diff options
| author | Max Krummenacher <max.krummenacher@toradex.com> | 2020-03-28 21:14:50 +0100 |
|---|---|---|
| committer | Max Krummenacher <max.krummenacher@toradex.com> | 2020-03-28 21:14:50 +0100 |
| commit | 4a31b8a3519d5dde0eacbb088b0d45c83732535b (patch) | |
| tree | ee0d405004393bba659643108bfe40f21788b96d | |
| parent | 73b51c4600180ca69bfa5f22ad097edbf655d0d1 (diff) | |
| parent | 3b41c631678a15390920ffc1e72470e83db73ac8 (diff) | |
Merge tag 'v4.4.217' into toradex_vf_4.4-next
This is the 4.4.217 stable release
244 files changed, 2417 insertions, 9095 deletions
@@ -1,6 +1,6 @@ VERSION = 4 PATCHLEVEL = 4 -SUBLEVEL = 214 +SUBLEVEL = 217 EXTRAVERSION = NAME = Blurry Fish Butt diff --git a/arch/arc/include/asm/linkage.h b/arch/arc/include/asm/linkage.h index 5faad17118b4..3ed7ea726fb5 100644 --- a/arch/arc/include/asm/linkage.h +++ b/arch/arc/include/asm/linkage.h @@ -12,6 +12,8 @@ #ifdef __ASSEMBLY__ #define ASM_NL ` /* use '`' to mark new line in macro */ +#define __ALIGN .align 4 +#define __ALIGN_STR __stringify(__ALIGN) /* annotation for data we want in DCCM - if enabled in .config */ .macro ARCFP_DATA nm diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 2ba69df49cf8..45f2a5930379 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -2000,7 +2000,7 @@ config XIP_PHYS_ADDR config KEXEC bool "Kexec system call (EXPERIMENTAL)" depends on (!SMP || PM_SLEEP_SMP) - depends on !CPU_V7M + depends on MMU select KEXEC_CORE help kexec is a system call that implements the ability to shutdown your diff --git a/arch/arm/boot/dts/r8a7779.dtsi b/arch/arm/boot/dts/r8a7779.dtsi index 6afa909865b5..8636e2321ab7 100644 --- a/arch/arm/boot/dts/r8a7779.dtsi +++ b/arch/arm/boot/dts/r8a7779.dtsi @@ -63,6 +63,14 @@ <0xf0000100 0x100>; }; + timer@f0000200 { + compatible = "arm,cortex-a9-global-timer"; + reg = <0xf0000200 0x100>; + interrupts = <GIC_PPI 11 + (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>; + clocks = <&cpg_clocks R8A7779_CLK_ZS>; + }; + timer@f0000600 { compatible = "arm,cortex-a9-twd-timer"; reg = <0xf0000600 0x20>; diff --git a/arch/arm/kernel/vdso.c b/arch/arm/kernel/vdso.c index 2dee87273e51..5ab9af255c78 100644 --- a/arch/arm/kernel/vdso.c +++ b/arch/arm/kernel/vdso.c @@ -85,6 +85,8 @@ static bool __init cntvct_functional(void) */ np = of_find_compatible_node(NULL, NULL, "arm,armv7-timer"); if (!np) + np = of_find_compatible_node(NULL, NULL, "arm,armv8-timer"); + if (!np) goto out_put; if (of_property_read_bool(np, "arm,cpu-registers-not-fw-configured")) diff --git a/arch/arm/lib/copy_from_user.S b/arch/arm/lib/copy_from_user.S index e32b51838439..05955ed85c2c 100644 --- a/arch/arm/lib/copy_from_user.S +++ b/arch/arm/lib/copy_from_user.S @@ -100,7 +100,7 @@ ENTRY(arm_copy_from_user) ENDPROC(arm_copy_from_user) - .pushsection .fixup,"ax" + .pushsection .text.fixup,"ax" .align 0 copy_abort_preamble ldmfd sp!, {r1, r2} diff --git a/arch/arm/mach-imx/Makefile b/arch/arm/mach-imx/Makefile index 1fffae129a4a..c0f8b001b1ea 100644 --- a/arch/arm/mach-imx/Makefile +++ b/arch/arm/mach-imx/Makefile @@ -93,6 +93,8 @@ obj-$(CONFIG_SOC_IMX53) += suspend-imx53.o AFLAGS_suspend-vf610.o :=-Wa,-march=armv7-a obj-$(CONFIG_SOC_VF610) += suspend-vf610.o endif +AFLAGS_resume-imx6.o :=-Wa,-march=armv7-a +obj-$(CONFIG_SOC_IMX6) += resume-imx6.o obj-$(CONFIG_SOC_IMX6) += pm-imx6.o obj-$(CONFIG_SOC_VF610) += pm-vf610.o diff --git a/arch/arm/mach-imx/common.h b/arch/arm/mach-imx/common.h index 94d93a3b3b58..91d22f3a4dbe 100644 --- a/arch/arm/mach-imx/common.h +++ b/arch/arm/mach-imx/common.h @@ -122,19 +122,19 @@ void imx_cpu_die(unsigned int cpu); int imx_cpu_kill(unsigned int cpu); #ifdef CONFIG_SUSPEND -void v7_cpu_resume(void); void imx53_suspend(void __iomem *ocram_vbase); extern const u32 imx53_suspend_sz; void imx6_suspend(void __iomem *ocram_vbase); void vf610_suspend(void __iomem *ocram_vbase); #else -static inline void v7_cpu_resume(void) {} static inline void imx53_suspend(void __iomem *ocram_vbase) {} static const u32 imx53_suspend_sz; static inline void imx6_suspend(void __iomem *ocram_vbase) {} static inline void vf610_suspend(void __iomem *ocram_vbase) {} #endif +void v7_cpu_resume(void); + void imx6_pm_ccm_init(const char *ccm_compat); void imx6q_pm_init(void); void imx6dl_pm_init(void); diff --git a/arch/arm/mach-imx/resume-imx6.S b/arch/arm/mach-imx/resume-imx6.S new file mode 100644 index 000000000000..5bd1ba7ef15b --- /dev/null +++ b/arch/arm/mach-imx/resume-imx6.S @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright 2014 Freescale Semiconductor, Inc. + */ + +#include <linux/linkage.h> +#include <asm/assembler.h> +#include <asm/asm-offsets.h> +#include <asm/hardware/cache-l2x0.h> +#include "hardware.h" + +/* + * The following code must assume it is running from physical address + * where absolute virtual addresses to the data section have to be + * turned into relative ones. + */ + +ENTRY(v7_cpu_resume) + bl v7_invalidate_l1 +#ifdef CONFIG_CACHE_L2X0 + bl l2c310_early_resume +#endif + b cpu_resume +ENDPROC(v7_cpu_resume) diff --git a/arch/arm/mach-imx/suspend-imx6.S b/arch/arm/mach-imx/suspend-imx6.S index 76ee2ceec8d5..7d84b617af48 100644 --- a/arch/arm/mach-imx/suspend-imx6.S +++ b/arch/arm/mach-imx/suspend-imx6.S @@ -333,17 +333,3 @@ resume: ret lr ENDPROC(imx6_suspend) - -/* - * The following code must assume it is running from physical address - * where absolute virtual addresses to the data section have to be - * turned into relative ones. - */ - -ENTRY(v7_cpu_resume) - bl v7_invalidate_l1 -#ifdef CONFIG_CACHE_L2X0 - bl l2c310_early_resume -#endif - b cpu_resume -ENDPROC(v7_cpu_resume) diff --git a/arch/microblaze/kernel/cpu/cache.c b/arch/microblaze/kernel/cpu/cache.c index 0bde47e4fa69..dcba53803fa5 100644 --- a/arch/microblaze/kernel/cpu/cache.c +++ b/arch/microblaze/kernel/cpu/cache.c @@ -92,7 +92,8 @@ static inline void __disable_dcache_nomsr(void) #define CACHE_LOOP_LIMITS(start, end, cache_line_length, cache_size) \ do { \ int align = ~(cache_line_length - 1); \ - end = min(start + cache_size, end); \ + if (start < UINT_MAX - cache_size) \ + end = min(start + cache_size, end); \ start &= align; \ } while (0) diff --git a/arch/mips/kernel/vpe.c b/arch/mips/kernel/vpe.c index 9067b651c7a2..ca93984ff5a6 100644 --- a/arch/mips/kernel/vpe.c +++ b/arch/mips/kernel/vpe.c @@ -134,7 +134,7 @@ void release_vpe(struct vpe *v) { list_del(&v->list); if (v->load_addr) - release_progmem(v); + release_progmem(v->load_addr); kfree(v); } diff --git a/arch/mips/loongson64/loongson-3/platform.c b/arch/mips/loongson64/loongson-3/platform.c index 25a97cc0ee33..0db4cc3196eb 100644 --- a/arch/mips/loongson64/loongson-3/platform.c +++ b/arch/mips/loongson64/loongson-3/platform.c @@ -31,6 +31,9 @@ static int __init loongson3_platform_init(void) continue; pdev = kzalloc(sizeof(struct platform_device), GFP_KERNEL); + if (!pdev) + return -ENOMEM; + pdev->name = loongson_sysconf.sensors[i].name; pdev->id = loongson_sysconf.sensors[i].id; pdev->dev.platform_data = &loongson_sysconf.sensors[i]; diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 7d80bfdfb15e..7ad686009795 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -2147,11 +2147,13 @@ static struct cpu_spec * __init setup_cpu_spec(unsigned long offset, * oprofile_cpu_type already has a value, then we are * possibly overriding a real PVR with a logical one, * and, in that case, keep the current value for - * oprofile_cpu_type. + * oprofile_cpu_type. Futhermore, let's ensure that the + * fix for the PMAO bug is enabled on compatibility mode. */ if (old.oprofile_cpu_type != NULL) { t->oprofile_cpu_type = old.oprofile_cpu_type; t->oprofile_type = old.oprofile_type; + t->cpu_features |= old.cpu_features & CPU_FTR_PMAO_BUG; } } diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h index dcb6312a0b91..ec94e8812283 100644 --- a/arch/s390/include/asm/timex.h +++ b/arch/s390/include/asm/timex.h @@ -82,7 +82,7 @@ static inline void get_tod_clock_ext(char *clk) static inline unsigned long long get_tod_clock(void) { - unsigned char clk[STORE_CLOCK_EXT_SIZE]; + char clk[STORE_CLOCK_EXT_SIZE]; get_tod_clock_ext(clk); return *((unsigned long long *)&clk[1]); diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S index 6c1c7d399bf9..78ba14546e00 100644 --- a/arch/s390/kernel/mcount.S +++ b/arch/s390/kernel/mcount.S @@ -23,6 +23,12 @@ ENTRY(ftrace_stub) #define STACK_PTREGS (STACK_FRAME_OVERHEAD) #define STACK_PTREGS_GPRS (STACK_PTREGS + __PT_GPRS) #define STACK_PTREGS_PSW (STACK_PTREGS + __PT_PSW) +#ifdef __PACK_STACK +/* allocate just enough for r14, r15 and backchain */ +#define TRACED_FUNC_FRAME_SIZE 24 +#else +#define TRACED_FUNC_FRAME_SIZE STACK_FRAME_OVERHEAD +#endif ENTRY(_mcount) BR_EX %r14 @@ -34,9 +40,16 @@ ENTRY(ftrace_caller) #ifndef CC_USING_HOTPATCH aghi %r0,MCOUNT_RETURN_FIXUP #endif - aghi %r15,-STACK_FRAME_SIZE + # allocate stack frame for ftrace_caller to contain traced function + aghi %r15,-TRACED_FUNC_FRAME_SIZE stg %r1,__SF_BACKCHAIN(%r15) + stg %r0,(__SF_GPRS+8*8)(%r15) + stg %r15,(__SF_GPRS+9*8)(%r15) + # allocate pt_regs and stack frame for ftrace_trace_function + aghi %r15,-STACK_FRAME_SIZE stg %r1,(STACK_PTREGS_GPRS+15*8)(%r15) + aghi %r1,-TRACED_FUNC_FRAME_SIZE + stg %r1,__SF_BACKCHAIN(%r15) stg %r0,(STACK_PTREGS_PSW+8)(%r15) stmg %r2,%r14,(STACK_PTREGS_GPRS+2*8)(%r15) #ifdef CONFIG_HAVE_MARCH_Z196_FEATURES diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c index 7ad41be8b373..4f7dad36b3c1 100644 --- a/arch/s390/mm/gup.c +++ b/arch/s390/mm/gup.c @@ -37,7 +37,8 @@ static inline int gup_pte_range(pmd_t *pmdp, pmd_t pmd, unsigned long addr, return 0; VM_BUG_ON(!pfn_valid(pte_pfn(pte))); page = pte_page(pte); - if (!page_cache_get_speculative(page)) + if (WARN_ON_ONCE(page_ref_count(page) < 0) + || !page_cache_get_speculative(page)) return 0; if (unlikely(pte_val(pte) != pte_val(*ptep))) { put_page(page); @@ -76,7 +77,8 @@ static inline int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr, refs++; } while (addr += PAGE_SIZE, addr != end); - if (!page_cache_add_speculative(head, refs)) { + if (WARN_ON_ONCE(page_ref_count(head) < 0) + || !page_cache_add_speculative(head, refs)) { *nr -= refs; return 0; } diff --git a/arch/sh/include/cpu-sh2a/cpu/sh7269.h b/arch/sh/include/cpu-sh2a/cpu/sh7269.h index 2a0ca8780f0d..e4caddd443da 100644 --- a/arch/sh/include/cpu-sh2a/cpu/sh7269.h +++ b/arch/sh/include/cpu-sh2a/cpu/sh7269.h @@ -79,8 +79,15 @@ enum { GPIO_FN_WDTOVF, /* CAN */ - GPIO_FN_CTX1, GPIO_FN_CRX1, GPIO_FN_CTX0, GPIO_FN_CTX0_CTX1, - GPIO_FN_CRX0, GPIO_FN_CRX0_CRX1, GPIO_FN_CRX0_CRX1_CRX2, + GPIO_FN_CTX2, GPIO_FN_CRX2, + GPIO_FN_CTX1, GPIO_FN_CRX1, + GPIO_FN_CTX0, GPIO_FN_CRX0, + GPIO_FN_CTX0_CTX1, GPIO_FN_CRX0_CRX1, + GPIO_FN_CTX0_CTX1_CTX2, GPIO_FN_CRX0_CRX1_CRX2, + GPIO_FN_CTX2_PJ21, GPIO_FN_CRX2_PJ20, + GPIO_FN_CTX1_PJ23, GPIO_FN_CRX1_PJ22, + GPIO_FN_CTX0_CTX1_PJ23, GPIO_FN_CRX0_CRX1_PJ22, + GPIO_FN_CTX0_CTX1_CTX2_PJ21, GPIO_FN_CRX0_CRX1_CRX2_PJ20, /* DMAC */ GPIO_FN_TEND0, GPIO_FN_DACK0, GPIO_FN_DREQ0, diff --git a/arch/x86/entry/vdso/vdso32-setup.c b/arch/x86/entry/vdso/vdso32-setup.c index 3f9d1a83891a..50c1f77cab15 100644 --- a/arch/x86/entry/vdso/vdso32-setup.c +++ b/arch/x86/entry/vdso/vdso32-setup.c @@ -10,6 +10,7 @@ #include <linux/smp.h> #include <linux/kernel.h> #include <linux/mm_types.h> +#include <linux/elf.h> #include <asm/processor.h> #include <asm/vdso.h> diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 94491e4d21a7..01ec126c5969 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -301,6 +301,7 @@ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */ #define X86_FEATURE_PKU (16*32+ 3) /* Protection Keys for Userspace */ #define X86_FEATURE_OSPKE (16*32+ 4) /* OS Protection Keys Enable */ +#define X86_FEATURE_RDPID (16*32+ 22) /* RDPID instruction */ /* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */ #define X86_FEATURE_OVERFLOW_RECOV (17*32+0) /* MCA overflow recovery support */ diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h index f556c4843aa1..51e7533bbf79 100644 --- a/arch/x86/include/asm/vgtod.h +++ b/arch/x86/include/asm/vgtod.h @@ -83,8 +83,13 @@ static inline unsigned int __getcpu(void) * works on all CPUs. This is volatile so that it orders * correctly wrt barrier() and to keep gcc from cleverly * hoisting it out of the calling function. + * + * If RDPID is available, use it. */ - asm volatile ("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG)); + alternative_io ("lsl %[p],%[seg]", + ".byte 0xf3,0x0f,0xc7,0xf8", /* RDPID %eax/rax */ + X86_FEATURE_RDPID, + [p] "=a" (p), [seg] "r" (__PER_CPU_SEG)); return p; } diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 2116176c1721..37f5c2608844 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -560,9 +560,12 @@ static const struct sysfs_ops threshold_ops = { .store = store, }; +static void threshold_block_release(struct kobject *kobj); + static struct kobj_type threshold_ktype = { .sysfs_ops = &threshold_ops, .default_attrs = default_attrs, + .release = threshold_block_release, }; static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank, @@ -765,8 +768,12 @@ static int threshold_create_device(unsigned int cpu) return err; } -static void deallocate_threshold_block(unsigned int cpu, - unsigned int bank) +static void threshold_block_release(struct kobject *kobj) +{ + kfree(to_block(kobj)); +} + +static void deallocate_threshold_block(unsigned int cpu, unsigned int bank) { struct threshold_block *pos = NULL; struct threshold_block *tmp = NULL; @@ -776,13 +783,11 @@ static void deallocate_threshold_block(unsigned int cpu, return; list_for_each_entry_safe(pos, tmp, &head->blocks->miscj, miscj) { - kobject_put(&pos->kobj); list_del(&pos->miscj); - kfree(pos); + kobject_put(&pos->kobj); } - kfree(per_cpu(threshold_banks, cpu)[bank]->blocks); - per_cpu(threshold_banks, cpu)[bank]->blocks = NULL; + kobject_put(&head->blocks->kobj); } static void __threshold_remove_blocks(struct threshold_bank *b) diff --git a/arch/x86/kernel/cpu/perf_event_amd_uncore.c b/arch/x86/kernel/cpu/perf_event_amd_uncore.c index 49742746a6c9..98e786a779fd 100644 --- a/arch/x86/kernel/cpu/perf_event_amd_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_amd_uncore.c @@ -181,21 +181,19 @@ static int amd_uncore_event_init(struct perf_event *event) return -ENOENT; /* - * NB and L2 counters (MSRs) are shared across all cores that share the - * same NB / L2 cache. Interrupts can be directed to a single target - * core, however, event counts generated by processes running on other - * cores cannot be masked out. So we do not support sampling and - * per-thread events. + * NB and Last level cache counters (MSRs) are shared across all cores + * that share the same NB / Last level cache. On family 16h and below, + * Interrupts can be directed to a single target core, however, event + * counts generated by processes running on other cores cannot be masked + * out. So we do not support sampling and per-thread events via + * CAP_NO_INTERRUPT, and we do not enable counter overflow interrupts: */ - if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK) - return -EINVAL; /* NB and L2 counters do not have usr/os/guest/host bits */ if (event->attr.exclude_user || event->attr.exclude_kernel || event->attr.exclude_host || event->attr.exclude_guest) return -EINVAL; - /* and we do not enable counter overflow interrupts */ hwc->config = event->attr.config & AMD64_RAW_EVENT_MASK_NB; hwc->idx = -1; @@ -271,6 +269,7 @@ static struct pmu amd_nb_pmu = { .start = amd_uncore_start, .stop = amd_uncore_stop, .read = amd_uncore_read, + .capabilities = PERF_PMU_CAP_NO_INTERRUPT, }; static struct pmu amd_l2_pmu = { @@ -282,6 +281,7 @@ static struct pmu amd_l2_pmu = { .start = amd_uncore_start, .stop = amd_uncore_stop, .read = amd_uncore_read, + .capabilities = PERF_PMU_CAP_NO_INTERRUPT, }; static struct amd_uncore *amd_uncore_alloc(unsigned int cpu) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index f4795f5c579d..f876414ca8a3 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -267,13 +267,18 @@ static int __do_cpuid_ent_emulated(struct kvm_cpuid_entry2 *entry, { switch (func) { case 0: - entry->eax = 1; /* only one leaf currently */ + entry->eax = 7; ++*nent; break; case 1: entry->ecx = F(MOVBE); ++*nent; break; + case 7: + entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; + if (index == 0) + entry->ecx = F(RDPID); + ++*nent; default: break; } diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index ffbdd201c1f1..466028623e1a 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -3519,6 +3519,16 @@ static int em_cwd(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } +static int em_rdpid(struct x86_emulate_ctxt *ctxt) +{ + u64 tsc_aux = 0; + + if (ctxt->ops->get_msr(ctxt, MSR_TSC_AUX, &tsc_aux)) + return emulate_gp(ctxt, 0); + ctxt->dst.val = tsc_aux; + return X86EMUL_CONTINUE; +} + static int em_rdtsc(struct x86_emulate_ctxt *ctxt) { u64 tsc = 0; @@ -4379,10 +4389,20 @@ static const struct opcode group8[] = { F(DstMem | SrcImmByte | Lock | PageTable, em_btc), }; +/* + * The "memory" destination is actually always a register, since we come + * from the register case of group9. + */ +static const struct gprefix pfx_0f_c7_7 = { + N, N, N, II(DstMem | ModRM | Op3264 | EmulateOnUD, em_rdpid, rdtscp), +}; + + static const struct group_dual group9 = { { N, I(DstMem64 | Lock | PageTable, em_cmpxchg8b), N, N, N, N, N, N, }, { - N, N, N, N, N, N, N, N, + N, N, N, N, N, N, N, + GP(0, &pfx_0f_c7_7), } }; static const struct opcode group11[] = { @@ -4990,6 +5010,7 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len) ctxt->fetch.ptr = ctxt->fetch.data; ctxt->fetch.end = ctxt->fetch.data + insn_len; ctxt->opcode_len = 1; + ctxt->intercept = x86_intercept_none; if (insn_len > 0) memcpy(ctxt->fetch.data, insn, insn_len); else { diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index ce8c4ae25c15..078b2176f2a2 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -536,9 +536,11 @@ static inline bool pv_eoi_enabled(struct kvm_vcpu *vcpu) static bool pv_eoi_get_pending(struct kvm_vcpu *vcpu) { u8 val; - if (pv_eoi_get_user(vcpu, &val) < 0) + if (pv_eoi_get_user(vcpu, &val) < 0) { apic_debug("Can't read EOI MSR value: 0x%llx\n", (unsigned long long)vcpu->arch.pv_eoi.msr_val); + return false; + } return val & 0x1; } diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 6c2b45f5d501..78daf891abec 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -4275,6 +4275,26 @@ static bool cs_ss_rpl_check(struct kvm_vcpu *vcpu) (ss.selector & SEGMENT_RPL_MASK)); } +static bool nested_vmx_check_io_bitmaps(struct kvm_vcpu *vcpu, + unsigned int port, int size); +static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu, + struct vmcs12 *vmcs12) +{ + unsigned long exit_qualification; + unsigned short port; + int size; + + if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS)) + return nested_cpu_has(vmcs12, CPU_BASED_UNCOND_IO_EXITING); + + exit_qualification = vmcs_readl(EXIT_QUALIFICATION); + + port = exit_qualification >> 16; + size = (exit_qualification & 7) + 1; + + return nested_vmx_check_io_bitmaps(vcpu, port, size); +} + /* * Check if guest state is valid. Returns true if valid, false if * not. @@ -7624,23 +7644,17 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { static const int kvm_vmx_max_exit_handlers = ARRAY_SIZE(kvm_vmx_exit_handlers); -static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu, - struct vmcs12 *vmcs12) +/* + * Return true if an IO instruction with the specified port and size should cause + * a VM-exit into L1. + */ +bool nested_vmx_check_io_bitmaps(struct kvm_vcpu *vcpu, unsigned int port, + int size) { - unsigned long exit_qualification; + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); gpa_t bitmap, last_bitmap; - unsigned int port; - int size; u8 b; - if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS)) - return nested_cpu_has(vmcs12, CPU_BASED_UNCOND_IO_EXITING); - - exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - - port = exit_qualification >> 16; - size = (exit_qualification & 7) + 1; - last_bitmap = (gpa_t)-1; b = -1; @@ -10740,11 +10754,71 @@ static void nested_vmx_entry_failure(struct kvm_vcpu *vcpu, to_vmx(vcpu)->nested.sync_shadow_vmcs = true; } +static int vmx_check_intercept_io(struct kvm_vcpu *vcpu, + struct x86_instruction_info *info) +{ + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + unsigned short port; + bool intercept; + int size; + + if (info->intercept == x86_intercept_in || + info->intercept == x86_intercept_ins) { + port = info->src_val; + size = info->dst_bytes; + } else { + port = info->dst_val; + size = info->src_bytes; + } + + /* + * If the 'use IO bitmaps' VM-execution control is 0, IO instruction + * VM-exits depend on the 'unconditional IO exiting' VM-execution + * control. + * + * Otherwise, IO instruction VM-exits are controlled by the IO bitmaps. + */ + if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS)) + intercept = nested_cpu_has(vmcs12, + CPU_BASED_UNCOND_IO_EXITING); + else + intercept = nested_vmx_check_io_bitmaps(vcpu, port, size); + + return intercept ? X86EMUL_UNHANDLEABLE : X86EMUL_CONTINUE; +} + static int vmx_check_intercept(struct kvm_vcpu *vcpu, struct x86_instruction_info *info, enum x86_intercept_stage stage) { - return X86EMUL_CONTINUE; + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + + switch (info->intercept) { + /* + * RDPID causes #UD if disabled through secondary execution controls. + * Because it is marked as EmulateOnUD, we need to intercept it here. + */ + case x86_intercept_rdtscp: + if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDTSCP)) { + ctxt->exception.vector = UD_VECTOR; + ctxt->exception.error_code_valid = false; + return X86EMUL_PROPAGATE_FAULT; + } + break; + + case x86_intercept_in: + case x86_intercept_ins: + case x86_intercept_out: + case x86_intercept_outs: + return vmx_check_intercept_io(vcpu, info); + + /* TODO: check more intercepts... */ + default: + break; + } + + return X86EMUL_UNHANDLEABLE; } static void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c deleted file mode 100644 index 3791ce8d269e..000000000000 --- a/arch/x86/kvm/vmx/vmx.c +++ /dev/null @@ -1,8033 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Kernel-based Virtual Machine driver for Linux - * - * This module enables machines with Intel VT-x extensions to run virtual - * machines without emulation or binary translation. - * - * Copyright (C) 2006 Qumranet, Inc. - * Copyright 2010 Red Hat, Inc. and/or its affiliates. - * - * Authors: - * Avi Kivity <avi@qumranet.com> - * Yaniv Kamay <yaniv@qumranet.com> - */ - -#include <linux/frame.h> -#include <linux/highmem.h> -#include <linux/hrtimer.h> -#include <linux/kernel.h> -#include <linux/kvm_host.h> -#include <linux/module.h> -#include <linux/moduleparam.h> -#include <linux/mod_devicetable.h> -#include <linux/mm.h> -#include <linux/sched.h> -#include <linux/sched/smt.h> -#include <linux/slab.h> -#include <linux/tboot.h> -#include <linux/trace_events.h> - -#include <asm/apic.h> -#include <asm/asm.h> -#include <asm/cpu.h> -#include <asm/debugreg.h> -#include <asm/desc.h> -#include <asm/fpu/internal.h> -#include <asm/io.h> -#include <asm/irq_remapping.h> -#include <asm/kexec.h> -#include <asm/perf_event.h> -#include <asm/mce.h> -#include <asm/mmu_context.h> -#include <asm/mshyperv.h> -#include <asm/spec-ctrl.h> -#include <asm/virtext.h> -#include <asm/vmx.h> - -#include "capabilities.h" -#include "cpuid.h" -#include "evmcs.h" -#include "irq.h" -#include "kvm_cache_regs.h" -#include "lapic.h" -#include "mmu.h" -#include "nested.h" -#include "ops.h" -#include "pmu.h" -#include "trace.h" -#include "vmcs.h" -#include "vmcs12.h" -#include "vmx.h" -#include "x86.h" - -MODULE_AUTHOR("Qumranet"); -MODULE_LICENSE("GPL"); - -static const struct x86_cpu_id vmx_cpu_id[] = { - X86_FEATURE_MATCH(X86_FEATURE_VMX), - {} -}; -MODULE_DEVICE_TABLE(x86cpu, vmx_cpu_id); - -bool __read_mostly enable_vpid = 1; -module_param_named(vpid, enable_vpid, bool, 0444); - -static bool __read_mostly enable_vnmi = 1; -module_param_named(vnmi, enable_vnmi, bool, S_IRUGO); - -bool __read_mostly flexpriority_enabled = 1; -module_param_named(flexpriority, flexpriority_enabled, bool, S_IRUGO); - -bool __read_mostly enable_ept = 1; -module_param_named(ept, enable_ept, bool, S_IRUGO); - -bool __read_mostly enable_unrestricted_guest = 1; -module_param_named(unrestricted_guest, - enable_unrestricted_guest, bool, S_IRUGO); - -bool __read_mostly enable_ept_ad_bits = 1; -module_param_named(eptad, enable_ept_ad_bits, bool, S_IRUGO); - -static bool __read_mostly emulate_invalid_guest_state = true; -module_param(emulate_invalid_guest_state, bool, S_IRUGO); - -static bool __read_mostly fasteoi = 1; -module_param(fasteoi, bool, S_IRUGO); - -static bool __read_mostly enable_apicv = 1; -module_param(enable_apicv, bool, S_IRUGO); - -/* - * If nested=1, nested virtualization is supported, i.e., guests may use - * VMX and be a hypervisor for its own guests. If nested=0, guests may not - * use VMX instructions. - */ -static bool __read_mostly nested = 1; -module_param(nested, bool, S_IRUGO); - -bool __read_mostly enable_pml = 1; -module_param_named(pml, enable_pml, bool, S_IRUGO); - -static bool __read_mostly dump_invalid_vmcs = 0; -module_param(dump_invalid_vmcs, bool, 0644); - -#define MSR_BITMAP_MODE_X2APIC 1 -#define MSR_BITMAP_MODE_X2APIC_APICV 2 - -#define KVM_VMX_TSC_MULTIPLIER_MAX 0xffffffffffffffffULL - -/* Guest_tsc -> host_tsc conversion requires 64-bit division. */ -static int __read_mostly cpu_preemption_timer_multi; -static bool __read_mostly enable_preemption_timer = 1; -#ifdef CONFIG_X86_64 -module_param_named(preemption_timer, enable_preemption_timer, bool, S_IRUGO); -#endif - -#define KVM_VM_CR0_ALWAYS_OFF (X86_CR0_NW | X86_CR0_CD) -#define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST X86_CR0_NE -#define KVM_VM_CR0_ALWAYS_ON \ - (KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST | \ - X86_CR0_WP | X86_CR0_PG | X86_CR0_PE) -#define KVM_CR4_GUEST_OWNED_BITS \ - (X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR \ - | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_TSD) - -#define KVM_VM_CR4_ALWAYS_ON_UNRESTRICTED_GUEST X86_CR4_VMXE -#define KVM_PMODE_VM_CR4_ALWAYS_ON (X86_CR4_PAE | X86_CR4_VMXE) -#define KVM_RMODE_VM_CR4_ALWAYS_ON (X86_CR4_VME | X86_CR4_PAE | X86_CR4_VMXE) - -#define RMODE_GUEST_OWNED_EFLAGS_BITS (~(X86_EFLAGS_IOPL | X86_EFLAGS_VM)) - -#define MSR_IA32_RTIT_STATUS_MASK (~(RTIT_STATUS_FILTEREN | \ - RTIT_STATUS_CONTEXTEN | RTIT_STATUS_TRIGGEREN | \ - RTIT_STATUS_ERROR | RTIT_STATUS_STOPPED | \ - RTIT_STATUS_BYTECNT)) - -#define MSR_IA32_RTIT_OUTPUT_BASE_MASK \ - (~((1UL << cpuid_query_maxphyaddr(vcpu)) - 1) | 0x7f) - -/* - * These 2 parameters are used to config the controls for Pause-Loop Exiting: - * ple_gap: upper bound on the amount of time between two successive - * executions of PAUSE in a loop. Also indicate if ple enabled. - * According to test, this time is usually smaller than 128 cycles. - * ple_window: upper bound on the amount of time a guest is allowed to execute - * in a PAUSE loop. Tests indicate that most spinlocks are held for - * less than 2^12 cycles - * Time is measured based on a counter that runs at the same rate as the TSC, - * refer SDM volume 3b section 21.6.13 & 22.1.3. - */ -static unsigned int ple_gap = KVM_DEFAULT_PLE_GAP; -module_param(ple_gap, uint, 0444); - -static unsigned int ple_window = KVM_VMX_DEFAULT_PLE_WINDOW; -module_param(ple_window, uint, 0444); - -/* Default doubles per-vcpu window every exit. */ -static unsigned int ple_window_grow = KVM_DEFAULT_PLE_WINDOW_GROW; -module_param(ple_window_grow, uint, 0444); - -/* Default resets per-vcpu window every exit to ple_window. */ -static unsigned int ple_window_shrink = KVM_DEFAULT_PLE_WINDOW_SHRINK; -module_param(ple_window_shrink, uint, 0444); - -/* Default is to compute the maximum so we can never overflow. */ -static unsigned int ple_window_max = KVM_VMX_DEFAULT_PLE_WINDOW_MAX; -module_param(ple_window_max, uint, 0444); - -/* Default is SYSTEM mode, 1 for host-guest mode */ -int __read_mostly pt_mode = PT_MODE_SYSTEM; -module_param(pt_mode, int, S_IRUGO); - -static DEFINE_STATIC_KEY_FALSE(vmx_l1d_should_flush); -static DEFINE_STATIC_KEY_FALSE(vmx_l1d_flush_cond); -static DEFINE_MUTEX(vmx_l1d_flush_mutex); - -/* Storage for pre module init parameter parsing */ -static enum vmx_l1d_flush_state __read_mostly vmentry_l1d_flush_param = VMENTER_L1D_FLUSH_AUTO; - -static const struct { - const char *option; - bool for_parse; -} vmentry_l1d_param[] = { - [VMENTER_L1D_FLUSH_AUTO] = {"auto", true}, - [VMENTER_L1D_FLUSH_NEVER] = {"never", true}, - [VMENTER_L1D_FLUSH_COND] = {"cond", true}, - [VMENTER_L1D_FLUSH_ALWAYS] = {"always", true}, - [VMENTER_L1D_FLUSH_EPT_DISABLED] = {"EPT disabled", false}, - [VMENTER_L1D_FLUSH_NOT_REQUIRED] = {"not required", false}, -}; - -#define L1D_CACHE_ORDER 4 -static void *vmx_l1d_flush_pages; - -static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf) -{ - struct page *page; - unsigned int i; - - if (!boot_cpu_has_bug(X86_BUG_L1TF)) { - l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_NOT_REQUIRED; - return 0; - } - - if (!enable_ept) { - l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_EPT_DISABLED; - return 0; - } - - if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) { - u64 msr; - - rdmsrl(MSR_IA32_ARCH_CAPABILITIES, msr); - if (msr & ARCH_CAP_SKIP_VMENTRY_L1DFLUSH) { - l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_NOT_REQUIRED; - return 0; - } - } - - /* If set to auto use the default l1tf mitigation method */ - if (l1tf == VMENTER_L1D_FLUSH_AUTO) { - switch (l1tf_mitigation) { - case L1TF_MITIGATION_OFF: - l1tf = VMENTER_L1D_FLUSH_NEVER; - break; - case L1TF_MITIGATION_FLUSH_NOWARN: - case L1TF_MITIGATION_FLUSH: - case L1TF_MITIGATION_FLUSH_NOSMT: - l1tf = VMENTER_L1D_FLUSH_COND; - break; - case L1TF_MITIGATION_FULL: - case L1TF_MITIGATION_FULL_FORCE: - l1tf = VMENTER_L1D_FLUSH_ALWAYS; - break; - } - } else if (l1tf_mitigation == L1TF_MITIGATION_FULL_FORCE) { - l1tf = VMENTER_L1D_FLUSH_ALWAYS; - } - - if (l1tf != VMENTER_L1D_FLUSH_NEVER && !vmx_l1d_flush_pages && - !boot_cpu_has(X86_FEATURE_FLUSH_L1D)) { - /* - * This allocation for vmx_l1d_flush_pages is not tied to a VM - * lifetime and so should not be charged to a memcg. - */ - page = alloc_pages(GFP_KERNEL, L1D_CACHE_ORDER); - if (!page) - return -ENOMEM; - vmx_l1d_flush_pages = page_address(page); - - /* - * Initialize each page with a different pattern in - * order to protect against KSM in the nested - * virtualization case. - */ - for (i = 0; i < 1u << L1D_CACHE_ORDER; ++i) { - memset(vmx_l1d_flush_pages + i * PAGE_SIZE, i + 1, - PAGE_SIZE); - } - } - - l1tf_vmx_mitigation = l1tf; - - if (l1tf != VMENTER_L1D_FLUSH_NEVER) - static_branch_enable(&vmx_l1d_should_flush); - else - static_branch_disable(&vmx_l1d_should_flush); - - if (l1tf == VMENTER_L1D_FLUSH_COND) - static_branch_enable(&vmx_l1d_flush_cond); - else - static_branch_disable(&vmx_l1d_flush_cond); - return 0; -} - -static int vmentry_l1d_flush_parse(const char *s) -{ - unsigned int i; - - if (s) { - for (i = 0; i < ARRAY_SIZE(vmentry_l1d_param); i++) { - if (vmentry_l1d_param[i].for_parse && - sysfs_streq(s, vmentry_l1d_param[i].option)) - return i; - } - } - return -EINVAL; -} - -static int vmentry_l1d_flush_set(const char *s, const struct kernel_param *kp) -{ - int l1tf, ret; - - l1tf = vmentry_l1d_flush_parse(s); - if (l1tf < 0) - return l1tf; - - if (!boot_cpu_has(X86_BUG_L1TF)) - return 0; - - /* - * Has vmx_init() run already? If not then this is the pre init - * parameter parsing. In that case just store the value and let - * vmx_init() do the proper setup after enable_ept has been - * established. - */ - if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_AUTO) { - vmentry_l1d_flush_param = l1tf; - return 0; - } - - mutex_lock(&vmx_l1d_flush_mutex); - ret = vmx_setup_l1d_flush(l1tf); - mutex_unlock(&vmx_l1d_flush_mutex); - return ret; -} - -static int vmentry_l1d_flush_get(char *s, const struct kernel_param *kp) -{ - if (WARN_ON_ONCE(l1tf_vmx_mitigation >= ARRAY_SIZE(vmentry_l1d_param))) - return sprintf(s, "???\n"); - - return sprintf(s, "%s\n", vmentry_l1d_param[l1tf_vmx_mitigation].option); -} - -static const struct kernel_param_ops vmentry_l1d_flush_ops = { - .set = vmentry_l1d_flush_set, - .get = vmentry_l1d_flush_get, -}; -module_param_cb(vmentry_l1d_flush, &vmentry_l1d_flush_ops, NULL, 0644); - -static bool guest_state_valid(struct kvm_vcpu *vcpu); -static u32 vmx_segment_access_rights(struct kvm_segment *var); -static __always_inline void vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, - u32 msr, int type); - -void vmx_vmexit(void); - -#define vmx_insn_failed(fmt...) \ -do { \ - WARN_ONCE(1, fmt); \ - pr_warn_ratelimited(fmt); \ -} while (0) - -asmlinkage void vmread_error(unsigned long field, bool fault) -{ - if (fault) - kvm_spurious_fault(); - else - vmx_insn_failed("kvm: vmread failed: field=%lx\n", field); -} - -noinline void vmwrite_error(unsigned long field, unsigned long value) -{ - vmx_insn_failed("kvm: vmwrite failed: field=%lx val=%lx err=%d\n", - field, value, vmcs_read32(VM_INSTRUCTION_ERROR)); -} - -noinline void vmclear_error(struct vmcs *vmcs, u64 phys_addr) -{ - vmx_insn_failed("kvm: vmclear failed: %p/%llx\n", vmcs, phys_addr); -} - -noinline void vmptrld_error(struct vmcs *vmcs, u64 phys_addr) -{ - vmx_insn_failed("kvm: vmptrld failed: %p/%llx\n", vmcs, phys_addr); -} - -noinline void invvpid_error(unsigned long ext, u16 vpid, gva_t gva) -{ - vmx_insn_failed("kvm: invvpid failed: ext=0x%lx vpid=%u gva=0x%lx\n", - ext, vpid, gva); -} - -noinline void invept_error(unsigned long ext, u64 eptp, gpa_t gpa) -{ - vmx_insn_failed("kvm: invept failed: ext=0x%lx eptp=%llx gpa=0x%llx\n", - ext, eptp, gpa); -} - -static DEFINE_PER_CPU(struct vmcs *, vmxarea); -DEFINE_PER_CPU(struct vmcs *, current_vmcs); -/* - * We maintain a per-CPU linked-list of VMCS loaded on that CPU. This is needed - * when a CPU is brought down, and we need to VMCLEAR all VMCSs loaded on it. - */ -static DEFINE_PER_CPU(struct list_head, loaded_vmcss_on_cpu); - -/* - * We maintian a per-CPU linked-list of vCPU, so in wakeup_handler() we - * can find which vCPU should be waken up. - */ -static DEFINE_PER_CPU(struct list_head, blocked_vcpu_on_cpu); -static DEFINE_PER_CPU(spinlock_t, blocked_vcpu_on_cpu_lock); - -static DECLARE_BITMAP(vmx_vpid_bitmap, VMX_NR_VPIDS); -static DEFINE_SPINLOCK(vmx_vpid_lock); - -struct vmcs_config vmcs_config; -struct vmx_capability vmx_capability; - -#define VMX_SEGMENT_FIELD(seg) \ - [VCPU_SREG_##seg] = { \ - .selector = GUEST_##seg##_SELECTOR, \ - .base = GUEST_##seg##_BASE, \ - .limit = GUEST_##seg##_LIMIT, \ - .ar_bytes = GUEST_##seg##_AR_BYTES, \ - } - -static const struct kvm_vmx_segment_field { - unsigned selector; - unsigned base; - unsigned limit; - unsigned ar_bytes; -} kvm_vmx_segment_fields[] = { - VMX_SEGMENT_FIELD(CS), - VMX_SEGMENT_FIELD(DS), - VMX_SEGMENT_FIELD(ES), - VMX_SEGMENT_FIELD(FS), - VMX_SEGMENT_FIELD(GS), - VMX_SEGMENT_FIELD(SS), - VMX_SEGMENT_FIELD(TR), - VMX_SEGMENT_FIELD(LDTR), -}; - -u64 host_efer; -static unsigned long host_idt_base; - -/* - * Though SYSCALL is only supported in 64-bit mode on Intel CPUs, kvm - * will emulate SYSCALL in legacy mode if the vendor string in guest - * CPUID.0:{EBX,ECX,EDX} is "AuthenticAMD" or "AMDisbetter!" To - * support this emulation, IA32_STAR must always be included in - * vmx_msr_index[], even in i386 builds. - */ -const u32 vmx_msr_index[] = { -#ifdef CONFIG_X86_64 - MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR, -#endif - MSR_EFER, MSR_TSC_AUX, MSR_STAR, - MSR_IA32_TSX_CTRL, -}; - -#if IS_ENABLED(CONFIG_HYPERV) -static bool __read_mostly enlightened_vmcs = true; -module_param(enlightened_vmcs, bool, 0444); - -/* check_ept_pointer() should be under protection of ept_pointer_lock. */ -static void check_ept_pointer_match(struct kvm *kvm) -{ - struct kvm_vcpu *vcpu; - u64 tmp_eptp = INVALID_PAGE; - int i; - - kvm_for_each_vcpu(i, vcpu, kvm) { - if (!VALID_PAGE(tmp_eptp)) { - tmp_eptp = to_vmx(vcpu)->ept_pointer; - } else if (tmp_eptp != to_vmx(vcpu)->ept_pointer) { - to_kvm_vmx(kvm)->ept_pointers_match - = EPT_POINTERS_MISMATCH; - return; - } - } - - to_kvm_vmx(kvm)->ept_pointers_match = EPT_POINTERS_MATCH; -} - -static int kvm_fill_hv_flush_list_func(struct hv_guest_mapping_flush_list *flush, - void *data) -{ - struct kvm_tlb_range *range = data; - - return hyperv_fill_flush_guest_mapping_list(flush, range->start_gfn, - range->pages); -} - -static inline int __hv_remote_flush_tlb_with_range(struct kvm *kvm, - struct kvm_vcpu *vcpu, struct kvm_tlb_range *range) -{ - u64 ept_pointer = to_vmx(vcpu)->ept_pointer; - - /* - * FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE hypercall needs address - * of the base of EPT PML4 table, strip off EPT configuration - * information. - */ - if (range) - return hyperv_flush_guest_mapping_range(ept_pointer & PAGE_MASK, - kvm_fill_hv_flush_list_func, (void *)range); - else - return hyperv_flush_guest_mapping(ept_pointer & PAGE_MASK); -} - -static int hv_remote_flush_tlb_with_range(struct kvm *kvm, - struct kvm_tlb_range *range) -{ - struct kvm_vcpu *vcpu; - int ret = 0, i; - - spin_lock(&to_kvm_vmx(kvm)->ept_pointer_lock); - - if (to_kvm_vmx(kvm)->ept_pointers_match == EPT_POINTERS_CHECK) - check_ept_pointer_match(kvm); - - if (to_kvm_vmx(kvm)->ept_pointers_match != EPT_POINTERS_MATCH) { - kvm_for_each_vcpu(i, vcpu, kvm) { - /* If ept_pointer is invalid pointer, bypass flush request. */ - if (VALID_PAGE(to_vmx(vcpu)->ept_pointer)) - ret |= __hv_remote_flush_tlb_with_range( - kvm, vcpu, range); - } - } else { - ret = __hv_remote_flush_tlb_with_range(kvm, - kvm_get_vcpu(kvm, 0), range); - } - - spin_unlock(&to_kvm_vmx(kvm)->ept_pointer_lock); - return ret; -} -static int hv_remote_flush_tlb(struct kvm *kvm) -{ - return hv_remote_flush_tlb_with_range(kvm, NULL); -} - -static int hv_enable_direct_tlbflush(struct kvm_vcpu *vcpu) -{ - struct hv_enlightened_vmcs *evmcs; - struct hv_partition_assist_pg **p_hv_pa_pg = - &vcpu->kvm->arch.hyperv.hv_pa_pg; - /* - * Synthetic VM-Exit is not enabled in current code and so All - * evmcs in singe VM shares same assist page. - */ - if (!*p_hv_pa_pg) - *p_hv_pa_pg = kzalloc(PAGE_SIZE, GFP_KERNEL); - - if (!*p_hv_pa_pg) - return -ENOMEM; - - evmcs = (struct hv_enlightened_vmcs *)to_vmx(vcpu)->loaded_vmcs->vmcs; - - evmcs->partition_assist_page = - __pa(*p_hv_pa_pg); - evmcs->hv_vm_id = (unsigned long)vcpu->kvm; - evmcs->hv_enlightenments_control.nested_flush_hypercall = 1; - - return 0; -} - -#endif /* IS_ENABLED(CONFIG_HYPERV) */ - -/* - * Comment's format: document - errata name - stepping - processor name. - * Refer from - * https://www.virtualbox.org/svn/vbox/trunk/src/VBox/VMM/VMMR0/HMR0.cpp - */ -static u32 vmx_preemption_cpu_tfms[] = { -/* 323344.pdf - BA86 - D0 - Xeon 7500 Series */ -0x000206E6, -/* 323056.pdf - AAX65 - C2 - Xeon L3406 */ -/* 322814.pdf - AAT59 - C2 - i7-600, i5-500, i5-400 and i3-300 Mobile */ -/* 322911.pdf - AAU65 - C2 - i5-600, i3-500 Desktop and Pentium G6950 */ -0x00020652, -/* 322911.pdf - AAU65 - K0 - i5-600, i3-500 Desktop and Pentium G6950 */ -0x00020655, -/* 322373.pdf - AAO95 - B1 - Xeon 3400 Series */ -/* 322166.pdf - AAN92 - B1 - i7-800 and i5-700 Desktop */ -/* - * 320767.pdf - AAP86 - B1 - - * i7-900 Mobile Extreme, i7-800 and i7-700 Mobile - */ -0x000106E5, -/* 321333.pdf - AAM126 - C0 - Xeon 3500 */ -0x000106A0, -/* 321333.pdf - AAM126 - C1 - Xeon 3500 */ -0x000106A1, -/* 320836.pdf - AAJ124 - C0 - i7-900 Desktop Extreme and i7-900 Desktop */ -0x000106A4, - /* 321333.pdf - AAM126 - D0 - Xeon 3500 */ - /* 321324.pdf - AAK139 - D0 - Xeon 5500 */ - /* 320836.pdf - AAJ124 - D0 - i7-900 Extreme and i7-900 Desktop */ -0x000106A5, - /* Xeon E3-1220 V2 */ -0x000306A8, -}; - -static inline bool cpu_has_broken_vmx_preemption_timer(void) -{ - u32 eax = cpuid_eax(0x00000001), i; - - /* Clear the reserved bits */ - eax &= ~(0x3U << 14 | 0xfU << 28); - for (i = 0; i < ARRAY_SIZE(vmx_preemption_cpu_tfms); i++) - if (eax == vmx_preemption_cpu_tfms[i]) - return true; - - return false; -} - -static inline bool cpu_need_virtualize_apic_accesses(struct kvm_vcpu *vcpu) -{ - return flexpriority_enabled && lapic_in_kernel(vcpu); -} - -static inline bool report_flexpriority(void) -{ - return flexpriority_enabled; -} - -static inline int __find_msr_index(struct vcpu_vmx *vmx, u32 msr) -{ - int i; - - for (i = 0; i < vmx->nmsrs; ++i) - if (vmx_msr_index[vmx->guest_msrs[i].index] == msr) - return i; - return -1; -} - -struct shared_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr) -{ - int i; - - i = __find_msr_index(vmx, msr); - if (i >= 0) - return &vmx->guest_msrs[i]; - return NULL; -} - -static int vmx_set_guest_msr(struct vcpu_vmx *vmx, struct shared_msr_entry *msr, u64 data) -{ - int ret = 0; - - u64 old_msr_data = msr->data; - msr->data = data; - if (msr - vmx->guest_msrs < vmx->save_nmsrs) { - preempt_disable(); - ret = kvm_set_shared_msr(msr->index, msr->data, - msr->mask); - preempt_enable(); - if (ret) - msr->data = old_msr_data; - } - return ret; -} - -void loaded_vmcs_init(struct loaded_vmcs *loaded_vmcs) -{ - vmcs_clear(loaded_vmcs->vmcs); - if (loaded_vmcs->shadow_vmcs && loaded_vmcs->launched) - vmcs_clear(loaded_vmcs->shadow_vmcs); - loaded_vmcs->cpu = -1; - loaded_vmcs->launched = 0; -} - -#ifdef CONFIG_KEXEC_CORE -/* - * This bitmap is used to indicate whether the vmclear - * operation is enabled on all cpus. All disabled by - * default. - */ -static cpumask_t crash_vmclear_enabled_bitmap = CPU_MASK_NONE; - -static inline void crash_enable_local_vmclear(int cpu) -{ - cpumask_set_cpu(cpu, &crash_vmclear_enabled_bitmap); -} - -static inline void crash_disable_local_vmclear(int cpu) -{ - cpumask_clear_cpu(cpu, &crash_vmclear_enabled_bitmap); -} - -static inline int crash_local_vmclear_enabled(int cpu) -{ - return cpumask_test_cpu(cpu, &crash_vmclear_enabled_bitmap); -} - -static void crash_vmclear_local_loaded_vmcss(void) -{ - int cpu = raw_smp_processor_id(); - struct loaded_vmcs *v; - - if (!crash_local_vmclear_enabled(cpu)) - return; - - list_for_each_entry(v, &per_cpu(loaded_vmcss_on_cpu, cpu), - loaded_vmcss_on_cpu_link) - vmcs_clear(v->vmcs); -} -#else -static inline void crash_enable_local_vmclear(int cpu) { } -static inline void crash_disable_local_vmclear(int cpu) { } -#endif /* CONFIG_KEXEC_CORE */ - -static void __loaded_vmcs_clear(void *arg) -{ - struct loaded_vmcs *loaded_vmcs = arg; - int cpu = raw_smp_processor_id(); - - if (loaded_vmcs->cpu != cpu) - return; /* vcpu migration can race with cpu offline */ - if (per_cpu(current_vmcs, cpu) == loaded_vmcs->vmcs) - per_cpu(current_vmcs, cpu) = NULL; - crash_disable_local_vmclear(cpu); - list_del(&loaded_vmcs->loaded_vmcss_on_cpu_link); - - /* - * we should ensure updating loaded_vmcs->loaded_vmcss_on_cpu_link - * is before setting loaded_vmcs->vcpu to -1 which is done in - * loaded_vmcs_init. Otherwise, other cpu can see vcpu = -1 fist - * then adds the vmcs into percpu list before it is deleted. - */ - smp_wmb(); - - loaded_vmcs_init(loaded_vmcs); - crash_enable_local_vmclear(cpu); -} - -void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs) -{ - int cpu = loaded_vmcs->cpu; - - if (cpu != -1) - smp_call_function_single(cpu, - __loaded_vmcs_clear, loaded_vmcs, 1); -} - -static bool vmx_segment_cache_test_set(struct vcpu_vmx *vmx, unsigned seg, - unsigned field) -{ - bool ret; - u32 mask = 1 << (seg * SEG_FIELD_NR + field); - - if (!kvm_register_is_available(&vmx->vcpu, VCPU_EXREG_SEGMENTS)) { - kvm_register_mark_available(&vmx->vcpu, VCPU_EXREG_SEGMENTS); - vmx->segment_cache.bitmask = 0; - } - ret = vmx->segment_cache.bitmask & mask; - vmx->segment_cache.bitmask |= mask; - return ret; -} - -static u16 vmx_read_guest_seg_selector(struct vcpu_vmx *vmx, unsigned seg) -{ - u16 *p = &vmx->segment_cache.seg[seg].selector; - - if (!vmx_segment_cache_test_set(vmx, seg, SEG_FIELD_SEL)) - *p = vmcs_read16(kvm_vmx_segment_fields[seg].selector); - return *p; -} - -static ulong vmx_read_guest_seg_base(struct vcpu_vmx *vmx, unsigned seg) -{ - ulong *p = &vmx->segment_cache.seg[seg].base; - - if (!vmx_segment_cache_test_set(vmx, seg, SEG_FIELD_BASE)) - *p = vmcs_readl(kvm_vmx_segment_fields[seg].base); - return *p; -} - -static u32 vmx_read_guest_seg_limit(struct vcpu_vmx *vmx, unsigned seg) -{ - u32 *p = &vmx->segment_cache.seg[seg].limit; - - if (!vmx_segment_cache_test_set(vmx, seg, SEG_FIELD_LIMIT)) - *p = vmcs_read32(kvm_vmx_segment_fields[seg].limit); - return *p; -} - -static u32 vmx_read_guest_seg_ar(struct vcpu_vmx *vmx, unsigned seg) -{ - u32 *p = &vmx->segment_cache.seg[seg].ar; - - if (!vmx_segment_cache_test_set(vmx, seg, SEG_FIELD_AR)) - *p = vmcs_read32(kvm_vmx_segment_fields[seg].ar_bytes); - return *p; -} - -void update_exception_bitmap(struct kvm_vcpu *vcpu) -{ - u32 eb; - - eb = (1u << PF_VECTOR) | (1u << UD_VECTOR) | (1u << MC_VECTOR) | - (1u << DB_VECTOR) | (1u << AC_VECTOR); - /* - * Guest access to VMware backdoor ports could legitimately - * trigger #GP because of TSS I/O permission bitmap. - * We intercept those #GP and allow access to them anyway - * as VMware does. - */ - if (enable_vmware_backdoor) - eb |= (1u << GP_VECTOR); - if ((vcpu->guest_debug & - (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP)) == - (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP)) - eb |= 1u << BP_VECTOR; - if (to_vmx(vcpu)->rmode.vm86_active) - eb = ~0; - if (enable_ept) - eb &= ~(1u << PF_VECTOR); /* bypass_guest_pf = 0 */ - - /* When we are running a nested L2 guest and L1 specified for it a - * certain exception bitmap, we must trap the same exceptions and pass - * them to L1. When running L2, we will only handle the exceptions - * specified above if L1 did not want them. - */ - if (is_guest_mode(vcpu)) - eb |= get_vmcs12(vcpu)->exception_bitmap; - - vmcs_write32(EXCEPTION_BITMAP, eb); -} - -/* - * Check if MSR is intercepted for currently loaded MSR bitmap. - */ -static bool msr_write_intercepted(struct kvm_vcpu *vcpu, u32 msr) -{ - unsigned long *msr_bitmap; - int f = sizeof(unsigned long); - - if (!cpu_has_vmx_msr_bitmap()) - return true; - - msr_bitmap = to_vmx(vcpu)->loaded_vmcs->msr_bitmap; - - if (msr <= 0x1fff) { - return !!test_bit(msr, msr_bitmap + 0x800 / f); - } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { - msr &= 0x1fff; - return !!test_bit(msr, msr_bitmap + 0xc00 / f); - } - - return true; -} - -static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx, - unsigned long entry, unsigned long exit) -{ - vm_entry_controls_clearbit(vmx, entry); - vm_exit_controls_clearbit(vmx, exit); -} - -int vmx_find_msr_index(struct vmx_msrs *m, u32 msr) -{ - unsigned int i; - - for (i = 0; i < m->nr; ++i) { - if (m->val[i].index == msr) - return i; - } - return -ENOENT; -} - -static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr) -{ - int i; - struct msr_autoload *m = &vmx->msr_autoload; - - switch (msr) { - case MSR_EFER: - if (cpu_has_load_ia32_efer()) { - clear_atomic_switch_msr_special(vmx, - VM_ENTRY_LOAD_IA32_EFER, - VM_EXIT_LOAD_IA32_EFER); - return; - } - break; - case MSR_CORE_PERF_GLOBAL_CTRL: - if (cpu_has_load_perf_global_ctrl()) { - clear_atomic_switch_msr_special(vmx, - VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL, - VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL); - return; - } - break; - } - i = vmx_find_msr_index(&m->guest, msr); - if (i < 0) - goto skip_guest; - --m->guest.nr; - m->guest.val[i] = m->guest.val[m->guest.nr]; - vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr); - -skip_guest: - i = vmx_find_msr_index(&m->host, msr); - if (i < 0) - return; - - --m->host.nr; - m->host.val[i] = m->host.val[m->host.nr]; - vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->host.nr); -} - -static void add_atomic_switch_msr_special(struct vcpu_vmx *vmx, - unsigned long entry, unsigned long exit, - unsigned long guest_val_vmcs, unsigned long host_val_vmcs, - u64 guest_val, u64 host_val) -{ - vmcs_write64(guest_val_vmcs, guest_val); - if (host_val_vmcs != HOST_IA32_EFER) - vmcs_write64(host_val_vmcs, host_val); - vm_entry_controls_setbit(vmx, entry); - vm_exit_controls_setbit(vmx, exit); -} - -static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr, - u64 guest_val, u64 host_val, bool entry_only) -{ - int i, j = 0; - struct msr_autoload *m = &vmx->msr_autoload; - - switch (msr) { - case MSR_EFER: - if (cpu_has_load_ia32_efer()) { - add_atomic_switch_msr_special(vmx, - VM_ENTRY_LOAD_IA32_EFER, - VM_EXIT_LOAD_IA32_EFER, - GUEST_IA32_EFER, - HOST_IA32_EFER, - guest_val, host_val); - return; - } - break; - case MSR_CORE_PERF_GLOBAL_CTRL: - if (cpu_has_load_perf_global_ctrl()) { - add_atomic_switch_msr_special(vmx, - VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL, - VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL, - GUEST_IA32_PERF_GLOBAL_CTRL, - HOST_IA32_PERF_GLOBAL_CTRL, - guest_val, host_val); - return; - } - break; - case MSR_IA32_PEBS_ENABLE: - /* PEBS needs a quiescent period after being disabled (to write - * a record). Disabling PEBS through VMX MSR swapping doesn't - * provide that period, so a CPU could write host's record into - * guest's memory. - */ - wrmsrl(MSR_IA32_PEBS_ENABLE, 0); - } - - i = vmx_find_msr_index(&m->guest, msr); - if (!entry_only) - j = vmx_find_msr_index(&m->host, msr); - - if ((i < 0 && m->guest.nr == NR_LOADSTORE_MSRS) || - (j < 0 && m->host.nr == NR_LOADSTORE_MSRS)) { - printk_once(KERN_WARNING "Not enough msr switch entries. " - "Can't add msr %x\n", msr); - return; - } - if (i < 0) { - i = m->guest.nr++; - vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr); - } - m->guest.val[i].index = msr; - m->guest.val[i].value = guest_val; - - if (entry_only) - return; - - if (j < 0) { - j = m->host.nr++; - vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->host.nr); - } - m->host.val[j].index = msr; - m->host.val[j].value = host_val; -} - -static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) -{ - u64 guest_efer = vmx->vcpu.arch.efer; - u64 ignore_bits = 0; - - /* Shadow paging assumes NX to be available. */ - if (!enable_ept) - guest_efer |= EFER_NX; - - /* - * LMA and LME handled by hardware; SCE meaningless outside long mode. - */ - ignore_bits |= EFER_SCE; -#ifdef CONFIG_X86_64 - ignore_bits |= EFER_LMA | EFER_LME; - /* SCE is meaningful only in long mode on Intel */ - if (guest_efer & EFER_LMA) - ignore_bits &= ~(u64)EFER_SCE; -#endif - - /* - * On EPT, we can't emulate NX, so we must switch EFER atomically. - * On CPUs that support "load IA32_EFER", always switch EFER - * atomically, since it's faster than switching it manually. - */ - if (cpu_has_load_ia32_efer() || - (enable_ept && ((vmx->vcpu.arch.efer ^ host_efer) & EFER_NX))) { - if (!(guest_efer & EFER_LMA)) - guest_efer &= ~EFER_LME; - if (guest_efer != host_efer) - add_atomic_switch_msr(vmx, MSR_EFER, - guest_efer, host_efer, false); - else - clear_atomic_switch_msr(vmx, MSR_EFER); - return false; - } else { - clear_atomic_switch_msr(vmx, MSR_EFER); - - guest_efer &= ~ignore_bits; - guest_efer |= host_efer & ignore_bits; - - vmx->guest_msrs[efer_offset].data = guest_efer; - vmx->guest_msrs[efer_offset].mask = ~ignore_bits; - - return true; - } -} - -#ifdef CONFIG_X86_32 -/* - * On 32-bit kernels, VM exits still load the FS and GS bases from the - * VMCS rather than the segment table. KVM uses this helper to figure - * out the current bases to poke them into the VMCS before entry. - */ -static unsigned long segment_base(u16 selector) -{ - struct desc_struct *table; - unsigned long v; - - if (!(selector & ~SEGMENT_RPL_MASK)) - return 0; - - table = get_current_gdt_ro(); - - if ((selector & SEGMENT_TI_MASK) == SEGMENT_LDT) { - u16 ldt_selector = kvm_read_ldt(); - - if (!(ldt_selector & ~SEGMENT_RPL_MASK)) - return 0; - - table = (struct desc_struct *)segment_base(ldt_selector); - } - v = get_desc_base(&table[selector >> 3]); - return v; -} -#endif - -static inline void pt_load_msr(struct pt_ctx *ctx, u32 addr_range) -{ - u32 i; - - wrmsrl(MSR_IA32_RTIT_STATUS, ctx->status); - wrmsrl(MSR_IA32_RTIT_OUTPUT_BASE, ctx->output_base); - wrmsrl(MSR_IA32_RTIT_OUTPUT_MASK, ctx->output_mask); - wrmsrl(MSR_IA32_RTIT_CR3_MATCH, ctx->cr3_match); - for (i = 0; i < addr_range; i++) { - wrmsrl(MSR_IA32_RTIT_ADDR0_A + i * 2, ctx->addr_a[i]); - wrmsrl(MSR_IA32_RTIT_ADDR0_B + i * 2, ctx->addr_b[i]); - } -} - -static inline void pt_save_msr(struct pt_ctx *ctx, u32 addr_range) -{ - u32 i; - - rdmsrl(MSR_IA32_RTIT_STATUS, ctx->status); - rdmsrl(MSR_IA32_RTIT_OUTPUT_BASE, ctx->output_base); - rdmsrl(MSR_IA32_RTIT_OUTPUT_MASK, ctx->output_mask); - rdmsrl(MSR_IA32_RTIT_CR3_MATCH, ctx->cr3_match); - for (i = 0; i < addr_range; i++) { - rdmsrl(MSR_IA32_RTIT_ADDR0_A + i * 2, ctx->addr_a[i]); - rdmsrl(MSR_IA32_RTIT_ADDR0_B + i * 2, ctx->addr_b[i]); - } -} - -static void pt_guest_enter(struct vcpu_vmx *vmx) -{ - if (pt_mode == PT_MODE_SYSTEM) - return; - - /* - * GUEST_IA32_RTIT_CTL is already set in the VMCS. - * Save host state before VM entry. - */ - rdmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl); - if (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) { - wrmsrl(MSR_IA32_RTIT_CTL, 0); - pt_save_msr(&vmx->pt_desc.host, vmx->pt_desc.addr_range); - pt_load_msr(&vmx->pt_desc.guest, vmx->pt_desc.addr_range); - } -} - -static void pt_guest_exit(struct vcpu_vmx *vmx) -{ - if (pt_mode == PT_MODE_SYSTEM) - return; - - if (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) { - pt_save_msr(&vmx->pt_desc.guest, vmx->pt_desc.addr_range); - pt_load_msr(&vmx->pt_desc.host, vmx->pt_desc.addr_range); - } - - /* Reload host state (IA32_RTIT_CTL will be cleared on VM exit). */ - wrmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl); -} - -void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel, - unsigned long fs_base, unsigned long gs_base) -{ - if (unlikely(fs_sel != host->fs_sel)) { - if (!(fs_sel & 7)) - vmcs_write16(HOST_FS_SELECTOR, fs_sel); - else - vmcs_write16(HOST_FS_SELECTOR, 0); - host->fs_sel = fs_sel; - } - if (unlikely(gs_sel != host->gs_sel)) { - if (!(gs_sel & 7)) - vmcs_write16(HOST_GS_SELECTOR, gs_sel); - else - vmcs_write16(HOST_GS_SELECTOR, 0); - host->gs_sel = gs_sel; - } - if (unlikely(fs_base != host->fs_base)) { - vmcs_writel(HOST_FS_BASE, fs_base); - host->fs_base = fs_base; - } - if (unlikely(gs_base != host->gs_base)) { - vmcs_writel(HOST_GS_BASE, gs_base); - host->gs_base = gs_base; - } -} - -void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - struct vmcs_host_state *host_state; -#ifdef CONFIG_X86_64 - int cpu = raw_smp_processor_id(); -#endif - unsigned long fs_base, gs_base; - u16 fs_sel, gs_sel; - int i; - - vmx->req_immediate_exit = false; - - /* - * Note that guest MSRs to be saved/restored can also be changed - * when guest state is loaded. This happens when guest transitions - * to/from long-mode by setting MSR_EFER.LMA. - */ - if (!vmx->guest_msrs_ready) { - vmx->guest_msrs_ready = true; - for (i = 0; i < vmx->save_nmsrs; ++i) - kvm_set_shared_msr(vmx->guest_msrs[i].index, - vmx->guest_msrs[i].data, - vmx->guest_msrs[i].mask); - - } - if (vmx->guest_state_loaded) - return; - - host_state = &vmx->loaded_vmcs->host_state; - - /* - * Set host fs and gs selectors. Unfortunately, 22.2.3 does not - * allow segment selectors with cpl > 0 or ti == 1. - */ - host_state->ldt_sel = kvm_read_ldt(); - -#ifdef CONFIG_X86_64 - savesegment(ds, host_state->ds_sel); - savesegment(es, host_state->es_sel); - - gs_base = cpu_kernelmode_gs_base(cpu); - if (likely(is_64bit_mm(current->mm))) { - save_fsgs_for_kvm(); - fs_sel = current->thread.fsindex; - gs_sel = current->thread.gsindex; - fs_base = current->thread.fsbase; - vmx->msr_host_kernel_gs_base = current->thread.gsbase; - } else { - savesegment(fs, fs_sel); - savesegment(gs, gs_sel); - fs_base = read_msr(MSR_FS_BASE); - vmx->msr_host_kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE); - } - - wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); -#else - savesegment(fs, fs_sel); - savesegment(gs, gs_sel); - fs_base = segment_base(fs_sel); - gs_base = segment_base(gs_sel); -#endif - - vmx_set_host_fs_gs(host_state, fs_sel, gs_sel, fs_base, gs_base); - vmx->guest_state_loaded = true; -} - -static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx) -{ - struct vmcs_host_state *host_state; - - if (!vmx->guest_state_loaded) - return; - - host_state = &vmx->loaded_vmcs->host_state; - - ++vmx->vcpu.stat.host_state_reload; - -#ifdef CONFIG_X86_64 - rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); -#endif - if (host_state->ldt_sel || (host_state->gs_sel & 7)) { - kvm_load_ldt(host_state->ldt_sel); -#ifdef CONFIG_X86_64 - load_gs_index(host_state->gs_sel); -#else - loadsegment(gs, host_state->gs_sel); -#endif - } - if (host_state->fs_sel & 7) - loadsegment(fs, host_state->fs_sel); -#ifdef CONFIG_X86_64 - if (unlikely(host_state->ds_sel | host_state->es_sel)) { - loadsegment(ds, host_state->ds_sel); - loadsegment(es, host_state->es_sel); - } -#endif - invalidate_tss_limit(); -#ifdef CONFIG_X86_64 - wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base); -#endif - load_fixmap_gdt(raw_smp_processor_id()); - vmx->guest_state_loaded = false; - vmx->guest_msrs_ready = false; -} - -#ifdef CONFIG_X86_64 -static u64 vmx_read_guest_kernel_gs_base(struct vcpu_vmx *vmx) -{ - preempt_disable(); - if (vmx->guest_state_loaded) - rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); - preempt_enable(); - return vmx->msr_guest_kernel_gs_base; -} - -static void vmx_write_guest_kernel_gs_base(struct vcpu_vmx *vmx, u64 data) -{ - preempt_disable(); - if (vmx->guest_state_loaded) - wrmsrl(MSR_KERNEL_GS_BASE, data); - preempt_enable(); - vmx->msr_guest_kernel_gs_base = data; -} -#endif - -static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) -{ - struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); - struct pi_desc old, new; - unsigned int dest; - - /* - * In case of hot-plug or hot-unplug, we may have to undo - * vmx_vcpu_pi_put even if there is no assigned device. And we - * always keep PI.NDST up to date for simplicity: it makes the - * code easier, and CPU migration is not a fast path. - */ - if (!pi_test_sn(pi_desc) && vcpu->cpu == cpu) - return; - - /* - * If the 'nv' field is POSTED_INTR_WAKEUP_VECTOR, do not change - * PI.NDST: pi_post_block is the one expected to change PID.NDST and the - * wakeup handler expects the vCPU to be on the blocked_vcpu_list that - * matches PI.NDST. Otherwise, a vcpu may not be able to be woken up - * correctly. - */ - if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR || vcpu->cpu == cpu) { - pi_clear_sn(pi_desc); - goto after_clear_sn; - } - - /* The full case. */ - do { - old.control = new.control = pi_desc->control; - - dest = cpu_physical_id(cpu); - - if (x2apic_enabled()) - new.ndst = dest; - else - new.ndst = (dest << 8) & 0xFF00; - - new.sn = 0; - } while (cmpxchg64(&pi_desc->control, old.control, - new.control) != old.control); - -after_clear_sn: - - /* - * Clear SN before reading the bitmap. The VT-d firmware - * writes the bitmap and reads SN atomically (5.2.3 in the - * spec), so it doesn't really have a memory barrier that - * pairs with this, but we cannot do that and we need one. - */ - smp_mb__after_atomic(); - - if (!pi_is_pir_empty(pi_desc)) - pi_set_on(pi_desc); -} - -void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - bool already_loaded = vmx->loaded_vmcs->cpu == cpu; - - if (!already_loaded) { - loaded_vmcs_clear(vmx->loaded_vmcs); - local_irq_disable(); - crash_disable_local_vmclear(cpu); - - /* - * Read loaded_vmcs->cpu should be before fetching - * loaded_vmcs->loaded_vmcss_on_cpu_link. - * See the comments in __loaded_vmcs_clear(). - */ - smp_rmb(); - - list_add(&vmx->loaded_vmcs->loaded_vmcss_on_cpu_link, - &per_cpu(loaded_vmcss_on_cpu, cpu)); - crash_enable_local_vmclear(cpu); - local_irq_enable(); - } - - if (per_cpu(current_vmcs, cpu) != vmx->loaded_vmcs->vmcs) { - per_cpu(current_vmcs, cpu) = vmx->loaded_vmcs->vmcs; - vmcs_load(vmx->loaded_vmcs->vmcs); - indirect_branch_prediction_barrier(); - } - - if (!already_loaded) { - void *gdt = get_current_gdt_ro(); - unsigned long sysenter_esp; - - kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); - - /* - * Linux uses per-cpu TSS and GDT, so set these when switching - * processors. See 22.2.4. - */ - vmcs_writel(HOST_TR_BASE, - (unsigned long)&get_cpu_entry_area(cpu)->tss.x86_tss); - vmcs_writel(HOST_GDTR_BASE, (unsigned long)gdt); /* 22.2.4 */ - - rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp); - vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */ - - vmx->loaded_vmcs->cpu = cpu; - } - - /* Setup TSC multiplier */ - if (kvm_has_tsc_control && - vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio) - decache_tsc_multiplier(vmx); -} - -/* - * Switches to specified vcpu, until a matching vcpu_put(), but assumes - * vcpu mutex is already taken. - */ -void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - - vmx_vcpu_load_vmcs(vcpu, cpu); - - vmx_vcpu_pi_load(vcpu, cpu); - - vmx->host_pkru = read_pkru(); - vmx->host_debugctlmsr = get_debugctlmsr(); -} - -static void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu) -{ - struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); - - if (!kvm_arch_has_assigned_device(vcpu->kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP) || - !kvm_vcpu_apicv_active(vcpu)) - return; - - /* Set SN when the vCPU is preempted */ - if (vcpu->preempted) - pi_set_sn(pi_desc); -} - -static void vmx_vcpu_put(struct kvm_vcpu *vcpu) -{ - vmx_vcpu_pi_put(vcpu); - - vmx_prepare_switch_to_host(to_vmx(vcpu)); -} - -static bool emulation_required(struct kvm_vcpu *vcpu) -{ - return emulate_invalid_guest_state && !guest_state_valid(vcpu); -} - -static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu); - -unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long rflags, save_rflags; - - if (!kvm_register_is_available(vcpu, VCPU_EXREG_RFLAGS)) { - kvm_register_mark_available(vcpu, VCPU_EXREG_RFLAGS); - rflags = vmcs_readl(GUEST_RFLAGS); - if (vmx->rmode.vm86_active) { - rflags &= RMODE_GUEST_OWNED_EFLAGS_BITS; - save_rflags = vmx->rmode.save_rflags; - rflags |= save_rflags & ~RMODE_GUEST_OWNED_EFLAGS_BITS; - } - vmx->rflags = rflags; - } - return vmx->rflags; -} - -void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long old_rflags; - - if (enable_unrestricted_guest) { - kvm_register_mark_available(vcpu, VCPU_EXREG_RFLAGS); - vmx->rflags = rflags; - vmcs_writel(GUEST_RFLAGS, rflags); - return; - } - - old_rflags = vmx_get_rflags(vcpu); - vmx->rflags = rflags; - if (vmx->rmode.vm86_active) { - vmx->rmode.save_rflags = rflags; - rflags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM; - } - vmcs_writel(GUEST_RFLAGS, rflags); - - if ((old_rflags ^ vmx->rflags) & X86_EFLAGS_VM) - vmx->emulation_required = emulation_required(vcpu); -} - -u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu) -{ - u32 interruptibility = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO); - int ret = 0; - - if (interruptibility & GUEST_INTR_STATE_STI) - ret |= KVM_X86_SHADOW_INT_STI; - if (interruptibility & GUEST_INTR_STATE_MOV_SS) - ret |= KVM_X86_SHADOW_INT_MOV_SS; - - return ret; -} - -void vmx_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask) -{ - u32 interruptibility_old = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO); - u32 interruptibility = interruptibility_old; - - interruptibility &= ~(GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS); - - if (mask & KVM_X86_SHADOW_INT_MOV_SS) - interruptibility |= GUEST_INTR_STATE_MOV_SS; - else if (mask & KVM_X86_SHADOW_INT_STI) - interruptibility |= GUEST_INTR_STATE_STI; - - if ((interruptibility != interruptibility_old)) - vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, interruptibility); -} - -static int vmx_rtit_ctl_check(struct kvm_vcpu *vcpu, u64 data) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long value; - - /* - * Any MSR write that attempts to change bits marked reserved will - * case a #GP fault. - */ - if (data & vmx->pt_desc.ctl_bitmask) - return 1; - - /* - * Any attempt to modify IA32_RTIT_CTL while TraceEn is set will - * result in a #GP unless the same write also clears TraceEn. - */ - if ((vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) && - ((vmx->pt_desc.guest.ctl ^ data) & ~RTIT_CTL_TRACEEN)) - return 1; - - /* - * WRMSR to IA32_RTIT_CTL that sets TraceEn but clears this bit - * and FabricEn would cause #GP, if - * CPUID.(EAX=14H, ECX=0):ECX.SNGLRGNOUT[bit 2] = 0 - */ - if ((data & RTIT_CTL_TRACEEN) && !(data & RTIT_CTL_TOPA) && - !(data & RTIT_CTL_FABRIC_EN) && - !intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_single_range_output)) - return 1; - - /* - * MTCFreq, CycThresh and PSBFreq encodings check, any MSR write that - * utilize encodings marked reserved will casue a #GP fault. - */ - value = intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_mtc_periods); - if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_mtc) && - !test_bit((data & RTIT_CTL_MTC_RANGE) >> - RTIT_CTL_MTC_RANGE_OFFSET, &value)) - return 1; - value = intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_cycle_thresholds); - if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_psb_cyc) && - !test_bit((data & RTIT_CTL_CYC_THRESH) >> - RTIT_CTL_CYC_THRESH_OFFSET, &value)) - return 1; - value = intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_psb_periods); - if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_psb_cyc) && - !test_bit((data & RTIT_CTL_PSB_FREQ) >> - RTIT_CTL_PSB_FREQ_OFFSET, &value)) - return 1; - - /* - * If ADDRx_CFG is reserved or the encodings is >2 will - * cause a #GP fault. - */ - value = (data & RTIT_CTL_ADDR0) >> RTIT_CTL_ADDR0_OFFSET; - if ((value && (vmx->pt_desc.addr_range < 1)) || (value > 2)) - return 1; - value = (data & RTIT_CTL_ADDR1) >> RTIT_CTL_ADDR1_OFFSET; - if ((value && (vmx->pt_desc.addr_range < 2)) || (value > 2)) - return 1; - value = (data & RTIT_CTL_ADDR2) >> RTIT_CTL_ADDR2_OFFSET; - if ((value && (vmx->pt_desc.addr_range < 3)) || (value > 2)) - return 1; - value = (data & RTIT_CTL_ADDR3) >> RTIT_CTL_ADDR3_OFFSET; - if ((value && (vmx->pt_desc.addr_range < 4)) || (value > 2)) - return 1; - - return 0; -} - -static int skip_emulated_instruction(struct kvm_vcpu *vcpu) -{ - unsigned long rip; - - /* - * Using VMCS.VM_EXIT_INSTRUCTION_LEN on EPT misconfig depends on - * undefined behavior: Intel's SDM doesn't mandate the VMCS field be - * set when EPT misconfig occurs. In practice, real hardware updates - * VM_EXIT_INSTRUCTION_LEN on EPT misconfig, but other hypervisors - * (namely Hyper-V) don't set it due to it being undefined behavior, - * i.e. we end up advancing IP with some random value. - */ - if (!static_cpu_has(X86_FEATURE_HYPERVISOR) || - to_vmx(vcpu)->exit_reason != EXIT_REASON_EPT_MISCONFIG) { - rip = kvm_rip_read(vcpu); - rip += vmcs_read32(VM_EXIT_INSTRUCTION_LEN); - kvm_rip_write(vcpu, rip); - } else { - if (!kvm_emulate_instruction(vcpu, EMULTYPE_SKIP)) - return 0; - } - - /* skipping an emulated instruction also counts */ - vmx_set_interrupt_shadow(vcpu, 0); - - return 1; -} - -static void vmx_clear_hlt(struct kvm_vcpu *vcpu) -{ - /* - * Ensure that we clear the HLT state in the VMCS. We don't need to - * explicitly skip the instruction because if the HLT state is set, - * then the instruction is already executing and RIP has already been - * advanced. - */ - if (kvm_hlt_in_guest(vcpu->kvm) && - vmcs_read32(GUEST_ACTIVITY_STATE) == GUEST_ACTIVITY_HLT) - vmcs_write32(GUEST_ACTIVITY_STATE, GUEST_ACTIVITY_ACTIVE); -} - -static void vmx_queue_exception(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned nr = vcpu->arch.exception.nr; - bool has_error_code = vcpu->arch.exception.has_error_code; - u32 error_code = vcpu->arch.exception.error_code; - u32 intr_info = nr | INTR_INFO_VALID_MASK; - - kvm_deliver_exception_payload(vcpu); - - if (has_error_code) { - vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code); - intr_info |= INTR_INFO_DELIVER_CODE_MASK; - } - - if (vmx->rmode.vm86_active) { - int inc_eip = 0; - if (kvm_exception_is_soft(nr)) - inc_eip = vcpu->arch.event_exit_inst_len; - kvm_inject_realmode_interrupt(vcpu, nr, inc_eip); - return; - } - - WARN_ON_ONCE(vmx->emulation_required); - - if (kvm_exception_is_soft(nr)) { - vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, - vmx->vcpu.arch.event_exit_inst_len); - intr_info |= INTR_TYPE_SOFT_EXCEPTION; - } else - intr_info |= INTR_TYPE_HARD_EXCEPTION; - - vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr_info); - - vmx_clear_hlt(vcpu); -} - -static bool vmx_rdtscp_supported(void) -{ - return cpu_has_vmx_rdtscp(); -} - -static bool vmx_invpcid_supported(void) -{ - return cpu_has_vmx_invpcid(); -} - -/* - * Swap MSR entry in host/guest MSR entry array. - */ -static void move_msr_up(struct vcpu_vmx *vmx, int from, int to) -{ - struct shared_msr_entry tmp; - - tmp = vmx->guest_msrs[to]; - vmx->guest_msrs[to] = vmx->guest_msrs[from]; - vmx->guest_msrs[from] = tmp; -} - -/* - * Set up the vmcs to automatically save and restore system - * msrs. Don't touch the 64-bit msrs if the guest is in legacy - * mode, as fiddling with msrs is very expensive. - */ -static void setup_msrs(struct vcpu_vmx *vmx) -{ - int save_nmsrs, index; - - save_nmsrs = 0; -#ifdef CONFIG_X86_64 - /* - * The SYSCALL MSRs are only needed on long mode guests, and only - * when EFER.SCE is set. - */ - if (is_long_mode(&vmx->vcpu) && (vmx->vcpu.arch.efer & EFER_SCE)) { - index = __find_msr_index(vmx, MSR_STAR); - if (index >= 0) - move_msr_up(vmx, index, save_nmsrs++); - index = __find_msr_index(vmx, MSR_LSTAR); - if (index >= 0) - move_msr_up(vmx, index, save_nmsrs++); - index = __find_msr_index(vmx, MSR_SYSCALL_MASK); - if (index >= 0) - move_msr_up(vmx, index, save_nmsrs++); - } -#endif - index = __find_msr_index(vmx, MSR_EFER); - if (index >= 0 && update_transition_efer(vmx, index)) - move_msr_up(vmx, index, save_nmsrs++); - index = __find_msr_index(vmx, MSR_TSC_AUX); - if (index >= 0 && guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDTSCP)) - move_msr_up(vmx, index, save_nmsrs++); - index = __find_msr_index(vmx, MSR_IA32_TSX_CTRL); - if (index >= 0) - move_msr_up(vmx, index, save_nmsrs++); - - vmx->save_nmsrs = save_nmsrs; - vmx->guest_msrs_ready = false; - - if (cpu_has_vmx_msr_bitmap()) - vmx_update_msr_bitmap(&vmx->vcpu); -} - -static u64 vmx_read_l1_tsc_offset(struct kvm_vcpu *vcpu) -{ - struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - - if (is_guest_mode(vcpu) && - (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING)) - return vcpu->arch.tsc_offset - vmcs12->tsc_offset; - - return vcpu->arch.tsc_offset; -} - -static u64 vmx_write_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) -{ - struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - u64 g_tsc_offset = 0; - - /* - * We're here if L1 chose not to trap WRMSR to TSC. According - * to the spec, this should set L1's TSC; The offset that L1 - * set for L2 remains unchanged, and still needs to be added - * to the newly set TSC to get L2's TSC. - */ - if (is_guest_mode(vcpu) && - (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING)) - g_tsc_offset = vmcs12->tsc_offset; - - trace_kvm_write_tsc_offset(vcpu->vcpu_id, - vcpu->arch.tsc_offset - g_tsc_offset, - offset); - vmcs_write64(TSC_OFFSET, offset + g_tsc_offset); - return offset + g_tsc_offset; -} - -/* - * nested_vmx_allowed() checks whether a guest should be allowed to use VMX - * instructions and MSRs (i.e., nested VMX). Nested VMX is disabled for - * all guests if the "nested" module option is off, and can also be disabled - * for a single guest by disabling its VMX cpuid bit. - */ -bool nested_vmx_allowed(struct kvm_vcpu *vcpu) -{ - return nested && guest_cpuid_has(vcpu, X86_FEATURE_VMX); -} - -static inline bool vmx_feature_control_msr_valid(struct kvm_vcpu *vcpu, - uint64_t val) -{ - uint64_t valid_bits = to_vmx(vcpu)->msr_ia32_feature_control_valid_bits; - - return !(val & ~valid_bits); -} - -static int vmx_get_msr_feature(struct kvm_msr_entry *msr) -{ - switch (msr->index) { - case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: - if (!nested) - return 1; - return vmx_get_vmx_msr(&vmcs_config.nested, msr->index, &msr->data); - default: - return 1; - } -} - -/* - * Reads an msr value (of 'msr_index') into 'pdata'. - * Returns 0 on success, non-0 otherwise. - * Assumes vcpu_load() was already called. - */ -static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - struct shared_msr_entry *msr; - u32 index; - - switch (msr_info->index) { -#ifdef CONFIG_X86_64 - case MSR_FS_BASE: - msr_info->data = vmcs_readl(GUEST_FS_BASE); - break; - case MSR_GS_BASE: - msr_info->data = vmcs_readl(GUEST_GS_BASE); - break; - case MSR_KERNEL_GS_BASE: - msr_info->data = vmx_read_guest_kernel_gs_base(vmx); - break; -#endif - case MSR_EFER: - return kvm_get_msr_common(vcpu, msr_info); - case MSR_IA32_TSX_CTRL: - if (!msr_info->host_initiated && - !(vcpu->arch.arch_capabilities & ARCH_CAP_TSX_CTRL_MSR)) - return 1; - goto find_shared_msr; - case MSR_IA32_UMWAIT_CONTROL: - if (!msr_info->host_initiated && !vmx_has_waitpkg(vmx)) - return 1; - - msr_info->data = vmx->msr_ia32_umwait_control; - break; - case MSR_IA32_SPEC_CTRL: - if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) - return 1; - - msr_info->data = to_vmx(vcpu)->spec_ctrl; - break; - case MSR_IA32_SYSENTER_CS: - msr_info->data = vmcs_read32(GUEST_SYSENTER_CS); - break; - case MSR_IA32_SYSENTER_EIP: - msr_info->data = vmcs_readl(GUEST_SYSENTER_EIP); - break; - case MSR_IA32_SYSENTER_ESP: - msr_info->data = vmcs_readl(GUEST_SYSENTER_ESP); - break; - case MSR_IA32_BNDCFGS: - if (!kvm_mpx_supported() || - (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_MPX))) - return 1; - msr_info->data = vmcs_read64(GUEST_BNDCFGS); - break; - case MSR_IA32_MCG_EXT_CTL: - if (!msr_info->host_initiated && - !(vmx->msr_ia32_feature_control & - FEATURE_CONTROL_LMCE)) - return 1; - msr_info->data = vcpu->arch.mcg_ext_ctl; - break; - case MSR_IA32_FEATURE_CONTROL: - msr_info->data = vmx->msr_ia32_feature_control; - break; - case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: - if (!nested_vmx_allowed(vcpu)) - return 1; - return vmx_get_vmx_msr(&vmx->nested.msrs, msr_info->index, - &msr_info->data); - case MSR_IA32_RTIT_CTL: - if (pt_mode != PT_MODE_HOST_GUEST) - return 1; - msr_info->data = vmx->pt_desc.guest.ctl; - break; - case MSR_IA32_RTIT_STATUS: - if (pt_mode != PT_MODE_HOST_GUEST) - return 1; - msr_info->data = vmx->pt_desc.guest.status; - break; - case MSR_IA32_RTIT_CR3_MATCH: - if ((pt_mode != PT_MODE_HOST_GUEST) || - !intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_cr3_filtering)) - return 1; - msr_info->data = vmx->pt_desc.guest.cr3_match; - break; - case MSR_IA32_RTIT_OUTPUT_BASE: - if ((pt_mode != PT_MODE_HOST_GUEST) || - (!intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_topa_output) && - !intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_single_range_output))) - return 1; - msr_info->data = vmx->pt_desc.guest.output_base; - break; - case MSR_IA32_RTIT_OUTPUT_MASK: - if ((pt_mode != PT_MODE_HOST_GUEST) || - (!intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_topa_output) && - !intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_single_range_output))) - return 1; - msr_info->data = vmx->pt_desc.guest.output_mask; - break; - case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: - index = msr_info->index - MSR_IA32_RTIT_ADDR0_A; - if ((pt_mode != PT_MODE_HOST_GUEST) || - (index >= 2 * intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_num_address_ranges))) - return 1; - if (is_noncanonical_address(data, vcpu)) - return 1; - if (index % 2) - msr_info->data = vmx->pt_desc.guest.addr_b[index / 2]; - else - msr_info->data = vmx->pt_desc.guest.addr_a[index / 2]; - break; - case MSR_TSC_AUX: - if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP)) - return 1; - goto find_shared_msr; - default: - find_shared_msr: - msr = find_msr_entry(vmx, msr_info->index); - if (msr) { - msr_info->data = msr->data; - break; - } - return kvm_get_msr_common(vcpu, msr_info); - } - - return 0; -} - -/* - * Writes msr value into the appropriate "register". - * Returns 0 on success, non-0 otherwise. - * Assumes vcpu_load() was already called. - */ -static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - struct shared_msr_entry *msr; - int ret = 0; - u32 msr_index = msr_info->index; - u64 data = msr_info->data; - u32 index; - - switch (msr_index) { - case MSR_EFER: - ret = kvm_set_msr_common(vcpu, msr_info); - break; -#ifdef CONFIG_X86_64 - case MSR_FS_BASE: - vmx_segment_cache_clear(vmx); - vmcs_writel(GUEST_FS_BASE, data); - break; - case MSR_GS_BASE: - vmx_segment_cache_clear(vmx); - vmcs_writel(GUEST_GS_BASE, data); - break; - case MSR_KERNEL_GS_BASE: - vmx_write_guest_kernel_gs_base(vmx, data); - break; -#endif - case MSR_IA32_SYSENTER_CS: - if (is_guest_mode(vcpu)) - get_vmcs12(vcpu)->guest_sysenter_cs = data; - vmcs_write32(GUEST_SYSENTER_CS, data); - break; - case MSR_IA32_SYSENTER_EIP: - if (is_guest_mode(vcpu)) - get_vmcs12(vcpu)->guest_sysenter_eip = data; - vmcs_writel(GUEST_SYSENTER_EIP, data); - break; - case MSR_IA32_SYSENTER_ESP: - if (is_guest_mode(vcpu)) - get_vmcs12(vcpu)->guest_sysenter_esp = data; - vmcs_writel(GUEST_SYSENTER_ESP, data); - break; - case MSR_IA32_DEBUGCTLMSR: - if (is_guest_mode(vcpu) && get_vmcs12(vcpu)->vm_exit_controls & - VM_EXIT_SAVE_DEBUG_CONTROLS) - get_vmcs12(vcpu)->guest_ia32_debugctl = data; - - ret = kvm_set_msr_common(vcpu, msr_info); - break; - - case MSR_IA32_BNDCFGS: - if (!kvm_mpx_supported() || - (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_MPX))) - return 1; - if (is_noncanonical_address(data & PAGE_MASK, vcpu) || - (data & MSR_IA32_BNDCFGS_RSVD)) - return 1; - vmcs_write64(GUEST_BNDCFGS, data); - break; - case MSR_IA32_UMWAIT_CONTROL: - if (!msr_info->host_initiated && !vmx_has_waitpkg(vmx)) - return 1; - - /* The reserved bit 1 and non-32 bit [63:32] should be zero */ - if (data & (BIT_ULL(1) | GENMASK_ULL(63, 32))) - return 1; - - vmx->msr_ia32_umwait_control = data; - break; - case MSR_IA32_SPEC_CTRL: - if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) - return 1; - - /* The STIBP bit doesn't fault even if it's not advertised */ - if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD)) - return 1; - - vmx->spec_ctrl = data; - - if (!data) - break; - - /* - * For non-nested: - * When it's written (to non-zero) for the first time, pass - * it through. - * - * For nested: - * The handling of the MSR bitmap for L2 guests is done in - * nested_vmx_prepare_msr_bitmap. We should not touch the - * vmcs02.msr_bitmap here since it gets completely overwritten - * in the merging. We update the vmcs01 here for L1 as well - * since it will end up touching the MSR anyway now. - */ - vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, - MSR_IA32_SPEC_CTRL, - MSR_TYPE_RW); - break; - case MSR_IA32_TSX_CTRL: - if (!msr_info->host_initiated && - !(vcpu->arch.arch_capabilities & ARCH_CAP_TSX_CTRL_MSR)) - return 1; - if (data & ~(TSX_CTRL_RTM_DISABLE | TSX_CTRL_CPUID_CLEAR)) - return 1; - goto find_shared_msr; - case MSR_IA32_PRED_CMD: - if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) - return 1; - - if (data & ~PRED_CMD_IBPB) - return 1; - - if (!data) - break; - - wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB); - - /* - * For non-nested: - * When it's written (to non-zero) for the first time, pass - * it through. - * - * For nested: - * The handling of the MSR bitmap for L2 guests is done in - * nested_vmx_prepare_msr_bitmap. We should not touch the - * vmcs02.msr_bitmap here since it gets completely overwritten - * in the merging. - */ - vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, MSR_IA32_PRED_CMD, - MSR_TYPE_W); - break; - case MSR_IA32_CR_PAT: - if (!kvm_pat_valid(data)) - return 1; - - if (is_guest_mode(vcpu) && - get_vmcs12(vcpu)->vm_exit_controls & VM_EXIT_SAVE_IA32_PAT) - get_vmcs12(vcpu)->guest_ia32_pat = data; - - if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) { - vmcs_write64(GUEST_IA32_PAT, data); - vcpu->arch.pat = data; - break; - } - ret = kvm_set_msr_common(vcpu, msr_info); - break; - case MSR_IA32_TSC_ADJUST: - ret = kvm_set_msr_common(vcpu, msr_info); - break; - case MSR_IA32_MCG_EXT_CTL: - if ((!msr_info->host_initiated && - !(to_vmx(vcpu)->msr_ia32_feature_control & - FEATURE_CONTROL_LMCE)) || - (data & ~MCG_EXT_CTL_LMCE_EN)) - return 1; - vcpu->arch.mcg_ext_ctl = data; - break; - case MSR_IA32_FEATURE_CONTROL: - if (!vmx_feature_control_msr_valid(vcpu, data) || - (to_vmx(vcpu)->msr_ia32_feature_control & - FEATURE_CONTROL_LOCKED && !msr_info->host_initiated)) - return 1; - vmx->msr_ia32_feature_control = data; - if (msr_info->host_initiated && data == 0) - vmx_leave_nested(vcpu); - break; - case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: - if (!msr_info->host_initiated) - return 1; /* they are read-only */ - if (!nested_vmx_allowed(vcpu)) - return 1; - return vmx_set_vmx_msr(vcpu, msr_index, data); - case MSR_IA32_RTIT_CTL: - if ((pt_mode != PT_MODE_HOST_GUEST) || - vmx_rtit_ctl_check(vcpu, data) || - vmx->nested.vmxon) - return 1; - vmcs_write64(GUEST_IA32_RTIT_CTL, data); - vmx->pt_desc.guest.ctl = data; - pt_update_intercept_for_msr(vmx); - break; - case MSR_IA32_RTIT_STATUS: - if ((pt_mode != PT_MODE_HOST_GUEST) || - (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) || - (data & MSR_IA32_RTIT_STATUS_MASK)) - return 1; - vmx->pt_desc.guest.status = data; - break; - case MSR_IA32_RTIT_CR3_MATCH: - if ((pt_mode != PT_MODE_HOST_GUEST) || - (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) || - !intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_cr3_filtering)) - return 1; - vmx->pt_desc.guest.cr3_match = data; - break; - case MSR_IA32_RTIT_OUTPUT_BASE: - if ((pt_mode != PT_MODE_HOST_GUEST) || - (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) || - (!intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_topa_output) && - !intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_single_range_output)) || - (data & MSR_IA32_RTIT_OUTPUT_BASE_MASK)) - return 1; - vmx->pt_desc.guest.output_base = data; - break; - case MSR_IA32_RTIT_OUTPUT_MASK: - if ((pt_mode != PT_MODE_HOST_GUEST) || - (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) || - (!intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_topa_output) && - !intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_single_range_output))) - return 1; - vmx->pt_desc.guest.output_mask = data; - break; - case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: - index = msr_info->index - MSR_IA32_RTIT_ADDR0_A; - if ((pt_mode != PT_MODE_HOST_GUEST) || - (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) || - (index >= 2 * intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_num_address_ranges))) - return 1; - if (is_noncanonical_address(data, vcpu)) - return 1; - if (index % 2) - vmx->pt_desc.guest.addr_b[index / 2] = data; - else - vmx->pt_desc.guest.addr_a[index / 2] = data; - break; - case MSR_TSC_AUX: - if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP)) - return 1; - /* Check reserved bit, higher 32 bits should be zero */ - if ((data >> 32) != 0) - return 1; - goto find_shared_msr; - - default: - find_shared_msr: - msr = find_msr_entry(vmx, msr_index); - if (msr) - ret = vmx_set_guest_msr(vmx, msr, data); - else - ret = kvm_set_msr_common(vcpu, msr_info); - } - - return ret; -} - -static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) -{ - kvm_register_mark_available(vcpu, reg); - - switch (reg) { - case VCPU_REGS_RSP: - vcpu->arch.regs[VCPU_REGS_RSP] = vmcs_readl(GUEST_RSP); - break; - case VCPU_REGS_RIP: - vcpu->arch.regs[VCPU_REGS_RIP] = vmcs_readl(GUEST_RIP); - break; - case VCPU_EXREG_PDPTR: - if (enable_ept) - ept_save_pdptrs(vcpu); - break; - case VCPU_EXREG_CR3: - if (enable_unrestricted_guest || (enable_ept && is_paging(vcpu))) - vcpu->arch.cr3 = vmcs_readl(GUEST_CR3); - break; - default: - WARN_ON_ONCE(1); - break; - } -} - -static __init int cpu_has_kvm_support(void) -{ - return cpu_has_vmx(); -} - -static __init int vmx_disabled_by_bios(void) -{ - u64 msr; - - rdmsrl(MSR_IA32_FEATURE_CONTROL, msr); - if (msr & FEATURE_CONTROL_LOCKED) { - /* launched w/ TXT and VMX disabled */ - if (!(msr & FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX) - && tboot_enabled()) - return 1; - /* launched w/o TXT and VMX only enabled w/ TXT */ - if (!(msr & FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX) - && (msr & FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX) - && !tboot_enabled()) { - printk(KERN_WARNING "kvm: disable TXT in the BIOS or " - "activate TXT before enabling KVM\n"); - return 1; - } - /* launched w/o TXT and VMX disabled */ - if (!(msr & FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX) - && !tboot_enabled()) - return 1; - } - - return 0; -} - -static void kvm_cpu_vmxon(u64 addr) -{ - cr4_set_bits(X86_CR4_VMXE); - intel_pt_handle_vmx(1); - - asm volatile ("vmxon %0" : : "m"(addr)); -} - -static int hardware_enable(void) -{ - int cpu = raw_smp_processor_id(); - u64 phys_addr = __pa(per_cpu(vmxarea, cpu)); - u64 old, test_bits; - - if (cr4_read_shadow() & X86_CR4_VMXE) - return -EBUSY; - - /* - * This can happen if we hot-added a CPU but failed to allocate - * VP assist page for it. - */ - if (static_branch_unlikely(&enable_evmcs) && - !hv_get_vp_assist_page(cpu)) - return -EFAULT; - - INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu)); - INIT_LIST_HEAD(&per_cpu(blocked_vcpu_on_cpu, cpu)); - spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu)); - - /* - * Now we can enable the vmclear operation in kdump - * since the loaded_vmcss_on_cpu list on this cpu - * has been initialized. - * - * Though the cpu is not in VMX operation now, there - * is no problem to enable the vmclear operation - * for the loaded_vmcss_on_cpu list is empty! - */ - crash_enable_local_vmclear(cpu); - - rdmsrl(MSR_IA32_FEATURE_CONTROL, old); - - test_bits = FEATURE_CONTROL_LOCKED; - test_bits |= FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX; - if (tboot_enabled()) - test_bits |= FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX; - - if ((old & test_bits) != test_bits) { - /* enable and lock */ - wrmsrl(MSR_IA32_FEATURE_CONTROL, old | test_bits); - } - kvm_cpu_vmxon(phys_addr); - if (enable_ept) - ept_sync_global(); - - return 0; -} - -static void vmclear_local_loaded_vmcss(void) -{ - int cpu = raw_smp_processor_id(); - struct loaded_vmcs *v, *n; - - list_for_each_entry_safe(v, n, &per_cpu(loaded_vmcss_on_cpu, cpu), - loaded_vmcss_on_cpu_link) - __loaded_vmcs_clear(v); -} - - -/* Just like cpu_vmxoff(), but with the __kvm_handle_fault_on_reboot() - * tricks. - */ -static void kvm_cpu_vmxoff(void) -{ - asm volatile (__ex("vmxoff")); - - intel_pt_handle_vmx(0); - cr4_clear_bits(X86_CR4_VMXE); -} - -static void hardware_disable(void) -{ - vmclear_local_loaded_vmcss(); - kvm_cpu_vmxoff(); -} - -static __init int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt, - u32 msr, u32 *result) -{ - u32 vmx_msr_low, vmx_msr_high; - u32 ctl = ctl_min | ctl_opt; - - rdmsr(msr, vmx_msr_low, vmx_msr_high); - - ctl &= vmx_msr_high; /* bit == 0 in high word ==> must be zero */ - ctl |= vmx_msr_low; /* bit == 1 in low word ==> must be one */ - - /* Ensure minimum (required) set of control bits are supported. */ - if (ctl_min & ~ctl) - return -EIO; - - *result = ctl; - return 0; -} - -static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, - struct vmx_capability *vmx_cap) -{ - u32 vmx_msr_low, vmx_msr_high; - u32 min, opt, min2, opt2; - u32 _pin_based_exec_control = 0; - u32 _cpu_based_exec_control = 0; - u32 _cpu_based_2nd_exec_control = 0; - u32 _vmexit_control = 0; - u32 _vmentry_control = 0; - - memset(vmcs_conf, 0, sizeof(*vmcs_conf)); - min = CPU_BASED_HLT_EXITING | -#ifdef CONFIG_X86_64 - CPU_BASED_CR8_LOAD_EXITING | - CPU_BASED_CR8_STORE_EXITING | -#endif - CPU_BASED_CR3_LOAD_EXITING | - CPU_BASED_CR3_STORE_EXITING | - CPU_BASED_UNCOND_IO_EXITING | - CPU_BASED_MOV_DR_EXITING | - CPU_BASED_USE_TSC_OFFSETTING | - CPU_BASED_MWAIT_EXITING | - CPU_BASED_MONITOR_EXITING | - CPU_BASED_INVLPG_EXITING | - CPU_BASED_RDPMC_EXITING; - - opt = CPU_BASED_TPR_SHADOW | - CPU_BASED_USE_MSR_BITMAPS | - CPU_BASED_ACTIVATE_SECONDARY_CONTROLS; - if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PROCBASED_CTLS, - &_cpu_based_exec_control) < 0) - return -EIO; -#ifdef CONFIG_X86_64 - if ((_cpu_based_exec_control & CPU_BASED_TPR_SHADOW)) - _cpu_based_exec_control &= ~CPU_BASED_CR8_LOAD_EXITING & - ~CPU_BASED_CR8_STORE_EXITING; -#endif - if (_cpu_based_exec_control & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) { - min2 = 0; - opt2 = SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | - SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | - SECONDARY_EXEC_WBINVD_EXITING | - SECONDARY_EXEC_ENABLE_VPID | - SECONDARY_EXEC_ENABLE_EPT | - SECONDARY_EXEC_UNRESTRICTED_GUEST | - SECONDARY_EXEC_PAUSE_LOOP_EXITING | - SECONDARY_EXEC_DESC | - SECONDARY_EXEC_RDTSCP | - SECONDARY_EXEC_ENABLE_INVPCID | - SECONDARY_EXEC_APIC_REGISTER_VIRT | - SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | - SECONDARY_EXEC_SHADOW_VMCS | - SECONDARY_EXEC_XSAVES | - SECONDARY_EXEC_RDSEED_EXITING | - SECONDARY_EXEC_RDRAND_EXITING | - SECONDARY_EXEC_ENABLE_PML | - SECONDARY_EXEC_TSC_SCALING | - SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | - SECONDARY_EXEC_PT_USE_GPA | - SECONDARY_EXEC_PT_CONCEAL_VMX | - SECONDARY_EXEC_ENABLE_VMFUNC | - SECONDARY_EXEC_ENCLS_EXITING; - if (adjust_vmx_controls(min2, opt2, - MSR_IA32_VMX_PROCBASED_CTLS2, - &_cpu_based_2nd_exec_control) < 0) - return -EIO; - } -#ifndef CONFIG_X86_64 - if (!(_cpu_based_2nd_exec_control & - SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) - _cpu_based_exec_control &= ~CPU_BASED_TPR_SHADOW; -#endif - - if (!(_cpu_based_exec_control & CPU_BASED_TPR_SHADOW)) - _cpu_based_2nd_exec_control &= ~( - SECONDARY_EXEC_APIC_REGISTER_VIRT | - SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | - SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY); - - rdmsr_safe(MSR_IA32_VMX_EPT_VPID_CAP, - &vmx_cap->ept, &vmx_cap->vpid); - - if (_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_EPT) { - /* CR3 accesses and invlpg don't need to cause VM Exits when EPT - enabled */ - _cpu_based_exec_control &= ~(CPU_BASED_CR3_LOAD_EXITING | - CPU_BASED_CR3_STORE_EXITING | - CPU_BASED_INVLPG_EXITING); - } else if (vmx_cap->ept) { - vmx_cap->ept = 0; - pr_warn_once("EPT CAP should not exist if not support " - "1-setting enable EPT VM-execution control\n"); - } - if (!(_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_VPID) && - vmx_cap->vpid) { - vmx_cap->vpid = 0; - pr_warn_once("VPID CAP should not exist if not support " - "1-setting enable VPID VM-execution control\n"); - } - - min = VM_EXIT_SAVE_DEBUG_CONTROLS | VM_EXIT_ACK_INTR_ON_EXIT; -#ifdef CONFIG_X86_64 - min |= VM_EXIT_HOST_ADDR_SPACE_SIZE; -#endif - opt = VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | - VM_EXIT_LOAD_IA32_PAT | - VM_EXIT_LOAD_IA32_EFER | - VM_EXIT_CLEAR_BNDCFGS | - VM_EXIT_PT_CONCEAL_PIP | - VM_EXIT_CLEAR_IA32_RTIT_CTL; - if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_EXIT_CTLS, - &_vmexit_control) < 0) - return -EIO; - - min = PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING; - opt = PIN_BASED_VIRTUAL_NMIS | PIN_BASED_POSTED_INTR | - PIN_BASED_VMX_PREEMPTION_TIMER; - if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PINBASED_CTLS, - &_pin_based_exec_control) < 0) - return -EIO; - - if (cpu_has_broken_vmx_preemption_timer()) - _pin_based_exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER; - if (!(_cpu_based_2nd_exec_control & - SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY)) - _pin_based_exec_control &= ~PIN_BASED_POSTED_INTR; - - min = VM_ENTRY_LOAD_DEBUG_CONTROLS; - opt = VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | - VM_ENTRY_LOAD_IA32_PAT | - VM_ENTRY_LOAD_IA32_EFER | - VM_ENTRY_LOAD_BNDCFGS | - VM_ENTRY_PT_CONCEAL_PIP | - VM_ENTRY_LOAD_IA32_RTIT_CTL; - if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_ENTRY_CTLS, - &_vmentry_control) < 0) - return -EIO; - - /* - * Some cpus support VM_{ENTRY,EXIT}_IA32_PERF_GLOBAL_CTRL but they - * can't be used due to an errata where VM Exit may incorrectly clear - * IA32_PERF_GLOBAL_CTRL[34:32]. Workaround the errata by using the - * MSR load mechanism to switch IA32_PERF_GLOBAL_CTRL. - */ - if (boot_cpu_data.x86 == 0x6) { - switch (boot_cpu_data.x86_model) { - case 26: /* AAK155 */ - case 30: /* AAP115 */ - case 37: /* AAT100 */ - case 44: /* BC86,AAY89,BD102 */ - case 46: /* BA97 */ - _vmentry_control &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; - _vmexit_control &= ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; - pr_warn_once("kvm: VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL " - "does not work properly. Using workaround\n"); - break; - default: - break; - } - } - - - rdmsr(MSR_IA32_VMX_BASIC, vmx_msr_low, vmx_msr_high); - - /* IA-32 SDM Vol 3B: VMCS size is never greater than 4kB. */ - if ((vmx_msr_high & 0x1fff) > PAGE_SIZE) - return -EIO; - -#ifdef CONFIG_X86_64 - /* IA-32 SDM Vol 3B: 64-bit CPUs always have VMX_BASIC_MSR[48]==0. */ - if (vmx_msr_high & (1u<<16)) - return -EIO; -#endif - - /* Require Write-Back (WB) memory type for VMCS accesses. */ - if (((vmx_msr_high >> 18) & 15) != 6) - return -EIO; - - vmcs_conf->size = vmx_msr_high & 0x1fff; - vmcs_conf->order = get_order(vmcs_conf->size); - vmcs_conf->basic_cap = vmx_msr_high & ~0x1fff; - - vmcs_conf->revision_id = vmx_msr_low; - - vmcs_conf->pin_based_exec_ctrl = _pin_based_exec_control; - vmcs_conf->cpu_based_exec_ctrl = _cpu_based_exec_control; - vmcs_conf->cpu_based_2nd_exec_ctrl = _cpu_based_2nd_exec_control; - vmcs_conf->vmexit_ctrl = _vmexit_control; - vmcs_conf->vmentry_ctrl = _vmentry_control; - - if (static_branch_unlikely(&enable_evmcs)) - evmcs_sanitize_exec_ctrls(vmcs_conf); - - return 0; -} - -struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu, gfp_t flags) -{ - int node = cpu_to_node(cpu); - struct page *pages; - struct vmcs *vmcs; - - pages = __alloc_pages_node(node, flags, vmcs_config.order); - if (!pages) - return NULL; - vmcs = page_address(pages); - memset(vmcs, 0, vmcs_config.size); - - /* KVM supports Enlightened VMCS v1 only */ - if (static_branch_unlikely(&enable_evmcs)) - vmcs->hdr.revision_id = KVM_EVMCS_VERSION; - else - vmcs->hdr.revision_id = vmcs_config.revision_id; - - if (shadow) - vmcs->hdr.shadow_vmcs = 1; - return vmcs; -} - -void free_vmcs(struct vmcs *vmcs) -{ - free_pages((unsigned long)vmcs, vmcs_config.order); -} - -/* - * Free a VMCS, but before that VMCLEAR it on the CPU where it was last loaded - */ -void free_loaded_vmcs(struct loaded_vmcs *loaded_vmcs) -{ - if (!loaded_vmcs->vmcs) - return; - loaded_vmcs_clear(loaded_vmcs); - free_vmcs(loaded_vmcs->vmcs); - loaded_vmcs->vmcs = NULL; - if (loaded_vmcs->msr_bitmap) - free_page((unsigned long)loaded_vmcs->msr_bitmap); - WARN_ON(loaded_vmcs->shadow_vmcs != NULL); -} - -int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs) -{ - loaded_vmcs->vmcs = alloc_vmcs(false); - if (!loaded_vmcs->vmcs) - return -ENOMEM; - - loaded_vmcs->shadow_vmcs = NULL; - loaded_vmcs->hv_timer_soft_disabled = false; - loaded_vmcs_init(loaded_vmcs); - - if (cpu_has_vmx_msr_bitmap()) { - loaded_vmcs->msr_bitmap = (unsigned long *) - __get_free_page(GFP_KERNEL_ACCOUNT); - if (!loaded_vmcs->msr_bitmap) - goto out_vmcs; - memset(loaded_vmcs->msr_bitmap, 0xff, PAGE_SIZE); - - if (IS_ENABLED(CONFIG_HYPERV) && - static_branch_unlikely(&enable_evmcs) && - (ms_hyperv.nested_features & HV_X64_NESTED_MSR_BITMAP)) { - struct hv_enlightened_vmcs *evmcs = - (struct hv_enlightened_vmcs *)loaded_vmcs->vmcs; - - evmcs->hv_enlightenments_control.msr_bitmap = 1; - } - } - - memset(&loaded_vmcs->host_state, 0, sizeof(struct vmcs_host_state)); - memset(&loaded_vmcs->controls_shadow, 0, - sizeof(struct vmcs_controls_shadow)); - - return 0; - -out_vmcs: - free_loaded_vmcs(loaded_vmcs); - return -ENOMEM; -} - -static void free_kvm_area(void) -{ - int cpu; - - for_each_possible_cpu(cpu) { - free_vmcs(per_cpu(vmxarea, cpu)); - per_cpu(vmxarea, cpu) = NULL; - } -} - -static __init int alloc_kvm_area(void) -{ - int cpu; - - for_each_possible_cpu(cpu) { - struct vmcs *vmcs; - - vmcs = alloc_vmcs_cpu(false, cpu, GFP_KERNEL); - if (!vmcs) { - free_kvm_area(); - return -ENOMEM; - } - - /* - * When eVMCS is enabled, alloc_vmcs_cpu() sets - * vmcs->revision_id to KVM_EVMCS_VERSION instead of - * revision_id reported by MSR_IA32_VMX_BASIC. - * - * However, even though not explicitly documented by - * TLFS, VMXArea passed as VMXON argument should - * still be marked with revision_id reported by - * physical CPU. - */ - if (static_branch_unlikely(&enable_evmcs)) - vmcs->hdr.revision_id = vmcs_config.revision_id; - - per_cpu(vmxarea, cpu) = vmcs; - } - return 0; -} - -static void fix_pmode_seg(struct kvm_vcpu *vcpu, int seg, - struct kvm_segment *save) -{ - if (!emulate_invalid_guest_state) { - /* - * CS and SS RPL should be equal during guest entry according - * to VMX spec, but in reality it is not always so. Since vcpu - * is in the middle of the transition from real mode to - * protected mode it is safe to assume that RPL 0 is a good - * default value. - */ - if (seg == VCPU_SREG_CS || seg == VCPU_SREG_SS) - save->selector &= ~SEGMENT_RPL_MASK; - save->dpl = save->selector & SEGMENT_RPL_MASK; - save->s = 1; - } - vmx_set_segment(vcpu, save, seg); -} - -static void enter_pmode(struct kvm_vcpu *vcpu) -{ - unsigned long flags; - struct vcpu_vmx *vmx = to_vmx(vcpu); - - /* - * Update real mode segment cache. It may be not up-to-date if sement - * register was written while vcpu was in a guest mode. - */ - vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_ES], VCPU_SREG_ES); - vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_DS], VCPU_SREG_DS); - vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_FS], VCPU_SREG_FS); - vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_GS], VCPU_SREG_GS); - vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_SS], VCPU_SREG_SS); - vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_CS], VCPU_SREG_CS); - - vmx->rmode.vm86_active = 0; - - vmx_segment_cache_clear(vmx); - - vmx_set_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_TR], VCPU_SREG_TR); - - flags = vmcs_readl(GUEST_RFLAGS); - flags &= RMODE_GUEST_OWNED_EFLAGS_BITS; - flags |= vmx->rmode.save_rflags & ~RMODE_GUEST_OWNED_EFLAGS_BITS; - vmcs_writel(GUEST_RFLAGS, flags); - - vmcs_writel(GUEST_CR4, (vmcs_readl(GUEST_CR4) & ~X86_CR4_VME) | - (vmcs_readl(CR4_READ_SHADOW) & X86_CR4_VME)); - - update_exception_bitmap(vcpu); - - fix_pmode_seg(vcpu, VCPU_SREG_CS, &vmx->rmode.segs[VCPU_SREG_CS]); - fix_pmode_seg(vcpu, VCPU_SREG_SS, &vmx->rmode.segs[VCPU_SREG_SS]); - fix_pmode_seg(vcpu, VCPU_SREG_ES, &vmx->rmode.segs[VCPU_SREG_ES]); - fix_pmode_seg(vcpu, VCPU_SREG_DS, &vmx->rmode.segs[VCPU_SREG_DS]); - fix_pmode_seg(vcpu, VCPU_SREG_FS, &vmx->rmode.segs[VCPU_SREG_FS]); - fix_pmode_seg(vcpu, VCPU_SREG_GS, &vmx->rmode.segs[VCPU_SREG_GS]); -} - -static void fix_rmode_seg(int seg, struct kvm_segment *save) -{ - const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; - struct kvm_segment var = *save; - - var.dpl = 0x3; - if (seg == VCPU_SREG_CS) - var.type = 0x3; - - if (!emulate_invalid_guest_state) { - var.selector = var.base >> 4; - var.base = var.base & 0xffff0; - var.limit = 0xffff; - var.g = 0; - var.db = 0; - var.present = 1; - var.s = 1; - var.l = 0; - var.unusable = 0; - var.type = 0x3; - var.avl = 0; - if (save->base & 0xf) - printk_once(KERN_WARNING "kvm: segment base is not " - "paragraph aligned when entering " - "protected mode (seg=%d)", seg); - } - - vmcs_write16(sf->selector, var.selector); - vmcs_writel(sf->base, var.base); - vmcs_write32(sf->limit, var.limit); - vmcs_write32(sf->ar_bytes, vmx_segment_access_rights(&var)); -} - -static void enter_rmode(struct kvm_vcpu *vcpu) -{ - unsigned long flags; - struct vcpu_vmx *vmx = to_vmx(vcpu); - struct kvm_vmx *kvm_vmx = to_kvm_vmx(vcpu->kvm); - - vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_TR], VCPU_SREG_TR); - vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_ES], VCPU_SREG_ES); - vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_DS], VCPU_SREG_DS); - vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_FS], VCPU_SREG_FS); - vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_GS], VCPU_SREG_GS); - vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_SS], VCPU_SREG_SS); - vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_CS], VCPU_SREG_CS); - - vmx->rmode.vm86_active = 1; - - /* - * Very old userspace does not call KVM_SET_TSS_ADDR before entering - * vcpu. Warn the user that an update is overdue. - */ - if (!kvm_vmx->tss_addr) - printk_once(KERN_WARNING "kvm: KVM_SET_TSS_ADDR need to be " - "called before entering vcpu\n"); - - vmx_segment_cache_clear(vmx); - - vmcs_writel(GUEST_TR_BASE, kvm_vmx->tss_addr); - vmcs_write32(GUEST_TR_LIMIT, RMODE_TSS_SIZE - 1); - vmcs_write32(GUEST_TR_AR_BYTES, 0x008b); - - flags = vmcs_readl(GUEST_RFLAGS); - vmx->rmode.save_rflags = flags; - - flags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM; - - vmcs_writel(GUEST_RFLAGS, flags); - vmcs_writel(GUEST_CR4, vmcs_readl(GUEST_CR4) | X86_CR4_VME); - update_exception_bitmap(vcpu); - - fix_rmode_seg(VCPU_SREG_SS, &vmx->rmode.segs[VCPU_SREG_SS]); - fix_rmode_seg(VCPU_SREG_CS, &vmx->rmode.segs[VCPU_SREG_CS]); - fix_rmode_seg(VCPU_SREG_ES, &vmx->rmode.segs[VCPU_SREG_ES]); - fix_rmode_seg(VCPU_SREG_DS, &vmx->rmode.segs[VCPU_SREG_DS]); - fix_rmode_seg(VCPU_SREG_GS, &vmx->rmode.segs[VCPU_SREG_GS]); - fix_rmode_seg(VCPU_SREG_FS, &vmx->rmode.segs[VCPU_SREG_FS]); - - kvm_mmu_reset_context(vcpu); -} - -void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - struct shared_msr_entry *msr = find_msr_entry(vmx, MSR_EFER); - - if (!msr) - return; - - vcpu->arch.efer = efer; - if (efer & EFER_LMA) { - vm_entry_controls_setbit(to_vmx(vcpu), VM_ENTRY_IA32E_MODE); - msr->data = efer; - } else { - vm_entry_controls_clearbit(to_vmx(vcpu), VM_ENTRY_IA32E_MODE); - - msr->data = efer & ~EFER_LME; - } - setup_msrs(vmx); -} - -#ifdef CONFIG_X86_64 - -static void enter_lmode(struct kvm_vcpu *vcpu) -{ - u32 guest_tr_ar; - - vmx_segment_cache_clear(to_vmx(vcpu)); - - guest_tr_ar = vmcs_read32(GUEST_TR_AR_BYTES); - if ((guest_tr_ar & VMX_AR_TYPE_MASK) != VMX_AR_TYPE_BUSY_64_TSS) { - pr_debug_ratelimited("%s: tss fixup for long mode. \n", - __func__); - vmcs_write32(GUEST_TR_AR_BYTES, - (guest_tr_ar & ~VMX_AR_TYPE_MASK) - | VMX_AR_TYPE_BUSY_64_TSS); - } - vmx_set_efer(vcpu, vcpu->arch.efer | EFER_LMA); -} - -static void exit_lmode(struct kvm_vcpu *vcpu) -{ - vm_entry_controls_clearbit(to_vmx(vcpu), VM_ENTRY_IA32E_MODE); - vmx_set_efer(vcpu, vcpu->arch.efer & ~EFER_LMA); -} - -#endif - -static void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr) -{ - int vpid = to_vmx(vcpu)->vpid; - - if (!vpid_sync_vcpu_addr(vpid, addr)) - vpid_sync_context(vpid); - - /* - * If VPIDs are not supported or enabled, then the above is a no-op. - * But we don't really need a TLB flush in that case anyway, because - * each VM entry/exit includes an implicit flush when VPID is 0. - */ -} - -static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu) -{ - ulong cr0_guest_owned_bits = vcpu->arch.cr0_guest_owned_bits; - - vcpu->arch.cr0 &= ~cr0_guest_owned_bits; - vcpu->arch.cr0 |= vmcs_readl(GUEST_CR0) & cr0_guest_owned_bits; -} - -static void vmx_decache_cr4_guest_bits(struct kvm_vcpu *vcpu) -{ - ulong cr4_guest_owned_bits = vcpu->arch.cr4_guest_owned_bits; - - vcpu->arch.cr4 &= ~cr4_guest_owned_bits; - vcpu->arch.cr4 |= vmcs_readl(GUEST_CR4) & cr4_guest_owned_bits; -} - -static void ept_load_pdptrs(struct kvm_vcpu *vcpu) -{ - struct kvm_mmu *mmu = vcpu->arch.walk_mmu; - - if (!kvm_register_is_dirty(vcpu, VCPU_EXREG_PDPTR)) - return; - - if (is_pae_paging(vcpu)) { - vmcs_write64(GUEST_PDPTR0, mmu->pdptrs[0]); - vmcs_write64(GUEST_PDPTR1, mmu->pdptrs[1]); - vmcs_write64(GUEST_PDPTR2, mmu->pdptrs[2]); - vmcs_write64(GUEST_PDPTR3, mmu->pdptrs[3]); - } -} - -void ept_save_pdptrs(struct kvm_vcpu *vcpu) -{ - struct kvm_mmu *mmu = vcpu->arch.walk_mmu; - - if (is_pae_paging(vcpu)) { - mmu->pdptrs[0] = vmcs_read64(GUEST_PDPTR0); - mmu->pdptrs[1] = vmcs_read64(GUEST_PDPTR1); - mmu->pdptrs[2] = vmcs_read64(GUEST_PDPTR2); - mmu->pdptrs[3] = vmcs_read64(GUEST_PDPTR3); - } - - kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR); -} - -static void ept_update_paging_mode_cr0(unsigned long *hw_cr0, - unsigned long cr0, - struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - - if (!kvm_register_is_available(vcpu, VCPU_EXREG_CR3)) - vmx_cache_reg(vcpu, VCPU_EXREG_CR3); - if (!(cr0 & X86_CR0_PG)) { - /* From paging/starting to nonpaging */ - exec_controls_setbit(vmx, CPU_BASED_CR3_LOAD_EXITING | - CPU_BASED_CR3_STORE_EXITING); - vcpu->arch.cr0 = cr0; - vmx_set_cr4(vcpu, kvm_read_cr4(vcpu)); - } else if (!is_paging(vcpu)) { - /* From nonpaging to paging */ - exec_controls_clearbit(vmx, CPU_BASED_CR3_LOAD_EXITING | - CPU_BASED_CR3_STORE_EXITING); - vcpu->arch.cr0 = cr0; - vmx_set_cr4(vcpu, kvm_read_cr4(vcpu)); - } - - if (!(cr0 & X86_CR0_WP)) - *hw_cr0 &= ~X86_CR0_WP; -} - -void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long hw_cr0; - - hw_cr0 = (cr0 & ~KVM_VM_CR0_ALWAYS_OFF); - if (enable_unrestricted_guest) - hw_cr0 |= KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST; - else { - hw_cr0 |= KVM_VM_CR0_ALWAYS_ON; - - if (vmx->rmode.vm86_active && (cr0 & X86_CR0_PE)) - enter_pmode(vcpu); - - if (!vmx->rmode.vm86_active && !(cr0 & X86_CR0_PE)) - enter_rmode(vcpu); - } - -#ifdef CONFIG_X86_64 - if (vcpu->arch.efer & EFER_LME) { - if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) - enter_lmode(vcpu); - if (is_paging(vcpu) && !(cr0 & X86_CR0_PG)) - exit_lmode(vcpu); - } -#endif - - if (enable_ept && !enable_unrestricted_guest) - ept_update_paging_mode_cr0(&hw_cr0, cr0, vcpu); - - vmcs_writel(CR0_READ_SHADOW, cr0); - vmcs_writel(GUEST_CR0, hw_cr0); - vcpu->arch.cr0 = cr0; - - /* depends on vcpu->arch.cr0 to be set to a new value */ - vmx->emulation_required = emulation_required(vcpu); -} - -static int get_ept_level(struct kvm_vcpu *vcpu) -{ - if (cpu_has_vmx_ept_5levels() && (cpuid_maxphyaddr(vcpu) > 48)) - return 5; - return 4; -} - -u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa) -{ - u64 eptp = VMX_EPTP_MT_WB; - - eptp |= (get_ept_level(vcpu) == 5) ? VMX_EPTP_PWL_5 : VMX_EPTP_PWL_4; - - if (enable_ept_ad_bits && - (!is_guest_mode(vcpu) || nested_ept_ad_enabled(vcpu))) - eptp |= VMX_EPTP_AD_ENABLE_BIT; - eptp |= (root_hpa & PAGE_MASK); - - return eptp; -} - -void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) -{ - struct kvm *kvm = vcpu->kvm; - bool update_guest_cr3 = true; - unsigned long guest_cr3; - u64 eptp; - - guest_cr3 = cr3; - if (enable_ept) { - eptp = construct_eptp(vcpu, cr3); - vmcs_write64(EPT_POINTER, eptp); - - if (kvm_x86_ops->tlb_remote_flush) { - spin_lock(&to_kvm_vmx(kvm)->ept_pointer_lock); - to_vmx(vcpu)->ept_pointer = eptp; - to_kvm_vmx(kvm)->ept_pointers_match - = EPT_POINTERS_CHECK; - spin_unlock(&to_kvm_vmx(kvm)->ept_pointer_lock); - } - - /* Loading vmcs02.GUEST_CR3 is handled by nested VM-Enter. */ - if (is_guest_mode(vcpu)) - update_guest_cr3 = false; - else if (!enable_unrestricted_guest && !is_paging(vcpu)) - guest_cr3 = to_kvm_vmx(kvm)->ept_identity_map_addr; - else if (test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail)) - guest_cr3 = vcpu->arch.cr3; - else /* vmcs01.GUEST_CR3 is already up-to-date. */ - update_guest_cr3 = false; - ept_load_pdptrs(vcpu); - } - - if (update_guest_cr3) - vmcs_writel(GUEST_CR3, guest_cr3); -} - -int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - /* - * Pass through host's Machine Check Enable value to hw_cr4, which - * is in force while we are in guest mode. Do not let guests control - * this bit, even if host CR4.MCE == 0. - */ - unsigned long hw_cr4; - - hw_cr4 = (cr4_read_shadow() & X86_CR4_MCE) | (cr4 & ~X86_CR4_MCE); - if (enable_unrestricted_guest) - hw_cr4 |= KVM_VM_CR4_ALWAYS_ON_UNRESTRICTED_GUEST; - else if (vmx->rmode.vm86_active) - hw_cr4 |= KVM_RMODE_VM_CR4_ALWAYS_ON; - else - hw_cr4 |= KVM_PMODE_VM_CR4_ALWAYS_ON; - - if (!boot_cpu_has(X86_FEATURE_UMIP) && vmx_umip_emulated()) { - if (cr4 & X86_CR4_UMIP) { - secondary_exec_controls_setbit(vmx, SECONDARY_EXEC_DESC); - hw_cr4 &= ~X86_CR4_UMIP; - } else if (!is_guest_mode(vcpu) || - !nested_cpu_has2(get_vmcs12(vcpu), SECONDARY_EXEC_DESC)) { - secondary_exec_controls_clearbit(vmx, SECONDARY_EXEC_DESC); - } - } - - if (cr4 & X86_CR4_VMXE) { - /* - * To use VMXON (and later other VMX instructions), a guest - * must first be able to turn on cr4.VMXE (see handle_vmon()). - * So basically the check on whether to allow nested VMX - * is here. We operate under the default treatment of SMM, - * so VMX cannot be enabled under SMM. - */ - if (!nested_vmx_allowed(vcpu) || is_smm(vcpu)) - return 1; - } - - if (vmx->nested.vmxon && !nested_cr4_valid(vcpu, cr4)) - return 1; - - vcpu->arch.cr4 = cr4; - - if (!enable_unrestricted_guest) { - if (enable_ept) { - if (!is_paging(vcpu)) { - hw_cr4 &= ~X86_CR4_PAE; - hw_cr4 |= X86_CR4_PSE; - } else if (!(cr4 & X86_CR4_PAE)) { - hw_cr4 &= ~X86_CR4_PAE; - } - } - - /* - * SMEP/SMAP/PKU is disabled if CPU is in non-paging mode in - * hardware. To emulate this behavior, SMEP/SMAP/PKU needs - * to be manually disabled when guest switches to non-paging - * mode. - * - * If !enable_unrestricted_guest, the CPU is always running - * with CR0.PG=1 and CR4 needs to be modified. - * If enable_unrestricted_guest, the CPU automatically - * disables SMEP/SMAP/PKU when the guest sets CR0.PG=0. - */ - if (!is_paging(vcpu)) - hw_cr4 &= ~(X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE); - } - - vmcs_writel(CR4_READ_SHADOW, cr4); - vmcs_writel(GUEST_CR4, hw_cr4); - return 0; -} - -void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - u32 ar; - - if (vmx->rmode.vm86_active && seg != VCPU_SREG_LDTR) { - *var = vmx->rmode.segs[seg]; - if (seg == VCPU_SREG_TR - || var->selector == vmx_read_guest_seg_selector(vmx, seg)) - return; - var->base = vmx_read_guest_seg_base(vmx, seg); - var->selector = vmx_read_guest_seg_selector(vmx, seg); - return; - } - var->base = vmx_read_guest_seg_base(vmx, seg); - var->limit = vmx_read_guest_seg_limit(vmx, seg); - var->selector = vmx_read_guest_seg_selector(vmx, seg); - ar = vmx_read_guest_seg_ar(vmx, seg); - var->unusable = (ar >> 16) & 1; - var->type = ar & 15; - var->s = (ar >> 4) & 1; - var->dpl = (ar >> 5) & 3; - /* - * Some userspaces do not preserve unusable property. Since usable - * segment has to be present according to VMX spec we can use present - * property to amend userspace bug by making unusable segment always - * nonpresent. vmx_segment_access_rights() already marks nonpresent - * segment as unusable. - */ - var->present = !var->unusable; - var->avl = (ar >> 12) & 1; - var->l = (ar >> 13) & 1; - var->db = (ar >> 14) & 1; - var->g = (ar >> 15) & 1; -} - -static u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg) -{ - struct kvm_segment s; - - if (to_vmx(vcpu)->rmode.vm86_active) { - vmx_get_segment(vcpu, &s, seg); - return s.base; - } - return vmx_read_guest_seg_base(to_vmx(vcpu), seg); -} - -int vmx_get_cpl(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - - if (unlikely(vmx->rmode.vm86_active)) - return 0; - else { - int ar = vmx_read_guest_seg_ar(vmx, VCPU_SREG_SS); - return VMX_AR_DPL(ar); - } -} - -static u32 vmx_segment_access_rights(struct kvm_segment *var) -{ - u32 ar; - - if (var->unusable || !var->present) - ar = 1 << 16; - else { - ar = var->type & 15; - ar |= (var->s & 1) << 4; - ar |= (var->dpl & 3) << 5; - ar |= (var->present & 1) << 7; - ar |= (var->avl & 1) << 12; - ar |= (var->l & 1) << 13; - ar |= (var->db & 1) << 14; - ar |= (var->g & 1) << 15; - } - - return ar; -} - -void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; - - vmx_segment_cache_clear(vmx); - - if (vmx->rmode.vm86_active && seg != VCPU_SREG_LDTR) { - vmx->rmode.segs[seg] = *var; - if (seg == VCPU_SREG_TR) - vmcs_write16(sf->selector, var->selector); - else if (var->s) - fix_rmode_seg(seg, &vmx->rmode.segs[seg]); - goto out; - } - - vmcs_writel(sf->base, var->base); - vmcs_write32(sf->limit, var->limit); - vmcs_write16(sf->selector, var->selector); - - /* - * Fix the "Accessed" bit in AR field of segment registers for older - * qemu binaries. - * IA32 arch specifies that at the time of processor reset the - * "Accessed" bit in the AR field of segment registers is 1. And qemu - * is setting it to 0 in the userland code. This causes invalid guest - * state vmexit when "unrestricted guest" mode is turned on. - * Fix for this setup issue in cpu_reset is being pushed in the qemu - * tree. Newer qemu binaries with that qemu fix would not need this - * kvm hack. - */ - if (enable_unrestricted_guest && (seg != VCPU_SREG_LDTR)) - var->type |= 0x1; /* Accessed */ - - vmcs_write32(sf->ar_bytes, vmx_segment_access_rights(var)); - -out: - vmx->emulation_required = emulation_required(vcpu); -} - -static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) -{ - u32 ar = vmx_read_guest_seg_ar(to_vmx(vcpu), VCPU_SREG_CS); - - *db = (ar >> 14) & 1; - *l = (ar >> 13) & 1; -} - -static void vmx_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) -{ - dt->size = vmcs_read32(GUEST_IDTR_LIMIT); - dt->address = vmcs_readl(GUEST_IDTR_BASE); -} - -static void vmx_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) -{ - vmcs_write32(GUEST_IDTR_LIMIT, dt->size); - vmcs_writel(GUEST_IDTR_BASE, dt->address); -} - -static void vmx_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) -{ - dt->size = vmcs_read32(GUEST_GDTR_LIMIT); - dt->address = vmcs_readl(GUEST_GDTR_BASE); -} - -static void vmx_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) -{ - vmcs_write32(GUEST_GDTR_LIMIT, dt->size); - vmcs_writel(GUEST_GDTR_BASE, dt->address); -} - -static bool rmode_segment_valid(struct kvm_vcpu *vcpu, int seg) -{ - struct kvm_segment var; - u32 ar; - - vmx_get_segment(vcpu, &var, seg); - var.dpl = 0x3; - if (seg == VCPU_SREG_CS) - var.type = 0x3; - ar = vmx_segment_access_rights(&var); - - if (var.base != (var.selector << 4)) - return false; - if (var.limit != 0xffff) - return false; - if (ar != 0xf3) - return false; - - return true; -} - -static bool code_segment_valid(struct kvm_vcpu *vcpu) -{ - struct kvm_segment cs; - unsigned int cs_rpl; - - vmx_get_segment(vcpu, &cs, VCPU_SREG_CS); - cs_rpl = cs.selector & SEGMENT_RPL_MASK; - - if (cs.unusable) - return false; - if (~cs.type & (VMX_AR_TYPE_CODE_MASK|VMX_AR_TYPE_ACCESSES_MASK)) - return false; - if (!cs.s) - return false; - if (cs.type & VMX_AR_TYPE_WRITEABLE_MASK) { - if (cs.dpl > cs_rpl) - return false; - } else { - if (cs.dpl != cs_rpl) - return false; - } - if (!cs.present) - return false; - - /* TODO: Add Reserved field check, this'll require a new member in the kvm_segment_field structure */ - return true; -} - -static bool stack_segment_valid(struct kvm_vcpu *vcpu) -{ - struct kvm_segment ss; - unsigned int ss_rpl; - - vmx_get_segment(vcpu, &ss, VCPU_SREG_SS); - ss_rpl = ss.selector & SEGMENT_RPL_MASK; - - if (ss.unusable) - return true; - if (ss.type != 3 && ss.type != 7) - return false; - if (!ss.s) - return false; - if (ss.dpl != ss_rpl) /* DPL != RPL */ - return false; - if (!ss.present) - return false; - - return true; -} - -static bool data_segment_valid(struct kvm_vcpu *vcpu, int seg) -{ - struct kvm_segment var; - unsigned int rpl; - - vmx_get_segment(vcpu, &var, seg); - rpl = var.selector & SEGMENT_RPL_MASK; - - if (var.unusable) - return true; - if (!var.s) - return false; - if (!var.present) - return false; - if (~var.type & (VMX_AR_TYPE_CODE_MASK|VMX_AR_TYPE_WRITEABLE_MASK)) { - if (var.dpl < rpl) /* DPL < RPL */ - return false; - } - - /* TODO: Add other members to kvm_segment_field to allow checking for other access - * rights flags - */ - return true; -} - -static bool tr_valid(struct kvm_vcpu *vcpu) -{ - struct kvm_segment tr; - - vmx_get_segment(vcpu, &tr, VCPU_SREG_TR); - - if (tr.unusable) - return false; - if (tr.selector & SEGMENT_TI_MASK) /* TI = 1 */ - return false; - if (tr.type != 3 && tr.type != 11) /* TODO: Check if guest is in IA32e mode */ - return false; - if (!tr.present) - return false; - - return true; -} - -static bool ldtr_valid(struct kvm_vcpu *vcpu) -{ - struct kvm_segment ldtr; - - vmx_get_segment(vcpu, &ldtr, VCPU_SREG_LDTR); - - if (ldtr.unusable) - return true; - if (ldtr.selector & SEGMENT_TI_MASK) /* TI = 1 */ - return false; - if (ldtr.type != 2) - return false; - if (!ldtr.present) - return false; - - return true; -} - -static bool cs_ss_rpl_check(struct kvm_vcpu *vcpu) -{ - struct kvm_segment cs, ss; - - vmx_get_segment(vcpu, &cs, VCPU_SREG_CS); - vmx_get_segment(vcpu, &ss, VCPU_SREG_SS); - - return ((cs.selector & SEGMENT_RPL_MASK) == - (ss.selector & SEGMENT_RPL_MASK)); -} - -/* - * Check if guest state is valid. Returns true if valid, false if - * not. - * We assume that registers are always usable - */ -static bool guest_state_valid(struct kvm_vcpu *vcpu) -{ - if (enable_unrestricted_guest) - return true; - - /* real mode guest state checks */ - if (!is_protmode(vcpu) || (vmx_get_rflags(vcpu) & X86_EFLAGS_VM)) { - if (!rmode_segment_valid(vcpu, VCPU_SREG_CS)) - return false; - if (!rmode_segment_valid(vcpu, VCPU_SREG_SS)) - return false; - if (!rmode_segment_valid(vcpu, VCPU_SREG_DS)) - return false; - if (!rmode_segment_valid(vcpu, VCPU_SREG_ES)) - return false; - if (!rmode_segment_valid(vcpu, VCPU_SREG_FS)) - return false; - if (!rmode_segment_valid(vcpu, VCPU_SREG_GS)) - return false; - } else { - /* protected mode guest state checks */ - if (!cs_ss_rpl_check(vcpu)) - return false; - if (!code_segment_valid(vcpu)) - return false; - if (!stack_segment_valid(vcpu)) - return false; - if (!data_segment_valid(vcpu, VCPU_SREG_DS)) - return false; - if (!data_segment_valid(vcpu, VCPU_SREG_ES)) - return false; - if (!data_segment_valid(vcpu, VCPU_SREG_FS)) - return false; - if (!data_segment_valid(vcpu, VCPU_SREG_GS)) - return false; - if (!tr_valid(vcpu)) - return false; - if (!ldtr_valid(vcpu)) - return false; - } - /* TODO: - * - Add checks on RIP - * - Add checks on RFLAGS - */ - - return true; -} - -static int init_rmode_tss(struct kvm *kvm) -{ - gfn_t fn; - u16 data = 0; - int idx, r; - - idx = srcu_read_lock(&kvm->srcu); - fn = to_kvm_vmx(kvm)->tss_addr >> PAGE_SHIFT; - r = kvm_clear_guest_page(kvm, fn, 0, PAGE_SIZE); - if (r < 0) - goto out; - data = TSS_BASE_SIZE + TSS_REDIRECTION_SIZE; - r = kvm_write_guest_page(kvm, fn++, &data, - TSS_IOPB_BASE_OFFSET, sizeof(u16)); - if (r < 0) - goto out; - r = kvm_clear_guest_page(kvm, fn++, 0, PAGE_SIZE); - if (r < 0) - goto out; - r = kvm_clear_guest_page(kvm, fn, 0, PAGE_SIZE); - if (r < 0) - goto out; - data = ~0; - r = kvm_write_guest_page(kvm, fn, &data, - RMODE_TSS_SIZE - 2 * PAGE_SIZE - 1, - sizeof(u8)); -out: - srcu_read_unlock(&kvm->srcu, idx); - return r; -} - -static int init_rmode_identity_map(struct kvm *kvm) -{ - struct kvm_vmx *kvm_vmx = to_kvm_vmx(kvm); - int i, idx, r = 0; - kvm_pfn_t identity_map_pfn; - u32 tmp; - - /* Protect kvm_vmx->ept_identity_pagetable_done. */ - mutex_lock(&kvm->slots_lock); - - if (likely(kvm_vmx->ept_identity_pagetable_done)) - goto out2; - - if (!kvm_vmx->ept_identity_map_addr) - kvm_vmx->ept_identity_map_addr = VMX_EPT_IDENTITY_PAGETABLE_ADDR; - identity_map_pfn = kvm_vmx->ept_identity_map_addr >> PAGE_SHIFT; - - r = __x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT, - kvm_vmx->ept_identity_map_addr, PAGE_SIZE); - if (r < 0) - goto out2; - - idx = srcu_read_lock(&kvm->srcu); - r = kvm_clear_guest_page(kvm, identity_map_pfn, 0, PAGE_SIZE); - if (r < 0) - goto out; - /* Set up identity-mapping pagetable for EPT in real mode */ - for (i = 0; i < PT32_ENT_PER_PAGE; i++) { - tmp = (i << 22) + (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | - _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_PSE); - r = kvm_write_guest_page(kvm, identity_map_pfn, - &tmp, i * sizeof(tmp), sizeof(tmp)); - if (r < 0) - goto out; - } - kvm_vmx->ept_identity_pagetable_done = true; - -out: - srcu_read_unlock(&kvm->srcu, idx); - -out2: - mutex_unlock(&kvm->slots_lock); - return r; -} - -static void seg_setup(int seg) -{ - const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; - unsigned int ar; - - vmcs_write16(sf->selector, 0); - vmcs_writel(sf->base, 0); - vmcs_write32(sf->limit, 0xffff); - ar = 0x93; - if (seg == VCPU_SREG_CS) - ar |= 0x08; /* code segment */ - - vmcs_write32(sf->ar_bytes, ar); -} - -static int alloc_apic_access_page(struct kvm *kvm) -{ - struct page *page; - int r = 0; - - mutex_lock(&kvm->slots_lock); - if (kvm->arch.apic_access_page_done) - goto out; - r = __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, - APIC_DEFAULT_PHYS_BASE, PAGE_SIZE); - if (r) - goto out; - - page = gfn_to_page(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT); - if (is_error_page(page)) { - r = -EFAULT; - goto out; - } - - /* - * Do not pin the page in memory, so that memory hot-unplug - * is able to migrate it. - */ - put_page(page); - kvm->arch.apic_access_page_done = true; -out: - mutex_unlock(&kvm->slots_lock); - return r; -} - -int allocate_vpid(void) -{ - int vpid; - - if (!enable_vpid) - return 0; - spin_lock(&vmx_vpid_lock); - vpid = find_first_zero_bit(vmx_vpid_bitmap, VMX_NR_VPIDS); - if (vpid < VMX_NR_VPIDS) - __set_bit(vpid, vmx_vpid_bitmap); - else - vpid = 0; - spin_unlock(&vmx_vpid_lock); - return vpid; -} - -void free_vpid(int vpid) -{ - if (!enable_vpid || vpid == 0) - return; - spin_lock(&vmx_vpid_lock); - __clear_bit(vpid, vmx_vpid_bitmap); - spin_unlock(&vmx_vpid_lock); -} - -static __always_inline void vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, - u32 msr, int type) -{ - int f = sizeof(unsigned long); - - if (!cpu_has_vmx_msr_bitmap()) - return; - - if (static_branch_unlikely(&enable_evmcs)) - evmcs_touch_msr_bitmap(); - - /* - * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals - * have the write-low and read-high bitmap offsets the wrong way round. - * We can control MSRs 0x00000000-0x00001fff and 0xc0000000-0xc0001fff. - */ - if (msr <= 0x1fff) { - if (type & MSR_TYPE_R) - /* read-low */ - __clear_bit(msr, msr_bitmap + 0x000 / f); - - if (type & MSR_TYPE_W) - /* write-low */ - __clear_bit(msr, msr_bitmap + 0x800 / f); - - } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { - msr &= 0x1fff; - if (type & MSR_TYPE_R) - /* read-high */ - __clear_bit(msr, msr_bitmap + 0x400 / f); - - if (type & MSR_TYPE_W) - /* write-high */ - __clear_bit(msr, msr_bitmap + 0xc00 / f); - - } -} - -static __always_inline void vmx_enable_intercept_for_msr(unsigned long *msr_bitmap, - u32 msr, int type) -{ - int f = sizeof(unsigned long); - - if (!cpu_has_vmx_msr_bitmap()) - return; - - if (static_branch_unlikely(&enable_evmcs)) - evmcs_touch_msr_bitmap(); - - /* - * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals - * have the write-low and read-high bitmap offsets the wrong way round. - * We can control MSRs 0x00000000-0x00001fff and 0xc0000000-0xc0001fff. - */ - if (msr <= 0x1fff) { - if (type & MSR_TYPE_R) - /* read-low */ - __set_bit(msr, msr_bitmap + 0x000 / f); - - if (type & MSR_TYPE_W) - /* write-low */ - __set_bit(msr, msr_bitmap + 0x800 / f); - - } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { - msr &= 0x1fff; - if (type & MSR_TYPE_R) - /* read-high */ - __set_bit(msr, msr_bitmap + 0x400 / f); - - if (type & MSR_TYPE_W) - /* write-high */ - __set_bit(msr, msr_bitmap + 0xc00 / f); - - } -} - -static __always_inline void vmx_set_intercept_for_msr(unsigned long *msr_bitmap, - u32 msr, int type, bool value) -{ - if (value) - vmx_enable_intercept_for_msr(msr_bitmap, msr, type); - else - vmx_disable_intercept_for_msr(msr_bitmap, msr, type); -} - -static u8 vmx_msr_bitmap_mode(struct kvm_vcpu *vcpu) -{ - u8 mode = 0; - - if (cpu_has_secondary_exec_ctrls() && - (secondary_exec_controls_get(to_vmx(vcpu)) & - SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) { - mode |= MSR_BITMAP_MODE_X2APIC; - if (enable_apicv && kvm_vcpu_apicv_active(vcpu)) - mode |= MSR_BITMAP_MODE_X2APIC_APICV; - } - - return mode; -} - -static void vmx_update_msr_bitmap_x2apic(unsigned long *msr_bitmap, - u8 mode) -{ - int msr; - - for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) { - unsigned word = msr / BITS_PER_LONG; - msr_bitmap[word] = (mode & MSR_BITMAP_MODE_X2APIC_APICV) ? 0 : ~0; - msr_bitmap[word + (0x800 / sizeof(long))] = ~0; - } - - if (mode & MSR_BITMAP_MODE_X2APIC) { - /* - * TPR reads and writes can be virtualized even if virtual interrupt - * delivery is not in use. - */ - vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_TASKPRI), MSR_TYPE_RW); - if (mode & MSR_BITMAP_MODE_X2APIC_APICV) { - vmx_enable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_TMCCT), MSR_TYPE_R); - vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_EOI), MSR_TYPE_W); - vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_SELF_IPI), MSR_TYPE_W); - } - } -} - -void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap; - u8 mode = vmx_msr_bitmap_mode(vcpu); - u8 changed = mode ^ vmx->msr_bitmap_mode; - - if (!changed) - return; - - if (changed & (MSR_BITMAP_MODE_X2APIC | MSR_BITMAP_MODE_X2APIC_APICV)) - vmx_update_msr_bitmap_x2apic(msr_bitmap, mode); - - vmx->msr_bitmap_mode = mode; -} - -void pt_update_intercept_for_msr(struct vcpu_vmx *vmx) -{ - unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap; - bool flag = !(vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN); - u32 i; - - vmx_set_intercept_for_msr(msr_bitmap, MSR_IA32_RTIT_STATUS, - MSR_TYPE_RW, flag); - vmx_set_intercept_for_msr(msr_bitmap, MSR_IA32_RTIT_OUTPUT_BASE, - MSR_TYPE_RW, flag); - vmx_set_intercept_for_msr(msr_bitmap, MSR_IA32_RTIT_OUTPUT_MASK, - MSR_TYPE_RW, flag); - vmx_set_intercept_for_msr(msr_bitmap, MSR_IA32_RTIT_CR3_MATCH, - MSR_TYPE_RW, flag); - for (i = 0; i < vmx->pt_desc.addr_range; i++) { - vmx_set_intercept_for_msr(msr_bitmap, - MSR_IA32_RTIT_ADDR0_A + i * 2, MSR_TYPE_RW, flag); - vmx_set_intercept_for_msr(msr_bitmap, - MSR_IA32_RTIT_ADDR0_B + i * 2, MSR_TYPE_RW, flag); - } -} - -static bool vmx_get_enable_apicv(struct kvm *kvm) -{ - return enable_apicv; -} - -static bool vmx_guest_apic_has_interrupt(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - void *vapic_page; - u32 vppr; - int rvi; - - if (WARN_ON_ONCE(!is_guest_mode(vcpu)) || - !nested_cpu_has_vid(get_vmcs12(vcpu)) || - WARN_ON_ONCE(!vmx->nested.virtual_apic_map.gfn)) - return false; - - rvi = vmx_get_rvi(); - - vapic_page = vmx->nested.virtual_apic_map.hva; - vppr = *((u32 *)(vapic_page + APIC_PROCPRI)); - - return ((rvi & 0xf0) > (vppr & 0xf0)); -} - -static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu, - bool nested) -{ -#ifdef CONFIG_SMP - int pi_vec = nested ? POSTED_INTR_NESTED_VECTOR : POSTED_INTR_VECTOR; - - if (vcpu->mode == IN_GUEST_MODE) { - /* - * The vector of interrupt to be delivered to vcpu had - * been set in PIR before this function. - * - * Following cases will be reached in this block, and - * we always send a notification event in all cases as - * explained below. - * - * Case 1: vcpu keeps in non-root mode. Sending a - * notification event posts the interrupt to vcpu. - * - * Case 2: vcpu exits to root mode and is still - * runnable. PIR will be synced to vIRR before the - * next vcpu entry. Sending a notification event in - * this case has no effect, as vcpu is not in root - * mode. - * - * Case 3: vcpu exits to root mode and is blocked. - * vcpu_block() has already synced PIR to vIRR and - * never blocks vcpu if vIRR is not cleared. Therefore, - * a blocked vcpu here does not wait for any requested - * interrupts in PIR, and sending a notification event - * which has no effect is safe here. - */ - - apic->send_IPI_mask(get_cpu_mask(vcpu->cpu), pi_vec); - return true; - } -#endif - return false; -} - -static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu, - int vector) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - - if (is_guest_mode(vcpu) && - vector == vmx->nested.posted_intr_nv) { - /* - * If a posted intr is not recognized by hardware, - * we will accomplish it in the next vmentry. - */ - vmx->nested.pi_pending = true; - kvm_make_request(KVM_REQ_EVENT, vcpu); - /* the PIR and ON have been set by L1. */ - if (!kvm_vcpu_trigger_posted_interrupt(vcpu, true)) - kvm_vcpu_kick(vcpu); - return 0; - } - return -1; -} -/* - * Send interrupt to vcpu via posted interrupt way. - * 1. If target vcpu is running(non-root mode), send posted interrupt - * notification to vcpu and hardware will sync PIR to vIRR atomically. - * 2. If target vcpu isn't running(root mode), kick it to pick up the - * interrupt from PIR in next vmentry. - */ -static void vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - int r; - - r = vmx_deliver_nested_posted_interrupt(vcpu, vector); - if (!r) - return; - - if (pi_test_and_set_pir(vector, &vmx->pi_desc)) - return; - - /* If a previous notification has sent the IPI, nothing to do. */ - if (pi_test_and_set_on(&vmx->pi_desc)) - return; - - if (!kvm_vcpu_trigger_posted_interrupt(vcpu, false)) - kvm_vcpu_kick(vcpu); -} - -/* - * Set up the vmcs's constant host-state fields, i.e., host-state fields that - * will not change in the lifetime of the guest. - * Note that host-state that does change is set elsewhere. E.g., host-state - * that is set differently for each CPU is set in vmx_vcpu_load(), not here. - */ -void vmx_set_constant_host_state(struct vcpu_vmx *vmx) -{ - u32 low32, high32; - unsigned long tmpl; - unsigned long cr0, cr3, cr4; - - cr0 = read_cr0(); - WARN_ON(cr0 & X86_CR0_TS); - vmcs_writel(HOST_CR0, cr0); /* 22.2.3 */ - - /* - * Save the most likely value for this task's CR3 in the VMCS. - * We can't use __get_current_cr3_fast() because we're not atomic. - */ - cr3 = __read_cr3(); - vmcs_writel(HOST_CR3, cr3); /* 22.2.3 FIXME: shadow tables */ - vmx->loaded_vmcs->host_state.cr3 = cr3; - - /* Save the most likely value for this task's CR4 in the VMCS. */ - cr4 = cr4_read_shadow(); - vmcs_writel(HOST_CR4, cr4); /* 22.2.3, 22.2.5 */ - vmx->loaded_vmcs->host_state.cr4 = cr4; - - vmcs_write16(HOST_CS_SELECTOR, __KERNEL_CS); /* 22.2.4 */ -#ifdef CONFIG_X86_64 - /* - * Load null selectors, so we can avoid reloading them in - * vmx_prepare_switch_to_host(), in case userspace uses - * the null selectors too (the expected case). - */ - vmcs_write16(HOST_DS_SELECTOR, 0); - vmcs_write16(HOST_ES_SELECTOR, 0); -#else - vmcs_write16(HOST_DS_SELECTOR, __KERNEL_DS); /* 22.2.4 */ - vmcs_write16(HOST_ES_SELECTOR, __KERNEL_DS); /* 22.2.4 */ -#endif - vmcs_write16(HOST_SS_SELECTOR, __KERNEL_DS); /* 22.2.4 */ - vmcs_write16(HOST_TR_SELECTOR, GDT_ENTRY_TSS*8); /* 22.2.4 */ - - vmcs_writel(HOST_IDTR_BASE, host_idt_base); /* 22.2.4 */ - - vmcs_writel(HOST_RIP, (unsigned long)vmx_vmexit); /* 22.2.5 */ - - rdmsr(MSR_IA32_SYSENTER_CS, low32, high32); - vmcs_write32(HOST_IA32_SYSENTER_CS, low32); - rdmsrl(MSR_IA32_SYSENTER_EIP, tmpl); - vmcs_writel(HOST_IA32_SYSENTER_EIP, tmpl); /* 22.2.3 */ - - if (vmcs_config.vmexit_ctrl & VM_EXIT_LOAD_IA32_PAT) { - rdmsr(MSR_IA32_CR_PAT, low32, high32); - vmcs_write64(HOST_IA32_PAT, low32 | ((u64) high32 << 32)); - } - - if (cpu_has_load_ia32_efer()) - vmcs_write64(HOST_IA32_EFER, host_efer); -} - -void set_cr4_guest_host_mask(struct vcpu_vmx *vmx) -{ - vmx->vcpu.arch.cr4_guest_owned_bits = KVM_CR4_GUEST_OWNED_BITS; - if (enable_ept) - vmx->vcpu.arch.cr4_guest_owned_bits |= X86_CR4_PGE; - if (is_guest_mode(&vmx->vcpu)) - vmx->vcpu.arch.cr4_guest_owned_bits &= - ~get_vmcs12(&vmx->vcpu)->cr4_guest_host_mask; - vmcs_writel(CR4_GUEST_HOST_MASK, ~vmx->vcpu.arch.cr4_guest_owned_bits); -} - -u32 vmx_pin_based_exec_ctrl(struct vcpu_vmx *vmx) -{ - u32 pin_based_exec_ctrl = vmcs_config.pin_based_exec_ctrl; - - if (!kvm_vcpu_apicv_active(&vmx->vcpu)) - pin_based_exec_ctrl &= ~PIN_BASED_POSTED_INTR; - - if (!enable_vnmi) - pin_based_exec_ctrl &= ~PIN_BASED_VIRTUAL_NMIS; - - if (!enable_preemption_timer) - pin_based_exec_ctrl &= ~PIN_BASED_VMX_PREEMPTION_TIMER; - - return pin_based_exec_ctrl; -} - -static void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - - pin_controls_set(vmx, vmx_pin_based_exec_ctrl(vmx)); - if (cpu_has_secondary_exec_ctrls()) { - if (kvm_vcpu_apicv_active(vcpu)) - secondary_exec_controls_setbit(vmx, - SECONDARY_EXEC_APIC_REGISTER_VIRT | - SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY); - else - secondary_exec_controls_clearbit(vmx, - SECONDARY_EXEC_APIC_REGISTER_VIRT | - SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY); - } - - if (cpu_has_vmx_msr_bitmap()) - vmx_update_msr_bitmap(vcpu); -} - -u32 vmx_exec_control(struct vcpu_vmx *vmx) -{ - u32 exec_control = vmcs_config.cpu_based_exec_ctrl; - - if (vmx->vcpu.arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT) - exec_control &= ~CPU_BASED_MOV_DR_EXITING; - - if (!cpu_need_tpr_shadow(&vmx->vcpu)) { - exec_control &= ~CPU_BASED_TPR_SHADOW; -#ifdef CONFIG_X86_64 - exec_control |= CPU_BASED_CR8_STORE_EXITING | - CPU_BASED_CR8_LOAD_EXITING; -#endif - } - if (!enable_ept) - exec_control |= CPU_BASED_CR3_STORE_EXITING | - CPU_BASED_CR3_LOAD_EXITING | - CPU_BASED_INVLPG_EXITING; - if (kvm_mwait_in_guest(vmx->vcpu.kvm)) - exec_control &= ~(CPU_BASED_MWAIT_EXITING | - CPU_BASED_MONITOR_EXITING); - if (kvm_hlt_in_guest(vmx->vcpu.kvm)) - exec_control &= ~CPU_BASED_HLT_EXITING; - return exec_control; -} - - -static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx) -{ - struct kvm_vcpu *vcpu = &vmx->vcpu; - - u32 exec_control = vmcs_config.cpu_based_2nd_exec_ctrl; - - if (pt_mode == PT_MODE_SYSTEM) - exec_control &= ~(SECONDARY_EXEC_PT_USE_GPA | SECONDARY_EXEC_PT_CONCEAL_VMX); - if (!cpu_need_virtualize_apic_accesses(vcpu)) - exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; - if (vmx->vpid == 0) - exec_control &= ~SECONDARY_EXEC_ENABLE_VPID; - if (!enable_ept) { - exec_control &= ~SECONDARY_EXEC_ENABLE_EPT; - enable_unrestricted_guest = 0; - } - if (!enable_unrestricted_guest) - exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST; - if (kvm_pause_in_guest(vmx->vcpu.kvm)) - exec_control &= ~SECONDARY_EXEC_PAUSE_LOOP_EXITING; - if (!kvm_vcpu_apicv_active(vcpu)) - exec_control &= ~(SECONDARY_EXEC_APIC_REGISTER_VIRT | - SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY); - exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE; - - /* SECONDARY_EXEC_DESC is enabled/disabled on writes to CR4.UMIP, - * in vmx_set_cr4. */ - exec_control &= ~SECONDARY_EXEC_DESC; - - /* SECONDARY_EXEC_SHADOW_VMCS is enabled when L1 executes VMPTRLD - (handle_vmptrld). - We can NOT enable shadow_vmcs here because we don't have yet - a current VMCS12 - */ - exec_control &= ~SECONDARY_EXEC_SHADOW_VMCS; - - if (!enable_pml) - exec_control &= ~SECONDARY_EXEC_ENABLE_PML; - - if (vmx_xsaves_supported()) { - /* Exposing XSAVES only when XSAVE is exposed */ - bool xsaves_enabled = - guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && - guest_cpuid_has(vcpu, X86_FEATURE_XSAVES); - - vcpu->arch.xsaves_enabled = xsaves_enabled; - - if (!xsaves_enabled) - exec_control &= ~SECONDARY_EXEC_XSAVES; - - if (nested) { - if (xsaves_enabled) - vmx->nested.msrs.secondary_ctls_high |= - SECONDARY_EXEC_XSAVES; - else - vmx->nested.msrs.secondary_ctls_high &= - ~SECONDARY_EXEC_XSAVES; - } - } - - if (vmx_rdtscp_supported()) { - bool rdtscp_enabled = guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP); - if (!rdtscp_enabled) - exec_control &= ~SECONDARY_EXEC_RDTSCP; - - if (nested) { - if (rdtscp_enabled) - vmx->nested.msrs.secondary_ctls_high |= - SECONDARY_EXEC_RDTSCP; - else - vmx->nested.msrs.secondary_ctls_high &= - ~SECONDARY_EXEC_RDTSCP; - } - } - - if (vmx_invpcid_supported()) { - /* Exposing INVPCID only when PCID is exposed */ - bool invpcid_enabled = - guest_cpuid_has(vcpu, X86_FEATURE_INVPCID) && - guest_cpuid_has(vcpu, X86_FEATURE_PCID); - - if (!invpcid_enabled) { - exec_control &= ~SECONDARY_EXEC_ENABLE_INVPCID; - guest_cpuid_clear(vcpu, X86_FEATURE_INVPCID); - } - - if (nested) { - if (invpcid_enabled) - vmx->nested.msrs.secondary_ctls_high |= - SECONDARY_EXEC_ENABLE_INVPCID; - else - vmx->nested.msrs.secondary_ctls_high &= - ~SECONDARY_EXEC_ENABLE_INVPCID; - } - } - - if (vmx_rdrand_supported()) { - bool rdrand_enabled = guest_cpuid_has(vcpu, X86_FEATURE_RDRAND); - if (rdrand_enabled) - exec_control &= ~SECONDARY_EXEC_RDRAND_EXITING; - - if (nested) { - if (rdrand_enabled) - vmx->nested.msrs.secondary_ctls_high |= - SECONDARY_EXEC_RDRAND_EXITING; - else - vmx->nested.msrs.secondary_ctls_high &= - ~SECONDARY_EXEC_RDRAND_EXITING; - } - } - - if (vmx_rdseed_supported()) { - bool rdseed_enabled = guest_cpuid_has(vcpu, X86_FEATURE_RDSEED); - if (rdseed_enabled) - exec_control &= ~SECONDARY_EXEC_RDSEED_EXITING; - - if (nested) { - if (rdseed_enabled) - vmx->nested.msrs.secondary_ctls_high |= - SECONDARY_EXEC_RDSEED_EXITING; - else - vmx->nested.msrs.secondary_ctls_high &= - ~SECONDARY_EXEC_RDSEED_EXITING; - } - } - - if (vmx_waitpkg_supported()) { - bool waitpkg_enabled = - guest_cpuid_has(vcpu, X86_FEATURE_WAITPKG); - - if (!waitpkg_enabled) - exec_control &= ~SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE; - - if (nested) { - if (waitpkg_enabled) - vmx->nested.msrs.secondary_ctls_high |= - SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE; - else - vmx->nested.msrs.secondary_ctls_high &= - ~SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE; - } - } - - vmx->secondary_exec_control = exec_control; -} - -static void ept_set_mmio_spte_mask(void) -{ - /* - * EPT Misconfigurations can be generated if the value of bits 2:0 - * of an EPT paging-structure entry is 110b (write/execute). - */ - kvm_mmu_set_mmio_spte_mask(VMX_EPT_RWX_MASK, - VMX_EPT_MISCONFIG_WX_VALUE, 0); -} - -#define VMX_XSS_EXIT_BITMAP 0 - -/* - * Noting that the initialization of Guest-state Area of VMCS is in - * vmx_vcpu_reset(). - */ -static void init_vmcs(struct vcpu_vmx *vmx) -{ - if (nested) - nested_vmx_set_vmcs_shadowing_bitmap(); - - if (cpu_has_vmx_msr_bitmap()) - vmcs_write64(MSR_BITMAP, __pa(vmx->vmcs01.msr_bitmap)); - - vmcs_write64(VMCS_LINK_POINTER, -1ull); /* 22.3.1.5 */ - - /* Control */ - pin_controls_set(vmx, vmx_pin_based_exec_ctrl(vmx)); - - exec_controls_set(vmx, vmx_exec_control(vmx)); - - if (cpu_has_secondary_exec_ctrls()) { - vmx_compute_secondary_exec_control(vmx); - secondary_exec_controls_set(vmx, vmx->secondary_exec_control); - } - - if (kvm_vcpu_apicv_active(&vmx->vcpu)) { - vmcs_write64(EOI_EXIT_BITMAP0, 0); - vmcs_write64(EOI_EXIT_BITMAP1, 0); - vmcs_write64(EOI_EXIT_BITMAP2, 0); - vmcs_write64(EOI_EXIT_BITMAP3, 0); - - vmcs_write16(GUEST_INTR_STATUS, 0); - - vmcs_write16(POSTED_INTR_NV, POSTED_INTR_VECTOR); - vmcs_write64(POSTED_INTR_DESC_ADDR, __pa((&vmx->pi_desc))); - } - - if (!kvm_pause_in_guest(vmx->vcpu.kvm)) { - vmcs_write32(PLE_GAP, ple_gap); - vmx->ple_window = ple_window; - vmx->ple_window_dirty = true; - } - - vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, 0); - vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, 0); - vmcs_write32(CR3_TARGET_COUNT, 0); /* 22.2.1 */ - - vmcs_write16(HOST_FS_SELECTOR, 0); /* 22.2.4 */ - vmcs_write16(HOST_GS_SELECTOR, 0); /* 22.2.4 */ - vmx_set_constant_host_state(vmx); - vmcs_writel(HOST_FS_BASE, 0); /* 22.2.4 */ - vmcs_writel(HOST_GS_BASE, 0); /* 22.2.4 */ - - if (cpu_has_vmx_vmfunc()) - vmcs_write64(VM_FUNCTION_CONTROL, 0); - - vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0); - vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, 0); - vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host.val)); - vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0); - vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest.val)); - - if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) - vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat); - - vm_exit_controls_set(vmx, vmx_vmexit_ctrl()); - - /* 22.2.1, 20.8.1 */ - vm_entry_controls_set(vmx, vmx_vmentry_ctrl()); - - vmx->vcpu.arch.cr0_guest_owned_bits = X86_CR0_TS; - vmcs_writel(CR0_GUEST_HOST_MASK, ~X86_CR0_TS); - - set_cr4_guest_host_mask(vmx); - - if (vmx->vpid != 0) - vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid); - - if (vmx_xsaves_supported()) - vmcs_write64(XSS_EXIT_BITMAP, VMX_XSS_EXIT_BITMAP); - - if (enable_pml) { - vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg)); - vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1); - } - - if (cpu_has_vmx_encls_vmexit()) - vmcs_write64(ENCLS_EXITING_BITMAP, -1ull); - - if (pt_mode == PT_MODE_HOST_GUEST) { - memset(&vmx->pt_desc, 0, sizeof(vmx->pt_desc)); - /* Bit[6~0] are forced to 1, writes are ignored. */ - vmx->pt_desc.guest.output_mask = 0x7F; - vmcs_write64(GUEST_IA32_RTIT_CTL, 0); - } -} - -static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - struct msr_data apic_base_msr; - u64 cr0; - - vmx->rmode.vm86_active = 0; - vmx->spec_ctrl = 0; - - vmx->msr_ia32_umwait_control = 0; - - vcpu->arch.microcode_version = 0x100000000ULL; - vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val(); - vmx->hv_deadline_tsc = -1; - kvm_set_cr8(vcpu, 0); - - if (!init_event) { - apic_base_msr.data = APIC_DEFAULT_PHYS_BASE | - MSR_IA32_APICBASE_ENABLE; - if (kvm_vcpu_is_reset_bsp(vcpu)) - apic_base_msr.data |= MSR_IA32_APICBASE_BSP; - apic_base_msr.host_initiated = true; - kvm_set_apic_base(vcpu, &apic_base_msr); - } - - vmx_segment_cache_clear(vmx); - - seg_setup(VCPU_SREG_CS); - vmcs_write16(GUEST_CS_SELECTOR, 0xf000); - vmcs_writel(GUEST_CS_BASE, 0xffff0000ul); - - seg_setup(VCPU_SREG_DS); - seg_setup(VCPU_SREG_ES); - seg_setup(VCPU_SREG_FS); - seg_setup(VCPU_SREG_GS); - seg_setup(VCPU_SREG_SS); - - vmcs_write16(GUEST_TR_SELECTOR, 0); - vmcs_writel(GUEST_TR_BASE, 0); - vmcs_write32(GUEST_TR_LIMIT, 0xffff); - vmcs_write32(GUEST_TR_AR_BYTES, 0x008b); - - vmcs_write16(GUEST_LDTR_SELECTOR, 0); - vmcs_writel(GUEST_LDTR_BASE, 0); - vmcs_write32(GUEST_LDTR_LIMIT, 0xffff); - vmcs_write32(GUEST_LDTR_AR_BYTES, 0x00082); - - if (!init_event) { - vmcs_write32(GUEST_SYSENTER_CS, 0); - vmcs_writel(GUEST_SYSENTER_ESP, 0); - vmcs_writel(GUEST_SYSENTER_EIP, 0); - vmcs_write64(GUEST_IA32_DEBUGCTL, 0); - } - - kvm_set_rflags(vcpu, X86_EFLAGS_FIXED); - kvm_rip_write(vcpu, 0xfff0); - - vmcs_writel(GUEST_GDTR_BASE, 0); - vmcs_write32(GUEST_GDTR_LIMIT, 0xffff); - - vmcs_writel(GUEST_IDTR_BASE, 0); - vmcs_write32(GUEST_IDTR_LIMIT, 0xffff); - - vmcs_write32(GUEST_ACTIVITY_STATE, GUEST_ACTIVITY_ACTIVE); - vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, 0); - vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, 0); - if (kvm_mpx_supported()) - vmcs_write64(GUEST_BNDCFGS, 0); - - setup_msrs(vmx); - - vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0); /* 22.2.1 */ - - if (cpu_has_vmx_tpr_shadow() && !init_event) { - vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, 0); - if (cpu_need_tpr_shadow(vcpu)) - vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, - __pa(vcpu->arch.apic->regs)); - vmcs_write32(TPR_THRESHOLD, 0); - } - - kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); - - cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET; - vmx->vcpu.arch.cr0 = cr0; - vmx_set_cr0(vcpu, cr0); /* enter rmode */ - vmx_set_cr4(vcpu, 0); - vmx_set_efer(vcpu, 0); - - update_exception_bitmap(vcpu); - - vpid_sync_context(vmx->vpid); - if (init_event) - vmx_clear_hlt(vcpu); -} - -static void enable_irq_window(struct kvm_vcpu *vcpu) -{ - exec_controls_setbit(to_vmx(vcpu), CPU_BASED_INTR_WINDOW_EXITING); -} - -static void enable_nmi_window(struct kvm_vcpu *vcpu) -{ - if (!enable_vnmi || - vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_STI) { - enable_irq_window(vcpu); - return; - } - - exec_controls_setbit(to_vmx(vcpu), CPU_BASED_NMI_WINDOW_EXITING); -} - -static void vmx_inject_irq(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - uint32_t intr; - int irq = vcpu->arch.interrupt.nr; - - trace_kvm_inj_virq(irq); - - ++vcpu->stat.irq_injections; - if (vmx->rmode.vm86_active) { - int inc_eip = 0; - if (vcpu->arch.interrupt.soft) - inc_eip = vcpu->arch.event_exit_inst_len; - kvm_inject_realmode_interrupt(vcpu, irq, inc_eip); - return; - } - intr = irq | INTR_INFO_VALID_MASK; - if (vcpu->arch.interrupt.soft) { - intr |= INTR_TYPE_SOFT_INTR; - vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, - vmx->vcpu.arch.event_exit_inst_len); - } else - intr |= INTR_TYPE_EXT_INTR; - vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr); - - vmx_clear_hlt(vcpu); -} - -static void vmx_inject_nmi(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - - if (!enable_vnmi) { - /* - * Tracking the NMI-blocked state in software is built upon - * finding the next open IRQ window. This, in turn, depends on - * well-behaving guests: They have to keep IRQs disabled at - * least as long as the NMI handler runs. Otherwise we may - * cause NMI nesting, maybe breaking the guest. But as this is - * highly unlikely, we can live with the residual risk. - */ - vmx->loaded_vmcs->soft_vnmi_blocked = 1; - vmx->loaded_vmcs->vnmi_blocked_time = 0; - } - - ++vcpu->stat.nmi_injections; - vmx->loaded_vmcs->nmi_known_unmasked = false; - - if (vmx->rmode.vm86_active) { - kvm_inject_realmode_interrupt(vcpu, NMI_VECTOR, 0); - return; - } - - vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, - INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK | NMI_VECTOR); - - vmx_clear_hlt(vcpu); -} - -bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - bool masked; - - if (!enable_vnmi) - return vmx->loaded_vmcs->soft_vnmi_blocked; - if (vmx->loaded_vmcs->nmi_known_unmasked) - return false; - masked = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_NMI; - vmx->loaded_vmcs->nmi_known_unmasked = !masked; - return masked; -} - -void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - - if (!enable_vnmi) { - if (vmx->loaded_vmcs->soft_vnmi_blocked != masked) { - vmx->loaded_vmcs->soft_vnmi_blocked = masked; - vmx->loaded_vmcs->vnmi_blocked_time = 0; - } - } else { - vmx->loaded_vmcs->nmi_known_unmasked = !masked; - if (masked) - vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, - GUEST_INTR_STATE_NMI); - else - vmcs_clear_bits(GUEST_INTERRUPTIBILITY_INFO, - GUEST_INTR_STATE_NMI); - } -} - -static int vmx_nmi_allowed(struct kvm_vcpu *vcpu) -{ - if (to_vmx(vcpu)->nested.nested_run_pending) - return 0; - - if (!enable_vnmi && - to_vmx(vcpu)->loaded_vmcs->soft_vnmi_blocked) - return 0; - - return !(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & - (GUEST_INTR_STATE_MOV_SS | GUEST_INTR_STATE_STI - | GUEST_INTR_STATE_NMI)); -} - -static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu) -{ - return (!to_vmx(vcpu)->nested.nested_run_pending && - vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) && - !(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & - (GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS)); -} - -static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) -{ - int ret; - - if (enable_unrestricted_guest) - return 0; - - ret = x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, addr, - PAGE_SIZE * 3); - if (ret) - return ret; - to_kvm_vmx(kvm)->tss_addr = addr; - return init_rmode_tss(kvm); -} - -static int vmx_set_identity_map_addr(struct kvm *kvm, u64 ident_addr) -{ - to_kvm_vmx(kvm)->ept_identity_map_addr = ident_addr; - return 0; -} - -static bool rmode_exception(struct kvm_vcpu *vcpu, int vec) -{ - switch (vec) { - case BP_VECTOR: - /* - * Update instruction length as we may reinject the exception - * from user space while in guest debugging mode. - */ - to_vmx(vcpu)->vcpu.arch.event_exit_inst_len = - vmcs_read32(VM_EXIT_INSTRUCTION_LEN); - if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) - return false; - /* fall through */ - case DB_VECTOR: - if (vcpu->guest_debug & - (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) - return false; - /* fall through */ - case DE_VECTOR: - case OF_VECTOR: - case BR_VECTOR: - case UD_VECTOR: - case DF_VECTOR: - case SS_VECTOR: - case GP_VECTOR: - case MF_VECTOR: - return true; - break; - } - return false; -} - -static int handle_rmode_exception(struct kvm_vcpu *vcpu, - int vec, u32 err_code) -{ - /* - * Instruction with address size override prefix opcode 0x67 - * Cause the #SS fault with 0 error code in VM86 mode. - */ - if (((vec == GP_VECTOR) || (vec == SS_VECTOR)) && err_code == 0) { - if (kvm_emulate_instruction(vcpu, 0)) { - if (vcpu->arch.halt_request) { - vcpu->arch.halt_request = 0; - return kvm_vcpu_halt(vcpu); - } - return 1; - } - return 0; - } - - /* - * Forward all other exceptions that are valid in real mode. - * FIXME: Breaks guest debugging in real mode, needs to be fixed with - * the required debugging infrastructure rework. - */ - kvm_queue_exception(vcpu, vec); - return 1; -} - -/* - * Trigger machine check on the host. We assume all the MSRs are already set up - * by the CPU and that we still run on the same CPU as the MCE occurred on. - * We pass a fake environment to the machine check handler because we want - * the guest to be always treated like user space, no matter what context - * it used internally. - */ -static void kvm_machine_check(void) -{ -#if defined(CONFIG_X86_MCE) && defined(CONFIG_X86_64) - struct pt_regs regs = { - .cs = 3, /* Fake ring 3 no matter what the guest ran on */ - .flags = X86_EFLAGS_IF, - }; - - do_machine_check(®s, 0); -#endif -} - -static int handle_machine_check(struct kvm_vcpu *vcpu) -{ - /* handled by vmx_vcpu_run() */ - return 1; -} - -static int handle_exception_nmi(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - struct kvm_run *kvm_run = vcpu->run; - u32 intr_info, ex_no, error_code; - unsigned long cr2, rip, dr6; - u32 vect_info; - - vect_info = vmx->idt_vectoring_info; - intr_info = vmx->exit_intr_info; - - if (is_machine_check(intr_info) || is_nmi(intr_info)) - return 1; /* handled by handle_exception_nmi_irqoff() */ - - if (is_invalid_opcode(intr_info)) - return handle_ud(vcpu); - - error_code = 0; - if (intr_info & INTR_INFO_DELIVER_CODE_MASK) - error_code = vmcs_read32(VM_EXIT_INTR_ERROR_CODE); - - if (!vmx->rmode.vm86_active && is_gp_fault(intr_info)) { - WARN_ON_ONCE(!enable_vmware_backdoor); - - /* - * VMware backdoor emulation on #GP interception only handles - * IN{S}, OUT{S}, and RDPMC, none of which generate a non-zero - * error code on #GP. - */ - if (error_code) { - kvm_queue_exception_e(vcpu, GP_VECTOR, error_code); - return 1; - } - return kvm_emulate_instruction(vcpu, EMULTYPE_VMWARE_GP); - } - - /* - * The #PF with PFEC.RSVD = 1 indicates the guest is accessing - * MMIO, it is better to report an internal error. - * See the comments in vmx_handle_exit. - */ - if ((vect_info & VECTORING_INFO_VALID_MASK) && - !(is_page_fault(intr_info) && !(error_code & PFERR_RSVD_MASK))) { - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_SIMUL_EX; - vcpu->run->internal.ndata = 3; - vcpu->run->internal.data[0] = vect_info; - vcpu->run->internal.data[1] = intr_info; - vcpu->run->internal.data[2] = error_code; - return 0; - } - - if (is_page_fault(intr_info)) { - cr2 = vmcs_readl(EXIT_QUALIFICATION); - /* EPT won't cause page fault directly */ - WARN_ON_ONCE(!vcpu->arch.apf.host_apf_reason && enable_ept); - return kvm_handle_page_fault(vcpu, error_code, cr2, NULL, 0); - } - - ex_no = intr_info & INTR_INFO_VECTOR_MASK; - - if (vmx->rmode.vm86_active && rmode_exception(vcpu, ex_no)) - return handle_rmode_exception(vcpu, ex_no, error_code); - - switch (ex_no) { - case AC_VECTOR: - kvm_queue_exception_e(vcpu, AC_VECTOR, error_code); - return 1; - case DB_VECTOR: - dr6 = vmcs_readl(EXIT_QUALIFICATION); - if (!(vcpu->guest_debug & - (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) { - vcpu->arch.dr6 &= ~DR_TRAP_BITS; - vcpu->arch.dr6 |= dr6 | DR6_RTM; - if (is_icebp(intr_info)) - WARN_ON(!skip_emulated_instruction(vcpu)); - - kvm_queue_exception(vcpu, DB_VECTOR); - return 1; - } - kvm_run->debug.arch.dr6 = dr6 | DR6_FIXED_1; - kvm_run->debug.arch.dr7 = vmcs_readl(GUEST_DR7); - /* fall through */ - case BP_VECTOR: - /* - * Update instruction length as we may reinject #BP from - * user space while in guest debugging mode. Reading it for - * #DB as well causes no harm, it is not used in that case. - */ - vmx->vcpu.arch.event_exit_inst_len = - vmcs_read32(VM_EXIT_INSTRUCTION_LEN); - kvm_run->exit_reason = KVM_EXIT_DEBUG; - rip = kvm_rip_read(vcpu); - kvm_run->debug.arch.pc = vmcs_readl(GUEST_CS_BASE) + rip; - kvm_run->debug.arch.exception = ex_no; - break; - default: - kvm_run->exit_reason = KVM_EXIT_EXCEPTION; - kvm_run->ex.exception = ex_no; - kvm_run->ex.error_code = error_code; - break; - } - return 0; -} - -static __always_inline int handle_external_interrupt(struct kvm_vcpu *vcpu) -{ - ++vcpu->stat.irq_exits; - return 1; -} - -static int handle_triple_fault(struct kvm_vcpu *vcpu) -{ - vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN; - vcpu->mmio_needed = 0; - return 0; -} - -static int handle_io(struct kvm_vcpu *vcpu) -{ - unsigned long exit_qualification; - int size, in, string; - unsigned port; - - exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - string = (exit_qualification & 16) != 0; - - ++vcpu->stat.io_exits; - - if (string) - return kvm_emulate_instruction(vcpu, 0); - - port = exit_qualification >> 16; - size = (exit_qualification & 7) + 1; - in = (exit_qualification & 8) != 0; - - return kvm_fast_pio(vcpu, size, port, in); -} - -static void -vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall) -{ - /* - * Patch in the VMCALL instruction: - */ - hypercall[0] = 0x0f; - hypercall[1] = 0x01; - hypercall[2] = 0xc1; -} - -/* called to set cr0 as appropriate for a mov-to-cr0 exit. */ -static int handle_set_cr0(struct kvm_vcpu *vcpu, unsigned long val) -{ - if (is_guest_mode(vcpu)) { - struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - unsigned long orig_val = val; - - /* - * We get here when L2 changed cr0 in a way that did not change - * any of L1's shadowed bits (see nested_vmx_exit_handled_cr), - * but did change L0 shadowed bits. So we first calculate the - * effective cr0 value that L1 would like to write into the - * hardware. It consists of the L2-owned bits from the new - * value combined with the L1-owned bits from L1's guest_cr0. - */ - val = (val & ~vmcs12->cr0_guest_host_mask) | - (vmcs12->guest_cr0 & vmcs12->cr0_guest_host_mask); - - if (!nested_guest_cr0_valid(vcpu, val)) - return 1; - - if (kvm_set_cr0(vcpu, val)) - return 1; - vmcs_writel(CR0_READ_SHADOW, orig_val); - return 0; - } else { - if (to_vmx(vcpu)->nested.vmxon && - !nested_host_cr0_valid(vcpu, val)) - return 1; - - return kvm_set_cr0(vcpu, val); - } -} - -static int handle_set_cr4(struct kvm_vcpu *vcpu, unsigned long val) -{ - if (is_guest_mode(vcpu)) { - struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - unsigned long orig_val = val; - - /* analogously to handle_set_cr0 */ - val = (val & ~vmcs12->cr4_guest_host_mask) | - (vmcs12->guest_cr4 & vmcs12->cr4_guest_host_mask); - if (kvm_set_cr4(vcpu, val)) - return 1; - vmcs_writel(CR4_READ_SHADOW, orig_val); - return 0; - } else - return kvm_set_cr4(vcpu, val); -} - -static int handle_desc(struct kvm_vcpu *vcpu) -{ - WARN_ON(!(vcpu->arch.cr4 & X86_CR4_UMIP)); - return kvm_emulate_instruction(vcpu, 0); -} - -static int handle_cr(struct kvm_vcpu *vcpu) -{ - unsigned long exit_qualification, val; - int cr; - int reg; - int err; - int ret; - - exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - cr = exit_qualification & 15; - reg = (exit_qualification >> 8) & 15; - switch ((exit_qualification >> 4) & 3) { - case 0: /* mov to cr */ - val = kvm_register_readl(vcpu, reg); - trace_kvm_cr_write(cr, val); - switch (cr) { - case 0: - err = handle_set_cr0(vcpu, val); - return kvm_complete_insn_gp(vcpu, err); - case 3: - WARN_ON_ONCE(enable_unrestricted_guest); - err = kvm_set_cr3(vcpu, val); - return kvm_complete_insn_gp(vcpu, err); - case 4: - err = handle_set_cr4(vcpu, val); - return kvm_complete_insn_gp(vcpu, err); - case 8: { - u8 cr8_prev = kvm_get_cr8(vcpu); - u8 cr8 = (u8)val; - err = kvm_set_cr8(vcpu, cr8); - ret = kvm_complete_insn_gp(vcpu, err); - if (lapic_in_kernel(vcpu)) - return ret; - if (cr8_prev <= cr8) - return ret; - /* - * TODO: we might be squashing a - * KVM_GUESTDBG_SINGLESTEP-triggered - * KVM_EXIT_DEBUG here. - */ - vcpu->run->exit_reason = KVM_EXIT_SET_TPR; - return 0; - } - } - break; - case 2: /* clts */ - WARN_ONCE(1, "Guest should always own CR0.TS"); - vmx_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~X86_CR0_TS)); - trace_kvm_cr_write(0, kvm_read_cr0(vcpu)); - return kvm_skip_emulated_instruction(vcpu); - case 1: /*mov from cr*/ - switch (cr) { - case 3: - WARN_ON_ONCE(enable_unrestricted_guest); - val = kvm_read_cr3(vcpu); - kvm_register_write(vcpu, reg, val); - trace_kvm_cr_read(cr, val); - return kvm_skip_emulated_instruction(vcpu); - case 8: - val = kvm_get_cr8(vcpu); - kvm_register_write(vcpu, reg, val); - trace_kvm_cr_read(cr, val); - return kvm_skip_emulated_instruction(vcpu); - } - break; - case 3: /* lmsw */ - val = (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f; - trace_kvm_cr_write(0, (kvm_read_cr0(vcpu) & ~0xful) | val); - kvm_lmsw(vcpu, val); - - return kvm_skip_emulated_instruction(vcpu); - default: - break; - } - vcpu->run->exit_reason = 0; - vcpu_unimpl(vcpu, "unhandled control register: op %d cr %d\n", - (int)(exit_qualification >> 4) & 3, cr); - return 0; -} - -static int handle_dr(struct kvm_vcpu *vcpu) -{ - unsigned long exit_qualification; - int dr, dr7, reg; - - exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - dr = exit_qualification & DEBUG_REG_ACCESS_NUM; - - /* First, if DR does not exist, trigger UD */ - if (!kvm_require_dr(vcpu, dr)) - return 1; - - /* Do not handle if the CPL > 0, will trigger GP on re-entry */ - if (!kvm_require_cpl(vcpu, 0)) - return 1; - dr7 = vmcs_readl(GUEST_DR7); - if (dr7 & DR7_GD) { - /* - * As the vm-exit takes precedence over the debug trap, we - * need to emulate the latter, either for the host or the - * guest debugging itself. - */ - if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) { - vcpu->run->debug.arch.dr6 = vcpu->arch.dr6; - vcpu->run->debug.arch.dr7 = dr7; - vcpu->run->debug.arch.pc = kvm_get_linear_rip(vcpu); - vcpu->run->debug.arch.exception = DB_VECTOR; - vcpu->run->exit_reason = KVM_EXIT_DEBUG; - return 0; - } else { - vcpu->arch.dr6 &= ~DR_TRAP_BITS; - vcpu->arch.dr6 |= DR6_BD | DR6_RTM; - kvm_queue_exception(vcpu, DB_VECTOR); - return 1; - } - } - - if (vcpu->guest_debug == 0) { - exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_MOV_DR_EXITING); - - /* - * No more DR vmexits; force a reload of the debug registers - * and reenter on this instruction. The next vmexit will - * retrieve the full state of the debug registers. - */ - vcpu->arch.switch_db_regs |= KVM_DEBUGREG_WONT_EXIT; - return 1; - } - - reg = DEBUG_REG_ACCESS_REG(exit_qualification); - if (exit_qualification & TYPE_MOV_FROM_DR) { - unsigned long val; - - if (kvm_get_dr(vcpu, dr, &val)) - return 1; - kvm_register_write(vcpu, reg, val); - } else - if (kvm_set_dr(vcpu, dr, kvm_register_readl(vcpu, reg))) - return 1; - - return kvm_skip_emulated_instruction(vcpu); -} - -static u64 vmx_get_dr6(struct kvm_vcpu *vcpu) -{ - return vcpu->arch.dr6; -} - -static void vmx_set_dr6(struct kvm_vcpu *vcpu, unsigned long val) -{ -} - -static void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) -{ - get_debugreg(vcpu->arch.db[0], 0); - get_debugreg(vcpu->arch.db[1], 1); - get_debugreg(vcpu->arch.db[2], 2); - get_debugreg(vcpu->arch.db[3], 3); - get_debugreg(vcpu->arch.dr6, 6); - vcpu->arch.dr7 = vmcs_readl(GUEST_DR7); - - vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_WONT_EXIT; - exec_controls_setbit(to_vmx(vcpu), CPU_BASED_MOV_DR_EXITING); -} - -static void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val) -{ - vmcs_writel(GUEST_DR7, val); -} - -static int handle_tpr_below_threshold(struct kvm_vcpu *vcpu) -{ - kvm_apic_update_ppr(vcpu); - return 1; -} - -static int handle_interrupt_window(struct kvm_vcpu *vcpu) -{ - exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_INTR_WINDOW_EXITING); - - kvm_make_request(KVM_REQ_EVENT, vcpu); - - ++vcpu->stat.irq_window_exits; - return 1; -} - -static int handle_vmcall(struct kvm_vcpu *vcpu) -{ - return kvm_emulate_hypercall(vcpu); -} - -static int handle_invd(struct kvm_vcpu *vcpu) -{ - return kvm_emulate_instruction(vcpu, 0); -} - -static int handle_invlpg(struct kvm_vcpu *vcpu) -{ - unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - - kvm_mmu_invlpg(vcpu, exit_qualification); - return kvm_skip_emulated_instruction(vcpu); -} - -static int handle_rdpmc(struct kvm_vcpu *vcpu) -{ - int err; - - err = kvm_rdpmc(vcpu); - return kvm_complete_insn_gp(vcpu, err); -} - -static int handle_wbinvd(struct kvm_vcpu *vcpu) -{ - return kvm_emulate_wbinvd(vcpu); -} - -static int handle_xsetbv(struct kvm_vcpu *vcpu) -{ - u64 new_bv = kvm_read_edx_eax(vcpu); - u32 index = kvm_rcx_read(vcpu); - - if (kvm_set_xcr(vcpu, index, new_bv) == 0) - return kvm_skip_emulated_instruction(vcpu); - return 1; -} - -static int handle_apic_access(struct kvm_vcpu *vcpu) -{ - if (likely(fasteoi)) { - unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - int access_type, offset; - - access_type = exit_qualification & APIC_ACCESS_TYPE; - offset = exit_qualification & APIC_ACCESS_OFFSET; - /* - * Sane guest uses MOV to write EOI, with written value - * not cared. So make a short-circuit here by avoiding - * heavy instruction emulation. - */ - if ((access_type == TYPE_LINEAR_APIC_INST_WRITE) && - (offset == APIC_EOI)) { - kvm_lapic_set_eoi(vcpu); - return kvm_skip_emulated_instruction(vcpu); - } - } - return kvm_emulate_instruction(vcpu, 0); -} - -static int handle_apic_eoi_induced(struct kvm_vcpu *vcpu) -{ - unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - int vector = exit_qualification & 0xff; - - /* EOI-induced VM exit is trap-like and thus no need to adjust IP */ - kvm_apic_set_eoi_accelerated(vcpu, vector); - return 1; -} - -static int handle_apic_write(struct kvm_vcpu *vcpu) -{ - unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - u32 offset = exit_qualification & 0xfff; - - /* APIC-write VM exit is trap-like and thus no need to adjust IP */ - kvm_apic_write_nodecode(vcpu, offset); - return 1; -} - -static int handle_task_switch(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long exit_qualification; - bool has_error_code = false; - u32 error_code = 0; - u16 tss_selector; - int reason, type, idt_v, idt_index; - - idt_v = (vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK); - idt_index = (vmx->idt_vectoring_info & VECTORING_INFO_VECTOR_MASK); - type = (vmx->idt_vectoring_info & VECTORING_INFO_TYPE_MASK); - - exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - - reason = (u32)exit_qualification >> 30; - if (reason == TASK_SWITCH_GATE && idt_v) { - switch (type) { - case INTR_TYPE_NMI_INTR: - vcpu->arch.nmi_injected = false; - vmx_set_nmi_mask(vcpu, true); - break; - case INTR_TYPE_EXT_INTR: - case INTR_TYPE_SOFT_INTR: - kvm_clear_interrupt_queue(vcpu); - break; - case INTR_TYPE_HARD_EXCEPTION: - if (vmx->idt_vectoring_info & - VECTORING_INFO_DELIVER_CODE_MASK) { - has_error_code = true; - error_code = - vmcs_read32(IDT_VECTORING_ERROR_CODE); - } - /* fall through */ - case INTR_TYPE_SOFT_EXCEPTION: - kvm_clear_exception_queue(vcpu); - break; - default: - break; - } - } - tss_selector = exit_qualification; - - if (!idt_v || (type != INTR_TYPE_HARD_EXCEPTION && - type != INTR_TYPE_EXT_INTR && - type != INTR_TYPE_NMI_INTR)) - WARN_ON(!skip_emulated_instruction(vcpu)); - - /* - * TODO: What about debug traps on tss switch? - * Are we supposed to inject them and update dr6? - */ - return kvm_task_switch(vcpu, tss_selector, - type == INTR_TYPE_SOFT_INTR ? idt_index : -1, - reason, has_error_code, error_code); -} - -static int handle_ept_violation(struct kvm_vcpu *vcpu) -{ - unsigned long exit_qualification; - gpa_t gpa; - u64 error_code; - - exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - - /* - * EPT violation happened while executing iret from NMI, - * "blocked by NMI" bit has to be set before next VM entry. - * There are errata that may cause this bit to not be set: - * AAK134, BY25. - */ - if (!(to_vmx(vcpu)->idt_vectoring_info & VECTORING_INFO_VALID_MASK) && - enable_vnmi && - (exit_qualification & INTR_INFO_UNBLOCK_NMI)) - vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, GUEST_INTR_STATE_NMI); - - gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS); - trace_kvm_page_fault(gpa, exit_qualification); - - /* Is it a read fault? */ - error_code = (exit_qualification & EPT_VIOLATION_ACC_READ) - ? PFERR_USER_MASK : 0; - /* Is it a write fault? */ - error_code |= (exit_qualification & EPT_VIOLATION_ACC_WRITE) - ? PFERR_WRITE_MASK : 0; - /* Is it a fetch fault? */ - error_code |= (exit_qualification & EPT_VIOLATION_ACC_INSTR) - ? PFERR_FETCH_MASK : 0; - /* ept page table entry is present? */ - error_code |= (exit_qualification & - (EPT_VIOLATION_READABLE | EPT_VIOLATION_WRITABLE | - EPT_VIOLATION_EXECUTABLE)) - ? PFERR_PRESENT_MASK : 0; - - error_code |= (exit_qualification & 0x100) != 0 ? - PFERR_GUEST_FINAL_MASK : PFERR_GUEST_PAGE_MASK; - - vcpu->arch.exit_qualification = exit_qualification; - return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0); -} - -static int handle_ept_misconfig(struct kvm_vcpu *vcpu) -{ - gpa_t gpa; - - /* - * A nested guest cannot optimize MMIO vmexits, because we have an - * nGPA here instead of the required GPA. - */ - gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS); - if (!is_guest_mode(vcpu) && - !kvm_io_bus_write(vcpu, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) { - trace_kvm_fast_mmio(gpa); - return kvm_skip_emulated_instruction(vcpu); - } - - return kvm_mmu_page_fault(vcpu, gpa, PFERR_RSVD_MASK, NULL, 0); -} - -static int handle_nmi_window(struct kvm_vcpu *vcpu) -{ - WARN_ON_ONCE(!enable_vnmi); - exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_NMI_WINDOW_EXITING); - ++vcpu->stat.nmi_window_exits; - kvm_make_request(KVM_REQ_EVENT, vcpu); - - return 1; -} - -static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - bool intr_window_requested; - unsigned count = 130; - - /* - * We should never reach the point where we are emulating L2 - * due to invalid guest state as that means we incorrectly - * allowed a nested VMEntry with an invalid vmcs12. - */ - WARN_ON_ONCE(vmx->emulation_required && vmx->nested.nested_run_pending); - - intr_window_requested = exec_controls_get(vmx) & - CPU_BASED_INTR_WINDOW_EXITING; - - while (vmx->emulation_required && count-- != 0) { - if (intr_window_requested && vmx_interrupt_allowed(vcpu)) - return handle_interrupt_window(&vmx->vcpu); - - if (kvm_test_request(KVM_REQ_EVENT, vcpu)) - return 1; - - if (!kvm_emulate_instruction(vcpu, 0)) - return 0; - - if (vmx->emulation_required && !vmx->rmode.vm86_active && - vcpu->arch.exception.pending) { - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = - KVM_INTERNAL_ERROR_EMULATION; - vcpu->run->internal.ndata = 0; - return 0; - } - - if (vcpu->arch.halt_request) { - vcpu->arch.halt_request = 0; - return kvm_vcpu_halt(vcpu); - } - - /* - * Note, return 1 and not 0, vcpu_run() is responsible for - * morphing the pending signal into the proper return code. - */ - if (signal_pending(current)) - return 1; - - if (need_resched()) - schedule(); - } - - return 1; -} - -static void grow_ple_window(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned int old = vmx->ple_window; - - vmx->ple_window = __grow_ple_window(old, ple_window, - ple_window_grow, - ple_window_max); - - if (vmx->ple_window != old) { - vmx->ple_window_dirty = true; - trace_kvm_ple_window_update(vcpu->vcpu_id, - vmx->ple_window, old); - } -} - -static void shrink_ple_window(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned int old = vmx->ple_window; - - vmx->ple_window = __shrink_ple_window(old, ple_window, - ple_window_shrink, - ple_window); - - if (vmx->ple_window != old) { - vmx->ple_window_dirty = true; - trace_kvm_ple_window_update(vcpu->vcpu_id, - vmx->ple_window, old); - } -} - -/* - * Handler for POSTED_INTERRUPT_WAKEUP_VECTOR. - */ -static void wakeup_handler(void) -{ - struct kvm_vcpu *vcpu; - int cpu = smp_processor_id(); - - spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu)); - list_for_each_entry(vcpu, &per_cpu(blocked_vcpu_on_cpu, cpu), - blocked_vcpu_list) { - struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); - - if (pi_test_on(pi_desc) == 1) - kvm_vcpu_kick(vcpu); - } - spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu)); -} - -static void vmx_enable_tdp(void) -{ - kvm_mmu_set_mask_ptes(VMX_EPT_READABLE_MASK, - enable_ept_ad_bits ? VMX_EPT_ACCESS_BIT : 0ull, - enable_ept_ad_bits ? VMX_EPT_DIRTY_BIT : 0ull, - 0ull, VMX_EPT_EXECUTABLE_MASK, - cpu_has_vmx_ept_execute_only() ? 0ull : VMX_EPT_READABLE_MASK, - VMX_EPT_RWX_MASK, 0ull); - - ept_set_mmio_spte_mask(); - kvm_enable_tdp(); -} - -/* - * Indicate a busy-waiting vcpu in spinlock. We do not enable the PAUSE - * exiting, so only get here on cpu with PAUSE-Loop-Exiting. - */ -static int handle_pause(struct kvm_vcpu *vcpu) -{ - if (!kvm_pause_in_guest(vcpu->kvm)) - grow_ple_window(vcpu); - - /* - * Intel sdm vol3 ch-25.1.3 says: The "PAUSE-loop exiting" - * VM-execution control is ignored if CPL > 0. OTOH, KVM - * never set PAUSE_EXITING and just set PLE if supported, - * so the vcpu must be CPL=0 if it gets a PAUSE exit. - */ - kvm_vcpu_on_spin(vcpu, true); - return kvm_skip_emulated_instruction(vcpu); -} - -static int handle_nop(struct kvm_vcpu *vcpu) -{ - return kvm_skip_emulated_instruction(vcpu); -} - -static int handle_mwait(struct kvm_vcpu *vcpu) -{ - printk_once(KERN_WARNING "kvm: MWAIT instruction emulated as NOP!\n"); - return handle_nop(vcpu); -} - -static int handle_invalid_op(struct kvm_vcpu *vcpu) -{ - kvm_queue_exception(vcpu, UD_VECTOR); - return 1; -} - -static int handle_monitor_trap(struct kvm_vcpu *vcpu) -{ - return 1; -} - -static int handle_monitor(struct kvm_vcpu *vcpu) -{ - printk_once(KERN_WARNING "kvm: MONITOR instruction emulated as NOP!\n"); - return handle_nop(vcpu); -} - -static int handle_invpcid(struct kvm_vcpu *vcpu) -{ - u32 vmx_instruction_info; - unsigned long type; - bool pcid_enabled; - gva_t gva; - struct x86_exception e; - unsigned i; - unsigned long roots_to_free = 0; - struct { - u64 pcid; - u64 gla; - } operand; - - if (!guest_cpuid_has(vcpu, X86_FEATURE_INVPCID)) { - kvm_queue_exception(vcpu, UD_VECTOR); - return 1; - } - - vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); - type = kvm_register_readl(vcpu, (vmx_instruction_info >> 28) & 0xf); - - if (type > 3) { - kvm_inject_gp(vcpu, 0); - return 1; - } - - /* According to the Intel instruction reference, the memory operand - * is read even if it isn't needed (e.g., for type==all) - */ - if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION), - vmx_instruction_info, false, - sizeof(operand), &gva)) - return 1; - - if (kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e)) { - kvm_inject_page_fault(vcpu, &e); - return 1; - } - - if (operand.pcid >> 12 != 0) { - kvm_inject_gp(vcpu, 0); - return 1; - } - - pcid_enabled = kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE); - - switch (type) { - case INVPCID_TYPE_INDIV_ADDR: - if ((!pcid_enabled && (operand.pcid != 0)) || - is_noncanonical_address(operand.gla, vcpu)) { - kvm_inject_gp(vcpu, 0); - return 1; - } - kvm_mmu_invpcid_gva(vcpu, operand.gla, operand.pcid); - return kvm_skip_emulated_instruction(vcpu); - - case INVPCID_TYPE_SINGLE_CTXT: - if (!pcid_enabled && (operand.pcid != 0)) { - kvm_inject_gp(vcpu, 0); - return 1; - } - - if (kvm_get_active_pcid(vcpu) == operand.pcid) { - kvm_mmu_sync_roots(vcpu); - kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); - } - - for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) - if (kvm_get_pcid(vcpu, vcpu->arch.mmu->prev_roots[i].cr3) - == operand.pcid) - roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i); - - kvm_mmu_free_roots(vcpu, vcpu->arch.mmu, roots_to_free); - /* - * If neither the current cr3 nor any of the prev_roots use the - * given PCID, then nothing needs to be done here because a - * resync will happen anyway before switching to any other CR3. - */ - - return kvm_skip_emulated_instruction(vcpu); - - case INVPCID_TYPE_ALL_NON_GLOBAL: - /* - * Currently, KVM doesn't mark global entries in the shadow - * page tables, so a non-global flush just degenerates to a - * global flush. If needed, we could optimize this later by - * keeping track of global entries in shadow page tables. - */ - - /* fall-through */ - case INVPCID_TYPE_ALL_INCL_GLOBAL: - kvm_mmu_unload(vcpu); - return kvm_skip_emulated_instruction(vcpu); - - default: - BUG(); /* We have already checked above that type <= 3 */ - } -} - -static int handle_pml_full(struct kvm_vcpu *vcpu) -{ - unsigned long exit_qualification; - - trace_kvm_pml_full(vcpu->vcpu_id); - - exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - - /* - * PML buffer FULL happened while executing iret from NMI, - * "blocked by NMI" bit has to be set before next VM entry. - */ - if (!(to_vmx(vcpu)->idt_vectoring_info & VECTORING_INFO_VALID_MASK) && - enable_vnmi && - (exit_qualification & INTR_INFO_UNBLOCK_NMI)) - vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, - GUEST_INTR_STATE_NMI); - - /* - * PML buffer already flushed at beginning of VMEXIT. Nothing to do - * here.., and there's no userspace involvement needed for PML. - */ - return 1; -} - -static int handle_preemption_timer(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - - if (!vmx->req_immediate_exit && - !unlikely(vmx->loaded_vmcs->hv_timer_soft_disabled)) - kvm_lapic_expired_hv_timer(vcpu); - - return 1; -} - -/* - * When nested=0, all VMX instruction VM Exits filter here. The handlers - * are overwritten by nested_vmx_setup() when nested=1. - */ -static int handle_vmx_instruction(struct kvm_vcpu *vcpu) -{ - kvm_queue_exception(vcpu, UD_VECTOR); - return 1; -} - -static int handle_encls(struct kvm_vcpu *vcpu) -{ - /* - * SGX virtualization is not yet supported. There is no software - * enable bit for SGX, so we have to trap ENCLS and inject a #UD - * to prevent the guest from executing ENCLS. - */ - kvm_queue_exception(vcpu, UD_VECTOR); - return 1; -} - -/* - * The exit handlers return 1 if the exit was handled fully and guest execution - * may resume. Otherwise they set the kvm_run parameter to indicate what needs - * to be done to userspace and return 0. - */ -static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { - [EXIT_REASON_EXCEPTION_NMI] = handle_exception_nmi, - [EXIT_REASON_EXTERNAL_INTERRUPT] = handle_external_interrupt, - [EXIT_REASON_TRIPLE_FAULT] = handle_triple_fault, - [EXIT_REASON_NMI_WINDOW] = handle_nmi_window, - [EXIT_REASON_IO_INSTRUCTION] = handle_io, - [EXIT_REASON_CR_ACCESS] = handle_cr, - [EXIT_REASON_DR_ACCESS] = handle_dr, - [EXIT_REASON_CPUID] = kvm_emulate_cpuid, - [EXIT_REASON_MSR_READ] = kvm_emulate_rdmsr, - [EXIT_REASON_MSR_WRITE] = kvm_emulate_wrmsr, - [EXIT_REASON_INTERRUPT_WINDOW] = handle_interrupt_window, - [EXIT_REASON_HLT] = kvm_emulate_halt, - [EXIT_REASON_INVD] = handle_invd, - [EXIT_REASON_INVLPG] = handle_invlpg, - [EXIT_REASON_RDPMC] = handle_rdpmc, - [EXIT_REASON_VMCALL] = handle_vmcall, - [EXIT_REASON_VMCLEAR] = handle_vmx_instruction, - [EXIT_REASON_VMLAUNCH] = handle_vmx_instruction, - [EXIT_REASON_VMPTRLD] = handle_vmx_instruction, - [EXIT_REASON_VMPTRST] = handle_vmx_instruction, - [EXIT_REASON_VMREAD] = handle_vmx_instruction, - [EXIT_REASON_VMRESUME] = handle_vmx_instruction, - [EXIT_REASON_VMWRITE] = handle_vmx_instruction, - [EXIT_REASON_VMOFF] = handle_vmx_instruction, - [EXIT_REASON_VMON] = handle_vmx_instruction, - [EXIT_REASON_TPR_BELOW_THRESHOLD] = handle_tpr_below_threshold, - [EXIT_REASON_APIC_ACCESS] = handle_apic_access, - [EXIT_REASON_APIC_WRITE] = handle_apic_write, - [EXIT_REASON_EOI_INDUCED] = handle_apic_eoi_induced, - [EXIT_REASON_WBINVD] = handle_wbinvd, - [EXIT_REASON_XSETBV] = handle_xsetbv, - [EXIT_REASON_TASK_SWITCH] = handle_task_switch, - [EXIT_REASON_MCE_DURING_VMENTRY] = handle_machine_check, - [EXIT_REASON_GDTR_IDTR] = handle_desc, - [EXIT_REASON_LDTR_TR] = handle_desc, - [EXIT_REASON_EPT_VIOLATION] = handle_ept_violation, - [EXIT_REASON_EPT_MISCONFIG] = handle_ept_misconfig, - [EXIT_REASON_PAUSE_INSTRUCTION] = handle_pause, - [EXIT_REASON_MWAIT_INSTRUCTION] = handle_mwait, - [EXIT_REASON_MONITOR_TRAP_FLAG] = handle_monitor_trap, - [EXIT_REASON_MONITOR_INSTRUCTION] = handle_monitor, - [EXIT_REASON_INVEPT] = handle_vmx_instruction, - [EXIT_REASON_INVVPID] = handle_vmx_instruction, - [EXIT_REASON_RDRAND] = handle_invalid_op, - [EXIT_REASON_RDSEED] = handle_invalid_op, - [EXIT_REASON_PML_FULL] = handle_pml_full, - [EXIT_REASON_INVPCID] = handle_invpcid, - [EXIT_REASON_VMFUNC] = handle_vmx_instruction, - [EXIT_REASON_PREEMPTION_TIMER] = handle_preemption_timer, - [EXIT_REASON_ENCLS] = handle_encls, -}; - -static const int kvm_vmx_max_exit_handlers = - ARRAY_SIZE(kvm_vmx_exit_handlers); - -static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2) -{ - *info1 = vmcs_readl(EXIT_QUALIFICATION); - *info2 = vmcs_read32(VM_EXIT_INTR_INFO); -} - -static void vmx_destroy_pml_buffer(struct vcpu_vmx *vmx) -{ - if (vmx->pml_pg) { - __free_page(vmx->pml_pg); - vmx->pml_pg = NULL; - } -} - -static void vmx_flush_pml_buffer(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - u64 *pml_buf; - u16 pml_idx; - - pml_idx = vmcs_read16(GUEST_PML_INDEX); - - /* Do nothing if PML buffer is empty */ - if (pml_idx == (PML_ENTITY_NUM - 1)) - return; - - /* PML index always points to next available PML buffer entity */ - if (pml_idx >= PML_ENTITY_NUM) - pml_idx = 0; - else - pml_idx++; - - pml_buf = page_address(vmx->pml_pg); - for (; pml_idx < PML_ENTITY_NUM; pml_idx++) { - u64 gpa; - - gpa = pml_buf[pml_idx]; - WARN_ON(gpa & (PAGE_SIZE - 1)); - kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT); - } - - /* reset PML index */ - vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1); -} - -/* - * Flush all vcpus' PML buffer and update logged GPAs to dirty_bitmap. - * Called before reporting dirty_bitmap to userspace. - */ -static void kvm_flush_pml_buffers(struct kvm *kvm) -{ - int i; - struct kvm_vcpu *vcpu; - /* - * We only need to kick vcpu out of guest mode here, as PML buffer - * is flushed at beginning of all VMEXITs, and it's obvious that only - * vcpus running in guest are possible to have unflushed GPAs in PML - * buffer. - */ - kvm_for_each_vcpu(i, vcpu, kvm) - kvm_vcpu_kick(vcpu); -} - -static void vmx_dump_sel(char *name, uint32_t sel) -{ - pr_err("%s sel=0x%04x, attr=0x%05x, limit=0x%08x, base=0x%016lx\n", - name, vmcs_read16(sel), - vmcs_read32(sel + GUEST_ES_AR_BYTES - GUEST_ES_SELECTOR), - vmcs_read32(sel + GUEST_ES_LIMIT - GUEST_ES_SELECTOR), - vmcs_readl(sel + GUEST_ES_BASE - GUEST_ES_SELECTOR)); -} - -static void vmx_dump_dtsel(char *name, uint32_t limit) -{ - pr_err("%s limit=0x%08x, base=0x%016lx\n", - name, vmcs_read32(limit), - vmcs_readl(limit + GUEST_GDTR_BASE - GUEST_GDTR_LIMIT)); -} - -void dump_vmcs(void) -{ - u32 vmentry_ctl, vmexit_ctl; - u32 cpu_based_exec_ctrl, pin_based_exec_ctrl, secondary_exec_control; - unsigned long cr4; - u64 efer; - int i, n; - - if (!dump_invalid_vmcs) { - pr_warn_ratelimited("set kvm_intel.dump_invalid_vmcs=1 to dump internal KVM state.\n"); - return; - } - - vmentry_ctl = vmcs_read32(VM_ENTRY_CONTROLS); - vmexit_ctl = vmcs_read32(VM_EXIT_CONTROLS); - cpu_based_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); - pin_based_exec_ctrl = vmcs_read32(PIN_BASED_VM_EXEC_CONTROL); - cr4 = vmcs_readl(GUEST_CR4); - efer = vmcs_read64(GUEST_IA32_EFER); - secondary_exec_control = 0; - if (cpu_has_secondary_exec_ctrls()) - secondary_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); - - pr_err("*** Guest State ***\n"); - pr_err("CR0: actual=0x%016lx, shadow=0x%016lx, gh_mask=%016lx\n", - vmcs_readl(GUEST_CR0), vmcs_readl(CR0_READ_SHADOW), - vmcs_readl(CR0_GUEST_HOST_MASK)); - pr_err("CR4: actual=0x%016lx, shadow=0x%016lx, gh_mask=%016lx\n", - cr4, vmcs_readl(CR4_READ_SHADOW), vmcs_readl(CR4_GUEST_HOST_MASK)); - pr_err("CR3 = 0x%016lx\n", vmcs_readl(GUEST_CR3)); - if ((secondary_exec_control & SECONDARY_EXEC_ENABLE_EPT) && - (cr4 & X86_CR4_PAE) && !(efer & EFER_LMA)) - { - pr_err("PDPTR0 = 0x%016llx PDPTR1 = 0x%016llx\n", - vmcs_read64(GUEST_PDPTR0), vmcs_read64(GUEST_PDPTR1)); - pr_err("PDPTR2 = 0x%016llx PDPTR3 = 0x%016llx\n", - vmcs_read64(GUEST_PDPTR2), vmcs_read64(GUEST_PDPTR3)); - } - pr_err("RSP = 0x%016lx RIP = 0x%016lx\n", - vmcs_readl(GUEST_RSP), vmcs_readl(GUEST_RIP)); - pr_err("RFLAGS=0x%08lx DR7 = 0x%016lx\n", - vmcs_readl(GUEST_RFLAGS), vmcs_readl(GUEST_DR7)); - pr_err("Sysenter RSP=%016lx CS:RIP=%04x:%016lx\n", - vmcs_readl(GUEST_SYSENTER_ESP), - vmcs_read32(GUEST_SYSENTER_CS), vmcs_readl(GUEST_SYSENTER_EIP)); - vmx_dump_sel("CS: ", GUEST_CS_SELECTOR); - vmx_dump_sel("DS: ", GUEST_DS_SELECTOR); - vmx_dump_sel("SS: ", GUEST_SS_SELECTOR); - vmx_dump_sel("ES: ", GUEST_ES_SELECTOR); - vmx_dump_sel("FS: ", GUEST_FS_SELECTOR); - vmx_dump_sel("GS: ", GUEST_GS_SELECTOR); - vmx_dump_dtsel("GDTR:", GUEST_GDTR_LIMIT); - vmx_dump_sel("LDTR:", GUEST_LDTR_SELECTOR); - vmx_dump_dtsel("IDTR:", GUEST_IDTR_LIMIT); - vmx_dump_sel("TR: ", GUEST_TR_SELECTOR); - if ((vmexit_ctl & (VM_EXIT_SAVE_IA32_PAT | VM_EXIT_SAVE_IA32_EFER)) || - (vmentry_ctl & (VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_LOAD_IA32_EFER))) - pr_err("EFER = 0x%016llx PAT = 0x%016llx\n", - efer, vmcs_read64(GUEST_IA32_PAT)); - pr_err("DebugCtl = 0x%016llx DebugExceptions = 0x%016lx\n", - vmcs_read64(GUEST_IA32_DEBUGCTL), - vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS)); - if (cpu_has_load_perf_global_ctrl() && - vmentry_ctl & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) - pr_err("PerfGlobCtl = 0x%016llx\n", - vmcs_read64(GUEST_IA32_PERF_GLOBAL_CTRL)); - if (vmentry_ctl & VM_ENTRY_LOAD_BNDCFGS) - pr_err("BndCfgS = 0x%016llx\n", vmcs_read64(GUEST_BNDCFGS)); - pr_err("Interruptibility = %08x ActivityState = %08x\n", - vmcs_read32(GUEST_INTERRUPTIBILITY_INFO), - vmcs_read32(GUEST_ACTIVITY_STATE)); - if (secondary_exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY) - pr_err("InterruptStatus = %04x\n", - vmcs_read16(GUEST_INTR_STATUS)); - - pr_err("*** Host State ***\n"); - pr_err("RIP = 0x%016lx RSP = 0x%016lx\n", - vmcs_readl(HOST_RIP), vmcs_readl(HOST_RSP)); - pr_err("CS=%04x SS=%04x DS=%04x ES=%04x FS=%04x GS=%04x TR=%04x\n", - vmcs_read16(HOST_CS_SELECTOR), vmcs_read16(HOST_SS_SELECTOR), - vmcs_read16(HOST_DS_SELECTOR), vmcs_read16(HOST_ES_SELECTOR), - vmcs_read16(HOST_FS_SELECTOR), vmcs_read16(HOST_GS_SELECTOR), - vmcs_read16(HOST_TR_SELECTOR)); - pr_err("FSBase=%016lx GSBase=%016lx TRBase=%016lx\n", - vmcs_readl(HOST_FS_BASE), vmcs_readl(HOST_GS_BASE), - vmcs_readl(HOST_TR_BASE)); - pr_err("GDTBase=%016lx IDTBase=%016lx\n", - vmcs_readl(HOST_GDTR_BASE), vmcs_readl(HOST_IDTR_BASE)); - pr_err("CR0=%016lx CR3=%016lx CR4=%016lx\n", - vmcs_readl(HOST_CR0), vmcs_readl(HOST_CR3), - vmcs_readl(HOST_CR4)); - pr_err("Sysenter RSP=%016lx CS:RIP=%04x:%016lx\n", - vmcs_readl(HOST_IA32_SYSENTER_ESP), - vmcs_read32(HOST_IA32_SYSENTER_CS), - vmcs_readl(HOST_IA32_SYSENTER_EIP)); - if (vmexit_ctl & (VM_EXIT_LOAD_IA32_PAT | VM_EXIT_LOAD_IA32_EFER)) - pr_err("EFER = 0x%016llx PAT = 0x%016llx\n", - vmcs_read64(HOST_IA32_EFER), - vmcs_read64(HOST_IA32_PAT)); - if (cpu_has_load_perf_global_ctrl() && - vmexit_ctl & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL) - pr_err("PerfGlobCtl = 0x%016llx\n", - vmcs_read64(HOST_IA32_PERF_GLOBAL_CTRL)); - - pr_err("*** Control State ***\n"); - pr_err("PinBased=%08x CPUBased=%08x SecondaryExec=%08x\n", - pin_based_exec_ctrl, cpu_based_exec_ctrl, secondary_exec_control); - pr_err("EntryControls=%08x ExitControls=%08x\n", vmentry_ctl, vmexit_ctl); - pr_err("ExceptionBitmap=%08x PFECmask=%08x PFECmatch=%08x\n", - vmcs_read32(EXCEPTION_BITMAP), - vmcs_read32(PAGE_FAULT_ERROR_CODE_MASK), - vmcs_read32(PAGE_FAULT_ERROR_CODE_MATCH)); - pr_err("VMEntry: intr_info=%08x errcode=%08x ilen=%08x\n", - vmcs_read32(VM_ENTRY_INTR_INFO_FIELD), - vmcs_read32(VM_ENTRY_EXCEPTION_ERROR_CODE), - vmcs_read32(VM_ENTRY_INSTRUCTION_LEN)); - pr_err("VMExit: intr_info=%08x errcode=%08x ilen=%08x\n", - vmcs_read32(VM_EXIT_INTR_INFO), - vmcs_read32(VM_EXIT_INTR_ERROR_CODE), - vmcs_read32(VM_EXIT_INSTRUCTION_LEN)); - pr_err(" reason=%08x qualification=%016lx\n", - vmcs_read32(VM_EXIT_REASON), vmcs_readl(EXIT_QUALIFICATION)); - pr_err("IDTVectoring: info=%08x errcode=%08x\n", - vmcs_read32(IDT_VECTORING_INFO_FIELD), - vmcs_read32(IDT_VECTORING_ERROR_CODE)); - pr_err("TSC Offset = 0x%016llx\n", vmcs_read64(TSC_OFFSET)); - if (secondary_exec_control & SECONDARY_EXEC_TSC_SCALING) - pr_err("TSC Multiplier = 0x%016llx\n", - vmcs_read64(TSC_MULTIPLIER)); - if (cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW) { - if (secondary_exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY) { - u16 status = vmcs_read16(GUEST_INTR_STATUS); - pr_err("SVI|RVI = %02x|%02x ", status >> 8, status & 0xff); - } - pr_cont("TPR Threshold = 0x%02x\n", vmcs_read32(TPR_THRESHOLD)); - if (secondary_exec_control & SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) - pr_err("APIC-access addr = 0x%016llx ", vmcs_read64(APIC_ACCESS_ADDR)); - pr_cont("virt-APIC addr = 0x%016llx\n", vmcs_read64(VIRTUAL_APIC_PAGE_ADDR)); - } - if (pin_based_exec_ctrl & PIN_BASED_POSTED_INTR) - pr_err("PostedIntrVec = 0x%02x\n", vmcs_read16(POSTED_INTR_NV)); - if ((secondary_exec_control & SECONDARY_EXEC_ENABLE_EPT)) - pr_err("EPT pointer = 0x%016llx\n", vmcs_read64(EPT_POINTER)); - n = vmcs_read32(CR3_TARGET_COUNT); - for (i = 0; i + 1 < n; i += 4) - pr_err("CR3 target%u=%016lx target%u=%016lx\n", - i, vmcs_readl(CR3_TARGET_VALUE0 + i * 2), - i + 1, vmcs_readl(CR3_TARGET_VALUE0 + i * 2 + 2)); - if (i < n) - pr_err("CR3 target%u=%016lx\n", - i, vmcs_readl(CR3_TARGET_VALUE0 + i * 2)); - if (secondary_exec_control & SECONDARY_EXEC_PAUSE_LOOP_EXITING) - pr_err("PLE Gap=%08x Window=%08x\n", - vmcs_read32(PLE_GAP), vmcs_read32(PLE_WINDOW)); - if (secondary_exec_control & SECONDARY_EXEC_ENABLE_VPID) - pr_err("Virtual processor ID = 0x%04x\n", - vmcs_read16(VIRTUAL_PROCESSOR_ID)); -} - -/* - * The guest has exited. See if we can fix it or if we need userspace - * assistance. - */ -static int vmx_handle_exit(struct kvm_vcpu *vcpu, - enum exit_fastpath_completion exit_fastpath) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - u32 exit_reason = vmx->exit_reason; - u32 vectoring_info = vmx->idt_vectoring_info; - - trace_kvm_exit(exit_reason, vcpu, KVM_ISA_VMX); - - /* - * Flush logged GPAs PML buffer, this will make dirty_bitmap more - * updated. Another good is, in kvm_vm_ioctl_get_dirty_log, before - * querying dirty_bitmap, we only need to kick all vcpus out of guest - * mode as if vcpus is in root mode, the PML buffer must has been - * flushed already. - */ - if (enable_pml) - vmx_flush_pml_buffer(vcpu); - - /* If guest state is invalid, start emulating */ - if (vmx->emulation_required) - return handle_invalid_guest_state(vcpu); - - if (is_guest_mode(vcpu) && nested_vmx_exit_reflected(vcpu, exit_reason)) - return nested_vmx_reflect_vmexit(vcpu, exit_reason); - - if (exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY) { - dump_vmcs(); - vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY; - vcpu->run->fail_entry.hardware_entry_failure_reason - = exit_reason; - return 0; - } - - if (unlikely(vmx->fail)) { - dump_vmcs(); - vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY; - vcpu->run->fail_entry.hardware_entry_failure_reason - = vmcs_read32(VM_INSTRUCTION_ERROR); - return 0; - } - - /* - * Note: - * Do not try to fix EXIT_REASON_EPT_MISCONFIG if it caused by - * delivery event since it indicates guest is accessing MMIO. - * The vm-exit can be triggered again after return to guest that - * will cause infinite loop. - */ - if ((vectoring_info & VECTORING_INFO_VALID_MASK) && - (exit_reason != EXIT_REASON_EXCEPTION_NMI && - exit_reason != EXIT_REASON_EPT_VIOLATION && - exit_reason != EXIT_REASON_PML_FULL && - exit_reason != EXIT_REASON_TASK_SWITCH)) { - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV; - vcpu->run->internal.ndata = 3; - vcpu->run->internal.data[0] = vectoring_info; - vcpu->run->internal.data[1] = exit_reason; - vcpu->run->internal.data[2] = vcpu->arch.exit_qualification; - if (exit_reason == EXIT_REASON_EPT_MISCONFIG) { - vcpu->run->internal.ndata++; - vcpu->run->internal.data[3] = - vmcs_read64(GUEST_PHYSICAL_ADDRESS); - } - return 0; - } - - if (unlikely(!enable_vnmi && - vmx->loaded_vmcs->soft_vnmi_blocked)) { - if (vmx_interrupt_allowed(vcpu)) { - vmx->loaded_vmcs->soft_vnmi_blocked = 0; - } else if (vmx->loaded_vmcs->vnmi_blocked_time > 1000000000LL && - vcpu->arch.nmi_pending) { - /* - * This CPU don't support us in finding the end of an - * NMI-blocked window if the guest runs with IRQs - * disabled. So we pull the trigger after 1 s of - * futile waiting, but inform the user about this. - */ - printk(KERN_WARNING "%s: Breaking out of NMI-blocked " - "state on VCPU %d after 1 s timeout\n", - __func__, vcpu->vcpu_id); - vmx->loaded_vmcs->soft_vnmi_blocked = 0; - } - } - - if (exit_fastpath == EXIT_FASTPATH_SKIP_EMUL_INS) { - kvm_skip_emulated_instruction(vcpu); - return 1; - } else if (exit_reason < kvm_vmx_max_exit_handlers - && kvm_vmx_exit_handlers[exit_reason]) { -#ifdef CONFIG_RETPOLINE - if (exit_reason == EXIT_REASON_MSR_WRITE) - return kvm_emulate_wrmsr(vcpu); - else if (exit_reason == EXIT_REASON_PREEMPTION_TIMER) - return handle_preemption_timer(vcpu); - else if (exit_reason == EXIT_REASON_INTERRUPT_WINDOW) - return handle_interrupt_window(vcpu); - else if (exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT) - return handle_external_interrupt(vcpu); - else if (exit_reason == EXIT_REASON_HLT) - return kvm_emulate_halt(vcpu); - else if (exit_reason == EXIT_REASON_EPT_MISCONFIG) - return handle_ept_misconfig(vcpu); -#endif - return kvm_vmx_exit_handlers[exit_reason](vcpu); - } else { - vcpu_unimpl(vcpu, "vmx: unexpected exit reason 0x%x\n", - exit_reason); - dump_vmcs(); - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = - KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON; - vcpu->run->internal.ndata = 1; - vcpu->run->internal.data[0] = exit_reason; - return 0; - } -} - -/* - * Software based L1D cache flush which is used when microcode providing - * the cache control MSR is not loaded. - * - * The L1D cache is 32 KiB on Nehalem and later microarchitectures, but to - * flush it is required to read in 64 KiB because the replacement algorithm - * is not exactly LRU. This could be sized at runtime via topology - * information but as all relevant affected CPUs have 32KiB L1D cache size - * there is no point in doing so. - */ -static void vmx_l1d_flush(struct kvm_vcpu *vcpu) -{ - int size = PAGE_SIZE << L1D_CACHE_ORDER; - - /* - * This code is only executed when the the flush mode is 'cond' or - * 'always' - */ - if (static_branch_likely(&vmx_l1d_flush_cond)) { - bool flush_l1d; - - /* - * Clear the per-vcpu flush bit, it gets set again - * either from vcpu_run() or from one of the unsafe - * VMEXIT handlers. - */ - flush_l1d = vcpu->arch.l1tf_flush_l1d; - vcpu->arch.l1tf_flush_l1d = false; - - /* - * Clear the per-cpu flush bit, it gets set again from - * the interrupt handlers. - */ - flush_l1d |= kvm_get_cpu_l1tf_flush_l1d(); - kvm_clear_cpu_l1tf_flush_l1d(); - - if (!flush_l1d) - return; - } - - vcpu->stat.l1d_flush++; - - if (static_cpu_has(X86_FEATURE_FLUSH_L1D)) { - wrmsrl(MSR_IA32_FLUSH_CMD, L1D_FLUSH); - return; - } - - asm volatile( - /* First ensure the pages are in the TLB */ - "xorl %%eax, %%eax\n" - ".Lpopulate_tlb:\n\t" - "movzbl (%[flush_pages], %%" _ASM_AX "), %%ecx\n\t" - "addl $4096, %%eax\n\t" - "cmpl %%eax, %[size]\n\t" - "jne .Lpopulate_tlb\n\t" - "xorl %%eax, %%eax\n\t" - "cpuid\n\t" - /* Now fill the cache */ - "xorl %%eax, %%eax\n" - ".Lfill_cache:\n" - "movzbl (%[flush_pages], %%" _ASM_AX "), %%ecx\n\t" - "addl $64, %%eax\n\t" - "cmpl %%eax, %[size]\n\t" - "jne .Lfill_cache\n\t" - "lfence\n" - :: [flush_pages] "r" (vmx_l1d_flush_pages), - [size] "r" (size) - : "eax", "ebx", "ecx", "edx"); -} - -static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) -{ - struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - int tpr_threshold; - - if (is_guest_mode(vcpu) && - nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) - return; - - tpr_threshold = (irr == -1 || tpr < irr) ? 0 : irr; - if (is_guest_mode(vcpu)) - to_vmx(vcpu)->nested.l1_tpr_threshold = tpr_threshold; - else - vmcs_write32(TPR_THRESHOLD, tpr_threshold); -} - -void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - u32 sec_exec_control; - - if (!lapic_in_kernel(vcpu)) - return; - - if (!flexpriority_enabled && - !cpu_has_vmx_virtualize_x2apic_mode()) - return; - - /* Postpone execution until vmcs01 is the current VMCS. */ - if (is_guest_mode(vcpu)) { - vmx->nested.change_vmcs01_virtual_apic_mode = true; - return; - } - - sec_exec_control = secondary_exec_controls_get(vmx); - sec_exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | - SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE); - - switch (kvm_get_apic_mode(vcpu)) { - case LAPIC_MODE_INVALID: - WARN_ONCE(true, "Invalid local APIC state"); - case LAPIC_MODE_DISABLED: - break; - case LAPIC_MODE_XAPIC: - if (flexpriority_enabled) { - sec_exec_control |= - SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; - vmx_flush_tlb(vcpu, true); - } - break; - case LAPIC_MODE_X2APIC: - if (cpu_has_vmx_virtualize_x2apic_mode()) - sec_exec_control |= - SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE; - break; - } - secondary_exec_controls_set(vmx, sec_exec_control); - - vmx_update_msr_bitmap(vcpu); -} - -static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa) -{ - if (!is_guest_mode(vcpu)) { - vmcs_write64(APIC_ACCESS_ADDR, hpa); - vmx_flush_tlb(vcpu, true); - } -} - -static void vmx_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr) -{ - u16 status; - u8 old; - - if (max_isr == -1) - max_isr = 0; - - status = vmcs_read16(GUEST_INTR_STATUS); - old = status >> 8; - if (max_isr != old) { - status &= 0xff; - status |= max_isr << 8; - vmcs_write16(GUEST_INTR_STATUS, status); - } -} - -static void vmx_set_rvi(int vector) -{ - u16 status; - u8 old; - - if (vector == -1) - vector = 0; - - status = vmcs_read16(GUEST_INTR_STATUS); - old = (u8)status & 0xff; - if ((u8)vector != old) { - status &= ~0xff; - status |= (u8)vector; - vmcs_write16(GUEST_INTR_STATUS, status); - } -} - -static void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr) -{ - /* - * When running L2, updating RVI is only relevant when - * vmcs12 virtual-interrupt-delivery enabled. - * However, it can be enabled only when L1 also - * intercepts external-interrupts and in that case - * we should not update vmcs02 RVI but instead intercept - * interrupt. Therefore, do nothing when running L2. - */ - if (!is_guest_mode(vcpu)) - vmx_set_rvi(max_irr); -} - -static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - int max_irr; - bool max_irr_updated; - - WARN_ON(!vcpu->arch.apicv_active); - if (pi_test_on(&vmx->pi_desc)) { - pi_clear_on(&vmx->pi_desc); - /* - * IOMMU can write to PID.ON, so the barrier matters even on UP. - * But on x86 this is just a compiler barrier anyway. - */ - smp_mb__after_atomic(); - max_irr_updated = - kvm_apic_update_irr(vcpu, vmx->pi_desc.pir, &max_irr); - - /* - * If we are running L2 and L1 has a new pending interrupt - * which can be injected, we should re-evaluate - * what should be done with this new L1 interrupt. - * If L1 intercepts external-interrupts, we should - * exit from L2 to L1. Otherwise, interrupt should be - * delivered directly to L2. - */ - if (is_guest_mode(vcpu) && max_irr_updated) { - if (nested_exit_on_intr(vcpu)) - kvm_vcpu_exiting_guest_mode(vcpu); - else - kvm_make_request(KVM_REQ_EVENT, vcpu); - } - } else { - max_irr = kvm_lapic_find_highest_irr(vcpu); - } - vmx_hwapic_irr_update(vcpu, max_irr); - return max_irr; -} - -static bool vmx_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu) -{ - struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); - - return pi_test_on(pi_desc) || - (pi_test_sn(pi_desc) && !pi_is_pir_empty(pi_desc)); -} - -static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) -{ - if (!kvm_vcpu_apicv_active(vcpu)) - return; - - vmcs_write64(EOI_EXIT_BITMAP0, eoi_exit_bitmap[0]); - vmcs_write64(EOI_EXIT_BITMAP1, eoi_exit_bitmap[1]); - vmcs_write64(EOI_EXIT_BITMAP2, eoi_exit_bitmap[2]); - vmcs_write64(EOI_EXIT_BITMAP3, eoi_exit_bitmap[3]); -} - -static void vmx_apicv_post_state_restore(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - - pi_clear_on(&vmx->pi_desc); - memset(vmx->pi_desc.pir, 0, sizeof(vmx->pi_desc.pir)); -} - -static void handle_exception_nmi_irqoff(struct vcpu_vmx *vmx) -{ - vmx->exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO); - - /* if exit due to PF check for async PF */ - if (is_page_fault(vmx->exit_intr_info)) - vmx->vcpu.arch.apf.host_apf_reason = kvm_read_and_reset_pf_reason(); - - /* Handle machine checks before interrupts are enabled */ - if (is_machine_check(vmx->exit_intr_info)) - kvm_machine_check(); - - /* We need to handle NMIs before interrupts are enabled */ - if (is_nmi(vmx->exit_intr_info)) { - kvm_before_interrupt(&vmx->vcpu); - asm("int $2"); - kvm_after_interrupt(&vmx->vcpu); - } -} - -static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu) -{ - unsigned int vector; - unsigned long entry; -#ifdef CONFIG_X86_64 - unsigned long tmp; -#endif - gate_desc *desc; - u32 intr_info; - - intr_info = vmcs_read32(VM_EXIT_INTR_INFO); - if (WARN_ONCE(!is_external_intr(intr_info), - "KVM: unexpected VM-Exit interrupt info: 0x%x", intr_info)) - return; - - vector = intr_info & INTR_INFO_VECTOR_MASK; - desc = (gate_desc *)host_idt_base + vector; - entry = gate_offset(desc); - - kvm_before_interrupt(vcpu); - - asm volatile( -#ifdef CONFIG_X86_64 - "mov %%" _ASM_SP ", %[sp]\n\t" - "and $0xfffffffffffffff0, %%" _ASM_SP "\n\t" - "push $%c[ss]\n\t" - "push %[sp]\n\t" -#endif - "pushf\n\t" - __ASM_SIZE(push) " $%c[cs]\n\t" - CALL_NOSPEC - : -#ifdef CONFIG_X86_64 - [sp]"=&r"(tmp), -#endif - ASM_CALL_CONSTRAINT - : - THUNK_TARGET(entry), - [ss]"i"(__KERNEL_DS), - [cs]"i"(__KERNEL_CS) - ); - - kvm_after_interrupt(vcpu); -} -STACK_FRAME_NON_STANDARD(handle_external_interrupt_irqoff); - -static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu, - enum exit_fastpath_completion *exit_fastpath) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - - if (vmx->exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT) - handle_external_interrupt_irqoff(vcpu); - else if (vmx->exit_reason == EXIT_REASON_EXCEPTION_NMI) - handle_exception_nmi_irqoff(vmx); - else if (!is_guest_mode(vcpu) && - vmx->exit_reason == EXIT_REASON_MSR_WRITE) - *exit_fastpath = handle_fastpath_set_msr_irqoff(vcpu); -} - -static bool vmx_has_emulated_msr(int index) -{ - switch (index) { - case MSR_IA32_SMBASE: - /* - * We cannot do SMM unless we can run the guest in big - * real mode. - */ - return enable_unrestricted_guest || emulate_invalid_guest_state; - case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: - return nested; - case MSR_AMD64_VIRT_SPEC_CTRL: - /* This is AMD only. */ - return false; - default: - return true; - } -} - -static bool vmx_pt_supported(void) -{ - return pt_mode == PT_MODE_HOST_GUEST; -} - -static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx) -{ - u32 exit_intr_info; - bool unblock_nmi; - u8 vector; - bool idtv_info_valid; - - idtv_info_valid = vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK; - - if (enable_vnmi) { - if (vmx->loaded_vmcs->nmi_known_unmasked) - return; - /* - * Can't use vmx->exit_intr_info since we're not sure what - * the exit reason is. - */ - exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO); - unblock_nmi = (exit_intr_info & INTR_INFO_UNBLOCK_NMI) != 0; - vector = exit_intr_info & INTR_INFO_VECTOR_MASK; - /* - * SDM 3: 27.7.1.2 (September 2008) - * Re-set bit "block by NMI" before VM entry if vmexit caused by - * a guest IRET fault. - * SDM 3: 23.2.2 (September 2008) - * Bit 12 is undefined in any of the following cases: - * If the VM exit sets the valid bit in the IDT-vectoring - * information field. - * If the VM exit is due to a double fault. - */ - if ((exit_intr_info & INTR_INFO_VALID_MASK) && unblock_nmi && - vector != DF_VECTOR && !idtv_info_valid) - vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, - GUEST_INTR_STATE_NMI); - else - vmx->loaded_vmcs->nmi_known_unmasked = - !(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) - & GUEST_INTR_STATE_NMI); - } else if (unlikely(vmx->loaded_vmcs->soft_vnmi_blocked)) - vmx->loaded_vmcs->vnmi_blocked_time += - ktime_to_ns(ktime_sub(ktime_get(), - vmx->loaded_vmcs->entry_time)); -} - -static void __vmx_complete_interrupts(struct kvm_vcpu *vcpu, - u32 idt_vectoring_info, - int instr_len_field, - int error_code_field) -{ - u8 vector; - int type; - bool idtv_info_valid; - - idtv_info_valid = idt_vectoring_info & VECTORING_INFO_VALID_MASK; - - vcpu->arch.nmi_injected = false; - kvm_clear_exception_queue(vcpu); - kvm_clear_interrupt_queue(vcpu); - - if (!idtv_info_valid) - return; - - kvm_make_request(KVM_REQ_EVENT, vcpu); - - vector = idt_vectoring_info & VECTORING_INFO_VECTOR_MASK; - type = idt_vectoring_info & VECTORING_INFO_TYPE_MASK; - - switch (type) { - case INTR_TYPE_NMI_INTR: - vcpu->arch.nmi_injected = true; - /* - * SDM 3: 27.7.1.2 (September 2008) - * Clear bit "block by NMI" before VM entry if a NMI - * delivery faulted. - */ - vmx_set_nmi_mask(vcpu, false); - break; - case INTR_TYPE_SOFT_EXCEPTION: - vcpu->arch.event_exit_inst_len = vmcs_read32(instr_len_field); - /* fall through */ - case INTR_TYPE_HARD_EXCEPTION: - if (idt_vectoring_info & VECTORING_INFO_DELIVER_CODE_MASK) { - u32 err = vmcs_read32(error_code_field); - kvm_requeue_exception_e(vcpu, vector, err); - } else - kvm_requeue_exception(vcpu, vector); - break; - case INTR_TYPE_SOFT_INTR: - vcpu->arch.event_exit_inst_len = vmcs_read32(instr_len_field); - /* fall through */ - case INTR_TYPE_EXT_INTR: - kvm_queue_interrupt(vcpu, vector, type == INTR_TYPE_SOFT_INTR); - break; - default: - break; - } -} - -static void vmx_complete_interrupts(struct vcpu_vmx *vmx) -{ - __vmx_complete_interrupts(&vmx->vcpu, vmx->idt_vectoring_info, - VM_EXIT_INSTRUCTION_LEN, - IDT_VECTORING_ERROR_CODE); -} - -static void vmx_cancel_injection(struct kvm_vcpu *vcpu) -{ - __vmx_complete_interrupts(vcpu, - vmcs_read32(VM_ENTRY_INTR_INFO_FIELD), - VM_ENTRY_INSTRUCTION_LEN, - VM_ENTRY_EXCEPTION_ERROR_CODE); - - vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0); -} - -static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx) -{ - int i, nr_msrs; - struct perf_guest_switch_msr *msrs; - - msrs = perf_guest_get_msrs(&nr_msrs); - - if (!msrs) - return; - - for (i = 0; i < nr_msrs; i++) - if (msrs[i].host == msrs[i].guest) - clear_atomic_switch_msr(vmx, msrs[i].msr); - else - add_atomic_switch_msr(vmx, msrs[i].msr, msrs[i].guest, - msrs[i].host, false); -} - -static void atomic_switch_umwait_control_msr(struct vcpu_vmx *vmx) -{ - u32 host_umwait_control; - - if (!vmx_has_waitpkg(vmx)) - return; - - host_umwait_control = get_umwait_control_msr(); - - if (vmx->msr_ia32_umwait_control != host_umwait_control) - add_atomic_switch_msr(vmx, MSR_IA32_UMWAIT_CONTROL, - vmx->msr_ia32_umwait_control, - host_umwait_control, false); - else - clear_atomic_switch_msr(vmx, MSR_IA32_UMWAIT_CONTROL); -} - -static void vmx_update_hv_timer(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - u64 tscl; - u32 delta_tsc; - - if (vmx->req_immediate_exit) { - vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, 0); - vmx->loaded_vmcs->hv_timer_soft_disabled = false; - } else if (vmx->hv_deadline_tsc != -1) { - tscl = rdtsc(); - if (vmx->hv_deadline_tsc > tscl) - /* set_hv_timer ensures the delta fits in 32-bits */ - delta_tsc = (u32)((vmx->hv_deadline_tsc - tscl) >> - cpu_preemption_timer_multi); - else - delta_tsc = 0; - - vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, delta_tsc); - vmx->loaded_vmcs->hv_timer_soft_disabled = false; - } else if (!vmx->loaded_vmcs->hv_timer_soft_disabled) { - vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, -1); - vmx->loaded_vmcs->hv_timer_soft_disabled = true; - } -} - -void vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp) -{ - if (unlikely(host_rsp != vmx->loaded_vmcs->host_state.rsp)) { - vmx->loaded_vmcs->host_state.rsp = host_rsp; - vmcs_writel(HOST_RSP, host_rsp); - } -} - -bool __vmx_vcpu_run(struct vcpu_vmx *vmx, unsigned long *regs, bool launched); - -static void vmx_vcpu_run(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long cr3, cr4; - - /* Record the guest's net vcpu time for enforced NMI injections. */ - if (unlikely(!enable_vnmi && - vmx->loaded_vmcs->soft_vnmi_blocked)) - vmx->loaded_vmcs->entry_time = ktime_get(); - - /* Don't enter VMX if guest state is invalid, let the exit handler - start emulation until we arrive back to a valid state */ - if (vmx->emulation_required) - return; - - if (vmx->ple_window_dirty) { - vmx->ple_window_dirty = false; - vmcs_write32(PLE_WINDOW, vmx->ple_window); - } - - if (vmx->nested.need_vmcs12_to_shadow_sync) - nested_sync_vmcs12_to_shadow(vcpu); - - if (kvm_register_is_dirty(vcpu, VCPU_REGS_RSP)) - vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]); - if (kvm_register_is_dirty(vcpu, VCPU_REGS_RIP)) - vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]); - - cr3 = __get_current_cr3_fast(); - if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) { - vmcs_writel(HOST_CR3, cr3); - vmx->loaded_vmcs->host_state.cr3 = cr3; - } - - cr4 = cr4_read_shadow(); - if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) { - vmcs_writel(HOST_CR4, cr4); - vmx->loaded_vmcs->host_state.cr4 = cr4; - } - - /* When single-stepping over STI and MOV SS, we must clear the - * corresponding interruptibility bits in the guest state. Otherwise - * vmentry fails as it then expects bit 14 (BS) in pending debug - * exceptions being set, but that's not correct for the guest debugging - * case. */ - if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) - vmx_set_interrupt_shadow(vcpu, 0); - - kvm_load_guest_xsave_state(vcpu); - - if (static_cpu_has(X86_FEATURE_PKU) && - kvm_read_cr4_bits(vcpu, X86_CR4_PKE) && - vcpu->arch.pkru != vmx->host_pkru) - __write_pkru(vcpu->arch.pkru); - - pt_guest_enter(vmx); - - atomic_switch_perf_msrs(vmx); - atomic_switch_umwait_control_msr(vmx); - - if (enable_preemption_timer) - vmx_update_hv_timer(vcpu); - - if (lapic_in_kernel(vcpu) && - vcpu->arch.apic->lapic_timer.timer_advance_ns) - kvm_wait_lapic_expire(vcpu); - - /* - * If this vCPU has touched SPEC_CTRL, restore the guest's value if - * it's non-zero. Since vmentry is serialising on affected CPUs, there - * is no need to worry about the conditional branch over the wrmsr - * being speculatively taken. - */ - x86_spec_ctrl_set_guest(vmx->spec_ctrl, 0); - - /* L1D Flush includes CPU buffer clear to mitigate MDS */ - if (static_branch_unlikely(&vmx_l1d_should_flush)) - vmx_l1d_flush(vcpu); - else if (static_branch_unlikely(&mds_user_clear)) - mds_clear_cpu_buffers(); - - if (vcpu->arch.cr2 != read_cr2()) - write_cr2(vcpu->arch.cr2); - - vmx->fail = __vmx_vcpu_run(vmx, (unsigned long *)&vcpu->arch.regs, - vmx->loaded_vmcs->launched); - - vcpu->arch.cr2 = read_cr2(); - - /* - * We do not use IBRS in the kernel. If this vCPU has used the - * SPEC_CTRL MSR it may have left it on; save the value and - * turn it off. This is much more efficient than blindly adding - * it to the atomic save/restore list. Especially as the former - * (Saving guest MSRs on vmexit) doesn't even exist in KVM. - * - * For non-nested case: - * If the L01 MSR bitmap does not intercept the MSR, then we need to - * save it. - * - * For nested case: - * If the L02 MSR bitmap does not intercept the MSR, then we need to - * save it. - */ - if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL))) - vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL); - - x86_spec_ctrl_restore_host(vmx->spec_ctrl, 0); - - /* All fields are clean at this point */ - if (static_branch_unlikely(&enable_evmcs)) - current_evmcs->hv_clean_fields |= - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; - - if (static_branch_unlikely(&enable_evmcs)) - current_evmcs->hv_vp_id = vcpu->arch.hyperv.vp_index; - - /* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */ - if (vmx->host_debugctlmsr) - update_debugctlmsr(vmx->host_debugctlmsr); - -#ifndef CONFIG_X86_64 - /* - * The sysexit path does not restore ds/es, so we must set them to - * a reasonable value ourselves. - * - * We can't defer this to vmx_prepare_switch_to_host() since that - * function may be executed in interrupt context, which saves and - * restore segments around it, nullifying its effect. - */ - loadsegment(ds, __USER_DS); - loadsegment(es, __USER_DS); -#endif - - vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP) - | (1 << VCPU_EXREG_RFLAGS) - | (1 << VCPU_EXREG_PDPTR) - | (1 << VCPU_EXREG_SEGMENTS) - | (1 << VCPU_EXREG_CR3)); - vcpu->arch.regs_dirty = 0; - - pt_guest_exit(vmx); - - /* - * eager fpu is enabled if PKEY is supported and CR4 is switched - * back on host, so it is safe to read guest PKRU from current - * XSAVE. - */ - if (static_cpu_has(X86_FEATURE_PKU) && - kvm_read_cr4_bits(vcpu, X86_CR4_PKE)) { - vcpu->arch.pkru = rdpkru(); - if (vcpu->arch.pkru != vmx->host_pkru) - __write_pkru(vmx->host_pkru); - } - - kvm_load_host_xsave_state(vcpu); - - vmx->nested.nested_run_pending = 0; - vmx->idt_vectoring_info = 0; - - vmx->exit_reason = vmx->fail ? 0xdead : vmcs_read32(VM_EXIT_REASON); - if ((u16)vmx->exit_reason == EXIT_REASON_MCE_DURING_VMENTRY) - kvm_machine_check(); - - if (vmx->fail || (vmx->exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY)) - return; - - vmx->loaded_vmcs->launched = 1; - vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD); - - vmx_recover_nmi_blocking(vmx); - vmx_complete_interrupts(vmx); -} - -static struct kvm *vmx_vm_alloc(void) -{ - struct kvm_vmx *kvm_vmx = __vmalloc(sizeof(struct kvm_vmx), - GFP_KERNEL_ACCOUNT | __GFP_ZERO, - PAGE_KERNEL); - return &kvm_vmx->kvm; -} - -static void vmx_vm_free(struct kvm *kvm) -{ - kfree(kvm->arch.hyperv.hv_pa_pg); - vfree(to_kvm_vmx(kvm)); -} - -static void vmx_free_vcpu(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - - if (enable_pml) - vmx_destroy_pml_buffer(vmx); - free_vpid(vmx->vpid); - nested_vmx_free_vcpu(vcpu); - free_loaded_vmcs(vmx->loaded_vmcs); - kvm_vcpu_uninit(vcpu); - kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.user_fpu); - kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.guest_fpu); - kmem_cache_free(kvm_vcpu_cache, vmx); -} - -static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) -{ - int err; - struct vcpu_vmx *vmx; - unsigned long *msr_bitmap; - int i, cpu; - - BUILD_BUG_ON_MSG(offsetof(struct vcpu_vmx, vcpu) != 0, - "struct kvm_vcpu must be at offset 0 for arch usercopy region"); - - vmx = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL_ACCOUNT); - if (!vmx) - return ERR_PTR(-ENOMEM); - - vmx->vcpu.arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache, - GFP_KERNEL_ACCOUNT); - if (!vmx->vcpu.arch.user_fpu) { - printk(KERN_ERR "kvm: failed to allocate kvm userspace's fpu\n"); - err = -ENOMEM; - goto free_partial_vcpu; - } - - vmx->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache, - GFP_KERNEL_ACCOUNT); - if (!vmx->vcpu.arch.guest_fpu) { - printk(KERN_ERR "kvm: failed to allocate vcpu's fpu\n"); - err = -ENOMEM; - goto free_user_fpu; - } - - vmx->vpid = allocate_vpid(); - - err = kvm_vcpu_init(&vmx->vcpu, kvm, id); - if (err) - goto free_vcpu; - - err = -ENOMEM; - - /* - * If PML is turned on, failure on enabling PML just results in failure - * of creating the vcpu, therefore we can simplify PML logic (by - * avoiding dealing with cases, such as enabling PML partially on vcpus - * for the guest), etc. - */ - if (enable_pml) { - vmx->pml_pg = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); - if (!vmx->pml_pg) - goto uninit_vcpu; - } - - BUILD_BUG_ON(ARRAY_SIZE(vmx_msr_index) != NR_SHARED_MSRS); - - for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i) { - u32 index = vmx_msr_index[i]; - u32 data_low, data_high; - int j = vmx->nmsrs; - - if (rdmsr_safe(index, &data_low, &data_high) < 0) - continue; - if (wrmsr_safe(index, data_low, data_high) < 0) - continue; - - vmx->guest_msrs[j].index = i; - vmx->guest_msrs[j].data = 0; - switch (index) { - case MSR_IA32_TSX_CTRL: - /* - * No need to pass TSX_CTRL_CPUID_CLEAR through, so - * let's avoid changing CPUID bits under the host - * kernel's feet. - */ - vmx->guest_msrs[j].mask = ~(u64)TSX_CTRL_CPUID_CLEAR; - break; - default: - vmx->guest_msrs[j].mask = -1ull; - break; - } - ++vmx->nmsrs; - } - - err = alloc_loaded_vmcs(&vmx->vmcs01); - if (err < 0) - goto free_pml; - - msr_bitmap = vmx->vmcs01.msr_bitmap; - vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_TSC, MSR_TYPE_R); - vmx_disable_intercept_for_msr(msr_bitmap, MSR_FS_BASE, MSR_TYPE_RW); - vmx_disable_intercept_for_msr(msr_bitmap, MSR_GS_BASE, MSR_TYPE_RW); - vmx_disable_intercept_for_msr(msr_bitmap, MSR_KERNEL_GS_BASE, MSR_TYPE_RW); - vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW); - vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW); - vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW); - if (kvm_cstate_in_guest(kvm)) { - vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C1_RES, MSR_TYPE_R); - vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C3_RESIDENCY, MSR_TYPE_R); - vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C6_RESIDENCY, MSR_TYPE_R); - vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C7_RESIDENCY, MSR_TYPE_R); - } - vmx->msr_bitmap_mode = 0; - - vmx->loaded_vmcs = &vmx->vmcs01; - cpu = get_cpu(); - vmx_vcpu_load(&vmx->vcpu, cpu); - vmx->vcpu.cpu = cpu; - init_vmcs(vmx); - vmx_vcpu_put(&vmx->vcpu); - put_cpu(); - if (cpu_need_virtualize_apic_accesses(&vmx->vcpu)) { - err = alloc_apic_access_page(kvm); - if (err) - goto free_vmcs; - } - - if (enable_ept && !enable_unrestricted_guest) { - err = init_rmode_identity_map(kvm); - if (err) - goto free_vmcs; - } - - if (nested) - nested_vmx_setup_ctls_msrs(&vmx->nested.msrs, - vmx_capability.ept, - kvm_vcpu_apicv_active(&vmx->vcpu)); - else - memset(&vmx->nested.msrs, 0, sizeof(vmx->nested.msrs)); - - vmx->nested.posted_intr_nv = -1; - vmx->nested.current_vmptr = -1ull; - - vmx->msr_ia32_feature_control_valid_bits = FEATURE_CONTROL_LOCKED; - - /* - * Enforce invariant: pi_desc.nv is always either POSTED_INTR_VECTOR - * or POSTED_INTR_WAKEUP_VECTOR. - */ - vmx->pi_desc.nv = POSTED_INTR_VECTOR; - vmx->pi_desc.sn = 1; - - vmx->ept_pointer = INVALID_PAGE; - - return &vmx->vcpu; - -free_vmcs: - free_loaded_vmcs(vmx->loaded_vmcs); -free_pml: - vmx_destroy_pml_buffer(vmx); -uninit_vcpu: - kvm_vcpu_uninit(&vmx->vcpu); -free_vcpu: - free_vpid(vmx->vpid); - kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.guest_fpu); -free_user_fpu: - kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.user_fpu); -free_partial_vcpu: - kmem_cache_free(kvm_vcpu_cache, vmx); - return ERR_PTR(err); -} - -#define L1TF_MSG_SMT "L1TF CPU bug present and SMT on, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/l1tf.html for details.\n" -#define L1TF_MSG_L1D "L1TF CPU bug present and virtualization mitigation disabled, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/l1tf.html for details.\n" - -static int vmx_vm_init(struct kvm *kvm) -{ - spin_lock_init(&to_kvm_vmx(kvm)->ept_pointer_lock); - - if (!ple_gap) - kvm->arch.pause_in_guest = true; - - if (boot_cpu_has(X86_BUG_L1TF) && enable_ept) { - switch (l1tf_mitigation) { - case L1TF_MITIGATION_OFF: - case L1TF_MITIGATION_FLUSH_NOWARN: - /* 'I explicitly don't care' is set */ - break; - case L1TF_MITIGATION_FLUSH: - case L1TF_MITIGATION_FLUSH_NOSMT: - case L1TF_MITIGATION_FULL: - /* - * Warn upon starting the first VM in a potentially - * insecure environment. - */ - if (sched_smt_active()) - pr_warn_once(L1TF_MSG_SMT); - if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_NEVER) - pr_warn_once(L1TF_MSG_L1D); - break; - case L1TF_MITIGATION_FULL_FORCE: - /* Flush is enforced */ - break; - } - } - return 0; -} - -static int __init vmx_check_processor_compat(void) -{ - struct vmcs_config vmcs_conf; - struct vmx_capability vmx_cap; - - if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0) - return -EIO; - if (nested) - nested_vmx_setup_ctls_msrs(&vmcs_conf.nested, vmx_cap.ept, - enable_apicv); - if (memcmp(&vmcs_config, &vmcs_conf, sizeof(struct vmcs_config)) != 0) { - printk(KERN_ERR "kvm: CPU %d feature inconsistency!\n", - smp_processor_id()); - return -EIO; - } - return 0; -} - -static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) -{ - u8 cache; - u64 ipat = 0; - - /* For VT-d and EPT combination - * 1. MMIO: always map as UC - * 2. EPT with VT-d: - * a. VT-d without snooping control feature: can't guarantee the - * result, try to trust guest. - * 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)) { - ipat = VMX_EPT_IPAT_BIT; - cache = MTRR_TYPE_WRBACK; - goto exit; - } - - if (kvm_read_cr0(vcpu) & X86_CR0_CD) { - ipat = VMX_EPT_IPAT_BIT; - if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED)) - cache = MTRR_TYPE_WRBACK; - else - cache = MTRR_TYPE_UNCACHABLE; - goto exit; - } - - cache = kvm_mtrr_get_guest_memory_type(vcpu, gfn); - -exit: - return (cache << VMX_EPT_MT_EPTE_SHIFT) | ipat; -} - -static int vmx_get_lpage_level(void) -{ - if (enable_ept && !cpu_has_vmx_ept_1g_page()) - return PT_DIRECTORY_LEVEL; - else - /* For shadow and EPT supported 1GB page */ - return PT_PDPE_LEVEL; -} - -static void vmcs_set_secondary_exec_control(struct vcpu_vmx *vmx) -{ - /* - * These bits in the secondary execution controls field - * are dynamic, the others are mostly based on the hypervisor - * architecture and the guest's CPUID. Do not touch the - * dynamic bits. - */ - u32 mask = - SECONDARY_EXEC_SHADOW_VMCS | - SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | - SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | - SECONDARY_EXEC_DESC; - - u32 new_ctl = vmx->secondary_exec_control; - u32 cur_ctl = secondary_exec_controls_get(vmx); - - secondary_exec_controls_set(vmx, (new_ctl & ~mask) | (cur_ctl & mask)); -} - -/* - * Generate MSR_IA32_VMX_CR{0,4}_FIXED1 according to CPUID. Only set bits - * (indicating "allowed-1") if they are supported in the guest's CPUID. - */ -static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - struct kvm_cpuid_entry2 *entry; - - vmx->nested.msrs.cr0_fixed1 = 0xffffffff; - vmx->nested.msrs.cr4_fixed1 = X86_CR4_PCE; - -#define cr4_fixed1_update(_cr4_mask, _reg, _cpuid_mask) do { \ - if (entry && (entry->_reg & (_cpuid_mask))) \ - vmx->nested.msrs.cr4_fixed1 |= (_cr4_mask); \ -} while (0) - - entry = kvm_find_cpuid_entry(vcpu, 0x1, 0); - cr4_fixed1_update(X86_CR4_VME, edx, bit(X86_FEATURE_VME)); - cr4_fixed1_update(X86_CR4_PVI, edx, bit(X86_FEATURE_VME)); - cr4_fixed1_update(X86_CR4_TSD, edx, bit(X86_FEATURE_TSC)); - cr4_fixed1_update(X86_CR4_DE, edx, bit(X86_FEATURE_DE)); - cr4_fixed1_update(X86_CR4_PSE, edx, bit(X86_FEATURE_PSE)); - cr4_fixed1_update(X86_CR4_PAE, edx, bit(X86_FEATURE_PAE)); - cr4_fixed1_update(X86_CR4_MCE, edx, bit(X86_FEATURE_MCE)); - cr4_fixed1_update(X86_CR4_PGE, edx, bit(X86_FEATURE_PGE)); - cr4_fixed1_update(X86_CR4_OSFXSR, edx, bit(X86_FEATURE_FXSR)); - cr4_fixed1_update(X86_CR4_OSXMMEXCPT, edx, bit(X86_FEATURE_XMM)); - cr4_fixed1_update(X86_CR4_VMXE, ecx, bit(X86_FEATURE_VMX)); - cr4_fixed1_update(X86_CR4_SMXE, ecx, bit(X86_FEATURE_SMX)); - cr4_fixed1_update(X86_CR4_PCIDE, ecx, bit(X86_FEATURE_PCID)); - cr4_fixed1_update(X86_CR4_OSXSAVE, ecx, bit(X86_FEATURE_XSAVE)); - - entry = kvm_find_cpuid_entry(vcpu, 0x7, 0); - cr4_fixed1_update(X86_CR4_FSGSBASE, ebx, bit(X86_FEATURE_FSGSBASE)); - cr4_fixed1_update(X86_CR4_SMEP, ebx, bit(X86_FEATURE_SMEP)); - cr4_fixed1_update(X86_CR4_SMAP, ebx, bit(X86_FEATURE_SMAP)); - cr4_fixed1_update(X86_CR4_PKE, ecx, bit(X86_FEATURE_PKU)); - cr4_fixed1_update(X86_CR4_UMIP, ecx, bit(X86_FEATURE_UMIP)); - cr4_fixed1_update(X86_CR4_LA57, ecx, bit(X86_FEATURE_LA57)); - -#undef cr4_fixed1_update -} - -static void nested_vmx_entry_exit_ctls_update(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - - if (kvm_mpx_supported()) { - bool mpx_enabled = guest_cpuid_has(vcpu, X86_FEATURE_MPX); - - if (mpx_enabled) { - vmx->nested.msrs.entry_ctls_high |= VM_ENTRY_LOAD_BNDCFGS; - vmx->nested.msrs.exit_ctls_high |= VM_EXIT_CLEAR_BNDCFGS; - } else { - vmx->nested.msrs.entry_ctls_high &= ~VM_ENTRY_LOAD_BNDCFGS; - vmx->nested.msrs.exit_ctls_high &= ~VM_EXIT_CLEAR_BNDCFGS; - } - } -} - -static void update_intel_pt_cfg(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - struct kvm_cpuid_entry2 *best = NULL; - int i; - - for (i = 0; i < PT_CPUID_LEAVES; i++) { - best = kvm_find_cpuid_entry(vcpu, 0x14, i); - if (!best) - return; - vmx->pt_desc.caps[CPUID_EAX + i*PT_CPUID_REGS_NUM] = best->eax; - vmx->pt_desc.caps[CPUID_EBX + i*PT_CPUID_REGS_NUM] = best->ebx; - vmx->pt_desc.caps[CPUID_ECX + i*PT_CPUID_REGS_NUM] = best->ecx; - vmx->pt_desc.caps[CPUID_EDX + i*PT_CPUID_REGS_NUM] = best->edx; - } - - /* Get the number of configurable Address Ranges for filtering */ - vmx->pt_desc.addr_range = intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_num_address_ranges); - - /* Initialize and clear the no dependency bits */ - vmx->pt_desc.ctl_bitmask = ~(RTIT_CTL_TRACEEN | RTIT_CTL_OS | - RTIT_CTL_USR | RTIT_CTL_TSC_EN | RTIT_CTL_DISRETC); - - /* - * If CPUID.(EAX=14H,ECX=0):EBX[0]=1 CR3Filter can be set otherwise - * will inject an #GP - */ - if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_cr3_filtering)) - vmx->pt_desc.ctl_bitmask &= ~RTIT_CTL_CR3EN; - - /* - * If CPUID.(EAX=14H,ECX=0):EBX[1]=1 CYCEn, CycThresh and - * PSBFreq can be set - */ - if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_psb_cyc)) - vmx->pt_desc.ctl_bitmask &= ~(RTIT_CTL_CYCLEACC | - RTIT_CTL_CYC_THRESH | RTIT_CTL_PSB_FREQ); - - /* - * If CPUID.(EAX=14H,ECX=0):EBX[3]=1 MTCEn BranchEn and - * MTCFreq can be set - */ - if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_mtc)) - vmx->pt_desc.ctl_bitmask &= ~(RTIT_CTL_MTC_EN | - RTIT_CTL_BRANCH_EN | RTIT_CTL_MTC_RANGE); - - /* If CPUID.(EAX=14H,ECX=0):EBX[4]=1 FUPonPTW and PTWEn can be set */ - if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_ptwrite)) - vmx->pt_desc.ctl_bitmask &= ~(RTIT_CTL_FUP_ON_PTW | - RTIT_CTL_PTW_EN); - - /* If CPUID.(EAX=14H,ECX=0):EBX[5]=1 PwrEvEn can be set */ - if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_power_event_trace)) - vmx->pt_desc.ctl_bitmask &= ~RTIT_CTL_PWR_EVT_EN; - - /* If CPUID.(EAX=14H,ECX=0):ECX[0]=1 ToPA can be set */ - if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_topa_output)) - vmx->pt_desc.ctl_bitmask &= ~RTIT_CTL_TOPA; - - /* If CPUID.(EAX=14H,ECX=0):ECX[3]=1 FabircEn can be set */ - if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_output_subsys)) - vmx->pt_desc.ctl_bitmask &= ~RTIT_CTL_FABRIC_EN; - - /* unmask address range configure area */ - for (i = 0; i < vmx->pt_desc.addr_range; i++) - vmx->pt_desc.ctl_bitmask &= ~(0xfULL << (32 + i * 4)); -} - -static void vmx_cpuid_update(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - - /* xsaves_enabled is recomputed in vmx_compute_secondary_exec_control(). */ - vcpu->arch.xsaves_enabled = false; - - if (cpu_has_secondary_exec_ctrls()) { - vmx_compute_secondary_exec_control(vmx); - vmcs_set_secondary_exec_control(vmx); - } - - if (nested_vmx_allowed(vcpu)) - to_vmx(vcpu)->msr_ia32_feature_control_valid_bits |= - FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX | - FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX; - else - to_vmx(vcpu)->msr_ia32_feature_control_valid_bits &= - ~(FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX | - FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX); - - if (nested_vmx_allowed(vcpu)) { - nested_vmx_cr_fixed1_bits_update(vcpu); - nested_vmx_entry_exit_ctls_update(vcpu); - } - - if (boot_cpu_has(X86_FEATURE_INTEL_PT) && - guest_cpuid_has(vcpu, X86_FEATURE_INTEL_PT)) - update_intel_pt_cfg(vcpu); - - if (boot_cpu_has(X86_FEATURE_RTM)) { - struct shared_msr_entry *msr; - msr = find_msr_entry(vmx, MSR_IA32_TSX_CTRL); - if (msr) { - bool enabled = guest_cpuid_has(vcpu, X86_FEATURE_RTM); - vmx_set_guest_msr(vmx, msr, enabled ? 0 : TSX_CTRL_RTM_DISABLE); - } - } -} - -static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) -{ - if (func == 1 && nested) - entry->ecx |= bit(X86_FEATURE_VMX); -} - -static void vmx_request_immediate_exit(struct kvm_vcpu *vcpu) -{ - to_vmx(vcpu)->req_immediate_exit = true; -} - -static int vmx_check_intercept(struct kvm_vcpu *vcpu, - struct x86_instruction_info *info, - enum x86_intercept_stage stage) -{ - struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; - - /* - * RDPID causes #UD if disabled through secondary execution controls. - * Because it is marked as EmulateOnUD, we need to intercept it here. - */ - if (info->intercept == x86_intercept_rdtscp && - !nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDTSCP)) { - ctxt->exception.vector = UD_VECTOR; - ctxt->exception.error_code_valid = false; - return X86EMUL_PROPAGATE_FAULT; - } - - /* TODO: check more intercepts... */ - return X86EMUL_CONTINUE; -} - -#ifdef CONFIG_X86_64 -/* (a << shift) / divisor, return 1 if overflow otherwise 0 */ -static inline int u64_shl_div_u64(u64 a, unsigned int shift, - u64 divisor, u64 *result) -{ - u64 low = a << shift, high = a >> (64 - shift); - - /* To avoid the overflow on divq */ - if (high >= divisor) - return 1; - - /* Low hold the result, high hold rem which is discarded */ - asm("divq %2\n\t" : "=a" (low), "=d" (high) : - "rm" (divisor), "0" (low), "1" (high)); - *result = low; - - return 0; -} - -static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc, - bool *expired) -{ - struct vcpu_vmx *vmx; - u64 tscl, guest_tscl, delta_tsc, lapic_timer_advance_cycles; - struct kvm_timer *ktimer = &vcpu->arch.apic->lapic_timer; - - if (kvm_mwait_in_guest(vcpu->kvm) || - kvm_can_post_timer_interrupt(vcpu)) - return -EOPNOTSUPP; - - vmx = to_vmx(vcpu); - tscl = rdtsc(); - guest_tscl = kvm_read_l1_tsc(vcpu, tscl); - delta_tsc = max(guest_deadline_tsc, guest_tscl) - guest_tscl; - lapic_timer_advance_cycles = nsec_to_cycles(vcpu, - ktimer->timer_advance_ns); - - if (delta_tsc > lapic_timer_advance_cycles) - delta_tsc -= lapic_timer_advance_cycles; - else - delta_tsc = 0; - - /* Convert to host delta tsc if tsc scaling is enabled */ - if (vcpu->arch.tsc_scaling_ratio != kvm_default_tsc_scaling_ratio && - delta_tsc && u64_shl_div_u64(delta_tsc, - kvm_tsc_scaling_ratio_frac_bits, - vcpu->arch.tsc_scaling_ratio, &delta_tsc)) - return -ERANGE; - - /* - * If the delta tsc can't fit in the 32 bit after the multi shift, - * we can't use the preemption timer. - * It's possible that it fits on later vmentries, but checking - * on every vmentry is costly so we just use an hrtimer. - */ - if (delta_tsc >> (cpu_preemption_timer_multi + 32)) - return -ERANGE; - - vmx->hv_deadline_tsc = tscl + delta_tsc; - *expired = !delta_tsc; - return 0; -} - -static void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu) -{ - to_vmx(vcpu)->hv_deadline_tsc = -1; -} -#endif - -static void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu) -{ - if (!kvm_pause_in_guest(vcpu->kvm)) - shrink_ple_window(vcpu); -} - -static void vmx_slot_enable_log_dirty(struct kvm *kvm, - struct kvm_memory_slot *slot) -{ - kvm_mmu_slot_leaf_clear_dirty(kvm, slot); - kvm_mmu_slot_largepage_remove_write_access(kvm, slot); -} - -static void vmx_slot_disable_log_dirty(struct kvm *kvm, - struct kvm_memory_slot *slot) -{ - kvm_mmu_slot_set_dirty(kvm, slot); -} - -static void vmx_flush_log_dirty(struct kvm *kvm) -{ - kvm_flush_pml_buffers(kvm); -} - -static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu) -{ - struct vmcs12 *vmcs12; - struct vcpu_vmx *vmx = to_vmx(vcpu); - gpa_t gpa, dst; - - if (is_guest_mode(vcpu)) { - WARN_ON_ONCE(vmx->nested.pml_full); - - /* - * Check if PML is enabled for the nested guest. - * Whether eptp bit 6 is set is already checked - * as part of A/D emulation. - */ - vmcs12 = get_vmcs12(vcpu); - if (!nested_cpu_has_pml(vmcs12)) - return 0; - - if (vmcs12->guest_pml_index >= PML_ENTITY_NUM) { - vmx->nested.pml_full = true; - return 1; - } - - gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS) & ~0xFFFull; - dst = vmcs12->pml_address + sizeof(u64) * vmcs12->guest_pml_index; - - if (kvm_write_guest_page(vcpu->kvm, gpa_to_gfn(dst), &gpa, - offset_in_page(dst), sizeof(gpa))) - return 0; - - vmcs12->guest_pml_index--; - } - - return 0; -} - -static void vmx_enable_log_dirty_pt_masked(struct kvm *kvm, - struct kvm_memory_slot *memslot, - gfn_t offset, unsigned long mask) -{ - kvm_mmu_clear_dirty_pt_masked(kvm, memslot, offset, mask); -} - -static void __pi_post_block(struct kvm_vcpu *vcpu) -{ - struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); - struct pi_desc old, new; - unsigned int dest; - - do { - old.control = new.control = pi_desc->control; - WARN(old.nv != POSTED_INTR_WAKEUP_VECTOR, - "Wakeup handler not enabled while the VCPU is blocked\n"); - - dest = cpu_physical_id(vcpu->cpu); - - if (x2apic_enabled()) - new.ndst = dest; - else - new.ndst = (dest << 8) & 0xFF00; - - /* set 'NV' to 'notification vector' */ - new.nv = POSTED_INTR_VECTOR; - } while (cmpxchg64(&pi_desc->control, old.control, - new.control) != old.control); - - if (!WARN_ON_ONCE(vcpu->pre_pcpu == -1)) { - spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); - list_del(&vcpu->blocked_vcpu_list); - spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); - vcpu->pre_pcpu = -1; - } -} - -/* - * This routine does the following things for vCPU which is going - * to be blocked if VT-d PI is enabled. - * - Store the vCPU to the wakeup list, so when interrupts happen - * we can find the right vCPU to wake up. - * - Change the Posted-interrupt descriptor as below: - * 'NDST' <-- vcpu->pre_pcpu - * 'NV' <-- POSTED_INTR_WAKEUP_VECTOR - * - If 'ON' is set during this process, which means at least one - * interrupt is posted for this vCPU, we cannot block it, in - * this case, return 1, otherwise, return 0. - * - */ -static int pi_pre_block(struct kvm_vcpu *vcpu) -{ - unsigned int dest; - struct pi_desc old, new; - struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); - - if (!kvm_arch_has_assigned_device(vcpu->kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP) || - !kvm_vcpu_apicv_active(vcpu)) - return 0; - - WARN_ON(irqs_disabled()); - local_irq_disable(); - if (!WARN_ON_ONCE(vcpu->pre_pcpu != -1)) { - vcpu->pre_pcpu = vcpu->cpu; - spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); - list_add_tail(&vcpu->blocked_vcpu_list, - &per_cpu(blocked_vcpu_on_cpu, - vcpu->pre_pcpu)); - spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); - } - - do { - old.control = new.control = pi_desc->control; - - WARN((pi_desc->sn == 1), - "Warning: SN field of posted-interrupts " - "is set before blocking\n"); - - /* - * Since vCPU can be preempted during this process, - * vcpu->cpu could be different with pre_pcpu, we - * need to set pre_pcpu as the destination of wakeup - * notification event, then we can find the right vCPU - * to wakeup in wakeup handler if interrupts happen - * when the vCPU is in blocked state. - */ - dest = cpu_physical_id(vcpu->pre_pcpu); - - if (x2apic_enabled()) - new.ndst = dest; - else - new.ndst = (dest << 8) & 0xFF00; - - /* set 'NV' to 'wakeup vector' */ - new.nv = POSTED_INTR_WAKEUP_VECTOR; - } while (cmpxchg64(&pi_desc->control, old.control, - new.control) != old.control); - - /* We should not block the vCPU if an interrupt is posted for it. */ - if (pi_test_on(pi_desc) == 1) - __pi_post_block(vcpu); - - local_irq_enable(); - return (vcpu->pre_pcpu == -1); -} - -static int vmx_pre_block(struct kvm_vcpu *vcpu) -{ - if (pi_pre_block(vcpu)) - return 1; - - if (kvm_lapic_hv_timer_in_use(vcpu)) - kvm_lapic_switch_to_sw_timer(vcpu); - - return 0; -} - -static void pi_post_block(struct kvm_vcpu *vcpu) -{ - if (vcpu->pre_pcpu == -1) - return; - - WARN_ON(irqs_disabled()); - local_irq_disable(); - __pi_post_block(vcpu); - local_irq_enable(); -} - -static void vmx_post_block(struct kvm_vcpu *vcpu) -{ - if (kvm_x86_ops->set_hv_timer) - kvm_lapic_switch_to_hv_timer(vcpu); - - pi_post_block(vcpu); -} - -/* - * vmx_update_pi_irte - set IRTE for Posted-Interrupts - * - * @kvm: kvm - * @host_irq: host irq of the interrupt - * @guest_irq: gsi of the interrupt - * @set: set or unset PI - * returns 0 on success, < 0 on failure - */ -static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq, - uint32_t guest_irq, bool set) -{ - struct kvm_kernel_irq_routing_entry *e; - struct kvm_irq_routing_table *irq_rt; - struct kvm_lapic_irq irq; - struct kvm_vcpu *vcpu; - struct vcpu_data vcpu_info; - int idx, ret = 0; - - if (!kvm_arch_has_assigned_device(kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP) || - !kvm_vcpu_apicv_active(kvm->vcpus[0])) - return 0; - - idx = srcu_read_lock(&kvm->irq_srcu); - irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu); - if (guest_irq >= irq_rt->nr_rt_entries || - hlist_empty(&irq_rt->map[guest_irq])) { - pr_warn_once("no route for guest_irq %u/%u (broken user space?)\n", - guest_irq, irq_rt->nr_rt_entries); - goto out; - } - - hlist_for_each_entry(e, &irq_rt->map[guest_irq], link) { - if (e->type != KVM_IRQ_ROUTING_MSI) - continue; - /* - * VT-d PI cannot support posting multicast/broadcast - * interrupts to a vCPU, we still use interrupt remapping - * for these kind of interrupts. - * - * For lowest-priority interrupts, we only support - * those with single CPU as the destination, e.g. user - * configures the interrupts via /proc/irq or uses - * irqbalance to make the interrupts single-CPU. - * - * We will support full lowest-priority interrupt later. - * - * In addition, we can only inject generic interrupts using - * the PI mechanism, refuse to route others through it. - */ - - kvm_set_msi_irq(kvm, e, &irq); - if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu) || - !kvm_irq_is_postable(&irq)) { - /* - * Make sure the IRTE is in remapped mode if - * we don't handle it in posted mode. - */ - ret = irq_set_vcpu_affinity(host_irq, NULL); - if (ret < 0) { - printk(KERN_INFO - "failed to back to remapped mode, irq: %u\n", - host_irq); - goto out; - } - - continue; - } - - vcpu_info.pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu)); - vcpu_info.vector = irq.vector; - - trace_kvm_pi_irte_update(host_irq, vcpu->vcpu_id, e->gsi, - vcpu_info.vector, vcpu_info.pi_desc_addr, set); - - if (set) - ret = irq_set_vcpu_affinity(host_irq, &vcpu_info); - else - ret = irq_set_vcpu_affinity(host_irq, NULL); - - if (ret < 0) { - printk(KERN_INFO "%s: failed to update PI IRTE\n", - __func__); - goto out; - } - } - - ret = 0; -out: - srcu_read_unlock(&kvm->irq_srcu, idx); - return ret; -} - -static void vmx_setup_mce(struct kvm_vcpu *vcpu) -{ - if (vcpu->arch.mcg_cap & MCG_LMCE_P) - to_vmx(vcpu)->msr_ia32_feature_control_valid_bits |= - FEATURE_CONTROL_LMCE; - else - to_vmx(vcpu)->msr_ia32_feature_control_valid_bits &= - ~FEATURE_CONTROL_LMCE; -} - -static int vmx_smi_allowed(struct kvm_vcpu *vcpu) -{ - /* we need a nested vmexit to enter SMM, postpone if run is pending */ - if (to_vmx(vcpu)->nested.nested_run_pending) - return 0; - return 1; -} - -static int vmx_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - - vmx->nested.smm.guest_mode = is_guest_mode(vcpu); - if (vmx->nested.smm.guest_mode) - nested_vmx_vmexit(vcpu, -1, 0, 0); - - vmx->nested.smm.vmxon = vmx->nested.vmxon; - vmx->nested.vmxon = false; - vmx_clear_hlt(vcpu); - return 0; -} - -static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - int ret; - - if (vmx->nested.smm.vmxon) { - vmx->nested.vmxon = true; - vmx->nested.smm.vmxon = false; - } - - if (vmx->nested.smm.guest_mode) { - ret = nested_vmx_enter_non_root_mode(vcpu, false); - if (ret) - return ret; - - vmx->nested.smm.guest_mode = false; - } - return 0; -} - -static int enable_smi_window(struct kvm_vcpu *vcpu) -{ - return 0; -} - -static bool vmx_need_emulation_on_page_fault(struct kvm_vcpu *vcpu) -{ - return false; -} - -static bool vmx_apic_init_signal_blocked(struct kvm_vcpu *vcpu) -{ - return to_vmx(vcpu)->nested.vmxon; -} - -static __init int hardware_setup(void) -{ - unsigned long host_bndcfgs; - struct desc_ptr dt; - int r, i; - - rdmsrl_safe(MSR_EFER, &host_efer); - - store_idt(&dt); - host_idt_base = dt.address; - - for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i) - kvm_define_shared_msr(i, vmx_msr_index[i]); - - if (setup_vmcs_config(&vmcs_config, &vmx_capability) < 0) - return -EIO; - - if (boot_cpu_has(X86_FEATURE_NX)) - kvm_enable_efer_bits(EFER_NX); - - if (boot_cpu_has(X86_FEATURE_MPX)) { - rdmsrl(MSR_IA32_BNDCFGS, host_bndcfgs); - WARN_ONCE(host_bndcfgs, "KVM: BNDCFGS in host will be lost"); - } - - if (!cpu_has_vmx_vpid() || !cpu_has_vmx_invvpid() || - !(cpu_has_vmx_invvpid_single() || cpu_has_vmx_invvpid_global())) - enable_vpid = 0; - - if (!cpu_has_vmx_ept() || - !cpu_has_vmx_ept_4levels() || - !cpu_has_vmx_ept_mt_wb() || - !cpu_has_vmx_invept_global()) - enable_ept = 0; - - if (!cpu_has_vmx_ept_ad_bits() || !enable_ept) - enable_ept_ad_bits = 0; - - if (!cpu_has_vmx_unrestricted_guest() || !enable_ept) - enable_unrestricted_guest = 0; - - if (!cpu_has_vmx_flexpriority()) - flexpriority_enabled = 0; - - if (!cpu_has_virtual_nmis()) - enable_vnmi = 0; - - /* - * set_apic_access_page_addr() is used to reload apic access - * page upon invalidation. No need to do anything if not - * using the APIC_ACCESS_ADDR VMCS field. - */ - if (!flexpriority_enabled) - kvm_x86_ops->set_apic_access_page_addr = NULL; - - if (!cpu_has_vmx_tpr_shadow()) - kvm_x86_ops->update_cr8_intercept = NULL; - - if (enable_ept && !cpu_has_vmx_ept_2m_page()) - kvm_disable_largepages(); - -#if IS_ENABLED(CONFIG_HYPERV) - if (ms_hyperv.nested_features & HV_X64_NESTED_GUEST_MAPPING_FLUSH - && enable_ept) { - kvm_x86_ops->tlb_remote_flush = hv_remote_flush_tlb; - kvm_x86_ops->tlb_remote_flush_with_range = - hv_remote_flush_tlb_with_range; - } -#endif - - if (!cpu_has_vmx_ple()) { - ple_gap = 0; - ple_window = 0; - ple_window_grow = 0; - ple_window_max = 0; - ple_window_shrink = 0; - } - - if (!cpu_has_vmx_apicv()) { - enable_apicv = 0; - kvm_x86_ops->sync_pir_to_irr = NULL; - } - - if (cpu_has_vmx_tsc_scaling()) { - kvm_has_tsc_control = true; - kvm_max_tsc_scaling_ratio = KVM_VMX_TSC_MULTIPLIER_MAX; - kvm_tsc_scaling_ratio_frac_bits = 48; - } - - set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */ - - if (enable_ept) - vmx_enable_tdp(); - else - kvm_disable_tdp(); - - /* - * Only enable PML when hardware supports PML feature, and both EPT - * and EPT A/D bit features are enabled -- PML depends on them to work. - */ - if (!enable_ept || !enable_ept_ad_bits || !cpu_has_vmx_pml()) - enable_pml = 0; - - if (!enable_pml) { - kvm_x86_ops->slot_enable_log_dirty = NULL; - kvm_x86_ops->slot_disable_log_dirty = NULL; - kvm_x86_ops->flush_log_dirty = NULL; - kvm_x86_ops->enable_log_dirty_pt_masked = NULL; - } - - if (!cpu_has_vmx_preemption_timer()) - enable_preemption_timer = false; - - if (enable_preemption_timer) { - u64 use_timer_freq = 5000ULL * 1000 * 1000; - u64 vmx_msr; - - rdmsrl(MSR_IA32_VMX_MISC, vmx_msr); - cpu_preemption_timer_multi = - vmx_msr & VMX_MISC_PREEMPTION_TIMER_RATE_MASK; - - if (tsc_khz) - use_timer_freq = (u64)tsc_khz * 1000; - use_timer_freq >>= cpu_preemption_timer_multi; - - /* - * KVM "disables" the preemption timer by setting it to its max - * value. Don't use the timer if it might cause spurious exits - * at a rate faster than 0.1 Hz (of uninterrupted guest time). - */ - if (use_timer_freq > 0xffffffffu / 10) - enable_preemption_timer = false; - } - - if (!enable_preemption_timer) { - kvm_x86_ops->set_hv_timer = NULL; - kvm_x86_ops->cancel_hv_timer = NULL; - kvm_x86_ops->request_immediate_exit = __kvm_request_immediate_exit; - } - - kvm_set_posted_intr_wakeup_handler(wakeup_handler); - - kvm_mce_cap_supported |= MCG_LMCE_P; - - if (pt_mode != PT_MODE_SYSTEM && pt_mode != PT_MODE_HOST_GUEST) - return -EINVAL; - if (!enable_ept || !cpu_has_vmx_intel_pt()) - pt_mode = PT_MODE_SYSTEM; - - if (nested) { - nested_vmx_setup_ctls_msrs(&vmcs_config.nested, - vmx_capability.ept, enable_apicv); - - r = nested_vmx_hardware_setup(kvm_vmx_exit_handlers); - if (r) - return r; - } - - r = alloc_kvm_area(); - if (r) - nested_vmx_hardware_unsetup(); - return r; -} - -static __exit void hardware_unsetup(void) -{ - if (nested) - nested_vmx_hardware_unsetup(); - - free_kvm_area(); -} - -static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { - .cpu_has_kvm_support = cpu_has_kvm_support, - .disabled_by_bios = vmx_disabled_by_bios, - .hardware_setup = hardware_setup, - .hardware_unsetup = hardware_unsetup, - .check_processor_compatibility = vmx_check_processor_compat, - .hardware_enable = hardware_enable, - .hardware_disable = hardware_disable, - .cpu_has_accelerated_tpr = report_flexpriority, - .has_emulated_msr = vmx_has_emulated_msr, - - .vm_init = vmx_vm_init, - .vm_alloc = vmx_vm_alloc, - .vm_free = vmx_vm_free, - - .vcpu_create = vmx_create_vcpu, - .vcpu_free = vmx_free_vcpu, - .vcpu_reset = vmx_vcpu_reset, - - .prepare_guest_switch = vmx_prepare_switch_to_guest, - .vcpu_load = vmx_vcpu_load, - .vcpu_put = vmx_vcpu_put, - - .update_bp_intercept = update_exception_bitmap, - .get_msr_feature = vmx_get_msr_feature, - .get_msr = vmx_get_msr, - .set_msr = vmx_set_msr, - .get_segment_base = vmx_get_segment_base, - .get_segment = vmx_get_segment, - .set_segment = vmx_set_segment, - .get_cpl = vmx_get_cpl, - .get_cs_db_l_bits = vmx_get_cs_db_l_bits, - .decache_cr0_guest_bits = vmx_decache_cr0_guest_bits, - .decache_cr4_guest_bits = vmx_decache_cr4_guest_bits, - .set_cr0 = vmx_set_cr0, - .set_cr3 = vmx_set_cr3, - .set_cr4 = vmx_set_cr4, - .set_efer = vmx_set_efer, - .get_idt = vmx_get_idt, - .set_idt = vmx_set_idt, - .get_gdt = vmx_get_gdt, - .set_gdt = vmx_set_gdt, - .get_dr6 = vmx_get_dr6, - .set_dr6 = vmx_set_dr6, - .set_dr7 = vmx_set_dr7, - .sync_dirty_debug_regs = vmx_sync_dirty_debug_regs, - .cache_reg = vmx_cache_reg, - .get_rflags = vmx_get_rflags, - .set_rflags = vmx_set_rflags, - - .tlb_flush = vmx_flush_tlb, - .tlb_flush_gva = vmx_flush_tlb_gva, - - .run = vmx_vcpu_run, - .handle_exit = vmx_handle_exit, - .skip_emulated_instruction = skip_emulated_instruction, - .set_interrupt_shadow = vmx_set_interrupt_shadow, - .get_interrupt_shadow = vmx_get_interrupt_shadow, - .patch_hypercall = vmx_patch_hypercall, - .set_irq = vmx_inject_irq, - .set_nmi = vmx_inject_nmi, - .queue_exception = vmx_queue_exception, - .cancel_injection = vmx_cancel_injection, - .interrupt_allowed = vmx_interrupt_allowed, - .nmi_allowed = vmx_nmi_allowed, - .get_nmi_mask = vmx_get_nmi_mask, - .set_nmi_mask = vmx_set_nmi_mask, - .enable_nmi_window = enable_nmi_window, - .enable_irq_window = enable_irq_window, - .update_cr8_intercept = update_cr8_intercept, - .set_virtual_apic_mode = vmx_set_virtual_apic_mode, - .set_apic_access_page_addr = vmx_set_apic_access_page_addr, - .get_enable_apicv = vmx_get_enable_apicv, - .refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl, - .load_eoi_exitmap = vmx_load_eoi_exitmap, - .apicv_post_state_restore = vmx_apicv_post_state_restore, - .hwapic_irr_update = vmx_hwapic_irr_update, - .hwapic_isr_update = vmx_hwapic_isr_update, - .guest_apic_has_interrupt = vmx_guest_apic_has_interrupt, - .sync_pir_to_irr = vmx_sync_pir_to_irr, - .deliver_posted_interrupt = vmx_deliver_posted_interrupt, - .dy_apicv_has_pending_interrupt = vmx_dy_apicv_has_pending_interrupt, - - .set_tss_addr = vmx_set_tss_addr, - .set_identity_map_addr = vmx_set_identity_map_addr, - .get_tdp_level = get_ept_level, - .get_mt_mask = vmx_get_mt_mask, - - .get_exit_info = vmx_get_exit_info, - - .get_lpage_level = vmx_get_lpage_level, - - .cpuid_update = vmx_cpuid_update, - - .rdtscp_supported = vmx_rdtscp_supported, - .invpcid_supported = vmx_invpcid_supported, - - .set_supported_cpuid = vmx_set_supported_cpuid, - - .has_wbinvd_exit = cpu_has_vmx_wbinvd_exit, - - .read_l1_tsc_offset = vmx_read_l1_tsc_offset, - .write_l1_tsc_offset = vmx_write_l1_tsc_offset, - - .set_tdp_cr3 = vmx_set_cr3, - - .check_intercept = vmx_check_intercept, - .handle_exit_irqoff = vmx_handle_exit_irqoff, - .mpx_supported = vmx_mpx_supported, - .xsaves_supported = vmx_xsaves_supported, - .umip_emulated = vmx_umip_emulated, - .pt_supported = vmx_pt_supported, - - .request_immediate_exit = vmx_request_immediate_exit, - - .sched_in = vmx_sched_in, - - .slot_enable_log_dirty = vmx_slot_enable_log_dirty, - .slot_disable_log_dirty = vmx_slot_disable_log_dirty, - .flush_log_dirty = vmx_flush_log_dirty, - .enable_log_dirty_pt_masked = vmx_enable_log_dirty_pt_masked, - .write_log_dirty = vmx_write_pml_buffer, - - .pre_block = vmx_pre_block, - .post_block = vmx_post_block, - - .pmu_ops = &intel_pmu_ops, - - .update_pi_irte = vmx_update_pi_irte, - -#ifdef CONFIG_X86_64 - .set_hv_timer = vmx_set_hv_timer, - .cancel_hv_timer = vmx_cancel_hv_timer, -#endif - - .setup_mce = vmx_setup_mce, - - .smi_allowed = vmx_smi_allowed, - .pre_enter_smm = vmx_pre_enter_smm, - .pre_leave_smm = vmx_pre_leave_smm, - .enable_smi_window = enable_smi_window, - - .check_nested_events = NULL, - .get_nested_state = NULL, - .set_nested_state = NULL, - .get_vmcs12_pages = NULL, - .nested_enable_evmcs = NULL, - .nested_get_evmcs_version = NULL, - .need_emulation_on_page_fault = vmx_need_emulation_on_page_fault, - .apic_init_signal_blocked = vmx_apic_init_signal_blocked, -}; - -static void vmx_cleanup_l1d_flush(void) -{ - if (vmx_l1d_flush_pages) { - free_pages((unsigned long)vmx_l1d_flush_pages, L1D_CACHE_ORDER); - vmx_l1d_flush_pages = NULL; - } - /* Restore state so sysfs ignores VMX */ - l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO; -} - -static void vmx_exit(void) -{ -#ifdef CONFIG_KEXEC_CORE - RCU_INIT_POINTER(crash_vmclear_loaded_vmcss, NULL); - synchronize_rcu(); -#endif - - kvm_exit(); - -#if IS_ENABLED(CONFIG_HYPERV) - if (static_branch_unlikely(&enable_evmcs)) { - int cpu; - struct hv_vp_assist_page *vp_ap; - /* - * Reset everything to support using non-enlightened VMCS - * access later (e.g. when we reload the module with - * enlightened_vmcs=0) - */ - for_each_online_cpu(cpu) { - vp_ap = hv_get_vp_assist_page(cpu); - - if (!vp_ap) - continue; - - vp_ap->nested_control.features.directhypercall = 0; - vp_ap->current_nested_vmcs = 0; - vp_ap->enlighten_vmentry = 0; - } - - static_branch_disable(&enable_evmcs); - } -#endif - vmx_cleanup_l1d_flush(); -} -module_exit(vmx_exit); - -static int __init vmx_init(void) -{ - int r; - -#if IS_ENABLED(CONFIG_HYPERV) - /* - * Enlightened VMCS usage should be recommended and the host needs - * to support eVMCS v1 or above. We can also disable eVMCS support - * with module parameter. - */ - if (enlightened_vmcs && - ms_hyperv.hints & HV_X64_ENLIGHTENED_VMCS_RECOMMENDED && - (ms_hyperv.nested_features & HV_X64_ENLIGHTENED_VMCS_VERSION) >= - KVM_EVMCS_VERSION) { - int cpu; - - /* Check that we have assist pages on all online CPUs */ - for_each_online_cpu(cpu) { - if (!hv_get_vp_assist_page(cpu)) { - enlightened_vmcs = false; - break; - } - } - - if (enlightened_vmcs) { - pr_info("KVM: vmx: using Hyper-V Enlightened VMCS\n"); - static_branch_enable(&enable_evmcs); - } - - if (ms_hyperv.nested_features & HV_X64_NESTED_DIRECT_FLUSH) - vmx_x86_ops.enable_direct_tlbflush - = hv_enable_direct_tlbflush; - - } else { - enlightened_vmcs = false; - } -#endif - - r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx), - __alignof__(struct vcpu_vmx), THIS_MODULE); - if (r) - return r; - - /* - * Must be called after kvm_init() so enable_ept is properly set - * up. Hand the parameter mitigation value in which was stored in - * the pre module init parser. If no parameter was given, it will - * contain 'auto' which will be turned into the default 'cond' - * mitigation mode. - */ - r = vmx_setup_l1d_flush(vmentry_l1d_flush_param); - if (r) { - vmx_exit(); - return r; - } - -#ifdef CONFIG_KEXEC_CORE - rcu_assign_pointer(crash_vmclear_loaded_vmcss, - crash_vmclear_local_loaded_vmcss); -#endif - vmx_check_vmcs12_offsets(); - - return 0; -} -module_init(vmx_init); diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c index 7d2542ad346a..6612d532e42e 100644 --- a/arch/x86/mm/gup.c +++ b/arch/x86/mm/gup.c @@ -95,7 +95,10 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr, } VM_BUG_ON(!pfn_valid(pte_pfn(pte))); page = pte_page(pte); - get_page(page); + if (unlikely(!try_get_page(page))) { + pte_unmap(ptep); + return 0; + } SetPageReferenced(page); pages[*nr] = page; (*nr)++; @@ -132,6 +135,8 @@ static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr, refs = 0; head = pmd_page(pmd); + if (WARN_ON_ONCE(page_ref_count(head) <= 0)) + return 0; page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT); do { VM_BUG_ON_PAGE(compound_head(page) != head, page); @@ -208,6 +213,8 @@ static noinline int gup_huge_pud(pud_t pud, unsigned long addr, refs = 0; head = pud_page(pud); + if (WARN_ON_ONCE(page_ref_count(head) <= 0)) + return 0; page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT); do { VM_BUG_ON_PAGE(compound_head(page) != head, page); diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 4bc352fc08f1..105872617be0 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -465,7 +465,6 @@ void __init efi_init(void) efi_char16_t *c16; char vendor[100] = "unknown"; int i = 0; - void *tmp; #ifdef CONFIG_X86_32 if (boot_params.efi_info.efi_systab_hi || @@ -490,14 +489,16 @@ void __init efi_init(void) /* * Show what we know for posterity */ - c16 = tmp = early_memremap(efi.systab->fw_vendor, 2); + c16 = early_memremap_ro(efi.systab->fw_vendor, + sizeof(vendor) * sizeof(efi_char16_t)); if (c16) { - for (i = 0; i < sizeof(vendor) - 1 && *c16; ++i) - vendor[i] = *c16++; + for (i = 0; i < sizeof(vendor) - 1 && c16[i]; ++i) + vendor[i] = c16[i]; vendor[i] = '\0'; - } else + early_memunmap(c16, sizeof(vendor) * sizeof(efi_char16_t)); + } else { pr_err("Could not map the firmware vendor!\n"); - early_memunmap(tmp, 2); + } pr_info("EFI v%u.%.02u by %s\n", efi.systab->hdr.revision >> 16, diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c index d12782dc9683..9bd4691cc5c5 100644 --- a/crypto/algif_skcipher.c +++ b/crypto/algif_skcipher.c @@ -538,7 +538,7 @@ static int skcipher_recvmsg_async(struct socket *sock, struct msghdr *msg, lock_sock(sk); tx_nents = skcipher_all_sg_nents(ctx); sreq->tsg = kcalloc(tx_nents, sizeof(*sg), GFP_KERNEL); - if (unlikely(!sreq->tsg)) + if (unlikely(ZERO_OR_NULL_PTR(sreq->tsg))) goto unlock; sg_init_table(sreq->tsg, tx_nents); memcpy(iv, ctx->iv, ivsize); diff --git a/drivers/acpi/acpica/dsfield.c b/drivers/acpi/acpica/dsfield.c index 20de148594fd..d56cbcda37c1 100644 --- a/drivers/acpi/acpica/dsfield.c +++ b/drivers/acpi/acpica/dsfield.c @@ -272,7 +272,7 @@ cleanup: * FUNCTION: acpi_ds_get_field_names * * PARAMETERS: info - create_field info structure - * ` walk_state - Current method state + * walk_state - Current method state * arg - First parser arg for the field name list * * RETURN: Status diff --git a/drivers/acpi/acpica/dswload.c b/drivers/acpi/acpica/dswload.c index 097188a6b1c1..35f1d7657927 100644 --- a/drivers/acpi/acpica/dswload.c +++ b/drivers/acpi/acpica/dswload.c @@ -440,6 +440,27 @@ acpi_status acpi_ds_load1_end_op(struct acpi_walk_state *walk_state) ACPI_DEBUG_PRINT((ACPI_DB_DISPATCH, "Op=%p State=%p\n", op, walk_state)); + /* + * Disassembler: handle create field operators here. + * + * create_buffer_field is a deferred op that is typically processed in load + * pass 2. However, disassembly of control method contents walk the parse + * tree with ACPI_PARSE_LOAD_PASS1 and AML_CREATE operators are processed + * in a later walk. This is a problem when there is a control method that + * has the same name as the AML_CREATE object. In this case, any use of the + * name segment will be detected as a method call rather than a reference + * to a buffer field. + * + * This earlier creation during disassembly solves this issue by inserting + * the named object in the ACPI namespace so that references to this name + * would be a name string rather than a method call. + */ + if ((walk_state->parse_flags & ACPI_PARSE_DISASSEMBLE) && + (walk_state->op_info->flags & AML_CREATE)) { + status = acpi_ds_create_buffer_field(op, walk_state); + return_ACPI_STATUS(status); + } + /* We are only interested in opcodes that have an associated name */ if (!(walk_state->op_info->flags & (AML_NAMED | AML_FIELD))) { diff --git a/drivers/base/dd.c b/drivers/base/dd.c index 1dffb018a7fe..04a923186081 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -283,7 +283,10 @@ static int really_probe(struct device *dev, struct device_driver *drv) atomic_inc(&probe_count); pr_debug("bus: '%s': %s: probing driver %s with device %s\n", drv->bus->name, __func__, drv->name, dev_name(dev)); - WARN_ON(!list_empty(&dev->devres_head)); + if (!list_empty(&dev->devres_head)) { + dev_crit(dev, "Resources present before probing\n"); + return -EBUSY; + } dev->driver = drv; diff --git a/drivers/block/brd.c b/drivers/block/brd.c index 1914c63ca8b1..58c1138ad5e1 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -581,6 +581,25 @@ static struct kobject *brd_probe(dev_t dev, int *part, void *data) return kobj; } +static inline void brd_check_and_reset_par(void) +{ + if (unlikely(!max_part)) + max_part = 1; + + /* + * make sure 'max_part' can be divided exactly by (1U << MINORBITS), + * otherwise, it is possiable to get same dev_t when adding partitions. + */ + if ((1U << MINORBITS) % max_part != 0) + max_part = 1UL << fls(max_part); + + if (max_part > DISK_MAX_PARTS) { + pr_info("brd: max_part can't be larger than %d, reset max_part = %d.\n", + DISK_MAX_PARTS, DISK_MAX_PARTS); + max_part = DISK_MAX_PARTS; + } +} + static int __init brd_init(void) { struct brd_device *brd, *next; @@ -604,8 +623,7 @@ static int __init brd_init(void) if (register_blkdev(RAMDISK_MAJOR, "ramdisk")) return -EIO; - if (unlikely(!max_part)) - max_part = 1; + brd_check_and_reset_par(); for (i = 0; i < rd_nr; i++) { brd = brd_alloc(i); diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index a12a163c6e6d..58ce577ba6d7 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -848,14 +848,17 @@ static void reset_fdc_info(int mode) /* selects the fdc and drive, and enables the fdc's input/dma. */ static void set_fdc(int drive) { + unsigned int new_fdc = fdc; + if (drive >= 0 && drive < N_DRIVE) { - fdc = FDC(drive); + new_fdc = FDC(drive); current_drive = drive; } - if (fdc != 1 && fdc != 0) { + if (new_fdc >= N_FDC) { pr_info("bad fdc value\n"); return; } + fdc = new_fdc; set_dor(fdc, ~0, 8); #if N_FDC > 1 set_dor(1 - fdc, ~8, 0); diff --git a/drivers/char/ipmi/ipmi_ssif.c b/drivers/char/ipmi/ipmi_ssif.c index 67d23ed2d1a0..29082d99264e 100644 --- a/drivers/char/ipmi/ipmi_ssif.c +++ b/drivers/char/ipmi/ipmi_ssif.c @@ -742,10 +742,14 @@ static void msg_done_handler(struct ssif_info *ssif_info, int result, flags = ipmi_ssif_lock_cond(ssif_info, &oflags); msg = ssif_info->curr_msg; if (msg) { + if (data) { + if (len > IPMI_MAX_MSG_LENGTH) + len = IPMI_MAX_MSG_LENGTH; + memcpy(msg->rsp, data, len); + } else { + len = 0; + } msg->rsp_size = len; - if (msg->rsp_size > IPMI_MAX_MSG_LENGTH) - msg->rsp_size = IPMI_MAX_MSG_LENGTH; - memcpy(msg->rsp, data, msg->rsp_size); ssif_info->curr_msg = NULL; } diff --git a/drivers/clk/qcom/clk-rcg2.c b/drivers/clk/qcom/clk-rcg2.c index 350a01f74870..8b549ece9f13 100644 --- a/drivers/clk/qcom/clk-rcg2.c +++ b/drivers/clk/qcom/clk-rcg2.c @@ -194,6 +194,9 @@ static int _freq_tbl_determine_rate(struct clk_hw *hw, clk_flags = clk_hw_get_flags(hw); p = clk_hw_get_parent_by_index(hw, index); + if (!p) + return -EINVAL; + if (clk_flags & CLK_SET_RATE_PARENT) { if (f->pre_div) { if (!rate) diff --git a/drivers/dma/coh901318.c b/drivers/dma/coh901318.c index 4746fee4cd48..546a91186de1 100644 --- a/drivers/dma/coh901318.c +++ b/drivers/dma/coh901318.c @@ -1960,8 +1960,6 @@ static void dma_tc_handle(struct coh901318_chan *cohc) return; } - spin_lock(&cohc->lock); - /* * When we reach this point, at least one queue item * should have been moved over from cohc->queue to @@ -1982,8 +1980,6 @@ static void dma_tc_handle(struct coh901318_chan *cohc) if (coh901318_queue_start(cohc) == NULL) cohc->busy = 0; - spin_unlock(&cohc->lock); - /* * This tasklet will remove items from cohc->active * and thus terminates them. diff --git a/drivers/dma/tegra20-apb-dma.c b/drivers/dma/tegra20-apb-dma.c index 67f201b8dcda..b5cf5d36de2b 100644 --- a/drivers/dma/tegra20-apb-dma.c +++ b/drivers/dma/tegra20-apb-dma.c @@ -285,7 +285,7 @@ static struct tegra_dma_desc *tegra_dma_desc_get( /* Do not allocate if desc are waiting for ack */ list_for_each_entry(dma_desc, &tdc->free_dma_desc, node) { - if (async_tx_test_ack(&dma_desc->txd)) { + if (async_tx_test_ack(&dma_desc->txd) && !dma_desc->cb_count) { list_del(&dma_desc->node); spin_unlock_irqrestore(&tdc->lock, flags); dma_desc->txd.flags = 0; @@ -754,10 +754,6 @@ static int tegra_dma_terminate_all(struct dma_chan *dc) bool was_busy; spin_lock_irqsave(&tdc->lock, flags); - if (list_empty(&tdc->pending_sg_req)) { - spin_unlock_irqrestore(&tdc->lock, flags); - return 0; - } if (!tdc->busy) goto skip_dma_stop; diff --git a/drivers/firmware/efi/efivars.c b/drivers/firmware/efi/efivars.c index 10e6774ab2a2..fc4d0228b7d8 100644 --- a/drivers/firmware/efi/efivars.c +++ b/drivers/firmware/efi/efivars.c @@ -139,13 +139,16 @@ static ssize_t efivar_attr_read(struct efivar_entry *entry, char *buf) { struct efi_variable *var = &entry->var; + unsigned long size = sizeof(var->Data); char *str = buf; + int ret; if (!entry || !buf) return -EINVAL; - var->DataSize = 1024; - if (efivar_entry_get(entry, &var->Attributes, &var->DataSize, var->Data)) + ret = efivar_entry_get(entry, &var->Attributes, &size, var->Data); + var->DataSize = size; + if (ret) return -EIO; if (var->Attributes & EFI_VARIABLE_NON_VOLATILE) @@ -172,13 +175,16 @@ static ssize_t efivar_size_read(struct efivar_entry *entry, char *buf) { struct efi_variable *var = &entry->var; + unsigned long size = sizeof(var->Data); char *str = buf; + int ret; if (!entry || !buf) return -EINVAL; - var->DataSize = 1024; - if (efivar_entry_get(entry, &var->Attributes, &var->DataSize, var->Data)) + ret = efivar_entry_get(entry, &var->Attributes, &size, var->Data); + var->DataSize = size; + if (ret) return -EIO; str += sprintf(str, "0x%lx\n", var->DataSize); @@ -189,12 +195,15 @@ static ssize_t efivar_data_read(struct efivar_entry *entry, char *buf) { struct efi_variable *var = &entry->var; + unsigned long size = sizeof(var->Data); + int ret; if (!entry || !buf) return -EINVAL; - var->DataSize = 1024; - if (efivar_entry_get(entry, &var->Attributes, &var->DataSize, var->Data)) + ret = efivar_entry_get(entry, &var->Attributes, &size, var->Data); + var->DataSize = size; + if (ret) return -EIO; memcpy(buf, var->Data, var->DataSize); @@ -263,6 +272,9 @@ efivar_store_raw(struct efivar_entry *entry, const char *buf, size_t count) u8 *data; int err; + if (!entry || !buf) + return -EINVAL; + if (is_compat()) { struct compat_efi_variable *compat; @@ -314,14 +326,16 @@ efivar_show_raw(struct efivar_entry *entry, char *buf) { struct efi_variable *var = &entry->var; struct compat_efi_variable *compat; + unsigned long datasize = sizeof(var->Data); size_t size; + int ret; if (!entry || !buf) return 0; - var->DataSize = 1024; - if (efivar_entry_get(entry, &entry->var.Attributes, - &entry->var.DataSize, entry->var.Data)) + ret = efivar_entry_get(entry, &var->Attributes, &datasize, var->Data); + var->DataSize = datasize; + if (ret) return -EIO; if (is_compat()) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c index 3e90ddcbb24a..96d557b97f5c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c @@ -319,17 +319,9 @@ bool amdgpu_atombios_get_connector_info_from_object_table(struct amdgpu_device * path_size += le16_to_cpu(path->usSize); if (device_support & le16_to_cpu(path->usDeviceTag)) { - uint8_t con_obj_id, con_obj_num, con_obj_type; - - con_obj_id = + uint8_t con_obj_id = (le16_to_cpu(path->usConnObjectId) & OBJECT_ID_MASK) >> OBJECT_ID_SHIFT; - con_obj_num = - (le16_to_cpu(path->usConnObjectId) & ENUM_ID_MASK) - >> ENUM_ID_SHIFT; - con_obj_type = - (le16_to_cpu(path->usConnObjectId) & - OBJECT_TYPE_MASK) >> OBJECT_TYPE_SHIFT; /* Skip TV/CV support */ if ((le16_to_cpu(path->usDeviceTag) == @@ -354,15 +346,7 @@ bool amdgpu_atombios_get_connector_info_from_object_table(struct amdgpu_device * router.ddc_valid = false; router.cd_valid = false; for (j = 0; j < ((le16_to_cpu(path->usSize) - 8) / 2); j++) { - uint8_t grph_obj_id, grph_obj_num, grph_obj_type; - - grph_obj_id = - (le16_to_cpu(path->usGraphicObjIds[j]) & - OBJECT_ID_MASK) >> OBJECT_ID_SHIFT; - grph_obj_num = - (le16_to_cpu(path->usGraphicObjIds[j]) & - ENUM_ID_MASK) >> ENUM_ID_SHIFT; - grph_obj_type = + uint8_t grph_obj_type = (le16_to_cpu(path->usGraphicObjIds[j]) & OBJECT_TYPE_MASK) >> OBJECT_TYPE_SHIFT; diff --git a/drivers/gpu/drm/gma500/framebuffer.c b/drivers/gpu/drm/gma500/framebuffer.c index 2eaf1b31c7bd..ef60bb197195 100644 --- a/drivers/gpu/drm/gma500/framebuffer.c +++ b/drivers/gpu/drm/gma500/framebuffer.c @@ -533,6 +533,7 @@ static int psbfb_probe(struct drm_fb_helper *helper, container_of(helper, struct psb_fbdev, psb_fb_helper); struct drm_device *dev = psb_fbdev->psb_fb_helper.dev; struct drm_psb_private *dev_priv = dev->dev_private; + unsigned int fb_size; int bytespp; bytespp = sizes->surface_bpp / 8; @@ -542,8 +543,11 @@ static int psbfb_probe(struct drm_fb_helper *helper, /* If the mode will not fit in 32bit then switch to 16bit to get a console on full resolution. The X mode setting server will allocate its own 32bit GEM framebuffer */ - if (ALIGN(sizes->fb_width * bytespp, 64) * sizes->fb_height > - dev_priv->vram_stolen_size) { + fb_size = ALIGN(sizes->surface_width * bytespp, 64) * + sizes->surface_height; + fb_size = ALIGN(fb_size, PAGE_SIZE); + + if (fb_size > dev_priv->vram_stolen_size) { sizes->surface_bpp = 16; sizes->surface_depth = 16; } diff --git a/drivers/gpu/drm/msm/dsi/dsi_manager.c b/drivers/gpu/drm/msm/dsi/dsi_manager.c index 0455ff75074a..34220df1265f 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_manager.c +++ b/drivers/gpu/drm/msm/dsi/dsi_manager.c @@ -302,7 +302,7 @@ static int dsi_mgr_connector_get_modes(struct drm_connector *connector) return num; } -static int dsi_mgr_connector_mode_valid(struct drm_connector *connector, +static enum drm_mode_status dsi_mgr_connector_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { int id = dsi_mgr_connector_get_id(connector); @@ -434,6 +434,7 @@ static void dsi_mgr_bridge_post_disable(struct drm_bridge *bridge) struct msm_dsi *msm_dsi1 = dsi_mgr_get_dsi(DSI_1); struct mipi_dsi_host *host = msm_dsi->host; struct drm_panel *panel = msm_dsi->panel; + struct msm_dsi_pll *src_pll; bool is_dual_dsi = IS_DUAL_DSI(); int ret; @@ -467,6 +468,10 @@ static void dsi_mgr_bridge_post_disable(struct drm_bridge *bridge) id, ret); } + /* Save PLL status if it is a clock source */ + src_pll = msm_dsi_phy_get_pll(msm_dsi->phy); + msm_dsi_pll_save_state(src_pll); + ret = msm_dsi_host_power_off(host); if (ret) pr_err("%s: host %d power off failed,%d\n", __func__, id, ret); diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c index 574c36b492ee..fccec23731e2 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.c +++ b/drivers/gpu/drm/nouveau/nouveau_fence.c @@ -157,7 +157,7 @@ nouveau_fence_wait_uevent_handler(struct nvif_notify *notify) fence = list_entry(fctx->pending.next, typeof(*fence), head); chan = rcu_dereference_protected(fence->channel, lockdep_is_held(&fctx->lock)); - if (nouveau_fence_update(fence->channel, fctx)) + if (nouveau_fence_update(chan, fctx)) ret = NVIF_NOTIFY_DROP; } spin_unlock_irqrestore(&fctx->lock, flags); diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c index 01803c0679b6..d012df9fb9df 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c @@ -72,6 +72,8 @@ nv50_disp_chan_mthd(struct nv50_disp_chan *chan, int debug) if (debug > subdev->debug) return; + if (!mthd) + return; for (i = 0; (list = mthd->data[i].mthd) != NULL; i++) { u32 base = chan->head * mthd->addr; diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c index 446d99062306..4572bfba017c 100644 --- a/drivers/gpu/drm/radeon/radeon_display.c +++ b/drivers/gpu/drm/radeon/radeon_display.c @@ -110,6 +110,8 @@ static void dce5_crtc_load_lut(struct drm_crtc *crtc) DRM_DEBUG_KMS("%d\n", radeon_crtc->crtc_id); + msleep(10); + WREG32(NI_INPUT_CSC_CONTROL + radeon_crtc->crtc_offset, (NI_INPUT_CSC_GRPH_MODE(NI_INPUT_CSC_BYPASS) | NI_INPUT_CSC_OVL_MODE(NI_INPUT_CSC_BYPASS))); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c index 1f013d45c9e9..0c7c3005594c 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c @@ -210,8 +210,10 @@ int vmw_cmdbuf_res_add(struct vmw_cmdbuf_res_manager *man, cres->hash.key = user_key | (res_type << 24); ret = drm_ht_insert_item(&man->resources, &cres->hash); - if (unlikely(ret != 0)) + if (unlikely(ret != 0)) { + kfree(cres); goto out_invalid_key; + } cres->state = VMW_CMDBUF_RES_ADD; cres->res = vmw_resource_reference(res); diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 16ff8d3c7cfe..325adbef134c 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -1508,7 +1508,9 @@ int hid_report_raw_event(struct hid_device *hid, int type, u8 *data, u32 size, rsize = ((report->size - 1) >> 3) + 1; - if (rsize > HID_MAX_BUFFER_SIZE) + if (report_enum->numbered && rsize >= HID_MAX_BUFFER_SIZE) + rsize = HID_MAX_BUFFER_SIZE - 1; + else if (rsize > HID_MAX_BUFFER_SIZE) rsize = HID_MAX_BUFFER_SIZE; if (csize < rsize) { diff --git a/drivers/hid/usbhid/hiddev.c b/drivers/hid/usbhid/hiddev.c index 8903ea09ac58..dbdd265075da 100644 --- a/drivers/hid/usbhid/hiddev.c +++ b/drivers/hid/usbhid/hiddev.c @@ -962,9 +962,9 @@ void hiddev_disconnect(struct hid_device *hid) hiddev->exist = 0; if (hiddev->open) { - mutex_unlock(&hiddev->existancelock); usbhid_close(hiddev->hid); wake_up_interruptible(&hiddev->wait); + mutex_unlock(&hiddev->existancelock); } else { mutex_unlock(&hiddev->existancelock); kfree(hiddev); diff --git a/drivers/hwmon/adt7462.c b/drivers/hwmon/adt7462.c index 5929e126da63..d9923d63eb4f 100644 --- a/drivers/hwmon/adt7462.c +++ b/drivers/hwmon/adt7462.c @@ -426,7 +426,7 @@ static int ADT7462_REG_VOLT(struct adt7462_data *data, int which) return 0x95; break; } - return -ENODEV; + return 0; } /* Provide labels for sysfs */ diff --git a/drivers/hwmon/pmbus/ltc2978.c b/drivers/hwmon/pmbus/ltc2978.c index 58b789c28b48..94eea2ac6251 100644 --- a/drivers/hwmon/pmbus/ltc2978.c +++ b/drivers/hwmon/pmbus/ltc2978.c @@ -89,8 +89,8 @@ enum chips { ltc2974, ltc2975, ltc2977, ltc2978, ltc2980, ltc3880, ltc3882, #define LTC_POLL_TIMEOUT 100 /* in milli-seconds */ -#define LTC_NOT_BUSY BIT(5) -#define LTC_NOT_PENDING BIT(4) +#define LTC_NOT_BUSY BIT(6) +#define LTC_NOT_PENDING BIT(5) /* * LTC2978 clears peak data whenever the CLEAR_FAULTS command is executed, which diff --git a/drivers/i2c/busses/i2c-jz4780.c b/drivers/i2c/busses/i2c-jz4780.c index 4b58e8aaf5c5..ba3b94505c14 100644 --- a/drivers/i2c/busses/i2c-jz4780.c +++ b/drivers/i2c/busses/i2c-jz4780.c @@ -82,25 +82,6 @@ #define JZ4780_I2C_STA_TFNF BIT(1) #define JZ4780_I2C_STA_ACT BIT(0) -static const char * const jz4780_i2c_abrt_src[] = { - "ABRT_7B_ADDR_NOACK", - "ABRT_10ADDR1_NOACK", - "ABRT_10ADDR2_NOACK", - "ABRT_XDATA_NOACK", - "ABRT_GCALL_NOACK", - "ABRT_GCALL_READ", - "ABRT_HS_ACKD", - "SBYTE_ACKDET", - "ABRT_HS_NORSTRT", - "SBYTE_NORSTRT", - "ABRT_10B_RD_NORSTRT", - "ABRT_MASTER_DIS", - "ARB_LOST", - "SLVFLUSH_TXFIFO", - "SLV_ARBLOST", - "SLVRD_INTX", -}; - #define JZ4780_I2C_INTST_IGC BIT(11) #define JZ4780_I2C_INTST_ISTT BIT(10) #define JZ4780_I2C_INTST_ISTP BIT(9) @@ -538,21 +519,8 @@ done: static void jz4780_i2c_txabrt(struct jz4780_i2c *i2c, int src) { - int i; - - dev_err(&i2c->adap.dev, "txabrt: 0x%08x\n", src); - dev_err(&i2c->adap.dev, "device addr=%x\n", - jz4780_i2c_readw(i2c, JZ4780_I2C_TAR)); - dev_err(&i2c->adap.dev, "send cmd count:%d %d\n", - i2c->cmd, i2c->cmd_buf[i2c->cmd]); - dev_err(&i2c->adap.dev, "receive data count:%d %d\n", - i2c->cmd, i2c->data_buf[i2c->cmd]); - - for (i = 0; i < 16; i++) { - if (src & BIT(i)) - dev_dbg(&i2c->adap.dev, "I2C TXABRT[%d]=%s\n", - i, jz4780_i2c_abrt_src[i]); - } + dev_dbg(&i2c->adap.dev, "txabrt: 0x%08x, cmd: %d, send: %d, recv: %d\n", + src, i2c->cmd, i2c->cmd_buf[i2c->cmd], i2c->data_buf[i2c->cmd]); } static inline int jz4780_i2c_xfer_read(struct jz4780_i2c *i2c, diff --git a/drivers/ide/cmd64x.c b/drivers/ide/cmd64x.c index b127ed60c733..9dde8390da09 100644 --- a/drivers/ide/cmd64x.c +++ b/drivers/ide/cmd64x.c @@ -65,6 +65,9 @@ static void cmd64x_program_timings(ide_drive_t *drive, u8 mode) struct ide_timing t; u8 arttim = 0; + if (drive->dn >= ARRAY_SIZE(drwtim_regs)) + return; + ide_timing_compute(drive, mode, &t, T, 0); /* diff --git a/drivers/ide/serverworks.c b/drivers/ide/serverworks.c index a97affca18ab..0f57d45484d1 100644 --- a/drivers/ide/serverworks.c +++ b/drivers/ide/serverworks.c @@ -114,6 +114,9 @@ static void svwks_set_pio_mode(ide_hwif_t *hwif, ide_drive_t *drive) struct pci_dev *dev = to_pci_dev(hwif->dev); const u8 pio = drive->pio_mode - XFER_PIO_0; + if (drive->dn >= ARRAY_SIZE(drive_pci)) + return; + pci_write_config_byte(dev, drive_pci[drive->dn], pio_modes[pio]); if (svwks_csb_check(dev)) { @@ -140,6 +143,9 @@ static void svwks_set_dma_mode(ide_hwif_t *hwif, ide_drive_t *drive) u8 ultra_enable = 0, ultra_timing = 0, dma_timing = 0; + if (drive->dn >= ARRAY_SIZE(drive_pci2)) + return; + pci_read_config_byte(dev, (0x56|hwif->channel), &ultra_timing); pci_read_config_byte(dev, 0x54, &ultra_enable); diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index 941cd9b83941..53c622c99ee4 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -1073,6 +1073,7 @@ struct ib_cm_id *ib_cm_insert_listen(struct ib_device *device, /* Sharing an ib_cm_id with different handlers is not * supported */ spin_unlock_irqrestore(&cm.lock, flags); + ib_destroy_cm_id(cm_id); return ERR_PTR(-EINVAL); } atomic_inc(&cm_id_priv->refcount); diff --git a/drivers/infiniband/core/iwcm.c b/drivers/infiniband/core/iwcm.c index ff9163dc1596..c4b779cc3b94 100644 --- a/drivers/infiniband/core/iwcm.c +++ b/drivers/infiniband/core/iwcm.c @@ -125,8 +125,10 @@ static void dealloc_work_entries(struct iwcm_id_private *cm_id_priv) { struct list_head *e, *tmp; - list_for_each_safe(e, tmp, &cm_id_priv->work_free_list) + list_for_each_safe(e, tmp, &cm_id_priv->work_free_list) { + list_del(e); kfree(list_entry(e, struct iwcm_work, free_list)); + } } static int alloc_work_entries(struct iwcm_id_private *cm_id_priv, int count) diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index 32ef17e1aef8..d8adb586362c 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -3295,6 +3295,17 @@ isert_wait4flush(struct isert_conn *isert_conn) wait_for_completion(&isert_conn->wait_comp_err); } +static void +isert_wait4cmds(struct iscsi_conn *conn) +{ + isert_info("iscsi_conn %p\n", conn); + + if (conn->sess) { + target_sess_cmd_list_set_waiting(conn->sess->se_sess); + target_wait_for_sess_cmds(conn->sess->se_sess); + } +} + /** * isert_put_unsol_pending_cmds() - Drop commands waiting for * unsolicitate dataout @@ -3350,6 +3361,7 @@ static void isert_wait_conn(struct iscsi_conn *conn) isert_wait4flush(isert_conn); isert_put_unsol_pending_cmds(conn); + isert_wait4cmds(conn); isert_wait4logout(isert_conn); queue_work(isert_release_wq, &isert_conn->release_work); diff --git a/drivers/input/touchscreen/edt-ft5x06.c b/drivers/input/touchscreen/edt-ft5x06.c index 0b0f8c17f3f7..a9d97d577a7e 100644 --- a/drivers/input/touchscreen/edt-ft5x06.c +++ b/drivers/input/touchscreen/edt-ft5x06.c @@ -880,6 +880,7 @@ static int edt_ft5x06_ts_probe(struct i2c_client *client, { const struct edt_i2c_chip_data *chip_data; struct edt_ft5x06_ts_data *tsdata; + u8 buf[2] = { 0xfc, 0x00 }; struct input_dev *input; unsigned long irq_flags; int error; @@ -949,6 +950,12 @@ static int edt_ft5x06_ts_probe(struct i2c_client *client, return error; } + /* + * Dummy read access. EP0700MLP1 returns bogus data on the first + * register read access and ignores writes. + */ + edt_ft5x06_ts_readwrite(tsdata->client, 2, buf, 2, buf); + edt_ft5x06_ts_set_regs(tsdata); edt_ft5x06_ts_get_defaults(&client->dev, tsdata); edt_ft5x06_ts_get_parameters(tsdata); diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index eb9937225d64..6c10f307a1c9 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -1090,7 +1090,8 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid, } arm_smmu_sync_ste_for_sid(smmu, sid); - dst[0] = cpu_to_le64(val); + /* See comment in arm_smmu_write_ctx_desc() */ + WRITE_ONCE(dst[0], cpu_to_le64(val)); arm_smmu_sync_ste_for_sid(smmu, sid); /* It's likely that we'll want to use the new STE soon */ diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c index cbad1926cec1..00169c9eb3ee 100644 --- a/drivers/iommu/dmar.c +++ b/drivers/iommu/dmar.c @@ -39,6 +39,7 @@ #include <linux/dmi.h> #include <linux/slab.h> #include <linux/iommu.h> +#include <linux/limits.h> #include <asm/irq_remapping.h> #include <asm/iommu_table.h> @@ -138,6 +139,13 @@ dmar_alloc_pci_notify_info(struct pci_dev *dev, unsigned long event) BUG_ON(dev->is_virtfn); + /* + * Ignore devices that have a domain number higher than what can + * be looked up in DMAR, e.g. VMD subdevices with domain 0x10000 + */ + if (pci_domain_nr(dev->bus) > U16_MAX) + return NULL; + /* Only generate path[] for device addition event */ if (event == BUS_NOTIFY_ADD_DEVICE) for (tmp = dev; tmp; tmp = tmp->bus->self) @@ -438,12 +446,13 @@ static int __init dmar_parse_one_andd(struct acpi_dmar_header *header, /* Check for NUL termination within the designated length */ if (strnlen(andd->device_name, header->length - 8) == header->length - 8) { - WARN_TAINT(1, TAINT_FIRMWARE_WORKAROUND, + pr_warn(FW_BUG "Your BIOS is broken; ANDD object name is not NUL-terminated\n" "BIOS vendor: %s; Ver: %s; Product Version: %s\n", dmi_get_system_info(DMI_BIOS_VENDOR), dmi_get_system_info(DMI_BIOS_VERSION), dmi_get_system_info(DMI_PRODUCT_VERSION)); + add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK); return -EINVAL; } pr_info("ANDD device: %x name: %s\n", andd->device_number, @@ -469,14 +478,14 @@ static int dmar_parse_one_rhsa(struct acpi_dmar_header *header, void *arg) return 0; } } - WARN_TAINT( - 1, TAINT_FIRMWARE_WORKAROUND, + pr_warn(FW_BUG "Your BIOS is broken; RHSA refers to non-existent DMAR unit at %llx\n" "BIOS vendor: %s; Ver: %s; Product Version: %s\n", - drhd->reg_base_addr, + rhsa->base_address, dmi_get_system_info(DMI_BIOS_VENDOR), dmi_get_system_info(DMI_BIOS_VERSION), dmi_get_system_info(DMI_PRODUCT_VERSION)); + add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK); return 0; } @@ -822,14 +831,14 @@ int __init dmar_table_init(void) static void warn_invalid_dmar(u64 addr, const char *message) { - WARN_TAINT_ONCE( - 1, TAINT_FIRMWARE_WORKAROUND, + pr_warn_once(FW_BUG "Your BIOS is broken; DMAR reported at address %llx%s!\n" "BIOS vendor: %s; Ver: %s; Product Version: %s\n", addr, message, dmi_get_system_info(DMI_BIOS_VENDOR), dmi_get_system_info(DMI_BIOS_VERSION), dmi_get_system_info(DMI_PRODUCT_VERSION)); + add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK); } static int __ref diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index a2005b82ec8f..ed6cb3abf645 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -3949,10 +3949,11 @@ static void quirk_ioat_snb_local_iommu(struct pci_dev *pdev) /* we know that the this iommu should be at offset 0xa000 from vtbar */ drhd = dmar_find_matched_drhd_unit(pdev); - if (WARN_TAINT_ONCE(!drhd || drhd->reg_base_addr - vtbar != 0xa000, - TAINT_FIRMWARE_WORKAROUND, - "BIOS assigned incorrect VT-d unit for Intel(R) QuickData Technology device\n")) + if (!drhd || drhd->reg_base_addr - vtbar != 0xa000) { + pr_warn_once(FW_BUG "BIOS assigned incorrect VT-d unit for Intel(R) QuickData Technology device\n"); + add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK); pdev->dev.archdata.iommu = DUMMY_DEVICE_DOMAIN_INFO; + } } DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB, quirk_ioat_snb_local_iommu); @@ -5016,8 +5017,10 @@ static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain, u64 phys = 0; pte = pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, &level); - if (pte) - phys = dma_pte_addr(pte); + if (pte && dma_pte_present(pte)) + phys = dma_pte_addr(pte) + + (iova & (BIT_MASK(level_to_offset_bits(level) + + VTD_PAGE_SHIFT) - 1)); return phys; } diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index cf11d43ce241..d4ae43f71e72 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -352,7 +352,7 @@ static struct its_collection *its_build_invall_cmd(struct its_cmd_block *cmd, struct its_cmd_desc *desc) { its_encode_cmd(cmd, GITS_CMD_INVALL); - its_encode_collection(cmd, desc->its_mapc_cmd.col->col_id); + its_encode_collection(cmd, desc->its_invall_cmd.col->col_id); its_fixup_cmd(cmd); diff --git a/drivers/md/bcache/bset.h b/drivers/md/bcache/bset.h index b935839ab79c..f483041eed98 100644 --- a/drivers/md/bcache/bset.h +++ b/drivers/md/bcache/bset.h @@ -380,7 +380,8 @@ void bch_btree_keys_stats(struct btree_keys *, struct bset_stats *); /* Bkey utility code */ -#define bset_bkey_last(i) bkey_idx((struct bkey *) (i)->d, (i)->keys) +#define bset_bkey_last(i) bkey_idx((struct bkey *) (i)->d, \ + (unsigned int)(i)->keys) static inline struct bkey *bset_bkey_idx(struct bset *i, unsigned idx) { diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 531d6f3a786e..c95139fea15c 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -2193,8 +2193,8 @@ static void wait_for_migrations(struct cache *cache) static void stop_worker(struct cache *cache) { - cancel_delayed_work(&cache->waker); - flush_workqueue(cache->wq); + cancel_delayed_work_sync(&cache->waker); + drain_workqueue(cache->wq); } static void requeue_deferred_cells(struct cache *cache) diff --git a/drivers/media/i2c/mt9v032.c b/drivers/media/i2c/mt9v032.c index a68ce94ee097..cacdab30fece 100644 --- a/drivers/media/i2c/mt9v032.c +++ b/drivers/media/i2c/mt9v032.c @@ -454,10 +454,12 @@ static int mt9v032_enum_mbus_code(struct v4l2_subdev *subdev, struct v4l2_subdev_pad_config *cfg, struct v4l2_subdev_mbus_code_enum *code) { + struct mt9v032 *mt9v032 = to_mt9v032(subdev); + if (code->index > 0) return -EINVAL; - code->code = MEDIA_BUS_FMT_SGRBG10_1X10; + code->code = mt9v032->format.code; return 0; } @@ -465,7 +467,11 @@ static int mt9v032_enum_frame_size(struct v4l2_subdev *subdev, struct v4l2_subdev_pad_config *cfg, struct v4l2_subdev_frame_size_enum *fse) { - if (fse->index >= 3 || fse->code != MEDIA_BUS_FMT_SGRBG10_1X10) + struct mt9v032 *mt9v032 = to_mt9v032(subdev); + + if (fse->index >= 3) + return -EINVAL; + if (mt9v032->format.code != fse->code) return -EINVAL; fse->min_width = MT9V032_WINDOW_WIDTH_DEF / (1 << fse->index); diff --git a/drivers/media/platform/sti/bdisp/bdisp-hw.c b/drivers/media/platform/sti/bdisp/bdisp-hw.c index 052c932ac942..0792db43ce9d 100644 --- a/drivers/media/platform/sti/bdisp/bdisp-hw.c +++ b/drivers/media/platform/sti/bdisp/bdisp-hw.c @@ -14,8 +14,8 @@ #define MAX_SRC_WIDTH 2048 /* Reset & boot poll config */ -#define POLL_RST_MAX 50 -#define POLL_RST_DELAY_MS 20 +#define POLL_RST_MAX 500 +#define POLL_RST_DELAY_MS 2 enum bdisp_target_plan { BDISP_RGB, @@ -77,7 +77,7 @@ int bdisp_hw_reset(struct bdisp_dev *bdisp) for (i = 0; i < POLL_RST_MAX; i++) { if (readl(bdisp->regs + BLT_STA1) & BLT_STA1_IDLE) break; - msleep(POLL_RST_DELAY_MS); + udelay(POLL_RST_DELAY_MS * 1000); } if (i == POLL_RST_MAX) dev_err(bdisp->dev, "Reset timeout\n"); diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index 0615522933dc..41bd9186d383 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -74,11 +74,6 @@ struct arp_pkt { }; #pragma pack() -static inline struct arp_pkt *arp_pkt(const struct sk_buff *skb) -{ - return (struct arp_pkt *)skb_network_header(skb); -} - /* Forward declaration */ static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[], bool strict_match); @@ -577,10 +572,11 @@ static void rlb_req_update_subnet_clients(struct bonding *bond, __be32 src_ip) spin_unlock(&bond->mode_lock); } -static struct slave *rlb_choose_channel(struct sk_buff *skb, struct bonding *bond) +static struct slave *rlb_choose_channel(struct sk_buff *skb, + struct bonding *bond, + const struct arp_pkt *arp) { struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); - struct arp_pkt *arp = arp_pkt(skb); struct slave *assigned_slave, *curr_active_slave; struct rlb_client_info *client_info; u32 hash_index = 0; @@ -677,8 +673,12 @@ static struct slave *rlb_choose_channel(struct sk_buff *skb, struct bonding *bon */ static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond) { - struct arp_pkt *arp = arp_pkt(skb); struct slave *tx_slave = NULL; + struct arp_pkt *arp; + + if (!pskb_network_may_pull(skb, sizeof(*arp))) + return NULL; + arp = (struct arp_pkt *)skb_network_header(skb); /* Don't modify or load balance ARPs that do not originate locally * (e.g.,arrive via a bridge). @@ -688,7 +688,7 @@ static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond) if (arp->op_code == htons(ARPOP_REPLY)) { /* the arp must be sent on the selected rx channel */ - tx_slave = rlb_choose_channel(skb, bond); + tx_slave = rlb_choose_channel(skb, bond, arp); if (tx_slave) ether_addr_copy(arp->mac_src, tx_slave->dev->dev_addr); netdev_dbg(bond->dev, "Server sent ARP Reply packet\n"); @@ -698,7 +698,7 @@ static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond) * When the arp reply is received the entry will be updated * with the correct unicast address of the client. */ - rlb_choose_channel(skb, bond); + rlb_choose_channel(skb, bond, arp); /* The ARP reply packets must be delayed so that * they can cancel out the influence of the ARP request. diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 81282b811a6c..d91953eabfeb 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -5310,13 +5310,13 @@ static int bnxt_change_mtu(struct net_device *dev, int new_mtu) return -EINVAL; if (netif_running(dev)) - bnxt_close_nic(bp, false, false); + bnxt_close_nic(bp, true, false); dev->mtu = new_mtu; bnxt_set_ring_params(bp); if (netif_running(dev)) - return bnxt_open_nic(bp, false, false); + return bnxt_open_nic(bp, true, false); return 0; } diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c index 3c20d0dc9256..9b9793333816 100644 --- a/drivers/net/ethernet/cisco/enic/enic_main.c +++ b/drivers/net/ethernet/cisco/enic/enic_main.c @@ -1807,10 +1807,10 @@ static int enic_stop(struct net_device *netdev) } netif_carrier_off(netdev); - netif_tx_disable(netdev); if (vnic_dev_get_intr_mode(enic->vdev) == VNIC_DEV_INTR_MODE_MSIX) for (i = 0; i < enic->wq_count; i++) napi_disable(&enic->napi[enic_cq_wq(enic, i)]); + netif_tx_disable(netdev); if (!enic_is_dynamic(enic) && !enic_is_sriov_vf(enic)) enic_dev_del_station_addr(enic); diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 53f3390043f2..1d2707525ee9 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -2521,15 +2521,15 @@ fec_enet_set_coalesce(struct net_device *ndev, struct ethtool_coalesce *ec) return -EINVAL; } - cycle = fec_enet_us_to_itr_clock(ndev, fep->rx_time_itr); + cycle = fec_enet_us_to_itr_clock(ndev, ec->rx_coalesce_usecs); if (cycle > 0xFFFF) { pr_err("Rx coalesed usec exceeed hardware limiation"); return -EINVAL; } - cycle = fec_enet_us_to_itr_clock(ndev, fep->tx_time_itr); + cycle = fec_enet_us_to_itr_clock(ndev, ec->tx_coalesce_usecs); if (cycle > 0xFFFF) { - pr_err("Rx coalesed usec exceeed hardware limiation"); + pr_err("Tx coalesed usec exceeed hardware limiation"); return -EINVAL; } diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index 2d61369f586f..37cc1f838dd8 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -2679,13 +2679,17 @@ static void gfar_clean_tx_ring(struct gfar_priv_tx_q *tx_queue) skb_dirtytx = tx_queue->skb_dirtytx; while ((skb = tx_queue->tx_skbuff[skb_dirtytx])) { + bool do_tstamp; + + do_tstamp = (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && + priv->hwts_tx_en; frags = skb_shinfo(skb)->nr_frags; /* When time stamping, one additional TxBD must be freed. * Also, we need to dma_unmap_single() the TxPAL. */ - if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS)) + if (unlikely(do_tstamp)) nr_txbds = frags + 2; else nr_txbds = frags + 1; @@ -2699,7 +2703,7 @@ static void gfar_clean_tx_ring(struct gfar_priv_tx_q *tx_queue) (lstatus & BD_LENGTH_MASK)) break; - if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS)) { + if (unlikely(do_tstamp)) { next = next_txbd(bdp, base, tx_ring_size); buflen = be16_to_cpu(next->length) + GMAC_FCB_LEN + GMAC_TXPAL_LEN; @@ -2709,7 +2713,7 @@ static void gfar_clean_tx_ring(struct gfar_priv_tx_q *tx_queue) dma_unmap_single(priv->dev, be32_to_cpu(bdp->bufPtr), buflen, DMA_TO_DEVICE); - if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS)) { + if (unlikely(do_tstamp)) { struct skb_shared_hwtstamps shhwtstamps; u64 *ns = (u64 *)(((uintptr_t)skb->data + 0x10) & ~0x7UL); diff --git a/drivers/net/ethernet/micrel/ks8851_mll.c b/drivers/net/ethernet/micrel/ks8851_mll.c index 8dc1f0277117..d4747caf1e7c 100644 --- a/drivers/net/ethernet/micrel/ks8851_mll.c +++ b/drivers/net/ethernet/micrel/ks8851_mll.c @@ -475,24 +475,6 @@ static int msg_enable; */ /** - * ks_rdreg8 - read 8 bit register from device - * @ks : The chip information - * @offset: The register address - * - * Read a 8bit register from the chip, returning the result - */ -static u8 ks_rdreg8(struct ks_net *ks, int offset) -{ - u16 data; - u8 shift_bit = offset & 0x03; - u8 shift_data = (offset & 1) << 3; - ks->cmd_reg_cache = (u16) offset | (u16)(BE0 << shift_bit); - iowrite16(ks->cmd_reg_cache, ks->hw_addr_cmd); - data = ioread16(ks->hw_addr); - return (u8)(data >> shift_data); -} - -/** * ks_rdreg16 - read 16 bit register from device * @ks : The chip information * @offset: The register address @@ -502,28 +484,12 @@ static u8 ks_rdreg8(struct ks_net *ks, int offset) static u16 ks_rdreg16(struct ks_net *ks, int offset) { - ks->cmd_reg_cache = (u16)offset | ((BE1 | BE0) << (offset & 0x02)); + ks->cmd_reg_cache = (u16)offset | ((BE3 | BE2) >> (offset & 0x02)); iowrite16(ks->cmd_reg_cache, ks->hw_addr_cmd); return ioread16(ks->hw_addr); } /** - * ks_wrreg8 - write 8bit register value to chip - * @ks: The chip information - * @offset: The register address - * @value: The value to write - * - */ -static void ks_wrreg8(struct ks_net *ks, int offset, u8 value) -{ - u8 shift_bit = (offset & 0x03); - u16 value_write = (u16)(value << ((offset & 1) << 3)); - ks->cmd_reg_cache = (u16)offset | (BE0 << shift_bit); - iowrite16(ks->cmd_reg_cache, ks->hw_addr_cmd); - iowrite16(value_write, ks->hw_addr); -} - -/** * ks_wrreg16 - write 16bit register value to chip * @ks: The chip information * @offset: The register address @@ -533,7 +499,7 @@ static void ks_wrreg8(struct ks_net *ks, int offset, u8 value) static void ks_wrreg16(struct ks_net *ks, int offset, u16 value) { - ks->cmd_reg_cache = (u16)offset | ((BE1 | BE0) << (offset & 0x02)); + ks->cmd_reg_cache = (u16)offset | ((BE3 | BE2) >> (offset & 0x02)); iowrite16(ks->cmd_reg_cache, ks->hw_addr_cmd); iowrite16(value, ks->hw_addr); } @@ -549,7 +515,7 @@ static inline void ks_inblk(struct ks_net *ks, u16 *wptr, u32 len) { len >>= 1; while (len--) - *wptr++ = (u16)ioread16(ks->hw_addr); + *wptr++ = be16_to_cpu(ioread16(ks->hw_addr)); } /** @@ -563,7 +529,7 @@ static inline void ks_outblk(struct ks_net *ks, u16 *wptr, u32 len) { len >>= 1; while (len--) - iowrite16(*wptr++, ks->hw_addr); + iowrite16(cpu_to_be16(*wptr++), ks->hw_addr); } static void ks_disable_int(struct ks_net *ks) @@ -642,8 +608,7 @@ static void ks_read_config(struct ks_net *ks) u16 reg_data = 0; /* Regardless of bus width, 8 bit read should always work.*/ - reg_data = ks_rdreg8(ks, KS_CCR) & 0x00FF; - reg_data |= ks_rdreg8(ks, KS_CCR+1) << 8; + reg_data = ks_rdreg16(ks, KS_CCR); /* addr/data bus are multiplexed */ ks->sharedbus = (reg_data & CCR_SHARED) == CCR_SHARED; @@ -747,7 +712,7 @@ static inline void ks_read_qmu(struct ks_net *ks, u16 *buf, u32 len) /* 1. set sudo DMA mode */ ks_wrreg16(ks, KS_RXFDPR, RXFDPR_RXFPAI); - ks_wrreg8(ks, KS_RXQCR, (ks->rc_rxqcr | RXQCR_SDA) & 0xff); + ks_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr | RXQCR_SDA); /* 2. read prepend data */ /** @@ -764,7 +729,7 @@ static inline void ks_read_qmu(struct ks_net *ks, u16 *buf, u32 len) ks_inblk(ks, buf, ALIGN(len, 4)); /* 4. reset sudo DMA Mode */ - ks_wrreg8(ks, KS_RXQCR, ks->rc_rxqcr); + ks_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr); } /** @@ -866,14 +831,17 @@ static irqreturn_t ks_irq(int irq, void *pw) { struct net_device *netdev = pw; struct ks_net *ks = netdev_priv(netdev); + unsigned long flags; u16 status; + spin_lock_irqsave(&ks->statelock, flags); /*this should be the first in IRQ handler */ ks_save_cmd_reg(ks); status = ks_rdreg16(ks, KS_ISR); if (unlikely(!status)) { ks_restore_cmd_reg(ks); + spin_unlock_irqrestore(&ks->statelock, flags); return IRQ_NONE; } @@ -899,6 +867,7 @@ static irqreturn_t ks_irq(int irq, void *pw) ks->netdev->stats.rx_over_errors++; /* this should be the last in IRQ handler*/ ks_restore_cmd_reg(ks); + spin_unlock_irqrestore(&ks->statelock, flags); return IRQ_HANDLED; } @@ -968,6 +937,7 @@ static int ks_net_stop(struct net_device *netdev) /* shutdown RX/TX QMU */ ks_disable_qmu(ks); + ks_disable_int(ks); /* set powermode to soft power down to save power */ ks_set_powermode(ks, PMECR_PM_SOFTDOWN); @@ -997,13 +967,13 @@ static void ks_write_qmu(struct ks_net *ks, u8 *pdata, u16 len) ks->txh.txw[1] = cpu_to_le16(len); /* 1. set sudo-DMA mode */ - ks_wrreg8(ks, KS_RXQCR, (ks->rc_rxqcr | RXQCR_SDA) & 0xff); + ks_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr | RXQCR_SDA); /* 2. write status/lenth info */ ks_outblk(ks, ks->txh.txw, 4); /* 3. write pkt data */ ks_outblk(ks, (u16 *)pdata, ALIGN(len, 4)); /* 4. reset sudo-DMA mode */ - ks_wrreg8(ks, KS_RXQCR, ks->rc_rxqcr); + ks_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr); /* 5. Enqueue Tx(move the pkt from TX buffer into TXQ) */ ks_wrreg16(ks, KS_TXQCR, TXQCR_METFE); /* 6. wait until TXQCR_METFE is auto-cleared */ @@ -1024,10 +994,9 @@ static netdev_tx_t ks_start_xmit(struct sk_buff *skb, struct net_device *netdev) { netdev_tx_t retv = NETDEV_TX_OK; struct ks_net *ks = netdev_priv(netdev); + unsigned long flags; - disable_irq(netdev->irq); - ks_disable_int(ks); - spin_lock(&ks->statelock); + spin_lock_irqsave(&ks->statelock, flags); /* Extra space are required: * 4 byte for alignment, 4 for status/length, 4 for CRC @@ -1041,9 +1010,7 @@ static netdev_tx_t ks_start_xmit(struct sk_buff *skb, struct net_device *netdev) dev_kfree_skb(skb); } else retv = NETDEV_TX_BUSY; - spin_unlock(&ks->statelock); - ks_enable_int(ks); - enable_irq(netdev->irq); + spin_unlock_irqrestore(&ks->statelock, flags); return retv; } diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index 142015af43db..835087597b82 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -251,6 +251,7 @@ acct: } else { kfree_skb(skb); } + cond_resched(); } } @@ -429,19 +430,21 @@ static int ipvlan_process_outbound(struct sk_buff *skb, struct ethhdr *ethh = eth_hdr(skb); int ret = NET_XMIT_DROP; - /* In this mode we dont care about multicast and broadcast traffic */ - if (is_multicast_ether_addr(ethh->h_dest)) { - pr_warn_ratelimited("Dropped {multi|broad}cast of type= [%x]\n", - ntohs(skb->protocol)); - kfree_skb(skb); - goto out; - } - /* The ipvlan is a pseudo-L2 device, so the packets that we receive * will have L2; which need to discarded and processed further * in the net-ns of the main-device. */ if (skb_mac_header_was_set(skb)) { + /* In this mode we dont care about + * multicast and broadcast traffic */ + if (is_multicast_ether_addr(ethh->h_dest)) { + pr_debug_ratelimited( + "Dropped {multi|broad}cast of type=[%x]\n", + ntohs(skb->protocol)); + kfree_skb(skb); + goto out; + } + skb_pull(skb, sizeof(*ethh)); skb->mac_header = (typeof(skb->mac_header))~0U; skb_reset_network_header(skb); diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index ae02ce17c505..b4d5f53c97d3 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -145,7 +145,6 @@ static void ipvlan_uninit(struct net_device *dev) static int ipvlan_open(struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); - struct net_device *phy_dev = ipvlan->phy_dev; struct ipvl_addr *addr; if (ipvlan->port->mode == IPVLAN_MODE_L3) @@ -156,7 +155,7 @@ static int ipvlan_open(struct net_device *dev) list_for_each_entry(addr, &ipvlan->addrs, anode) ipvlan_ht_addr_add(ipvlan, addr); - return dev_uc_add(phy_dev, phy_dev->dev_addr); + return 0; } static int ipvlan_stop(struct net_device *dev) @@ -168,8 +167,6 @@ static int ipvlan_stop(struct net_device *dev) dev_uc_unsync(phy_dev, dev); dev_mc_unsync(phy_dev, dev); - dev_uc_del(phy_dev, phy_dev->dev_addr); - list_for_each_entry(addr, &ipvlan->addrs, anode) ipvlan_ht_addr_del(addr); diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index bd49303f7db2..84767722065a 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -306,6 +306,8 @@ static void macvlan_process_broadcast(struct work_struct *w) rcu_read_unlock(); kfree_skb(skb); + + cond_resched(); } } diff --git a/drivers/net/phy/mdio-bcm-iproc.c b/drivers/net/phy/mdio-bcm-iproc.c index 46fe1ae919a3..51ce3ea17fb3 100644 --- a/drivers/net/phy/mdio-bcm-iproc.c +++ b/drivers/net/phy/mdio-bcm-iproc.c @@ -188,6 +188,23 @@ static int iproc_mdio_remove(struct platform_device *pdev) return 0; } +#ifdef CONFIG_PM_SLEEP +int iproc_mdio_resume(struct device *dev) +{ + struct platform_device *pdev = to_platform_device(dev); + struct iproc_mdio_priv *priv = platform_get_drvdata(pdev); + + /* restore the mii clock configuration */ + iproc_mdio_config_clk(priv->base); + + return 0; +} + +static const struct dev_pm_ops iproc_mdio_pm_ops = { + .resume = iproc_mdio_resume +}; +#endif /* CONFIG_PM_SLEEP */ + static const struct of_device_id iproc_mdio_of_match[] = { { .compatible = "brcm,iproc-mdio", }, { /* sentinel */ }, @@ -198,6 +215,9 @@ static struct platform_driver iproc_mdio_driver = { .driver = { .name = "iproc-mdio", .of_match_table = iproc_mdio_of_match, +#ifdef CONFIG_PM_SLEEP + .pm = &iproc_mdio_pm_ops, +#endif }, .probe = iproc_mdio_probe, .remove = iproc_mdio_remove, diff --git a/drivers/net/slip/slhc.c b/drivers/net/slip/slhc.c index ddceed3c5a4a..a516470da015 100644 --- a/drivers/net/slip/slhc.c +++ b/drivers/net/slip/slhc.c @@ -232,7 +232,7 @@ slhc_compress(struct slcompress *comp, unsigned char *icp, int isize, register struct cstate *cs = lcs->next; register unsigned long deltaS, deltaA; register short changes = 0; - int hlen; + int nlen, hlen; unsigned char new_seq[16]; register unsigned char *cp = new_seq; struct iphdr *ip; @@ -248,6 +248,8 @@ slhc_compress(struct slcompress *comp, unsigned char *icp, int isize, return isize; ip = (struct iphdr *) icp; + if (ip->version != 4 || ip->ihl < 5) + return isize; /* Bail if this packet isn't TCP, or is an IP fragment */ if (ip->protocol != IPPROTO_TCP || (ntohs(ip->frag_off) & 0x3fff)) { @@ -258,10 +260,14 @@ slhc_compress(struct slcompress *comp, unsigned char *icp, int isize, comp->sls_o_tcp++; return isize; } - /* Extract TCP header */ + nlen = ip->ihl * 4; + if (isize < nlen + sizeof(*th)) + return isize; - th = (struct tcphdr *)(((unsigned char *)ip) + ip->ihl*4); - hlen = ip->ihl*4 + th->doff*4; + th = (struct tcphdr *)(icp + nlen); + if (th->doff < sizeof(struct tcphdr) / 4) + return isize; + hlen = nlen + th->doff * 4; /* Bail if the TCP packet isn't `compressible' (i.e., ACK isn't set or * some other control bit is set). Also uncompressible if diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c index 0f8d5609ed51..d4a33baa33b6 100644 --- a/drivers/net/slip/slip.c +++ b/drivers/net/slip/slip.c @@ -868,7 +868,6 @@ err_free_chan: tty->disc_data = NULL; clear_bit(SLF_INUSE, &sl->flags); sl_free_netdev(sl->dev); - free_netdev(sl->dev); err_exit: rtnl_unlock(); diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 285d376f53ef..e51fb7cb7728 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -2169,6 +2169,8 @@ team_nl_option_policy[TEAM_ATTR_OPTION_MAX + 1] = { [TEAM_ATTR_OPTION_CHANGED] = { .type = NLA_FLAG }, [TEAM_ATTR_OPTION_TYPE] = { .type = NLA_U8 }, [TEAM_ATTR_OPTION_DATA] = { .type = NLA_BINARY }, + [TEAM_ATTR_OPTION_PORT_IFINDEX] = { .type = NLA_U32 }, + [TEAM_ATTR_OPTION_ARRAY_INDEX] = { .type = NLA_U32 }, }; static int team_nl_cmd_noop(struct sk_buff *skb, struct genl_info *info) diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 23e299c86b81..27e9c089b2fc 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -3328,14 +3328,20 @@ static void r8153_init(struct r8152 *tp) if (ocp_read_word(tp, MCU_TYPE_PLA, PLA_BOOT_CTRL) & AUTOLOAD_DONE) break; + msleep(20); + if (test_bit(RTL8152_UNPLUG, &tp->flags)) + break; } for (i = 0; i < 500; i++) { ocp_data = ocp_reg_read(tp, OCP_PHY_STATUS) & PHY_STAT_MASK; if (ocp_data == PHY_STAT_LAN_ON || ocp_data == PHY_STAT_PWRDN) break; + msleep(20); + if (test_bit(RTL8152_UNPLUG, &tp->flags)) + break; } usb_disable_lpm(tp->udev); diff --git a/drivers/net/wan/ixp4xx_hss.c b/drivers/net/wan/ixp4xx_hss.c index e7bbdb7af53a..97968e6a6a4e 100644 --- a/drivers/net/wan/ixp4xx_hss.c +++ b/drivers/net/wan/ixp4xx_hss.c @@ -261,7 +261,7 @@ struct port { struct hss_plat_info *plat; buffer_t *rx_buff_tab[RX_DESCS], *tx_buff_tab[TX_DESCS]; struct desc *desc_tab; /* coherent */ - u32 desc_tab_phys; + dma_addr_t desc_tab_phys; unsigned int id; unsigned int clock_type, clock_rate, loopback; unsigned int initialized, carrier; @@ -861,7 +861,7 @@ static int hss_hdlc_xmit(struct sk_buff *skb, struct net_device *dev) dev->stats.tx_dropped++; return NETDEV_TX_OK; } - memcpy_swab32(mem, (u32 *)((int)skb->data & ~3), bytes / 4); + memcpy_swab32(mem, (u32 *)((uintptr_t)skb->data & ~3), bytes / 4); dev_kfree_skb(skb); #endif diff --git a/drivers/net/wireless/b43legacy/main.c b/drivers/net/wireless/b43legacy/main.c index afc1fb3e38df..bd35a702382f 100644 --- a/drivers/net/wireless/b43legacy/main.c +++ b/drivers/net/wireless/b43legacy/main.c @@ -1304,8 +1304,9 @@ static void handle_irq_ucode_debug(struct b43legacy_wldev *dev) } /* Interrupt handler bottom-half */ -static void b43legacy_interrupt_tasklet(struct b43legacy_wldev *dev) +static void b43legacy_interrupt_tasklet(unsigned long data) { + struct b43legacy_wldev *dev = (struct b43legacy_wldev *)data; u32 reason; u32 dma_reason[ARRAY_SIZE(dev->dma_reason)]; u32 merged_dma_reason = 0; @@ -3775,7 +3776,7 @@ static int b43legacy_one_core_attach(struct ssb_device *dev, b43legacy_set_status(wldev, B43legacy_STAT_UNINIT); wldev->bad_frames_preempt = modparam_bad_frames_preempt; tasklet_init(&wldev->isr_tasklet, - (void (*)(unsigned long))b43legacy_interrupt_tasklet, + b43legacy_interrupt_tasklet, (unsigned long)wldev); if (modparam_pio) wldev->__using_pio = true; diff --git a/drivers/net/wireless/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/brcm80211/brcmfmac/sdio.c index 9954e641c943..8bb028f740fd 100644 --- a/drivers/net/wireless/brcm80211/brcmfmac/sdio.c +++ b/drivers/net/wireless/brcm80211/brcmfmac/sdio.c @@ -2027,6 +2027,7 @@ static uint brcmf_sdio_readframes(struct brcmf_sdio *bus, uint maxframes) BRCMF_SDIO_FT_NORMAL)) { rd->len = 0; brcmu_pkt_buf_free_skb(pkt); + continue; } bus->sdcnt.rx_readahead_cnt++; if (rd->len != roundup(rd_new.len, 16)) { diff --git a/drivers/net/wireless/hostap/hostap_ap.c b/drivers/net/wireless/hostap/hostap_ap.c index c995ace153ee..30171d4c4718 100644 --- a/drivers/net/wireless/hostap/hostap_ap.c +++ b/drivers/net/wireless/hostap/hostap_ap.c @@ -2570,7 +2570,7 @@ static int prism2_hostapd_add_sta(struct ap_data *ap, sta->supported_rates[0] = 2; if (sta->tx_supp_rates & WLAN_RATE_2M) sta->supported_rates[1] = 4; - if (sta->tx_supp_rates & WLAN_RATE_5M5) + if (sta->tx_supp_rates & WLAN_RATE_5M5) sta->supported_rates[2] = 11; if (sta->tx_supp_rates & WLAN_RATE_11M) sta->supported_rates[3] = 22; diff --git a/drivers/net/wireless/ipw2x00/ipw2100.c b/drivers/net/wireless/ipw2x00/ipw2100.c index 36818c7f30b9..11cfc5822eb0 100644 --- a/drivers/net/wireless/ipw2x00/ipw2100.c +++ b/drivers/net/wireless/ipw2x00/ipw2100.c @@ -3213,8 +3213,9 @@ static void ipw2100_tx_send_data(struct ipw2100_priv *priv) } } -static void ipw2100_irq_tasklet(struct ipw2100_priv *priv) +static void ipw2100_irq_tasklet(unsigned long data) { + struct ipw2100_priv *priv = (struct ipw2100_priv *)data; struct net_device *dev = priv->net_dev; unsigned long flags; u32 inta, tmp; @@ -6022,7 +6023,7 @@ static void ipw2100_rf_kill(struct work_struct *work) spin_unlock_irqrestore(&priv->low_lock, flags); } -static void ipw2100_irq_tasklet(struct ipw2100_priv *priv); +static void ipw2100_irq_tasklet(unsigned long data); static const struct net_device_ops ipw2100_netdev_ops = { .ndo_open = ipw2100_open, @@ -6151,7 +6152,7 @@ static struct net_device *ipw2100_alloc_device(struct pci_dev *pci_dev, INIT_DELAYED_WORK(&priv->rf_kill, ipw2100_rf_kill); INIT_DELAYED_WORK(&priv->scan_event, ipw2100_scan_event); - tasklet_init(&priv->irq_tasklet, (void (*)(unsigned long)) + tasklet_init(&priv->irq_tasklet, ipw2100_irq_tasklet, (unsigned long)priv); /* NOTE: We do not start the deferred work for status checks yet */ diff --git a/drivers/net/wireless/ipw2x00/ipw2200.c b/drivers/net/wireless/ipw2x00/ipw2200.c index ed0adaf1eec4..1e08f94dc4da 100644 --- a/drivers/net/wireless/ipw2x00/ipw2200.c +++ b/drivers/net/wireless/ipw2x00/ipw2200.c @@ -1968,8 +1968,9 @@ static void notify_wx_assoc_event(struct ipw_priv *priv) wireless_send_event(priv->net_dev, SIOCGIWAP, &wrqu, NULL); } -static void ipw_irq_tasklet(struct ipw_priv *priv) +static void ipw_irq_tasklet(unsigned long data) { + struct ipw_priv *priv = (struct ipw_priv *)data; u32 inta, inta_mask, handled = 0; unsigned long flags; int rc = 0; @@ -10705,7 +10706,7 @@ static int ipw_setup_deferred_work(struct ipw_priv *priv) INIT_WORK(&priv->qos_activate, ipw_bg_qos_activate); #endif /* CONFIG_IPW2200_QOS */ - tasklet_init(&priv->irq_tasklet, (void (*)(unsigned long)) + tasklet_init(&priv->irq_tasklet, ipw_irq_tasklet, (unsigned long)priv); return ret; diff --git a/drivers/net/wireless/iwlegacy/3945-mac.c b/drivers/net/wireless/iwlegacy/3945-mac.c index af1b3e6839fa..775f5e7791d4 100644 --- a/drivers/net/wireless/iwlegacy/3945-mac.c +++ b/drivers/net/wireless/iwlegacy/3945-mac.c @@ -1399,8 +1399,9 @@ il3945_dump_nic_error_log(struct il_priv *il) } static void -il3945_irq_tasklet(struct il_priv *il) +il3945_irq_tasklet(unsigned long data) { + struct il_priv *il = (struct il_priv *)data; u32 inta, handled = 0; u32 inta_fh; unsigned long flags; @@ -3432,7 +3433,7 @@ il3945_setup_deferred_work(struct il_priv *il) setup_timer(&il->watchdog, il_bg_watchdog, (unsigned long)il); tasklet_init(&il->irq_tasklet, - (void (*)(unsigned long))il3945_irq_tasklet, + il3945_irq_tasklet, (unsigned long)il); } diff --git a/drivers/net/wireless/iwlegacy/4965-mac.c b/drivers/net/wireless/iwlegacy/4965-mac.c index 04b0349a6ad9..b1925bdb1171 100644 --- a/drivers/net/wireless/iwlegacy/4965-mac.c +++ b/drivers/net/wireless/iwlegacy/4965-mac.c @@ -4361,8 +4361,9 @@ il4965_synchronize_irq(struct il_priv *il) } static void -il4965_irq_tasklet(struct il_priv *il) +il4965_irq_tasklet(unsigned long data) { + struct il_priv *il = (struct il_priv *)data; u32 inta, handled = 0; u32 inta_fh; unsigned long flags; @@ -6257,7 +6258,7 @@ il4965_setup_deferred_work(struct il_priv *il) setup_timer(&il->watchdog, il_bg_watchdog, (unsigned long)il); tasklet_init(&il->irq_tasklet, - (void (*)(unsigned long))il4965_irq_tasklet, + il4965_irq_tasklet, (unsigned long)il); } diff --git a/drivers/net/wireless/iwlegacy/common.c b/drivers/net/wireless/iwlegacy/common.c index 887114582583..544ab3750ea6 100644 --- a/drivers/net/wireless/iwlegacy/common.c +++ b/drivers/net/wireless/iwlegacy/common.c @@ -717,7 +717,7 @@ il_eeprom_init(struct il_priv *il) u32 gp = _il_rd(il, CSR_EEPROM_GP); int sz; int ret; - u16 addr; + int addr; /* allocate eeprom */ sz = il->cfg->eeprom_size; diff --git a/drivers/net/wireless/iwlwifi/pcie/rx.c b/drivers/net/wireless/iwlwifi/pcie/rx.c index d6f9858ff2de..7fdb3ad9f53d 100644 --- a/drivers/net/wireless/iwlwifi/pcie/rx.c +++ b/drivers/net/wireless/iwlwifi/pcie/rx.c @@ -708,9 +708,13 @@ int iwl_pcie_rx_init(struct iwl_trans *trans) if (err) return err; } - if (!rba->alloc_wq) + if (!rba->alloc_wq) { rba->alloc_wq = alloc_workqueue("rb_allocator", WQ_HIGHPRI | WQ_UNBOUND, 1); + if (!rba->alloc_wq) + return -ENOMEM; + } + INIT_WORK(&rba->rx_alloc, iwl_pcie_rx_allocator_work); cancel_work_sync(&rba->rx_alloc); diff --git a/drivers/net/wireless/mwifiex/tdls.c b/drivers/net/wireless/mwifiex/tdls.c index 9275f9c3f869..14ce8ead5941 100644 --- a/drivers/net/wireless/mwifiex/tdls.c +++ b/drivers/net/wireless/mwifiex/tdls.c @@ -910,59 +910,117 @@ void mwifiex_process_tdls_action_frame(struct mwifiex_private *priv, switch (*pos) { case WLAN_EID_SUPP_RATES: + if (pos[1] > 32) + return; sta_ptr->tdls_cap.rates_len = pos[1]; for (i = 0; i < pos[1]; i++) sta_ptr->tdls_cap.rates[i] = pos[i + 2]; break; case WLAN_EID_EXT_SUPP_RATES: + if (pos[1] > 32) + return; basic = sta_ptr->tdls_cap.rates_len; + if (pos[1] > 32 - basic) + return; for (i = 0; i < pos[1]; i++) sta_ptr->tdls_cap.rates[basic + i] = pos[i + 2]; sta_ptr->tdls_cap.rates_len += pos[1]; break; case WLAN_EID_HT_CAPABILITY: - memcpy((u8 *)&sta_ptr->tdls_cap.ht_capb, pos, + if (pos > end - sizeof(struct ieee80211_ht_cap) - 2) + return; + if (pos[1] != sizeof(struct ieee80211_ht_cap)) + return; + /* copy the ie's value into ht_capb*/ + memcpy((u8 *)&sta_ptr->tdls_cap.ht_capb, pos + 2, sizeof(struct ieee80211_ht_cap)); sta_ptr->is_11n_enabled = 1; break; case WLAN_EID_HT_OPERATION: - memcpy(&sta_ptr->tdls_cap.ht_oper, pos, + if (pos > end - + sizeof(struct ieee80211_ht_operation) - 2) + return; + if (pos[1] != sizeof(struct ieee80211_ht_operation)) + return; + /* copy the ie's value into ht_oper*/ + memcpy(&sta_ptr->tdls_cap.ht_oper, pos + 2, sizeof(struct ieee80211_ht_operation)); break; case WLAN_EID_BSS_COEX_2040: + if (pos > end - 3) + return; + if (pos[1] != 1) + return; sta_ptr->tdls_cap.coex_2040 = pos[2]; break; case WLAN_EID_EXT_CAPABILITY: + if (pos > end - sizeof(struct ieee_types_header)) + return; + if (pos[1] < sizeof(struct ieee_types_header)) + return; + if (pos[1] > 8) + return; memcpy((u8 *)&sta_ptr->tdls_cap.extcap, pos, sizeof(struct ieee_types_header) + min_t(u8, pos[1], 8)); break; case WLAN_EID_RSN: + if (pos > end - sizeof(struct ieee_types_header)) + return; + if (pos[1] < sizeof(struct ieee_types_header)) + return; + if (pos[1] > IEEE_MAX_IE_SIZE - + sizeof(struct ieee_types_header)) + return; memcpy((u8 *)&sta_ptr->tdls_cap.rsn_ie, pos, sizeof(struct ieee_types_header) + min_t(u8, pos[1], IEEE_MAX_IE_SIZE - sizeof(struct ieee_types_header))); break; case WLAN_EID_QOS_CAPA: + if (pos > end - 3) + return; + if (pos[1] != 1) + return; sta_ptr->tdls_cap.qos_info = pos[2]; break; case WLAN_EID_VHT_OPERATION: - if (priv->adapter->is_hw_11ac_capable) - memcpy(&sta_ptr->tdls_cap.vhtoper, pos, + if (priv->adapter->is_hw_11ac_capable) { + if (pos > end - + sizeof(struct ieee80211_vht_operation) - 2) + return; + if (pos[1] != + sizeof(struct ieee80211_vht_operation)) + return; + /* copy the ie's value into vhtoper*/ + memcpy(&sta_ptr->tdls_cap.vhtoper, pos + 2, sizeof(struct ieee80211_vht_operation)); + } break; case WLAN_EID_VHT_CAPABILITY: if (priv->adapter->is_hw_11ac_capable) { - memcpy((u8 *)&sta_ptr->tdls_cap.vhtcap, pos, + if (pos > end - + sizeof(struct ieee80211_vht_cap) - 2) + return; + if (pos[1] != sizeof(struct ieee80211_vht_cap)) + return; + /* copy the ie's value into vhtcap*/ + memcpy((u8 *)&sta_ptr->tdls_cap.vhtcap, pos + 2, sizeof(struct ieee80211_vht_cap)); sta_ptr->is_11ac_enabled = 1; } break; case WLAN_EID_AID: - if (priv->adapter->is_hw_11ac_capable) + if (priv->adapter->is_hw_11ac_capable) { + if (pos > end - 4) + return; + if (pos[1] != 2) + return; sta_ptr->tdls_cap.aid = le16_to_cpu(*(__le16 *)(pos + 2)); + } + break; default: break; } diff --git a/drivers/net/wireless/orinoco/orinoco_usb.c b/drivers/net/wireless/orinoco/orinoco_usb.c index e434f7ca8ff3..3c5baccd6792 100644 --- a/drivers/net/wireless/orinoco/orinoco_usb.c +++ b/drivers/net/wireless/orinoco/orinoco_usb.c @@ -1351,7 +1351,8 @@ static int ezusb_init(struct hermes *hw) int retval; BUG_ON(in_interrupt()); - BUG_ON(!upriv); + if (!upriv) + return -EINVAL; upriv->reply_count = 0; /* Write the MAGIC number on the simulated registers to keep diff --git a/drivers/net/wireless/realtek/rtlwifi/pci.c b/drivers/net/wireless/realtek/rtlwifi/pci.c index b51815eccdb3..17a07d6b961c 100644 --- a/drivers/net/wireless/realtek/rtlwifi/pci.c +++ b/drivers/net/wireless/realtek/rtlwifi/pci.c @@ -1096,13 +1096,15 @@ done: return ret; } -static void _rtl_pci_irq_tasklet(struct ieee80211_hw *hw) +static void _rtl_pci_irq_tasklet(unsigned long data) { + struct ieee80211_hw *hw = (struct ieee80211_hw *)data; _rtl_pci_tx_chk_waitq(hw); } -static void _rtl_pci_prepare_bcn_tasklet(struct ieee80211_hw *hw) +static void _rtl_pci_prepare_bcn_tasklet(unsigned long data) { + struct ieee80211_hw *hw = (struct ieee80211_hw *)data; struct rtl_priv *rtlpriv = rtl_priv(hw); struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw)); struct rtl_mac *mac = rtl_mac(rtl_priv(hw)); @@ -1223,10 +1225,10 @@ static void _rtl_pci_init_struct(struct ieee80211_hw *hw, /*task */ tasklet_init(&rtlpriv->works.irq_tasklet, - (void (*)(unsigned long))_rtl_pci_irq_tasklet, + _rtl_pci_irq_tasklet, (unsigned long)hw); tasklet_init(&rtlpriv->works.irq_prepare_bcn_tasklet, - (void (*)(unsigned long))_rtl_pci_prepare_bcn_tasklet, + _rtl_pci_prepare_bcn_tasklet, (unsigned long)hw); INIT_WORK(&rtlpriv->works.lps_change_work, rtl_lps_change_work_callback); diff --git a/drivers/nfc/pn544/i2c.c b/drivers/nfc/pn544/i2c.c index fa75c53f3fa5..22522edb6341 100644 --- a/drivers/nfc/pn544/i2c.c +++ b/drivers/nfc/pn544/i2c.c @@ -241,6 +241,7 @@ static void pn544_hci_i2c_platform_init(struct pn544_i2c_phy *phy) out: gpio_set_value_cansleep(phy->gpio_en, !phy->en_polarity); + usleep_range(10000, 15000); } static void pn544_hci_i2c_enable_mode(struct pn544_i2c_phy *phy, int run_mode) diff --git a/drivers/nfc/port100.c b/drivers/nfc/port100.c index 87d509996704..3ffbed72adf7 100644 --- a/drivers/nfc/port100.c +++ b/drivers/nfc/port100.c @@ -545,7 +545,7 @@ static void port100_tx_update_payload_len(void *_frame, int len) { struct port100_frame *frame = _frame; - frame->datalen = cpu_to_le16(le16_to_cpu(frame->datalen) + len); + le16_add_cpu(&frame->datalen, len); } static bool port100_rx_frame_is_valid(void *_frame) diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c index 1723ac1b30e1..fe2865a0da39 100644 --- a/drivers/pci/setup-bus.c +++ b/drivers/pci/setup-bus.c @@ -1760,12 +1760,18 @@ again: /* restore size and flags */ list_for_each_entry(fail_res, &fail_head, list) { struct resource *res = fail_res->res; + int idx; res->start = fail_res->start; res->end = fail_res->end; res->flags = fail_res->flags; - if (fail_res->dev->subordinate) - res->flags = 0; + + if (pci_is_bridge(fail_res->dev)) { + idx = res - &fail_res->dev->resource[0]; + if (idx >= PCI_BRIDGE_RESOURCES && + idx <= PCI_BRIDGE_RESOURCE_END) + res->flags = 0; + } } free_list(&fail_head); @@ -1826,12 +1832,18 @@ again: /* restore size and flags */ list_for_each_entry(fail_res, &fail_head, list) { struct resource *res = fail_res->res; + int idx; res->start = fail_res->start; res->end = fail_res->end; res->flags = fail_res->flags; - if (fail_res->dev->subordinate) - res->flags = 0; + + if (pci_is_bridge(fail_res->dev)) { + idx = res - &fail_res->dev->resource[0]; + if (idx >= PCI_BRIDGE_RESOURCES && + idx <= PCI_BRIDGE_RESOURCE_END) + res->flags = 0; + } } free_list(&fail_head); diff --git a/drivers/pinctrl/sh-pfc/pfc-sh7264.c b/drivers/pinctrl/sh-pfc/pfc-sh7264.c index e1c34e19222e..3ddb9565ed80 100644 --- a/drivers/pinctrl/sh-pfc/pfc-sh7264.c +++ b/drivers/pinctrl/sh-pfc/pfc-sh7264.c @@ -500,17 +500,15 @@ enum { SD_WP_MARK, SD_CLK_MARK, SD_CMD_MARK, CRX0_MARK, CRX1_MARK, CTX0_MARK, CTX1_MARK, + CRX0_CRX1_MARK, CTX0_CTX1_MARK, PWM1A_MARK, PWM1B_MARK, PWM1C_MARK, PWM1D_MARK, PWM1E_MARK, PWM1F_MARK, PWM1G_MARK, PWM1H_MARK, PWM2A_MARK, PWM2B_MARK, PWM2C_MARK, PWM2D_MARK, PWM2E_MARK, PWM2F_MARK, PWM2G_MARK, PWM2H_MARK, IERXD_MARK, IETXD_MARK, - CRX0_CRX1_MARK, WDTOVF_MARK, - CRX0X1_MARK, - /* DMAC */ TEND0_MARK, DACK0_MARK, DREQ0_MARK, TEND1_MARK, DACK1_MARK, DREQ1_MARK, @@ -998,12 +996,12 @@ static const u16 pinmux_data[] = { PINMUX_DATA(PJ3_DATA, PJ3MD_00), PINMUX_DATA(CRX1_MARK, PJ3MD_01), - PINMUX_DATA(CRX0X1_MARK, PJ3MD_10), + PINMUX_DATA(CRX0_CRX1_MARK, PJ3MD_10), PINMUX_DATA(IRQ1_PJ_MARK, PJ3MD_11), PINMUX_DATA(PJ2_DATA, PJ2MD_000), PINMUX_DATA(CTX1_MARK, PJ2MD_001), - PINMUX_DATA(CRX0_CRX1_MARK, PJ2MD_010), + PINMUX_DATA(CTX0_CTX1_MARK, PJ2MD_010), PINMUX_DATA(CS2_MARK, PJ2MD_011), PINMUX_DATA(SCK0_MARK, PJ2MD_100), PINMUX_DATA(LCD_M_DISP_MARK, PJ2MD_101), @@ -1248,6 +1246,7 @@ static const struct pinmux_func pinmux_func_gpios[] = { GPIO_FN(CTX1), GPIO_FN(CRX1), GPIO_FN(CTX0), + GPIO_FN(CTX0_CTX1), GPIO_FN(CRX0), GPIO_FN(CRX0_CRX1), diff --git a/drivers/pinctrl/sh-pfc/pfc-sh7269.c b/drivers/pinctrl/sh-pfc/pfc-sh7269.c index cfdb4fc177c3..3df0c0d139d0 100644 --- a/drivers/pinctrl/sh-pfc/pfc-sh7269.c +++ b/drivers/pinctrl/sh-pfc/pfc-sh7269.c @@ -740,13 +740,12 @@ enum { CRX0_MARK, CTX0_MARK, CRX1_MARK, CTX1_MARK, CRX2_MARK, CTX2_MARK, - CRX0_CRX1_MARK, - CRX0_CRX1_CRX2_MARK, - CTX0CTX1CTX2_MARK, + CRX0_CRX1_MARK, CTX0_CTX1_MARK, + CRX0_CRX1_CRX2_MARK, CTX0_CTX1_CTX2_MARK, CRX1_PJ22_MARK, CTX1_PJ23_MARK, CRX2_PJ20_MARK, CTX2_PJ21_MARK, - CRX0CRX1_PJ22_MARK, - CRX0CRX1CRX2_PJ20_MARK, + CRX0_CRX1_PJ22_MARK, CTX0_CTX1_PJ23_MARK, + CRX0_CRX1_CRX2_PJ20_MARK, CTX0_CTX1_CTX2_PJ21_MARK, /* VDC */ DV_CLK_MARK, @@ -824,6 +823,7 @@ static const u16 pinmux_data[] = { PINMUX_DATA(CS3_MARK, PC8MD_001), PINMUX_DATA(TXD7_MARK, PC8MD_010), PINMUX_DATA(CTX1_MARK, PC8MD_011), + PINMUX_DATA(CTX0_CTX1_MARK, PC8MD_100), PINMUX_DATA(PC7_DATA, PC7MD_000), PINMUX_DATA(CKE_MARK, PC7MD_001), @@ -836,11 +836,12 @@ static const u16 pinmux_data[] = { PINMUX_DATA(CAS_MARK, PC6MD_001), PINMUX_DATA(SCK7_MARK, PC6MD_010), PINMUX_DATA(CTX0_MARK, PC6MD_011), + PINMUX_DATA(CTX0_CTX1_CTX2_MARK, PC6MD_100), PINMUX_DATA(PC5_DATA, PC5MD_000), PINMUX_DATA(RAS_MARK, PC5MD_001), PINMUX_DATA(CRX0_MARK, PC5MD_011), - PINMUX_DATA(CTX0CTX1CTX2_MARK, PC5MD_100), + PINMUX_DATA(CTX0_CTX1_CTX2_MARK, PC5MD_100), PINMUX_DATA(IRQ0_PC_MARK, PC5MD_101), PINMUX_DATA(PC4_DATA, PC4MD_00), @@ -1292,30 +1293,32 @@ static const u16 pinmux_data[] = { PINMUX_DATA(LCD_DATA23_PJ23_MARK, PJ23MD_010), PINMUX_DATA(LCD_TCON6_MARK, PJ23MD_011), PINMUX_DATA(IRQ3_PJ_MARK, PJ23MD_100), - PINMUX_DATA(CTX1_MARK, PJ23MD_101), + PINMUX_DATA(CTX1_PJ23_MARK, PJ23MD_101), + PINMUX_DATA(CTX0_CTX1_PJ23_MARK, PJ23MD_110), PINMUX_DATA(PJ22_DATA, PJ22MD_000), PINMUX_DATA(DV_DATA22_MARK, PJ22MD_001), PINMUX_DATA(LCD_DATA22_PJ22_MARK, PJ22MD_010), PINMUX_DATA(LCD_TCON5_MARK, PJ22MD_011), PINMUX_DATA(IRQ2_PJ_MARK, PJ22MD_100), - PINMUX_DATA(CRX1_MARK, PJ22MD_101), - PINMUX_DATA(CRX0_CRX1_MARK, PJ22MD_110), + PINMUX_DATA(CRX1_PJ22_MARK, PJ22MD_101), + PINMUX_DATA(CRX0_CRX1_PJ22_MARK, PJ22MD_110), PINMUX_DATA(PJ21_DATA, PJ21MD_000), PINMUX_DATA(DV_DATA21_MARK, PJ21MD_001), PINMUX_DATA(LCD_DATA21_PJ21_MARK, PJ21MD_010), PINMUX_DATA(LCD_TCON4_MARK, PJ21MD_011), PINMUX_DATA(IRQ1_PJ_MARK, PJ21MD_100), - PINMUX_DATA(CTX2_MARK, PJ21MD_101), + PINMUX_DATA(CTX2_PJ21_MARK, PJ21MD_101), + PINMUX_DATA(CTX0_CTX1_CTX2_PJ21_MARK, PJ21MD_110), PINMUX_DATA(PJ20_DATA, PJ20MD_000), PINMUX_DATA(DV_DATA20_MARK, PJ20MD_001), PINMUX_DATA(LCD_DATA20_PJ20_MARK, PJ20MD_010), PINMUX_DATA(LCD_TCON3_MARK, PJ20MD_011), PINMUX_DATA(IRQ0_PJ_MARK, PJ20MD_100), - PINMUX_DATA(CRX2_MARK, PJ20MD_101), - PINMUX_DATA(CRX0CRX1CRX2_PJ20_MARK, PJ20MD_110), + PINMUX_DATA(CRX2_PJ20_MARK, PJ20MD_101), + PINMUX_DATA(CRX0_CRX1_CRX2_PJ20_MARK, PJ20MD_110), PINMUX_DATA(PJ19_DATA, PJ19MD_000), PINMUX_DATA(DV_DATA19_MARK, PJ19MD_001), @@ -1666,12 +1669,24 @@ static const struct pinmux_func pinmux_func_gpios[] = { GPIO_FN(WDTOVF), /* CAN */ + GPIO_FN(CTX2), + GPIO_FN(CRX2), GPIO_FN(CTX1), GPIO_FN(CRX1), GPIO_FN(CTX0), GPIO_FN(CRX0), + GPIO_FN(CTX0_CTX1), GPIO_FN(CRX0_CRX1), + GPIO_FN(CTX0_CTX1_CTX2), GPIO_FN(CRX0_CRX1_CRX2), + GPIO_FN(CTX2_PJ21), + GPIO_FN(CRX2_PJ20), + GPIO_FN(CTX1_PJ23), + GPIO_FN(CRX1_PJ22), + GPIO_FN(CTX0_CTX1_PJ23), + GPIO_FN(CRX0_CRX1_PJ22), + GPIO_FN(CTX0_CTX1_CTX2_PJ21), + GPIO_FN(CRX0_CRX1_CRX2_PJ20), /* DMAC */ GPIO_FN(TEND0), diff --git a/drivers/regulator/rk808-regulator.c b/drivers/regulator/rk808-regulator.c index d86a3dcd61e2..b96d50a03022 100644 --- a/drivers/regulator/rk808-regulator.c +++ b/drivers/regulator/rk808-regulator.c @@ -551,7 +551,7 @@ static int rk808_regulator_dt_parse_pdata(struct device *dev, } if (!pdata->dvs_gpio[i]) { - dev_warn(dev, "there is no dvs%d gpio\n", i); + dev_info(dev, "there is no dvs%d gpio\n", i); continue; } diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c index 44d0f5995f54..153c7b0f763a 100644 --- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -1479,7 +1479,7 @@ static int __init remoteproc_init(void) return 0; } -module_init(remoteproc_init); +subsys_initcall(remoteproc_init); static void __exit remoteproc_exit(void) { diff --git a/drivers/s390/cio/blacklist.c b/drivers/s390/cio/blacklist.c index 20314aad7ab7..f329459cadf1 100644 --- a/drivers/s390/cio/blacklist.c +++ b/drivers/s390/cio/blacklist.c @@ -303,8 +303,10 @@ static void * cio_ignore_proc_seq_next(struct seq_file *s, void *it, loff_t *offset) { struct ccwdev_iter *iter; + loff_t p = *offset; - if (*offset >= (__MAX_SUBCHANNEL + 1) * (__MAX_SSID + 1)) + (*offset)++; + if (p >= (__MAX_SUBCHANNEL + 1) * (__MAX_SSID + 1)) return NULL; iter = it; if (iter->devno == __MAX_SUBCHANNEL) { @@ -314,7 +316,6 @@ cio_ignore_proc_seq_next(struct seq_file *s, void *it, loff_t *offset) return NULL; } else iter->devno++; - (*offset)++; return iter; } diff --git a/drivers/scsi/aic7xxx/aic7xxx_core.c b/drivers/scsi/aic7xxx/aic7xxx_core.c index 64ab9eaec428..def3208dd290 100644 --- a/drivers/scsi/aic7xxx/aic7xxx_core.c +++ b/drivers/scsi/aic7xxx/aic7xxx_core.c @@ -2321,7 +2321,7 @@ ahc_find_syncrate(struct ahc_softc *ahc, u_int *period, * At some speeds, we only support * ST transfers. */ - if ((syncrate->sxfr_u2 & ST_SXFR) != 0) + if ((syncrate->sxfr_u2 & ST_SXFR) != 0) *ppr_options &= ~MSG_EXT_PPR_DT_REQ; break; } diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c index fccb8991bd5b..64a49dccb0b6 100644 --- a/drivers/scsi/iscsi_tcp.c +++ b/drivers/scsi/iscsi_tcp.c @@ -872,6 +872,10 @@ free_host: static void iscsi_sw_tcp_session_destroy(struct iscsi_cls_session *cls_session) { struct Scsi_Host *shost = iscsi_session_to_shost(cls_session); + struct iscsi_session *session = cls_session->dd_data; + + if (WARN_ON_ONCE(session->leadconn)) + return; iscsi_tcp_r2tpool_free(cls_session->dd_data); iscsi_session_teardown(cls_session); diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 8975baab73e5..daafb60fa13e 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -429,6 +429,12 @@ static int qla25xx_setup_mode(struct scsi_qla_host *vha) goto fail; } if (ql2xmultique_tag) { + ha->wq = alloc_workqueue("qla2xxx_wq", WQ_MEM_RECLAIM, 1); + if (unlikely(!ha->wq)) { + ql_log(ql_log_warn, vha, 0x01e0, + "Failed to alloc workqueue.\n"); + goto fail; + } /* create a request queue for IO */ options |= BIT_7; req = qla25xx_create_req_que(ha, options, 0, 0, -1, @@ -436,9 +442,8 @@ static int qla25xx_setup_mode(struct scsi_qla_host *vha) if (!req) { ql_log(ql_log_warn, vha, 0x00e0, "Failed to create request queue.\n"); - goto fail; + goto fail2; } - ha->wq = alloc_workqueue("qla2xxx_wq", WQ_MEM_RECLAIM, 1); vha->req = ha->req_q_map[req]; options |= BIT_1; for (ques = 1; ques < ha->max_rsp_queues; ques++) { @@ -446,7 +451,7 @@ static int qla25xx_setup_mode(struct scsi_qla_host *vha) if (!ret) { ql_log(ql_log_warn, vha, 0x00e8, "Failed to create response queue.\n"); - goto fail2; + goto fail3; } } ha->flags.cpu_affinity_enabled = 1; @@ -460,11 +465,13 @@ static int qla25xx_setup_mode(struct scsi_qla_host *vha) ha->max_rsp_queues, ha->max_req_queues); } return 0; -fail2: + +fail3: qla25xx_delete_queues(vha); - destroy_workqueue(ha->wq); - ha->wq = NULL; vha->req = ha->req_q_map[0]; +fail2: + destroy_workqueue(ha->wq); + ha->wq = NULL; fail: ha->mqenable = 0; kfree(ha->req_q_map); diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index ab32e6073642..20cf01d6ded7 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -2965,6 +2965,24 @@ iscsi_set_path(struct iscsi_transport *transport, struct iscsi_uevent *ev) return err; } +static int iscsi_session_has_conns(int sid) +{ + struct iscsi_cls_conn *conn; + unsigned long flags; + int found = 0; + + spin_lock_irqsave(&connlock, flags); + list_for_each_entry(conn, &connlist, conn_list) { + if (iscsi_conn_get_sid(conn) == sid) { + found = 1; + break; + } + } + spin_unlock_irqrestore(&connlock, flags); + + return found; +} + static int iscsi_set_iface_params(struct iscsi_transport *transport, struct iscsi_uevent *ev, uint32_t len) @@ -3539,10 +3557,12 @@ iscsi_if_recv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, uint32_t *group) break; case ISCSI_UEVENT_DESTROY_SESSION: session = iscsi_session_lookup(ev->u.d_session.sid); - if (session) - transport->destroy_session(session); - else + if (!session) err = -EINVAL; + else if (iscsi_session_has_conns(ev->u.d_session.sid)) + err = -EBUSY; + else + transport->destroy_session(session); break; case ISCSI_UEVENT_UNBIND_SESSION: session = iscsi_session_lookup(ev->u.d_session.sid); diff --git a/drivers/soc/tegra/fuse/tegra-apbmisc.c b/drivers/soc/tegra/fuse/tegra-apbmisc.c index 5b18f6ffa45c..cd61c883c19f 100644 --- a/drivers/soc/tegra/fuse/tegra-apbmisc.c +++ b/drivers/soc/tegra/fuse/tegra-apbmisc.c @@ -134,7 +134,7 @@ void __init tegra_init_apbmisc(void) apbmisc.flags = IORESOURCE_MEM; /* strapping options */ - if (tegra_get_chip_id() == TEGRA124) { + if (of_machine_is_compatible("nvidia,tegra124")) { straps.start = 0x7000e864; straps.end = 0x7000e867; } else { diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c index b4c425383f99..d6efd07146ce 100644 --- a/drivers/staging/android/ashmem.c +++ b/drivers/staging/android/ashmem.c @@ -357,8 +357,23 @@ static inline vm_flags_t calc_vm_may_flags(unsigned long prot) _calc_vm_trans(prot, PROT_EXEC, VM_MAYEXEC); } +static int ashmem_vmfile_mmap(struct file *file, struct vm_area_struct *vma) +{ + /* do not allow to mmap ashmem backing shmem file directly */ + return -EPERM; +} + +static unsigned long +ashmem_vmfile_get_unmapped_area(struct file *file, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags) +{ + return current->mm->get_unmapped_area(file, addr, len, pgoff, flags); +} + static int ashmem_mmap(struct file *file, struct vm_area_struct *vma) { + static struct file_operations vmfile_fops; struct ashmem_area *asma = file->private_data; int ret = 0; @@ -399,6 +414,19 @@ static int ashmem_mmap(struct file *file, struct vm_area_struct *vma) } vmfile->f_mode |= FMODE_LSEEK; asma->file = vmfile; + /* + * override mmap operation of the vmfile so that it can't be + * remapped which would lead to creation of a new vma with no + * asma permission checks. Have to override get_unmapped_area + * as well to prevent VM_BUG_ON check for f_ops modification. + */ + if (!vmfile_fops.mmap) { + vmfile_fops = *vmfile->f_op; + vmfile_fops.mmap = ashmem_vmfile_mmap; + vmfile_fops.get_unmapped_area = + ashmem_vmfile_get_unmapped_area; + } + vmfile->f_op = &vmfile_fops; } get_file(asma->file); diff --git a/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c b/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c index ec90f2781085..2a6192e08b75 100644 --- a/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c +++ b/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c @@ -2054,7 +2054,7 @@ static int wpa_supplicant_ioctl(struct net_device *dev, struct iw_point *p) struct ieee_param *param; uint ret = 0; - if (p->length < sizeof(struct ieee_param) || !p->pointer) { + if (!p->pointer || p->length != sizeof(struct ieee_param)) { ret = -EINVAL; goto out; } @@ -2859,7 +2859,7 @@ static int rtw_hostapd_ioctl(struct net_device *dev, struct iw_point *p) goto out; } - if (!p->pointer) { + if (!p->pointer || p->length != sizeof(struct ieee_param)) { ret = -EINVAL; goto out; } diff --git a/drivers/staging/vt6656/dpc.c b/drivers/staging/vt6656/dpc.c index e6367ed3b0bb..4fc6f00666ca 100644 --- a/drivers/staging/vt6656/dpc.c +++ b/drivers/staging/vt6656/dpc.c @@ -144,7 +144,7 @@ int vnt_rx_data(struct vnt_private *priv, struct vnt_rcb *ptr_rcb, vnt_rf_rssi_to_dbm(priv, *rssi, &rx_dbm); - priv->bb_pre_ed_rssi = (u8)rx_dbm + 1; + priv->bb_pre_ed_rssi = (u8)-rx_dbm + 1; priv->current_rssi = priv->bb_pre_ed_rssi; frame = skb_data + 8; diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index 07d9384bce94..cbb4414edd71 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -993,9 +993,7 @@ int iscsit_setup_scsi_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd, hdr->cmdsn, be32_to_cpu(hdr->data_length), payload_length, conn->cid); - if (target_get_sess_cmd(&cmd->se_cmd, true) < 0) - return iscsit_add_reject_cmd(cmd, - ISCSI_REASON_WAITING_FOR_LOGOUT, buf); + target_get_sess_cmd(&cmd->se_cmd, true); cmd->sense_reason = transport_lookup_cmd_lun(&cmd->se_cmd, scsilun_to_int(&hdr->lun)); @@ -1806,9 +1804,7 @@ iscsit_handle_task_mgt_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd, conn->sess->se_sess, 0, DMA_NONE, TCM_SIMPLE_TAG, cmd->sense_buffer + 2); - if (target_get_sess_cmd(&cmd->se_cmd, true) < 0) - return iscsit_add_reject_cmd(cmd, - ISCSI_REASON_WAITING_FOR_LOGOUT, buf); + target_get_sess_cmd(&cmd->se_cmd, true); /* * TASK_REASSIGN for ERL=2 / connection stays inside of @@ -4309,6 +4305,9 @@ int iscsit_close_connection( iscsit_stop_nopin_response_timer(conn); iscsit_stop_nopin_timer(conn); + if (conn->conn_transport->iscsit_wait_conn) + conn->conn_transport->iscsit_wait_conn(conn); + /* * During Connection recovery drop unacknowledged out of order * commands for this connection, and prepare the other commands @@ -4391,11 +4390,6 @@ int iscsit_close_connection( * must wait until they have completed. */ iscsit_check_conn_usage_count(conn); - target_sess_cmd_list_set_waiting(sess->se_sess); - target_wait_for_sess_cmds(sess->se_sess); - - if (conn->conn_transport->iscsit_wait_conn) - conn->conn_transport->iscsit_wait_conn(conn); if (conn->conn_rx_hash.tfm) crypto_free_hash(conn->conn_rx_hash.tfm); diff --git a/drivers/tty/serial/ar933x_uart.c b/drivers/tty/serial/ar933x_uart.c index 1519d2ca7705..40194791cde0 100644 --- a/drivers/tty/serial/ar933x_uart.c +++ b/drivers/tty/serial/ar933x_uart.c @@ -294,6 +294,10 @@ static void ar933x_uart_set_termios(struct uart_port *port, ar933x_uart_rmw_set(up, AR933X_UART_CS_REG, AR933X_UART_CS_HOST_INT_EN); + /* enable RX and TX ready overide */ + ar933x_uart_rmw_set(up, AR933X_UART_CS_REG, + AR933X_UART_CS_TX_READY_ORIDE | AR933X_UART_CS_RX_READY_ORIDE); + /* reenable the UART */ ar933x_uart_rmw(up, AR933X_UART_CS_REG, AR933X_UART_CS_IF_MODE_M << AR933X_UART_CS_IF_MODE_S, @@ -426,6 +430,10 @@ static int ar933x_uart_startup(struct uart_port *port) ar933x_uart_rmw_set(up, AR933X_UART_CS_REG, AR933X_UART_CS_HOST_INT_EN); + /* enable RX and TX ready overide */ + ar933x_uart_rmw_set(up, AR933X_UART_CS_REG, + AR933X_UART_CS_TX_READY_ORIDE | AR933X_UART_CS_RX_READY_ORIDE); + /* Enable RX interrupts */ up->ier = AR933X_UART_INT_RX_VALID; ar933x_uart_write(up, AR933X_UART_INT_EN_REG, up->ier); diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c index b59d0dafefab..ca69e2ca6b56 100644 --- a/drivers/tty/serial/imx.c +++ b/drivers/tty/serial/imx.c @@ -529,7 +529,7 @@ static void imx_dma_tx(struct imx_port *sport) sport->tx_bytes = uart_circ_chars_pending(xmit); - if (xmit->tail < xmit->head) { + if (xmit->tail < xmit->head || xmit->head == 0) { sport->dma_tx_nents = 1; sg_init_one(sgl, xmit->buf + xmit->tail, sport->tx_bytes); } else { diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c index ed27fda13387..def99f020d82 100644 --- a/drivers/tty/sysrq.c +++ b/drivers/tty/sysrq.c @@ -542,7 +542,6 @@ void __handle_sysrq(int key, bool check_mask) */ orig_log_level = console_loglevel; console_loglevel = CONSOLE_LOGLEVEL_DEFAULT; - pr_info("SysRq : "); op_p = __sysrq_get_key_op(key); if (op_p) { @@ -551,14 +550,15 @@ void __handle_sysrq(int key, bool check_mask) * should not) and is the invoked operation enabled? */ if (!check_mask || sysrq_on_mask(op_p->enable_mask)) { - pr_cont("%s\n", op_p->action_msg); + pr_info("%s\n", op_p->action_msg); console_loglevel = orig_log_level; op_p->handler(key); } else { - pr_cont("This sysrq operation is disabled.\n"); + pr_info("This sysrq operation is disabled.\n"); + console_loglevel = orig_log_level; } } else { - pr_cont("HELP : "); + pr_info("HELP : "); /* Only print the help msg once per handler */ for (i = 0; i < ARRAY_SIZE(sysrq_key_table); i++) { if (sysrq_key_table[i]) { diff --git a/drivers/tty/vt/selection.c b/drivers/tty/vt/selection.c index 381a2b13682c..9dae02ce4092 100644 --- a/drivers/tty/vt/selection.c +++ b/drivers/tty/vt/selection.c @@ -13,6 +13,7 @@ #include <linux/tty.h> #include <linux/sched.h> #include <linux/mm.h> +#include <linux/mutex.h> #include <linux/slab.h> #include <linux/types.h> @@ -40,6 +41,7 @@ static volatile int sel_start = -1; /* cleared by clear_selection */ static int sel_end; static int sel_buffer_lth; static char *sel_buffer; +static DEFINE_MUTEX(sel_lock); /* clear_selection, highlight and highlight_pointer can be called from interrupt (via scrollback/front) */ @@ -156,14 +158,14 @@ static int store_utf8(u16 c, char *p) * The entire selection process is managed under the console_lock. It's * a lot under the lock but its hardly a performance path */ -int set_selection(const struct tiocl_selection __user *sel, struct tty_struct *tty) +static int __set_selection(const struct tiocl_selection __user *sel, struct tty_struct *tty) { struct vc_data *vc = vc_cons[fg_console].d; int sel_mode, new_sel_start, new_sel_end, spc; char *bp, *obp; int i, ps, pe, multiplier; u16 c; - int mode; + int mode, ret = 0; poke_blanked_console(); @@ -324,7 +326,21 @@ int set_selection(const struct tiocl_selection __user *sel, struct tty_struct *t } } sel_buffer_lth = bp - sel_buffer; - return 0; + + return ret; +} + +int set_selection(const struct tiocl_selection __user *v, struct tty_struct *tty) +{ + int ret; + + mutex_lock(&sel_lock); + console_lock(); + ret = __set_selection(v, tty); + console_unlock(); + mutex_unlock(&sel_lock); + + return ret; } /* Insert the contents of the selection buffer into the @@ -350,6 +366,7 @@ int paste_selection(struct tty_struct *tty) tty_buffer_lock_exclusive(&vc->port); add_wait_queue(&vc->paste_wait, &wait); + mutex_lock(&sel_lock); while (sel_buffer && sel_buffer_lth > pasted) { set_current_state(TASK_INTERRUPTIBLE); if (test_bit(TTY_THROTTLED, &tty->flags)) { @@ -362,6 +379,7 @@ int paste_selection(struct tty_struct *tty) count); pasted += count; } + mutex_unlock(&sel_lock); remove_wait_queue(&vc->paste_wait, &wait); __set_current_state(TASK_RUNNING); diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 6779f733bb83..5b8b6ebebf3e 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -2687,9 +2687,7 @@ int tioclinux(struct tty_struct *tty, unsigned long arg) switch (type) { case TIOCL_SETSEL: - console_lock(); ret = set_selection((struct tiocl_selection __user *)(p+1), tty); - console_unlock(); break; case TIOCL_PASTESEL: ret = paste_selection(tty); diff --git a/drivers/tty/vt/vt_ioctl.c b/drivers/tty/vt/vt_ioctl.c index a86bc7afb3b2..e9d9f9f3dc88 100644 --- a/drivers/tty/vt/vt_ioctl.c +++ b/drivers/tty/vt/vt_ioctl.c @@ -850,58 +850,49 @@ int vt_ioctl(struct tty_struct *tty, case VT_RESIZEX: { - struct vt_consize __user *vtconsize = up; - ushort ll,cc,vlin,clin,vcol,ccol; + struct vt_consize v; if (!perm) return -EPERM; - if (!access_ok(VERIFY_READ, vtconsize, - sizeof(struct vt_consize))) { - ret = -EFAULT; - break; - } + if (copy_from_user(&v, up, sizeof(struct vt_consize))) + return -EFAULT; /* FIXME: Should check the copies properly */ - __get_user(ll, &vtconsize->v_rows); - __get_user(cc, &vtconsize->v_cols); - __get_user(vlin, &vtconsize->v_vlin); - __get_user(clin, &vtconsize->v_clin); - __get_user(vcol, &vtconsize->v_vcol); - __get_user(ccol, &vtconsize->v_ccol); - vlin = vlin ? vlin : vc->vc_scan_lines; - if (clin) { - if (ll) { - if (ll != vlin/clin) { - /* Parameters don't add up */ - ret = -EINVAL; - break; - } - } else - ll = vlin/clin; + if (!v.v_vlin) + v.v_vlin = vc->vc_scan_lines; + if (v.v_clin) { + int rows = v.v_vlin/v.v_clin; + if (v.v_rows != rows) { + if (v.v_rows) /* Parameters don't add up */ + return -EINVAL; + v.v_rows = rows; + } } - if (vcol && ccol) { - if (cc) { - if (cc != vcol/ccol) { - ret = -EINVAL; - break; - } - } else - cc = vcol/ccol; + if (v.v_vcol && v.v_ccol) { + int cols = v.v_vcol/v.v_ccol; + if (v.v_cols != cols) { + if (v.v_cols) + return -EINVAL; + v.v_cols = cols; + } } - if (clin > 32) { - ret = -EINVAL; - break; - } - + if (v.v_clin > 32) + return -EINVAL; + for (i = 0; i < MAX_NR_CONSOLES; i++) { + struct vc_data *vcp; + if (!vc_cons[i].d) continue; console_lock(); - if (vlin) - vc_cons[i].d->vc_scan_lines = vlin; - if (clin) - vc_cons[i].d->vc_font.height = clin; - vc_cons[i].d->vc_resize_user = 1; - vc_resize(vc_cons[i].d, cc, ll); + vcp = vc_cons[i].d; + if (vcp) { + if (v.v_vlin) + vcp->vc_scan_lines = v.v_vlin; + if (v.v_clin) + vcp->vc_font.height = v.v_clin; + vcp->vc_resize_user = 1; + vc_resize(vcp, v.v_cols, v.v_rows); + } console_unlock(); } break; diff --git a/drivers/uio/uio_dmem_genirq.c b/drivers/uio/uio_dmem_genirq.c index e1134a4d97f3..a00b4aee6c79 100644 --- a/drivers/uio/uio_dmem_genirq.c +++ b/drivers/uio/uio_dmem_genirq.c @@ -135,11 +135,13 @@ static int uio_dmem_genirq_irqcontrol(struct uio_info *dev_info, s32 irq_on) if (irq_on) { if (test_and_clear_bit(0, &priv->flags)) enable_irq(dev_info->irq); + spin_unlock_irqrestore(&priv->lock, flags); } else { - if (!test_and_set_bit(0, &priv->flags)) + if (!test_and_set_bit(0, &priv->flags)) { + spin_unlock_irqrestore(&priv->lock, flags); disable_irq(dev_info->irq); + } } - spin_unlock_irqrestore(&priv->lock, flags); return 0; } diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 75a07b73a82b..963dd8a4b540 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -938,13 +938,17 @@ int usb_remove_device(struct usb_device *udev) { struct usb_hub *hub; struct usb_interface *intf; + int ret; if (!udev->parent) /* Can't remove a root hub */ return -EINVAL; hub = usb_hub_to_struct_hub(udev->parent); intf = to_usb_interface(hub->intfdev); - usb_autopm_get_interface(intf); + ret = usb_autopm_get_interface(intf); + if (ret < 0) + return ret; + set_bit(udev->portnum, hub->removed_bits); hub_port_logical_disconnect(hub, udev->portnum); usb_autopm_put_interface(intf); @@ -1171,11 +1175,6 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type) #ifdef CONFIG_PM udev->reset_resume = 1; #endif - /* Don't set the change_bits when the device - * was powered off. - */ - if (test_bit(port1, hub->power_bits)) - set_bit(port1, hub->change_bits); } else { /* The power session is gone; tell hub_wq */ diff --git a/drivers/usb/core/port.c b/drivers/usb/core/port.c index 5487fe308f01..1235e678184b 100644 --- a/drivers/usb/core/port.c +++ b/drivers/usb/core/port.c @@ -98,7 +98,10 @@ static int usb_port_runtime_resume(struct device *dev) if (!port_dev->is_superspeed && peer) pm_runtime_get_sync(&peer->dev); - usb_autopm_get_interface(intf); + retval = usb_autopm_get_interface(intf); + if (retval < 0) + return retval; + retval = usb_hub_set_port_power(hdev, hub, port1, true); msleep(hub_power_on_good_delay(hub)); if (udev && !retval) { @@ -151,7 +154,10 @@ static int usb_port_runtime_suspend(struct device *dev) if (usb_port_block_power_off) return -EBUSY; - usb_autopm_get_interface(intf); + retval = usb_autopm_get_interface(intf); + if (retval < 0) + return retval; + retval = usb_hub_set_port_power(hdev, hub, port1, false); usb_clear_port_feature(hdev, port1, USB_PORT_FEAT_C_CONNECTION); if (!port_dev->is_superspeed) diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 19e819aa2419..64c03e871f2d 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -86,6 +86,9 @@ static const struct usb_device_id usb_quirk_list[] = { /* Logitech PTZ Pro Camera */ { USB_DEVICE(0x046d, 0x0853), .driver_info = USB_QUIRK_DELAY_INIT }, + /* Logitech Screen Share */ + { USB_DEVICE(0x046d, 0x086c), .driver_info = USB_QUIRK_NO_LPM }, + /* Logitech Quickcam Fusion */ { USB_DEVICE(0x046d, 0x08c1), .driver_info = USB_QUIRK_RESET_RESUME }, @@ -291,6 +294,9 @@ static const struct usb_device_id usb_quirk_list[] = { /* INTEL VALUE SSD */ { USB_DEVICE(0x8086, 0xf1a5), .driver_info = USB_QUIRK_RESET_RESUME }, + /* novation SoundControl XL */ + { USB_DEVICE(0x1235, 0x0061), .driver_info = USB_QUIRK_RESET_RESUME }, + { } /* terminating entry must be last */ }; diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 4cb1355271ec..9536c409a90d 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -888,18 +888,19 @@ static int ffs_aio_cancel(struct kiocb *kiocb) { struct ffs_io_data *io_data = kiocb->private; struct ffs_epfile *epfile = kiocb->ki_filp->private_data; + unsigned long flags; int value; ENTER(); - spin_lock_irq(&epfile->ffs->eps_lock); + spin_lock_irqsave(&epfile->ffs->eps_lock, flags); if (likely(io_data && io_data->ep && io_data->req)) value = usb_ep_dequeue(io_data->ep, io_data->req); else value = -EINVAL; - spin_unlock_irq(&epfile->ffs->eps_lock); + spin_unlock_irqrestore(&epfile->ffs->eps_lock, flags); return value; } diff --git a/drivers/usb/gadget/function/u_serial.c b/drivers/usb/gadget/function/u_serial.c index 31e08bb3cb41..58a699cfa458 100644 --- a/drivers/usb/gadget/function/u_serial.c +++ b/drivers/usb/gadget/function/u_serial.c @@ -701,8 +701,10 @@ static int gs_start_io(struct gs_port *port) port->n_read = 0; started = gs_start_rx(port); - /* unblock any pending writes into our circular buffer */ if (started) { + gs_start_tx(port); + /* Unblock any pending writes into our circular buffer, in case + * we didn't in gs_start_tx() */ tty_wakeup(port->port.tty); } else { gs_free_requests(ep, head, &port->read_allocated); diff --git a/drivers/usb/gadget/udc/gr_udc.c b/drivers/usb/gadget/udc/gr_udc.c index b9429bc42511..594639e5cbf8 100644 --- a/drivers/usb/gadget/udc/gr_udc.c +++ b/drivers/usb/gadget/udc/gr_udc.c @@ -2201,8 +2201,6 @@ static int gr_probe(struct platform_device *pdev) return -ENOMEM; } - spin_lock(&dev->lock); - /* Inside lock so that no gadget can use this udc until probe is done */ retval = usb_add_gadget_udc(dev->dev, &dev->gadget); if (retval) { @@ -2211,15 +2209,21 @@ static int gr_probe(struct platform_device *pdev) } dev->added = 1; + spin_lock(&dev->lock); + retval = gr_udc_init(dev); - if (retval) + if (retval) { + spin_unlock(&dev->lock); goto out; - - gr_dfs_create(dev); + } /* Clear all interrupt enables that might be left on since last boot */ gr_disable_interrupts_and_pullup(dev); + spin_unlock(&dev->lock); + + gr_dfs_create(dev); + retval = gr_request_irq(dev, dev->irq); if (retval) { dev_err(dev->dev, "Failed to request irq %d\n", dev->irq); @@ -2248,8 +2252,6 @@ static int gr_probe(struct platform_device *pdev) dev_info(dev->dev, "regs: %p, irq %d\n", dev->regs, dev->irq); out: - spin_unlock(&dev->lock); - if (retval) gr_remove(pdev); diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index df86ea308415..5af57afb4e56 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -53,6 +53,7 @@ #define PCI_DEVICE_ID_INTEL_BROXTON_B_XHCI 0x1aa8 #define PCI_DEVICE_ID_INTEL_APL_XHCI 0x5aa8 #define PCI_DEVICE_ID_INTEL_DNV_XHCI 0x19d0 +#define PCI_DEVICE_ID_INTEL_CML_XHCI 0xa3af static const char hcd_name[] = "xhci_hcd"; @@ -169,7 +170,8 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) pdev->device == PCI_DEVICE_ID_INTEL_BROXTON_M_XHCI || pdev->device == PCI_DEVICE_ID_INTEL_BROXTON_B_XHCI || pdev->device == PCI_DEVICE_ID_INTEL_APL_XHCI || - pdev->device == PCI_DEVICE_ID_INTEL_DNV_XHCI)) { + pdev->device == PCI_DEVICE_ID_INTEL_DNV_XHCI || + pdev->device == PCI_DEVICE_ID_INTEL_CML_XHCI)) { xhci->quirks |= XHCI_PME_STUCK_QUIRK; } if (pdev->vendor == PCI_VENDOR_ID_INTEL && diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c index a7cc0bc68deb..b38d9f162123 100644 --- a/drivers/usb/storage/uas.c +++ b/drivers/usb/storage/uas.c @@ -46,6 +46,7 @@ struct uas_dev_info { struct scsi_cmnd *cmnd[MAX_CMNDS]; spinlock_t lock; struct work_struct work; + struct work_struct scan_work; /* for async scanning */ }; enum { @@ -115,6 +116,17 @@ out: spin_unlock_irqrestore(&devinfo->lock, flags); } +static void uas_scan_work(struct work_struct *work) +{ + struct uas_dev_info *devinfo = + container_of(work, struct uas_dev_info, scan_work); + struct Scsi_Host *shost = usb_get_intfdata(devinfo->intf); + + dev_dbg(&devinfo->intf->dev, "starting scan\n"); + scsi_scan_host(shost); + dev_dbg(&devinfo->intf->dev, "scan complete\n"); +} + static void uas_add_work(struct uas_cmd_info *cmdinfo) { struct scsi_pointer *scp = (void *)cmdinfo; @@ -929,6 +941,7 @@ static int uas_probe(struct usb_interface *intf, const struct usb_device_id *id) init_usb_anchor(&devinfo->data_urbs); spin_lock_init(&devinfo->lock); INIT_WORK(&devinfo->work, uas_do_work); + INIT_WORK(&devinfo->scan_work, uas_scan_work); result = uas_configure_endpoints(devinfo); if (result) @@ -945,7 +958,9 @@ static int uas_probe(struct usb_interface *intf, const struct usb_device_id *id) if (result) goto free_streams; - scsi_scan_host(shost); + /* Submit the delayed_work for SCSI-device scanning */ + schedule_work(&devinfo->scan_work); + return result; free_streams: @@ -1113,6 +1128,12 @@ static void uas_disconnect(struct usb_interface *intf) usb_kill_anchored_urbs(&devinfo->data_urbs); uas_zap_pending(devinfo, DID_NO_CONNECT); + /* + * Prevent SCSI scanning (if it hasn't started yet) + * or wait for the SCSI-scanning routine to stop. + */ + cancel_work_sync(&devinfo->scan_work); + scsi_remove_host(shost); uas_free_streams(devinfo); scsi_host_put(shost); diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h index a98259e136dd..2e0a8088ffe2 100644 --- a/drivers/usb/storage/unusual_devs.h +++ b/drivers/usb/storage/unusual_devs.h @@ -1206,6 +1206,12 @@ UNUSUAL_DEV( 0x090a, 0x1200, 0x0000, 0x9999, USB_SC_RBC, USB_PR_BULK, NULL, 0 ), +UNUSUAL_DEV(0x090c, 0x1000, 0x1100, 0x1100, + "Samsung", + "Flash Drive FIT", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_MAX_SECTORS_64), + /* aeb */ UNUSUAL_DEV( 0x090c, 0x1132, 0x0000, 0xffff, "Feiya", diff --git a/drivers/video/console/vgacon.c b/drivers/video/console/vgacon.c index 598ec7545e84..e5231dd55e6e 100644 --- a/drivers/video/console/vgacon.c +++ b/drivers/video/console/vgacon.c @@ -1330,6 +1330,9 @@ static int vgacon_font_get(struct vc_data *c, struct console_font *font) static int vgacon_resize(struct vc_data *c, unsigned int width, unsigned int height, unsigned int user) { + if ((width << 1) * height > vga_vram_size) + return -EINVAL; + if (width % 2 || width > screen_info.orig_video_cols || height > (screen_info.orig_video_lines * vga_default_font_height)/ c->vc_font.height) diff --git a/drivers/watchdog/da9062_wdt.c b/drivers/watchdog/da9062_wdt.c index 7386111220d5..daeb645fcea8 100644 --- a/drivers/watchdog/da9062_wdt.c +++ b/drivers/watchdog/da9062_wdt.c @@ -126,13 +126,6 @@ static int da9062_wdt_stop(struct watchdog_device *wdd) struct da9062_watchdog *wdt = watchdog_get_drvdata(wdd); int ret; - ret = da9062_reset_watchdog_timer(wdt); - if (ret) { - dev_err(wdt->hw->dev, "Failed to ping the watchdog (err = %d)\n", - ret); - return ret; - } - ret = regmap_update_bits(wdt->hw->regmap, DA9062AA_CONTROL_D, DA9062AA_TWDSCALE_MASK, diff --git a/drivers/xen/preempt.c b/drivers/xen/preempt.c index 08cb419eb4e6..5f6b77ea34fb 100644 --- a/drivers/xen/preempt.c +++ b/drivers/xen/preempt.c @@ -37,7 +37,9 @@ asmlinkage __visible void xen_maybe_preempt_hcall(void) * cpu. */ __this_cpu_write(xen_in_preemptible_hcall, false); - _cond_resched(); + local_irq_enable(); + cond_resched(); + local_irq_disable(); __this_cpu_write(xen_in_preemptible_hcall, true); } } diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 2fb533233e8e..656f0b768185 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2972,6 +2972,7 @@ retry_root_backup: /* do not make disk changes in broken FS */ if (btrfs_super_log_root(disk_super) != 0) { + btrfs_info(fs_info, "start tree-log replay"); ret = btrfs_replay_log(fs_info, fs_devices); if (ret) { err = ret; diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index 84fb56d5c018..3818b65b0682 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -227,6 +227,17 @@ static void try_merge_map(struct extent_map_tree *tree, struct extent_map *em) struct extent_map *merge = NULL; struct rb_node *rb; + /* + * We can't modify an extent map that is in the tree and that is being + * used by another task, as it can cause that other task to see it in + * inconsistent state during the merging. We always have 1 reference for + * the tree and 1 for this task (which is unpinning the extent map or + * clearing the logging flag), so anything > 2 means it's being used by + * other tasks too. + */ + if (atomic_read(&em->refs) > 2) + return; + if (em->start != 0) { rb = rb_prev(&em->rb_node); if (rb) diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 8c27292ea9ea..2eadc8f8c9ef 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -820,10 +820,15 @@ int btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len) } btrfs_start_ordered_extent(inode, ordered, 1); end = ordered->file_offset; + /* + * If the ordered extent had an error save the error but don't + * exit without waiting first for all other ordered extents in + * the range to complete. + */ if (test_bit(BTRFS_ORDERED_IOERR, &ordered->flags)) ret = -EIO; btrfs_put_ordered_extent(ordered); - if (ret || end == 0 || end == start) + if (end == 0 || end == start) break; end--; } diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index df211bad255c..404051bf5cba 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1702,6 +1702,8 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) } if (btrfs_super_log_root(fs_info->super_copy) != 0) { + btrfs_warn(fs_info, + "mount required to replay tree-log, cannot remount read-write"); ret = -EINVAL; goto restore; } diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c index 3f93125916bf..f5b87a8f75c4 100644 --- a/fs/cifs/cifsacl.c +++ b/fs/cifs/cifsacl.c @@ -480,7 +480,7 @@ static void access_flags_to_mode(__le32 ace_flags, int type, umode_t *pmode, ((flags & FILE_EXEC_RIGHTS) == FILE_EXEC_RIGHTS)) *pmode |= (S_IXUGO & (*pbits_to_set)); - cifs_dbg(NOISY, "access flags 0x%x mode now 0x%x\n", flags, *pmode); + cifs_dbg(NOISY, "access flags 0x%x mode now %04o\n", flags, *pmode); return; } @@ -509,7 +509,7 @@ static void mode_to_access_flags(umode_t mode, umode_t bits_to_use, if (mode & S_IXUGO) *pace_flags |= SET_FILE_EXEC_RIGHTS; - cifs_dbg(NOISY, "mode: 0x%x, access flags now 0x%x\n", + cifs_dbg(NOISY, "mode: %04o, access flags now 0x%x\n", mode, *pace_flags); return; } diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 4bde8acca455..cf104bbe30a1 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -3402,7 +3402,7 @@ void cifs_setup_cifs_sb(struct smb_vol *pvolume_info, cifs_sb->mnt_gid = pvolume_info->linux_gid; cifs_sb->mnt_file_mode = pvolume_info->file_mode; cifs_sb->mnt_dir_mode = pvolume_info->dir_mode; - cifs_dbg(FYI, "file mode: 0x%hx dir mode: 0x%hx\n", + cifs_dbg(FYI, "file mode: %04ho dir mode: %04ho\n", cifs_sb->mnt_file_mode, cifs_sb->mnt_dir_mode); cifs_sb->actimeo = pvolume_info->actimeo; diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 0a219545940d..c18c26a78453 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -1540,7 +1540,7 @@ int cifs_mkdir(struct inode *inode, struct dentry *direntry, umode_t mode) struct TCP_Server_Info *server; char *full_path; - cifs_dbg(FYI, "In cifs_mkdir, mode = 0x%hx inode = 0x%p\n", + cifs_dbg(FYI, "In cifs_mkdir, mode = %04ho inode = 0x%p\n", mode, inode); cifs_sb = CIFS_SB(inode->i_sb); @@ -1957,6 +1957,7 @@ int cifs_revalidate_dentry_attr(struct dentry *dentry) struct inode *inode = d_inode(dentry); struct super_block *sb = dentry->d_sb; char *full_path = NULL; + int count = 0; if (inode == NULL) return -ENOENT; @@ -1978,15 +1979,18 @@ int cifs_revalidate_dentry_attr(struct dentry *dentry) full_path, inode, inode->i_count.counter, dentry, dentry->d_time, jiffies); +again: if (cifs_sb_master_tcon(CIFS_SB(sb))->unix_ext) rc = cifs_get_inode_info_unix(&inode, full_path, sb, xid); else rc = cifs_get_inode_info(&inode, full_path, NULL, sb, xid, NULL); - + if (rc == -EAGAIN && count++ < 10) + goto again; out: kfree(full_path); free_xid(xid); + return rc; } diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c index f246f1760ba2..83e9f6272bfb 100644 --- a/fs/ecryptfs/crypto.c +++ b/fs/ecryptfs/crypto.c @@ -346,8 +346,10 @@ static int crypt_scatterlist(struct ecryptfs_crypt_stat *crypt_stat, struct extent_crypt_result ecr; int rc = 0; - BUG_ON(!crypt_stat || !crypt_stat->tfm - || !(crypt_stat->flags & ECRYPTFS_STRUCT_INITIALIZED)); + if (!crypt_stat || !crypt_stat->tfm + || !(crypt_stat->flags & ECRYPTFS_STRUCT_INITIALIZED)) + return -EINVAL; + if (unlikely(ecryptfs_verbosity > 0)) { ecryptfs_printk(KERN_DEBUG, "Key size [%zd]; key:\n", crypt_stat->key_size); diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c index 20632ee51ae5..37920394c64c 100644 --- a/fs/ecryptfs/keystore.c +++ b/fs/ecryptfs/keystore.c @@ -1330,7 +1330,7 @@ parse_tag_1_packet(struct ecryptfs_crypt_stat *crypt_stat, printk(KERN_WARNING "Tag 1 packet contains key larger " "than ECRYPTFS_MAX_ENCRYPTED_KEY_BYTES"); rc = -EINVAL; - goto out; + goto out_free; } memcpy((*new_auth_tok)->session_key.encrypted_key, &data[(*packet_size)], (body_size - (ECRYPTFS_SIG_SIZE + 2))); diff --git a/fs/ecryptfs/messaging.c b/fs/ecryptfs/messaging.c index 4f457d5c4933..26464f9d9b76 100644 --- a/fs/ecryptfs/messaging.c +++ b/fs/ecryptfs/messaging.c @@ -397,6 +397,7 @@ int __init ecryptfs_init_messaging(void) * ecryptfs_message_buf_len), GFP_KERNEL); if (!ecryptfs_msg_ctx_arr) { + kfree(ecryptfs_daemon_hash); rc = -ENOMEM; printk(KERN_ERR "%s: Failed to allocate memory\n", __func__); goto out; diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index e0fb7cdcee89..b041a215cd73 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -279,6 +279,7 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb, ext4_group_t ngroups = ext4_get_groups_count(sb); struct ext4_group_desc *desc; struct ext4_sb_info *sbi = EXT4_SB(sb); + struct buffer_head *bh_p; if (block_group >= ngroups) { ext4_error(sb, "block_group >= groups_count - block_group = %u," @@ -289,7 +290,14 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb, group_desc = block_group >> EXT4_DESC_PER_BLOCK_BITS(sb); offset = block_group & (EXT4_DESC_PER_BLOCK(sb) - 1); - if (!sbi->s_group_desc[group_desc]) { + bh_p = sbi_array_rcu_deref(sbi, s_group_desc, group_desc); + /* + * sbi_array_rcu_deref returns with rcu unlocked, this is ok since + * the pointer being dereferenced won't be dereferenced again. By + * looking at the usage in add_new_gdb() the value isn't modified, + * just the pointer, and so it remains valid. + */ + if (!bh_p) { ext4_error(sb, "Group descriptor not loaded - " "block_group = %u, group_desc = %u, desc = %u", block_group, group_desc, offset); @@ -297,10 +305,10 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb, } desc = (struct ext4_group_desc *)( - (__u8 *)sbi->s_group_desc[group_desc]->b_data + + (__u8 *)bh_p->b_data + offset * EXT4_DESC_SIZE(sb)); if (bh) - *bh = sbi->s_group_desc[group_desc]; + *bh = bh_p; return desc; } diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index 209018f08dfd..7b626e942987 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -125,12 +125,14 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) if (err != ERR_BAD_DX_DIR) { return err; } - /* - * We don't set the inode dirty flag since it's not - * critical that it get flushed back to the disk. - */ - ext4_clear_inode_flag(file_inode(file), - EXT4_INODE_INDEX); + /* Can we just clear INDEX flag to ignore htree information? */ + if (!ext4_has_metadata_csum(sb)) { + /* + * We don't set the inode dirty flag since it's not + * critical that it gets flushed back to the disk. + */ + ext4_clear_inode_flag(inode, EXT4_INODE_INDEX); + } } if (ext4_has_inline_data(inode)) { diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index b6e25d771eea..ab0f08c89d5f 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1303,7 +1303,7 @@ struct ext4_sb_info { loff_t s_bitmap_maxbytes; /* max bytes for bitmap files */ struct buffer_head * s_sbh; /* Buffer containing the super block */ struct ext4_super_block *s_es; /* Pointer to the super block in the buffer */ - struct buffer_head **s_group_desc; + struct buffer_head * __rcu *s_group_desc; unsigned int s_mount_opt; unsigned int s_mount_opt2; unsigned int s_mount_flags; @@ -1363,7 +1363,7 @@ struct ext4_sb_info { #endif /* for buddy allocator */ - struct ext4_group_info ***s_group_info; + struct ext4_group_info ** __rcu *s_group_info; struct inode *s_buddy_cache; spinlock_t s_md_lock; unsigned short *s_mb_offsets; @@ -1410,7 +1410,7 @@ struct ext4_sb_info { unsigned int s_extent_max_zeroout_kb; unsigned int s_log_groups_per_flex; - struct flex_groups *s_flex_groups; + struct flex_groups * __rcu *s_flex_groups; ext4_group_t s_flex_groups_allocated; /* workqueue for reserved extent conversions (buffered io) */ @@ -1492,6 +1492,23 @@ static inline void ext4_inode_aio_set(struct inode *inode, ext4_io_end_t *io) } /* + * Returns: sbi->field[index] + * Used to access an array element from the following sbi fields which require + * rcu protection to avoid dereferencing an invalid pointer due to reassignment + * - s_group_desc + * - s_group_info + * - s_flex_group + */ +#define sbi_array_rcu_deref(sbi, field, index) \ +({ \ + typeof(*((sbi)->field)) _v; \ + rcu_read_lock(); \ + _v = ((typeof(_v)*)rcu_dereference((sbi)->field))[index]; \ + rcu_read_unlock(); \ + _v; \ +}) + +/* * Inode dynamic state flags */ enum { @@ -2381,8 +2398,11 @@ int ext4_insert_dentry(struct inode *dir, struct ext4_filename *fname); static inline void ext4_update_dx_flag(struct inode *inode) { - if (!ext4_has_feature_dir_index(inode->i_sb)) + if (!ext4_has_feature_dir_index(inode->i_sb)) { + /* ext4_iget() should have caught this... */ + WARN_ON_ONCE(ext4_has_feature_metadata_csum(inode->i_sb)); ext4_clear_inode_flag(inode, EXT4_INODE_INDEX); + } } static unsigned char ext4_filetype_table[] = { DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK @@ -2552,6 +2572,7 @@ extern int ext4_generic_delete_entry(handle_t *handle, extern int ext4_empty_dir(struct inode *inode); /* resize.c */ +extern void ext4_kvfree_array_rcu(void *to_free); extern int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input); extern int ext4_group_extend(struct super_block *sb, @@ -2792,13 +2813,13 @@ static inline struct ext4_group_info *ext4_get_group_info(struct super_block *sb, ext4_group_t group) { - struct ext4_group_info ***grp_info; + struct ext4_group_info **grp_info; long indexv, indexh; BUG_ON(group >= EXT4_SB(sb)->s_groups_count); - grp_info = EXT4_SB(sb)->s_group_info; indexv = group >> (EXT4_DESC_PER_BLOCK_BITS(sb)); indexh = group & ((EXT4_DESC_PER_BLOCK(sb)) - 1); - return grp_info[indexv][indexh]; + grp_info = sbi_array_rcu_deref(EXT4_SB(sb), s_group_info, indexv); + return grp_info[indexh]; } /* @@ -2848,7 +2869,7 @@ static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize) !mutex_is_locked(&inode->i_mutex)); down_write(&EXT4_I(inode)->i_data_sem); if (newsize > EXT4_I(inode)->i_disksize) - EXT4_I(inode)->i_disksize = newsize; + WRITE_ONCE(EXT4_I(inode)->i_disksize, newsize); up_write(&EXT4_I(inode)->i_data_sem); } diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 0963213e9cd3..c31b05f0bd69 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -331,11 +331,13 @@ void ext4_free_inode(handle_t *handle, struct inode *inode) percpu_counter_inc(&sbi->s_freeinodes_counter); if (sbi->s_log_groups_per_flex) { - ext4_group_t f = ext4_flex_group(sbi, block_group); + struct flex_groups *fg; - atomic_inc(&sbi->s_flex_groups[f].free_inodes); + fg = sbi_array_rcu_deref(sbi, s_flex_groups, + ext4_flex_group(sbi, block_group)); + atomic_inc(&fg->free_inodes); if (is_directory) - atomic_dec(&sbi->s_flex_groups[f].used_dirs); + atomic_dec(&fg->used_dirs); } BUFFER_TRACE(bh2, "call ext4_handle_dirty_metadata"); fatal = ext4_handle_dirty_metadata(handle, NULL, bh2); @@ -376,12 +378,13 @@ static void get_orlov_stats(struct super_block *sb, ext4_group_t g, int flex_size, struct orlov_stats *stats) { struct ext4_group_desc *desc; - struct flex_groups *flex_group = EXT4_SB(sb)->s_flex_groups; if (flex_size > 1) { - stats->free_inodes = atomic_read(&flex_group[g].free_inodes); - stats->free_clusters = atomic64_read(&flex_group[g].free_clusters); - stats->used_dirs = atomic_read(&flex_group[g].used_dirs); + struct flex_groups *fg = sbi_array_rcu_deref(EXT4_SB(sb), + s_flex_groups, g); + stats->free_inodes = atomic_read(&fg->free_inodes); + stats->free_clusters = atomic64_read(&fg->free_clusters); + stats->used_dirs = atomic_read(&fg->used_dirs); return; } @@ -981,7 +984,8 @@ got: if (sbi->s_log_groups_per_flex) { ext4_group_t f = ext4_flex_group(sbi, group); - atomic_inc(&sbi->s_flex_groups[f].used_dirs); + atomic_inc(&sbi_array_rcu_deref(sbi, s_flex_groups, + f)->used_dirs); } } if (ext4_has_group_desc_csum(sb)) { @@ -1004,7 +1008,8 @@ got: if (sbi->s_log_groups_per_flex) { flex_group = ext4_flex_group(sbi, group); - atomic_dec(&sbi->s_flex_groups[flex_group].free_inodes); + atomic_dec(&sbi_array_rcu_deref(sbi, s_flex_groups, + flex_group)->free_inodes); } inode->i_ino = ino + group * EXT4_INODES_PER_GROUP(sb); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 271d8d9d0598..d1daac8d81f3 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2320,7 +2320,7 @@ update_disksize: * truncate are avoided by checking i_size under i_data_sem. */ disksize = ((loff_t)mpd->first_page) << PAGE_CACHE_SHIFT; - if (disksize > EXT4_I(inode)->i_disksize) { + if (disksize > READ_ONCE(EXT4_I(inode)->i_disksize)) { int err2; loff_t i_size; @@ -4325,6 +4325,18 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) ret = -EFSCORRUPTED; goto bad_inode; } + /* + * If dir_index is not enabled but there's dir with INDEX flag set, + * we'd normally treat htree data as empty space. But with metadata + * checksumming that corrupts checksums so forbid that. + */ + if (!ext4_has_feature_dir_index(sb) && ext4_has_metadata_csum(sb) && + ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) { + EXT4_ERROR_INODE(inode, + "iget: Dir with htree data on filesystem without dir_index feature."); + ret = -EFSCORRUPTED; + goto bad_inode; + } ei->i_disksize = inode->i_size; #ifdef CONFIG_QUOTA ei->i_reserved_quota = 0; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 828b4c080c38..fda49f4c5a8e 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2378,7 +2378,7 @@ int ext4_mb_alloc_groupinfo(struct super_block *sb, ext4_group_t ngroups) { struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned size; - struct ext4_group_info ***new_groupinfo; + struct ext4_group_info ***old_groupinfo, ***new_groupinfo; size = (ngroups + EXT4_DESC_PER_BLOCK(sb) - 1) >> EXT4_DESC_PER_BLOCK_BITS(sb); @@ -2391,13 +2391,16 @@ int ext4_mb_alloc_groupinfo(struct super_block *sb, ext4_group_t ngroups) ext4_msg(sb, KERN_ERR, "can't allocate buddy meta group"); return -ENOMEM; } - if (sbi->s_group_info) { - memcpy(new_groupinfo, sbi->s_group_info, + rcu_read_lock(); + old_groupinfo = rcu_dereference(sbi->s_group_info); + if (old_groupinfo) + memcpy(new_groupinfo, old_groupinfo, sbi->s_group_info_size * sizeof(*sbi->s_group_info)); - kvfree(sbi->s_group_info); - } - sbi->s_group_info = new_groupinfo; + rcu_read_unlock(); + rcu_assign_pointer(sbi->s_group_info, new_groupinfo); sbi->s_group_info_size = size / sizeof(*sbi->s_group_info); + if (old_groupinfo) + ext4_kvfree_array_rcu(old_groupinfo); ext4_debug("allocated s_groupinfo array for %d meta_bg's\n", sbi->s_group_info_size); return 0; @@ -2409,6 +2412,7 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, { int i; int metalen = 0; + int idx = group >> EXT4_DESC_PER_BLOCK_BITS(sb); struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_group_info **meta_group_info; struct kmem_cache *cachep = get_groupinfo_cache(sb->s_blocksize_bits); @@ -2427,12 +2431,12 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, "for a buddy group"); goto exit_meta_group_info; } - sbi->s_group_info[group >> EXT4_DESC_PER_BLOCK_BITS(sb)] = - meta_group_info; + rcu_read_lock(); + rcu_dereference(sbi->s_group_info)[idx] = meta_group_info; + rcu_read_unlock(); } - meta_group_info = - sbi->s_group_info[group >> EXT4_DESC_PER_BLOCK_BITS(sb)]; + meta_group_info = sbi_array_rcu_deref(sbi, s_group_info, idx); i = group & (EXT4_DESC_PER_BLOCK(sb) - 1); meta_group_info[i] = kmem_cache_zalloc(cachep, GFP_NOFS); @@ -2480,8 +2484,13 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, exit_group_info: /* If a meta_group_info table has been allocated, release it now */ if (group % EXT4_DESC_PER_BLOCK(sb) == 0) { - kfree(sbi->s_group_info[group >> EXT4_DESC_PER_BLOCK_BITS(sb)]); - sbi->s_group_info[group >> EXT4_DESC_PER_BLOCK_BITS(sb)] = NULL; + struct ext4_group_info ***group_info; + + rcu_read_lock(); + group_info = rcu_dereference(sbi->s_group_info); + kfree(group_info[idx]); + group_info[idx] = NULL; + rcu_read_unlock(); } exit_meta_group_info: return -ENOMEM; @@ -2494,6 +2503,7 @@ static int ext4_mb_init_backend(struct super_block *sb) struct ext4_sb_info *sbi = EXT4_SB(sb); int err; struct ext4_group_desc *desc; + struct ext4_group_info ***group_info; struct kmem_cache *cachep; err = ext4_mb_alloc_groupinfo(sb, ngroups); @@ -2528,11 +2538,16 @@ err_freebuddy: while (i-- > 0) kmem_cache_free(cachep, ext4_get_group_info(sb, i)); i = sbi->s_group_info_size; + rcu_read_lock(); + group_info = rcu_dereference(sbi->s_group_info); while (i-- > 0) - kfree(sbi->s_group_info[i]); + kfree(group_info[i]); + rcu_read_unlock(); iput(sbi->s_buddy_cache); err_freesgi: - kvfree(sbi->s_group_info); + rcu_read_lock(); + kvfree(rcu_dereference(sbi->s_group_info)); + rcu_read_unlock(); return -ENOMEM; } @@ -2720,7 +2735,7 @@ int ext4_mb_release(struct super_block *sb) ext4_group_t ngroups = ext4_get_groups_count(sb); ext4_group_t i; int num_meta_group_infos; - struct ext4_group_info *grinfo; + struct ext4_group_info *grinfo, ***group_info; struct ext4_sb_info *sbi = EXT4_SB(sb); struct kmem_cache *cachep = get_groupinfo_cache(sb->s_blocksize_bits); @@ -2738,9 +2753,12 @@ int ext4_mb_release(struct super_block *sb) num_meta_group_infos = (ngroups + EXT4_DESC_PER_BLOCK(sb) - 1) >> EXT4_DESC_PER_BLOCK_BITS(sb); + rcu_read_lock(); + group_info = rcu_dereference(sbi->s_group_info); for (i = 0; i < num_meta_group_infos; i++) - kfree(sbi->s_group_info[i]); - kvfree(sbi->s_group_info); + kfree(group_info[i]); + kvfree(group_info); + rcu_read_unlock(); } kfree(sbi->s_mb_offsets); kfree(sbi->s_mb_maxs); @@ -2995,7 +3013,8 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, ext4_group_t flex_group = ext4_flex_group(sbi, ac->ac_b_ex.fe_group); atomic64_sub(ac->ac_b_ex.fe_len, - &sbi->s_flex_groups[flex_group].free_clusters); + &sbi_array_rcu_deref(sbi, s_flex_groups, + flex_group)->free_clusters); } err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh); @@ -4887,7 +4906,8 @@ do_more: if (sbi->s_log_groups_per_flex) { ext4_group_t flex_group = ext4_flex_group(sbi, block_group); atomic64_add(count_clusters, - &sbi->s_flex_groups[flex_group].free_clusters); + &sbi_array_rcu_deref(sbi, s_flex_groups, + flex_group)->free_clusters); } if (!(flags & EXT4_FREE_BLOCKS_NO_QUOT_UPDATE)) @@ -5032,7 +5052,8 @@ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb, if (sbi->s_log_groups_per_flex) { ext4_group_t flex_group = ext4_flex_group(sbi, block_group); atomic64_add(EXT4_NUM_B2C(sbi, blocks_freed), - &sbi->s_flex_groups[flex_group].free_clusters); + &sbi_array_rcu_deref(sbi, s_flex_groups, + flex_group)->free_clusters); } ext4_mb_unload_buddy(&e4b); diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 712bf332e394..49e0d97b2ee7 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1418,6 +1418,7 @@ restart: /* * We deal with the read-ahead logic here. */ + cond_resched(); if (ra_ptr >= ra_max) { /* Refill the readahead buffer */ ra_ptr = 0; @@ -2121,6 +2122,13 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, retval = ext4_dx_add_entry(handle, &fname, dentry, inode); if (!retval || (retval != ERR_BAD_DX_DIR)) goto out; + /* Can we just ignore htree data? */ + if (ext4_has_metadata_csum(sb)) { + EXT4_ERROR_INODE(dir, + "Directory has corrupted htree index."); + retval = -EFSCORRUPTED; + goto out; + } ext4_clear_inode_flag(dir, EXT4_INODE_INDEX); dx_fallback++; ext4_mark_inode_dirty(handle, dir); diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 5223eb25bf59..f5b6667b0ab0 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -16,6 +16,33 @@ #include "ext4_jbd2.h" +struct ext4_rcu_ptr { + struct rcu_head rcu; + void *ptr; +}; + +static void ext4_rcu_ptr_callback(struct rcu_head *head) +{ + struct ext4_rcu_ptr *ptr; + + ptr = container_of(head, struct ext4_rcu_ptr, rcu); + kvfree(ptr->ptr); + kfree(ptr); +} + +void ext4_kvfree_array_rcu(void *to_free) +{ + struct ext4_rcu_ptr *ptr = kzalloc(sizeof(*ptr), GFP_KERNEL); + + if (ptr) { + ptr->ptr = to_free; + call_rcu(&ptr->rcu, ext4_rcu_ptr_callback); + return; + } + synchronize_rcu(); + kvfree(to_free); +} + int ext4_resize_begin(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); @@ -541,8 +568,8 @@ static int setup_new_flex_group_blocks(struct super_block *sb, brelse(gdb); goto out; } - memcpy(gdb->b_data, sbi->s_group_desc[j]->b_data, - gdb->b_size); + memcpy(gdb->b_data, sbi_array_rcu_deref(sbi, + s_group_desc, j)->b_data, gdb->b_size); set_buffer_uptodate(gdb); err = ext4_handle_dirty_metadata(handle, NULL, gdb); @@ -849,13 +876,15 @@ static int add_new_gdb(handle_t *handle, struct inode *inode, } brelse(dind); - o_group_desc = EXT4_SB(sb)->s_group_desc; + rcu_read_lock(); + o_group_desc = rcu_dereference(EXT4_SB(sb)->s_group_desc); memcpy(n_group_desc, o_group_desc, EXT4_SB(sb)->s_gdb_count * sizeof(struct buffer_head *)); + rcu_read_unlock(); n_group_desc[gdb_num] = gdb_bh; - EXT4_SB(sb)->s_group_desc = n_group_desc; + rcu_assign_pointer(EXT4_SB(sb)->s_group_desc, n_group_desc); EXT4_SB(sb)->s_gdb_count++; - kvfree(o_group_desc); + ext4_kvfree_array_rcu(o_group_desc); le16_add_cpu(&es->s_reserved_gdt_blocks, -1); err = ext4_handle_dirty_super(handle, sb); @@ -903,9 +932,11 @@ static int add_new_gdb_meta_bg(struct super_block *sb, return err; } - o_group_desc = EXT4_SB(sb)->s_group_desc; + rcu_read_lock(); + o_group_desc = rcu_dereference(EXT4_SB(sb)->s_group_desc); memcpy(n_group_desc, o_group_desc, EXT4_SB(sb)->s_gdb_count * sizeof(struct buffer_head *)); + rcu_read_unlock(); n_group_desc[gdb_num] = gdb_bh; BUFFER_TRACE(gdb_bh, "get_write_access"); @@ -916,9 +947,9 @@ static int add_new_gdb_meta_bg(struct super_block *sb, return err; } - EXT4_SB(sb)->s_group_desc = n_group_desc; + rcu_assign_pointer(EXT4_SB(sb)->s_group_desc, n_group_desc); EXT4_SB(sb)->s_gdb_count++; - kvfree(o_group_desc); + ext4_kvfree_array_rcu(o_group_desc); return err; } @@ -1180,7 +1211,8 @@ static int ext4_add_new_descs(handle_t *handle, struct super_block *sb, * use non-sparse filesystems anymore. This is already checked above. */ if (gdb_off) { - gdb_bh = sbi->s_group_desc[gdb_num]; + gdb_bh = sbi_array_rcu_deref(sbi, s_group_desc, + gdb_num); BUFFER_TRACE(gdb_bh, "get_write_access"); err = ext4_journal_get_write_access(handle, gdb_bh); @@ -1262,7 +1294,7 @@ static int ext4_setup_new_descs(handle_t *handle, struct super_block *sb, /* * get_write_access() has been called on gdb_bh by ext4_add_new_desc(). */ - gdb_bh = sbi->s_group_desc[gdb_num]; + gdb_bh = sbi_array_rcu_deref(sbi, s_group_desc, gdb_num); /* Update group descriptor block for new group */ gdp = (struct ext4_group_desc *)(gdb_bh->b_data + gdb_off * EXT4_DESC_SIZE(sb)); @@ -1390,11 +1422,14 @@ static void ext4_update_super(struct super_block *sb, percpu_counter_read(&sbi->s_freeclusters_counter)); if (ext4_has_feature_flex_bg(sb) && sbi->s_log_groups_per_flex) { ext4_group_t flex_group; + struct flex_groups *fg; + flex_group = ext4_flex_group(sbi, group_data[0].group); + fg = sbi_array_rcu_deref(sbi, s_flex_groups, flex_group); atomic64_add(EXT4_NUM_B2C(sbi, free_blocks), - &sbi->s_flex_groups[flex_group].free_clusters); + &fg->free_clusters); atomic_add(EXT4_INODES_PER_GROUP(sb) * flex_gd->count, - &sbi->s_flex_groups[flex_group].free_inodes); + &fg->free_inodes); } /* @@ -1489,7 +1524,8 @@ exit_journal: for (; gdb_num <= gdb_num_end; gdb_num++) { struct buffer_head *gdb_bh; - gdb_bh = sbi->s_group_desc[gdb_num]; + gdb_bh = sbi_array_rcu_deref(sbi, s_group_desc, + gdb_num); if (old_gdb == gdb_bh->b_blocknr) continue; update_backups(sb, gdb_bh->b_blocknr, gdb_bh->b_data, diff --git a/fs/ext4/super.c b/fs/ext4/super.c index adf02b1509ca..f2e0220b00c3 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -794,6 +794,8 @@ static void ext4_put_super(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; + struct buffer_head **group_desc; + struct flex_groups **flex_groups; int aborted = 0; int i, err; @@ -826,10 +828,18 @@ static void ext4_put_super(struct super_block *sb) if (!(sb->s_flags & MS_RDONLY)) ext4_commit_super(sb, 1); + rcu_read_lock(); + group_desc = rcu_dereference(sbi->s_group_desc); for (i = 0; i < sbi->s_gdb_count; i++) - brelse(sbi->s_group_desc[i]); - kvfree(sbi->s_group_desc); - kvfree(sbi->s_flex_groups); + brelse(group_desc[i]); + kvfree(group_desc); + flex_groups = rcu_dereference(sbi->s_flex_groups); + if (flex_groups) { + for (i = 0; i < sbi->s_flex_groups_allocated; i++) + kvfree(flex_groups[i]); + kvfree(flex_groups); + } + rcu_read_unlock(); percpu_counter_destroy(&sbi->s_freeclusters_counter); percpu_counter_destroy(&sbi->s_freeinodes_counter); percpu_counter_destroy(&sbi->s_dirs_counter); @@ -1978,8 +1988,8 @@ done: int ext4_alloc_flex_bg_array(struct super_block *sb, ext4_group_t ngroup) { struct ext4_sb_info *sbi = EXT4_SB(sb); - struct flex_groups *new_groups; - int size; + struct flex_groups **old_groups, **new_groups; + int size, i, j; if (!sbi->s_log_groups_per_flex) return 0; @@ -1988,22 +1998,37 @@ int ext4_alloc_flex_bg_array(struct super_block *sb, ext4_group_t ngroup) if (size <= sbi->s_flex_groups_allocated) return 0; - size = roundup_pow_of_two(size * sizeof(struct flex_groups)); - new_groups = ext4_kvzalloc(size, GFP_KERNEL); + new_groups = ext4_kvzalloc(roundup_pow_of_two(size * + sizeof(*sbi->s_flex_groups)), GFP_KERNEL); if (!new_groups) { - ext4_msg(sb, KERN_ERR, "not enough memory for %d flex groups", - size / (int) sizeof(struct flex_groups)); + ext4_msg(sb, KERN_ERR, + "not enough memory for %d flex group pointers", size); return -ENOMEM; } - - if (sbi->s_flex_groups) { - memcpy(new_groups, sbi->s_flex_groups, - (sbi->s_flex_groups_allocated * - sizeof(struct flex_groups))); - kvfree(sbi->s_flex_groups); + for (i = sbi->s_flex_groups_allocated; i < size; i++) { + new_groups[i] = ext4_kvzalloc(roundup_pow_of_two( + sizeof(struct flex_groups)), + GFP_KERNEL); + if (!new_groups[i]) { + for (j = sbi->s_flex_groups_allocated; j < i; j++) + kvfree(new_groups[j]); + kvfree(new_groups); + ext4_msg(sb, KERN_ERR, + "not enough memory for %d flex groups", size); + return -ENOMEM; + } } - sbi->s_flex_groups = new_groups; - sbi->s_flex_groups_allocated = size / sizeof(struct flex_groups); + rcu_read_lock(); + old_groups = rcu_dereference(sbi->s_flex_groups); + if (old_groups) + memcpy(new_groups, old_groups, + (sbi->s_flex_groups_allocated * + sizeof(struct flex_groups *))); + rcu_read_unlock(); + rcu_assign_pointer(sbi->s_flex_groups, new_groups); + sbi->s_flex_groups_allocated = size; + if (old_groups) + ext4_kvfree_array_rcu(old_groups); return 0; } @@ -2011,6 +2036,7 @@ static int ext4_fill_flex_info(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_group_desc *gdp = NULL; + struct flex_groups *fg; ext4_group_t flex_group; int i, err; @@ -2028,12 +2054,11 @@ static int ext4_fill_flex_info(struct super_block *sb) gdp = ext4_get_group_desc(sb, i, NULL); flex_group = ext4_flex_group(sbi, i); - atomic_add(ext4_free_inodes_count(sb, gdp), - &sbi->s_flex_groups[flex_group].free_inodes); + fg = sbi_array_rcu_deref(sbi, s_flex_groups, flex_group); + atomic_add(ext4_free_inodes_count(sb, gdp), &fg->free_inodes); atomic64_add(ext4_free_group_clusters(sb, gdp), - &sbi->s_flex_groups[flex_group].free_clusters); - atomic_add(ext4_used_dirs_count(sb, gdp), - &sbi->s_flex_groups[flex_group].used_dirs); + &fg->free_clusters); + atomic_add(ext4_used_dirs_count(sb, gdp), &fg->used_dirs); } return 1; @@ -3236,9 +3261,10 @@ static void ext4_set_resv_clusters(struct super_block *sb) static int ext4_fill_super(struct super_block *sb, void *data, int silent) { char *orig_data = kstrdup(data, GFP_KERNEL); - struct buffer_head *bh; + struct buffer_head *bh, **group_desc; struct ext4_super_block *es = NULL; struct ext4_sb_info *sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); + struct flex_groups **flex_groups; ext4_fsblk_t block; ext4_fsblk_t sb_block = get_sb_block(&data); ext4_fsblk_t logical_sb_block; @@ -3795,9 +3821,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount; } } - sbi->s_group_desc = ext4_kvmalloc(db_count * + rcu_assign_pointer(sbi->s_group_desc, + ext4_kvmalloc(db_count * sizeof(struct buffer_head *), - GFP_KERNEL); + GFP_KERNEL)); if (sbi->s_group_desc == NULL) { ext4_msg(sb, KERN_ERR, "not enough memory"); ret = -ENOMEM; @@ -3807,14 +3834,19 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) bgl_lock_init(sbi->s_blockgroup_lock); for (i = 0; i < db_count; i++) { + struct buffer_head *bh; + block = descriptor_loc(sb, logical_sb_block, i); - sbi->s_group_desc[i] = sb_bread_unmovable(sb, block); - if (!sbi->s_group_desc[i]) { + bh = sb_bread_unmovable(sb, block); + if (!bh) { ext4_msg(sb, KERN_ERR, "can't read group descriptor %d", i); db_count = i; goto failed_mount2; } + rcu_read_lock(); + rcu_dereference(sbi->s_group_desc)[i] = bh; + rcu_read_unlock(); } sbi->s_gdb_count = db_count; if (!ext4_check_descriptors(sb, logical_sb_block, &first_not_zeroed)) { @@ -4149,8 +4181,14 @@ failed_mount7: ext4_unregister_li_request(sb); failed_mount6: ext4_mb_release(sb); - if (sbi->s_flex_groups) - kvfree(sbi->s_flex_groups); + rcu_read_lock(); + flex_groups = rcu_dereference(sbi->s_flex_groups); + if (flex_groups) { + for (i = 0; i < sbi->s_flex_groups_allocated; i++) + kvfree(flex_groups[i]); + kvfree(flex_groups); + } + rcu_read_unlock(); percpu_counter_destroy(&sbi->s_freeclusters_counter); percpu_counter_destroy(&sbi->s_freeinodes_counter); percpu_counter_destroy(&sbi->s_dirs_counter); @@ -4177,9 +4215,12 @@ failed_mount3: if (sbi->s_mmp_tsk) kthread_stop(sbi->s_mmp_tsk); failed_mount2: + rcu_read_lock(); + group_desc = rcu_dereference(sbi->s_group_desc); for (i = 0; i < db_count; i++) - brelse(sbi->s_group_desc[i]); - kvfree(sbi->s_group_desc); + brelse(group_desc[i]); + kvfree(group_desc); + rcu_read_unlock(); failed_mount: if (sbi->s_chksum_driver) crypto_free_shash(sbi->s_chksum_driver); diff --git a/fs/fat/inode.c b/fs/fat/inode.c index c81cfb79a339..5e87b9aa7ba6 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -653,6 +653,13 @@ static struct inode *fat_alloc_inode(struct super_block *sb) return NULL; init_rwsem(&ei->truncate_lock); + /* Zeroing to allow iput() even if partial initialized inode. */ + ei->mmu_private = 0; + ei->i_start = 0; + ei->i_logstart = 0; + ei->i_attrs = 0; + ei->i_pos = 0; + return &ei->vfs_inode; } @@ -1276,16 +1283,6 @@ out: return 0; } -static void fat_dummy_inode_init(struct inode *inode) -{ - /* Initialize this dummy inode to work as no-op. */ - MSDOS_I(inode)->mmu_private = 0; - MSDOS_I(inode)->i_start = 0; - MSDOS_I(inode)->i_logstart = 0; - MSDOS_I(inode)->i_attrs = 0; - MSDOS_I(inode)->i_pos = 0; -} - static int fat_read_root(struct inode *inode) { struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); @@ -1730,13 +1727,11 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, fat_inode = new_inode(sb); if (!fat_inode) goto out_fail; - fat_dummy_inode_init(fat_inode); sbi->fat_inode = fat_inode; fsinfo_inode = new_inode(sb); if (!fsinfo_inode) goto out_fail; - fat_dummy_inode_init(fsinfo_inode); fsinfo_inode->i_ino = MSDOS_FSINFO_INO; sbi->fsinfo_inode = fsinfo_inode; insert_inode_hash(fsinfo_inode); diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index f5d2d2340b44..16891f5364af 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -2031,10 +2031,8 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, rem += pipe->bufs[(pipe->curbuf + idx) & (pipe->buffers - 1)].len; ret = -EINVAL; - if (rem < len) { - pipe_unlock(pipe); - goto out; - } + if (rem < len) + goto out_free; rem = len; while (rem) { @@ -2052,7 +2050,9 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, pipe->curbuf = (pipe->curbuf + 1) & (pipe->buffers - 1); pipe->nrbufs--; } else { - ibuf->ops->get(pipe, ibuf); + if (!pipe_buf_get(pipe, ibuf)) + goto out_free; + *obuf = *ibuf; obuf->flags &= ~PIPE_BUF_FLAG_GIFT; obuf->len = rem; @@ -2075,13 +2075,13 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, ret = fuse_dev_do_write(fud, &cs, len); pipe_lock(pipe); +out_free: for (idx = 0; idx < nbuf; idx++) { struct pipe_buffer *buf = &bufs[idx]; buf->ops->release(pipe, buf); } pipe_unlock(pipe); -out: kfree(bufs); return ret; } diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 063fdfcf8275..32226dd19932 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -1245,7 +1245,7 @@ static int gfs2_atomic_open(struct inode *dir, struct dentry *dentry, if (!(*opened & FILE_OPENED)) return finish_no_open(file, d); dput(d); - return 0; + return excl && (flags & O_CREAT) ? -EEXIST : 0; } BUG_ON(d != NULL); diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 4d5a5a4cc017..addb0784dd1c 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -168,7 +168,7 @@ void __jbd2_log_wait_for_space(journal_t *journal) "journal space in %s\n", __func__, journal->j_devname); WARN_ON(1); - jbd2_journal_abort(journal, 0); + jbd2_journal_abort(journal, -EIO); } write_lock(&journal->j_state_lock); } else { diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index ebbd7d054cab..a7d12dd6d56e 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -797,7 +797,7 @@ start_journal_io: err = journal_submit_commit_record(journal, commit_transaction, &cbh, crc32_sum); if (err) - __jbd2_journal_abort_hard(journal); + jbd2_journal_abort(journal, err); } blk_finish_plug(&plug); @@ -890,7 +890,7 @@ start_journal_io: err = journal_submit_commit_record(journal, commit_transaction, &cbh, crc32_sum); if (err) - __jbd2_journal_abort_hard(journal); + jbd2_journal_abort(journal, err); } if (cbh) err = journal_wait_on_commit_record(journal, cbh); @@ -987,29 +987,33 @@ restart_loop: * it. */ /* - * A buffer which has been freed while still being journaled by - * a previous transaction. - */ - if (buffer_freed(bh)) { + * A buffer which has been freed while still being journaled + * by a previous transaction, refile the buffer to BJ_Forget of + * the running transaction. If the just committed transaction + * contains "add to orphan" operation, we can completely + * invalidate the buffer now. We are rather through in that + * since the buffer may be still accessible when blocksize < + * pagesize and it is attached to the last partial page. + */ + if (buffer_freed(bh) && !jh->b_next_transaction) { + struct address_space *mapping; + + clear_buffer_freed(bh); + clear_buffer_jbddirty(bh); + /* - * If the running transaction is the one containing - * "add to orphan" operation (b_next_transaction != - * NULL), we have to wait for that transaction to - * commit before we can really get rid of the buffer. - * So just clear b_modified to not confuse transaction - * credit accounting and refile the buffer to - * BJ_Forget of the running transaction. If the just - * committed transaction contains "add to orphan" - * operation, we can completely invalidate the buffer - * now. We are rather through in that since the - * buffer may be still accessible when blocksize < - * pagesize and it is attached to the last partial - * page. + * Block device buffers need to stay mapped all the + * time, so it is enough to clear buffer_jbddirty and + * buffer_freed bits. For the file mapping buffers (i.e. + * journalled data) we need to unmap buffer and clear + * more bits. We also need to be careful about the check + * because the data page mapping can get cleared under + * out hands, which alse need not to clear more bits + * because the page and buffers will be freed and can + * never be reused once we are done with them. */ - jh->b_modified = 0; - if (!jh->b_next_transaction) { - clear_buffer_freed(bh); - clear_buffer_jbddirty(bh); + mapping = READ_ONCE(bh->b_page->mapping); + if (mapping && !sb_is_blkdev_sb(mapping->host->i_sb)) { clear_buffer_mapped(bh); clear_buffer_new(bh); clear_buffer_req(bh); diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 9398d1b70545..d62435897d0d 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1656,6 +1656,11 @@ int jbd2_journal_load(journal_t *journal) journal->j_devname); return -EFSCORRUPTED; } + /* + * clear JBD2_ABORT flag initialized in journal_init_common + * here to update log tail information with the newest seq. + */ + journal->j_flags &= ~JBD2_ABORT; /* OK, we've finished with the dynamic journal bits: * reinitialise the dynamic contents of the superblock in memory @@ -1663,7 +1668,6 @@ int jbd2_journal_load(journal_t *journal) if (journal_reset(journal)) goto recovery_error; - journal->j_flags &= ~JBD2_ABORT; journal->j_flags |= JBD2_LOADED; return 0; @@ -2082,12 +2086,10 @@ static void __journal_abort_soft (journal_t *journal, int errno) __jbd2_journal_abort_hard(journal); - if (errno) { - jbd2_journal_update_sb_errno(journal); - write_lock(&journal->j_state_lock); - journal->j_flags |= JBD2_REC_ERR; - write_unlock(&journal->j_state_lock); - } + jbd2_journal_update_sb_errno(journal); + write_lock(&journal->j_state_lock); + journal->j_flags |= JBD2_REC_ERR; + write_unlock(&journal->j_state_lock); } /** @@ -2129,11 +2131,6 @@ static void __journal_abort_soft (journal_t *journal, int errno) * failure to disk. ext3_error, for example, now uses this * functionality. * - * Errors which originate from within the journaling layer will NOT - * supply an errno; a null errno implies that absolutely no further - * writes are done to the journal (unless there are any already in - * progress). - * */ void jbd2_journal_abort(journal_t *journal, int errno) diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index c34433432d47..3233e5ac9774 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -1041,8 +1041,8 @@ static bool jbd2_write_access_granted(handle_t *handle, struct buffer_head *bh, /* For undo access buffer must have data copied */ if (undo && !jh->b_committed_data) goto out; - if (jh->b_transaction != handle->h_transaction && - jh->b_next_transaction != handle->h_transaction) + if (READ_ONCE(jh->b_transaction) != handle->h_transaction && + READ_ONCE(jh->b_next_transaction) != handle->h_transaction) goto out; /* * There are two reasons for the barrier here: @@ -2223,14 +2223,16 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh, return -EBUSY; } /* - * OK, buffer won't be reachable after truncate. We just set - * j_next_transaction to the running transaction (if there is - * one) and mark buffer as freed so that commit code knows it - * should clear dirty bits when it is done with the buffer. + * OK, buffer won't be reachable after truncate. We just clear + * b_modified to not confuse transaction credit accounting, and + * set j_next_transaction to the running transaction (if there + * is one) and mark buffer as freed so that commit code knows + * it should clear dirty bits when it is done with the buffer. */ set_buffer_freed(bh); if (journal->j_running_transaction && buffer_jbddirty(bh)) jh->b_next_transaction = journal->j_running_transaction; + jh->b_modified = 0; jbd2_journal_put_journal_head(jh); spin_unlock(&journal->j_list_lock); jbd_unlock_bh_state(bh); @@ -2456,8 +2458,8 @@ void __jbd2_journal_refile_buffer(struct journal_head *jh) * our jh reference and thus __jbd2_journal_file_buffer() must not * take a new one. */ - jh->b_transaction = jh->b_next_transaction; - jh->b_next_transaction = NULL; + WRITE_ONCE(jh->b_transaction, jh->b_next_transaction); + WRITE_ONCE(jh->b_next_transaction, NULL); if (buffer_freed(bh)) jlist = BJ_Forget; else if (jh->b_modified) diff --git a/fs/namei.c b/fs/namei.c index 9f1aae507909..4a2b9371e00e 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1358,7 +1358,7 @@ static int follow_dotdot_rcu(struct nameidata *nd) nd->path.dentry = parent; nd->seq = seq; if (unlikely(!path_connected(&nd->path))) - return -ENOENT; + return -ECHILD; break; } else { struct mount *mnt = real_mount(nd->path.mnt); diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index b1daeafbea92..c3428767332c 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -89,7 +89,7 @@ config NFS_V4 config NFS_SWAP bool "Provide swap over NFS support" default n - depends on NFS_FS + depends on NFS_FS && SWAP select SUNRPC_SWAP help This option enables swapon to work on files located on NFS mounts. diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 2ac3d2527ad2..21e5fcbcb227 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -657,8 +657,6 @@ int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page, goto out_label_free; } - array = kmap(page); - status = nfs_readdir_alloc_pages(pages, array_size); if (status < 0) goto out_release_array; diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h index f4cd3c3e9fb7..0a4d2cbf512f 100644 --- a/fs/ocfs2/journal.h +++ b/fs/ocfs2/journal.h @@ -637,9 +637,11 @@ static inline void ocfs2_update_inode_fsync_trans(handle_t *handle, { struct ocfs2_inode_info *oi = OCFS2_I(inode); - oi->i_sync_tid = handle->h_transaction->t_tid; - if (datasync) - oi->i_datasync_tid = handle->h_transaction->t_tid; + if (!is_handle_aborted(handle)) { + oi->i_sync_tid = handle->h_transaction->t_tid; + if (datasync) + oi->i_datasync_tid = handle->h_transaction->t_tid; + } } #endif /* OCFS2_JOURNAL_H */ diff --git a/fs/pipe.c b/fs/pipe.c index 1e7263bb837a..6534470a6c19 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -178,9 +178,9 @@ EXPORT_SYMBOL(generic_pipe_buf_steal); * in the tee() system call, when we duplicate the buffers in one * pipe into another. */ -void generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) +bool generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { - page_cache_get(buf->page); + return try_get_page(buf->page); } EXPORT_SYMBOL(generic_pipe_buf_get); diff --git a/fs/reiserfs/stree.c b/fs/reiserfs/stree.c index 24cbe013240f..e3a4cbad9620 100644 --- a/fs/reiserfs/stree.c +++ b/fs/reiserfs/stree.c @@ -2249,7 +2249,8 @@ error_out: /* also releases the path */ unfix_nodes(&s_ins_balance); #ifdef REISERQUOTA_DEBUG - reiserfs_debug(th->t_super, REISERFS_DEBUG_CODE, + if (inode) + reiserfs_debug(th->t_super, REISERFS_DEBUG_CODE, "reiserquota insert_item(): freeing %u id=%u type=%c", quota_bytes, inode->i_uid, head2type(ih)); #endif diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index 519bf410e65b..f9796fd51531 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -1921,7 +1921,7 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent) if (!sbi->s_jdev) { SWARN(silent, s, "", "Cannot allocate memory for " "journal device name"); - goto error; + goto error_unlocked; } } #ifdef CONFIG_QUOTA diff --git a/fs/splice.c b/fs/splice.c index 8398974e1538..57ccc583a172 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -1876,7 +1876,11 @@ retry: * Get a reference to this pipe buffer, * so we can copy the contents over. */ - ibuf->ops->get(ipipe, ibuf); + if (!pipe_buf_get(ipipe, ibuf)) { + if (ret == 0) + ret = -EFAULT; + break; + } *obuf = *ibuf; /* @@ -1948,7 +1952,11 @@ static int link_pipe(struct pipe_inode_info *ipipe, * Get a reference to this pipe buffer, * so we can copy the contents over. */ - ibuf->ops->get(ipipe, ibuf); + if (!pipe_buf_get(ipipe, ibuf)) { + if (ret == 0) + ret = -EFAULT; + break; + } obuf = opipe->bufs + nbuf; *obuf = *ibuf; diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index ec6d6e90d0d2..e385d62fbc65 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -782,8 +782,9 @@ static int ubifs_do_bulk_read(struct ubifs_info *c, struct bu_info *bu, if (page_offset > end_index) break; - page = find_or_create_page(mapping, page_offset, - GFP_NOFS | __GFP_COLD); + page = pagecache_get_page(mapping, page_offset, + FGP_LOCK|FGP_ACCESSED|FGP_CREAT|FGP_NOWAIT, + GFP_NOFS | __GFP_COLD); if (!page) break; if (!PageUptodate(page)) diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 83edade218fa..ce2bb045b3fd 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -3,7 +3,8 @@ #include <asm/types.h> #include <linux/bits.h> -#define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long)) +#define BITS_PER_TYPE(type) (sizeof(type) * BITS_PER_BYTE) +#define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_TYPE(long)) extern unsigned int __sw_hweight8(unsigned int w); extern unsigned int __sw_hweight16(unsigned int w); diff --git a/include/linux/hid.h b/include/linux/hid.h index 5f3131885136..2149f650982e 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -451,7 +451,7 @@ struct hid_report_enum { }; #define HID_MIN_BUFFER_SIZE 64 /* make sure there is at least a packet size of space */ -#define HID_MAX_BUFFER_SIZE 4096 /* 4kb */ +#define HID_MAX_BUFFER_SIZE 8192 /* 8kb */ #define HID_CONTROL_FIFO_SIZE 256 /* to init devices with >100 reports */ #define HID_OUTPUT_FIFO_SIZE 64 diff --git a/include/linux/list_nulls.h b/include/linux/list_nulls.h index 444d2b1313bd..703928e4fd42 100644 --- a/include/linux/list_nulls.h +++ b/include/linux/list_nulls.h @@ -66,10 +66,10 @@ static inline void hlist_nulls_add_head(struct hlist_nulls_node *n, struct hlist_nulls_node *first = h->first; n->next = first; - n->pprev = &h->first; + WRITE_ONCE(n->pprev, &h->first); h->first = n; if (!is_a_nulls(first)) - first->pprev = &n->next; + WRITE_ONCE(first->pprev, &n->next); } static inline void __hlist_nulls_del(struct hlist_nulls_node *n) @@ -79,13 +79,13 @@ static inline void __hlist_nulls_del(struct hlist_nulls_node *n) WRITE_ONCE(*pprev, next); if (!is_a_nulls(next)) - next->pprev = pprev; + WRITE_ONCE(next->pprev, pprev); } static inline void hlist_nulls_del(struct hlist_nulls_node *n) { __hlist_nulls_del(n); - n->pprev = LIST_POISON2; + WRITE_ONCE(n->pprev, LIST_POISON2); } /** diff --git a/include/linux/mm.h b/include/linux/mm.h index 15f81b2b87ed..69fa3df9e712 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -488,6 +488,15 @@ static inline void get_huge_page_tail(struct page *page) extern bool __get_page_tail(struct page *page); +static inline int page_ref_count(struct page *page) +{ + return atomic_read(&page->_count); +} + +/* 127: arbitrary random number, small enough to assemble well */ +#define page_ref_zero_or_close_to_overflow(page) \ + ((unsigned int) atomic_read(&page->_count) + 127u <= 127u) + static inline void get_page(struct page *page) { if (unlikely(PageTail(page))) @@ -497,10 +506,22 @@ static inline void get_page(struct page *page) * Getting a normal page or the head of a compound page * requires to already have an elevated page->_count. */ - VM_BUG_ON_PAGE(atomic_read(&page->_count) <= 0, page); + VM_BUG_ON_PAGE(page_ref_zero_or_close_to_overflow(page), page); atomic_inc(&page->_count); } +static inline __must_check bool try_get_page(struct page *page) +{ + if (unlikely(PageTail(page))) + if (likely(__get_page_tail(page))) + return true; + + if (WARN_ON_ONCE(atomic_read(&page->_count) <= 0)) + return false; + atomic_inc(&page->_count); + return true; +} + static inline struct page *virt_to_head_page(const void *x) { struct page *page = virt_to_page(x); diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 24f5470d3944..0b28b65c12fb 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -112,9 +112,22 @@ struct pipe_buf_operations { /* * Get a reference to the pipe buffer. */ - void (*get)(struct pipe_inode_info *, struct pipe_buffer *); + bool (*get)(struct pipe_inode_info *, struct pipe_buffer *); }; +/** + * pipe_buf_get - get a reference to a pipe_buffer + * @pipe: the pipe that the buffer belongs to + * @buf: the buffer to get a reference to + * + * Return: %true if the reference was successfully obtained. + */ +static inline __must_check bool pipe_buf_get(struct pipe_inode_info *pipe, + struct pipe_buffer *buf) +{ + return buf->ops->get(pipe, buf); +} + /* Differs from PIPE_BUF in that PIPE_SIZE is the length of the actual memory allocation, whereas PIPE_BUF makes atomicity guarantees. */ #define PIPE_SIZE PAGE_SIZE @@ -137,7 +150,7 @@ struct pipe_inode_info *alloc_pipe_info(void); void free_pipe_info(struct pipe_inode_info *); /* Generic pipe buffer ops functions */ -void generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *); +bool generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *); int generic_pipe_buf_confirm(struct pipe_inode_info *, struct pipe_buffer *); int generic_pipe_buf_steal(struct pipe_inode_info *, struct pipe_buffer *); void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *); diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h index 1c33dd7da4a7..f35dc0a1d6eb 100644 --- a/include/linux/rculist_nulls.h +++ b/include/linux/rculist_nulls.h @@ -33,7 +33,7 @@ static inline void hlist_nulls_del_init_rcu(struct hlist_nulls_node *n) { if (!hlist_nulls_unhashed(n)) { __hlist_nulls_del(n); - n->pprev = NULL; + WRITE_ONCE(n->pprev, NULL); } } @@ -65,7 +65,7 @@ static inline void hlist_nulls_del_init_rcu(struct hlist_nulls_node *n) static inline void hlist_nulls_del_rcu(struct hlist_nulls_node *n) { __hlist_nulls_del(n); - n->pprev = LIST_POISON2; + WRITE_ONCE(n->pprev, LIST_POISON2); } /** @@ -93,10 +93,10 @@ static inline void hlist_nulls_add_head_rcu(struct hlist_nulls_node *n, struct hlist_nulls_node *first = h->first; n->next = first; - n->pprev = &h->first; + WRITE_ONCE(n->pprev, &h->first); rcu_assign_pointer(hlist_nulls_first_rcu(h), n); if (!is_a_nulls(first)) - first->pprev = &n->next; + WRITE_ONCE(first->pprev, &n->next); } /** * hlist_nulls_for_each_entry_rcu - iterate over rcu list of given type diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index 59160de702b6..99ae8ac65eca 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -85,6 +85,7 @@ struct fib_rules_ops { [FRA_OIFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, \ [FRA_PRIORITY] = { .type = NLA_U32 }, \ [FRA_FWMARK] = { .type = NLA_U32 }, \ + [FRA_TUN_ID] = { .type = NLA_U64 }, \ [FRA_FWMASK] = { .type = NLA_U32 }, \ [FRA_TABLE] = { .type = NLA_U32 }, \ [FRA_SUPPRESS_PREFIXLEN] = { .type = NLA_U32 }, \ diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index 62a462413081..a5a1a1650668 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -4,6 +4,7 @@ #include <linux/types.h> #include <linux/in6.h> #include <linux/siphash.h> +#include <linux/string.h> #include <uapi/linux/if_ether.h> /** @@ -185,4 +186,12 @@ static inline bool flow_keys_have_l4(struct flow_keys *keys) u32 flow_hash_from_keys(struct flow_keys *keys); +static inline void +flow_dissector_init_keys(struct flow_dissector_key_control *key_control, + struct flow_dissector_key_basic *key_basic) +{ + memset(key_control, 0, sizeof(*key_control)); + memset(key_basic, 0, sizeof(*key_basic)); +} + #endif diff --git a/include/scsi/iscsi_proto.h b/include/scsi/iscsi_proto.h index 1a2ae0862e23..c1260d80ef30 100644 --- a/include/scsi/iscsi_proto.h +++ b/include/scsi/iscsi_proto.h @@ -638,7 +638,6 @@ struct iscsi_reject { #define ISCSI_REASON_BOOKMARK_INVALID 9 #define ISCSI_REASON_BOOKMARK_NO_RESOURCES 10 #define ISCSI_REASON_NEGOTIATION_RESET 11 -#define ISCSI_REASON_WAITING_FOR_LOGOUT 12 /* Max. number of Key=Value pairs in a text message */ #define MAX_KEY_VALUE_PAIRS 8192 diff --git a/include/sound/rawmidi.h b/include/sound/rawmidi.h index 3b91ad5d5115..27b2c653d2f0 100644 --- a/include/sound/rawmidi.h +++ b/include/sound/rawmidi.h @@ -92,9 +92,9 @@ struct snd_rawmidi_substream { struct list_head list; /* list of all substream for given stream */ int stream; /* direction */ int number; /* substream number */ - unsigned int opened: 1, /* open flag */ - append: 1, /* append flag (merge more streams) */ - active_sensing: 1; /* send active sensing when close */ + bool opened; /* open flag */ + bool append; /* append flag (merge more streams) */ + bool active_sensing; /* send active sensing when close */ int use_count; /* use counter (for output) */ size_t bytes; struct snd_rawmidi *rmidi; diff --git a/ipc/sem.c b/ipc/sem.c index 9862c3d1c26d..9963ed351b43 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -2151,11 +2151,9 @@ void exit_sem(struct task_struct *tsk) ipc_assert_locked_object(&sma->sem_perm); list_del(&un->list_id); - /* we are the last process using this ulp, acquiring ulp->lock - * isn't required. Besides that, we are also protected against - * IPC_RMID as we hold sma->sem_perm lock now - */ + spin_lock(&ulp->lock); list_del_rcu(&un->list_proc); + spin_unlock(&ulp->lock); /* perform adjustments registered in un */ for (i = 0; i < sma->sem_nsems; i++) { diff --git a/kernel/audit.c b/kernel/audit.c index bdf0cf463815..84c445db5fe1 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -753,13 +753,11 @@ static void audit_log_feature_change(int which, u32 old_feature, u32 new_feature audit_log_end(ab); } -static int audit_set_feature(struct sk_buff *skb) +static int audit_set_feature(struct audit_features *uaf) { - struct audit_features *uaf; int i; BUILD_BUG_ON(AUDIT_LAST_FEATURE + 1 > ARRAY_SIZE(audit_feature_names)); - uaf = nlmsg_data(nlmsg_hdr(skb)); /* if there is ever a version 2 we should handle that here */ @@ -815,6 +813,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) { u32 seq; void *data; + int data_len; int err; struct audit_buffer *ab; u16 msg_type = nlh->nlmsg_type; @@ -838,6 +837,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) } seq = nlh->nlmsg_seq; data = nlmsg_data(nlh); + data_len = nlmsg_len(nlh); switch (msg_type) { case AUDIT_GET: { @@ -859,7 +859,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) struct audit_status s; memset(&s, 0, sizeof(s)); /* guard against past and future API changes */ - memcpy(&s, data, min_t(size_t, sizeof(s), nlmsg_len(nlh))); + memcpy(&s, data, min_t(size_t, sizeof(s), data_len)); if (s.mask & AUDIT_STATUS_ENABLED) { err = audit_set_enabled(s.enabled); if (err < 0) @@ -908,7 +908,9 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) return err; break; case AUDIT_SET_FEATURE: - err = audit_set_feature(skb); + if (data_len < sizeof(struct audit_features)) + return -EINVAL; + err = audit_set_feature(data); if (err) return err; break; @@ -920,6 +922,8 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) err = audit_filter_user(msg_type); if (err == 1) { /* match or error */ + char *str = data; + err = 0; if (msg_type == AUDIT_USER_TTY) { err = tty_audit_push_current(); @@ -928,19 +932,17 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) } mutex_unlock(&audit_cmd_mutex); audit_log_common_recv_msg(&ab, msg_type); - if (msg_type != AUDIT_USER_TTY) + if (msg_type != AUDIT_USER_TTY) { + /* ensure NULL termination */ + str[data_len - 1] = '\0'; audit_log_format(ab, " msg='%.*s'", AUDIT_MESSAGE_TEXT_MAX, - (char *)data); - else { - int size; - + str); + } else { audit_log_format(ab, " data="); - size = nlmsg_len(nlh); - if (size > 0 && - ((unsigned char *)data)[size - 1] == '\0') - size--; - audit_log_n_untrustedstring(ab, data, size); + if (data_len > 0 && str[data_len - 1] == '\0') + data_len--; + audit_log_n_untrustedstring(ab, str, data_len); } audit_set_portid(ab, NETLINK_CB(skb).portid); audit_log_end(ab); @@ -949,7 +951,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) break; case AUDIT_ADD_RULE: case AUDIT_DEL_RULE: - if (nlmsg_len(nlh) < sizeof(struct audit_rule_data)) + if (data_len < sizeof(struct audit_rule_data)) return -EINVAL; if (audit_enabled == AUDIT_LOCKED) { audit_log_common_recv_msg(&ab, AUDIT_CONFIG_CHANGE); @@ -958,7 +960,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) return -EPERM; } err = audit_rule_change(msg_type, NETLINK_CB(skb).portid, - seq, data, nlmsg_len(nlh)); + seq, data, data_len); break; case AUDIT_LIST_RULES: err = audit_list_rules_send(skb, seq); @@ -972,7 +974,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) case AUDIT_MAKE_EQUIV: { void *bufp = data; u32 sizes[2]; - size_t msglen = nlmsg_len(nlh); + size_t msglen = data_len; char *old, *new; err = -EINVAL; @@ -1049,7 +1051,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) memset(&s, 0, sizeof(s)); /* guard against past and future API changes */ - memcpy(&s, data, min_t(size_t, sizeof(s), nlmsg_len(nlh))); + memcpy(&s, data, min_t(size_t, sizeof(s), data_len)); /* check if new data is valid */ if ((s.enabled != 0 && s.enabled != 1) || (s.log_passwd != 0 && s.log_passwd != 1)) diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index cf7aa656b308..41a668a9d561 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -434,6 +434,7 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, bufp = data->buf; for (i = 0; i < data->field_count; i++) { struct audit_field *f = &entry->rule.fields[i]; + u32 f_val; err = -EINVAL; @@ -442,12 +443,12 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, goto exit_free; f->type = data->fields[i]; - f->val = data->values[i]; + f_val = data->values[i]; /* Support legacy tests for a valid loginuid */ - if ((f->type == AUDIT_LOGINUID) && (f->val == AUDIT_UID_UNSET)) { + if ((f->type == AUDIT_LOGINUID) && (f_val == AUDIT_UID_UNSET)) { f->type = AUDIT_LOGINUID_SET; - f->val = 0; + f_val = 0; entry->rule.pflags |= AUDIT_LOGINUID_LEGACY; } @@ -463,7 +464,7 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, case AUDIT_SUID: case AUDIT_FSUID: case AUDIT_OBJ_UID: - f->uid = make_kuid(current_user_ns(), f->val); + f->uid = make_kuid(current_user_ns(), f_val); if (!uid_valid(f->uid)) goto exit_free; break; @@ -472,11 +473,12 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, case AUDIT_SGID: case AUDIT_FSGID: case AUDIT_OBJ_GID: - f->gid = make_kgid(current_user_ns(), f->val); + f->gid = make_kgid(current_user_ns(), f_val); if (!gid_valid(f->gid)) goto exit_free; break; case AUDIT_ARCH: + f->val = f_val; entry->rule.arch_f = f; break; case AUDIT_SUBJ_USER: @@ -489,11 +491,13 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, case AUDIT_OBJ_TYPE: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: - str = audit_unpack_string(&bufp, &remain, f->val); - if (IS_ERR(str)) + str = audit_unpack_string(&bufp, &remain, f_val); + if (IS_ERR(str)) { + err = PTR_ERR(str); goto exit_free; - entry->rule.buflen += f->val; - + } + entry->rule.buflen += f_val; + f->lsm_str = str; err = security_audit_rule_init(f->type, f->op, str, (void **)&f->lsm_rule); /* Keep currently invalid fields around in case they @@ -502,68 +506,71 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, pr_warn("audit rule for LSM \'%s\' is invalid\n", str); err = 0; - } - if (err) { - kfree(str); + } else if (err) goto exit_free; - } else - f->lsm_str = str; break; case AUDIT_WATCH: - str = audit_unpack_string(&bufp, &remain, f->val); - if (IS_ERR(str)) + str = audit_unpack_string(&bufp, &remain, f_val); + if (IS_ERR(str)) { + err = PTR_ERR(str); goto exit_free; - entry->rule.buflen += f->val; - - err = audit_to_watch(&entry->rule, str, f->val, f->op); + } + err = audit_to_watch(&entry->rule, str, f_val, f->op); if (err) { kfree(str); goto exit_free; } + entry->rule.buflen += f_val; break; case AUDIT_DIR: - str = audit_unpack_string(&bufp, &remain, f->val); - if (IS_ERR(str)) + str = audit_unpack_string(&bufp, &remain, f_val); + if (IS_ERR(str)) { + err = PTR_ERR(str); goto exit_free; - entry->rule.buflen += f->val; - + } err = audit_make_tree(&entry->rule, str, f->op); kfree(str); if (err) goto exit_free; + entry->rule.buflen += f_val; break; case AUDIT_INODE: + f->val = f_val; err = audit_to_inode(&entry->rule, f); if (err) goto exit_free; break; case AUDIT_FILTERKEY: - if (entry->rule.filterkey || f->val > AUDIT_MAX_KEY_LEN) + if (entry->rule.filterkey || f_val > AUDIT_MAX_KEY_LEN) goto exit_free; - str = audit_unpack_string(&bufp, &remain, f->val); - if (IS_ERR(str)) + str = audit_unpack_string(&bufp, &remain, f_val); + if (IS_ERR(str)) { + err = PTR_ERR(str); goto exit_free; - entry->rule.buflen += f->val; + } + entry->rule.buflen += f_val; entry->rule.filterkey = str; break; case AUDIT_EXE: - if (entry->rule.exe || f->val > PATH_MAX) + if (entry->rule.exe || f_val > PATH_MAX) goto exit_free; - str = audit_unpack_string(&bufp, &remain, f->val); + str = audit_unpack_string(&bufp, &remain, f_val); if (IS_ERR(str)) { err = PTR_ERR(str); goto exit_free; } - entry->rule.buflen += f->val; - - audit_mark = audit_alloc_mark(&entry->rule, str, f->val); + audit_mark = audit_alloc_mark(&entry->rule, str, f_val); if (IS_ERR(audit_mark)) { kfree(str); err = PTR_ERR(audit_mark); goto exit_free; } + entry->rule.buflen += f_val; entry->rule.exe = audit_mark; break; + default: + f->val = f_val; + break; } } diff --git a/kernel/padata.c b/kernel/padata.c index 282b489a286d..0d7ec5fd520b 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -33,6 +33,8 @@ #define MAX_OBJ_NUM 1000 +static void padata_free_pd(struct parallel_data *pd); + static int padata_index_to_cpu(struct parallel_data *pd, int cpu_index) { int cpu, target_cpu; @@ -300,6 +302,7 @@ static void padata_serial_worker(struct work_struct *serial_work) struct padata_serial_queue *squeue; struct parallel_data *pd; LIST_HEAD(local_list); + int cnt; local_bh_disable(); squeue = container_of(serial_work, struct padata_serial_queue, work); @@ -309,6 +312,8 @@ static void padata_serial_worker(struct work_struct *serial_work) list_replace_init(&squeue->serial.list, &local_list); spin_unlock(&squeue->serial.lock); + cnt = 0; + while (!list_empty(&local_list)) { struct padata_priv *padata; @@ -318,9 +323,12 @@ static void padata_serial_worker(struct work_struct *serial_work) list_del_init(&padata->list); padata->serial(padata); - atomic_dec(&pd->refcnt); + cnt++; } local_bh_enable(); + + if (atomic_sub_and_test(cnt, &pd->refcnt)) + padata_free_pd(pd); } /** @@ -443,7 +451,7 @@ static struct parallel_data *padata_alloc_pd(struct padata_instance *pinst, setup_timer(&pd->timer, padata_reorder_timer, (unsigned long)pd); atomic_set(&pd->seq_nr, -1); atomic_set(&pd->reorder_objects, 0); - atomic_set(&pd->refcnt, 0); + atomic_set(&pd->refcnt, 1); pd->pinst = pinst; spin_lock_init(&pd->lock); @@ -468,31 +476,6 @@ static void padata_free_pd(struct parallel_data *pd) kfree(pd); } -/* Flush all objects out of the padata queues. */ -static void padata_flush_queues(struct parallel_data *pd) -{ - int cpu; - struct padata_parallel_queue *pqueue; - struct padata_serial_queue *squeue; - - for_each_cpu(cpu, pd->cpumask.pcpu) { - pqueue = per_cpu_ptr(pd->pqueue, cpu); - flush_work(&pqueue->work); - } - - del_timer_sync(&pd->timer); - - if (atomic_read(&pd->reorder_objects)) - padata_reorder(pd); - - for_each_cpu(cpu, pd->cpumask.cbcpu) { - squeue = per_cpu_ptr(pd->squeue, cpu); - flush_work(&squeue->work); - } - - BUG_ON(atomic_read(&pd->refcnt) != 0); -} - static void __padata_start(struct padata_instance *pinst) { pinst->flags |= PADATA_INIT; @@ -506,10 +489,6 @@ static void __padata_stop(struct padata_instance *pinst) pinst->flags &= ~PADATA_INIT; synchronize_rcu(); - - get_online_cpus(); - padata_flush_queues(pinst->pd); - put_online_cpus(); } /* Replace the internal control structure with a new one. */ @@ -530,8 +509,8 @@ static void padata_replace(struct padata_instance *pinst, if (!cpumask_equal(pd_old->cpumask.cbcpu, pd_new->cpumask.cbcpu)) notification_mask |= PADATA_CPU_SERIAL; - padata_flush_queues(pd_old); - padata_free_pd(pd_old); + if (atomic_dec_and_test(&pd_old->refcnt)) + padata_free_pd(pd_old); if (notification_mask) blocking_notifier_call_chain(&pinst->cpumask_change_notifier, diff --git a/kernel/signal.c b/kernel/signal.c index 7e4a4b199a11..90a94e54db09 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -373,27 +373,32 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimi { struct sigqueue *q = NULL; struct user_struct *user; + int sigpending; /* * Protect access to @t credentials. This can go away when all * callers hold rcu read lock. + * + * NOTE! A pending signal will hold on to the user refcount, + * and we get/put the refcount only when the sigpending count + * changes from/to zero. */ rcu_read_lock(); - user = get_uid(__task_cred(t)->user); - atomic_inc(&user->sigpending); + user = __task_cred(t)->user; + sigpending = atomic_inc_return(&user->sigpending); + if (sigpending == 1) + get_uid(user); rcu_read_unlock(); - if (override_rlimit || - atomic_read(&user->sigpending) <= - task_rlimit(t, RLIMIT_SIGPENDING)) { + if (override_rlimit || likely(sigpending <= task_rlimit(t, RLIMIT_SIGPENDING))) { q = kmem_cache_alloc(sigqueue_cachep, flags); } else { print_dropped_signal(sig); } if (unlikely(q == NULL)) { - atomic_dec(&user->sigpending); - free_uid(user); + if (atomic_dec_and_test(&user->sigpending)) + free_uid(user); } else { INIT_LIST_HEAD(&q->list); q->flags = 0; @@ -407,8 +412,8 @@ static void __sigqueue_free(struct sigqueue *q) { if (q->flags & SIGQUEUE_PREALLOC) return; - atomic_dec(&q->user->sigpending); - free_uid(q->user); + if (atomic_dec_and_test(&q->user->sigpending)) + free_uid(q->user); kmem_cache_free(sigqueue_cachep, q); } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 6176dc89b32c..06efd18bf3e3 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -5749,12 +5749,16 @@ static void buffer_pipe_buf_release(struct pipe_inode_info *pipe, buf->private = 0; } -static void buffer_pipe_buf_get(struct pipe_inode_info *pipe, +static bool buffer_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct buffer_ref *ref = (struct buffer_ref *)buf->private; + if (ref->ref > INT_MAX/2) + return false; + ref->ref++; + return true; } /* Pipe buffer operations for a buffer. */ diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index 8be66a2b0cac..6524920c6ebc 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -121,9 +121,10 @@ static void *trigger_next(struct seq_file *m, void *t, loff_t *pos) { struct trace_event_file *event_file = event_file_data(m->private); - if (t == SHOW_AVAILABLE_TRIGGERS) + if (t == SHOW_AVAILABLE_TRIGGERS) { + (*pos)++; return NULL; - + } return seq_list_next(t, &event_file->triggers, pos); } diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c index 6cf935316769..a2081a7f0c2c 100644 --- a/kernel/trace/trace_stat.c +++ b/kernel/trace/trace_stat.c @@ -302,7 +302,7 @@ static int init_stat_file(struct stat_session *session) int register_stat_tracer(struct tracer_stat *trace) { struct stat_session *session, *node; - int ret; + int ret = -EINVAL; if (!trace) return -EINVAL; @@ -313,17 +313,15 @@ int register_stat_tracer(struct tracer_stat *trace) /* Already registered? */ mutex_lock(&all_stat_sessions_mutex); list_for_each_entry(node, &all_stat_sessions, session_list) { - if (node->ts == trace) { - mutex_unlock(&all_stat_sessions_mutex); - return -EINVAL; - } + if (node->ts == trace) + goto out; } - mutex_unlock(&all_stat_sessions_mutex); + ret = -ENOMEM; /* Init the session */ session = kzalloc(sizeof(*session), GFP_KERNEL); if (!session) - return -ENOMEM; + goto out; session->ts = trace; INIT_LIST_HEAD(&session->session_list); @@ -332,15 +330,16 @@ int register_stat_tracer(struct tracer_stat *trace) ret = init_stat_file(session); if (ret) { destroy_session(session); - return ret; + goto out; } + ret = 0; /* Register */ - mutex_lock(&all_stat_sessions_mutex); list_add_tail(&session->session_list, &all_stat_sessions); + out: mutex_unlock(&all_stat_sessions_mutex); - return 0; + return ret; } void unregister_stat_tracer(struct tracer_stat *trace) diff --git a/lib/scatterlist.c b/lib/scatterlist.c index 0b86b7992f93..1875c09eede9 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -317,7 +317,7 @@ int __sg_alloc_table(struct sg_table *table, unsigned int nents, if (prv) table->nents = ++table->orig_nents; - return -ENOMEM; + return -ENOMEM; } sg_init_table(sg, alloc_size); @@ -126,8 +126,12 @@ retry: } } - if (flags & FOLL_GET) - get_page_foll(page); + if (flags & FOLL_GET) { + if (unlikely(!try_get_page_foll(page))) { + page = ERR_PTR(-ENOMEM); + goto out; + } + } if (flags & FOLL_TOUCH) { if ((flags & FOLL_WRITE) && !pte_dirty(pte) && !PageDirty(page)) @@ -289,7 +293,10 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address, goto unmap; *page = pte_page(*pte); } - get_page(*page); + if (unlikely(!try_get_page(*page))) { + ret = -ENOMEM; + goto unmap; + } out: ret = 0; unmap: @@ -1053,6 +1060,20 @@ struct page *get_dump_page(unsigned long addr) */ #ifdef CONFIG_HAVE_GENERIC_RCU_GUP +/* + * Return the compund head page with ref appropriately incremented, + * or NULL if that failed. + */ +static inline struct page *try_get_compound_head(struct page *page, int refs) +{ + struct page *head = compound_head(page); + if (WARN_ON_ONCE(atomic_read(&head->_count) < 0)) + return NULL; + if (unlikely(!page_cache_add_speculative(head, refs))) + return NULL; + return head; +} + #ifdef __HAVE_ARCH_PTE_SPECIAL static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) @@ -1083,6 +1104,9 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, VM_BUG_ON(!pfn_valid(pte_pfn(pte))); page = pte_page(pte); + if (WARN_ON_ONCE(page_ref_count(page) < 0)) + goto pte_unmap; + if (!page_cache_get_speculative(page)) goto pte_unmap; @@ -1130,18 +1154,17 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, return 0; refs = 0; - head = pmd_page(orig); - page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT); + page = pmd_page(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); tail = page; do { - VM_BUG_ON_PAGE(compound_head(page) != head, page); pages[*nr] = page; (*nr)++; page++; refs++; } while (addr += PAGE_SIZE, addr != end); - if (!page_cache_add_speculative(head, refs)) { + head = try_get_compound_head(pmd_page(orig), refs); + if (!head) { *nr -= refs; return 0; } @@ -1177,18 +1200,17 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, return 0; refs = 0; - head = pud_page(orig); - page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT); + page = pud_page(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT); tail = page; do { - VM_BUG_ON_PAGE(compound_head(page) != head, page); pages[*nr] = page; (*nr)++; page++; refs++; } while (addr += PAGE_SIZE, addr != end); - if (!page_cache_add_speculative(head, refs)) { + head = try_get_compound_head(pud_page(orig), refs); + if (!head) { *nr -= refs; return 0; } @@ -1220,18 +1242,17 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr, return 0; refs = 0; - head = pgd_page(orig); - page = head + ((addr & ~PGDIR_MASK) >> PAGE_SHIFT); + page = pgd_page(orig) + ((addr & ~PGDIR_MASK) >> PAGE_SHIFT); tail = page; do { - VM_BUG_ON_PAGE(compound_head(page) != head, page); pages[*nr] = page; (*nr)++; page++; refs++; } while (addr += PAGE_SIZE, addr != end); - if (!page_cache_add_speculative(head, refs)) { + head = try_get_compound_head(pgd_page(orig), refs); + if (!head) { *nr -= refs; return 0; } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index fd932e7a25dd..3a1501e85483 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3886,6 +3886,7 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long vaddr = *position; unsigned long remainder = *nr_pages; struct hstate *h = hstate_vma(vma); + int err = -EFAULT; while (vaddr < vma->vm_end && remainder) { pte_t *pte; @@ -3957,6 +3958,19 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, pfn_offset = (vaddr & ~huge_page_mask(h)) >> PAGE_SHIFT; page = pte_page(huge_ptep_get(pte)); + + /* + * Instead of doing 'try_get_page_foll()' below in the same_page + * loop, just check the count once here. + */ + if (unlikely(page_count(page) <= 0)) { + if (pages) { + spin_unlock(ptl); + remainder = 0; + err = -ENOMEM; + break; + } + } same_page: if (pages) { pages[i] = mem_map_offset(page, pfn_offset); @@ -3983,7 +3997,7 @@ same_page: *nr_pages = remainder; *position = vaddr; - return i ? i : -EFAULT; + return i ? i : err; } unsigned long hugetlb_change_protection(struct vm_area_struct *vma, diff --git a/mm/internal.h b/mm/internal.h index f63f4393d633..d83afc995a49 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -81,7 +81,8 @@ static inline void __get_page_tail_foll(struct page *page, * speculative page access (like in * page_cache_get_speculative()) on tail pages. */ - VM_BUG_ON_PAGE(atomic_read(&compound_head(page)->_count) <= 0, page); + VM_BUG_ON_PAGE(page_ref_zero_or_close_to_overflow(compound_head(page)), + page); if (get_page_head) atomic_inc(&compound_head(page)->_count); get_huge_page_tail(page); @@ -106,11 +107,34 @@ static inline void get_page_foll(struct page *page) * Getting a normal page or the head of a compound page * requires to already have an elevated page->_count. */ - VM_BUG_ON_PAGE(atomic_read(&page->_count) <= 0, page); + VM_BUG_ON_PAGE(page_ref_zero_or_close_to_overflow(page), page); atomic_inc(&page->_count); } } +static inline __must_check bool try_get_page_foll(struct page *page) +{ + if (unlikely(PageTail(page))) { + if (WARN_ON_ONCE(atomic_read(&compound_head(page)->_count) <= 0)) + return false; + /* + * This is safe only because + * __split_huge_page_refcount() can't run under + * get_page_foll() because we hold the proper PT lock. + */ + __get_page_tail_foll(page, true); + } else { + /* + * Getting a normal page or the head of a compound page + * requires to already have an elevated page->_count. + */ + if (WARN_ON_ONCE(atomic_read(&page->_count) <= 0)) + return false; + atomic_inc(&page->_count); + } + return true; +} + extern unsigned long highest_memmap_pfn; /* diff --git a/mm/slub.c b/mm/slub.c index 8f5dcb0ac24f..cb9069ccf67c 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2932,6 +2932,15 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, if (unlikely(!object)) { /* + * We may have removed an object from c->freelist using + * the fastpath in the previous iteration; in that case, + * c->tid has not been bumped yet. + * Since ___slab_alloc() may reenable interrupts while + * allocating memory, we should bump c->tid now. + */ + c->tid = next_tid(c->tid); + + /* * Invoking slow path likely have side-effect * of re-populating per CPU c->freelist */ diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 912d9c36fb1c..caea5bb38d4b 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -135,7 +135,7 @@ static void batadv_iv_ogm_orig_free(struct batadv_orig_node *orig_node) * Returns 0 on success, a negative error code otherwise. */ static int batadv_iv_ogm_orig_add_if(struct batadv_orig_node *orig_node, - int max_if_num) + unsigned int max_if_num) { void *data_ptr; size_t old_size; @@ -155,10 +155,8 @@ static int batadv_iv_ogm_orig_add_if(struct batadv_orig_node *orig_node, orig_node->bat_iv.bcast_own = data_ptr; data_ptr = kmalloc_array(max_if_num, sizeof(u8), GFP_ATOMIC); - if (!data_ptr) { - kfree(orig_node->bat_iv.bcast_own); + if (!data_ptr) goto unlock; - } memcpy(data_ptr, orig_node->bat_iv.bcast_own_sum, (max_if_num - 1) * sizeof(u8)); @@ -183,9 +181,11 @@ unlock: * Returns 0 on success, a negative error code otherwise. */ static int batadv_iv_ogm_orig_del_if(struct batadv_orig_node *orig_node, - int max_if_num, int del_if_num) + unsigned int max_if_num, + unsigned int del_if_num) { - int chunk_size, ret = -ENOMEM, if_offset; + int ret = -ENOMEM; + size_t chunk_size, if_offset; void *data_ptr = NULL; spin_lock_bh(&orig_node->bat_iv.ogm_cnt_lock); @@ -203,8 +203,9 @@ static int batadv_iv_ogm_orig_del_if(struct batadv_orig_node *orig_node, memcpy(data_ptr, orig_node->bat_iv.bcast_own, del_if_num * chunk_size); /* copy second part */ + if_offset = (del_if_num + 1) * chunk_size; memcpy((char *)data_ptr + del_if_num * chunk_size, - orig_node->bat_iv.bcast_own + ((del_if_num + 1) * chunk_size), + (uint8_t *)orig_node->bat_iv.bcast_own + if_offset, (max_if_num - del_if_num) * chunk_size); free_bcast_own: @@ -252,7 +253,8 @@ static struct batadv_orig_node * batadv_iv_ogm_orig_get(struct batadv_priv *bat_priv, const u8 *addr) { struct batadv_orig_node *orig_node; - int size, hash_added; + int hash_added; + size_t size; orig_node = batadv_orig_hash_find(bat_priv, addr); if (orig_node) @@ -314,14 +316,18 @@ static int batadv_iv_ogm_iface_enable(struct batadv_hard_iface *hard_iface) unsigned char *ogm_buff; u32 random_seqno; + mutex_lock(&hard_iface->bat_iv.ogm_buff_mutex); + /* randomize initial seqno to avoid collision */ get_random_bytes(&random_seqno, sizeof(random_seqno)); atomic_set(&hard_iface->bat_iv.ogm_seqno, random_seqno); hard_iface->bat_iv.ogm_buff_len = BATADV_OGM_HLEN; ogm_buff = kmalloc(hard_iface->bat_iv.ogm_buff_len, GFP_ATOMIC); - if (!ogm_buff) + if (!ogm_buff) { + mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex); return -ENOMEM; + } hard_iface->bat_iv.ogm_buff = ogm_buff; @@ -333,36 +339,60 @@ static int batadv_iv_ogm_iface_enable(struct batadv_hard_iface *hard_iface) batadv_ogm_packet->reserved = 0; batadv_ogm_packet->tq = BATADV_TQ_MAX_VALUE; + mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex); + return 0; } static void batadv_iv_ogm_iface_disable(struct batadv_hard_iface *hard_iface) { + mutex_lock(&hard_iface->bat_iv.ogm_buff_mutex); + kfree(hard_iface->bat_iv.ogm_buff); hard_iface->bat_iv.ogm_buff = NULL; + + mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex); } static void batadv_iv_ogm_iface_update_mac(struct batadv_hard_iface *hard_iface) { struct batadv_ogm_packet *batadv_ogm_packet; - unsigned char *ogm_buff = hard_iface->bat_iv.ogm_buff; + void *ogm_buff; - batadv_ogm_packet = (struct batadv_ogm_packet *)ogm_buff; + mutex_lock(&hard_iface->bat_iv.ogm_buff_mutex); + + ogm_buff = hard_iface->bat_iv.ogm_buff; + if (!ogm_buff) + goto unlock; + + batadv_ogm_packet = ogm_buff; ether_addr_copy(batadv_ogm_packet->orig, hard_iface->net_dev->dev_addr); ether_addr_copy(batadv_ogm_packet->prev_sender, hard_iface->net_dev->dev_addr); + +unlock: + mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex); } static void batadv_iv_ogm_primary_iface_set(struct batadv_hard_iface *hard_iface) { struct batadv_ogm_packet *batadv_ogm_packet; - unsigned char *ogm_buff = hard_iface->bat_iv.ogm_buff; + void *ogm_buff; - batadv_ogm_packet = (struct batadv_ogm_packet *)ogm_buff; + mutex_lock(&hard_iface->bat_iv.ogm_buff_mutex); + + ogm_buff = hard_iface->bat_iv.ogm_buff; + if (!ogm_buff) + goto unlock; + + batadv_ogm_packet = ogm_buff; batadv_ogm_packet->flags = BATADV_PRIMARIES_FIRST_HOP; batadv_ogm_packet->ttl = BATADV_TTL; + +unlock: + mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex); } /* when do we schedule our own ogm to be sent */ @@ -395,14 +425,19 @@ static u8 batadv_hop_penalty(u8 tq, const struct batadv_priv *bat_priv) return new_tq; } -/* is there another aggregated packet here? */ -static bool batadv_iv_ogm_aggr_packet(int buff_pos, int packet_len, - __be16 tvlv_len) +static bool +batadv_iv_ogm_aggr_packet(int buff_pos, int packet_len, + const struct batadv_ogm_packet *ogm_packet) { int next_buff_pos = 0; - next_buff_pos += buff_pos + BATADV_OGM_HLEN; - next_buff_pos += ntohs(tvlv_len); + /* check if there is enough space for the header */ + next_buff_pos += buff_pos + sizeof(*ogm_packet); + if (next_buff_pos > packet_len) + return false; + + /* check if there is enough space for the optional TVLV */ + next_buff_pos += ntohs(ogm_packet->tvlv_len); return (next_buff_pos <= packet_len) && (next_buff_pos <= BATADV_MAX_AGGREGATION_BYTES); @@ -430,7 +465,7 @@ static void batadv_iv_ogm_send_to_if(struct batadv_forw_packet *forw_packet, /* adjust all flags and log packets */ while (batadv_iv_ogm_aggr_packet(buff_pos, forw_packet->packet_len, - batadv_ogm_packet->tvlv_len)) { + batadv_ogm_packet)) { /* we might have aggregated direct link packets with an * ordinary base packet */ @@ -871,7 +906,7 @@ batadv_iv_ogm_slide_own_bcast_window(struct batadv_hard_iface *hard_iface) u32 i; size_t word_index; u8 *w; - int if_num; + unsigned int if_num; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; @@ -892,7 +927,11 @@ batadv_iv_ogm_slide_own_bcast_window(struct batadv_hard_iface *hard_iface) } } -static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface) +/** + * batadv_iv_ogm_schedule_buff() - schedule submission of hardif ogm buffer + * @hard_iface: interface whose ogm buffer should be transmitted + */ +static void batadv_iv_ogm_schedule_buff(struct batadv_hard_iface *hard_iface) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); unsigned char **ogm_buff = &hard_iface->bat_iv.ogm_buff; @@ -903,6 +942,12 @@ static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface) u16 tvlv_len = 0; unsigned long send_time; + lockdep_assert_held(&hard_iface->bat_iv.ogm_buff_mutex); + + /* interface already disabled by batadv_iv_ogm_iface_disable */ + if (!*ogm_buff) + return; + primary_if = batadv_primary_if_get_selected(bat_priv); if (hard_iface == primary_if) { @@ -954,6 +999,17 @@ out: batadv_hardif_free_ref(primary_if); } +static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface) +{ + if (hard_iface->if_status == BATADV_IF_NOT_IN_USE || + hard_iface->if_status == BATADV_IF_TO_BE_REMOVED) + return; + + mutex_lock(&hard_iface->bat_iv.ogm_buff_mutex); + batadv_iv_ogm_schedule_buff(hard_iface); + mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex); +} + /** * batadv_iv_ogm_orig_update - use OGM to update corresponding data in an * originator @@ -982,7 +1038,7 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv, struct batadv_neigh_node *tmp_neigh_node = NULL; struct batadv_neigh_node *router = NULL; struct batadv_orig_node *orig_node_tmp; - int if_num; + unsigned int if_num; u8 sum_orig, sum_neigh; u8 *neigh_addr; u8 tq_avg; @@ -1140,9 +1196,10 @@ static int batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node, u8 total_count; u8 orig_eq_count, neigh_rq_count, neigh_rq_inv, tq_own; unsigned int neigh_rq_inv_cube, neigh_rq_max_cube; - int tq_asym_penalty, inv_asym_penalty, if_num, ret = 0; + int if_num, ret = 0; + unsigned int tq_asym_penalty, inv_asym_penalty; unsigned int combined_tq; - int tq_iface_penalty; + unsigned int tq_iface_penalty; /* find corresponding one hop neighbor */ rcu_read_lock(); @@ -1179,7 +1236,7 @@ static int batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node, orig_node->last_seen = jiffies; /* find packet count of corresponding one hop neighbor */ - spin_lock_bh(&orig_node->bat_iv.ogm_cnt_lock); + spin_lock_bh(&orig_neigh_node->bat_iv.ogm_cnt_lock); if_num = if_incoming->if_num; orig_eq_count = orig_neigh_node->bat_iv.bcast_own_sum[if_num]; neigh_ifinfo = batadv_neigh_ifinfo_new(neigh_node, if_outgoing); @@ -1189,7 +1246,7 @@ static int batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node, } else { neigh_rq_count = 0; } - spin_unlock_bh(&orig_node->bat_iv.ogm_cnt_lock); + spin_unlock_bh(&orig_neigh_node->bat_iv.ogm_cnt_lock); /* pay attention to not get a value bigger than 100 % */ if (orig_eq_count > neigh_rq_count) @@ -1646,9 +1703,9 @@ static void batadv_iv_ogm_process(const struct sk_buff *skb, int ogm_offset, if (is_my_orig) { unsigned long *word; - int offset; + size_t offset; s32 bit_pos; - s16 if_num; + unsigned int if_num; u8 *weight; orig_neigh_node = batadv_iv_ogm_orig_get(bat_priv, @@ -1748,7 +1805,7 @@ static int batadv_iv_ogm_receive(struct sk_buff *skb, /* unpack the aggregated packets and process them one by one */ while (batadv_iv_ogm_aggr_packet(ogm_offset, skb_headlen(skb), - ogm_packet->tvlv_len)) { + ogm_packet)) { batadv_iv_ogm_process(skb, ogm_offset, if_incoming); ogm_offset += BATADV_OGM_HLEN; diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index c5208136e3fc..cea7fdeac5aa 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -129,7 +129,19 @@ batadv_backbone_gw_free_ref(struct batadv_bla_backbone_gw *backbone_gw) /* finally deinitialize the claim */ static void batadv_claim_release(struct batadv_bla_claim *claim) { - batadv_backbone_gw_free_ref(claim->backbone_gw); + struct batadv_bla_backbone_gw *old_backbone_gw; + + spin_lock_bh(&claim->backbone_lock); + old_backbone_gw = claim->backbone_gw; + claim->backbone_gw = NULL; + spin_unlock_bh(&claim->backbone_lock); + + spin_lock_bh(&old_backbone_gw->crc_lock); + old_backbone_gw->crc ^= crc16(0, claim->addr, ETH_ALEN); + spin_unlock_bh(&old_backbone_gw->crc_lock); + + batadv_backbone_gw_free_ref(old_backbone_gw); + kfree_rcu(claim, rcu); } @@ -256,7 +268,9 @@ batadv_bla_del_backbone_claims(struct batadv_bla_backbone_gw *backbone_gw) } /* all claims gone, initialize CRC */ + spin_lock_bh(&backbone_gw->crc_lock); backbone_gw->crc = BATADV_BLA_CRC_INIT; + spin_unlock_bh(&backbone_gw->crc_lock); } /** @@ -352,9 +366,12 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, u8 *mac, break; } - if (vid & BATADV_VLAN_HAS_TAG) + if (vid & BATADV_VLAN_HAS_TAG) { skb = vlan_insert_tag(skb, htons(ETH_P_8021Q), vid & VLAN_VID_MASK); + if (!skb) + goto out; + } skb_reset_mac_header(skb); skb->protocol = eth_type_trans(skb, soft_iface); @@ -404,6 +421,7 @@ batadv_bla_get_backbone_gw(struct batadv_priv *bat_priv, u8 *orig, entry->lasttime = jiffies; entry->crc = BATADV_BLA_CRC_INIT; entry->bat_priv = bat_priv; + spin_lock_init(&entry->crc_lock); atomic_set(&entry->request_sent, 0); atomic_set(&entry->wait_periods, 0); ether_addr_copy(entry->orig, orig); @@ -553,7 +571,9 @@ static void batadv_bla_send_announce(struct batadv_priv *bat_priv, __be16 crc; memcpy(mac, batadv_announce_mac, 4); + spin_lock_bh(&backbone_gw->crc_lock); crc = htons(backbone_gw->crc); + spin_unlock_bh(&backbone_gw->crc_lock); memcpy(&mac[4], &crc, 2); batadv_bla_send_claim(bat_priv, mac, backbone_gw->vid, @@ -571,8 +591,10 @@ static void batadv_bla_add_claim(struct batadv_priv *bat_priv, const u8 *mac, const unsigned short vid, struct batadv_bla_backbone_gw *backbone_gw) { + struct batadv_bla_backbone_gw *old_backbone_gw; struct batadv_bla_claim *claim; struct batadv_bla_claim search_claim; + bool remove_crc = false; int hash_added; ether_addr_copy(search_claim.addr, mac); @@ -586,8 +608,10 @@ static void batadv_bla_add_claim(struct batadv_priv *bat_priv, return; ether_addr_copy(claim->addr, mac); + spin_lock_init(&claim->backbone_lock); claim->vid = vid; claim->lasttime = jiffies; + atomic_inc(&backbone_gw->refcount); claim->backbone_gw = backbone_gw; atomic_set(&claim->refcount, 2); @@ -614,20 +638,55 @@ static void batadv_bla_add_claim(struct batadv_priv *bat_priv, "bla_add_claim(): changing ownership for %pM, vid %d\n", mac, BATADV_PRINT_VID(vid)); - claim->backbone_gw->crc ^= crc16(0, claim->addr, ETH_ALEN); - batadv_backbone_gw_free_ref(claim->backbone_gw); + remove_crc = true; } - /* set (new) backbone gw */ + + /* replace backbone_gw atomically and adjust reference counters */ + spin_lock_bh(&claim->backbone_lock); + old_backbone_gw = claim->backbone_gw; atomic_inc(&backbone_gw->refcount); claim->backbone_gw = backbone_gw; + spin_unlock_bh(&claim->backbone_lock); + + if (remove_crc) { + /* remove claim address from old backbone_gw */ + spin_lock_bh(&old_backbone_gw->crc_lock); + old_backbone_gw->crc ^= crc16(0, claim->addr, ETH_ALEN); + spin_unlock_bh(&old_backbone_gw->crc_lock); + } + batadv_backbone_gw_free_ref(old_backbone_gw); + + /* add claim address to new backbone_gw */ + spin_lock_bh(&backbone_gw->crc_lock); backbone_gw->crc ^= crc16(0, claim->addr, ETH_ALEN); + spin_unlock_bh(&backbone_gw->crc_lock); backbone_gw->lasttime = jiffies; claim_free_ref: batadv_claim_free_ref(claim); } +/** + * batadv_bla_claim_get_backbone_gw - Get valid reference for backbone_gw of + * claim + * @claim: claim whose backbone_gw should be returned + * + * Return: valid reference to claim::backbone_gw + */ +static struct batadv_bla_backbone_gw * +batadv_bla_claim_get_backbone_gw(struct batadv_bla_claim *claim) +{ + struct batadv_bla_backbone_gw *backbone_gw; + + spin_lock_bh(&claim->backbone_lock); + backbone_gw = claim->backbone_gw; + atomic_inc(&backbone_gw->refcount); + spin_unlock_bh(&claim->backbone_lock); + + return backbone_gw; +} + /* Delete a claim from the claim hash which has the * given mac address and vid. */ @@ -635,6 +694,8 @@ static void batadv_bla_del_claim(struct batadv_priv *bat_priv, const u8 *mac, const unsigned short vid) { struct batadv_bla_claim search_claim, *claim; + struct batadv_bla_claim *claim_removed_entry; + struct hlist_node *claim_removed_node; ether_addr_copy(search_claim.addr, mac); search_claim.vid = vid; @@ -645,12 +706,18 @@ static void batadv_bla_del_claim(struct batadv_priv *bat_priv, batadv_dbg(BATADV_DBG_BLA, bat_priv, "bla_del_claim(): %pM, vid %d\n", mac, BATADV_PRINT_VID(vid)); - batadv_hash_remove(bat_priv->bla.claim_hash, batadv_compare_claim, - batadv_choose_claim, claim); - batadv_claim_free_ref(claim); /* reference from the hash is gone */ + claim_removed_node = batadv_hash_remove(bat_priv->bla.claim_hash, + batadv_compare_claim, + batadv_choose_claim, claim); + if (!claim_removed_node) + goto free_claim; - claim->backbone_gw->crc ^= crc16(0, claim->addr, ETH_ALEN); + /* reference from the hash is gone */ + claim_removed_entry = hlist_entry(claim_removed_node, + struct batadv_bla_claim, hash_entry); + batadv_claim_free_ref(claim_removed_entry); +free_claim: /* don't need the reference from hash_find() anymore */ batadv_claim_free_ref(claim); } @@ -660,7 +727,7 @@ static int batadv_handle_announce(struct batadv_priv *bat_priv, u8 *an_addr, u8 *backbone_addr, unsigned short vid) { struct batadv_bla_backbone_gw *backbone_gw; - u16 crc; + u16 backbone_crc, crc; if (memcmp(an_addr, batadv_announce_mac, 4) != 0) return 0; @@ -679,12 +746,16 @@ static int batadv_handle_announce(struct batadv_priv *bat_priv, u8 *an_addr, "handle_announce(): ANNOUNCE vid %d (sent by %pM)... CRC = %#.4x\n", BATADV_PRINT_VID(vid), backbone_gw->orig, crc); - if (backbone_gw->crc != crc) { + spin_lock_bh(&backbone_gw->crc_lock); + backbone_crc = backbone_gw->crc; + spin_unlock_bh(&backbone_gw->crc_lock); + + if (backbone_crc != crc) { batadv_dbg(BATADV_DBG_BLA, backbone_gw->bat_priv, "handle_announce(): CRC FAILED for %pM/%d (my = %#.4x, sent = %#.4x)\n", backbone_gw->orig, BATADV_PRINT_VID(backbone_gw->vid), - backbone_gw->crc, crc); + backbone_crc, crc); batadv_bla_send_request(backbone_gw); } else { @@ -1056,6 +1127,7 @@ static void batadv_bla_purge_claims(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, int now) { + struct batadv_bla_backbone_gw *backbone_gw; struct batadv_bla_claim *claim; struct hlist_head *head; struct batadv_hashtable *hash; @@ -1070,14 +1142,17 @@ static void batadv_bla_purge_claims(struct batadv_priv *bat_priv, rcu_read_lock(); hlist_for_each_entry_rcu(claim, head, hash_entry) { + backbone_gw = batadv_bla_claim_get_backbone_gw(claim); if (now) goto purge_now; - if (!batadv_compare_eth(claim->backbone_gw->orig, + + if (!batadv_compare_eth(backbone_gw->orig, primary_if->net_dev->dev_addr)) - continue; + goto skip; + if (!batadv_has_timed_out(claim->lasttime, BATADV_BLA_CLAIM_TIMEOUT)) - continue; + goto skip; batadv_dbg(BATADV_DBG_BLA, bat_priv, "bla_purge_claims(): %pM, vid %d, time out\n", @@ -1085,8 +1160,10 @@ static void batadv_bla_purge_claims(struct batadv_priv *bat_priv, purge_now: batadv_handle_unclaim(bat_priv, primary_if, - claim->backbone_gw->orig, + backbone_gw->orig, claim->addr, claim->vid); +skip: + batadv_backbone_gw_free_ref(backbone_gw); } rcu_read_unlock(); } @@ -1470,9 +1547,11 @@ void batadv_bla_free(struct batadv_priv *bat_priv) int batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid, bool is_bcast) { + struct batadv_bla_backbone_gw *backbone_gw; struct ethhdr *ethhdr; struct batadv_bla_claim search_claim, *claim = NULL; struct batadv_hard_iface *primary_if; + bool own_claim; int ret; ethhdr = eth_hdr(skb); @@ -1504,8 +1583,12 @@ int batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, } /* if it is our own claim ... */ - if (batadv_compare_eth(claim->backbone_gw->orig, - primary_if->net_dev->dev_addr)) { + backbone_gw = batadv_bla_claim_get_backbone_gw(claim); + own_claim = batadv_compare_eth(backbone_gw->orig, + primary_if->net_dev->dev_addr); + batadv_backbone_gw_free_ref(backbone_gw); + + if (own_claim) { /* ... allow it in any case */ claim->lasttime = jiffies; goto allow; @@ -1568,7 +1651,9 @@ int batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb, { struct ethhdr *ethhdr; struct batadv_bla_claim search_claim, *claim = NULL; + struct batadv_bla_backbone_gw *backbone_gw; struct batadv_hard_iface *primary_if; + bool client_roamed; int ret = 0; primary_if = batadv_primary_if_get_selected(bat_priv); @@ -1598,8 +1683,12 @@ int batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb, goto allow; /* check if we are responsible. */ - if (batadv_compare_eth(claim->backbone_gw->orig, - primary_if->net_dev->dev_addr)) { + backbone_gw = batadv_bla_claim_get_backbone_gw(claim); + client_roamed = batadv_compare_eth(backbone_gw->orig, + primary_if->net_dev->dev_addr); + batadv_backbone_gw_free_ref(backbone_gw); + + if (client_roamed) { /* if yes, the client has roamed and we have * to unclaim it. */ @@ -1652,9 +1741,11 @@ int batadv_bla_claim_table_seq_print_text(struct seq_file *seq, void *offset) struct net_device *net_dev = (struct net_device *)seq->private; struct batadv_priv *bat_priv = netdev_priv(net_dev); struct batadv_hashtable *hash = bat_priv->bla.claim_hash; + struct batadv_bla_backbone_gw *backbone_gw; struct batadv_bla_claim *claim; struct batadv_hard_iface *primary_if; struct hlist_head *head; + u16 backbone_crc; u32 i; bool is_own; u8 *primary_addr; @@ -1675,13 +1766,21 @@ int batadv_bla_claim_table_seq_print_text(struct seq_file *seq, void *offset) rcu_read_lock(); hlist_for_each_entry_rcu(claim, head, hash_entry) { - is_own = batadv_compare_eth(claim->backbone_gw->orig, + backbone_gw = batadv_bla_claim_get_backbone_gw(claim); + + is_own = batadv_compare_eth(backbone_gw->orig, primary_addr); + + spin_lock_bh(&backbone_gw->crc_lock); + backbone_crc = backbone_gw->crc; + spin_unlock_bh(&backbone_gw->crc_lock); seq_printf(seq, " * %pM on %5d by %pM [%c] (%#.4x)\n", claim->addr, BATADV_PRINT_VID(claim->vid), - claim->backbone_gw->orig, + backbone_gw->orig, (is_own ? 'x' : ' '), - claim->backbone_gw->crc); + backbone_crc); + + batadv_backbone_gw_free_ref(backbone_gw); } rcu_read_unlock(); } @@ -1700,6 +1799,7 @@ int batadv_bla_backbone_table_seq_print_text(struct seq_file *seq, void *offset) struct batadv_hard_iface *primary_if; struct hlist_head *head; int secs, msecs; + u16 backbone_crc; u32 i; bool is_own; u8 *primary_addr; @@ -1730,10 +1830,14 @@ int batadv_bla_backbone_table_seq_print_text(struct seq_file *seq, void *offset) if (is_own) continue; + spin_lock_bh(&backbone_gw->crc_lock); + backbone_crc = backbone_gw->crc; + spin_unlock_bh(&backbone_gw->crc_lock); + seq_printf(seq, " * %pM on %5d %4i.%03is (%#.4x)\n", backbone_gw->orig, BATADV_PRINT_VID(backbone_gw->vid), secs, - msecs, backbone_gw->crc); + msecs, backbone_crc); } rcu_read_unlock(); } diff --git a/net/batman-adv/debugfs.c b/net/batman-adv/debugfs.c index c4c1e8030ba0..b2ef03a3a2d4 100644 --- a/net/batman-adv/debugfs.c +++ b/net/batman-adv/debugfs.c @@ -19,6 +19,7 @@ #include "main.h" #include <linux/compiler.h> +#include <linux/dcache.h> #include <linux/debugfs.h> #include <linux/device.h> #include <linux/errno.h> @@ -507,6 +508,25 @@ out: } /** + * batadv_debugfs_rename_hardif() - Fix debugfs path for renamed hardif + * @hard_iface: hard interface which was renamed + */ +void batadv_debugfs_rename_hardif(struct batadv_hard_iface *hard_iface) +{ + const char *name = hard_iface->net_dev->name; + struct dentry *dir; + struct dentry *d; + + dir = hard_iface->debug_dir; + if (!dir) + return; + + d = debugfs_rename(dir->d_parent, dir, dir->d_parent, name); + if (!d) + pr_err("Can't rename debugfs dir to %s\n", name); +} + +/** * batadv_debugfs_del_hardif - delete the base directory for a hard interface * in debugfs. * @hard_iface: hard interface which is deleted. @@ -561,6 +581,26 @@ out: return -ENOMEM; } +/** + * batadv_debugfs_rename_meshif() - Fix debugfs path for renamed softif + * @dev: net_device which was renamed + */ +void batadv_debugfs_rename_meshif(struct net_device *dev) +{ + struct batadv_priv *bat_priv = netdev_priv(dev); + const char *name = dev->name; + struct dentry *dir; + struct dentry *d; + + dir = bat_priv->debug_dir; + if (!dir) + return; + + d = debugfs_rename(dir->d_parent, dir, dir->d_parent, name); + if (!d) + pr_err("Can't rename debugfs dir to %s\n", name); +} + void batadv_debugfs_del_meshif(struct net_device *dev) { struct batadv_priv *bat_priv = netdev_priv(dev); diff --git a/net/batman-adv/debugfs.h b/net/batman-adv/debugfs.h index 80ab8d6f0ab3..347f793a18b2 100644 --- a/net/batman-adv/debugfs.h +++ b/net/batman-adv/debugfs.h @@ -31,8 +31,10 @@ struct net_device; void batadv_debugfs_init(void); void batadv_debugfs_destroy(void); int batadv_debugfs_add_meshif(struct net_device *dev); +void batadv_debugfs_rename_meshif(struct net_device *dev); void batadv_debugfs_del_meshif(struct net_device *dev); int batadv_debugfs_add_hardif(struct batadv_hard_iface *hard_iface); +void batadv_debugfs_rename_hardif(struct batadv_hard_iface *hard_iface); void batadv_debugfs_del_hardif(struct batadv_hard_iface *hard_iface); #else @@ -50,6 +52,10 @@ static inline int batadv_debugfs_add_meshif(struct net_device *dev) return 0; } +static inline void batadv_debugfs_rename_meshif(struct net_device *dev) +{ +} + static inline void batadv_debugfs_del_meshif(struct net_device *dev) { } @@ -61,6 +67,11 @@ int batadv_debugfs_add_hardif(struct batadv_hard_iface *hard_iface) } static inline +void batadv_debugfs_rename_hardif(struct batadv_hard_iface *hard_iface) +{ +} + +static inline void batadv_debugfs_del_hardif(struct batadv_hard_iface *hard_iface) { } diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index 76808c5e8183..769683da8d9d 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -993,15 +993,19 @@ bool batadv_dat_snoop_outgoing_arp_request(struct batadv_priv *bat_priv, if (!skb_new) goto out; - if (vid & BATADV_VLAN_HAS_TAG) + if (vid & BATADV_VLAN_HAS_TAG) { skb_new = vlan_insert_tag(skb_new, htons(ETH_P_8021Q), vid & VLAN_VID_MASK); + if (!skb_new) + goto out; + } skb_reset_mac_header(skb_new); skb_new->protocol = eth_type_trans(skb_new, bat_priv->soft_iface); - bat_priv->stats.rx_packets++; - bat_priv->stats.rx_bytes += skb->len + ETH_HLEN + hdr_size; + batadv_inc_counter(bat_priv, BATADV_CNT_RX); + batadv_add_counter(bat_priv, BATADV_CNT_RX_BYTES, + skb->len + ETH_HLEN + hdr_size); bat_priv->soft_iface->last_rx = jiffies; netif_rx(skb_new); @@ -1073,9 +1077,12 @@ bool batadv_dat_snoop_incoming_arp_request(struct batadv_priv *bat_priv, */ skb_reset_mac_header(skb_new); - if (vid & BATADV_VLAN_HAS_TAG) + if (vid & BATADV_VLAN_HAS_TAG) { skb_new = vlan_insert_tag(skb_new, htons(ETH_P_8021Q), vid & VLAN_VID_MASK); + if (!skb_new) + goto out; + } /* To preserve backwards compatibility, the node has choose the outgoing * format based on the incoming request packet type. The assumption is diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index d50c3b003dc9..9751b207b01f 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -233,8 +233,10 @@ err_unlock: spin_unlock_bh(&chain->lock); err: - if (!ret) + if (!ret) { kfree(frag_entry_new); + kfree_skb(skb); + } return ret; } @@ -329,9 +331,9 @@ bool batadv_frag_skb_buffer(struct sk_buff **skb, goto out_err; out: - *skb = skb_out; ret = true; out_err: + *skb = skb_out; return ret; } @@ -478,6 +480,10 @@ bool batadv_frag_send_packet(struct sk_buff *skb, /* Eat and send fragments from the tail of skb */ while (skb->len > max_fragment_size) { + /* The initial check in this function should cover this case */ + if (frag_header.no == BATADV_FRAG_MAX_FRAGMENTS - 1) + goto out_err; + skb_fragment = batadv_frag_create(skb, &frag_header, mtu); if (!skb_fragment) goto out_err; @@ -488,10 +494,6 @@ bool batadv_frag_send_packet(struct sk_buff *skb, batadv_send_skb_packet(skb_fragment, neigh_node->if_incoming, neigh_node->addr); frag_header.no++; - - /* The initial check in this function should cover this case */ - if (frag_header.no == BATADV_FRAG_MAX_FRAGMENTS - 1) - goto out_err; } /* Make room for the fragment header. */ diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index 6abfba1e227f..a88b529b7ca0 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -29,6 +29,7 @@ #include <linux/ipv6.h> #include <linux/kernel.h> #include <linux/list.h> +#include <linux/lockdep.h> #include <linux/netdevice.h> #include <linux/rculist.h> #include <linux/rcupdate.h> @@ -413,6 +414,9 @@ out: * @bat_priv: the bat priv with all the soft interface information * @orig_node: originator announcing gateway capabilities * @gateway: announced bandwidth information + * + * Has to be called with the appropriate locks being acquired + * (gw.list_lock). */ static void batadv_gw_node_add(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, @@ -420,6 +424,8 @@ static void batadv_gw_node_add(struct batadv_priv *bat_priv, { struct batadv_gw_node *gw_node; + lockdep_assert_held(&bat_priv->gw.list_lock); + if (gateway->bandwidth_down == 0) return; @@ -438,9 +444,7 @@ static void batadv_gw_node_add(struct batadv_priv *bat_priv, gw_node->bandwidth_up = ntohl(gateway->bandwidth_up); atomic_set(&gw_node->refcount, 1); - spin_lock_bh(&bat_priv->gw.list_lock); hlist_add_head_rcu(&gw_node->list, &bat_priv->gw.list); - spin_unlock_bh(&bat_priv->gw.list_lock); batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Found new gateway %pM -> gw bandwidth: %u.%u/%u.%u MBit\n", @@ -493,11 +497,14 @@ void batadv_gw_node_update(struct batadv_priv *bat_priv, { struct batadv_gw_node *gw_node, *curr_gw = NULL; + spin_lock_bh(&bat_priv->gw.list_lock); gw_node = batadv_gw_node_get(bat_priv, orig_node); if (!gw_node) { batadv_gw_node_add(bat_priv, orig_node, gateway); + spin_unlock_bh(&bat_priv->gw.list_lock); goto out; } + spin_unlock_bh(&bat_priv->gw.list_lock); if ((gw_node->bandwidth_down == ntohl(gateway->bandwidth_down)) && (gw_node->bandwidth_up == ntohl(gateway->bandwidth_up))) @@ -527,11 +534,12 @@ void batadv_gw_node_update(struct batadv_priv *bat_priv, * gets dereferenced. */ spin_lock_bh(&bat_priv->gw.list_lock); - hlist_del_init_rcu(&gw_node->list); + if (!hlist_unhashed(&gw_node->list)) { + hlist_del_init_rcu(&gw_node->list); + batadv_gw_node_free_ref(gw_node); + } spin_unlock_bh(&bat_priv->gw.list_lock); - batadv_gw_node_free_ref(gw_node); - curr_gw = batadv_gw_get_selected_gw_node(bat_priv); if (gw_node == curr_gw) batadv_gw_reselect(bat_priv); diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 3c8d8142e8c6..c59bbc327763 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -26,6 +26,7 @@ #include <linux/if.h> #include <linux/kernel.h> #include <linux/list.h> +#include <linux/mutex.h> #include <linux/netdevice.h> #include <linux/printk.h> #include <linux/rculist.h> @@ -45,13 +46,16 @@ #include "sysfs.h" #include "translation-table.h" -void batadv_hardif_free_rcu(struct rcu_head *rcu) +/** + * batadv_hardif_release - release hard interface from lists and queue for + * free after rcu grace period + * @hard_iface: the hard interface to free + */ +void batadv_hardif_release(struct batadv_hard_iface *hard_iface) { - struct batadv_hard_iface *hard_iface; - - hard_iface = container_of(rcu, struct batadv_hard_iface, rcu); dev_put(hard_iface->net_dev); - kfree(hard_iface); + + kfree_rcu(hard_iface, rcu); } struct batadv_hard_iface * @@ -74,6 +78,28 @@ out: } /** + * batadv_mutual_parents - check if two devices are each others parent + * @dev1: 1st net_device + * @dev2: 2nd net_device + * + * veth devices come in pairs and each is the parent of the other! + * + * Return: true if the devices are each others parent, otherwise false + */ +static bool batadv_mutual_parents(const struct net_device *dev1, + const struct net_device *dev2) +{ + int dev1_parent_iflink = dev_get_iflink(dev1); + int dev2_parent_iflink = dev_get_iflink(dev2); + + if (!dev1_parent_iflink || !dev2_parent_iflink) + return false; + + return (dev1_parent_iflink == dev2->ifindex) && + (dev2_parent_iflink == dev1->ifindex); +} + +/** * batadv_is_on_batman_iface - check if a device is a batman iface descendant * @net_dev: the device to check * @@ -108,6 +134,9 @@ static bool batadv_is_on_batman_iface(const struct net_device *net_dev) return false; } + if (batadv_mutual_parents(net_dev, parent_dev)) + return false; + ret = batadv_is_on_batman_iface(parent_dev); return ret; @@ -465,6 +494,11 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface, hard_iface->soft_iface = soft_iface; bat_priv = netdev_priv(hard_iface->soft_iface); + if (bat_priv->num_ifaces >= UINT_MAX) { + ret = -ENOSPC; + goto err_dev; + } + ret = netdev_master_upper_dev_link(hard_iface->net_dev, soft_iface); if (ret) goto err_dev; @@ -537,8 +571,7 @@ void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface, struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); struct batadv_hard_iface *primary_if = NULL; - if (hard_iface->if_status == BATADV_IF_ACTIVE) - batadv_hardif_deactivate_interface(hard_iface); + batadv_hardif_deactivate_interface(hard_iface); if (hard_iface->if_status != BATADV_IF_INACTIVE) goto out; @@ -573,7 +606,7 @@ void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface, batadv_hardif_recalc_extra_skbroom(hard_iface->soft_iface); /* nobody uses this interface anymore */ - if (!bat_priv->num_ifaces) { + if (bat_priv->num_ifaces == 0) { batadv_gw_check_client_stop(bat_priv); if (autodel == BATADV_IF_CLEANUP_AUTO) @@ -629,7 +662,7 @@ batadv_hardif_add_interface(struct net_device *net_dev) if (ret) goto free_if; - hard_iface->if_num = -1; + hard_iface->if_num = 0; hard_iface->net_dev = net_dev; hard_iface->soft_iface = NULL; hard_iface->if_status = BATADV_IF_NOT_IN_USE; @@ -639,6 +672,7 @@ batadv_hardif_add_interface(struct net_device *net_dev) goto free_sysfs; INIT_LIST_HEAD(&hard_iface->list); + mutex_init(&hard_iface->bat_iv.ogm_buff_mutex); INIT_WORK(&hard_iface->cleanup_work, batadv_hardif_remove_interface_finish); @@ -693,6 +727,32 @@ void batadv_hardif_remove_interfaces(void) rtnl_unlock(); } +/** + * batadv_hard_if_event_softif() - Handle events for soft interfaces + * @event: NETDEV_* event to handle + * @net_dev: net_device which generated an event + * + * Return: NOTIFY_* result + */ +static int batadv_hard_if_event_softif(unsigned long event, + struct net_device *net_dev) +{ + struct batadv_priv *bat_priv; + + switch (event) { + case NETDEV_REGISTER: + batadv_sysfs_add_meshif(net_dev); + bat_priv = netdev_priv(net_dev); + batadv_softif_create_vlan(bat_priv, BATADV_NO_FLAGS); + break; + case NETDEV_CHANGENAME: + batadv_debugfs_rename_meshif(net_dev); + break; + } + + return NOTIFY_DONE; +} + static int batadv_hard_if_event(struct notifier_block *this, unsigned long event, void *ptr) { @@ -701,12 +761,8 @@ static int batadv_hard_if_event(struct notifier_block *this, struct batadv_hard_iface *primary_if = NULL; struct batadv_priv *bat_priv; - if (batadv_softif_is_valid(net_dev) && event == NETDEV_REGISTER) { - batadv_sysfs_add_meshif(net_dev); - bat_priv = netdev_priv(net_dev); - batadv_softif_create_vlan(bat_priv, BATADV_NO_FLAGS); - return NOTIFY_DONE; - } + if (batadv_softif_is_valid(net_dev)) + return batadv_hard_if_event_softif(event, net_dev); hard_iface = batadv_hardif_get_by_netdev(net_dev); if (!hard_iface && event == NETDEV_REGISTER) @@ -748,6 +804,9 @@ static int batadv_hard_if_event(struct notifier_block *this, if (hard_iface == primary_if) batadv_primary_if_update_addr(bat_priv, NULL); break; + case NETDEV_CHANGENAME: + batadv_debugfs_rename_hardif(hard_iface); + break; default: break; } diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h index 7b12ea8ea29d..4d74c0415911 100644 --- a/net/batman-adv/hard-interface.h +++ b/net/batman-adv/hard-interface.h @@ -61,18 +61,18 @@ void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface, void batadv_hardif_remove_interfaces(void); int batadv_hardif_min_mtu(struct net_device *soft_iface); void batadv_update_min_mtu(struct net_device *soft_iface); -void batadv_hardif_free_rcu(struct rcu_head *rcu); +void batadv_hardif_release(struct batadv_hard_iface *hard_iface); /** * batadv_hardif_free_ref - decrement the hard interface refcounter and - * possibly free it + * possibly release it * @hard_iface: the hard interface to free */ static inline void batadv_hardif_free_ref(struct batadv_hard_iface *hard_iface) { if (atomic_dec_and_test(&hard_iface->refcount)) - call_rcu(&hard_iface->rcu, batadv_hardif_free_rcu); + batadv_hardif_release(hard_iface); } static inline struct batadv_hard_iface * diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index d7f17c1aa4a4..2bdbaff3279b 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -1079,15 +1079,20 @@ void batadv_tvlv_handler_register(struct batadv_priv *bat_priv, { struct batadv_tvlv_handler *tvlv_handler; + spin_lock_bh(&bat_priv->tvlv.handler_list_lock); + tvlv_handler = batadv_tvlv_handler_get(bat_priv, type, version); if (tvlv_handler) { + spin_unlock_bh(&bat_priv->tvlv.handler_list_lock); batadv_tvlv_handler_free_ref(tvlv_handler); return; } tvlv_handler = kzalloc(sizeof(*tvlv_handler), GFP_ATOMIC); - if (!tvlv_handler) + if (!tvlv_handler) { + spin_unlock_bh(&bat_priv->tvlv.handler_list_lock); return; + } tvlv_handler->ogm_handler = optr; tvlv_handler->unicast_handler = uptr; @@ -1097,7 +1102,6 @@ void batadv_tvlv_handler_register(struct batadv_priv *bat_priv, atomic_set(&tvlv_handler->refcount, 1); INIT_HLIST_NODE(&tvlv_handler->list); - spin_lock_bh(&bat_priv->tvlv.handler_list_lock); hlist_add_head_rcu(&tvlv_handler->list, &bat_priv->tvlv.handler_list); spin_unlock_bh(&bat_priv->tvlv.handler_list_lock); } diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index d0956f726547..86c69208da2b 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -828,19 +828,29 @@ static struct batadv_nc_node spinlock_t *lock; /* Used to lock list selected by "int in_coding" */ struct list_head *list; + /* Select ingoing or outgoing coding node */ + if (in_coding) { + lock = &orig_neigh_node->in_coding_list_lock; + list = &orig_neigh_node->in_coding_list; + } else { + lock = &orig_neigh_node->out_coding_list_lock; + list = &orig_neigh_node->out_coding_list; + } + + spin_lock_bh(lock); + /* Check if nc_node is already added */ nc_node = batadv_nc_find_nc_node(orig_node, orig_neigh_node, in_coding); /* Node found */ if (nc_node) - return nc_node; + goto unlock; nc_node = kzalloc(sizeof(*nc_node), GFP_ATOMIC); if (!nc_node) - return NULL; + goto unlock; - if (!atomic_inc_not_zero(&orig_neigh_node->refcount)) - goto free; + atomic_inc(&orig_neigh_node->refcount); /* Initialize nc_node */ INIT_LIST_HEAD(&nc_node->list); @@ -848,28 +858,15 @@ static struct batadv_nc_node nc_node->orig_node = orig_neigh_node; atomic_set(&nc_node->refcount, 2); - /* Select ingoing or outgoing coding node */ - if (in_coding) { - lock = &orig_neigh_node->in_coding_list_lock; - list = &orig_neigh_node->in_coding_list; - } else { - lock = &orig_neigh_node->out_coding_list_lock; - list = &orig_neigh_node->out_coding_list; - } - batadv_dbg(BATADV_DBG_NC, bat_priv, "Adding nc_node %pM -> %pM\n", nc_node->addr, nc_node->orig_node->orig); /* Add nc_node to orig_node */ - spin_lock_bh(lock); list_add_tail_rcu(&nc_node->list, list); +unlock: spin_unlock_bh(lock); return nc_node; - -free: - kfree(nc_node); - return NULL; } /** diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 6282f021ddfb..b3013fbc417e 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -462,6 +462,8 @@ batadv_neigh_node_new(struct batadv_orig_node *orig_node, { struct batadv_neigh_node *neigh_node; + spin_lock_bh(&orig_node->neigh_list_lock); + neigh_node = batadv_neigh_node_get(orig_node, hard_iface, neigh_addr); if (neigh_node) goto out; @@ -483,19 +485,20 @@ batadv_neigh_node_new(struct batadv_orig_node *orig_node, ether_addr_copy(neigh_node->addr, neigh_addr); neigh_node->if_incoming = hard_iface; neigh_node->orig_node = orig_node; + neigh_node->last_seen = jiffies; /* extra reference for return */ atomic_set(&neigh_node->refcount, 2); - spin_lock_bh(&orig_node->neigh_list_lock); hlist_add_head_rcu(&neigh_node->list, &orig_node->neigh_list); - spin_unlock_bh(&orig_node->neigh_list_lock); batadv_dbg(BATADV_DBG_BATMAN, orig_node->bat_priv, "Creating new neighbor %pM for orig_node %pM on interface %s\n", neigh_addr, orig_node->orig, hard_iface->net_dev->name); out: + spin_unlock_bh(&orig_node->neigh_list_lock); + return neigh_node; } @@ -561,6 +564,8 @@ static void batadv_orig_node_release(struct batadv_orig_node *orig_node) struct hlist_node *node_tmp; struct batadv_neigh_node *neigh_node; struct batadv_orig_ifinfo *orig_ifinfo; + struct batadv_orig_node_vlan *vlan; + struct batadv_orig_ifinfo *last_candidate; spin_lock_bh(&orig_node->neigh_list_lock); @@ -576,8 +581,21 @@ static void batadv_orig_node_release(struct batadv_orig_node *orig_node) hlist_del_rcu(&orig_ifinfo->list); batadv_orig_ifinfo_free_ref(orig_ifinfo); } + + last_candidate = orig_node->last_bonding_candidate; + orig_node->last_bonding_candidate = NULL; spin_unlock_bh(&orig_node->neigh_list_lock); + if (last_candidate) + batadv_orig_ifinfo_free_ref(last_candidate); + + spin_lock_bh(&orig_node->vlan_list_lock); + hlist_for_each_entry_safe(vlan, node_tmp, &orig_node->vlan_list, list) { + hlist_del_rcu(&vlan->list); + batadv_orig_node_vlan_free_ref(vlan); + } + spin_unlock_bh(&orig_node->vlan_list_lock); + /* Free nc_nodes */ batadv_nc_purge_orig(orig_node->bat_priv, orig_node, NULL); @@ -1085,7 +1103,7 @@ out: } int batadv_orig_hash_add_if(struct batadv_hard_iface *hard_iface, - int max_if_num) + unsigned int max_if_num) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); struct batadv_algo_ops *bao = bat_priv->bat_algo_ops; @@ -1121,7 +1139,7 @@ err: } int batadv_orig_hash_del_if(struct batadv_hard_iface *hard_iface, - int max_if_num) + unsigned int max_if_num) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); struct batadv_hashtable *hash = bat_priv->orig_hash; diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index a5c37882b409..65824d892a6a 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -67,9 +67,9 @@ void batadv_orig_ifinfo_free_ref(struct batadv_orig_ifinfo *orig_ifinfo); int batadv_orig_seq_print_text(struct seq_file *seq, void *offset); int batadv_orig_hardif_seq_print_text(struct seq_file *seq, void *offset); int batadv_orig_hash_add_if(struct batadv_hard_iface *hard_iface, - int max_if_num); + unsigned int max_if_num); int batadv_orig_hash_del_if(struct batadv_hard_iface *hard_iface, - int max_if_num); + unsigned int max_if_num); struct batadv_orig_node_vlan * batadv_orig_node_vlan_new(struct batadv_orig_node *orig_node, unsigned short vid); diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index d8a2f33e60e5..b3e8b0e3073c 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -359,6 +359,7 @@ int batadv_recv_icmp_packet(struct sk_buff *skb, if (skb_cow(skb, ETH_HLEN) < 0) goto out; + ethhdr = eth_hdr(skb); icmph = (struct batadv_icmp_header *)skb->data; icmp_packet_rr = (struct batadv_icmp_packet_rr *)icmph; if (icmp_packet_rr->rr_cur >= BATADV_RR_LEN) @@ -439,6 +440,52 @@ static int batadv_check_unicast_packet(struct batadv_priv *bat_priv, } /** + * batadv_last_bonding_get - Get last_bonding_candidate of orig_node + * @orig_node: originator node whose last bonding candidate should be retrieved + * + * Return: last bonding candidate of router or NULL if not found + * + * The object is returned with refcounter increased by 1. + */ +static struct batadv_orig_ifinfo * +batadv_last_bonding_get(struct batadv_orig_node *orig_node) +{ + struct batadv_orig_ifinfo *last_bonding_candidate; + + spin_lock_bh(&orig_node->neigh_list_lock); + last_bonding_candidate = orig_node->last_bonding_candidate; + + if (last_bonding_candidate) + atomic_inc(&last_bonding_candidate->refcount); + spin_unlock_bh(&orig_node->neigh_list_lock); + + return last_bonding_candidate; +} + +/** + * batadv_last_bonding_replace - Replace last_bonding_candidate of orig_node + * @orig_node: originator node whose bonding candidates should be replaced + * @new_candidate: new bonding candidate or NULL + */ +static void +batadv_last_bonding_replace(struct batadv_orig_node *orig_node, + struct batadv_orig_ifinfo *new_candidate) +{ + struct batadv_orig_ifinfo *old_candidate; + + spin_lock_bh(&orig_node->neigh_list_lock); + old_candidate = orig_node->last_bonding_candidate; + + if (new_candidate) + atomic_inc(&new_candidate->refcount); + orig_node->last_bonding_candidate = new_candidate; + spin_unlock_bh(&orig_node->neigh_list_lock); + + if (old_candidate) + batadv_orig_ifinfo_free_ref(old_candidate); +} + +/** * batadv_find_router - find a suitable router for this originator * @bat_priv: the bat priv with all the soft interface information * @orig_node: the destination node @@ -485,7 +532,7 @@ batadv_find_router(struct batadv_priv *bat_priv, * router - obviously there are no other candidates. */ rcu_read_lock(); - last_candidate = orig_node->last_bonding_candidate; + last_candidate = batadv_last_bonding_get(orig_node); if (last_candidate) last_cand_router = rcu_dereference(last_candidate->router); @@ -545,10 +592,6 @@ next: } rcu_read_unlock(); - /* last_bonding_candidate is reset below, remove the old reference. */ - if (orig_node->last_bonding_candidate) - batadv_orig_ifinfo_free_ref(orig_node->last_bonding_candidate); - /* After finding candidates, handle the three cases: * 1) there is a next candidate, use that * 2) there is no next candidate, use the first of the list @@ -557,23 +600,33 @@ next: if (next_candidate) { batadv_neigh_node_free_ref(router); - /* remove references to first candidate, we don't need it. */ - if (first_candidate) { - batadv_neigh_node_free_ref(first_candidate_router); - batadv_orig_ifinfo_free_ref(first_candidate); - } + atomic_inc(&next_candidate_router->refcount); router = next_candidate_router; - orig_node->last_bonding_candidate = next_candidate; + batadv_last_bonding_replace(orig_node, next_candidate); } else if (first_candidate) { batadv_neigh_node_free_ref(router); - /* refcounting has already been done in the loop above. */ + atomic_inc(&first_candidate_router->refcount); router = first_candidate_router; - orig_node->last_bonding_candidate = first_candidate; + batadv_last_bonding_replace(orig_node, first_candidate); } else { - orig_node->last_bonding_candidate = NULL; + batadv_last_bonding_replace(orig_node, NULL); + } + + /* cleanup of candidates */ + if (first_candidate) { + batadv_neigh_node_free_ref(first_candidate_router); + batadv_orig_ifinfo_free_ref(first_candidate); } + if (next_candidate) { + batadv_neigh_node_free_ref(next_candidate_router); + batadv_orig_ifinfo_free_ref(next_candidate); + } + + if (last_candidate) + batadv_orig_ifinfo_free_ref(last_candidate); + return router; } @@ -585,6 +638,7 @@ static int batadv_route_unicast_packet(struct sk_buff *skb, struct batadv_unicast_packet *unicast_packet; struct ethhdr *ethhdr = eth_hdr(skb); int res, hdr_len, ret = NET_RX_DROP; + unsigned int len; unicast_packet = (struct batadv_unicast_packet *)skb->data; @@ -625,6 +679,7 @@ static int batadv_route_unicast_packet(struct sk_buff *skb, if (hdr_len > 0) batadv_skb_set_priority(skb, hdr_len); + len = skb->len; res = batadv_send_skb_to_orig(skb, orig_node, recv_if); /* translate transmit result into receive result */ @@ -632,7 +687,7 @@ static int batadv_route_unicast_packet(struct sk_buff *skb, /* skb was transmitted and consumed */ batadv_inc_counter(bat_priv, BATADV_CNT_FORWARD); batadv_add_counter(bat_priv, BATADV_CNT_FORWARD_BYTES, - skb->len + ETH_HLEN); + len + ETH_HLEN); ret = NET_RX_SUCCESS; } else if (res == NET_XMIT_POLICED) { @@ -649,6 +704,7 @@ out: /** * batadv_reroute_unicast_packet - update the unicast header for re-routing * @bat_priv: the bat priv with all the soft interface information + * @skb: unicast packet to process * @unicast_packet: the unicast header to be updated * @dst_addr: the payload destination * @vid: VLAN identifier @@ -660,7 +716,7 @@ out: * Returns true if the packet header has been updated, false otherwise */ static bool -batadv_reroute_unicast_packet(struct batadv_priv *bat_priv, +batadv_reroute_unicast_packet(struct batadv_priv *bat_priv, struct sk_buff *skb, struct batadv_unicast_packet *unicast_packet, u8 *dst_addr, unsigned short vid) { @@ -689,8 +745,10 @@ batadv_reroute_unicast_packet(struct batadv_priv *bat_priv, } /* update the packet header */ + skb_postpull_rcsum(skb, unicast_packet, sizeof(*unicast_packet)); ether_addr_copy(unicast_packet->dest, orig_addr); unicast_packet->ttvn = orig_ttvn; + skb_postpush_rcsum(skb, unicast_packet, sizeof(*unicast_packet)); ret = true; out: @@ -730,7 +788,7 @@ static int batadv_check_unicast_ttvn(struct batadv_priv *bat_priv, * the packet to */ if (batadv_tt_local_client_is_roaming(bat_priv, ethhdr->h_dest, vid)) { - if (batadv_reroute_unicast_packet(bat_priv, unicast_packet, + if (batadv_reroute_unicast_packet(bat_priv, skb, unicast_packet, ethhdr->h_dest, vid)) batadv_dbg_ratelimited(BATADV_DBG_TT, bat_priv, @@ -776,7 +834,7 @@ static int batadv_check_unicast_ttvn(struct batadv_priv *bat_priv, * destination can possibly be updated and forwarded towards the new * target host */ - if (batadv_reroute_unicast_packet(bat_priv, unicast_packet, + if (batadv_reroute_unicast_packet(bat_priv, skb, unicast_packet, ethhdr->h_dest, vid)) { batadv_dbg_ratelimited(BATADV_DBG_TT, bat_priv, "Rerouting unicast packet to %pM (dst=%pM): TTVN mismatch old_ttvn=%u new_ttvn=%u\n", @@ -799,12 +857,14 @@ static int batadv_check_unicast_ttvn(struct batadv_priv *bat_priv, if (!primary_if) return 0; + /* update the packet header */ + skb_postpull_rcsum(skb, unicast_packet, sizeof(*unicast_packet)); ether_addr_copy(unicast_packet->dest, primary_if->net_dev->dev_addr); + unicast_packet->ttvn = curr_ttvn; + skb_postpush_rcsum(skb, unicast_packet, sizeof(*unicast_packet)); batadv_hardif_free_ref(primary_if); - unicast_packet->ttvn = curr_ttvn; - return 1; } @@ -849,7 +909,6 @@ int batadv_recv_unicast_packet(struct sk_buff *skb, bool is4addr; unicast_packet = (struct batadv_unicast_packet *)skb->data; - unicast_4addr_packet = (struct batadv_unicast_4addr_packet *)skb->data; is4addr = unicast_packet->packet_type == BATADV_UNICAST_4ADDR; /* the caller function should have already pulled 2 bytes */ @@ -870,9 +929,13 @@ int batadv_recv_unicast_packet(struct sk_buff *skb, if (!batadv_check_unicast_ttvn(bat_priv, skb, hdr_size)) return NET_RX_DROP; + unicast_packet = (struct batadv_unicast_packet *)skb->data; + /* packet for me */ if (batadv_is_my_mac(bat_priv, unicast_packet->dest)) { if (is4addr) { + unicast_4addr_packet = + (struct batadv_unicast_4addr_packet *)skb->data; subtype = unicast_4addr_packet->subtype; batadv_dat_inc_counter(bat_priv, subtype); @@ -998,6 +1061,12 @@ int batadv_recv_frag_packet(struct sk_buff *skb, batadv_inc_counter(bat_priv, BATADV_CNT_FRAG_RX); batadv_add_counter(bat_priv, BATADV_CNT_FRAG_RX_BYTES, skb->len); + /* batadv_frag_skb_buffer will always consume the skb and + * the caller should therefore never try to free the + * skb after this point + */ + ret = NET_RX_SUCCESS; + /* Add fragment to buffer and merge if possible. */ if (!batadv_frag_skb_buffer(&skb, orig_node_src)) goto out; diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index 0e0c3b8ed927..11fbfb222c49 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -381,8 +381,8 @@ int batadv_send_skb_via_gw(struct batadv_priv *bat_priv, struct sk_buff *skb, struct batadv_orig_node *orig_node; orig_node = batadv_gw_get_selected_orig(bat_priv); - return batadv_send_skb_unicast(bat_priv, skb, BATADV_UNICAST, 0, - orig_node, vid); + return batadv_send_skb_unicast(bat_priv, skb, BATADV_UNICAST_4ADDR, + BATADV_P_DATA, orig_node, vid); } void batadv_schedule_bat_ogm(struct batadv_hard_iface *hard_iface) diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 4812123e0a2c..ff693887ea82 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -1000,7 +1000,9 @@ void batadv_softif_destroy_sysfs(struct net_device *soft_iface) static void batadv_softif_destroy_netlink(struct net_device *soft_iface, struct list_head *head) { + struct batadv_priv *bat_priv = netdev_priv(soft_iface); struct batadv_hard_iface *hard_iface; + struct batadv_softif_vlan *vlan; list_for_each_entry(hard_iface, &batadv_hardif_list, list) { if (hard_iface->soft_iface == soft_iface) @@ -1008,6 +1010,13 @@ static void batadv_softif_destroy_netlink(struct net_device *soft_iface, BATADV_IF_CLEANUP_KEEP); } + /* destroy the "untagged" VLAN */ + vlan = batadv_softif_vlan_get(bat_priv, BATADV_NO_FLAGS); + if (vlan) { + batadv_softif_destroy_vlan(bat_priv, vlan); + batadv_softif_vlan_free_ref(vlan); + } + batadv_sysfs_del_meshif(soft_iface); unregister_netdevice_queue(soft_iface, head); } diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index ffd49b40e76a..67ee7c83a28d 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -197,8 +197,11 @@ batadv_tt_global_hash_find(struct batadv_priv *bat_priv, const u8 *addr, static void batadv_tt_local_entry_free_ref(struct batadv_tt_local_entry *tt_local_entry) { - if (atomic_dec_and_test(&tt_local_entry->common.refcount)) + if (atomic_dec_and_test(&tt_local_entry->common.refcount)) { + batadv_softif_vlan_free_ref(tt_local_entry->vlan); + kfree_rcu(tt_local_entry, common.rcu); + } } /** @@ -303,9 +306,11 @@ static void batadv_tt_global_size_mod(struct batadv_orig_node *orig_node, if (atomic_add_return(v, &vlan->tt.num_entries) == 0) { spin_lock_bh(&orig_node->vlan_list_lock); - hlist_del_init_rcu(&vlan->list); + if (!hlist_unhashed(&vlan->list)) { + hlist_del_init_rcu(&vlan->list); + batadv_orig_node_vlan_free_ref(vlan); + } spin_unlock_bh(&orig_node->vlan_list_lock); - batadv_orig_node_vlan_free_ref(vlan); } batadv_orig_node_vlan_free_ref(vlan); @@ -503,14 +508,26 @@ static void batadv_tt_global_free(struct batadv_priv *bat_priv, struct batadv_tt_global_entry *tt_global, const char *message) { + struct batadv_tt_global_entry *tt_removed_entry; + struct hlist_node *tt_removed_node; + batadv_dbg(BATADV_DBG_TT, bat_priv, "Deleting global tt entry %pM (vid: %d): %s\n", tt_global->common.addr, BATADV_PRINT_VID(tt_global->common.vid), message); - batadv_hash_remove(bat_priv->tt.global_hash, batadv_compare_tt, - batadv_choose_tt, &tt_global->common); - batadv_tt_global_entry_free_ref(tt_global); + tt_removed_node = batadv_hash_remove(bat_priv->tt.global_hash, + batadv_compare_tt, + batadv_choose_tt, + &tt_global->common); + if (!tt_removed_node) + return; + + /* drop reference of remove hash entry */ + tt_removed_entry = hlist_entry(tt_removed_node, + struct batadv_tt_global_entry, + common.hash_entry); + batadv_tt_global_entry_free_ref(tt_removed_entry); } /** @@ -636,7 +653,6 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const u8 *addr, if (unlikely(hash_added != 0)) { /* remove the reference for the hash */ batadv_tt_local_entry_free_ref(tt_local); - batadv_softif_vlan_free_ref(vlan); goto out; } @@ -740,7 +756,7 @@ batadv_tt_prepare_tvlv_global_data(struct batadv_orig_node *orig_node, struct batadv_orig_node_vlan *vlan; u8 *tt_change_ptr; - rcu_read_lock(); + spin_lock_bh(&orig_node->vlan_list_lock); hlist_for_each_entry_rcu(vlan, &orig_node->vlan_list, list) { num_vlan++; num_entries += atomic_read(&vlan->tt.num_entries); @@ -778,7 +794,7 @@ batadv_tt_prepare_tvlv_global_data(struct batadv_orig_node *orig_node, *tt_change = (struct batadv_tvlv_tt_change *)tt_change_ptr; out: - rcu_read_unlock(); + spin_unlock_bh(&orig_node->vlan_list_lock); return tvlv_len; } @@ -809,15 +825,20 @@ batadv_tt_prepare_tvlv_local_data(struct batadv_priv *bat_priv, struct batadv_tvlv_tt_vlan_data *tt_vlan; struct batadv_softif_vlan *vlan; u16 num_vlan = 0; - u16 num_entries = 0; + u16 vlan_entries = 0; + u16 total_entries = 0; u16 tvlv_len; u8 *tt_change_ptr; int change_offset; - rcu_read_lock(); + spin_lock_bh(&bat_priv->softif_vlan_list_lock); hlist_for_each_entry_rcu(vlan, &bat_priv->softif_vlan_list, list) { + vlan_entries = atomic_read(&vlan->tt.num_entries); + if (vlan_entries < 1) + continue; + num_vlan++; - num_entries += atomic_read(&vlan->tt.num_entries); + total_entries += vlan_entries; } change_offset = sizeof(**tt_data); @@ -825,7 +846,7 @@ batadv_tt_prepare_tvlv_local_data(struct batadv_priv *bat_priv, /* if tt_len is negative, allocate the space needed by the full table */ if (*tt_len < 0) - *tt_len = batadv_tt_len(num_entries); + *tt_len = batadv_tt_len(total_entries); tvlv_len = *tt_len; tvlv_len += change_offset; @@ -842,6 +863,10 @@ batadv_tt_prepare_tvlv_local_data(struct batadv_priv *bat_priv, tt_vlan = (struct batadv_tvlv_tt_vlan_data *)(*tt_data + 1); hlist_for_each_entry_rcu(vlan, &bat_priv->softif_vlan_list, list) { + vlan_entries = atomic_read(&vlan->tt.num_entries); + if (vlan_entries < 1) + continue; + tt_vlan->vid = htons(vlan->vid); tt_vlan->crc = htonl(vlan->tt.crc); @@ -852,7 +877,7 @@ batadv_tt_prepare_tvlv_local_data(struct batadv_priv *bat_priv, *tt_change = (struct batadv_tvlv_tt_change *)tt_change_ptr; out: - rcu_read_unlock(); + spin_unlock_bh(&bat_priv->softif_vlan_list_lock); return tvlv_len; } @@ -940,7 +965,6 @@ int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset) struct batadv_tt_common_entry *tt_common_entry; struct batadv_tt_local_entry *tt_local; struct batadv_hard_iface *primary_if; - struct batadv_softif_vlan *vlan; struct hlist_head *head; unsigned short vid; u32 i; @@ -977,13 +1001,6 @@ int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset) no_purge = tt_common_entry->flags & np_flag; - vlan = batadv_softif_vlan_get(bat_priv, vid); - if (!vlan) { - seq_printf(seq, "Cannot retrieve VLAN %d\n", - BATADV_PRINT_VID(vid)); - continue; - } - seq_printf(seq, " * %pM %4i [%c%c%c%c%c%c] %3u.%03u (%#.8x)\n", tt_common_entry->addr, @@ -1001,9 +1018,7 @@ int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset) BATADV_TT_CLIENT_ISOLA) ? 'I' : '.'), no_purge ? 0 : last_seen_secs, no_purge ? 0 : last_seen_msecs, - vlan->tt.crc); - - batadv_softif_vlan_free_ref(vlan); + tt_local->vlan->tt.crc); } rcu_read_unlock(); } @@ -1046,10 +1061,10 @@ u16 batadv_tt_local_remove(struct batadv_priv *bat_priv, const u8 *addr, unsigned short vid, const char *message, bool roaming) { + struct batadv_tt_local_entry *tt_removed_entry; struct batadv_tt_local_entry *tt_local_entry; u16 flags, curr_flags = BATADV_NO_FLAGS; - struct batadv_softif_vlan *vlan; - void *tt_entry_exists; + struct hlist_node *tt_removed_node; tt_local_entry = batadv_tt_local_hash_find(bat_priv, addr, vid); if (!tt_local_entry) @@ -1078,23 +1093,18 @@ u16 batadv_tt_local_remove(struct batadv_priv *bat_priv, const u8 *addr, */ batadv_tt_local_event(bat_priv, tt_local_entry, BATADV_TT_CLIENT_DEL); - tt_entry_exists = batadv_hash_remove(bat_priv->tt.local_hash, + tt_removed_node = batadv_hash_remove(bat_priv->tt.local_hash, batadv_compare_tt, batadv_choose_tt, &tt_local_entry->common); - if (!tt_entry_exists) - goto out; - - /* extra call to free the local tt entry */ - batadv_tt_local_entry_free_ref(tt_local_entry); - - /* decrease the reference held for this vlan */ - vlan = batadv_softif_vlan_get(bat_priv, vid); - if (!vlan) + if (!tt_removed_node) goto out; - batadv_softif_vlan_free_ref(vlan); - batadv_softif_vlan_free_ref(vlan); + /* drop reference of remove hash entry */ + tt_removed_entry = hlist_entry(tt_removed_node, + struct batadv_tt_local_entry, + common.hash_entry); + batadv_tt_local_entry_free_ref(tt_removed_entry); out: if (tt_local_entry) @@ -1168,7 +1178,6 @@ static void batadv_tt_local_table_free(struct batadv_priv *bat_priv) spinlock_t *list_lock; /* protects write access to the hash lists */ struct batadv_tt_common_entry *tt_common_entry; struct batadv_tt_local_entry *tt_local; - struct batadv_softif_vlan *vlan; struct hlist_node *node_tmp; struct hlist_head *head; u32 i; @@ -1190,14 +1199,6 @@ static void batadv_tt_local_table_free(struct batadv_priv *bat_priv) struct batadv_tt_local_entry, common); - /* decrease the reference held for this vlan */ - vlan = batadv_softif_vlan_get(bat_priv, - tt_common_entry->vid); - if (vlan) { - batadv_softif_vlan_free_ref(vlan); - batadv_softif_vlan_free_ref(vlan); - } - batadv_tt_local_entry_free_ref(tt_local); } spin_unlock_bh(list_lock); @@ -1273,7 +1274,8 @@ batadv_tt_global_orig_entry_find(const struct batadv_tt_global_entry *entry, */ static bool batadv_tt_global_entry_has_orig(const struct batadv_tt_global_entry *entry, - const struct batadv_orig_node *orig_node) + const struct batadv_orig_node *orig_node, + u8 *flags) { struct batadv_tt_orig_list_entry *orig_entry; bool found = false; @@ -1281,25 +1283,64 @@ batadv_tt_global_entry_has_orig(const struct batadv_tt_global_entry *entry, orig_entry = batadv_tt_global_orig_entry_find(entry, orig_node); if (orig_entry) { found = true; + + if (flags) + *flags = orig_entry->flags; + batadv_tt_orig_list_entry_free_ref(orig_entry); } return found; } +/** + * batadv_tt_global_sync_flags - update TT sync flags + * @tt_global: the TT global entry to update sync flags in + * + * Updates the sync flag bits in the tt_global flag attribute with a logical + * OR of all sync flags from any of its TT orig entries. + */ +static void +batadv_tt_global_sync_flags(struct batadv_tt_global_entry *tt_global) +{ + struct batadv_tt_orig_list_entry *orig_entry; + const struct hlist_head *head; + u16 flags = BATADV_NO_FLAGS; + + rcu_read_lock(); + head = &tt_global->orig_list; + hlist_for_each_entry_rcu(orig_entry, head, list) + flags |= orig_entry->flags; + rcu_read_unlock(); + + flags |= tt_global->common.flags & (~BATADV_TT_SYNC_MASK); + tt_global->common.flags = flags; +} + +/** + * batadv_tt_global_orig_entry_add - add or update a TT orig entry + * @tt_global: the TT global entry to add an orig entry in + * @orig_node: the originator to add an orig entry for + * @ttvn: translation table version number of this changeset + * @flags: TT sync flags + */ static void batadv_tt_global_orig_entry_add(struct batadv_tt_global_entry *tt_global, - struct batadv_orig_node *orig_node, int ttvn) + struct batadv_orig_node *orig_node, int ttvn, + u8 flags) { struct batadv_tt_orig_list_entry *orig_entry; + spin_lock_bh(&tt_global->list_lock); + orig_entry = batadv_tt_global_orig_entry_find(tt_global, orig_node); if (orig_entry) { /* refresh the ttvn: the current value could be a bogus one that * was added during a "temporary client detection" */ orig_entry->ttvn = ttvn; - goto out; + orig_entry->flags = flags; + goto sync_flags; } orig_entry = kzalloc(sizeof(*orig_entry), GFP_ATOMIC); @@ -1311,17 +1352,20 @@ batadv_tt_global_orig_entry_add(struct batadv_tt_global_entry *tt_global, batadv_tt_global_size_inc(orig_node, tt_global->common.vid); orig_entry->orig_node = orig_node; orig_entry->ttvn = ttvn; + orig_entry->flags = flags; atomic_set(&orig_entry->refcount, 2); - spin_lock_bh(&tt_global->list_lock); hlist_add_head_rcu(&orig_entry->list, &tt_global->orig_list); - spin_unlock_bh(&tt_global->list_lock); atomic_inc(&tt_global->orig_list_count); +sync_flags: + batadv_tt_global_sync_flags(tt_global); out: if (orig_entry) batadv_tt_orig_list_entry_free_ref(orig_entry); + + spin_unlock_bh(&tt_global->list_lock); } /** @@ -1379,7 +1423,8 @@ static bool batadv_tt_global_add(struct batadv_priv *bat_priv, ether_addr_copy(common->addr, tt_addr); common->vid = vid; - common->flags = flags; + common->flags = flags & (~BATADV_TT_SYNC_MASK); + tt_global_entry->roam_at = 0; /* node must store current time in case of roaming. This is * needed to purge this entry out on timeout (if nobody claims @@ -1420,7 +1465,7 @@ static bool batadv_tt_global_add(struct batadv_priv *bat_priv, if (!(common->flags & BATADV_TT_CLIENT_TEMP)) goto out; if (batadv_tt_global_entry_has_orig(tt_global_entry, - orig_node)) + orig_node, NULL)) goto out_remove; batadv_tt_global_del_orig_list(tt_global_entry); goto add_orig_entry; @@ -1441,7 +1486,7 @@ static bool batadv_tt_global_add(struct batadv_priv *bat_priv, * TT_CLIENT_WIFI, therefore they have to be copied in the * client entry */ - tt_global_entry->common.flags |= flags; + tt_global_entry->common.flags |= flags & (~BATADV_TT_SYNC_MASK); /* If there is the BATADV_TT_CLIENT_ROAM flag set, there is only * one originator left in the list and we previously received a @@ -1458,7 +1503,8 @@ static bool batadv_tt_global_add(struct batadv_priv *bat_priv, } add_orig_entry: /* add the new orig_entry (if needed) or update it */ - batadv_tt_global_orig_entry_add(tt_global_entry, orig_node, ttvn); + batadv_tt_global_orig_entry_add(tt_global_entry, orig_node, ttvn, + flags & BATADV_TT_SYNC_MASK); batadv_dbg(BATADV_DBG_TT, bat_priv, "Creating new global tt entry: %pM (vid: %d, via %pM)\n", @@ -2111,6 +2157,7 @@ static u32 batadv_tt_global_crc(struct batadv_priv *bat_priv, unsigned short vid) { struct batadv_hashtable *hash = bat_priv->tt.global_hash; + struct batadv_tt_orig_list_entry *tt_orig; struct batadv_tt_common_entry *tt_common; struct batadv_tt_global_entry *tt_global; struct hlist_head *head; @@ -2149,8 +2196,9 @@ static u32 batadv_tt_global_crc(struct batadv_priv *bat_priv, /* find out if this global entry is announced by this * originator */ - if (!batadv_tt_global_entry_has_orig(tt_global, - orig_node)) + tt_orig = batadv_tt_global_orig_entry_find(tt_global, + orig_node); + if (!tt_orig) continue; /* use network order to read the VID: this ensures that @@ -2162,10 +2210,12 @@ static u32 batadv_tt_global_crc(struct batadv_priv *bat_priv, /* compute the CRC on flags that have to be kept in sync * among nodes */ - flags = tt_common->flags & BATADV_TT_SYNC_MASK; + flags = tt_orig->flags; crc_tmp = crc32c(crc_tmp, &flags, sizeof(flags)); crc ^= crc32c(crc_tmp, tt_common->addr, ETH_ALEN); + + batadv_tt_orig_list_entry_free_ref(tt_orig); } rcu_read_unlock(); } @@ -2230,6 +2280,29 @@ static u32 batadv_tt_local_crc(struct batadv_priv *bat_priv, return crc; } +/** + * batadv_tt_req_node_release - free tt_req node entry + * @ref: kref pointer of the tt req_node entry + */ +static void batadv_tt_req_node_release(struct kref *ref) +{ + struct batadv_tt_req_node *tt_req_node; + + tt_req_node = container_of(ref, struct batadv_tt_req_node, refcount); + + kfree(tt_req_node); +} + +/** + * batadv_tt_req_node_put - decrement the tt_req_node refcounter and + * possibly release it + * @tt_req_node: tt_req_node to be free'd + */ +static void batadv_tt_req_node_put(struct batadv_tt_req_node *tt_req_node) +{ + kref_put(&tt_req_node->refcount, batadv_tt_req_node_release); +} + static void batadv_tt_req_list_free(struct batadv_priv *bat_priv) { struct batadv_tt_req_node *node; @@ -2239,7 +2312,7 @@ static void batadv_tt_req_list_free(struct batadv_priv *bat_priv) hlist_for_each_entry_safe(node, safe, &bat_priv->tt.req_list, list) { hlist_del_init(&node->list); - kfree(node); + batadv_tt_req_node_put(node); } spin_unlock_bh(&bat_priv->tt.req_list_lock); @@ -2276,7 +2349,7 @@ static void batadv_tt_req_purge(struct batadv_priv *bat_priv) if (batadv_has_timed_out(node->issued_at, BATADV_TT_REQUEST_TIMEOUT)) { hlist_del_init(&node->list); - kfree(node); + batadv_tt_req_node_put(node); } } spin_unlock_bh(&bat_priv->tt.req_list_lock); @@ -2308,9 +2381,11 @@ batadv_tt_req_node_new(struct batadv_priv *bat_priv, if (!tt_req_node) goto unlock; + kref_init(&tt_req_node->refcount); ether_addr_copy(tt_req_node->addr, orig_node->orig); tt_req_node->issued_at = jiffies; + kref_get(&tt_req_node->refcount); hlist_add_head(&tt_req_node->list, &bat_priv->tt.req_list); unlock: spin_unlock_bh(&bat_priv->tt.req_list_lock); @@ -2324,17 +2399,24 @@ unlock: * * Returns 1 if the entry is a valid, 0 otherwise. */ -static int batadv_tt_local_valid(const void *entry_ptr, const void *data_ptr) +static int batadv_tt_local_valid(const void *entry_ptr, + const void *data_ptr, + u8 *flags) { const struct batadv_tt_common_entry *tt_common_entry = entry_ptr; if (tt_common_entry->flags & BATADV_TT_CLIENT_NEW) return 0; + + if (flags) + *flags = tt_common_entry->flags; + return 1; } static int batadv_tt_global_valid(const void *entry_ptr, - const void *data_ptr) + const void *data_ptr, + u8 *flags) { const struct batadv_tt_common_entry *tt_common_entry = entry_ptr; const struct batadv_tt_global_entry *tt_global_entry; @@ -2348,7 +2430,8 @@ static int batadv_tt_global_valid(const void *entry_ptr, struct batadv_tt_global_entry, common); - return batadv_tt_global_entry_has_orig(tt_global_entry, orig_node); + return batadv_tt_global_entry_has_orig(tt_global_entry, orig_node, + flags); } /** @@ -2364,18 +2447,25 @@ static int batadv_tt_global_valid(const void *entry_ptr, static void batadv_tt_tvlv_generate(struct batadv_priv *bat_priv, struct batadv_hashtable *hash, void *tvlv_buff, u16 tt_len, - int (*valid_cb)(const void *, const void *), + int (*valid_cb)(const void *, + const void *, + u8 *flags), void *cb_data) { struct batadv_tt_common_entry *tt_common_entry; struct batadv_tvlv_tt_change *tt_change; struct hlist_head *head; u16 tt_tot, tt_num_entries = 0; + u8 flags; + bool ret; u32 i; tt_tot = batadv_tt_entries(tt_len); tt_change = (struct batadv_tvlv_tt_change *)tvlv_buff; + if (!valid_cb) + return; + rcu_read_lock(); for (i = 0; i < hash->size; i++) { head = &hash->table[i]; @@ -2385,11 +2475,12 @@ static void batadv_tt_tvlv_generate(struct batadv_priv *bat_priv, if (tt_tot == tt_num_entries) break; - if ((valid_cb) && (!valid_cb(tt_common_entry, cb_data))) + ret = valid_cb(tt_common_entry, cb_data, &flags); + if (!ret) continue; ether_addr_copy(tt_change->addr, tt_common_entry->addr); - tt_change->flags = tt_common_entry->flags; + tt_change->flags = flags; tt_change->vid = htons(tt_common_entry->vid); memset(tt_change->reserved, 0, sizeof(tt_change->reserved)); @@ -2560,13 +2651,19 @@ static int batadv_send_tt_request(struct batadv_priv *bat_priv, out: if (primary_if) batadv_hardif_free_ref(primary_if); + if (ret && tt_req_node) { spin_lock_bh(&bat_priv->tt.req_list_lock); - /* hlist_del_init() verifies tt_req_node still is in the list */ - hlist_del_init(&tt_req_node->list); + if (!hlist_unhashed(&tt_req_node->list)) { + hlist_del_init(&tt_req_node->list); + batadv_tt_req_node_put(tt_req_node); + } spin_unlock_bh(&bat_priv->tt.req_list_lock); - kfree(tt_req_node); } + + if (tt_req_node) + batadv_tt_req_node_put(tt_req_node); + kfree(tvlv_tt_data); return ret; } @@ -3002,7 +3099,7 @@ static void batadv_handle_tt_response(struct batadv_priv *bat_priv, if (!batadv_compare_eth(node->addr, resp_src)) continue; hlist_del_init(&node->list); - kfree(node); + batadv_tt_req_node_put(node); } spin_unlock_bh(&bat_priv->tt.req_list_lock); @@ -3227,7 +3324,6 @@ static void batadv_tt_local_purge_pending_clients(struct batadv_priv *bat_priv) struct batadv_hashtable *hash = bat_priv->tt.local_hash; struct batadv_tt_common_entry *tt_common; struct batadv_tt_local_entry *tt_local; - struct batadv_softif_vlan *vlan; struct hlist_node *node_tmp; struct hlist_head *head; spinlock_t *list_lock; /* protects write access to the hash lists */ @@ -3257,13 +3353,6 @@ static void batadv_tt_local_purge_pending_clients(struct batadv_priv *bat_priv) struct batadv_tt_local_entry, common); - /* decrease the reference held for this vlan */ - vlan = batadv_softif_vlan_get(bat_priv, tt_common->vid); - if (vlan) { - batadv_softif_vlan_free_ref(vlan); - batadv_softif_vlan_free_ref(vlan); - } - batadv_tt_local_entry_free_ref(tt_local); } spin_unlock_bh(list_lock); diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index cbd347c2e4a5..8fce1241ad6d 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -77,11 +77,13 @@ enum batadv_dhcp_recipient { * @ogm_buff: buffer holding the OGM packet * @ogm_buff_len: length of the OGM packet buffer * @ogm_seqno: OGM sequence number - used to identify each OGM + * @ogm_buff_mutex: lock protecting ogm_buff and ogm_buff_len */ struct batadv_hard_iface_bat_iv { unsigned char *ogm_buff; int ogm_buff_len; atomic_t ogm_seqno; + struct mutex ogm_buff_mutex; }; /** @@ -103,7 +105,7 @@ struct batadv_hard_iface_bat_iv { */ struct batadv_hard_iface { struct list_head list; - s16 if_num; + unsigned int if_num; char if_status; struct net_device *net_dev; u8 num_bcasts; @@ -287,7 +289,9 @@ struct batadv_orig_node { DECLARE_BITMAP(bcast_bits, BATADV_TQ_LOCAL_WINDOW_SIZE); u32 last_bcast_seqno; struct hlist_head neigh_list; - /* neigh_list_lock protects: neigh_list and router */ + /* neigh_list_lock protects: neigh_list, ifinfo_list, + * last_bonding_candidate and router + */ spinlock_t neigh_list_lock; struct hlist_node hash_entry; struct batadv_priv *bat_priv; @@ -806,7 +810,7 @@ struct batadv_priv { atomic_t bcast_seqno; atomic_t bcast_queue_left; atomic_t batman_queue_left; - char num_ifaces; + unsigned int num_ifaces; struct kobject *mesh_obj; struct dentry *debug_dir; struct hlist_head forw_bat_list; @@ -884,6 +888,7 @@ struct batadv_socket_packet { * backbone gateway - no bcast traffic is formwared until the situation was * resolved * @crc: crc16 checksum over all claims + * @crc_lock: lock protecting crc * @refcount: number of contexts the object is used * @rcu: struct used for freeing in an RCU-safe manner */ @@ -897,6 +902,7 @@ struct batadv_bla_backbone_gw { atomic_t wait_periods; atomic_t request_sent; u16 crc; + spinlock_t crc_lock; /* protects crc */ atomic_t refcount; struct rcu_head rcu; }; @@ -915,6 +921,7 @@ struct batadv_bla_claim { u8 addr[ETH_ALEN]; unsigned short vid; struct batadv_bla_backbone_gw *backbone_gw; + spinlock_t backbone_lock; /* protects backbone_gw */ unsigned long lasttime; struct hlist_node hash_entry; struct rcu_head rcu; @@ -947,10 +954,12 @@ struct batadv_tt_common_entry { * struct batadv_tt_local_entry - translation table local entry data * @common: general translation table data * @last_seen: timestamp used for purging stale tt local entries + * @vlan: soft-interface vlan of the entry */ struct batadv_tt_local_entry { struct batadv_tt_common_entry common; unsigned long last_seen; + struct batadv_softif_vlan *vlan; }; /** @@ -973,6 +982,7 @@ struct batadv_tt_global_entry { * struct batadv_tt_orig_list_entry - orig node announcing a non-mesh client * @orig_node: pointer to orig node announcing this non-mesh client * @ttvn: translation table version number which added the non-mesh client + * @flags: per orig entry TT sync flags * @list: list node for batadv_tt_global_entry::orig_list * @refcount: number of contexts the object is used * @rcu: struct used for freeing in an RCU-safe manner @@ -980,6 +990,7 @@ struct batadv_tt_global_entry { struct batadv_tt_orig_list_entry { struct batadv_orig_node *orig_node; u8 ttvn; + u8 flags; struct hlist_node list; atomic_t refcount; struct rcu_head rcu; @@ -999,11 +1010,13 @@ struct batadv_tt_change_node { * struct batadv_tt_req_node - data to keep track of the tt requests in flight * @addr: mac address address of the originator this request was sent to * @issued_at: timestamp used for purging stale tt requests + * @refcount: number of contexts the object is used by * @list: list node for batadv_priv_tt::req_list */ struct batadv_tt_req_node { u8 addr[ETH_ALEN]; unsigned long issued_at; + struct kref refcount; struct hlist_node list; }; @@ -1168,9 +1181,9 @@ struct batadv_algo_ops { struct batadv_hard_iface *hard_iface); void (*bat_orig_free)(struct batadv_orig_node *orig_node); int (*bat_orig_add_if)(struct batadv_orig_node *orig_node, - int max_if_num); + unsigned int max_if_num); int (*bat_orig_del_if)(struct batadv_orig_node *orig_node, - int max_if_num, int del_if_num); + unsigned int max_if_num, unsigned int del_if_num); }; /** diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 365de66436ac..2fd4aae8f285 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -570,7 +570,7 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, frh = nlmsg_data(nlh); frh->family = ops->family; - frh->table = rule->table; + frh->table = rule->table < 256 ? rule->table : RT_TABLE_COMPAT; if (nla_put_u32(skb, FRA_TABLE, rule->table)) goto nla_put_failure; if (nla_put_u32(skb, FRA_SUPPRESS_PREFIXLEN, rule->suppress_prefixlen)) diff --git a/net/ieee802154/nl_policy.c b/net/ieee802154/nl_policy.c index 35c432668454..040983fc15da 100644 --- a/net/ieee802154/nl_policy.c +++ b/net/ieee802154/nl_policy.c @@ -30,7 +30,13 @@ const struct nla_policy ieee802154_policy[IEEE802154_ATTR_MAX + 1] = { [IEEE802154_ATTR_HW_ADDR] = { .type = NLA_HW_ADDR, }, [IEEE802154_ATTR_PAN_ID] = { .type = NLA_U16, }, [IEEE802154_ATTR_CHANNEL] = { .type = NLA_U8, }, + [IEEE802154_ATTR_BCN_ORD] = { .type = NLA_U8, }, + [IEEE802154_ATTR_SF_ORD] = { .type = NLA_U8, }, + [IEEE802154_ATTR_PAN_COORD] = { .type = NLA_U8, }, + [IEEE802154_ATTR_BAT_EXT] = { .type = NLA_U8, }, + [IEEE802154_ATTR_COORD_REALIGN] = { .type = NLA_U8, }, [IEEE802154_ATTR_PAGE] = { .type = NLA_U8, }, + [IEEE802154_ATTR_DEV_TYPE] = { .type = NLA_U8, }, [IEEE802154_ATTR_COORD_SHORT_ADDR] = { .type = NLA_U16, }, [IEEE802154_ATTR_COORD_HW_ADDR] = { .type = NLA_HW_ADDR, }, [IEEE802154_ATTR_COORD_PAN_ID] = { .type = NLA_U16, }, diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 7fe643062013..98ed5e43ab7b 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1809,6 +1809,7 @@ void cipso_v4_error(struct sk_buff *skb, int error, u32 gateway) { unsigned char optbuf[sizeof(struct ip_options) + 40]; struct ip_options *opt = (struct ip_options *)optbuf; + int res; if (ip_hdr(skb)->protocol == IPPROTO_ICMP || error != -EACCES) return; @@ -1820,7 +1821,11 @@ void cipso_v4_error(struct sk_buff *skb, int error, u32 gateway) memset(opt, 0, sizeof(struct ip_options)); opt->optlen = ip_hdr(skb)->ihl*4 - sizeof(struct iphdr); - if (__ip_options_compile(dev_net(skb->dev), opt, skb, NULL)) + rcu_read_lock(); + res = __ip_options_compile(dev_net(skb->dev), opt, skb, NULL); + rcu_read_unlock(); + + if (res) return; if (gateway) diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index c23e02a7ccb0..30eb8bdcdbda 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -780,8 +780,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, found++; break; } - if (rt_can_ecmp) - fallback_ins = fallback_ins ?: ins; + fallback_ins = fallback_ins ?: ins; goto next_iter; } @@ -821,7 +820,9 @@ next_iter: } if (fallback_ins && !found) { - /* No ECMP-able route found, replace first non-ECMP one */ + /* No matching route with same ecmp-able-ness found, replace + * first matching route + */ ins = fallback_ins; iter = *ins; found++; diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 71263754b19b..bd2a6ec7572a 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -185,9 +185,15 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, retv = -EBUSY; break; } - } else if (sk->sk_protocol != IPPROTO_TCP) + } else if (sk->sk_protocol == IPPROTO_TCP) { + if (sk->sk_prot != &tcpv6_prot) { + retv = -EBUSY; + break; + } break; - + } else { + break; + } if (sk->sk_state != TCP_ESTABLISHED) { retv = -ENOTCONN; break; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index fffd2ad28942..63a7d31fa9f0 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2953,6 +2953,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg) */ cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL | NLM_F_REPLACE); + cfg->fc_nlinfo.nlh->nlmsg_flags |= NLM_F_CREATE; nhn++; } diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 2214c77d4172..4301a92fc160 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -939,16 +939,22 @@ u32 ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, elem_parse_failed = true; break; case WLAN_EID_VHT_OPERATION: - if (elen >= sizeof(struct ieee80211_vht_operation)) + if (elen >= sizeof(struct ieee80211_vht_operation)) { elems->vht_operation = (void *)pos; - else - elem_parse_failed = true; + if (calc_crc) + crc = crc32_be(crc, pos - 2, elen + 2); + break; + } + elem_parse_failed = true; break; case WLAN_EID_OPMODE_NOTIF: - if (elen > 0) + if (elen > 0) { elems->opmode_notif = pos; - else - elem_parse_failed = true; + if (calc_crc) + crc = crc32_be(crc, pos - 2, elen + 2); + break; + } + elem_parse_failed = true; break; case WLAN_EID_MESH_ID: elems->mesh_id = pos; diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c index ac143ae4f7b6..8c1733869343 100644 --- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -711,6 +711,8 @@ static const struct nla_policy nfnl_cthelper_policy[NFCTH_MAX+1] = { [NFCTH_NAME] = { .type = NLA_NUL_STRING, .len = NF_CT_HELPER_NAME_LEN-1 }, [NFCTH_QUEUE_NUM] = { .type = NLA_U32, }, + [NFCTH_PRIV_DATA_LEN] = { .type = NLA_U32, }, + [NFCTH_STATUS] = { .type = NLA_U32, }, }; static const struct nfnl_callback nfnl_cthelper_cb[NFNL_MSG_CTHELPER_MAX] = { diff --git a/net/netfilter/xt_bpf.c b/net/netfilter/xt_bpf.c index dffee9d47ec4..7b993f25aab9 100644 --- a/net/netfilter/xt_bpf.c +++ b/net/netfilter/xt_bpf.c @@ -25,6 +25,9 @@ static int bpf_mt_check(const struct xt_mtchk_param *par) struct xt_bpf_info *info = par->matchinfo; struct sock_fprog_kern program; + if (info->bpf_program_num_elem > XT_BPF_MAX_NUM_INSTR) + return -EINVAL; + program.len = info->bpf_program_num_elem; program.filter = info->bpf_program; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index bf292010760a..cc37a219e11e 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1003,7 +1003,8 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, if (nlk->netlink_bind && groups) { int group; - for (group = 0; group < nlk->ngroups; group++) { + /* nl_groups is a u32, so cap the maximum groups we can bind */ + for (group = 0; group < BITS_PER_TYPE(u32); group++) { if (!test_bit(group, &groups)) continue; err = nlk->netlink_bind(net, group + 1); @@ -1022,7 +1023,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, netlink_insert(sk, nladdr->nl_pid) : netlink_autobind(sock); if (err) { - netlink_undo_bind(nlk->ngroups, groups, sk); + netlink_undo_bind(BITS_PER_TYPE(u32), groups, sk); return err; } } diff --git a/net/nfc/hci/core.c b/net/nfc/hci/core.c index 5a58f9f38095..291f24fef19a 100644 --- a/net/nfc/hci/core.c +++ b/net/nfc/hci/core.c @@ -193,13 +193,20 @@ exit: void nfc_hci_cmd_received(struct nfc_hci_dev *hdev, u8 pipe, u8 cmd, struct sk_buff *skb) { - u8 gate = hdev->pipes[pipe].gate; u8 status = NFC_HCI_ANY_OK; struct hci_create_pipe_resp *create_info; struct hci_delete_pipe_noti *delete_info; struct hci_all_pipe_cleared_noti *cleared_info; + u8 gate; - pr_debug("from gate %x pipe %x cmd %x\n", gate, pipe, cmd); + pr_debug("from pipe %x cmd %x\n", pipe, cmd); + + if (pipe >= NFC_HCI_MAX_PIPES) { + status = NFC_HCI_ANY_E_NOK; + goto exit; + } + + gate = hdev->pipes[pipe].gate; switch (cmd) { case NFC_HCI_ADM_NOTIFY_PIPE_CREATED: @@ -387,8 +394,14 @@ void nfc_hci_event_received(struct nfc_hci_dev *hdev, u8 pipe, u8 event, struct sk_buff *skb) { int r = 0; - u8 gate = hdev->pipes[pipe].gate; + u8 gate; + + if (pipe >= NFC_HCI_MAX_PIPES) { + pr_err("Discarded event %x to invalid pipe %x\n", event, pipe); + goto exit; + } + gate = hdev->pipes[pipe].gate; if (gate == NFC_HCI_INVALID_GATE) { pr_err("Discarded event %x to unopened pipe %x\n", event, pipe); goto exit; diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index 04d4c388a7a8..c9d5e9c62178 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -62,7 +62,10 @@ static const struct nla_policy nfc_genl_policy[NFC_ATTR_MAX + 1] = { [NFC_ATTR_LLC_SDP] = { .type = NLA_NESTED }, [NFC_ATTR_FIRMWARE_NAME] = { .type = NLA_STRING, .len = NFC_FIRMWARE_NAME_MAXSIZE }, + [NFC_ATTR_SE_INDEX] = { .type = NLA_U32 }, [NFC_ATTR_SE_APDU] = { .type = NLA_BINARY }, + [NFC_ATTR_VENDOR_ID] = { .type = NLA_U32 }, + [NFC_ATTR_VENDOR_SUBCMD] = { .type = NLA_U32 }, [NFC_ATTR_VENDOR_DATA] = { .type = NLA_BINARY }, }; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index e5a58c82728a..5ab8205f988b 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -127,6 +127,7 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct fl_flow_key skb_key; struct fl_flow_key skb_mkey; + flow_dissector_init_keys(&skb_key.control, &skb_key.basic); fl_clear_masked_range(&skb_key, &head->mask); skb_key.indev_ifindex = skb->skb_iif; /* skb_flow_dissect() does not set n_proto in case an unknown protocol, diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index fb99872ef426..eb814ffc0902 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -668,6 +668,7 @@ static const struct nla_policy fq_policy[TCA_FQ_MAX + 1] = { [TCA_FQ_FLOW_MAX_RATE] = { .type = NLA_U32 }, [TCA_FQ_BUCKETS_LOG] = { .type = NLA_U32 }, [TCA_FQ_FLOW_REFILL_DELAY] = { .type = NLA_U32 }, + [TCA_FQ_ORPHAN_MASK] = { .type = NLA_U32 }, }; static int fq_change(struct Qdisc *sch, struct nlattr *opt) diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index df9ac3746c1b..adaaaaad527d 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -177,6 +177,16 @@ sctp_chunk_length_valid(struct sctp_chunk *chunk, return 1; } +/* Check for format error in an ABORT chunk */ +static inline bool sctp_err_chunk_valid(struct sctp_chunk *chunk) +{ + struct sctp_errhdr *err; + + sctp_walk_errors(err, chunk->chunk_hdr); + + return (void *)err == (void *)chunk->chunk_end; +} + /********************************************************** * These are the state functions for handling chunk events. **********************************************************/ @@ -2159,6 +2169,9 @@ sctp_disposition_t sctp_sf_shutdown_pending_abort( sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest)) return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands); + if (!sctp_err_chunk_valid(chunk)) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + return __sctp_sf_do_9_1_abort(net, ep, asoc, type, arg, commands); } @@ -2201,6 +2214,9 @@ sctp_disposition_t sctp_sf_shutdown_sent_abort(struct net *net, sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest)) return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands); + if (!sctp_err_chunk_valid(chunk)) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + /* Stop the T2-shutdown timer. */ sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, SCTP_TO(SCTP_EVENT_TIMEOUT_T2_SHUTDOWN)); @@ -2466,6 +2482,9 @@ sctp_disposition_t sctp_sf_do_9_1_abort(struct net *net, sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest)) return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands); + if (!sctp_err_chunk_valid(chunk)) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + return __sctp_sf_do_9_1_abort(net, ep, asoc, type, arg, commands); } @@ -2482,15 +2501,9 @@ static sctp_disposition_t __sctp_sf_do_9_1_abort(struct net *net, /* See if we have an error cause code in the chunk. */ len = ntohs(chunk->chunk_hdr->length); - if (len >= sizeof(struct sctp_chunkhdr) + sizeof(struct sctp_errhdr)) { - - sctp_errhdr_t *err; - sctp_walk_errors(err, chunk->chunk_hdr); - if ((void *)err != (void *)chunk->chunk_end) - return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + if (len >= sizeof(struct sctp_chunkhdr) + sizeof(struct sctp_errhdr)) error = ((sctp_errhdr_t *)chunk->skb->data)->cause; - } sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ECONNRESET)); /* ASSOC_FAILED will DELETE_TCB. */ diff --git a/net/wireless/ethtool.c b/net/wireless/ethtool.c index e9e91298c70d..3cedf2c2b60b 100644 --- a/net/wireless/ethtool.c +++ b/net/wireless/ethtool.c @@ -6,9 +6,13 @@ void cfg80211_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { struct wireless_dev *wdev = dev->ieee80211_ptr; + struct device *pdev = wiphy_dev(wdev->wiphy); - strlcpy(info->driver, wiphy_dev(wdev->wiphy)->driver->name, - sizeof(info->driver)); + if (pdev->driver) + strlcpy(info->driver, pdev->driver->name, + sizeof(info->driver)); + else + strlcpy(info->driver, "N/A", sizeof(info->driver)); strlcpy(info->version, init_utsname()->release, sizeof(info->version)); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index fd0bf278067e..c6c168f20b0f 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -330,6 +330,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_CONTROL_PORT_ETHERTYPE] = { .type = NLA_U16 }, [NL80211_ATTR_CONTROL_PORT_NO_ENCRYPT] = { .type = NLA_FLAG }, [NL80211_ATTR_PRIVACY] = { .type = NLA_FLAG }, + [NL80211_ATTR_STATUS_CODE] = { .type = NLA_U16 }, [NL80211_ATTR_CIPHER_SUITE_GROUP] = { .type = NLA_U32 }, [NL80211_ATTR_WPA_VERSIONS] = { .type = NLA_U32 }, [NL80211_ATTR_PID] = { .type = NLA_U32 }, @@ -403,6 +404,8 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_MDID] = { .type = NLA_U16 }, [NL80211_ATTR_IE_RIC] = { .type = NLA_BINARY, .len = IEEE80211_MAX_DATA_LEN }, + [NL80211_ATTR_CRIT_PROT_ID] = { .type = NLA_U16 }, + [NL80211_ATTR_MAX_CRIT_PROT_DURATION] = { .type = NLA_U16 }, [NL80211_ATTR_PEER_AID] = { .type = NLA_U16 }, [NL80211_ATTR_CH_SWITCH_COUNT] = { .type = NLA_U32 }, [NL80211_ATTR_CH_SWITCH_BLOCK_TX] = { .type = NLA_FLAG }, @@ -428,6 +431,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_USER_PRIO] = { .type = NLA_U8 }, [NL80211_ATTR_ADMITTED_TIME] = { .type = NLA_U16 }, [NL80211_ATTR_SMPS_MODE] = { .type = NLA_U8 }, + [NL80211_ATTR_OPER_CLASS] = { .type = NLA_U8 }, [NL80211_ATTR_MAC_MASK] = { .len = ETH_ALEN }, [NL80211_ATTR_WIPHY_SELF_MANAGED_REG] = { .type = NLA_FLAG }, [NL80211_ATTR_NETNS_FD] = { .type = NLA_U32 }, diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c index 138d7f100f7e..4216940e875d 100644 --- a/scripts/kconfig/confdata.c +++ b/scripts/kconfig/confdata.c @@ -1236,7 +1236,7 @@ bool conf_set_all_new_symbols(enum conf_def_mode mode) sym_calc_value(csym); if (mode == def_random) - has_changed = randomize_choice_values(csym); + has_changed |= randomize_choice_values(csym); else { set_all_choice_values(csym); has_changed = true; diff --git a/security/selinux/avc.c b/security/selinux/avc.c index 52f3c550abcc..f3c473791b69 100644 --- a/security/selinux/avc.c +++ b/security/selinux/avc.c @@ -865,7 +865,7 @@ static int avc_update_node(u32 event, u32 perms, u8 driver, u8 xperm, u32 ssid, if (orig->ae.xp_node) { rc = avc_xperms_populate(node, orig->ae.xp_node); if (rc) { - kmem_cache_free(avc_node_cachep, node); + avc_node_kill(node); goto out_unlock; } } diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c index 331a2b00e53f..4c31db1246c3 100644 --- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -577,7 +577,7 @@ static int update_timestamp_of_queue(struct snd_seq_event *event, event->queue = queue; event->flags &= ~SNDRV_SEQ_TIME_STAMP_MASK; if (real_time) { - event->time.time = snd_seq_timer_get_cur_time(q->timer); + event->time.time = snd_seq_timer_get_cur_time(q->timer, true); event->flags |= SNDRV_SEQ_TIME_STAMP_REAL; } else { event->time.tick = snd_seq_timer_get_cur_tick(q->timer); @@ -1694,7 +1694,7 @@ static int snd_seq_ioctl_get_queue_status(struct snd_seq_client *client, tmr = queue->timer; status.events = queue->tickq->cells + queue->timeq->cells; - status.time = snd_seq_timer_get_cur_time(tmr); + status.time = snd_seq_timer_get_cur_time(tmr, true); status.tick = snd_seq_timer_get_cur_tick(tmr); status.running = tmr->running; diff --git a/sound/core/seq/seq_queue.c b/sound/core/seq/seq_queue.c index 1a6dc4ff44a6..ea1aa0796276 100644 --- a/sound/core/seq/seq_queue.c +++ b/sound/core/seq/seq_queue.c @@ -261,6 +261,8 @@ void snd_seq_check_queue(struct snd_seq_queue *q, int atomic, int hop) { unsigned long flags; struct snd_seq_event_cell *cell; + snd_seq_tick_time_t cur_tick; + snd_seq_real_time_t cur_time; if (q == NULL) return; @@ -277,17 +279,18 @@ void snd_seq_check_queue(struct snd_seq_queue *q, int atomic, int hop) __again: /* Process tick queue... */ + cur_tick = snd_seq_timer_get_cur_tick(q->timer); for (;;) { - cell = snd_seq_prioq_cell_out(q->tickq, - &q->timer->tick.cur_tick); + cell = snd_seq_prioq_cell_out(q->tickq, &cur_tick); if (!cell) break; snd_seq_dispatch_event(cell, atomic, hop); } /* Process time queue... */ + cur_time = snd_seq_timer_get_cur_time(q->timer, false); for (;;) { - cell = snd_seq_prioq_cell_out(q->timeq, &q->timer->cur_time); + cell = snd_seq_prioq_cell_out(q->timeq, &cur_time); if (!cell) break; snd_seq_dispatch_event(cell, atomic, hop); @@ -415,6 +418,7 @@ int snd_seq_queue_check_access(int queueid, int client) int snd_seq_queue_set_owner(int queueid, int client, int locked) { struct snd_seq_queue *q = queueptr(queueid); + unsigned long flags; if (q == NULL) return -EINVAL; @@ -424,8 +428,10 @@ int snd_seq_queue_set_owner(int queueid, int client, int locked) return -EPERM; } + spin_lock_irqsave(&q->owner_lock, flags); q->locked = locked ? 1 : 0; q->owner = client; + spin_unlock_irqrestore(&q->owner_lock, flags); queue_access_unlock(q); queuefree(q); @@ -564,15 +570,17 @@ void snd_seq_queue_client_termination(int client) unsigned long flags; int i; struct snd_seq_queue *q; + bool matched; for (i = 0; i < SNDRV_SEQ_MAX_QUEUES; i++) { if ((q = queueptr(i)) == NULL) continue; spin_lock_irqsave(&q->owner_lock, flags); - if (q->owner == client) + matched = (q->owner == client); + if (matched) q->klocked = 1; spin_unlock_irqrestore(&q->owner_lock, flags); - if (q->owner == client) { + if (matched) { if (q->timer->running) snd_seq_timer_stop(q->timer); snd_seq_timer_reset(q->timer); @@ -764,6 +772,8 @@ void snd_seq_info_queues_read(struct snd_info_entry *entry, int i, bpm; struct snd_seq_queue *q; struct snd_seq_timer *tmr; + bool locked; + int owner; for (i = 0; i < SNDRV_SEQ_MAX_QUEUES; i++) { if ((q = queueptr(i)) == NULL) @@ -775,9 +785,14 @@ void snd_seq_info_queues_read(struct snd_info_entry *entry, else bpm = 0; + spin_lock_irq(&q->owner_lock); + locked = q->locked; + owner = q->owner; + spin_unlock_irq(&q->owner_lock); + snd_iprintf(buffer, "queue %d: [%s]\n", q->queue, q->name); - snd_iprintf(buffer, "owned by client : %d\n", q->owner); - snd_iprintf(buffer, "lock status : %s\n", q->locked ? "Locked" : "Free"); + snd_iprintf(buffer, "owned by client : %d\n", owner); + snd_iprintf(buffer, "lock status : %s\n", locked ? "Locked" : "Free"); snd_iprintf(buffer, "queued time events : %d\n", snd_seq_prioq_avail(q->timeq)); snd_iprintf(buffer, "queued tick events : %d\n", snd_seq_prioq_avail(q->tickq)); snd_iprintf(buffer, "timer state : %s\n", tmr->running ? "Running" : "Stopped"); diff --git a/sound/core/seq/seq_timer.c b/sound/core/seq/seq_timer.c index c526201fd0df..adc820f874ee 100644 --- a/sound/core/seq/seq_timer.c +++ b/sound/core/seq/seq_timer.c @@ -436,14 +436,15 @@ int snd_seq_timer_continue(struct snd_seq_timer *tmr) } /* return current 'real' time. use timeofday() to get better granularity. */ -snd_seq_real_time_t snd_seq_timer_get_cur_time(struct snd_seq_timer *tmr) +snd_seq_real_time_t snd_seq_timer_get_cur_time(struct snd_seq_timer *tmr, + bool adjust_ktime) { snd_seq_real_time_t cur_time; unsigned long flags; spin_lock_irqsave(&tmr->lock, flags); cur_time = tmr->cur_time; - if (tmr->running) { + if (adjust_ktime && tmr->running) { struct timeval tm; int usec; do_gettimeofday(&tm); @@ -465,7 +466,13 @@ snd_seq_real_time_t snd_seq_timer_get_cur_time(struct snd_seq_timer *tmr) high PPQ values) */ snd_seq_tick_time_t snd_seq_timer_get_cur_tick(struct snd_seq_timer *tmr) { - return tmr->tick.cur_tick; + snd_seq_tick_time_t cur_tick; + unsigned long flags; + + spin_lock_irqsave(&tmr->lock, flags); + cur_tick = tmr->tick.cur_tick; + spin_unlock_irqrestore(&tmr->lock, flags); + return cur_tick; } diff --git a/sound/core/seq/seq_timer.h b/sound/core/seq/seq_timer.h index 88dfb71805ae..6221a43c307a 100644 --- a/sound/core/seq/seq_timer.h +++ b/sound/core/seq/seq_timer.h @@ -135,7 +135,8 @@ int snd_seq_timer_set_ppq(struct snd_seq_timer *tmr, int ppq); int snd_seq_timer_set_position_tick(struct snd_seq_timer *tmr, snd_seq_tick_time_t position); int snd_seq_timer_set_position_time(struct snd_seq_timer *tmr, snd_seq_real_time_t position); int snd_seq_timer_set_skew(struct snd_seq_timer *tmr, unsigned int skew, unsigned int base); -snd_seq_real_time_t snd_seq_timer_get_cur_time(struct snd_seq_timer *tmr); +snd_seq_real_time_t snd_seq_timer_get_cur_time(struct snd_seq_timer *tmr, + bool adjust_ktime); snd_seq_tick_time_t snd_seq_timer_get_cur_tick(struct snd_seq_timer *tmr); extern int seq_default_timer_class; diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c index ad0b23a21bc8..16664b07b553 100644 --- a/sound/pci/hda/hda_codec.c +++ b/sound/pci/hda/hda_codec.c @@ -4098,7 +4098,7 @@ void snd_print_pcm_bits(int pcm, char *buf, int buflen) for (i = 0, j = 0; i < ARRAY_SIZE(bits); i++) if (pcm & (AC_SUPPCM_BITS_8 << i)) - j += snprintf(buf + j, buflen - j, " %d", bits[i]); + j += scnprintf(buf + j, buflen - j, " %d", bits[i]); buf[j] = '\0'; /* necessary when j == 0 */ } diff --git a/sound/pci/hda/hda_eld.c b/sound/pci/hda/hda_eld.c index 563984dd2562..d469c76b5e92 100644 --- a/sound/pci/hda/hda_eld.c +++ b/sound/pci/hda/hda_eld.c @@ -385,7 +385,7 @@ static void hdmi_print_pcm_rates(int pcm, char *buf, int buflen) for (i = 0, j = 0; i < ARRAY_SIZE(alsa_rates); i++) if (pcm & (1 << i)) - j += snprintf(buf + j, buflen - j, " %d", + j += scnprintf(buf + j, buflen - j, " %d", alsa_rates[i]); buf[j] = '\0'; /* necessary when j == 0 */ diff --git a/sound/pci/hda/hda_sysfs.c b/sound/pci/hda/hda_sysfs.c index 9739fce9e032..f3ac19d33bd4 100644 --- a/sound/pci/hda/hda_sysfs.c +++ b/sound/pci/hda/hda_sysfs.c @@ -221,7 +221,7 @@ static ssize_t init_verbs_show(struct device *dev, mutex_lock(&codec->user_mutex); for (i = 0; i < codec->init_verbs.used; i++) { struct hda_verb *v = snd_array_elem(&codec->init_verbs, i); - len += snprintf(buf + len, PAGE_SIZE - len, + len += scnprintf(buf + len, PAGE_SIZE - len, "0x%02x 0x%03x 0x%04x\n", v->nid, v->verb, v->param); } @@ -271,7 +271,7 @@ static ssize_t hints_show(struct device *dev, mutex_lock(&codec->user_mutex); for (i = 0; i < codec->hints.used; i++) { struct hda_hint *hint = snd_array_elem(&codec->hints, i); - len += snprintf(buf + len, PAGE_SIZE - len, + len += scnprintf(buf + len, PAGE_SIZE - len, "%s = %s\n", hint->key, hint->val); } mutex_unlock(&codec->user_mutex); diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index 05e745e2f427..3150ddfbdb25 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -866,6 +866,7 @@ static const struct snd_pci_quirk cxt5066_fixups[] = { SND_PCI_QUIRK(0x17aa, 0x215f, "Lenovo T510", CXT_PINCFG_LENOVO_TP410), SND_PCI_QUIRK(0x17aa, 0x21ce, "Lenovo T420", CXT_PINCFG_LENOVO_TP410), SND_PCI_QUIRK(0x17aa, 0x21cf, "Lenovo T520", CXT_PINCFG_LENOVO_TP410), + SND_PCI_QUIRK(0x17aa, 0x21d2, "Lenovo T420s", CXT_PINCFG_LENOVO_TP410), SND_PCI_QUIRK(0x17aa, 0x21da, "Lenovo X220", CXT_PINCFG_LENOVO_TP410), SND_PCI_QUIRK(0x17aa, 0x21db, "Lenovo X220-tablet", CXT_PINCFG_LENOVO_TP410), SND_PCI_QUIRK(0x17aa, 0x38af, "Lenovo IdeaPad Z560", CXT_FIXUP_MUTE_LED_EAPD), diff --git a/sound/sh/aica.c b/sound/sh/aica.c index ad3d9ae38034..dd601b39f69e 100644 --- a/sound/sh/aica.c +++ b/sound/sh/aica.c @@ -120,10 +120,10 @@ static void spu_memset(u32 toi, u32 what, int length) } /* spu_memload - write to SPU address space */ -static void spu_memload(u32 toi, void *from, int length) +static void spu_memload(u32 toi, const void *from, int length) { unsigned long flags; - u32 *froml = from; + const u32 *froml = from; u32 __iomem *to = (u32 __iomem *) (SPU_MEMORY_BASE + toi); int i; u32 val; diff --git a/sound/soc/atmel/Kconfig b/sound/soc/atmel/Kconfig index 2d30464b81ce..d7b471c69f4f 100644 --- a/sound/soc/atmel/Kconfig +++ b/sound/soc/atmel/Kconfig @@ -24,6 +24,8 @@ config SND_ATMEL_SOC_DMA config SND_ATMEL_SOC_SSC_DMA tristate + select SND_ATMEL_SOC_DMA + select SND_ATMEL_SOC_PDC config SND_ATMEL_SOC_SSC tristate diff --git a/sound/soc/codecs/pcm512x.c b/sound/soc/codecs/pcm512x.c index 047c48953a20..1a90732e7621 100644 --- a/sound/soc/codecs/pcm512x.c +++ b/sound/soc/codecs/pcm512x.c @@ -1439,13 +1439,15 @@ int pcm512x_probe(struct device *dev, struct regmap *regmap) } pcm512x->sclk = devm_clk_get(dev, NULL); - if (PTR_ERR(pcm512x->sclk) == -EPROBE_DEFER) - return -EPROBE_DEFER; + if (PTR_ERR(pcm512x->sclk) == -EPROBE_DEFER) { + ret = -EPROBE_DEFER; + goto err; + } if (!IS_ERR(pcm512x->sclk)) { ret = clk_prepare_enable(pcm512x->sclk); if (ret != 0) { dev_err(dev, "Failed to enable SCLK: %d\n", ret); - return ret; + goto err; } } diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index 7e26d173da41..b245379b4dfc 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -4317,7 +4317,7 @@ static void soc_dapm_shutdown_dapm(struct snd_soc_dapm_context *dapm) continue; if (w->power) { dapm_seq_insert(w, &down_list, false); - w->power = 0; + w->new_power = 0; powerdown = 1; } } diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index 81bedd9bb922..7cffa98ec313 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -2866,16 +2866,16 @@ static ssize_t dpcm_show_state(struct snd_soc_pcm_runtime *fe, ssize_t offset = 0; /* FE state */ - offset += snprintf(buf + offset, size - offset, + offset += scnprintf(buf + offset, size - offset, "[%s - %s]\n", fe->dai_link->name, stream ? "Capture" : "Playback"); - offset += snprintf(buf + offset, size - offset, "State: %s\n", + offset += scnprintf(buf + offset, size - offset, "State: %s\n", dpcm_state_string(fe->dpcm[stream].state)); if ((fe->dpcm[stream].state >= SND_SOC_DPCM_STATE_HW_PARAMS) && (fe->dpcm[stream].state <= SND_SOC_DPCM_STATE_STOP)) - offset += snprintf(buf + offset, size - offset, + offset += scnprintf(buf + offset, size - offset, "Hardware Params: " "Format = %s, Channels = %d, Rate = %d\n", snd_pcm_format_name(params_format(params)), @@ -2883,10 +2883,10 @@ static ssize_t dpcm_show_state(struct snd_soc_pcm_runtime *fe, params_rate(params)); /* BEs state */ - offset += snprintf(buf + offset, size - offset, "Backends:\n"); + offset += scnprintf(buf + offset, size - offset, "Backends:\n"); if (list_empty(&fe->dpcm[stream].be_clients)) { - offset += snprintf(buf + offset, size - offset, + offset += scnprintf(buf + offset, size - offset, " No active DSP links\n"); goto out; } @@ -2895,16 +2895,16 @@ static ssize_t dpcm_show_state(struct snd_soc_pcm_runtime *fe, struct snd_soc_pcm_runtime *be = dpcm->be; params = &dpcm->hw_params; - offset += snprintf(buf + offset, size - offset, + offset += scnprintf(buf + offset, size - offset, "- %s\n", be->dai_link->name); - offset += snprintf(buf + offset, size - offset, + offset += scnprintf(buf + offset, size - offset, " State: %s\n", dpcm_state_string(be->dpcm[stream].state)); if ((be->dpcm[stream].state >= SND_SOC_DPCM_STATE_HW_PARAMS) && (be->dpcm[stream].state <= SND_SOC_DPCM_STATE_STOP)) - offset += snprintf(buf + offset, size - offset, + offset += scnprintf(buf + offset, size - offset, " Hardware Params: " "Format = %s, Channels = %d, Rate = %d\n", snd_pcm_format_name(params_format(params)), diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 5e50386c8ebb..b7a7bf0e566c 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1150,6 +1150,7 @@ bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip) case USB_ID(0x1de7, 0x0014): /* Phoenix Audio TMX320 */ case USB_ID(0x1de7, 0x0114): /* Phoenix Audio MT202pcs */ case USB_ID(0x21B4, 0x0081): /* AudioQuest DragonFly */ + case USB_ID(0x2912, 0x30c8): /* Audioengine D1 */ return true; } return false; diff --git a/sound/usb/usx2y/usX2Yhwdep.c b/sound/usb/usx2y/usX2Yhwdep.c index 0b34dbc8f302..7dcb33d3886b 100644 --- a/sound/usb/usx2y/usX2Yhwdep.c +++ b/sound/usb/usx2y/usX2Yhwdep.c @@ -132,7 +132,7 @@ static int snd_usX2Y_hwdep_dsp_status(struct snd_hwdep *hw, info->num_dsps = 2; // 0: Prepad Data, 1: FPGA Code if (us428->chip_status & USX2Y_STAT_CHIP_INIT) info->chip_ready = 1; - info->version = USX2Y_DRIVER_VERSION; + info->version = USX2Y_DRIVER_VERSION; return 0; } diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c index 459599d1b6c4..58f05748dd39 100644 --- a/tools/lib/api/fs/fs.c +++ b/tools/lib/api/fs/fs.c @@ -179,6 +179,7 @@ static bool fs__env_override(struct fs *fs) size_t name_len = strlen(fs->name); /* name + "_PATH" + '\0' */ char upper_name[name_len + 5 + 1]; + memcpy(upper_name, fs->name, name_len); mem_toupper(upper_name, name_len); strcpy(&upper_name[name_len], "_PATH"); @@ -188,7 +189,8 @@ static bool fs__env_override(struct fs *fs) return false; fs->found = true; - strncpy(fs->path, override_path, sizeof(fs->path)); + strncpy(fs->path, override_path, sizeof(fs->path) - 1); + fs->path[sizeof(fs->path) - 1] = '\0'; return true; } diff --git a/tools/usb/usbip/src/usbip_network.c b/tools/usb/usbip/src/usbip_network.c index b4c37e76a6e0..187dfaa67d0a 100644 --- a/tools/usb/usbip/src/usbip_network.c +++ b/tools/usb/usbip/src/usbip_network.c @@ -62,39 +62,39 @@ void usbip_setup_port_number(char *arg) info("using port %d (\"%s\")", usbip_port, usbip_port_string); } -void usbip_net_pack_uint32_t(int pack, uint32_t *num) +uint32_t usbip_net_pack_uint32_t(int pack, uint32_t num) { uint32_t i; if (pack) - i = htonl(*num); + i = htonl(num); else - i = ntohl(*num); + i = ntohl(num); - *num = i; + return i; } -void usbip_net_pack_uint16_t(int pack, uint16_t *num) +uint16_t usbip_net_pack_uint16_t(int pack, uint16_t num) { uint16_t i; if (pack) - i = htons(*num); + i = htons(num); else - i = ntohs(*num); + i = ntohs(num); - *num = i; + return i; } void usbip_net_pack_usb_device(int pack, struct usbip_usb_device *udev) { - usbip_net_pack_uint32_t(pack, &udev->busnum); - usbip_net_pack_uint32_t(pack, &udev->devnum); - usbip_net_pack_uint32_t(pack, &udev->speed); + udev->busnum = usbip_net_pack_uint32_t(pack, udev->busnum); + udev->devnum = usbip_net_pack_uint32_t(pack, udev->devnum); + udev->speed = usbip_net_pack_uint32_t(pack, udev->speed); - usbip_net_pack_uint16_t(pack, &udev->idVendor); - usbip_net_pack_uint16_t(pack, &udev->idProduct); - usbip_net_pack_uint16_t(pack, &udev->bcdDevice); + udev->idVendor = usbip_net_pack_uint16_t(pack, udev->idVendor); + udev->idProduct = usbip_net_pack_uint16_t(pack, udev->idProduct); + udev->bcdDevice = usbip_net_pack_uint16_t(pack, udev->bcdDevice); } void usbip_net_pack_usb_interface(int pack __attribute__((unused)), @@ -141,6 +141,14 @@ ssize_t usbip_net_send(int sockfd, void *buff, size_t bufflen) return usbip_net_xmit(sockfd, buff, bufflen, 1); } +static inline void usbip_net_pack_op_common(int pack, + struct op_common *op_common) +{ + op_common->version = usbip_net_pack_uint16_t(pack, op_common->version); + op_common->code = usbip_net_pack_uint16_t(pack, op_common->code); + op_common->status = usbip_net_pack_uint32_t(pack, op_common->status); +} + int usbip_net_send_op_common(int sockfd, uint32_t code, uint32_t status) { struct op_common op_common; @@ -152,7 +160,7 @@ int usbip_net_send_op_common(int sockfd, uint32_t code, uint32_t status) op_common.code = code; op_common.status = status; - PACK_OP_COMMON(1, &op_common); + usbip_net_pack_op_common(1, &op_common); rc = usbip_net_send(sockfd, &op_common, sizeof(op_common)); if (rc < 0) { @@ -176,7 +184,7 @@ int usbip_net_recv_op_common(int sockfd, uint16_t *code) goto err; } - PACK_OP_COMMON(0, &op_common); + usbip_net_pack_op_common(0, &op_common); if (op_common.version != USBIP_VERSION) { dbg("version mismatch: %d %d", op_common.version, diff --git a/tools/usb/usbip/src/usbip_network.h b/tools/usb/usbip/src/usbip_network.h index c1e875cf1078..573fa839b66b 100644 --- a/tools/usb/usbip/src/usbip_network.h +++ b/tools/usb/usbip/src/usbip_network.h @@ -33,12 +33,6 @@ struct op_common { } __attribute__((packed)); -#define PACK_OP_COMMON(pack, op_common) do {\ - usbip_net_pack_uint16_t(pack, &(op_common)->version);\ - usbip_net_pack_uint16_t(pack, &(op_common)->code);\ - usbip_net_pack_uint32_t(pack, &(op_common)->status);\ -} while (0) - /* ---------------------------------------------------------------------- */ /* Dummy Code */ #define OP_UNSPEC 0x00 @@ -164,11 +158,11 @@ struct op_devlist_reply_extra { } while (0) #define PACK_OP_DEVLIST_REPLY(pack, reply) do {\ - usbip_net_pack_uint32_t(pack, &(reply)->ndev);\ + (reply)->ndev = usbip_net_pack_uint32_t(pack, (reply)->ndev);\ } while (0) -void usbip_net_pack_uint32_t(int pack, uint32_t *num); -void usbip_net_pack_uint16_t(int pack, uint16_t *num); +uint32_t usbip_net_pack_uint32_t(int pack, uint32_t num); +uint16_t usbip_net_pack_uint16_t(int pack, uint16_t num); void usbip_net_pack_usb_device(int pack, struct usbip_usb_device *udev); void usbip_net_pack_usb_interface(int pack, struct usbip_usb_interface *uinf); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 08a954582e31..82f3a9d78cab 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1865,12 +1865,12 @@ int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, if (slots->generation != ghc->generation) kvm_gfn_to_hva_cache_init(kvm, ghc, ghc->gpa, ghc->len); - if (unlikely(!ghc->memslot)) - return kvm_write_guest(kvm, ghc->gpa, data, len); - if (kvm_is_error_hva(ghc->hva)) return -EFAULT; + if (unlikely(!ghc->memslot)) + return kvm_write_guest(kvm, ghc->gpa, data, len); + r = __copy_to_user((void __user *)ghc->hva, data, len); if (r) return -EFAULT; @@ -1891,12 +1891,12 @@ int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, if (slots->generation != ghc->generation) kvm_gfn_to_hva_cache_init(kvm, ghc, ghc->gpa, ghc->len); - if (unlikely(!ghc->memslot)) - return kvm_read_guest(kvm, ghc->gpa, data, len); - if (kvm_is_error_hva(ghc->hva)) return -EFAULT; + if (unlikely(!ghc->memslot)) + return kvm_read_guest(kvm, ghc->gpa, data, len); + r = __copy_from_user(data, (void __user *)ghc->hva, len); if (r) return -EFAULT; |