @@ -710,8 +708,7 @@ static inline int post_send(struct ipoib_dev_priv *priv, void ipoib_cm_send(struct net_device *dev, struct sk_buff *skb, struct ipoib_cm_tx *tx) { struct ipoib_dev_priv *priv = netdev_priv(dev); - struct ipoib_cm_tx_buf *tx_req; - u64 addr; + struct ipoib_tx_buf *tx_req; int rc; if (unlikely(skb->len > tx->mtu)) { @@ -735,24 +732,21 @@ void ipoib_cm_send(struct net_device *dev, struct sk_buff *skb, struct ipoib_cm_ */ tx_req = &tx->tx_ring[tx->tx_head & (ipoib_sendq_size - 1)]; tx_req->skb = skb; - addr = ib_dma_map_single(priv->ca, skb->data, skb->len, DMA_TO_DEVICE); - if (unlikely(ib_dma_mapping_error(priv->ca, addr))) { + + if (unlikely(ipoib_dma_map_tx(priv->ca, tx_req))) { ++dev->stats.tx_errors; dev_kfree_skb_any(skb); return; } - tx_req->mapping = addr; - skb_orphan(skb); skb_dst_drop(skb); - rc = post_send(priv, tx, tx->tx_head & (ipoib_sendq_size - 1), - addr, skb->len); + rc = post_send(priv, tx, tx->tx_head & (ipoib_sendq_size - 1), tx_req); if (unlikely(rc)) { ipoib_warn(priv, "post_send failed, error %d\n", rc); ++dev->stats.tx_errors; - ib_dma_unmap_single(priv->ca, addr, skb->len, DMA_TO_DEVICE); + ipoib_dma_unmap_tx(priv, tx_req); dev_kfree_skb_any(skb); } else { dev->trans_start = jiffies; @@ -777,7 +771,7 @@ void ipoib_cm_handle_tx_wc(struct net_device *dev, struct ib_wc *wc) struct ipoib_dev_priv *priv = netdev_priv(dev); struct ipoib_cm_tx *tx = wc->qp->qp_context; unsigned int wr_id = wc->wr_id & ~IPOIB_OP_CM; - struct ipoib_cm_tx_buf *tx_req; + struct ipoib_tx_buf *tx_req; unsigned long flags; ipoib_dbg_data(priv, "cm send completion: id %d, status: %d\n", @@ -791,7 +785,7 @@ void ipoib_cm_handle_tx_wc(struct net_device *dev, struct ib_wc *wc) tx_req = &tx->tx_ring[wr_id]; - ib_dma_unmap_single(priv->ca, tx_req->mapping, tx_req->skb->len, DMA_TO_DEVICE); + ipoib_dma_unmap_tx(priv, tx_req); /* FIXME: is this right? Shouldn't we only increment on success? */ ++dev->stats.tx_packets; @@ -1036,6 +1030,9 @@ static struct ib_qp *ipoib_cm_create_tx_qp(struct net_device *dev, struct ipoib_ struct ib_qp *tx_qp; + if (dev->features & NETIF_F_SG) + attr.cap.max_send_sge = MAX_SKB_FRAGS + 1; + tx_qp = ib_create_qp(priv->pd, &attr); if (PTR_ERR(tx_qp) == -EINVAL) { ipoib_warn(priv, "can't use GFP_NOIO for QPs on device %s, using GFP_KERNEL\n", @@ -1170,7 +1167,7 @@ err_tx: static void ipoib_cm_tx_destroy(struct ipoib_cm_tx *p) { struct ipoib_dev_priv *priv = netdev_priv(p->dev); - struct ipoib_cm_tx_buf *tx_req; + struct ipoib_tx_buf *tx_req; unsigned long begin; ipoib_dbg(priv, "Destroy active connection 0x%x head 0x%x tail 0x%x\n", @@ -1197,8 +1194,7 @@ timeout: while ((int) p->tx_tail - (int) p->tx_head < 0) { tx_req = &p->tx_ring[p->tx_tail & (ipoib_sendq_size - 1)]; - ib_dma_unmap_single(priv->ca, tx_req->mapping, tx_req->skb->len, - DMA_TO_DEVICE); + ipoib_dma_unmap_tx(priv, tx_req); dev_kfree_skb_any(tx_req->skb); ++p->tx_tail; netif_tx_lock_bh(p->dev); @@ -1455,7 +1451,6 @@ static void ipoib_cm_stale_task(struct work_struct *work) spin_unlock_irq(&priv->lock); } - static ssize_t show_mode(struct device *d, struct device_attribute *attr, char *buf) { diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c index 63b92cbb29ad..d266667ca9b8 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c @@ -263,8 +263,7 @@ repost: "for buf %d\n", wr_id); } -static int ipoib_dma_map_tx(struct ib_device *ca, - struct ipoib_tx_buf *tx_req) +int ipoib_dma_map_tx(struct ib_device *ca, struct ipoib_tx_buf *tx_req) { struct sk_buff *skb = tx_req->skb; u64 *mapping = tx_req->mapping; @@ -305,8 +304,8 @@ partial_error: return -EIO; } -static void ipoib_dma_unmap_tx(struct ib_device *ca, - struct ipoib_tx_buf *tx_req) +void ipoib_dma_unmap_tx(struct ipoib_dev_priv *priv, + struct ipoib_tx_buf *tx_req) { struct sk_buff *skb = tx_req->skb; u64 *mapping = tx_req->mapping; @@ -314,7 +313,8 @@ static void ipoib_dma_unmap_tx(struct ib_device *ca, int off; if (skb_headlen(skb)) { - ib_dma_unmap_single(ca, mapping[0], skb_headlen(skb), DMA_TO_DEVICE); + ib_dma_unmap_single(priv->ca, mapping[0], skb_headlen(skb), + DMA_TO_DEVICE); off = 1; } else off = 0; @@ -322,8 +322,8 @@ static void ipoib_dma_unmap_tx(struct ib_device *ca, for (i = 0; i < skb_shinfo(skb)->nr_frags; ++i) { const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - ib_dma_unmap_page(ca, mapping[i + off], skb_frag_size(frag), - DMA_TO_DEVICE); + ib_dma_unmap_page(priv->ca, mapping[i + off], + skb_frag_size(frag), DMA_TO_DEVICE); } } @@ -389,7 +389,7 @@ static void ipoib_ib_handle_tx_wc(struct net_device *dev, struct ib_wc *wc) tx_req = &priv->tx_ring[wr_id]; - ipoib_dma_unmap_tx(priv->ca, tx_req); + ipoib_dma_unmap_tx(priv, tx_req); ++dev->stats.tx_packets; dev->stats.tx_bytes += tx_req->skb->len; @@ -514,24 +514,10 @@ static inline int post_send(struct ipoib_dev_priv *priv, void *head, int hlen) { struct ib_send_wr *bad_wr; - int i, off; struct sk_buff *skb = tx_req->skb; - skb_frag_t *frags = skb_shinfo(skb)->frags; - int nr_frags = skb_shinfo(skb)->nr_frags; - u64 *mapping = tx_req->mapping; - if (skb_headlen(skb)) { - priv->tx_sge[0].addr = mapping[0]; - priv->tx_sge[0].length = skb_headlen(skb); - off = 1; - } else - off = 0; + ipoib_build_sge(priv, tx_req); - for (i = 0; i < nr_frags; ++i) { - priv->tx_sge[i + off].addr = mapping[i + off]; - priv->tx_sge[i + off].length = skb_frag_size(&frags[i]); - } - priv->tx_wr.num_sge = nr_frags + off; priv->tx_wr.wr_id = wr_id; priv->tx_wr.wr.ud.remote_qpn = qpn; priv->tx_wr.wr.ud.ah = address; @@ -617,7 +603,7 @@ void ipoib_send(struct net_device *dev, struct sk_buff *skb, ipoib_warn(priv, "post_send failed, error %d\n", rc); ++dev->stats.tx_errors; --priv->tx_outstanding; - ipoib_dma_unmap_tx(priv->ca, tx_req); + ipoib_dma_unmap_tx(priv, tx_req); dev_kfree_skb_any(skb); if (netif_queue_stopped(dev)) netif_wake_queue(dev); @@ -868,7 +854,7 @@ int ipoib_ib_dev_stop(struct net_device *dev) while ((int) priv->tx_tail - (int) priv->tx_head < 0) { tx_req = &priv->tx_ring[priv->tx_tail & (ipoib_sendq_size - 1)]; - ipoib_dma_unmap_tx(priv->ca, tx_req); + ipoib_dma_unmap_tx(priv, tx_req); dev_kfree_skb_any(tx_req->skb); ++priv->tx_tail; --priv->tx_outstanding; @@ -985,20 +971,21 @@ static inline int update_child_pkey(struct ipoib_dev_priv *priv) } static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv, - enum ipoib_flush_level level) + enum ipoib_flush_level level, + int nesting) { struct ipoib_dev_priv *cpriv; struct net_device *dev = priv->dev; int result; - down_read(&priv->vlan_rwsem); + down_read_nested(&priv->vlan_rwsem, nesting); /* * Flush any child interfaces too -- they might be up even if * the parent is down. */ list_for_each_entry(cpriv, &priv->child_intfs, list) - __ipoib_ib_dev_flush(cpriv, level); + __ipoib_ib_dev_flush(cpriv, level, nesting + 1); up_read(&priv->vlan_rwsem); @@ -1076,7 +1063,7 @@ void ipoib_ib_dev_flush_light(struct work_struct *work) struct ipoib_dev_priv *priv = container_of(work, struct ipoib_dev_priv, flush_light); - __ipoib_ib_dev_flush(priv, IPOIB_FLUSH_LIGHT); + __ipoib_ib_dev_flush(priv, IPOIB_FLUSH_LIGHT, 0); } void ipoib_ib_dev_flush_normal(struct work_struct *work) @@ -1084,7 +1071,7 @@ void ipoib_ib_dev_flush_normal(struct work_struct *work) struct ipoib_dev_priv *priv = container_of(work, struct ipoib_dev_priv, flush_normal); - __ipoib_ib_dev_flush(priv, IPOIB_FLUSH_NORMAL); + __ipoib_ib_dev_flush(priv, IPOIB_FLUSH_NORMAL, 0); } void ipoib_ib_dev_flush_heavy(struct work_struct *work) @@ -1092,7 +1079,7 @@ void ipoib_ib_dev_flush_heavy(struct work_struct *work) struct ipoib_dev_priv *priv = container_of(work, struct ipoib_dev_priv, flush_heavy); - __ipoib_ib_dev_flush(priv, IPOIB_FLUSH_HEAVY); + __ipoib_ib_dev_flush(priv, IPOIB_FLUSH_HEAVY, 0); } void ipoib_ib_dev_cleanup(struct net_device *dev) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index da149c278cb8..b2943c84a5dd 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -190,7 +190,7 @@ static netdev_features_t ipoib_fix_features(struct net_device *dev, netdev_featu struct ipoib_dev_priv *priv = netdev_priv(dev); if (test_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags)) - features &= ~(NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO); + features &= ~(NETIF_F_IP_CSUM | NETIF_F_TSO); return features; } @@ -232,6 +232,7 @@ int ipoib_set_mode(struct net_device *dev, const char *buf) ipoib_warn(priv, "enabling connected mode " "will cause multicast packet drops\n"); netdev_update_features(dev); + dev_set_mtu(dev, ipoib_cm_max_mtu(dev)); rtnl_unlock(); priv->tx_wr.send_flags &= ~IB_SEND_IP_CSUM; @@ -1577,7 +1578,8 @@ static struct net_device *ipoib_add_port(const char *format, SET_NETDEV_DEV(priv->dev, hca->dma_device); priv->dev->dev_id = port - 1; - if (!ib_query_port(hca, port, &attr)) + result = ib_query_port(hca, port, &attr); + if (!result) priv->max_ib_mtu = ib_mtu_enum_to_int(attr.max_mtu); else { printk(KERN_WARNING "%s: ib_query_port %d failed\n", @@ -1598,7 +1600,8 @@ static struct net_device *ipoib_add_port(const char *format, goto device_init_failed; } - if (ipoib_set_dev_features(priv, hca)) + result = ipoib_set_dev_features(priv, hca); + if (result) goto device_init_failed; /* @@ -1684,7 +1687,7 @@ static void ipoib_add_one(struct ib_device *device) struct list_head *dev_list; struct net_device *dev; struct ipoib_dev_priv *priv; - int s, e, p; + int p; int count = 0; dev_list = kmalloc(sizeof *dev_list, GFP_KERNEL); @@ -1693,15 +1696,7 @@ static void ipoib_add_one(struct ib_device *device) INIT_LIST_HEAD(dev_list); - if (device->node_type == RDMA_NODE_IB_SWITCH) { - s = 0; - e = 0; - } else { - s = 1; - e = device->phys_port_cnt; - } - - for (p = s; p <= e; ++p) { + for (p = rdma_start_port(device); p <= rdma_end_port(device); ++p) { if (!rdma_protocol_ib(device, p)) continue; dev = ipoib_add_port("ib%d", device, p); diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index 267dc4f75502..31a20b462266 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -161,13 +161,10 @@ static int srp_tmo_set(const char *val, const struct kernel_param *kp) { int tmo, res; - if (strncmp(val, "off", 3) != 0) { - res = kstrtoint(val, 0, &tmo); - if (res) - goto out; - } else { - tmo = -1; - } + res = srp_parse_tmo(&tmo, val); + if (res) + goto out; + if (kp->arg == &srp_reconnect_delay) res = srp_tmo_valid(tmo, srp_fast_io_fail_tmo, srp_dev_loss_tmo); @@ -3379,7 +3376,7 @@ static void srp_add_one(struct ib_device *device) struct srp_device *srp_dev; struct ib_device_attr *dev_attr; struct srp_host *host; - int mr_page_shift, s, e, p; + int mr_page_shift, p; u64 max_pages_per_mr; dev_attr = kmalloc(sizeof *dev_attr, GFP_KERNEL); @@ -3443,15 +3440,7 @@ static void srp_add_one(struct ib_device *device) if (IS_ERR(srp_dev->mr)) goto err_pd; - if (device->node_type == RDMA_NODE_IB_SWITCH) { - s = 0; - e = 0; - } else { - s = 1; - e = device->phys_port_cnt; - } - - for (p = s; p <= e; ++p) { + for (p = rdma_start_port(device); p <= rdma_end_port(device); ++p) { host = srp_add_port(srp_dev, p); if (host) list_add_tail(&host->list, &srp_dev->dev_list); diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c index 82897ca17f32..60ff0a2390e5 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.c +++ b/drivers/infiniband/ulp/srpt/ib_srpt.c @@ -302,7 +302,7 @@ static void srpt_get_iou(struct ib_dm_mad *mad) int i; ioui = (struct ib_dm_iou_info *)mad->data; - ioui->change_id = __constant_cpu_to_be16(1); + ioui->change_id = cpu_to_be16(1); ioui->max_controllers = 16; /* set present for slot 1 and empty for the rest */ @@ -330,13 +330,13 @@ static void srpt_get_ioc(struct srpt_port *sport, u32 slot, if (!slot || slot > 16) { mad->mad_hdr.status - = __constant_cpu_to_be16(DM_MAD_STATUS_INVALID_FIELD); + = cpu_to_be16(DM_MAD_STATUS_INVALID_FIELD); return; } if (slot > 2) { mad->mad_hdr.status - = __constant_cpu_to_be16(DM_MAD_STATUS_NO_IOC); + = cpu_to_be16(DM_MAD_STATUS_NO_IOC); return; } @@ -348,10 +348,10 @@ static void srpt_get_ioc(struct srpt_port *sport, u32 slot, iocp->device_version = cpu_to_be16(sdev->dev_attr.hw_ver); iocp->subsys_vendor_id = cpu_to_be32(sdev->dev_attr.vendor_id); iocp->subsys_device_id = 0x0; - iocp->io_class = __constant_cpu_to_be16(SRP_REV16A_IB_IO_CLASS); - iocp->io_subclass = __constant_cpu_to_be16(SRP_IO_SUBCLASS); - iocp->protocol = __constant_cpu_to_be16(SRP_PROTOCOL); - iocp->protocol_version = __constant_cpu_to_be16(SRP_PROTOCOL_VERSION); + iocp->io_class = cpu_to_be16(SRP_REV16A_IB_IO_CLASS); + iocp->io_subclass = cpu_to_be16(SRP_IO_SUBCLASS); + iocp->protocol = cpu_to_be16(SRP_PROTOCOL); + iocp->protocol_version = cpu_to_be16(SRP_PROTOCOL_VERSION); iocp->send_queue_depth = cpu_to_be16(sdev->srq_size); iocp->rdma_read_depth = 4; iocp->send_size = cpu_to_be32(srp_max_req_size); @@ -379,13 +379,13 @@ static void srpt_get_svc_entries(u64 ioc_guid, if (!slot || slot > 16) { mad->mad_hdr.status - = __constant_cpu_to_be16(DM_MAD_STATUS_INVALID_FIELD); + = cpu_to_be16(DM_MAD_STATUS_INVALID_FIELD); return; } if (slot > 2 || lo > hi || hi > 1) { mad->mad_hdr.status - = __constant_cpu_to_be16(DM_MAD_STATUS_NO_IOC); + = cpu_to_be16(DM_MAD_STATUS_NO_IOC); return; } @@ -436,7 +436,7 @@ static void srpt_mgmt_method_get(struct srpt_port *sp, struct ib_mad *rq_mad, break; default: rsp_mad->mad_hdr.status = - __constant_cpu_to_be16(DM_MAD_STATUS_UNSUP_METHOD_ATTR); + cpu_to_be16(DM_MAD_STATUS_UNSUP_METHOD_ATTR); break; } } @@ -493,11 +493,11 @@ static void srpt_mad_recv_handler(struct ib_mad_agent *mad_agent, break; case IB_MGMT_METHOD_SET: dm_mad->mad_hdr.status = - __constant_cpu_to_be16(DM_MAD_STATUS_UNSUP_METHOD_ATTR); + cpu_to_be16(DM_MAD_STATUS_UNSUP_METHOD_ATTR); break; default: dm_mad->mad_hdr.status = - __constant_cpu_to_be16(DM_MAD_STATUS_UNSUP_METHOD); + cpu_to_be16(DM_MAD_STATUS_UNSUP_METHOD); break; } @@ -1535,7 +1535,7 @@ static int srpt_build_cmd_rsp(struct srpt_rdma_ch *ch, memset(srp_rsp, 0, sizeof *srp_rsp); srp_rsp->opcode = SRP_RSP; srp_rsp->req_lim_delta = - __constant_cpu_to_be32(1 + atomic_xchg(&ch->req_lim_delta, 0)); + cpu_to_be32(1 + atomic_xchg(&ch->req_lim_delta, 0)); srp_rsp->tag = tag; srp_rsp->status = status; @@ -1585,8 +1585,8 @@ static int srpt_build_tskmgmt_rsp(struct srpt_rdma_ch *ch, memset(srp_rsp, 0, sizeof *srp_rsp); srp_rsp->opcode = SRP_RSP; - srp_rsp->req_lim_delta = __constant_cpu_to_be32(1 - + atomic_xchg(&ch->req_lim_delta, 0)); + srp_rsp->req_lim_delta = + cpu_to_be32(1 + atomic_xchg(&ch->req_lim_delta, 0)); srp_rsp->tag = tag; srp_rsp->flags |= SRP_RSP_FLAG_RSPVALID; @@ -1630,7 +1630,7 @@ static uint64_t srpt_unpack_lun(const uint8_t *lun, int len) switch (len) { case 8: if ((*((__be64 *)lun) & - __constant_cpu_to_be64(0x0000FFFFFFFFFFFFLL)) != 0) + cpu_to_be64(0x0000FFFFFFFFFFFFLL)) != 0) goto out_err; break; case 4: @@ -2449,8 +2449,8 @@ static int srpt_cm_req_recv(struct ib_cm_id *cm_id, } if (it_iu_len > srp_max_req_size || it_iu_len < 64) { - rej->reason = __constant_cpu_to_be32( - SRP_LOGIN_REJ_REQ_IT_IU_LENGTH_TOO_LARGE); + rej->reason = cpu_to_be32( + SRP_LOGIN_REJ_REQ_IT_IU_LENGTH_TOO_LARGE); ret = -EINVAL; pr_err("rejected SRP_LOGIN_REQ because its" " length (%d bytes) is out of range (%d .. %d)\n", @@ -2459,8 +2459,8 @@ static int srpt_cm_req_recv(struct ib_cm_id *cm_id, } if (!sport->enabled) { - rej->reason = __constant_cpu_to_be32( - SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES); + rej->reason = cpu_to_be32( + SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES); ret = -EINVAL; pr_err("rejected SRP_LOGIN_REQ because the target port" " has not yet been enabled\n"); @@ -2505,8 +2505,8 @@ static int srpt_cm_req_recv(struct ib_cm_id *cm_id, if (*(__be64 *)req->target_port_id != cpu_to_be64(srpt_service_guid) || *(__be64 *)(req->target_port_id + 8) != cpu_to_be64(srpt_service_guid)) { - rej->reason = __constant_cpu_to_be32( - SRP_LOGIN_REJ_UNABLE_ASSOCIATE_CHANNEL); + rej->reason = cpu_to_be32( + SRP_LOGIN_REJ_UNABLE_ASSOCIATE_CHANNEL); ret = -ENOMEM; pr_err("rejected SRP_LOGIN_REQ because it" " has an invalid target port identifier.\n"); @@ -2515,8 +2515,8 @@ static int srpt_cm_req_recv(struct ib_cm_id *cm_id, ch = kzalloc(sizeof *ch, GFP_KERNEL); if (!ch) { - rej->reason = __constant_cpu_to_be32( - SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES); + rej->reason = cpu_to_be32( + SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES); pr_err("rejected SRP_LOGIN_REQ because no memory.\n"); ret = -ENOMEM; goto reject; @@ -2552,8 +2552,8 @@ static int srpt_cm_req_recv(struct ib_cm_id *cm_id, ret = srpt_create_ch_ib(ch); if (ret) { - rej->reason = __constant_cpu_to_be32( - SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES); + rej->reason = cpu_to_be32( + SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES); pr_err("rejected SRP_LOGIN_REQ because creating" " a new RDMA channel failed.\n"); goto free_ring; @@ -2561,8 +2561,7 @@ static int srpt_cm_req_recv(struct ib_cm_id *cm_id, ret = srpt_ch_qp_rtr(ch, ch->qp); if (ret) { - rej->reason = __constant_cpu_to_be32( - SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES); + rej->reason = cpu_to_be32(SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES); pr_err("rejected SRP_LOGIN_REQ because enabling" " RTR failed (error code = %d)\n", ret); goto destroy_ib; @@ -2580,15 +2579,15 @@ static int srpt_cm_req_recv(struct ib_cm_id *cm_id, if (!nacl) { pr_info("Rejected login because no ACL has been" " configured yet for initiator %s.\n", ch->sess_name); - rej->reason = __constant_cpu_to_be32( - SRP_LOGIN_REJ_CHANNEL_LIMIT_REACHED); + rej->reason = cpu_to_be32( + SRP_LOGIN_REJ_CHANNEL_LIMIT_REACHED); goto destroy_ib; } ch->sess = transport_init_session(TARGET_PROT_NORMAL); if (IS_ERR(ch->sess)) { - rej->reason = __constant_cpu_to_be32( - SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES); + rej->reason = cpu_to_be32( + SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES); pr_debug("Failed to create session\n"); goto deregister_session; } @@ -2604,8 +2603,8 @@ static int srpt_cm_req_recv(struct ib_cm_id *cm_id, rsp->max_it_iu_len = req->req_it_iu_len; rsp->max_ti_iu_len = req->req_it_iu_len; ch->max_ti_iu_len = it_iu_len; - rsp->buf_fmt = __constant_cpu_to_be16(SRP_BUF_FORMAT_DIRECT - | SRP_BUF_FORMAT_INDIRECT); + rsp->buf_fmt = cpu_to_be16(SRP_BUF_FORMAT_DIRECT + | SRP_BUF_FORMAT_INDIRECT); rsp->req_lim_delta = cpu_to_be32(ch->rq_size); atomic_set(&ch->req_lim, ch->rq_size); atomic_set(&ch->req_lim_delta, 0); @@ -2655,8 +2654,8 @@ free_ch: reject: rej->opcode = SRP_LOGIN_REJ; rej->tag = req->tag; - rej->buf_fmt = __constant_cpu_to_be16(SRP_BUF_FORMAT_DIRECT - | SRP_BUF_FORMAT_INDIRECT); + rej->buf_fmt = cpu_to_be16(SRP_BUF_FORMAT_DIRECT + | SRP_BUF_FORMAT_INDIRECT); ib_send_cm_rej(cm_id, IB_CM_REJ_CONSUMER_DEFINED, NULL, 0, (void *)rej, sizeof *rej); diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index 1aec8ff0b587..f73d2f579a7e 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -1863,6 +1863,33 @@ static void __dasd_device_check_expire(struct dasd_device *device) } /* + * return 1 when device is not eligible for IO + */ +static int __dasd_device_is_unusable(struct dasd_device *device, + struct dasd_ccw_req *cqr) +{ + int mask = ~(DASD_STOPPED_DC_WAIT | DASD_UNRESUMED_PM); + + if (test_bit(DASD_FLAG_OFFLINE, &device->flags)) { + /* dasd is being set offline. */ + return 1; + } + if (device->stopped) { + if (device->stopped & mask) { + /* stopped and CQR will not change that. */ + return 1; + } + if (!test_bit(DASD_CQR_VERIFY_PATH, &cqr->flags)) { + /* CQR is not able to change device to + * operational. */ + return 1; + } + /* CQR required to get device operational. */ + } + return 0; +} + +/* * Take a look at the first request on the ccw queue and check * if it needs to be started. */ @@ -1876,13 +1903,8 @@ static void __dasd_device_start_head(struct dasd_device *device) cqr = list_entry(device->ccw_queue.next, struct dasd_ccw_req, devlist); if (cqr->status != DASD_CQR_QUEUED) return; - /* when device is stopped, return request to previous layer - * exception: only the disconnect or unresumed bits are set and the - * cqr is a path verification request - */ - if (device->stopped && - !(!(device->stopped & ~(DASD_STOPPED_DC_WAIT | DASD_UNRESUMED_PM)) - && test_bit(DASD_CQR_VERIFY_PATH, &cqr->flags))) { + /* if device is not usable return request to upper layer */ + if (__dasd_device_is_unusable(device, cqr)) { cqr->intrc = -EAGAIN; cqr->status = DASD_CQR_CLEARED; dasd_schedule_device_bh(device); diff --git a/drivers/s390/block/dasd_alias.c b/drivers/s390/block/dasd_alias.c index a2597e683e79..ee3a6faae22a 100644 --- a/drivers/s390/block/dasd_alias.c +++ b/drivers/s390/block/dasd_alias.c @@ -699,7 +699,8 @@ struct dasd_device *dasd_alias_get_start_dev(struct dasd_device *base_device) struct dasd_device, alias_list); spin_unlock_irqrestore(&lcu->lock, flags); alias_priv = (struct dasd_eckd_private *) alias_device->private; - if ((alias_priv->count < private->count) && !alias_device->stopped) + if ((alias_priv->count < private->count) && !alias_device->stopped && + !test_bit(DASD_FLAG_OFFLINE, &alias_device->flags)) return alias_device; else return NULL; diff --git a/drivers/s390/char/sclp_early.c b/drivers/s390/char/sclp_early.c index aeed7969fd79..7bc6df3100ef 100644 --- a/drivers/s390/char/sclp_early.c +++ b/drivers/s390/char/sclp_early.c @@ -7,6 +7,7 @@ #define KMSG_COMPONENT "sclp_early" #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#include <linux/errno.h> #include <asm/ctl_reg.h> #include <asm/sclp.h> #include <asm/ipl.h> diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c index 08f1830cbfc4..01bf1f5cf2e9 100644 --- a/drivers/s390/crypto/zcrypt_api.c +++ b/drivers/s390/crypto/zcrypt_api.c @@ -54,6 +54,10 @@ MODULE_DESCRIPTION("Cryptographic Coprocessor interface, " \ "Copyright IBM Corp. 2001, 2012"); MODULE_LICENSE("GPL"); +static int zcrypt_hwrng_seed = 1; +module_param_named(hwrng_seed, zcrypt_hwrng_seed, int, S_IRUSR|S_IRGRP); +MODULE_PARM_DESC(hwrng_seed, "Turn on/off hwrng auto seed, default is 1 (on)."); + static DEFINE_SPINLOCK(zcrypt_device_lock); static LIST_HEAD(zcrypt_device_list); static int zcrypt_device_count = 0; @@ -1373,6 +1377,7 @@ static int zcrypt_rng_data_read(struct hwrng *rng, u32 *data) static struct hwrng zcrypt_rng_dev = { .name = "zcrypt", .data_read = zcrypt_rng_data_read, + .quality = 990, }; static int zcrypt_rng_device_add(void) @@ -1387,6 +1392,8 @@ static int zcrypt_rng_device_add(void) goto out; } zcrypt_rng_buffer_index = 0; + if (!zcrypt_hwrng_seed) + zcrypt_rng_dev.quality = 0; rc = hwrng_register(&zcrypt_rng_dev); if (rc) goto out_free; diff --git a/drivers/scsi/scsi_transport_srp.c b/drivers/scsi/scsi_transport_srp.c index a85292b1d09d..e3cd3ece4412 100644 --- a/drivers/scsi/scsi_transport_srp.c +++ b/drivers/scsi/scsi_transport_srp.c @@ -203,7 +203,7 @@ static ssize_t srp_show_tmo(char *buf, int tmo) return tmo >= 0 ? sprintf(buf, "%d\n", tmo) : sprintf(buf, "off\n"); } -static int srp_parse_tmo(int *tmo, const char *buf) +int srp_parse_tmo(int *tmo, const char *buf) { int res = 0; @@ -214,6 +214,7 @@ static int srp_parse_tmo(int *tmo, const char *buf) return res; } +EXPORT_SYMBOL(srp_parse_tmo); static ssize_t show_reconnect_delay(struct device *dev, struct device_attribute *attr, char *buf) diff --git a/fs/locks.c b/fs/locks.c index 653faabb07f4..d3d558ba4da7 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -862,12 +862,11 @@ static int posix_locks_deadlock(struct file_lock *caller_fl, * whether or not a lock was successfully freed by testing the return * value for -ENOENT. */ -static int flock_lock_file(struct file *filp, struct file_lock *request) +static int flock_lock_inode(struct inode *inode, struct file_lock *request) { struct file_lock *new_fl = NULL; struct file_lock *fl; struct file_lock_context *ctx; - struct inode *inode = file_inode(filp); int error = 0; bool found = false; LIST_HEAD(dispose); @@ -890,7 +889,7 @@ static int flock_lock_file(struct file *filp, struct file_lock *request) goto find_conflict; list_for_each_entry(fl, &ctx->flc_flock, fl_list) { - if (filp != fl->fl_file) + if (request->fl_file != fl->fl_file) continue; if (request->fl_type == fl->fl_type) goto out; @@ -1164,20 +1163,19 @@ int posix_lock_file(struct file *filp, struct file_lock *fl, EXPORT_SYMBOL(posix_lock_file); /** - * posix_lock_file_wait - Apply a POSIX-style lock to a file - * @filp: The file to apply the lock to + * posix_lock_inode_wait - Apply a POSIX-style lock to a file + * @inode: inode of file to which lock request should be applied * @fl: The lock to be applied * - * Add a POSIX style lock to a file. - * We merge adjacent & overlapping locks whenever possible. - * POSIX locks are sorted by owner task, then by starting address + * Variant of posix_lock_file_wait that does not take a filp, and so can be + * used after the filp has already been torn down. */ -int posix_lock_file_wait(struct file *filp, struct file_lock *fl) +int posix_lock_inode_wait(struct inode *inode, struct file_lock *fl) { int error; might_sleep (); for (;;) { - error = posix_lock_file(filp, fl, NULL); + error = __posix_lock_file(inode, fl, NULL); if (error != FILE_LOCK_DEFERRED) break; error = wait_event_interruptible(fl->fl_wait, !fl->fl_next); @@ -1189,7 +1187,7 @@ int posix_lock_file_wait(struct file *filp, struct file_lock *fl) } return error; } -EXPORT_SYMBOL(posix_lock_file_wait); +EXPORT_SYMBOL(posix_lock_inode_wait); /** * locks_mandatory_locked - Check for an active lock @@ -1851,18 +1849,18 @@ int fcntl_setlease(unsigned int fd, struct file *filp, long arg) } /** - * flock_lock_file_wait - Apply a FLOCK-style lock to a file - * @filp: The file to apply the lock to + * flock_lock_inode_wait - Apply a FLOCK-style lock to a file + * @inode: inode of the file to apply to * @fl: The lock to be applied * - * Add a FLOCK style lock to a file. + * Apply a FLOCK style lock request to an inode. */ -int flock_lock_file_wait(struct file *filp, struct file_lock *fl) +int flock_lock_inode_wait(struct inode *inode, struct file_lock *fl) { int error; might_sleep(); for (;;) { - error = flock_lock_file(filp, fl); + error = flock_lock_inode(inode, fl); if (error != FILE_LOCK_DEFERRED) break; error = wait_event_interruptible(fl->fl_wait, !fl->fl_next); @@ -1874,8 +1872,7 @@ int flock_lock_file_wait(struct file *filp, struct file_lock *fl) } return error; } - -EXPORT_SYMBOL(flock_lock_file_wait); +EXPORT_SYMBOL(flock_lock_inode_wait); /** * sys_flock: - flock() system call. @@ -2401,7 +2398,8 @@ locks_remove_flock(struct file *filp) .fl_type = F_UNLCK, .fl_end = OFFSET_MAX, }; - struct file_lock_context *flctx = file_inode(filp)->i_flctx; + struct inode *inode = file_inode(filp); + struct file_lock_context *flctx = inode->i_flctx; if (list_empty(&flctx->flc_flock)) return; @@ -2409,7 +2407,7 @@ locks_remove_flock(struct file *filp) if (filp->f_op->flock) filp->f_op->flock(filp, F_SETLKW, &fl); else - flock_lock_file(filp, &fl); + flock_lock_inode(inode, &fl); if (fl.fl_ops && fl.fl_ops->fl_release_private) fl.fl_ops->fl_release_private(&fl); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 6f228b5af819..8bee93469617 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5439,15 +5439,15 @@ static int nfs4_proc_getlk(struct nfs4_state *state, int cmd, struct file_lock * return err; } -static int do_vfs_lock(struct file *file, struct file_lock *fl) +static int do_vfs_lock(struct inode *inode, struct file_lock *fl) { int res = 0; switch (fl->fl_flags & (FL_POSIX|FL_FLOCK)) { case FL_POSIX: - res = posix_lock_file_wait(file, fl); + res = posix_lock_inode_wait(inode, fl); break; case FL_FLOCK: - res = flock_lock_file_wait(file, fl); + res = flock_lock_inode_wait(inode, fl); break; default: BUG(); @@ -5484,7 +5484,6 @@ static struct nfs4_unlockdata *nfs4_alloc_unlockdata(struct file_lock *fl, atomic_inc(&lsp->ls_count); /* Ensure we don't close file until we're done freeing locks! */ p->ctx = get_nfs_open_context(ctx); - get_file(fl->fl_file); memcpy(&p->fl, fl, sizeof(p->fl)); p->server = NFS_SERVER(inode); return p; @@ -5496,7 +5495,6 @@ static void nfs4_locku_release_calldata(void *data) nfs_free_seqid(calldata->arg.seqid); nfs4_put_lock_state(calldata->lsp); put_nfs_open_context(calldata->ctx); - fput(calldata->fl.fl_file); kfree(calldata); } @@ -5509,7 +5507,7 @@ static void nfs4_locku_done(struct rpc_task *task, void *data) switch (task->tk_status) { case 0: renew_lease(calldata->server, calldata->timestamp); - do_vfs_lock(calldata->fl.fl_file, &calldata->fl); + do_vfs_lock(calldata->lsp->ls_state->inode, &calldata->fl); if (nfs4_update_lock_stateid(calldata->lsp, &calldata->res.stateid)) break; @@ -5617,7 +5615,7 @@ static int nfs4_proc_unlck(struct nfs4_state *state, int cmd, struct file_lock * mutex_lock(&sp->so_delegreturn_mutex); /* Exclude nfs4_reclaim_open_stateid() - note nesting! */ down_read(&nfsi->rwsem); - if (do_vfs_lock(request->fl_file, request) == -ENOENT) { + if (do_vfs_lock(inode, request) == -ENOENT) { up_read(&nfsi->rwsem); mutex_unlock(&sp->so_delegreturn_mutex); goto out; @@ -5758,7 +5756,7 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata) data->timestamp); if (data->arg.new_lock) { data->fl.fl_flags &= ~(FL_SLEEP | FL_ACCESS); - if (do_vfs_lock(data->fl.fl_file, &data->fl) < 0) { + if (do_vfs_lock(lsp->ls_state->inode, &data->fl) < 0) { rpc_restart_call_prepare(task); break; } @@ -6000,7 +5998,7 @@ static int _nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock if (status != 0) goto out; request->fl_flags |= FL_ACCESS; - status = do_vfs_lock(request->fl_file, request); + status = do_vfs_lock(state->inode, request); if (status < 0) goto out; down_read(&nfsi->rwsem); @@ -6008,7 +6006,7 @@ static int _nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock /* Yes: cache locks! */ /* ...but avoid races with delegation recall... */ request->fl_flags = fl_flags & ~FL_SLEEP; - status = do_vfs_lock(request->fl_file, request); + status = do_vfs_lock(state->inode, request); up_read(&nfsi->rwsem); goto out; } diff --git a/include/linux/fs.h b/include/linux/fs.h index a0653e560c26..cc008c338f5a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1046,12 +1046,12 @@ extern void locks_remove_file(struct file *); extern void locks_release_private(struct file_lock *); extern void posix_test_lock(struct file *, struct file_lock *); extern int posix_lock_file(struct file *, struct file_lock *, struct file_lock *); -extern int posix_lock_file_wait(struct file *, struct file_lock *); +extern int posix_lock_inode_wait(struct inode *, struct file_lock *); extern int posix_unblock_lock(struct file_lock *); extern int vfs_test_lock(struct file *, struct file_lock *); extern int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *); extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl); -extern int flock_lock_file_wait(struct file *filp, struct file_lock *fl); +extern int flock_lock_inode_wait(struct inode *inode, struct file_lock *fl); extern int __break_lease(struct inode *inode, unsigned int flags, unsigned int type); extern void lease_get_mtime(struct inode *, struct timespec *time); extern int generic_setlease(struct file *, long, struct file_lock **, void **priv); @@ -1137,7 +1137,8 @@ static inline int posix_lock_file(struct file *filp, struct file_lock *fl, return -ENOLCK; } -static inline int posix_lock_file_wait(struct file *filp, struct file_lock *fl) +static inline int posix_lock_inode_wait(struct inode *inode, + struct file_lock *fl) { return -ENOLCK; } @@ -1163,8 +1164,8 @@ static inline int vfs_cancel_lock(struct file *filp, struct file_lock *fl) return 0; } -static inline int flock_lock_file_wait(struct file *filp, - struct file_lock *request) +static inline int flock_lock_inode_wait(struct inode *inode, + struct file_lock *request) { return -ENOLCK; } @@ -1202,6 +1203,20 @@ static inline void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files) {} #endif /* !CONFIG_FILE_LOCKING */ +static inline struct inode *file_inode(const struct file *f) +{ + return f->f_inode; +} + +static inline int posix_lock_file_wait(struct file *filp, struct file_lock *fl) +{ + return posix_lock_inode_wait(file_inode(filp), fl); +} + +static inline int flock_lock_file_wait(struct file *filp, struct file_lock *fl) +{ + return flock_lock_inode_wait(file_inode(filp), fl); +} struct fasync_struct { spinlock_t fa_lock; @@ -2011,11 +2026,6 @@ extern void ihold(struct inode * inode); extern void iput(struct inode *); extern int generic_update_time(struct inode *, struct timespec *, int); -static inline struct inode *file_inode(const struct file *f) -{ - return f->f_inode; -} - /* /sys/fs */ extern struct kobject *fs_kobj; diff --git a/include/linux/init.h b/include/linux/init.h index 7c68c36d3fd8..b449f378f995 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -282,68 +282,8 @@ void __init parse_early_param(void); void __init parse_early_options(char *cmdline); #endif /* __ASSEMBLY__ */ -/** - * module_init() - driver initialization entry point - * @x: function to be run at kernel boot time or module insertion - * - * module_init() will either be called during do_initcalls() (if - * builtin) or at module insertion time (if a module). There can only - * be one per module. - */ -#define module_init(x) __initcall(x); - -/** - * module_exit() - driver exit entry point - * @x: function to be run when driver is removed - * - * module_exit() will wrap the driver clean-up code - * with cleanup_module() when used with rmmod when - * the driver is a module. If the driver is statically - * compiled into the kernel, module_exit() has no effect. - * There can only be one per module. - */ -#define module_exit(x) __exitcall(x); - #else /* MODULE */ -/* - * In most cases loadable modules do not need custom - * initcall levels. There are still some valid cases where - * a driver may be needed early if built in, and does not - * matter when built as a loadable module. Like bus - * snooping debug drivers. - */ -#define early_initcall(fn) module_init(fn) -#define core_initcall(fn) module_init(fn) -#define core_initcall_sync(fn) module_init(fn) -#define postcore_initcall(fn) module_init(fn) -#define postcore_initcall_sync(fn) module_init(fn) -#define arch_initcall(fn) module_init(fn) -#define subsys_initcall(fn) module_init(fn) -#define subsys_initcall_sync(fn) module_init(fn) -#define fs_initcall(fn) module_init(fn) -#define fs_initcall_sync(fn) module_init(fn) -#define rootfs_initcall(fn) module_init(fn) -#define device_initcall(fn) module_init(fn) -#define device_initcall_sync(fn) module_init(fn) -#define late_initcall(fn) module_init(fn) -#define late_initcall_sync(fn) module_init(fn) - -#define console_initcall(fn) module_init(fn) -#define security_initcall(fn) module_init(fn) - -/* Each module must use one module_init(). */ -#define module_init(initfn) \ - static inline initcall_t __inittest(void) \ - { return initfn; } \ - int init_module(void) __attribute__((alias(#initfn))); - -/* This is only required if you want to be unloadable. */ -#define module_exit(exitfn) \ - static inline exitcall_t __exittest(void) \ - { return exitfn; } \ - void cleanup_module(void) __attribute__((alias(#exitfn))); - #define __setup_param(str, unique_id, fn) /* nothing */ #define __setup(str, func) /* nothing */ #endif @@ -351,24 +291,6 @@ void __init parse_early_options(char *cmdline); /* Data marked not to be saved by software suspend */ #define __nosavedata __section(.data..nosave) -/* This means "can be init if no module support, otherwise module load - may call it." */ -#ifdef CONFIG_MODULES -#define __init_or_module -#define __initdata_or_module -#define __initconst_or_module -#define __INIT_OR_MODULE .text -#define __INITDATA_OR_MODULE .data -#define __INITRODATA_OR_MODULE .section ".rodata","a",%progbits -#else -#define __init_or_module __init -#define __initdata_or_module __initdata -#define __initconst_or_module __initconst -#define __INIT_OR_MODULE __INIT -#define __INITDATA_OR_MODULE __INITDATA -#define __INITRODATA_OR_MODULE __INITRODATA -#endif /*CONFIG_MODULES*/ - #ifdef MODULE #define __exit_p(x) x #else diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 9564fd78c547..05e99b8ef465 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -734,6 +734,24 @@ static inline bool kvm_arch_has_noncoherent_dma(struct kvm *kvm) return false; } #endif +#ifdef __KVM_HAVE_ARCH_ASSIGNED_DEVICE +void kvm_arch_start_assignment(struct kvm *kvm); +void kvm_arch_end_assignment(struct kvm *kvm); +bool kvm_arch_has_assigned_device(struct kvm *kvm); +#else +static inline void kvm_arch_start_assignment(struct kvm *kvm) +{ +} + +static inline void kvm_arch_end_assignment(struct kvm *kvm) +{ +} + +static inline bool kvm_arch_has_assigned_device(struct kvm *kvm) +{ + return false; +} +#endif static inline wait_queue_head_t *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu) { diff --git a/include/linux/module.h b/include/linux/module.h index d67b1932cc59..3a19c79918e0 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -11,6 +11,7 @@ #include <linux/compiler.h> #include <linux/cache.h> #include <linux/kmod.h> +#include <linux/init.h> #include <linux/elf.h> #include <linux/stringify.h> #include <linux/kobject.h> @@ -71,6 +72,89 @@ extern struct module_attribute module_uevent; extern int init_module(void); extern void cleanup_module(void); +#ifndef MODULE +/** + * module_init() - driver initialization entry point + * @x: function to be run at kernel boot time or module insertion + * + * module_init() will either be called during do_initcalls() (if + * builtin) or at module insertion time (if a module). There can only + * be one per module. + */ +#define module_init(x) __initcall(x); + +/** + * module_exit() - driver exit entry point + * @x: function to be run when driver is removed + * + * module_exit() will wrap the driver clean-up code + * with cleanup_module() when used with rmmod when + * the driver is a module. If the driver is statically + * compiled into the kernel, module_exit() has no effect. + * There can only be one per module. + */ +#define module_exit(x) __exitcall(x); + +#else /* MODULE */ + +/* + * In most cases loadable modules do not need custom + * initcall levels. There are still some valid cases where + * a driver may be needed early if built in, and does not + * matter when built as a loadable module. Like bus + * snooping debug drivers. + */ +#define early_initcall(fn) module_init(fn) +#define core_initcall(fn) module_init(fn) +#define core_initcall_sync(fn) module_init(fn) +#define postcore_initcall(fn) module_init(fn) +#define postcore_initcall_sync(fn) module_init(fn) +#define arch_initcall(fn) module_init(fn) +#define subsys_initcall(fn) module_init(fn) +#define subsys_initcall_sync(fn) module_init(fn) +#define fs_initcall(fn) module_init(fn) +#define fs_initcall_sync(fn) module_init(fn) +#define rootfs_initcall(fn) module_init(fn) +#define device_initcall(fn) module_init(fn) +#define device_initcall_sync(fn) module_init(fn) +#define late_initcall(fn) module_init(fn) +#define late_initcall_sync(fn) module_init(fn) + +#define console_initcall(fn) module_init(fn) +#define security_initcall(fn) module_init(fn) + +/* Each module must use one module_init(). */ +#define module_init(initfn) \ + static inline initcall_t __inittest(void) \ + { return initfn; } \ + int init_module(void) __attribute__((alias(#initfn))); + +/* This is only required if you want to be unloadable. */ +#define module_exit(exitfn) \ + static inline exitcall_t __exittest(void) \ + { return exitfn; } \ + void cleanup_module(void) __attribute__((alias(#exitfn))); + +#endif + +/* This means "can be init if no module support, otherwise module load + may call it." */ +#ifdef CONFIG_MODULES +#define __init_or_module +#define __initdata_or_module +#define __initconst_or_module +#define __INIT_OR_MODULE .text +#define __INITDATA_OR_MODULE .data +#define __INITRODATA_OR_MODULE .section ".rodata","a",%progbits +#else +#define __init_or_module __init +#define __initdata_or_module __initdata +#define __initconst_or_module __initconst +#define __INIT_OR_MODULE __INIT +#define __INITDATA_OR_MODULE __INITDATA +#define __INITRODATA_OR_MODULE __INITRODATA +#endif /*CONFIG_MODULES*/ + /* Archs provide a method of finding the correct exception table. */ struct exception_table_entry; diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 986fddb08579..b0f898e3b2e7 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -1745,6 +1745,7 @@ struct ib_device { char node_desc[64]; __be64 node_guid; u32 local_dma_lkey; + u16 is_switch:1; u8 node_type; u8 phys_port_cnt; @@ -1824,6 +1825,20 @@ enum rdma_link_layer rdma_port_get_link_layer(struct ib_device *device, u8 port_num); /** + * rdma_cap_ib_switch - Check if the device is IB switch + * @device: Device to check + * + * Device driver is responsible for setting is_switch bit on + * in ib_device structure at init time. + * + * Return: true if the device is IB switch. + */ +static inline bool rdma_cap_ib_switch(const struct ib_device *device) +{ + return device->is_switch; +} + +/** * rdma_start_port - Return the first valid port number for the device * specified * @@ -1833,7 +1848,7 @@ enum rdma_link_layer rdma_port_get_link_layer(struct ib_device *device, */ static inline u8 rdma_start_port(const struct ib_device *device) { - return (device->node_type == RDMA_NODE_IB_SWITCH) ? 0 : 1; + return rdma_cap_ib_switch(device) ? 0 : 1; } /** @@ -1846,8 +1861,7 @@ static inline u8 rdma_start_port(const struct ib_device *device) */ static inline u8 rdma_end_port(const struct ib_device *device) { - return (device->node_type == RDMA_NODE_IB_SWITCH) ? - 0 : device->phys_port_cnt; + return rdma_cap_ib_switch(device) ? 0 : device->phys_port_cnt; } static inline bool rdma_protocol_ib(const struct ib_device *device, u8 port_num) diff --git a/include/scsi/scsi_transport_srp.h b/include/scsi/scsi_transport_srp.h index cdb05dd1d440..d40d3ef25707 100644 --- a/include/scsi/scsi_transport_srp.h +++ b/include/scsi/scsi_transport_srp.h @@ -119,6 +119,7 @@ extern struct srp_rport *srp_rport_add(struct Scsi_Host *, extern void srp_rport_del(struct srp_rport *); extern int srp_tmo_valid(int reconnect_delay, int fast_io_fail_tmo, int dev_loss_tmo); +int srp_parse_tmo(int *tmo, const char *buf); extern int srp_reconnect_rport(struct srp_rport *rport); extern void srp_start_tl_fail_timers(struct srp_rport *rport); extern void srp_remove_host(struct Scsi_Host *); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index f060716b02ae..74bde81601a9 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -444,6 +444,7 @@ enum { TRACE_CONTROL_BIT, + TRACE_BRANCH_BIT, /* * Abuse of the trace_recursion. * As we need a way to maintain state if we are tracing the function diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c index a87b43f49eb4..e2e12ad3186f 100644 --- a/kernel/trace/trace_branch.c +++ b/kernel/trace/trace_branch.c @@ -36,9 +36,12 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect) struct trace_branch *entry; struct ring_buffer *buffer; unsigned long flags; - int cpu, pc; + int pc; const char *p; + if (current->trace_recursion & TRACE_BRANCH_BIT) + return; + /* * I would love to save just the ftrace_likely_data pointer, but * this code can also be used by modules. Ugly things can happen @@ -49,10 +52,10 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect) if (unlikely(!tr)) return; - local_irq_save(flags); - cpu = raw_smp_processor_id(); - data = per_cpu_ptr(tr->trace_buffer.data, cpu); - if (atomic_inc_return(&data->disabled) != 1) + raw_local_irq_save(flags); + current->trace_recursion |= TRACE_BRANCH_BIT; + data = this_cpu_ptr(tr->trace_buffer.data); + if (atomic_read(&data->disabled)) goto out; pc = preempt_count(); @@ -81,8 +84,8 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect) __buffer_unlock_commit(buffer, event); out: - atomic_dec(&data->disabled); - local_irq_restore(flags); + current->trace_recursion &= ~TRACE_BRANCH_BIT; + raw_local_irq_restore(flags); } static inline diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c index 273b8bff6ba4..657ba9f5d308 100644 --- a/net/rds/ib_rdma.c +++ b/net/rds/ib_rdma.c @@ -759,8 +759,10 @@ void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents, } ibmr = rds_ib_alloc_fmr(rds_ibdev); - if (IS_ERR(ibmr)) + if (IS_ERR(ibmr)) { + rds_ib_dev_put(rds_ibdev); return ibmr; + } ret = rds_ib_map_fmr(rds_ibdev, ibmr, sg, nents); if (ret == 0) diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c index 620e37f741b8..1dd087da6f31 100644 --- a/virt/kvm/vfio.c +++ b/virt/kvm/vfio.c @@ -155,6 +155,8 @@ static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg) list_add_tail(&kvg->node, &kv->group_list); kvg->vfio_group = vfio_group; + kvm_arch_start_assignment(dev->kvm); + mutex_unlock(&kv->lock); kvm_vfio_update_coherency(dev); @@ -190,6 +192,8 @@ static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg) break; } + kvm_arch_end_assignment(dev->kvm); + mutex_unlock(&kv->lock); kvm_vfio_group_put_external_user(vfio_group); @@ -239,6 +243,7 @@ static void kvm_vfio_destroy(struct kvm_device *dev) kvm_vfio_group_put_external_user(kvg->vfio_group); list_del(&kvg->node); kfree(kvg); + kvm_arch_end_assignment(dev->kvm); } kvm_vfio_update_coherency(dev); |