Re: Linux 4.19.69

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index c96a8e9ad5c2..e8ddf0ef232e 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3948,6 +3948,13 @@ Run specified binary instead of /init from the ramdisk, used for early userspace startup. See initrd.

+ rdrand= [X86] + force - Override the decision by the kernel to hide the + advertisement of RDRAND support (this affects + certain AMD processors because of buggy BIOS + support, specifically around the suspend/resume + path). + rdt= [HW,X86,RDT] Turn on/off individual RDT features. List is: cmt, mbmtotal, mbmlocal, l3cat, l3cdp, l2cat, l2cdp, diff --git a/Makefile b/Makefile index 6f164b04d953..677341239449 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 4 PATCHLEVEL = 19 -SUBLEVEL = 68 +SUBLEVEL = 69 EXTRAVERSION = NAME = "People's Front"

diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c index fd6cde23bb5d..871fa50a09f1 100644 --- a/arch/arm/kvm/coproc.c +++ b/arch/arm/kvm/coproc.c @@ -658,13 +658,22 @@ int kvm_handle_cp14_64(struct kvm_vcpu *vcpu, struct kvm_run *run) }

static void reset_coproc_regs(struct kvm_vcpu *vcpu, - const struct coproc_reg *table, size_t num) + const struct coproc_reg *table, size_t num, + unsigned long *bmap) { unsigned long i;

for (i = 0; i < num; i++) - if (table[i].reset) + if (table[i].reset) { + int reg = table[i].reg; + table[i].reset(vcpu, &table[i]); + if (reg > 0 && reg < NR_CP15_REGS) { + set_bit(reg, bmap); + if (table[i].is_64bit) + set_bit(reg + 1, bmap); + } + } }

static struct coproc_params decode_32bit_hsr(struct kvm_vcpu *vcpu) @@ -1439,17 +1448,15 @@ void kvm_reset_coprocs(struct kvm_vcpu *vcpu) { size_t num; const struct coproc_reg *table; - - /* Catch someone adding a register without putting in reset entry. */ - memset(vcpu->arch.ctxt.cp15, 0x42, sizeof(vcpu->arch.ctxt.cp15)); + DECLARE_BITMAP(bmap, NR_CP15_REGS) = { 0, };

/* Generic chip reset first (so target could override). */ - reset_coproc_regs(vcpu, cp15_regs, ARRAY_SIZE(cp15_regs)); + reset_coproc_regs(vcpu, cp15_regs, ARRAY_SIZE(cp15_regs), bmap);

table = get_target_table(vcpu->arch.target, &num); - reset_coproc_regs(vcpu, table, num); + reset_coproc_regs(vcpu, table, num, bmap);

for (num = 1; num < NR_CP15_REGS; num++) - WARN(vcpu_cp15(vcpu, num) == 0x42424242, + WARN(!test_bit(num, bmap), "Didn't reset vcpu_cp15(vcpu, %zi)", num); } diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index d112af75680b..6da2bbdb9648 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -626,7 +626,7 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) */ val = ((pmcr & ~ARMV8_PMU_PMCR_MASK) | (ARMV8_PMU_PMCR_MASK & 0xdecafbad)) & (~ARMV8_PMU_PMCR_E); - __vcpu_sys_reg(vcpu, PMCR_EL0) = val; + __vcpu_sys_reg(vcpu, r->reg) = val; }

static bool check_pmu_access_disabled(struct kvm_vcpu *vcpu, u64 flags) @@ -968,13 +968,13 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, /* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */ #define DBG_BCR_BVR_WCR_WVR_EL1(n) \ { SYS_DESC(SYS_DBGBVRn_EL1(n)), \ - trap_bvr, reset_bvr, n, 0, get_bvr, set_bvr }, \ + trap_bvr, reset_bvr, 0, 0, get_bvr, set_bvr }, \ { SYS_DESC(SYS_DBGBCRn_EL1(n)), \ - trap_bcr, reset_bcr, n, 0, get_bcr, set_bcr }, \ + trap_bcr, reset_bcr, 0, 0, get_bcr, set_bcr }, \ { SYS_DESC(SYS_DBGWVRn_EL1(n)), \ - trap_wvr, reset_wvr, n, 0, get_wvr, set_wvr }, \ + trap_wvr, reset_wvr, 0, 0, get_wvr, set_wvr }, \ { SYS_DESC(SYS_DBGWCRn_EL1(n)), \ - trap_wcr, reset_wcr, n, 0, get_wcr, set_wcr } + trap_wcr, reset_wcr, 0, 0, get_wcr, set_wcr }

/* Macro to expand the PMEVCNTRn_EL0 register */ #define PMU_PMEVCNTR_EL0(n) \ @@ -1359,7 +1359,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {

{ SYS_DESC(SYS_CSSELR_EL1), NULL, reset_unknown, CSSELR_EL1 },

- { SYS_DESC(SYS_PMCR_EL0), access_pmcr, reset_pmcr, }, + { SYS_DESC(SYS_PMCR_EL0), access_pmcr, reset_pmcr, PMCR_EL0 }, { SYS_DESC(SYS_PMCNTENSET_EL0), access_pmcnten, reset_unknown, PMCNTENSET_EL0 }, { SYS_DESC(SYS_PMCNTENCLR_EL0), access_pmcnten, NULL, PMCNTENSET_EL0 }, { SYS_DESC(SYS_PMOVSCLR_EL0), access_pmovs, NULL, PMOVSSET_EL0 }, @@ -2072,13 +2072,19 @@ static int emulate_sys_reg(struct kvm_vcpu *vcpu, }

static void reset_sys_reg_descs(struct kvm_vcpu *vcpu, - const struct sys_reg_desc *table, size_t num) + const struct sys_reg_desc *table, size_t num, + unsigned long *bmap) { unsigned long i;

for (i = 0; i < num; i++) - if (table[i].reset) + if (table[i].reset) { + int reg = table[i].reg; + table[i].reset(vcpu, &table[i]); + if (reg > 0 && reg < NR_SYS_REGS) + set_bit(reg, bmap); + } }

/** @@ -2576,18 +2582,16 @@ void kvm_reset_sys_regs(struct kvm_vcpu *vcpu) { size_t num; const struct sys_reg_desc *table; - - /* Catch someone adding a register without putting in reset entry. */ - memset(&vcpu->arch.ctxt.sys_regs, 0x42, sizeof(vcpu->arch.ctxt.sys_regs)); + DECLARE_BITMAP(bmap, NR_SYS_REGS) = { 0, };

/* Generic chip reset first (so target could override). */ - reset_sys_reg_descs(vcpu, sys_reg_descs, ARRAY_SIZE(sys_reg_descs)); + reset_sys_reg_descs(vcpu, sys_reg_descs, ARRAY_SIZE(sys_reg_descs), bmap);

table = get_target_table(vcpu->arch.target, true, &num); - reset_sys_reg_descs(vcpu, table, num); + reset_sys_reg_descs(vcpu, table, num, bmap);

for (num = 1; num < NR_SYS_REGS; num++) { - if (WARN(__vcpu_sys_reg(vcpu, num) == 0x4242424242424242, + if (WARN(!test_bit(num, bmap), "Didn't reset __vcpu_sys_reg(%zi)\n", num)) break; } diff --git a/arch/mips/kernel/cacheinfo.c b/arch/mips/kernel/cacheinfo.c index 97d5239ca47b..428ef2189203 100644 --- a/arch/mips/kernel/cacheinfo.c +++ b/arch/mips/kernel/cacheinfo.c @@ -80,6 +80,8 @@ static int __populate_cache_leaves(unsigned int cpu) if (c->tcache.waysize) populate_cache(tcache, this_leaf, 3, CACHE_TYPE_UNIFIED);

+ this_cpu_ci->cpu_map_populated = true; + return 0; }

diff --git a/arch/mips/kernel/i8253.c b/arch/mips/kernel/i8253.c index 5f209f111e59..df7ddd246eaa 100644 --- a/arch/mips/kernel/i8253.c +++ b/arch/mips/kernel/i8253.c @@ -32,7 +32,8 @@ void __init setup_pit_timer(void)

static int __init init_pit_clocksource(void) { - if (num_possible_cpus() > 1) /* PIT does not scale! */ + if (num_possible_cpus() > 1 || /* PIT does not scale! */ + !clockevent_state_periodic(&i8253_clockevent)) return 0;

return clocksource_i8253_init(); diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index 262ba9481781..1bf6aaefd26a 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -135,7 +135,7 @@ _GLOBAL_TOC(flush_dcache_range) subf r8,r6,r4 /* compute length */ add r8,r8,r5 /* ensure we get enough */ lwz r9,DCACHEL1LOGBLOCKSIZE(r10) /* Get log-2 of dcache block size */ - srw. r8,r8,r9 /* compute line count */ + srd. r8,r8,r9 /* compute line count */ beqlr /* nothing to do? */ mtctr r8 0: dcbst 0,r6 @@ -153,7 +153,7 @@ _GLOBAL(flush_inval_dcache_range) subf r8,r6,r4 /* compute length */ add r8,r8,r5 /* ensure we get enough */ lwz r9,DCACHEL1LOGBLOCKSIZE(r10)/* Get log-2 of dcache block size */ - srw. r8,r8,r9 /* compute line count */ + srd. r8,r8,r9 /* compute line count */ beqlr /* nothing to do? */ sync isync diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index b43f8d33a369..18ede6e806b9 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -31,10 +31,9 @@ PHDRS { SECTIONS { . = 0x100000; - _stext = .; /* Start of text section */ .text : { - /* Text and read-only data */ - _text = .; + _stext = .; /* Start of text section */ + _text = .; /* Text and read-only data */ HEAD_TEXT TEXT_TEXT SCHED_TEXT @@ -46,11 +45,10 @@ SECTIONS *(.text.*_indirect_*) *(.fixup) *(.gnu.warning) + . = ALIGN(PAGE_SIZE); + _etext = .; /* End of text section */ } :text = 0x0700

- . = ALIGN(PAGE_SIZE); - _etext = .; /* End of text section */ - NOTES :text :note

.dummy : { *(.dummy) } :data diff --git a/arch/x86/include/asm/bootparam_utils.h b/arch/x86/include/asm/bootparam_utils.h index a07ffd23e4dd..d3983fdf1012 100644 --- a/arch/x86/include/asm/bootparam_utils.h +++ b/arch/x86/include/asm/bootparam_utils.h @@ -18,6 +18,20 @@ * Note: efi_info is commonly left uninitialized, but that field has a * private magic, so it is better to leave it unchanged. */ + +#define sizeof_mbr(type, member) ({ sizeof(((type *)0)->member); }) + +#define BOOT_PARAM_PRESERVE(struct_member) \ + { \ + .start = offsetof(struct boot_params, struct_member), \ + .len = sizeof_mbr(struct boot_params, struct_member), \ + } + +struct boot_params_to_save { + unsigned int start; + unsigned int len; +}; + static void sanitize_boot_params(struct boot_params *boot_params) { /* @@ -36,19 +50,40 @@ static void sanitize_boot_params(struct boot_params *boot_params) */ if (boot_params->sentinel) { /* fields in boot_params are left uninitialized, clear them */ - memset(&boot_params->ext_ramdisk_image, 0, - (char *)&boot_params->efi_info - - (char *)&boot_params->ext_ramdisk_image); - memset(&boot_params->kbd_status, 0, - (char *)&boot_params->hdr - - (char *)&boot_params->kbd_status); - memset(&boot_params->_pad7[0], 0, - (char *)&boot_params->edd_mbr_sig_buffer[0] - - (char *)&boot_params->_pad7[0]); - memset(&boot_params->_pad8[0], 0, - (char *)&boot_params->eddbuf[0] - - (char *)&boot_params->_pad8[0]); - memset(&boot_params->_pad9[0], 0, sizeof(boot_params->_pad9)); + static struct boot_params scratch; + char *bp_base = (char *)boot_params; + char *save_base = (char *)&scratch; + int i; + + const struct boot_params_to_save to_save[] = { + BOOT_PARAM_PRESERVE(screen_info), + BOOT_PARAM_PRESERVE(apm_bios_info), + BOOT_PARAM_PRESERVE(tboot_addr), + BOOT_PARAM_PRESERVE(ist_info), + BOOT_PARAM_PRESERVE(hd0_info), + BOOT_PARAM_PRESERVE(hd1_info), + BOOT_PARAM_PRESERVE(sys_desc_table), + BOOT_PARAM_PRESERVE(olpc_ofw_header), + BOOT_PARAM_PRESERVE(efi_info), + BOOT_PARAM_PRESERVE(alt_mem_k), + BOOT_PARAM_PRESERVE(scratch), + BOOT_PARAM_PRESERVE(e820_entries), + BOOT_PARAM_PRESERVE(eddbuf_entries), + BOOT_PARAM_PRESERVE(edd_mbr_sig_buf_entries), + BOOT_PARAM_PRESERVE(edd_mbr_sig_buffer), + BOOT_PARAM_PRESERVE(hdr), + BOOT_PARAM_PRESERVE(e820_table), + BOOT_PARAM_PRESERVE(eddbuf), + }; + + memset(&scratch, 0, sizeof(scratch)); + + for (i = 0; i < ARRAY_SIZE(to_save); i++) { + memcpy(save_base + to_save[i].start, + bp_base + to_save[i].start, to_save[i].len); + } + + memcpy(boot_params, save_base, sizeof(*boot_params)); } }

diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index f85f43db9225..a1d22e4428f6 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -334,6 +334,7 @@ #define MSR_AMD64_PATCH_LEVEL 0x0000008b #define MSR_AMD64_TSC_RATIO 0xc0000104 #define MSR_AMD64_NB_CFG 0xc001001f +#define MSR_AMD64_CPUID_FN_1 0xc0011004 #define MSR_AMD64_PATCH_LOADER 0xc0010020 #define MSR_AMD64_OSVW_ID_LENGTH 0xc0010140 #define MSR_AMD64_OSVW_STATUS 0xc0010141 diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 599c273f5d00..28cb2b31527a 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -202,7 +202,7 @@ " lfence;\n" \ " jmp 902b;\n" \ " .align 16\n" \ - "903: addl $4, %%esp;\n" \ + "903: lea 4(%%esp), %%esp;\n" \ " pushl %[thunk_target];\n" \ " ret;\n" \ " .align 16\n" \ diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 272a12865b2a..b316bd61a6ac 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -715,7 +715,7 @@ static __initdata unsigned long lapic_cal_pm1, lapic_cal_pm2; static __initdata unsigned long lapic_cal_j1, lapic_cal_j2;

/* - * Temporary interrupt handler. + * Temporary interrupt handler and polled calibration function. */ static void __init lapic_cal_handler(struct clock_event_device *dev) { @@ -799,7 +799,8 @@ calibrate_by_pmtimer(long deltapm, long *delta, long *deltatsc) static int __init calibrate_APIC_clock(void) { struct clock_event_device *levt = this_cpu_ptr(&lapic_events); - void (*real_handler)(struct clock_event_device *dev); + u64 tsc_perj = 0, tsc_start = 0; + unsigned long jif_start; unsigned long deltaj; long delta, deltatsc; int pm_referenced = 0; @@ -830,28 +831,64 @@ static int __init calibrate_APIC_clock(void) apic_printk(APIC_VERBOSE, "Using local APIC timer interrupts.\n" "calibrating APIC timer ...\n");

+ /* + * There are platforms w/o global clockevent devices. Instead of + * making the calibration conditional on that, use a polling based + * approach everywhere. + */ local_irq_disable();

- /* Replace the global interrupt handler */ - real_handler = global_clock_event->event_handler; - global_clock_event->event_handler = lapic_cal_handler; - /* * Setup the APIC counter to maximum. There is no way the lapic * can underflow in the 100ms detection time frame */ __setup_APIC_LVTT(0xffffffff, 0, 0);

- /* Let the interrupts run */ + /* + * Methods to terminate the calibration loop: + * 1) Global clockevent if available (jiffies) + * 2) TSC if available and frequency is known + */ + jif_start = READ_ONCE(jiffies); + + if (tsc_khz) { + tsc_start = rdtsc(); + tsc_perj = div_u64((u64)tsc_khz * 1000, HZ); + } + + /* + * Enable interrupts so the tick can fire, if a global + * clockevent device is available + */ local_irq_enable();

- while (lapic_cal_loops <= LAPIC_CAL_LOOPS) - cpu_relax(); + while (lapic_cal_loops <= LAPIC_CAL_LOOPS) { + /* Wait for a tick to elapse */ + while (1) { + if (tsc_khz) { + u64 tsc_now = rdtsc(); + if ((tsc_now - tsc_start) >= tsc_perj) { + tsc_start += tsc_perj; + break; + } + } else { + unsigned long jif_now = READ_ONCE(jiffies);

- local_irq_disable(); + if (time_after(jif_now, jif_start)) { + jif_start = jif_now; + break; + } + } + cpu_relax(); + }

- /* Restore the real event handler */ - global_clock_event->event_handler = real_handler; + /* Invoke the calibration routine */ + local_irq_disable(); + lapic_cal_handler(NULL); + local_irq_enable(); + } + + local_irq_disable();

/* Build delta t1-t2 as apic timer counts down */ delta = lapic_cal_t1 - lapic_cal_t2; @@ -904,10 +941,11 @@ static int __init calibrate_APIC_clock(void) levt->features &= ~CLOCK_EVT_FEAT_DUMMY;

/* - * PM timer calibration failed or not turned on - * so lets try APIC timer based calibration + * PM timer calibration failed or not turned on so lets try APIC + * timer based calibration, if a global clockevent device is + * available. */ - if (!pm_referenced) { + if (!pm_referenced && global_clock_event) { apic_printk(APIC_VERBOSE, "... verify APIC timer\n");

/* diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index da1f5e78363e..f86f912ce215 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -799,6 +799,64 @@ static void init_amd_ln(struct cpuinfo_x86 *c) msr_set_bit(MSR_AMD64_DE_CFG, 31); }

+static bool rdrand_force; + +static int __init rdrand_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!strcmp(str, "force")) + rdrand_force = true; + else + return -EINVAL; + + return 0; +} +early_param("rdrand", rdrand_cmdline); + +static void clear_rdrand_cpuid_bit(struct cpuinfo_x86 *c) +{ + /* + * Saving of the MSR used to hide the RDRAND support during + * suspend/resume is done by arch/x86/power/cpu.c, which is + * dependent on CONFIG_PM_SLEEP. + */ + if (!IS_ENABLED(CONFIG_PM_SLEEP)) + return; + + /* + * The nordrand option can clear X86_FEATURE_RDRAND, so check for + * RDRAND support using the CPUID function directly. + */ + if (!(cpuid_ecx(1) & BIT(30)) || rdrand_force) + return; + + msr_clear_bit(MSR_AMD64_CPUID_FN_1, 62); + + /* + * Verify that the CPUID change has occurred in case the kernel is + * running virtualized and the hypervisor doesn't support the MSR. + */ + if (cpuid_ecx(1) & BIT(30)) { + pr_info_once("BIOS may not properly restore RDRAND after suspend, but hypervisor does not support hiding RDRAND via CPUID.\n"); + return; + } + + clear_cpu_cap(c, X86_FEATURE_RDRAND); + pr_info_once("BIOS may not properly restore RDRAND after suspend, hiding RDRAND via CPUID. Use rdrand=force to reenable.\n"); +} + +static void init_amd_jg(struct cpuinfo_x86 *c) +{ + /* + * Some BIOS implementations do not restore proper RDRAND support + * across suspend and resume. Check on whether to hide the RDRAND + * instruction support via CPUID. + */ + clear_rdrand_cpuid_bit(c); +} + static void init_amd_bd(struct cpuinfo_x86 *c) { u64 value; @@ -813,6 +871,13 @@ static void init_amd_bd(struct cpuinfo_x86 *c) wrmsrl_safe(MSR_F15H_IC_CFG, value); } } + + /* + * Some BIOS implementations do not restore proper RDRAND support + * across suspend and resume. Check on whether to hide the RDRAND + * instruction support via CPUID. + */ + clear_rdrand_cpuid_bit(c); }

static void init_amd_zn(struct cpuinfo_x86 *c) @@ -855,6 +920,7 @@ static void init_amd(struct cpuinfo_x86 *c) case 0x10: init_amd_gh(c); break; case 0x12: init_amd_ln(c); break; case 0x15: init_amd_bd(c); break; + case 0x16: init_amd_jg(c); break; case 0x17: init_amd_zn(c); break; }

diff --git a/arch/x86/lib/cpu.c b/arch/x86/lib/cpu.c index 2dd1fe13a37b..19f707992db2 100644 --- a/arch/x86/lib/cpu.c +++ b/arch/x86/lib/cpu.c @@ -1,5 +1,6 @@ #include <linux/types.h> #include <linux/export.h> +#include <asm/cpu.h>

unsigned int x86_family(unsigned int sig) { diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 513ce09e9950..3aa3149df07f 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -13,6 +13,7 @@ #include <linux/smp.h> #include <linux/perf_event.h> #include <linux/tboot.h> +#include <linux/dmi.h>

#include <asm/pgtable.h> #include <asm/proto.h> @@ -24,7 +25,7 @@ #include <asm/debugreg.h> #include <asm/cpu.h> #include <asm/mmu_context.h> -#include <linux/dmi.h> +#include <asm/cpu_device_id.h>

#ifdef CONFIG_X86_32 __visible unsigned long saved_context_ebx; @@ -398,15 +399,14 @@ static int __init bsp_pm_check_init(void)

core_initcall(bsp_pm_check_init);

-static int msr_init_context(const u32 *msr_id, const int total_num) +static int msr_build_context(const u32 *msr_id, const int num) { - int i = 0; + struct saved_msrs *saved_msrs = &saved_context.saved_msrs; struct saved_msr *msr_array; + int total_num; + int i, j;

- if (saved_context.saved_msrs.array || saved_context.saved_msrs.num > 0) { - pr_err("x86/pm: MSR quirk already applied, please check your DMI match table.\n"); - return -EINVAL; - } + total_num = saved_msrs->num + num;

msr_array = kmalloc_array(total_num, sizeof(struct saved_msr), GFP_KERNEL); if (!msr_array) { @@ -414,19 +414,30 @@ static int msr_init_context(const u32 *msr_id, const int total_num) return -ENOMEM; }

- for (i = 0; i < total_num; i++) { - msr_array[i].info.msr_no = msr_id[i]; + if (saved_msrs->array) { + /* + * Multiple callbacks can invoke this function, so copy any + * MSR save requests from previous invocations. + */ + memcpy(msr_array, saved_msrs->array, + sizeof(struct saved_msr) * saved_msrs->num); + + kfree(saved_msrs->array); + } + + for (i = saved_msrs->num, j = 0; i < total_num; i++, j++) { + msr_array[i].info.msr_no = msr_id[j]; msr_array[i].valid = false; msr_array[i].info.reg.q = 0; } - saved_context.saved_msrs.num = total_num; - saved_context.saved_msrs.array = msr_array; + saved_msrs->num = total_num; + saved_msrs->array = msr_array;

return 0; }

/* - * The following section is a quirk framework for problematic BIOSen: + * The following sections are a quirk framework for problematic BIOSen: * Sometimes MSRs are modified by the BIOSen after suspended to * RAM, this might cause unexpected behavior after wakeup. * Thus we save/restore these specified MSRs across suspend/resume @@ -441,7 +452,7 @@ static int msr_initialize_bdw(const struct dmi_system_id *d) u32 bdw_msr_id[] = { MSR_IA32_THERM_CONTROL };

pr_info("x86/pm: %s detected, MSR saving is needed during suspending.\n", d->ident); - return msr_init_context(bdw_msr_id, ARRAY_SIZE(bdw_msr_id)); + return msr_build_context(bdw_msr_id, ARRAY_SIZE(bdw_msr_id)); }

static const struct dmi_system_id msr_save_dmi_table[] = { @@ -456,9 +467,58 @@ static const struct dmi_system_id msr_save_dmi_table[] = { {} };

+static int msr_save_cpuid_features(const struct x86_cpu_id *c) +{ + u32 cpuid_msr_id[] = { + MSR_AMD64_CPUID_FN_1, + }; + + pr_info("x86/pm: family %#hx cpu detected, MSR saving is needed during suspending.\n", + c->family); + + return msr_build_context(cpuid_msr_id, ARRAY_SIZE(cpuid_msr_id)); +} + +static const struct x86_cpu_id msr_save_cpu_table[] = { + { + .vendor = X86_VENDOR_AMD, + .family = 0x15, + .model = X86_MODEL_ANY, + .feature = X86_FEATURE_ANY, + .driver_data = (kernel_ulong_t)msr_save_cpuid_features, + }, + { + .vendor = X86_VENDOR_AMD, + .family = 0x16, + .model = X86_MODEL_ANY, + .feature = X86_FEATURE_ANY, + .driver_data = (kernel_ulong_t)msr_save_cpuid_features, + }, + {} +}; + +typedef int (*pm_cpu_match_t)(const struct x86_cpu_id *); +static int pm_cpu_check(const struct x86_cpu_id *c) +{ + const struct x86_cpu_id *m; + int ret = 0; + + m = x86_match_cpu(msr_save_cpu_table); + if (m) { + pm_cpu_match_t fn; + + fn = (pm_cpu_match_t)m->driver_data; + ret = fn(m); + } + + return ret; +} + static int pm_check_save_msr(void) { dmi_check_system(msr_save_dmi_table); + pm_cpu_check(msr_save_cpu_table); + return 0; }

diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index becd793a258c..d8d2ac294b0c 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -1886,9 +1886,14 @@ static void bfq_request_merged(struct request_queue *q, struct request *req, blk_rq_pos(container_of(rb_prev(&req->rb_node), struct request, rb_node))) { struct bfq_queue *bfqq = bfq_init_rq(req); - struct bfq_data *bfqd = bfqq->bfqd; + struct bfq_data *bfqd; struct request *prev, *next_rq;

+ if (!bfqq) + return; + + bfqd = bfqq->bfqd; + /* Reposition request in its sort_list */ elv_rb_del(&bfqq->sort_list, req); elv_rb_add(&bfqq->sort_list, req); @@ -1930,6 +1935,9 @@ static void bfq_requests_merged(struct request_queue *q, struct request *rq, struct bfq_queue *bfqq = bfq_init_rq(rq), *next_bfqq = bfq_init_rq(next);

+ if (!bfqq) + return; + /* * If next and rq belong to the same bfq_queue and next is older * than rq, then reposition rq in the fifo (by substituting next @@ -4590,12 +4598,12 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,

spin_lock_irq(&bfqd->lock); bfqq = bfq_init_rq(rq); - if (at_head || blk_rq_is_passthrough(rq)) { + if (!bfqq || at_head || blk_rq_is_passthrough(rq)) { if (at_head) list_add(&rq->queuelist, &bfqd->dispatch); else list_add_tail(&rq->queuelist, &bfqd->dispatch); - } else { /* bfqq is assumed to be non null here */ + } else { idle_timer_disabled = __bfq_insert_request(bfqd, rq); /* * Update bfqq, because, if a queue merge has occurred diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 1984fc78c750..3a64fa4aaf7e 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1803,6 +1803,21 @@ static unsigned int ata_scsi_verify_xlat(struct ata_queued_cmd *qc) return 1; }

+static bool ata_check_nblocks(struct scsi_cmnd *scmd, u32 n_blocks) +{ + struct request *rq = scmd->request; + u32 req_blocks; + + if (!blk_rq_is_passthrough(rq)) + return true; + + req_blocks = blk_rq_bytes(rq) / scmd->device->sector_size; + if (n_blocks > req_blocks) + return false; + + return true; +} + /** * ata_scsi_rw_xlat - Translate SCSI r/w command into an ATA one * @qc: Storage for translated ATA taskfile @@ -1847,6 +1862,8 @@ static unsigned int ata_scsi_rw_xlat(struct ata_queued_cmd *qc) scsi_10_lba_len(cdb, &block, &n_block); if (cdb[1] & (1 << 3)) tf_flags |= ATA_TFLAG_FUA; + if (!ata_check_nblocks(scmd, n_block)) + goto invalid_fld; break; case READ_6: case WRITE_6: @@ -1861,6 +1878,8 @@ static unsigned int ata_scsi_rw_xlat(struct ata_queued_cmd *qc) */ if (!n_block) n_block = 256; + if (!ata_check_nblocks(scmd, n_block)) + goto invalid_fld; break; case READ_16: case WRITE_16: @@ -1871,6 +1890,8 @@ static unsigned int ata_scsi_rw_xlat(struct ata_queued_cmd *qc) scsi_16_lba_len(cdb, &block, &n_block); if (cdb[1] & (1 << 3)) tf_flags |= ATA_TFLAG_FUA; + if (!ata_check_nblocks(scmd, n_block)) + goto invalid_fld; break; default: DPRINTK("no-byte command\n"); diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index c5ea0fc635e5..873cc0906055 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -674,6 +674,10 @@ static void ata_pio_sector(struct ata_queued_cmd *qc) unsigned int offset; unsigned char *buf;

+ if (!qc->cursg) { + qc->curbytes = qc->nbytes; + return; + } if (qc->curbytes == qc->nbytes - qc->sect_size) ap->hsm_task_state = HSM_ST_LAST;

@@ -699,6 +703,8 @@ static void ata_pio_sector(struct ata_queued_cmd *qc)

if (qc->cursg_ofs == qc->cursg->length) { qc->cursg = sg_next(qc->cursg); + if (!qc->cursg) + ap->hsm_task_state = HSM_ST_LAST; qc->cursg_ofs = 0; } } diff --git a/drivers/clk/socfpga/clk-periph-s10.c b/drivers/clk/socfpga/clk-periph-s10.c index 568f59b58ddf..e7c877d354c7 100644 --- a/drivers/clk/socfpga/clk-periph-s10.c +++ b/drivers/clk/socfpga/clk-periph-s10.c @@ -37,7 +37,7 @@ static unsigned long clk_peri_cnt_clk_recalc_rate(struct clk_hw *hwclk, if (socfpgaclk->fixed_div) { div = socfpgaclk->fixed_div; } else { - if (!socfpgaclk->bypass_reg) + if (socfpgaclk->hw.reg) div = ((readl(socfpgaclk->hw.reg) & 0x7ff) + 1); }

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index b308ce92685d..53395852f012 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -1082,9 +1082,11 @@ static long gpio_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) if (test_bit(FLAG_ACTIVE_LOW, &desc->flags)) lineinfo.flags |= GPIOLINE_FLAG_ACTIVE_LOW; if (test_bit(FLAG_OPEN_DRAIN, &desc->flags)) - lineinfo.flags |= GPIOLINE_FLAG_OPEN_DRAIN; + lineinfo.flags |= (GPIOLINE_FLAG_OPEN_DRAIN | + GPIOLINE_FLAG_IS_OUT); if (test_bit(FLAG_OPEN_SOURCE, &desc->flags)) - lineinfo.flags |= GPIOLINE_FLAG_OPEN_SOURCE; + lineinfo.flags |= (GPIOLINE_FLAG_OPEN_SOURCE | + GPIOLINE_FLAG_IS_OUT);

if (copy_to_user(ip, &lineinfo, sizeof(lineinfo))) return -EFAULT; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/aux.c b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/aux.c index b4e7404fe660..a11637b0f6cc 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/aux.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/aux.c @@ -40,8 +40,7 @@ nvkm_i2c_aux_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num) u8 *ptr = msg->buf;

while (remaining) { - u8 cnt = (remaining > 16) ? 16 : remaining; - u8 cmd; + u8 cnt, retries, cmd;

if (msg->flags & I2C_M_RD) cmd = 1; @@ -51,10 +50,19 @@ nvkm_i2c_aux_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num) if (mcnt || remaining > 16) cmd |= 4; /* MOT */

- ret = aux->func->xfer(aux, true, cmd, msg->addr, ptr, &cnt); - if (ret < 0) { - nvkm_i2c_aux_release(aux); - return ret; + for (retries = 0, cnt = 0; + retries < 32 && !cnt; + retries++) { + cnt = min_t(u8, remaining, 16); + ret = aux->func->xfer(aux, true, cmd, + msg->addr, ptr, &cnt); + if (ret < 0) + goto out; + } + if (!cnt) { + AUX_TRACE(aux, "no data after 32 retries"); + ret = -EIO; + goto out; }

ptr += cnt; @@ -64,8 +72,10 @@ nvkm_i2c_aux_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num) msg++; }

+ ret = num; +out: nvkm_i2c_aux_release(aux); - return num; + return ret; }

static u32 diff --git a/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c b/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c index 080f05352195..6a4da3a0ff1c 100644 --- a/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c +++ b/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c @@ -436,7 +436,7 @@ static int rockchip_dp_resume(struct device *dev)

static const struct dev_pm_ops rockchip_dp_pm_ops = { #ifdef CONFIG_PM_SLEEP - .suspend = rockchip_dp_suspend, + .suspend_late = rockchip_dp_suspend, .resume_early = rockchip_dp_resume, #endif }; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c index e4e09d47c5c0..59e9d05ab928 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c @@ -389,8 +389,10 @@ static int vmw_recv_msg(struct rpc_channel *channel, void **msg, break; }

- if (retries == RETRIES) + if (retries == RETRIES) { + kfree(reply); return -EINVAL; + }

*msg_len = reply_len; *msg = reply; diff --git a/drivers/hid/hid-a4tech.c b/drivers/hid/hid-a4tech.c index 9428ea7cdf8a..c52bd163abb3 100644 --- a/drivers/hid/hid-a4tech.c +++ b/drivers/hid/hid-a4tech.c @@ -26,12 +26,36 @@ #define A4_2WHEEL_MOUSE_HACK_7 0x01 #define A4_2WHEEL_MOUSE_HACK_B8 0x02

+#define A4_WHEEL_ORIENTATION (HID_UP_GENDESK | 0x000000b8) + struct a4tech_sc { unsigned long quirks; unsigned int hw_wheel; __s32 delayed_value; };

+static int a4_input_mapping(struct hid_device *hdev, struct hid_input *hi, + struct hid_field *field, struct hid_usage *usage, + unsigned long **bit, int *max) +{ + struct a4tech_sc *a4 = hid_get_drvdata(hdev); + + if (a4->quirks & A4_2WHEEL_MOUSE_HACK_B8 && + usage->hid == A4_WHEEL_ORIENTATION) { + /* + * We do not want to have this usage mapped to anything as it's + * nonstandard and doesn't really behave like an HID report. + * It's only selecting the orientation (vertical/horizontal) of + * the previous mouse wheel report. The input_events will be + * generated once both reports are recorded in a4_event(). + */ + return -1; + } + + return 0; + +} + static int a4_input_mapped(struct hid_device *hdev, struct hid_input *hi, struct hid_field *field, struct hid_usage *usage, unsigned long **bit, int *max) @@ -53,8 +77,7 @@ static int a4_event(struct hid_device *hdev, struct hid_field *field, struct a4tech_sc *a4 = hid_get_drvdata(hdev); struct input_dev *input;

- if (!(hdev->claimed & HID_CLAIMED_INPUT) || !field->hidinput || - !usage->type) + if (!(hdev->claimed & HID_CLAIMED_INPUT) || !field->hidinput) return 0;

input = field->hidinput->input; @@ -65,7 +88,7 @@ static int a4_event(struct hid_device *hdev, struct hid_field *field, return 1; }

- if (usage->hid == 0x000100b8) { + if (usage->hid == A4_WHEEL_ORIENTATION) { input_event(input, EV_REL, value ? REL_HWHEEL : REL_WHEEL, a4->delayed_value); return 1; @@ -129,6 +152,7 @@ MODULE_DEVICE_TABLE(hid, a4_devices); static struct hid_driver a4_driver = { .name = "a4tech", .id_table = a4_devices, + .input_mapping = a4_input_mapping, .input_mapped = a4_input_mapped, .event = a4_event, .probe = a4_probe, diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 2898bb061945..4a2fa57ddcb8 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -971,6 +971,7 @@ #define USB_DEVICE_ID_SAITEK_RAT7 0x0cd7 #define USB_DEVICE_ID_SAITEK_RAT9 0x0cfa #define USB_DEVICE_ID_SAITEK_MMO7 0x0cd0 +#define USB_DEVICE_ID_SAITEK_X52 0x075c

#define USB_VENDOR_ID_SAMSUNG 0x0419 #define USB_DEVICE_ID_SAMSUNG_IR_REMOTE 0x0001 diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index d29c7c9cd185..e553f6fae7a4 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -143,6 +143,7 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_RETROUSB, USB_DEVICE_ID_RETROUSB_SNES_RETROPAD), HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE }, { HID_USB_DEVICE(USB_VENDOR_ID_RETROUSB, USB_DEVICE_ID_RETROUSB_SNES_RETROPORT), HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE }, { HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_RUMBLEPAD), HID_QUIRK_BADPAD }, + { HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_X52), HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE }, { HID_USB_DEVICE(USB_VENDOR_ID_SEMICO, USB_DEVICE_ID_SEMICO_USB_KEYKOARD2), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_SEMICO, USB_DEVICE_ID_SEMICO_USB_KEYKOARD), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_SENNHEISER, USB_DEVICE_ID_SENNHEISER_BTD500USB), HID_QUIRK_NOGET }, diff --git a/drivers/hid/hid-tmff.c b/drivers/hid/hid-tmff.c index bea8def64f43..30b8c3256c99 100644 --- a/drivers/hid/hid-tmff.c +++ b/drivers/hid/hid-tmff.c @@ -34,6 +34,8 @@

#include "hid-ids.h"

+#define THRUSTMASTER_DEVICE_ID_2_IN_1_DT 0xb320 + static const signed short ff_rumble[] = { FF_RUMBLE, -1 @@ -88,6 +90,7 @@ static int tmff_play(struct input_dev *dev, void *data, struct hid_field *ff_field = tmff->ff_field; int x, y; int left, right; /* Rumbling */ + int motor_swap;

switch (effect->type) { case FF_CONSTANT: @@ -112,6 +115,13 @@ static int tmff_play(struct input_dev *dev, void *data, ff_field->logical_minimum, ff_field->logical_maximum);

+ /* 2-in-1 strong motor is left */ + if (hid->product == THRUSTMASTER_DEVICE_ID_2_IN_1_DT) { + motor_swap = left; + left = right; + right = motor_swap; + } + dbg_hid("(left,right)=(%08x, %08x)\n", left, right); ff_field->value[0] = left; ff_field->value[1] = right; @@ -238,6 +248,8 @@ static const struct hid_device_id tm_devices[] = { .driver_data = (unsigned long)ff_rumble }, { HID_USB_DEVICE(USB_VENDOR_ID_THRUSTMASTER, 0xb304), /* FireStorm Dual Power 2 (and 3) */ .driver_data = (unsigned long)ff_rumble }, + { HID_USB_DEVICE(USB_VENDOR_ID_THRUSTMASTER, THRUSTMASTER_DEVICE_ID_2_IN_1_DT), /* Dual Trigger 2-in-1 */ + .driver_data = (unsigned long)ff_rumble }, { HID_USB_DEVICE(USB_VENDOR_ID_THRUSTMASTER, 0xb323), /* Dual Trigger 3-in-1 (PC Mode) */ .driver_data = (unsigned long)ff_rumble }, { HID_USB_DEVICE(USB_VENDOR_ID_THRUSTMASTER, 0xb324), /* Dual Trigger 3-in-1 (PS3 Mode) */ diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index e56dc97fe4b6..50ef7b6cd195 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -848,6 +848,8 @@ static int wacom_intuos_general(struct wacom_wac *wacom) y >>= 1; distance >>= 1; } + if (features->type == INTUOSHT2) + distance = features->distance_max - distance; input_report_abs(input, ABS_X, x); input_report_abs(input, ABS_Y, y); input_report_abs(input, ABS_DISTANCE, distance); @@ -1061,7 +1063,7 @@ static int wacom_remote_irq(struct wacom_wac *wacom_wac, size_t len) input_report_key(input, BTN_BASE2, (data[11] & 0x02));

if (data[12] & 0x80) - input_report_abs(input, ABS_WHEEL, (data[12] & 0x7f)); + input_report_abs(input, ABS_WHEEL, (data[12] & 0x7f) - 1); else input_report_abs(input, ABS_WHEEL, 0);

diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c index 2f164bd74687..fdb0f832fade 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -38,7 +38,7 @@

static unsigned long virt_to_hvpfn(void *addr) { - unsigned long paddr; + phys_addr_t paddr;

if (is_vmalloc_addr(addr)) paddr = page_to_phys(vmalloc_to_page(addr)) + diff --git a/drivers/isdn/hardware/mISDN/hfcsusb.c b/drivers/isdn/hardware/mISDN/hfcsusb.c index 060dc7fd66c1..c952002c6301 100644 --- a/drivers/isdn/hardware/mISDN/hfcsusb.c +++ b/drivers/isdn/hardware/mISDN/hfcsusb.c @@ -1406,6 +1406,7 @@ start_isoc_chain(struct usb_fifo *fifo, int num_packets_per_urb, printk(KERN_DEBUG "%s: %s: alloc urb for fifo %i failed", hw->name, __func__, fifo->fifonum); + continue; } fifo->iso[i].owner_fifo = (struct usb_fifo *) fifo; fifo->iso[i].indx = i; @@ -1704,13 +1705,23 @@ hfcsusb_stop_endpoint(struct hfcsusb *hw, int channel) static int setup_hfcsusb(struct hfcsusb *hw) { + void *dmabuf = kmalloc(sizeof(u_char), GFP_KERNEL); u_char b; + int ret;

if (debug & DBG_HFC_CALL_TRACE) printk(KERN_DEBUG "%s: %s\n", hw->name, __func__);

+ if (!dmabuf) + return -ENOMEM; + + ret = read_reg_atomic(hw, HFCUSB_CHIP_ID, dmabuf); + + memcpy(&b, dmabuf, sizeof(u_char)); + kfree(dmabuf); + /* check the chip id */ - if (read_reg_atomic(hw, HFCUSB_CHIP_ID, &b) != 1) { + if (ret != 1) { printk(KERN_DEBUG "%s: %s: cannot read chip id\n", hw->name, __func__); return 1; diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index b1d0ae2dbd3d..dc385b70e4c3 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -1602,7 +1602,9 @@ dm_bufio_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) unsigned long freed;

c = container_of(shrink, struct dm_bufio_client, shrinker); - if (!dm_bufio_trylock(c)) + if (sc->gfp_mask & __GFP_FS) + dm_bufio_lock(c); + else if (!dm_bufio_trylock(c)) return SHRINK_STOP;

freed = __scan(c, sc->nr_to_scan, sc->gfp_mask); diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index dbdcc543832d..2e22d588f056 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -1749,7 +1749,22 @@ static void dm_integrity_map_continue(struct dm_integrity_io *dio, bool from_map queue_work(ic->wait_wq, &dio->work); return; } + if (journal_read_pos != NOT_FOUND) + dio->range.n_sectors = ic->sectors_per_block; wait_and_add_new_range(ic, &dio->range); + /* + * wait_and_add_new_range drops the spinlock, so the journal + * may have been changed arbitrarily. We need to recheck. + * To simplify the code, we restrict I/O size to just one block. + */ + if (journal_read_pos != NOT_FOUND) { + sector_t next_sector; + unsigned new_pos = find_journal_node(ic, dio->range.logical_sector, &next_sector); + if (unlikely(new_pos != journal_read_pos)) { + remove_range_unlocked(ic, &dio->range); + goto retry; + } + } } spin_unlock_irq(&ic->endio_wait.lock);

diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c index 671c24332802..3f694d9061ec 100644 --- a/drivers/md/dm-kcopyd.c +++ b/drivers/md/dm-kcopyd.c @@ -548,8 +548,10 @@ static int run_io_job(struct kcopyd_job *job) * no point in continuing. */ if (test_bit(DM_KCOPYD_WRITE_SEQ, &job->flags) && - job->master_job->write_err) + job->master_job->write_err) { + job->write_err = job->master_job->write_err; return -EIO; + }

io_job_start(job->kc->throttle);

@@ -601,6 +603,7 @@ static int process_jobs(struct list_head *jobs, struct dm_kcopyd_client *kc, else job->read_err = 1; push(&kc->complete_jobs, job); + wake(kc); break; }

diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index c44925e4e481..b78a8a4d061c 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -3199,7 +3199,7 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv) */ r = rs_prepare_reshape(rs); if (r) - return r; + goto bad;

/* Reshaping ain't recovery, so disable recovery */ rs_setup_recovery(rs, MaxSector); diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 34ab30dd5de9..36275c59e4e7 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -1349,7 +1349,7 @@ void dm_table_event(struct dm_table *t) } EXPORT_SYMBOL(dm_table_event);

-sector_t dm_table_get_size(struct dm_table *t) +inline sector_t dm_table_get_size(struct dm_table *t) { return t->num_targets ? (t->highs[t->num_targets - 1] + 1) : 0; } @@ -1374,6 +1374,9 @@ struct dm_target *dm_table_find_target(struct dm_table *t, sector_t sector) unsigned int l, n = 0, k = 0; sector_t *node;

+ if (unlikely(sector >= dm_table_get_size(t))) + return &t->targets[t->num_targets]; + for (l = 0; l < t->depth; l++) { n = get_child(n, k); node = get_node(t, l, n); diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c index 4cdde7a02e94..7e8d7fc99410 100644 --- a/drivers/md/dm-zoned-metadata.c +++ b/drivers/md/dm-zoned-metadata.c @@ -401,15 +401,18 @@ static struct dmz_mblock *dmz_get_mblock_slow(struct dmz_metadata *zmd, sector_t block = zmd->sb[zmd->mblk_primary].block + mblk_no; struct bio *bio;

+ if (dmz_bdev_is_dying(zmd->dev)) + return ERR_PTR(-EIO); + /* Get a new block and a BIO to read it */ mblk = dmz_alloc_mblock(zmd, mblk_no); if (!mblk) - return NULL; + return ERR_PTR(-ENOMEM);

bio = bio_alloc(GFP_NOIO, 1); if (!bio) { dmz_free_mblock(zmd, mblk); - return NULL; + return ERR_PTR(-ENOMEM); }

spin_lock(&zmd->mblk_lock); @@ -540,8 +543,8 @@ static struct dmz_mblock *dmz_get_mblock(struct dmz_metadata *zmd, if (!mblk) { /* Cache miss: read the block from disk */ mblk = dmz_get_mblock_slow(zmd, mblk_no); - if (!mblk) - return ERR_PTR(-ENOMEM); + if (IS_ERR(mblk)) + return mblk; }

/* Wait for on-going read I/O and check for error */ @@ -569,16 +572,19 @@ static void dmz_dirty_mblock(struct dmz_metadata *zmd, struct dmz_mblock *mblk) /* * Issue a metadata block write BIO. */ -static void dmz_write_mblock(struct dmz_metadata *zmd, struct dmz_mblock *mblk, - unsigned int set) +static int dmz_write_mblock(struct dmz_metadata *zmd, struct dmz_mblock *mblk, + unsigned int set) { sector_t block = zmd->sb[set].block + mblk->no; struct bio *bio;

+ if (dmz_bdev_is_dying(zmd->dev)) + return -EIO; + bio = bio_alloc(GFP_NOIO, 1); if (!bio) { set_bit(DMZ_META_ERROR, &mblk->state); - return; + return -ENOMEM; }

set_bit(DMZ_META_WRITING, &mblk->state); @@ -590,6 +596,8 @@ static void dmz_write_mblock(struct dmz_metadata *zmd, struct dmz_mblock *mblk, bio_set_op_attrs(bio, REQ_OP_WRITE, REQ_META | REQ_PRIO); bio_add_page(bio, mblk->page, DMZ_BLOCK_SIZE, 0); submit_bio(bio); + + return 0; }

/* @@ -601,6 +609,9 @@ static int dmz_rdwr_block(struct dmz_metadata *zmd, int op, sector_t block, struct bio *bio; int ret;

+ if (dmz_bdev_is_dying(zmd->dev)) + return -EIO; + bio = bio_alloc(GFP_NOIO, 1); if (!bio) return -ENOMEM; @@ -658,22 +669,29 @@ static int dmz_write_dirty_mblocks(struct dmz_metadata *zmd, { struct dmz_mblock *mblk; struct blk_plug plug; - int ret = 0; + int ret = 0, nr_mblks_submitted = 0;

/* Issue writes */ blk_start_plug(&plug); - list_for_each_entry(mblk, write_list, link) - dmz_write_mblock(zmd, mblk, set); + list_for_each_entry(mblk, write_list, link) { + ret = dmz_write_mblock(zmd, mblk, set); + if (ret) + break; + nr_mblks_submitted++; + } blk_finish_plug(&plug);

/* Wait for completion */ list_for_each_entry(mblk, write_list, link) { + if (!nr_mblks_submitted) + break; wait_on_bit_io(&mblk->state, DMZ_META_WRITING, TASK_UNINTERRUPTIBLE); if (test_bit(DMZ_META_ERROR, &mblk->state)) { clear_bit(DMZ_META_ERROR, &mblk->state); ret = -EIO; } + nr_mblks_submitted--; }

/* Flush drive cache (this will also sync data) */ @@ -735,6 +753,11 @@ int dmz_flush_metadata(struct dmz_metadata *zmd) */ dmz_lock_flush(zmd);

+ if (dmz_bdev_is_dying(zmd->dev)) { + ret = -EIO; + goto out; + } + /* Get dirty blocks */ spin_lock(&zmd->mblk_lock); list_splice_init(&zmd->mblk_dirty_list, &write_list); @@ -1534,7 +1557,7 @@ static struct dm_zone *dmz_get_rnd_zone_for_reclaim(struct dmz_metadata *zmd) struct dm_zone *zone;

if (list_empty(&zmd->map_rnd_list)) - return NULL; + return ERR_PTR(-EBUSY);

list_for_each_entry(zone, &zmd->map_rnd_list, link) { if (dmz_is_buf(zone)) @@ -1545,7 +1568,7 @@ static struct dm_zone *dmz_get_rnd_zone_for_reclaim(struct dmz_metadata *zmd) return dzone; }

- return NULL; + return ERR_PTR(-EBUSY); }

/* @@ -1556,7 +1579,7 @@ static struct dm_zone *dmz_get_seq_zone_for_reclaim(struct dmz_metadata *zmd) struct dm_zone *zone;

if (list_empty(&zmd->map_seq_list)) - return NULL; + return ERR_PTR(-EBUSY);

list_for_each_entry(zone, &zmd->map_seq_list, link) { if (!zone->bzone) @@ -1565,7 +1588,7 @@ static struct dm_zone *dmz_get_seq_zone_for_reclaim(struct dmz_metadata *zmd) return zone; }

- return NULL; + return ERR_PTR(-EBUSY); }

/* @@ -1623,6 +1646,10 @@ struct dm_zone *dmz_get_chunk_mapping(struct dmz_metadata *zmd, unsigned int chu /* Alloate a random zone */ dzone = dmz_alloc_zone(zmd, DMZ_ALLOC_RND); if (!dzone) { + if (dmz_bdev_is_dying(zmd->dev)) { + dzone = ERR_PTR(-EIO); + goto out; + } dmz_wait_for_free_zones(zmd); goto again; } @@ -1720,6 +1747,10 @@ struct dm_zone *dmz_get_chunk_buffer(struct dmz_metadata *zmd, /* Alloate a random zone */ bzone = dmz_alloc_zone(zmd, DMZ_ALLOC_RND); if (!bzone) { + if (dmz_bdev_is_dying(zmd->dev)) { + bzone = ERR_PTR(-EIO); + goto out; + } dmz_wait_for_free_zones(zmd); goto again; } diff --git a/drivers/md/dm-zoned-reclaim.c b/drivers/md/dm-zoned-reclaim.c index edf4b95eb075..9470b8f77a33 100644 --- a/drivers/md/dm-zoned-reclaim.c +++ b/drivers/md/dm-zoned-reclaim.c @@ -37,7 +37,7 @@ enum { /* * Number of seconds of target BIO inactivity to consider the target idle. */ -#define DMZ_IDLE_PERIOD (10UL * HZ) +#define DMZ_IDLE_PERIOD (10UL * HZ)

/* * Percentage of unmapped (free) random zones below which reclaim starts @@ -134,6 +134,9 @@ static int dmz_reclaim_copy(struct dmz_reclaim *zrc, set_bit(DM_KCOPYD_WRITE_SEQ, &flags);

while (block < end_block) { + if (dev->flags & DMZ_BDEV_DYING) + return -EIO; + /* Get a valid region from the source zone */ ret = dmz_first_valid_block(zmd, src_zone, &block); if (ret <= 0) @@ -215,7 +218,7 @@ static int dmz_reclaim_buf(struct dmz_reclaim *zrc, struct dm_zone *dzone)

dmz_unlock_flush(zmd);

- return 0; + return ret; }

/* @@ -259,7 +262,7 @@ static int dmz_reclaim_seq_data(struct dmz_reclaim *zrc, struct dm_zone *dzone)

dmz_unlock_flush(zmd);

- return 0; + return ret; }

/* @@ -312,7 +315,7 @@ static int dmz_reclaim_rnd_data(struct dmz_reclaim *zrc, struct dm_zone *dzone)

dmz_unlock_flush(zmd);

- return 0; + return ret; }

/* @@ -334,7 +337,7 @@ static void dmz_reclaim_empty(struct dmz_reclaim *zrc, struct dm_zone *dzone) /* * Find a candidate zone for reclaim and process it. */ -static void dmz_reclaim(struct dmz_reclaim *zrc) +static int dmz_do_reclaim(struct dmz_reclaim *zrc) { struct dmz_metadata *zmd = zrc->metadata; struct dm_zone *dzone; @@ -344,8 +347,8 @@ static void dmz_reclaim(struct dmz_reclaim *zrc)

/* Get a data zone */ dzone = dmz_get_zone_for_reclaim(zmd); - if (!dzone) - return; + if (IS_ERR(dzone)) + return PTR_ERR(dzone);

start = jiffies;

@@ -391,13 +394,20 @@ static void dmz_reclaim(struct dmz_reclaim *zrc) out: if (ret) { dmz_unlock_zone_reclaim(dzone); - return; + return ret; }

- (void) dmz_flush_metadata(zrc->metadata); + ret = dmz_flush_metadata(zrc->metadata); + if (ret) { + dmz_dev_debug(zrc->dev, + "Metadata flush for zone %u failed, err %d\n", + dmz_id(zmd, rzone), ret); + return ret; + }

dmz_dev_debug(zrc->dev, "Reclaimed zone %u in %u ms", dmz_id(zmd, rzone), jiffies_to_msecs(jiffies - start)); + return 0; }

/* @@ -442,6 +452,10 @@ static void dmz_reclaim_work(struct work_struct *work) struct dmz_metadata *zmd = zrc->metadata; unsigned int nr_rnd, nr_unmap_rnd; unsigned int p_unmap_rnd; + int ret; + + if (dmz_bdev_is_dying(zrc->dev)) + return;

if (!dmz_should_reclaim(zrc)) { mod_delayed_work(zrc->wq, &zrc->work, DMZ_IDLE_PERIOD); @@ -471,7 +485,17 @@ static void dmz_reclaim_work(struct work_struct *work) (dmz_target_idle(zrc) ? "Idle" : "Busy"), p_unmap_rnd, nr_unmap_rnd, nr_rnd);

- dmz_reclaim(zrc); + ret = dmz_do_reclaim(zrc); + if (ret) { + dmz_dev_debug(zrc->dev, "Reclaim error %d\n", ret); + if (ret == -EIO) + /* + * LLD might be performing some error handling sequence + * at the underlying device. To not interfere, do not + * attempt to schedule the next reclaim run immediately. + */ + return; + }

dmz_schedule_reclaim(zrc); } diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c index 85fb2baa8a7f..1030c42add05 100644 --- a/drivers/md/dm-zoned-target.c +++ b/drivers/md/dm-zoned-target.c @@ -133,6 +133,8 @@ static int dmz_submit_bio(struct dmz_target *dmz, struct dm_zone *zone,

atomic_inc(&bioctx->ref); generic_make_request(clone); + if (clone->bi_status == BLK_STS_IOERR) + return -EIO;

if (bio_op(bio) == REQ_OP_WRITE && dmz_is_seq(zone)) zone->wp_block += nr_blocks; @@ -277,8 +279,8 @@ static int dmz_handle_buffered_write(struct dmz_target *dmz,

/* Get the buffer zone. One will be allocated if needed */ bzone = dmz_get_chunk_buffer(zmd, zone); - if (!bzone) - return -ENOSPC; + if (IS_ERR(bzone)) + return PTR_ERR(bzone);

if (dmz_is_readonly(bzone)) return -EROFS; @@ -389,6 +391,11 @@ static void dmz_handle_bio(struct dmz_target *dmz, struct dm_chunk_work *cw,

dmz_lock_metadata(zmd);

+ if (dmz->dev->flags & DMZ_BDEV_DYING) { + ret = -EIO; + goto out; + } + /* * Get the data zone mapping the chunk. There may be no * mapping for read and discard. If a mapping is obtained, @@ -493,6 +500,8 @@ static void dmz_flush_work(struct work_struct *work)

/* Flush dirty metadata blocks */ ret = dmz_flush_metadata(dmz->metadata); + if (ret) + dmz_dev_debug(dmz->dev, "Metadata flush failed, rc=%d\n", ret);

/* Process queued flush requests */ while (1) { @@ -513,22 +522,24 @@ static void dmz_flush_work(struct work_struct *work) * Get a chunk work and start it to process a new BIO. * If the BIO chunk has no work yet, create one. */ -static void dmz_queue_chunk_work(struct dmz_target *dmz, struct bio *bio) +static int dmz_queue_chunk_work(struct dmz_target *dmz, struct bio *bio) { unsigned int chunk = dmz_bio_chunk(dmz->dev, bio); struct dm_chunk_work *cw; + int ret = 0;

mutex_lock(&dmz->chunk_lock);

/* Get the BIO chunk work. If one is not active yet, create one */ cw = radix_tree_lookup(&dmz->chunk_rxtree, chunk); if (!cw) { - int ret;

/* Create a new chunk work */ cw = kmalloc(sizeof(struct dm_chunk_work), GFP_NOIO); - if (!cw) + if (unlikely(!cw)) { + ret = -ENOMEM; goto out; + }

INIT_WORK(&cw->work, dmz_chunk_work); atomic_set(&cw->refcount, 0); @@ -539,7 +550,6 @@ static void dmz_queue_chunk_work(struct dmz_target *dmz, struct bio *bio) ret = radix_tree_insert(&dmz->chunk_rxtree, chunk, cw); if (unlikely(ret)) { kfree(cw); - cw = NULL; goto out; } } @@ -547,10 +557,38 @@ static void dmz_queue_chunk_work(struct dmz_target *dmz, struct bio *bio) bio_list_add(&cw->bio_list, bio); dmz_get_chunk_work(cw);

+ dmz_reclaim_bio_acc(dmz->reclaim); if (queue_work(dmz->chunk_wq, &cw->work)) dmz_get_chunk_work(cw); out: mutex_unlock(&dmz->chunk_lock); + return ret; +} + +/* + * Check the backing device availability. If it's on the way out, + * start failing I/O. Reclaim and metadata components also call this + * function to cleanly abort operation in the event of such failure. + */ +bool dmz_bdev_is_dying(struct dmz_dev *dmz_dev) +{ + struct gendisk *disk; + + if (!(dmz_dev->flags & DMZ_BDEV_DYING)) { + disk = dmz_dev->bdev->bd_disk; + if (blk_queue_dying(bdev_get_queue(dmz_dev->bdev))) { + dmz_dev_warn(dmz_dev, "Backing device queue dying"); + dmz_dev->flags |= DMZ_BDEV_DYING; + } else if (disk->fops->check_events) { + if (disk->fops->check_events(disk, 0) & + DISK_EVENT_MEDIA_CHANGE) { + dmz_dev_warn(dmz_dev, "Backing device offline"); + dmz_dev->flags |= DMZ_BDEV_DYING; + } + } + } + + return dmz_dev->flags & DMZ_BDEV_DYING; }

/* @@ -564,6 +602,10 @@ static int dmz_map(struct dm_target *ti, struct bio *bio) sector_t sector = bio->bi_iter.bi_sector; unsigned int nr_sectors = bio_sectors(bio); sector_t chunk_sector; + int ret; + + if (dmz_bdev_is_dying(dmz->dev)) + return DM_MAPIO_KILL;

dmz_dev_debug(dev, "BIO op %d sector %llu + %u => chunk %llu, block %llu, %u blocks", bio_op(bio), (unsigned long long)sector, nr_sectors, @@ -601,8 +643,14 @@ static int dmz_map(struct dm_target *ti, struct bio *bio) dm_accept_partial_bio(bio, dev->zone_nr_sectors - chunk_sector);

/* Now ready to handle this BIO */ - dmz_reclaim_bio_acc(dmz->reclaim); - dmz_queue_chunk_work(dmz, bio); + ret = dmz_queue_chunk_work(dmz, bio); + if (ret) { + dmz_dev_debug(dmz->dev, + "BIO op %d, can't process chunk %llu, err %i\n", + bio_op(bio), (u64)dmz_bio_chunk(dmz->dev, bio), + ret); + return DM_MAPIO_REQUEUE; + }

return DM_MAPIO_SUBMITTED; } @@ -856,6 +904,9 @@ static int dmz_prepare_ioctl(struct dm_target *ti, struct block_device **bdev) { struct dmz_target *dmz = ti->private;

+ if (dmz_bdev_is_dying(dmz->dev)) + return -ENODEV; + *bdev = dmz->dev->bdev;

return 0; diff --git a/drivers/md/dm-zoned.h b/drivers/md/dm-zoned.h index ed8de49c9a08..93a64529f219 100644 --- a/drivers/md/dm-zoned.h +++ b/drivers/md/dm-zoned.h @@ -56,6 +56,8 @@ struct dmz_dev {

unsigned int nr_zones;

+ unsigned int flags; + sector_t zone_nr_sectors; unsigned int zone_nr_sectors_shift;

@@ -67,6 +69,9 @@ struct dmz_dev { (dev)->zone_nr_sectors_shift) #define dmz_chunk_block(dev, b) ((b) & ((dev)->zone_nr_blocks - 1))

+/* Device flags. */ +#define DMZ_BDEV_DYING (1 << 0) + /* * Zone descriptor. */ @@ -245,4 +250,9 @@ void dmz_resume_reclaim(struct dmz_reclaim *zrc); void dmz_reclaim_bio_acc(struct dmz_reclaim *zrc); void dmz_schedule_reclaim(struct dmz_reclaim *zrc);

+/* + * Functions defined in dm-zoned-target.c + */ +bool dmz_bdev_is_dying(struct dmz_dev *dmz_dev); + #endif /* DM_ZONED_H */ diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c index 58b319757b1e..8aae0624a297 100644 --- a/drivers/md/persistent-data/dm-btree.c +++ b/drivers/md/persistent-data/dm-btree.c @@ -628,39 +628,40 @@ static int btree_split_beneath(struct shadow_spine *s, uint64_t key)

new_parent = shadow_current(s);

+ pn = dm_block_data(new_parent); + size = le32_to_cpu(pn->header.flags) & INTERNAL_NODE ? + sizeof(__le64) : s->info->value_type.size; + + /* create & init the left block */ r = new_block(s->info, &left); if (r < 0) return r;

+ ln = dm_block_data(left); + nr_left = le32_to_cpu(pn->header.nr_entries) / 2; + + ln->header.flags = pn->header.flags; + ln->header.nr_entries = cpu_to_le32(nr_left); + ln->header.max_entries = pn->header.max_entries; + ln->header.value_size = pn->header.value_size; + memcpy(ln->keys, pn->keys, nr_left * sizeof(pn->keys[0])); + memcpy(value_ptr(ln, 0), value_ptr(pn, 0), nr_left * size); + + /* create & init the right block */ r = new_block(s->info, &right); if (r < 0) { unlock_block(s->info, left); return r; }

- pn = dm_block_data(new_parent); - ln = dm_block_data(left); rn = dm_block_data(right); - - nr_left = le32_to_cpu(pn->header.nr_entries) / 2; nr_right = le32_to_cpu(pn->header.nr_entries) - nr_left;

- ln->header.flags = pn->header.flags; - ln->header.nr_entries = cpu_to_le32(nr_left); - ln->header.max_entries = pn->header.max_entries; - ln->header.value_size = pn->header.value_size; - rn->header.flags = pn->header.flags; rn->header.nr_entries = cpu_to_le32(nr_right); rn->header.max_entries = pn->header.max_entries; rn->header.value_size = pn->header.value_size; - - memcpy(ln->keys, pn->keys, nr_left * sizeof(pn->keys[0])); memcpy(rn->keys, pn->keys + nr_left, nr_right * sizeof(pn->keys[0])); - - size = le32_to_cpu(pn->header.flags) & INTERNAL_NODE ? - sizeof(__le64) : s->info->value_type.size; - memcpy(value_ptr(ln, 0), value_ptr(pn, 0), nr_left * size); memcpy(value_ptr(rn, 0), value_ptr(pn, nr_left), nr_right * size);

diff --git a/drivers/md/persistent-data/dm-space-map-metadata.c b/drivers/md/persistent-data/dm-space-map-metadata.c index aec449243966..25328582cc48 100644 --- a/drivers/md/persistent-data/dm-space-map-metadata.c +++ b/drivers/md/persistent-data/dm-space-map-metadata.c @@ -249,7 +249,7 @@ static int out(struct sm_metadata *smm) }

if (smm->recursion_count == 1) - apply_bops(smm); + r = apply_bops(smm);

smm->recursion_count--;

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 8f14f85b8e95..0d2392c4b625 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -2190,6 +2190,15 @@ static void bond_miimon_commit(struct bonding *bond) bond_for_each_slave(bond, slave, iter) { switch (slave->new_link) { case BOND_LINK_NOCHANGE: + /* For 802.3ad mode, check current slave speed and + * duplex again in case its port was disabled after + * invalid speed/duplex reporting but recovered before + * link monitoring could make a decision on the actual + * link status + */ + if (BOND_MODE(bond) == BOND_MODE_8023AD && + slave->link == BOND_LINK_UP) + bond_3ad_adapter_speed_duplex_changed(slave); continue;

case BOND_LINK_UP: diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c index c05e4d50d43d..bd127ce3aba2 100644 --- a/drivers/net/can/dev.c +++ b/drivers/net/can/dev.c @@ -1260,6 +1260,8 @@ int register_candev(struct net_device *dev) return -EINVAL;

dev->rtnl_link_ops = &can_link_ops; + netif_carrier_off(dev); + return register_netdev(dev); } EXPORT_SYMBOL_GPL(register_candev); diff --git a/drivers/net/can/sja1000/peak_pcmcia.c b/drivers/net/can/sja1000/peak_pcmcia.c index b8c39ede7cd5..179bfcd541f2 100644 --- a/drivers/net/can/sja1000/peak_pcmcia.c +++ b/drivers/net/can/sja1000/peak_pcmcia.c @@ -487,7 +487,7 @@ static void pcan_free_channels(struct pcan_pccard *card) if (!netdev) continue;

- strncpy(name, netdev->name, IFNAMSIZ); + strlcpy(name, netdev->name, IFNAMSIZ);

unregister_sja1000dev(netdev);

diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c index da64e71a62ee..fccb6bf21fad 100644 --- a/drivers/net/can/spi/mcp251x.c +++ b/drivers/net/can/spi/mcp251x.c @@ -678,17 +678,6 @@ static int mcp251x_power_enable(struct regulator *reg, int enable) return regulator_disable(reg); }

-static void mcp251x_open_clean(struct net_device *net) -{ - struct mcp251x_priv *priv = netdev_priv(net); - struct spi_device *spi = priv->spi; - - free_irq(spi->irq, priv); - mcp251x_hw_sleep(spi); - mcp251x_power_enable(priv->transceiver, 0); - close_candev(net); -} - static int mcp251x_stop(struct net_device *net) { struct mcp251x_priv *priv = netdev_priv(net); @@ -954,37 +943,43 @@ static int mcp251x_open(struct net_device *net) flags | IRQF_ONESHOT, DEVICE_NAME, priv); if (ret) { dev_err(&spi->dev, "failed to acquire irq %d\n", spi->irq); - mcp251x_power_enable(priv->transceiver, 0); - close_candev(net); - goto open_unlock; + goto out_close; }

priv->wq = alloc_workqueue("mcp251x_wq", WQ_FREEZABLE | WQ_MEM_RECLAIM, 0); + if (!priv->wq) { + ret = -ENOMEM; + goto out_clean; + } INIT_WORK(&priv->tx_work, mcp251x_tx_work_handler); INIT_WORK(&priv->restart_work, mcp251x_restart_work_handler);

ret = mcp251x_hw_reset(spi); - if (ret) { - mcp251x_open_clean(net); - goto open_unlock; - } + if (ret) + goto out_free_wq; ret = mcp251x_setup(net, spi); - if (ret) { - mcp251x_open_clean(net); - goto open_unlock; - } + if (ret) + goto out_free_wq; ret = mcp251x_set_normal_mode(spi); - if (ret) { - mcp251x_open_clean(net); - goto open_unlock; - } + if (ret) + goto out_free_wq;

can_led_event(net, CAN_LED_EVENT_OPEN);

netif_wake_queue(net); + mutex_unlock(&priv->mcp_lock);

-open_unlock: + return 0; + +out_free_wq: + destroy_workqueue(priv->wq); +out_clean: + free_irq(spi->irq, priv); + mcp251x_hw_sleep(spi); +out_close: + mcp251x_power_enable(priv->transceiver, 0); + close_candev(net); mutex_unlock(&priv->mcp_lock); return ret; } diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c index 740ef47eab01..43b0fa2b9932 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c @@ -863,7 +863,7 @@ static void peak_usb_disconnect(struct usb_interface *intf)

dev_prev_siblings = dev->prev_siblings; dev->state &= ~PCAN_USB_STATE_CONNECTED; - strncpy(name, netdev->name, IFNAMSIZ); + strlcpy(name, netdev->name, IFNAMSIZ);

unregister_netdev(netdev);

diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c index c34ea385fe4a..6be6de0774b6 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c +++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c @@ -3270,7 +3270,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (!adapter->regs) { dev_err(&pdev->dev, "cannot map device registers\n"); err = -ENOMEM; - goto out_free_adapter; + goto out_free_adapter_nofail; }

adapter->pdev = pdev; @@ -3398,6 +3398,9 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (adapter->port[i]) free_netdev(adapter->port[i]);

+out_free_adapter_nofail: + kfree_skb(adapter->nofail_skb); + out_free_adapter: kfree(adapter);

diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c index 6127697ede12..a91d49dd92ea 100644 --- a/drivers/net/ethernet/hisilicon/hip04_eth.c +++ b/drivers/net/ethernet/hisilicon/hip04_eth.c @@ -157,6 +157,7 @@ struct hip04_priv { unsigned int reg_inten;

struct napi_struct napi; + struct device *dev; struct net_device *ndev;

struct tx_desc *tx_desc; @@ -185,7 +186,7 @@ struct hip04_priv {

static inline unsigned int tx_count(unsigned int head, unsigned int tail) { - return (head - tail) % (TX_DESC_NUM - 1); + return (head - tail) % TX_DESC_NUM; }

static void hip04_config_port(struct net_device *ndev, u32 speed, u32 duplex) @@ -387,7 +388,7 @@ static int hip04_tx_reclaim(struct net_device *ndev, bool force) }

if (priv->tx_phys[tx_tail]) { - dma_unmap_single(&ndev->dev, priv->tx_phys[tx_tail], + dma_unmap_single(priv->dev, priv->tx_phys[tx_tail], priv->tx_skb[tx_tail]->len, DMA_TO_DEVICE); priv->tx_phys[tx_tail] = 0; @@ -437,8 +438,8 @@ static int hip04_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev) return NETDEV_TX_BUSY; }

- phys = dma_map_single(&ndev->dev, skb->data, skb->len, DMA_TO_DEVICE); - if (dma_mapping_error(&ndev->dev, phys)) { + phys = dma_map_single(priv->dev, skb->data, skb->len, DMA_TO_DEVICE); + if (dma_mapping_error(priv->dev, phys)) { dev_kfree_skb(skb); return NETDEV_TX_OK; } @@ -497,6 +498,9 @@ static int hip04_rx_poll(struct napi_struct *napi, int budget) u16 len; u32 err;

+ /* clean up tx descriptors */ + tx_remaining = hip04_tx_reclaim(ndev, false); + while (cnt && !last) { buf = priv->rx_buf[priv->rx_head]; skb = build_skb(buf, priv->rx_buf_size); @@ -505,7 +509,7 @@ static int hip04_rx_poll(struct napi_struct *napi, int budget) goto refill; }

- dma_unmap_single(&ndev->dev, priv->rx_phys[priv->rx_head], + dma_unmap_single(priv->dev, priv->rx_phys[priv->rx_head], RX_BUF_SIZE, DMA_FROM_DEVICE); priv->rx_phys[priv->rx_head] = 0;

@@ -534,9 +538,9 @@ static int hip04_rx_poll(struct napi_struct *napi, int budget) buf = netdev_alloc_frag(priv->rx_buf_size); if (!buf) goto done; - phys = dma_map_single(&ndev->dev, buf, + phys = dma_map_single(priv->dev, buf, RX_BUF_SIZE, DMA_FROM_DEVICE); - if (dma_mapping_error(&ndev->dev, phys)) + if (dma_mapping_error(priv->dev, phys)) goto done; priv->rx_buf[priv->rx_head] = buf; priv->rx_phys[priv->rx_head] = phys; @@ -557,8 +561,7 @@ static int hip04_rx_poll(struct napi_struct *napi, int budget) } napi_complete_done(napi, rx); done: - /* clean up tx descriptors and start a new timer if necessary */ - tx_remaining = hip04_tx_reclaim(ndev, false); + /* start a new timer if necessary */ if (rx < budget && tx_remaining) hip04_start_tx_timer(priv);

@@ -640,9 +643,9 @@ static int hip04_mac_open(struct net_device *ndev) for (i = 0; i < RX_DESC_NUM; i++) { dma_addr_t phys;

- phys = dma_map_single(&ndev->dev, priv->rx_buf[i], + phys = dma_map_single(priv->dev, priv->rx_buf[i], RX_BUF_SIZE, DMA_FROM_DEVICE); - if (dma_mapping_error(&ndev->dev, phys)) + if (dma_mapping_error(priv->dev, phys)) return -EIO;

priv->rx_phys[i] = phys; @@ -676,7 +679,7 @@ static int hip04_mac_stop(struct net_device *ndev)

for (i = 0; i < RX_DESC_NUM; i++) { if (priv->rx_phys[i]) { - dma_unmap_single(&ndev->dev, priv->rx_phys[i], + dma_unmap_single(priv->dev, priv->rx_phys[i], RX_BUF_SIZE, DMA_FROM_DEVICE); priv->rx_phys[i] = 0; } @@ -820,6 +823,7 @@ static int hip04_mac_probe(struct platform_device *pdev) return -ENOMEM;

priv = netdev_priv(ndev); + priv->dev = d; priv->ndev = ndev; platform_set_drvdata(pdev, ndev); SET_NETDEV_DEV(ndev, &pdev->dev); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 6455511457ca..9b608d23ff7e 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -4412,9 +4412,9 @@ static void mvpp2_xlg_config(struct mvpp2_port *port, unsigned int mode, if (state->pause & MLO_PAUSE_RX) ctrl0 |= MVPP22_XLG_CTRL0_RX_FLOW_CTRL_EN;

- ctrl4 &= ~MVPP22_XLG_CTRL4_MACMODSELECT_GMAC; - ctrl4 |= MVPP22_XLG_CTRL4_FWD_FC | MVPP22_XLG_CTRL4_FWD_PFC | - MVPP22_XLG_CTRL4_EN_IDLE_CHECK; + ctrl4 &= ~(MVPP22_XLG_CTRL4_MACMODSELECT_GMAC | + MVPP22_XLG_CTRL4_EN_IDLE_CHECK); + ctrl4 |= MVPP22_XLG_CTRL4_FWD_FC | MVPP22_XLG_CTRL4_FWD_PFC;

writel(ctrl0, port->base + MVPP22_XLG_CTRL0_REG); writel(ctrl4, port->base + MVPP22_XLG_CTRL4_REG); diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c index b22f464ea3fa..f9e475075d3e 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_int.c +++ b/drivers/net/ethernet/qlogic/qed/qed_int.c @@ -939,7 +939,7 @@ static int qed_int_deassertion(struct qed_hwfn *p_hwfn, snprintf(bit_name, 30, p_aeu->bit_name, num); else - strncpy(bit_name, + strlcpy(bit_name, p_aeu->bit_name, 30);

/* We now need to pass bitmask in its diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c index 13802b825d65..909422d93903 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c +++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c @@ -442,7 +442,7 @@ static void qed_rdma_init_devinfo(struct qed_hwfn *p_hwfn, /* Vendor specific information */ dev->vendor_id = cdev->vendor_id; dev->vendor_part_id = cdev->device_id; - dev->hw_ver = 0; + dev->hw_ver = cdev->chip_rev; dev->fw_ver = (FW_MAJOR_VERSION << 24) | (FW_MINOR_VERSION << 16) | (FW_REVISION_VERSION << 8) | (FW_ENGINEERING_VERSION);

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index d0e6e1503581..48cf5e2b2441 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -88,6 +88,8 @@ static void dwmac4_rx_queue_priority(struct mac_device_info *hw, u32 value;

base_register = (queue < 4) ? GMAC_RXQ_CTRL2 : GMAC_RXQ_CTRL3; + if (queue >= 4) + queue -= 4;

value = readl(ioaddr + base_register);

@@ -105,6 +107,8 @@ static void dwmac4_tx_queue_priority(struct mac_device_info *hw, u32 value;

base_register = (queue < 4) ? GMAC_TXQ_PRTY_MAP0 : GMAC_TXQ_PRTY_MAP1; + if (queue >= 4) + queue -= 4;

value = readl(ioaddr + base_register);

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c index d182f82f7b58..870302a7177e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c @@ -106,6 +106,8 @@ static void dwxgmac2_rx_queue_prio(struct mac_device_info *hw, u32 prio, u32 value, reg;

reg = (queue < 4) ? XGMAC_RXQ_CTRL2 : XGMAC_RXQ_CTRL3; + if (queue >= 4) + queue -= 4;

value = readl(ioaddr + reg); value &= ~XGMAC_PSRQ(queue); @@ -169,6 +171,8 @@ static void dwxgmac2_map_mtl_to_dma(struct mac_device_info *hw, u32 queue, u32 value, reg;

reg = (queue < 4) ? XGMAC_MTL_RXQ_DMA_MAP0 : XGMAC_MTL_RXQ_DMA_MAP1; + if (queue >= 4) + queue -= 4;

value = readl(ioaddr + reg); value &= ~XGMAC_QxMDMACH(queue); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c index 58ea18af9813..37c0bc699cd9 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c @@ -37,7 +37,7 @@ static struct stmmac_tc_entry *tc_find_entry(struct stmmac_priv *priv, entry = &priv->tc_entries[i]; if (!entry->in_use && !first && free) first = entry; - if (entry->handle == loc && !free) + if ((entry->handle == loc) && !free && !entry->is_frag) dup = entry; }

diff --git a/drivers/net/phy/phy_led_triggers.c b/drivers/net/phy/phy_led_triggers.c index 491efc1bf5c4..7278eca70f9f 100644 --- a/drivers/net/phy/phy_led_triggers.c +++ b/drivers/net/phy/phy_led_triggers.c @@ -58,8 +58,9 @@ void phy_led_trigger_change_speed(struct phy_device *phy) if (!phy->last_triggered) led_trigger_event(&phy->led_link_trigger->trigger, LED_FULL); + else + led_trigger_event(&phy->last_triggered->trigger, LED_OFF);

- led_trigger_event(&phy->last_triggered->trigger, LED_OFF); led_trigger_event(&plt->trigger, LED_FULL); phy->last_triggered = plt; } diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 128c8a327d8e..51017c6bb3bc 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1231,6 +1231,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x2001, 0x7e35, 4)}, /* D-Link DWM-222 */ {QMI_FIXED_INTF(0x2020, 0x2031, 4)}, /* Olicard 600 */ {QMI_FIXED_INTF(0x2020, 0x2033, 4)}, /* BroadMobi BM806U */ + {QMI_FIXED_INTF(0x2020, 0x2060, 4)}, /* BroadMobi BM818 */ {QMI_FIXED_INTF(0x0f3d, 0x68a2, 8)}, /* Sierra Wireless MC7700 */ {QMI_FIXED_INTF(0x114f, 0x68a2, 8)}, /* Sierra Wireless MC7750 */ {QMI_FIXED_INTF(0x1199, 0x68a2, 8)}, /* Sierra Wireless MC7710 in QMI mode */ diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 7cd428c0af43..ce2dd06af62e 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -3502,10 +3502,12 @@ static int hwsim_dump_radio_nl(struct sk_buff *skb, hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &hwsim_genl_family, NLM_F_MULTI, HWSIM_CMD_GET_RADIO); - if (!hdr) + if (hdr) { + genl_dump_check_consistent(cb, hdr); + genlmsg_end(skb, hdr); + } else { res = -EMSGSIZE; - genl_dump_check_consistent(cb, hdr); - genlmsg_end(skb, hdr); + } }

done: diff --git a/drivers/nfc/st-nci/se.c b/drivers/nfc/st-nci/se.c index f55d082ace71..5d6e7e931bc6 100644 --- a/drivers/nfc/st-nci/se.c +++ b/drivers/nfc/st-nci/se.c @@ -344,6 +344,8 @@ static int st_nci_hci_connectivity_event_received(struct nci_dev *ndev,

transaction = (struct nfc_evt_transaction *)devm_kzalloc(dev, skb->len - 2, GFP_KERNEL); + if (!transaction) + return -ENOMEM;

transaction->aid_len = skb->data[1]; memcpy(transaction->aid, &skb->data[2], transaction->aid_len); diff --git a/drivers/nfc/st21nfca/se.c b/drivers/nfc/st21nfca/se.c index 4bed9e842db3..fd967a38a94a 100644 --- a/drivers/nfc/st21nfca/se.c +++ b/drivers/nfc/st21nfca/se.c @@ -328,6 +328,8 @@ int st21nfca_connectivity_event_received(struct nfc_hci_dev *hdev, u8 host,

transaction = (struct nfc_evt_transaction *)devm_kzalloc(dev, skb->len - 2, GFP_KERNEL); + if (!transaction) + return -ENOMEM;

transaction->aid_len = skb->data[1]; memcpy(transaction->aid, &skb->data[2], diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 9c332a6f6667..476728bdae8c 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -913,8 +913,9 @@ static int ceph_writepages_start(struct address_space *mapping, if (page_offset(page) >= ceph_wbc.i_size) { dout("%p page eof %llu\n", page, ceph_wbc.i_size); - if (ceph_wbc.size_stable || - page_offset(page) >= i_size_read(inode)) + if ((ceph_wbc.size_stable || + page_offset(page) >= i_size_read(inode)) && + clear_page_dirty_for_io(page)) mapping->a_ops->invalidatepage(page, 0, PAGE_SIZE); unlock_page(page); diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c index 9dae2ec7e1fa..6a8f4a99582e 100644 --- a/fs/ceph/locks.c +++ b/fs/ceph/locks.c @@ -111,8 +111,7 @@ static int ceph_lock_message(u8 lock_type, u16 operation, struct inode *inode, req->r_wait_for_completion = ceph_lock_wait_for_completion;

err = ceph_mdsc_do_request(mdsc, inode, req); - - if (operation == CEPH_MDS_OP_GETFILELOCK) { + if (!err && operation == CEPH_MDS_OP_GETFILELOCK) { fl->fl_pid = -le64_to_cpu(req->r_reply_info.filelock_reply->pid); if (CEPH_LOCK_SHARED == req->r_reply_info.filelock_reply->type) fl->fl_type = F_RDLCK; diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 0ccf8f9b63a2..cc9e846a3865 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -2545,7 +2545,15 @@ fill_transform_hdr(struct smb2_transform_hdr *tr_hdr, unsigned int orig_len, static inline void smb2_sg_set_buf(struct scatterlist *sg, const void *buf, unsigned int buflen) { - sg_set_page(sg, virt_to_page(buf), buflen, offset_in_page(buf)); + void *addr; + /* + * VMAP_STACK (at least) puts stack into the vmalloc address space + */ + if (is_vmalloc_addr(buf)) + addr = vmalloc_to_page(buf); + else + addr = virt_to_page(buf); + sg_set_page(sg, addr, buflen, offset_in_page(buf)); }

/* Assumes the first rqst has a transform header as the first iov. @@ -3121,7 +3129,6 @@ receive_encrypted_standard(struct TCP_Server_Info *server, { int ret, length; char *buf = server->smallbuf; - char *tmpbuf; struct smb2_sync_hdr *shdr; unsigned int pdu_length = server->pdu_size; unsigned int buf_size; @@ -3151,18 +3158,15 @@ receive_encrypted_standard(struct TCP_Server_Info *server, return length;

next_is_large = server->large_buf; - one_more: +one_more: shdr = (struct smb2_sync_hdr *)buf; if (shdr->NextCommand) { - if (next_is_large) { - tmpbuf = server->bigbuf; + if (next_is_large) next_buffer = (char *)cifs_buf_get(); - } else { - tmpbuf = server->smallbuf; + else next_buffer = (char *)cifs_small_buf_get(); - } memcpy(next_buffer, - tmpbuf + le32_to_cpu(shdr->NextCommand), + buf + le32_to_cpu(shdr->NextCommand), pdu_length - le32_to_cpu(shdr->NextCommand)); }

@@ -3191,12 +3195,21 @@ receive_encrypted_standard(struct TCP_Server_Info *server, pdu_length -= le32_to_cpu(shdr->NextCommand); server->large_buf = next_is_large; if (next_is_large) - server->bigbuf = next_buffer; + server->bigbuf = buf = next_buffer; else - server->smallbuf = next_buffer; - - buf += le32_to_cpu(shdr->NextCommand); + server->smallbuf = buf = next_buffer; goto one_more; + } else if (ret != 0) { + /* + * ret != 0 here means that we didn't get to handle_mid() thus + * server->smallbuf and server->bigbuf are still valid. We need + * to free next_buffer because it is not going to be used + * anywhere. + */ + if (next_is_large) + free_rsp_buf(CIFS_LARGE_BUFFER, next_buffer); + else + free_rsp_buf(CIFS_SMALL_BUFFER, next_buffer); }

return ret; diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index 4dc887813c71..a7bc4e0494f9 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -118,6 +118,10 @@ void nfs_fscache_get_super_cookie(struct super_block *sb, const char *uniq, int struct rb_node **p, *parent; int diff;

+ nfss->fscache_key = NULL; + nfss->fscache = NULL; + if (!(nfss->options & NFS_OPTION_FSCACHE)) + return; if (!uniq) { uniq = ""; ulen = 1; @@ -230,10 +234,11 @@ void nfs_fscache_release_super_cookie(struct super_block *sb) void nfs_fscache_init_inode(struct inode *inode) { struct nfs_fscache_inode_auxdata auxdata; + struct nfs_server *nfss = NFS_SERVER(inode); struct nfs_inode *nfsi = NFS_I(inode);

nfsi->fscache = NULL; - if (!S_ISREG(inode->i_mode)) + if (!(nfss->fscache && S_ISREG(inode->i_mode))) return;

memset(&auxdata, 0, sizeof(auxdata)); diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h index 161ba2edb9d0..6363ea956858 100644 --- a/fs/nfs/fscache.h +++ b/fs/nfs/fscache.h @@ -186,7 +186,7 @@ static inline void nfs_fscache_wait_on_invalidate(struct inode *inode) */ static inline const char *nfs_server_fscache_state(struct nfs_server *server) { - if (server->fscache && (server->options & NFS_OPTION_FSCACHE)) + if (server->fscache) return "yes"; return "no "; } diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 63287d911c08..5b61520dce88 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -469,7 +469,8 @@ static inline void nfs4_schedule_session_recovery(struct nfs4_session *session,

extern struct nfs4_state_owner *nfs4_get_state_owner(struct nfs_server *, struct rpc_cred *, gfp_t); extern void nfs4_put_state_owner(struct nfs4_state_owner *); -extern void nfs4_purge_state_owners(struct nfs_server *); +extern void nfs4_purge_state_owners(struct nfs_server *, struct list_head *); +extern void nfs4_free_state_owners(struct list_head *head); extern struct nfs4_state * nfs4_get_open_state(struct inode *, struct nfs4_state_owner *); extern void nfs4_put_open_state(struct nfs4_state *); extern void nfs4_close_state(struct nfs4_state *, fmode_t); diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 8f53455c4765..86991bcfbeb1 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -754,9 +754,12 @@ int nfs41_walk_client_list(struct nfs_client *new,

static void nfs4_destroy_server(struct nfs_server *server) { + LIST_HEAD(freeme); + nfs_server_return_all_delegations(server); unset_pnfs_layoutdriver(server); - nfs4_purge_state_owners(server); + nfs4_purge_state_owners(server, &freeme); + nfs4_free_state_owners(&freeme); }

/* diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 3ba2087469ac..c36ef75f2054 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -628,24 +628,39 @@ void nfs4_put_state_owner(struct nfs4_state_owner *sp) /** * nfs4_purge_state_owners - Release all cached state owners * @server: nfs_server with cached state owners to release + * @head: resulting list of state owners * * Called at umount time. Remaining state owners will be on * the LRU with ref count of zero. + * Note that the state owners are not freed, but are added + * to the list @head, which can later be used as an argument + * to nfs4_free_state_owners. */ -void nfs4_purge_state_owners(struct nfs_server *server) +void nfs4_purge_state_owners(struct nfs_server *server, struct list_head *head) { struct nfs_client *clp = server->nfs_client; struct nfs4_state_owner *sp, *tmp; - LIST_HEAD(doomed);

spin_lock(&clp->cl_lock); list_for_each_entry_safe(sp, tmp, &server->state_owners_lru, so_lru) { - list_move(&sp->so_lru, &doomed); + list_move(&sp->so_lru, head); nfs4_remove_state_owner_locked(sp); } spin_unlock(&clp->cl_lock); +}

- list_for_each_entry_safe(sp, tmp, &doomed, so_lru) { +/** + * nfs4_purge_state_owners - Release all cached state owners + * @head: resulting list of state owners + * + * Frees a list of state owners that was generated by + * nfs4_purge_state_owners + */ +void nfs4_free_state_owners(struct list_head *head) +{ + struct nfs4_state_owner *sp, *tmp; + + list_for_each_entry_safe(sp, tmp, head, so_lru) { list_del(&sp->so_lru); nfs4_free_state_owner(sp); } @@ -1843,12 +1858,13 @@ static int nfs4_do_reclaim(struct nfs_client *clp, const struct nfs4_state_recov struct nfs4_state_owner *sp; struct nfs_server *server; struct rb_node *pos; + LIST_HEAD(freeme); int status = 0;

restart: rcu_read_lock(); list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) { - nfs4_purge_state_owners(server); + nfs4_purge_state_owners(server, &freeme); spin_lock(&clp->cl_lock); for (pos = rb_first(&server->state_owners); pos != NULL; @@ -1877,6 +1893,7 @@ static int nfs4_do_reclaim(struct nfs_client *clp, const struct nfs4_state_recov spin_unlock(&clp->cl_lock); } rcu_read_unlock(); + nfs4_free_state_owners(&freeme); return 0; }

diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 6df9b85caf20..d90efdea9fbd 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -2239,6 +2239,7 @@ nfs_compare_remount_data(struct nfs_server *nfss, data->acdirmin != nfss->acdirmin / HZ || data->acdirmax != nfss->acdirmax / HZ || data->timeo != (10U * nfss->client->cl_timeout->to_initval / HZ) || + (data->options & NFS_OPTION_FSCACHE) != (nfss->options & NFS_OPTION_FSCACHE) || data->nfs_server.port != nfss->port || data->nfs_server.addrlen != nfss->nfs_client->cl_addrlen || !rpc_cmp_addr((struct sockaddr *)&data->nfs_server.address, diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index e1ebdbe40032..9c2955f67f70 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -881,6 +881,7 @@ static int userfaultfd_release(struct inode *inode, struct file *file) /* len == 0 means wake all */ struct userfaultfd_wake_range range = { .len = 0, }; unsigned long new_flags; + bool still_valid;

WRITE_ONCE(ctx->released, true);

@@ -896,8 +897,7 @@ static int userfaultfd_release(struct inode *inode, struct file *file) * taking the mmap_sem for writing. */ down_write(&mm->mmap_sem); - if (!mmget_still_valid(mm)) - goto skip_mm; + still_valid = mmget_still_valid(mm); prev = NULL; for (vma = mm->mmap; vma; vma = vma->vm_next) { cond_resched(); @@ -908,19 +908,20 @@ static int userfaultfd_release(struct inode *inode, struct file *file) continue; } new_flags = vma->vm_flags & ~(VM_UFFD_MISSING | VM_UFFD_WP); - prev = vma_merge(mm, prev, vma->vm_start, vma->vm_end, - new_flags, vma->anon_vma, - vma->vm_file, vma->vm_pgoff, - vma_policy(vma), - NULL_VM_UFFD_CTX); - if (prev) - vma = prev; - else - prev = vma; + if (still_valid) { + prev = vma_merge(mm, prev, vma->vm_start, vma->vm_end, + new_flags, vma->anon_vma, + vma->vm_file, vma->vm_pgoff, + vma_policy(vma), + NULL_VM_UFFD_CTX); + if (prev) + vma = prev; + else + prev = vma; + } vma->vm_flags = new_flags; vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; } -skip_mm: up_write(&mm->mmap_sem); mmput(mm); wakeup: diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c index c6299f82a6e4..6410d3e00ce0 100644 --- a/fs/xfs/libxfs/xfs_attr.c +++ b/fs/xfs/libxfs/xfs_attr.c @@ -191,6 +191,121 @@ xfs_attr_calc_size( return nblks; }

+STATIC int +xfs_attr_try_sf_addname( + struct xfs_inode *dp, + struct xfs_da_args *args) +{ + + struct xfs_mount *mp = dp->i_mount; + int error, error2; + + error = xfs_attr_shortform_addname(args); + if (error == -ENOSPC) + return error; + + /* + * Commit the shortform mods, and we're done. + * NOTE: this is also the error path (EEXIST, etc). + */ + if (!error && (args->flags & ATTR_KERNOTIME) == 0) + xfs_trans_ichgtime(args->trans, dp, XFS_ICHGTIME_CHG); + + if (mp->m_flags & XFS_MOUNT_WSYNC) + xfs_trans_set_sync(args->trans); + + error2 = xfs_trans_commit(args->trans); + args->trans = NULL; + return error ? error : error2; +} + +/* + * Set the attribute specified in @args. + */ +int +xfs_attr_set_args( + struct xfs_da_args *args) +{ + struct xfs_inode *dp = args->dp; + struct xfs_buf *leaf_bp = NULL; + int error; + + /* + * If the attribute list is non-existent or a shortform list, + * upgrade it to a single-leaf-block attribute list. + */ + if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL || + (dp->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS && + dp->i_d.di_anextents == 0)) { + + /* + * Build initial attribute list (if required). + */ + if (dp->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS) + xfs_attr_shortform_create(args); + + /* + * Try to add the attr to the attribute list in the inode. + */ + error = xfs_attr_try_sf_addname(dp, args); + if (error != -ENOSPC) + return error; + + /* + * It won't fit in the shortform, transform to a leaf block. + * GROT: another possible req'mt for a double-split btree op. + */ + error = xfs_attr_shortform_to_leaf(args, &leaf_bp); + if (error) + return error; + + /* + * Prevent the leaf buffer from being unlocked so that a + * concurrent AIL push cannot grab the half-baked leaf + * buffer and run into problems with the write verifier. + * Once we're done rolling the transaction we can release + * the hold and add the attr to the leaf. + */ + xfs_trans_bhold(args->trans, leaf_bp); + error = xfs_defer_finish(&args->trans); + xfs_trans_bhold_release(args->trans, leaf_bp); + if (error) { + xfs_trans_brelse(args->trans, leaf_bp); + return error; + } + } + + if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) + error = xfs_attr_leaf_addname(args); + else + error = xfs_attr_node_addname(args); + return error; +} + +/* + * Remove the attribute specified in @args. + */ +int +xfs_attr_remove_args( + struct xfs_da_args *args) +{ + struct xfs_inode *dp = args->dp; + int error; + + if (!xfs_inode_hasattr(dp)) { + error = -ENOATTR; + } else if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) { + ASSERT(dp->i_afp->if_flags & XFS_IFINLINE); + error = xfs_attr_shortform_remove(args); + } else if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) { + error = xfs_attr_leaf_removename(args); + } else { + error = xfs_attr_node_removename(args); + } + + return error; +} + int xfs_attr_set( struct xfs_inode *dp, @@ -200,11 +315,10 @@ xfs_attr_set( int flags) { struct xfs_mount *mp = dp->i_mount; - struct xfs_buf *leaf_bp = NULL; struct xfs_da_args args; struct xfs_trans_res tres; int rsvd = (flags & ATTR_ROOT) != 0; - int error, err2, local; + int error, local;

XFS_STATS_INC(mp, xs_attr_set);

@@ -255,93 +369,17 @@ xfs_attr_set( error = xfs_trans_reserve_quota_nblks(args.trans, dp, args.total, 0, rsvd ? XFS_QMOPT_RES_REGBLKS | XFS_QMOPT_FORCE_RES : XFS_QMOPT_RES_REGBLKS); - if (error) { - xfs_iunlock(dp, XFS_ILOCK_EXCL); - xfs_trans_cancel(args.trans); - return error; - } + if (error) + goto out_trans_cancel;

xfs_trans_ijoin(args.trans, dp, 0); - - /* - * If the attribute list is non-existent or a shortform list, - * upgrade it to a single-leaf-block attribute list. - */ - if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL || - (dp->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS && - dp->i_d.di_anextents == 0)) { - - /* - * Build initial attribute list (if required). - */ - if (dp->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS) - xfs_attr_shortform_create(&args); - - /* - * Try to add the attr to the attribute list in - * the inode. - */ - error = xfs_attr_shortform_addname(&args); - if (error != -ENOSPC) { - /* - * Commit the shortform mods, and we're done. - * NOTE: this is also the error path (EEXIST, etc). - */ - ASSERT(args.trans != NULL); - - /* - * If this is a synchronous mount, make sure that - * the transaction goes to disk before returning - * to the user. - */ - if (mp->m_flags & XFS_MOUNT_WSYNC) - xfs_trans_set_sync(args.trans); - - if (!error && (flags & ATTR_KERNOTIME) == 0) { - xfs_trans_ichgtime(args.trans, dp, - XFS_ICHGTIME_CHG); - } - err2 = xfs_trans_commit(args.trans); - xfs_iunlock(dp, XFS_ILOCK_EXCL); - - return error ? error : err2; - } - - /* - * It won't fit in the shortform, transform to a leaf block. - * GROT: another possible req'mt for a double-split btree op. - */ - error = xfs_attr_shortform_to_leaf(&args, &leaf_bp); - if (error) - goto out; - /* - * Prevent the leaf buffer from being unlocked so that a - * concurrent AIL push cannot grab the half-baked leaf - * buffer and run into problems with the write verifier. - */ - xfs_trans_bhold(args.trans, leaf_bp); - error = xfs_defer_finish(&args.trans); - if (error) - goto out; - - /* - * Commit the leaf transformation. We'll need another (linked) - * transaction to add the new attribute to the leaf, which - * means that we have to hold & join the leaf buffer here too. - */ - error = xfs_trans_roll_inode(&args.trans, dp); - if (error) - goto out; - xfs_trans_bjoin(args.trans, leaf_bp); - leaf_bp = NULL; - } - - if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) - error = xfs_attr_leaf_addname(&args); - else - error = xfs_attr_node_addname(&args); + error = xfs_attr_set_args(&args); if (error) - goto out; + goto out_trans_cancel; + if (!args.trans) { + /* shortform attribute has already been committed */ + goto out_unlock; + }

/* * If this is a synchronous mount, make sure that the @@ -358,17 +396,14 @@ xfs_attr_set( */ xfs_trans_log_inode(args.trans, dp, XFS_ILOG_CORE); error = xfs_trans_commit(args.trans); +out_unlock: xfs_iunlock(dp, XFS_ILOCK_EXCL); - return error;

-out: - if (leaf_bp) - xfs_trans_brelse(args.trans, leaf_bp); +out_trans_cancel: if (args.trans) xfs_trans_cancel(args.trans); - xfs_iunlock(dp, XFS_ILOCK_EXCL); - return error; + goto out_unlock; }

/* @@ -423,17 +458,7 @@ xfs_attr_remove( */ xfs_trans_ijoin(args.trans, dp, 0);

- if (!xfs_inode_hasattr(dp)) { - error = -ENOATTR; - } else if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) { - ASSERT(dp->i_afp->if_flags & XFS_IFINLINE); - error = xfs_attr_shortform_remove(&args); - } else if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) { - error = xfs_attr_leaf_removename(&args); - } else { - error = xfs_attr_node_removename(&args); - } - + error = xfs_attr_remove_args(&args); if (error) goto out;

diff --git a/fs/xfs/libxfs/xfs_attr.h b/fs/xfs/libxfs/xfs_attr.h new file mode 100644 index 000000000000..cc04ee0aacfb --- /dev/null +++ b/fs/xfs/libxfs/xfs_attr.h @@ -0,0 +1,150 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2000,2002-2003,2005 Silicon Graphics, Inc. + * All Rights Reserved. + */ +#ifndef __XFS_ATTR_H__ +#define __XFS_ATTR_H__ + +struct xfs_inode; +struct xfs_da_args; +struct xfs_attr_list_context; + +/* + * Large attribute lists are structured around Btrees where all the data + * elements are in the leaf nodes. Attribute names are hashed into an int, + * then that int is used as the index into the Btree. Since the hashval + * of an attribute name may not be unique, we may have duplicate keys. + * The internal links in the Btree are logical block offsets into the file. + * + * Small attribute lists use a different format and are packed as tightly + * as possible so as to fit into the literal area of the inode. + */ + +/*======================================================================== + * External interfaces + *========================================================================*/ + + +#define ATTR_DONTFOLLOW 0x0001 /* -- unused, from IRIX -- */ +#define ATTR_ROOT 0x0002 /* use attrs in root (trusted) namespace */ +#define ATTR_TRUST 0x0004 /* -- unused, from IRIX -- */ +#define ATTR_SECURE 0x0008 /* use attrs in security namespace */ +#define ATTR_CREATE 0x0010 /* pure create: fail if attr already exists */ +#define ATTR_REPLACE 0x0020 /* pure set: fail if attr does not exist */ + +#define ATTR_KERNOTIME 0x1000 /* [kernel] don't update inode timestamps */ +#define ATTR_KERNOVAL 0x2000 /* [kernel] get attr size only, not value */ + +#define ATTR_INCOMPLETE 0x4000 /* [kernel] return INCOMPLETE attr keys */ + +#define XFS_ATTR_FLAGS \ + { ATTR_DONTFOLLOW, "DONTFOLLOW" }, \ + { ATTR_ROOT, "ROOT" }, \ + { ATTR_TRUST, "TRUST" }, \ + { ATTR_SECURE, "SECURE" }, \ + { ATTR_CREATE, "CREATE" }, \ + { ATTR_REPLACE, "REPLACE" }, \ + { ATTR_KERNOTIME, "KERNOTIME" }, \ + { ATTR_KERNOVAL, "KERNOVAL" }, \ + { ATTR_INCOMPLETE, "INCOMPLETE" } + +/* + * The maximum size (into the kernel or returned from the kernel) of an + * attribute value or the buffer used for an attr_list() call. Larger + * sizes will result in an ERANGE return code. + */ +#define ATTR_MAX_VALUELEN (64*1024) /* max length of a value */ + +/* + * Define how lists of attribute names are returned to the user from + * the attr_list() call. A large, 32bit aligned, buffer is passed in + * along with its size. We put an array of offsets at the top that each + * reference an attrlist_ent_t and pack the attrlist_ent_t's at the bottom. + */ +typedef struct attrlist { + __s32 al_count; /* number of entries in attrlist */ + __s32 al_more; /* T/F: more attrs (do call again) */ + __s32 al_offset[1]; /* byte offsets of attrs [var-sized] */ +} attrlist_t; + +/* + * Show the interesting info about one attribute. This is what the + * al_offset[i] entry points to. + */ +typedef struct attrlist_ent { /* data from attr_list() */ + __u32 a_valuelen; /* number bytes in value of attr */ + char a_name[1]; /* attr name (NULL terminated) */ +} attrlist_ent_t; + +/* + * Given a pointer to the (char*) buffer containing the attr_list() result, + * and an index, return a pointer to the indicated attribute in the buffer. + */ +#define ATTR_ENTRY(buffer, index) \ + ((attrlist_ent_t *) \ + &((char *)buffer)[ ((attrlist_t *)(buffer))->al_offset[index] ]) + +/* + * Kernel-internal version of the attrlist cursor. + */ +typedef struct attrlist_cursor_kern { + __u32 hashval; /* hash value of next entry to add */ + __u32 blkno; /* block containing entry (suggestion) */ + __u32 offset; /* offset in list of equal-hashvals */ + __u16 pad1; /* padding to match user-level */ + __u8 pad2; /* padding to match user-level */ + __u8 initted; /* T/F: cursor has been initialized */ +} attrlist_cursor_kern_t; + + +/*======================================================================== + * Structure used to pass context around among the routines. + *========================================================================*/ + + +/* void; state communicated via *context */ +typedef void (*put_listent_func_t)(struct xfs_attr_list_context *, int, + unsigned char *, int, int); + +typedef struct xfs_attr_list_context { + struct xfs_trans *tp; + struct xfs_inode *dp; /* inode */ + struct attrlist_cursor_kern *cursor; /* position in list */ + char *alist; /* output buffer */ + int seen_enough; /* T/F: seen enough of list? */ + ssize_t count; /* num used entries */ + int dupcnt; /* count dup hashvals seen */ + int bufsize; /* total buffer size */ + int firstu; /* first used byte in buffer */ + int flags; /* from VOP call */ + int resynch; /* T/F: resynch with cursor */ + put_listent_func_t put_listent; /* list output fmt function */ + int index; /* index into output buffer */ +} xfs_attr_list_context_t; + + +/*======================================================================== + * Function prototypes for the kernel. + *========================================================================*/ + +/* + * Overall external interface routines. + */ +int xfs_attr_inactive(struct xfs_inode *dp); +int xfs_attr_list_int_ilocked(struct xfs_attr_list_context *); +int xfs_attr_list_int(struct xfs_attr_list_context *); +int xfs_inode_hasattr(struct xfs_inode *ip); +int xfs_attr_get_ilocked(struct xfs_inode *ip, struct xfs_da_args *args); +int xfs_attr_get(struct xfs_inode *ip, const unsigned char *name, + unsigned char *value, int *valuelenp, int flags); +int xfs_attr_set(struct xfs_inode *dp, const unsigned char *name, + unsigned char *value, int valuelen, int flags); +int xfs_attr_set_args(struct xfs_da_args *args); +int xfs_attr_remove(struct xfs_inode *dp, const unsigned char *name, int flags); +int xfs_attr_remove_args(struct xfs_da_args *args); +int xfs_attr_list(struct xfs_inode *dp, char *buffer, int bufsize, + int flags, struct attrlist_cursor_kern *cursor); + + +#endif /* __XFS_ATTR_H__ */ diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 3a496ffe6551..06a7da8dbda5 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -1019,6 +1019,34 @@ xfs_bmap_add_attrfork_local( return -EFSCORRUPTED; }

+/* Set an inode attr fork off based on the format */ +int +xfs_bmap_set_attrforkoff( + struct xfs_inode *ip, + int size, + int *version) +{ + switch (ip->i_d.di_format) { + case XFS_DINODE_FMT_DEV: + ip->i_d.di_forkoff = roundup(sizeof(xfs_dev_t), 8) >> 3; + break; + case XFS_DINODE_FMT_LOCAL: + case XFS_DINODE_FMT_EXTENTS: + case XFS_DINODE_FMT_BTREE: + ip->i_d.di_forkoff = xfs_attr_shortform_bytesfit(ip, size); + if (!ip->i_d.di_forkoff) + ip->i_d.di_forkoff = xfs_default_attroffset(ip) >> 3; + else if ((ip->i_mount->m_flags & XFS_MOUNT_ATTR2) && version) + *version = 2; + break; + default: + ASSERT(0); + return -EINVAL; + } + + return 0; +} + /* * Convert inode from non-attributed to attributed. * Must not be in a transaction, ip must not be locked. @@ -1070,26 +1098,9 @@ xfs_bmap_add_attrfork(

xfs_trans_ijoin(tp, ip, 0); xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); - - switch (ip->i_d.di_format) { - case XFS_DINODE_FMT_DEV: - ip->i_d.di_forkoff = roundup(sizeof(xfs_dev_t), 8) >> 3; - break; - case XFS_DINODE_FMT_LOCAL: - case XFS_DINODE_FMT_EXTENTS: - case XFS_DINODE_FMT_BTREE: - ip->i_d.di_forkoff = xfs_attr_shortform_bytesfit(ip, size); - if (!ip->i_d.di_forkoff) - ip->i_d.di_forkoff = xfs_default_attroffset(ip) >> 3; - else if (mp->m_flags & XFS_MOUNT_ATTR2) - version = 2; - break; - default: - ASSERT(0); - error = -EINVAL; + error = xfs_bmap_set_attrforkoff(ip, size, &version); + if (error) goto trans_cancel; - } - ASSERT(ip->i_afp == NULL); ip->i_afp = kmem_zone_zalloc(xfs_ifork_zone, KM_SLEEP); ip->i_afp->if_flags = XFS_IFEXTENTS; @@ -1178,7 +1189,10 @@ xfs_iread_extents( * Root level must use BMAP_BROOT_PTR_ADDR macro to get ptr out. */ level = be16_to_cpu(block->bb_level); - ASSERT(level > 0); + if (unlikely(level == 0)) { + XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp); + return -EFSCORRUPTED; + } pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, 1, ifp->if_broot_bytes); bno = be64_to_cpu(*pp);

diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h index b6e9b639e731..488dc8860fd7 100644 --- a/fs/xfs/libxfs/xfs_bmap.h +++ b/fs/xfs/libxfs/xfs_bmap.h @@ -183,6 +183,7 @@ void xfs_trim_extent(struct xfs_bmbt_irec *irec, xfs_fileoff_t bno, xfs_filblks_t len); void xfs_trim_extent_eof(struct xfs_bmbt_irec *, struct xfs_inode *); int xfs_bmap_add_attrfork(struct xfs_inode *ip, int size, int rsvd); +int xfs_bmap_set_attrforkoff(struct xfs_inode *ip, int size, int *version); void xfs_bmap_local_to_extents_empty(struct xfs_inode *ip, int whichfork); void __xfs_bmap_add_free(struct xfs_trans *tp, xfs_fsblock_t bno, xfs_filblks_t len, struct xfs_owner_info *oinfo, diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c index e792b167150a..c52beee31836 100644 --- a/fs/xfs/libxfs/xfs_defer.c +++ b/fs/xfs/libxfs/xfs_defer.c @@ -266,13 +266,15 @@ xfs_defer_trans_roll(

trace_xfs_defer_trans_roll(tp, _RET_IP_);

- /* Roll the transaction. */ + /* + * Roll the transaction. Rolling always given a new transaction (even + * if committing the old one fails!) to hand back to the caller, so we + * join the held resources to the new transaction so that we always + * return with the held resources joined to @tpp, no matter what + * happened. + */ error = xfs_trans_roll(tpp); tp = *tpp; - if (error) { - trace_xfs_defer_trans_roll_error(tp, error); - return error; - }

/* Rejoin the joined inodes. */ for (i = 0; i < ipcount; i++) @@ -284,6 +286,8 @@ xfs_defer_trans_roll( xfs_trans_bhold(tp, bplist[i]); }

+ if (error) + trace_xfs_defer_trans_roll_error(tp, error); return error; }

diff --git a/fs/xfs/xfs_attr.h b/fs/xfs/xfs_attr.h deleted file mode 100644 index 033ff8c478e2..000000000000 --- a/fs/xfs/xfs_attr.h +++ /dev/null @@ -1,148 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (c) 2000,2002-2003,2005 Silicon Graphics, Inc. - * All Rights Reserved. - */ -#ifndef __XFS_ATTR_H__ -#define __XFS_ATTR_H__ - -struct xfs_inode; -struct xfs_da_args; -struct xfs_attr_list_context; - -/* - * Large attribute lists are structured around Btrees where all the data - * elements are in the leaf nodes. Attribute names are hashed into an int, - * then that int is used as the index into the Btree. Since the hashval - * of an attribute name may not be unique, we may have duplicate keys. - * The internal links in the Btree are logical block offsets into the file. - * - * Small attribute lists use a different format and are packed as tightly - * as possible so as to fit into the literal area of the inode. - */ - -/*======================================================================== - * External interfaces - *========================================================================*/ - - -#define ATTR_DONTFOLLOW 0x0001 /* -- unused, from IRIX -- */ -#define ATTR_ROOT 0x0002 /* use attrs in root (trusted) namespace */ -#define ATTR_TRUST 0x0004 /* -- unused, from IRIX -- */ -#define ATTR_SECURE 0x0008 /* use attrs in security namespace */ -#define ATTR_CREATE 0x0010 /* pure create: fail if attr already exists */ -#define ATTR_REPLACE 0x0020 /* pure set: fail if attr does not exist */ - -#define ATTR_KERNOTIME 0x1000 /* [kernel] don't update inode timestamps */ -#define ATTR_KERNOVAL 0x2000 /* [kernel] get attr size only, not value */ - -#define ATTR_INCOMPLETE 0x4000 /* [kernel] return INCOMPLETE attr keys */ - -#define XFS_ATTR_FLAGS \ - { ATTR_DONTFOLLOW, "DONTFOLLOW" }, \ - { ATTR_ROOT, "ROOT" }, \ - { ATTR_TRUST, "TRUST" }, \ - { ATTR_SECURE, "SECURE" }, \ - { ATTR_CREATE, "CREATE" }, \ - { ATTR_REPLACE, "REPLACE" }, \ - { ATTR_KERNOTIME, "KERNOTIME" }, \ - { ATTR_KERNOVAL, "KERNOVAL" }, \ - { ATTR_INCOMPLETE, "INCOMPLETE" } - -/* - * The maximum size (into the kernel or returned from the kernel) of an - * attribute value or the buffer used for an attr_list() call. Larger - * sizes will result in an ERANGE return code. - */ -#define ATTR_MAX_VALUELEN (64*1024) /* max length of a value */ - -/* - * Define how lists of attribute names are returned to the user from - * the attr_list() call. A large, 32bit aligned, buffer is passed in - * along with its size. We put an array of offsets at the top that each - * reference an attrlist_ent_t and pack the attrlist_ent_t's at the bottom. - */ -typedef struct attrlist { - __s32 al_count; /* number of entries in attrlist */ - __s32 al_more; /* T/F: more attrs (do call again) */ - __s32 al_offset[1]; /* byte offsets of attrs [var-sized] */ -} attrlist_t; - -/* - * Show the interesting info about one attribute. This is what the - * al_offset[i] entry points to. - */ -typedef struct attrlist_ent { /* data from attr_list() */ - __u32 a_valuelen; /* number bytes in value of attr */ - char a_name[1]; /* attr name (NULL terminated) */ -} attrlist_ent_t; - -/* - * Given a pointer to the (char*) buffer containing the attr_list() result, - * and an index, return a pointer to the indicated attribute in the buffer. - */ -#define ATTR_ENTRY(buffer, index) \ - ((attrlist_ent_t *) \ - &((char *)buffer)[ ((attrlist_t *)(buffer))->al_offset[index] ]) - -/* - * Kernel-internal version of the attrlist cursor. - */ -typedef struct attrlist_cursor_kern { - __u32 hashval; /* hash value of next entry to add */ - __u32 blkno; /* block containing entry (suggestion) */ - __u32 offset; /* offset in list of equal-hashvals */ - __u16 pad1; /* padding to match user-level */ - __u8 pad2; /* padding to match user-level */ - __u8 initted; /* T/F: cursor has been initialized */ -} attrlist_cursor_kern_t; - - -/*======================================================================== - * Structure used to pass context around among the routines. - *========================================================================*/ - - -/* void; state communicated via *context */ -typedef void (*put_listent_func_t)(struct xfs_attr_list_context *, int, - unsigned char *, int, int); - -typedef struct xfs_attr_list_context { - struct xfs_trans *tp; - struct xfs_inode *dp; /* inode */ - struct attrlist_cursor_kern *cursor; /* position in list */ - char *alist; /* output buffer */ - int seen_enough; /* T/F: seen enough of list? */ - ssize_t count; /* num used entries */ - int dupcnt; /* count dup hashvals seen */ - int bufsize; /* total buffer size */ - int firstu; /* first used byte in buffer */ - int flags; /* from VOP call */ - int resynch; /* T/F: resynch with cursor */ - put_listent_func_t put_listent; /* list output fmt function */ - int index; /* index into output buffer */ -} xfs_attr_list_context_t; - - -/*======================================================================== - * Function prototypes for the kernel. - *========================================================================*/ - -/* - * Overall external interface routines. - */ -int xfs_attr_inactive(struct xfs_inode *dp); -int xfs_attr_list_int_ilocked(struct xfs_attr_list_context *); -int xfs_attr_list_int(struct xfs_attr_list_context *); -int xfs_inode_hasattr(struct xfs_inode *ip); -int xfs_attr_get_ilocked(struct xfs_inode *ip, struct xfs_da_args *args); -int xfs_attr_get(struct xfs_inode *ip, const unsigned char *name, - unsigned char *value, int *valuelenp, int flags); -int xfs_attr_set(struct xfs_inode *dp, const unsigned char *name, - unsigned char *value, int valuelen, int flags); -int xfs_attr_remove(struct xfs_inode *dp, const unsigned char *name, int flags); -int xfs_attr_list(struct xfs_inode *dp, char *buffer, int bufsize, - int flags, struct attrlist_cursor_kern *cursor); - - -#endif /* __XFS_ATTR_H__ */ diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index 87e6dd5326d5..a1af984e4913 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -277,7 +277,8 @@ xfs_dquot_set_prealloc_limits(struct xfs_dquot *dqp)

/* * Ensure that the given in-core dquot has a buffer on disk backing it, and - * return the buffer. This is called when the bmapi finds a hole. + * return the buffer locked and held. This is called when the bmapi finds a + * hole. */ STATIC int xfs_dquot_disk_alloc( @@ -355,13 +356,14 @@ xfs_dquot_disk_alloc( * If everything succeeds, the caller of this function is returned a * buffer that is locked and held to the transaction. The caller * is responsible for unlocking any buffer passed back, either - * manually or by committing the transaction. + * manually or by committing the transaction. On error, the buffer is + * released and not passed back. */ xfs_trans_bhold(tp, bp); error = xfs_defer_finish(tpp); - tp = *tpp; if (error) { - xfs_buf_relse(bp); + xfs_trans_bhold_release(*tpp, bp); + xfs_trans_brelse(*tpp, bp); return error; } *bpp = bp; @@ -521,7 +523,6 @@ xfs_qm_dqread_alloc( struct xfs_buf **bpp) { struct xfs_trans *tp; - struct xfs_buf *bp; int error;

error = xfs_trans_alloc(mp, &M_RES(mp)->tr_qm_dqalloc, @@ -529,7 +530,7 @@ xfs_qm_dqread_alloc( if (error) goto err;

- error = xfs_dquot_disk_alloc(&tp, dqp, &bp); + error = xfs_dquot_disk_alloc(&tp, dqp, bpp); if (error) goto err_cancel;

@@ -539,10 +540,10 @@ xfs_qm_dqread_alloc( * Buffer was held to the transaction, so we have to unlock it * manually here because we're not passing it back. */ - xfs_buf_relse(bp); + xfs_buf_relse(*bpp); + *bpp = NULL; goto err; } - *bpp = bp; return 0;

err_cancel: diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 74047bd0c1ae..e427ad097e2e 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -803,6 +803,7 @@ xfs_setattr_nonsize(

out_cancel: xfs_trans_cancel(tp); + xfs_iunlock(ip, XFS_ILOCK_EXCL); out_dqrele: xfs_qm_dqrele(udqp); xfs_qm_dqrele(gdqp); diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 147546e0c11b..815dcfa64743 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -500,10 +500,10 @@ rxrpc_tx_points; #define E_(a, b) { a, b }

TRACE_EVENT(rxrpc_local, - TP_PROTO(struct rxrpc_local *local, enum rxrpc_local_trace op, + TP_PROTO(unsigned int local_debug_id, enum rxrpc_local_trace op, int usage, const void *where),

- TP_ARGS(local, op, usage, where), + TP_ARGS(local_debug_id, op, usage, where),

TP_STRUCT__entry( __field(unsigned int, local ) @@ -513,7 +513,7 @@ TRACE_EVENT(rxrpc_local, ),

TP_fast_assign( - __entry->local = local->debug_id; + __entry->local = local_debug_id; __entry->op = op; __entry->usage = usage; __entry->where = where; diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 8e009cee6517..26814a14013c 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -294,6 +294,18 @@ static void irq_sysfs_add(int irq, struct irq_desc *desc) } }

+static void irq_sysfs_del(struct irq_desc *desc) +{ + /* + * If irq_sysfs_init() has not yet been invoked (early boot), then + * irq_kobj_base is NULL and the descriptor was never added. + * kobject_del() complains about a object with no parent, so make + * it conditional. + */ + if (irq_kobj_base) + kobject_del(&desc->kobj); +} + static int __init irq_sysfs_init(void) { struct irq_desc *desc; @@ -324,6 +336,7 @@ static struct kobj_type irq_kobj_type = { };

static void irq_sysfs_add(int irq, struct irq_desc *desc) {} +static void irq_sysfs_del(struct irq_desc *desc) {}

#endif /* CONFIG_SYSFS */

@@ -437,7 +450,7 @@ static void free_desc(unsigned int irq) * The sysfs entry must be serialized against a concurrent * irq_sysfs_init() as well. */ - kobject_del(&desc->kobj); + irq_sysfs_del(desc); delete_irq_desc(irq);

/* diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 6fad1864ba03..09ce8528bbdd 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -33,6 +33,7 @@ #include <linux/page_idle.h> #include <linux/shmem_fs.h> #include <linux/oom.h> +#include <linux/page_owner.h>

#include <asm/tlb.h> #include <asm/pgalloc.h> @@ -2477,6 +2478,9 @@ static void __split_huge_page(struct page *page, struct list_head *list, }

ClearPageCompound(head); + + split_page_owner(head, HPAGE_PMD_ORDER); + /* See comment in __split_huge_page_tail() */ if (PageAnon(head)) { /* Additional pin to radix tree of swap cache */ diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 9da65552e7ca..c2c4f739da8f 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -53,6 +53,7 @@ #include <linux/zpool.h> #include <linux/mount.h> #include <linux/migrate.h> +#include <linux/wait.h> #include <linux/pagemap.h> #include <linux/fs.h>

@@ -267,6 +268,10 @@ struct zs_pool { #ifdef CONFIG_COMPACTION struct inode *inode; struct work_struct free_work; + /* A wait queue for when migration races with async_free_zspage() */ + struct wait_queue_head migration_wait; + atomic_long_t isolated_pages; + bool destroying; #endif };

@@ -1882,6 +1887,31 @@ static void dec_zspage_isolation(struct zspage *zspage) zspage->isolated--; }

+static void putback_zspage_deferred(struct zs_pool *pool, + struct size_class *class, + struct zspage *zspage) +{ + enum fullness_group fg; + + fg = putback_zspage(class, zspage); + if (fg == ZS_EMPTY) + schedule_work(&pool->free_work); + +} + +static inline void zs_pool_dec_isolated(struct zs_pool *pool) +{ + VM_BUG_ON(atomic_long_read(&pool->isolated_pages) <= 0); + atomic_long_dec(&pool->isolated_pages); + /* + * There's no possibility of racing, since wait_for_isolated_drain() + * checks the isolated count under &class->lock after enqueuing + * on migration_wait. + */ + if (atomic_long_read(&pool->isolated_pages) == 0 && pool->destroying) + wake_up_all(&pool->migration_wait); +} + static void replace_sub_page(struct size_class *class, struct zspage *zspage, struct page *newpage, struct page *oldpage) { @@ -1951,6 +1981,7 @@ static bool zs_page_isolate(struct page *page, isolate_mode_t mode) */ if (!list_empty(&zspage->list) && !is_zspage_isolated(zspage)) { get_zspage_mapping(zspage, &class_idx, &fullness); + atomic_long_inc(&pool->isolated_pages); remove_zspage(class, zspage, fullness); }

@@ -2050,8 +2081,16 @@ static int zs_page_migrate(struct address_space *mapping, struct page *newpage, * Page migration is done so let's putback isolated zspage to * the list if @page is final isolated subpage in the zspage. */ - if (!is_zspage_isolated(zspage)) - putback_zspage(class, zspage); + if (!is_zspage_isolated(zspage)) { + /* + * We cannot race with zs_destroy_pool() here because we wait + * for isolation to hit zero before we start destroying. + * Also, we ensure that everyone can see pool->destroying before + * we start waiting. + */ + putback_zspage_deferred(pool, class, zspage); + zs_pool_dec_isolated(pool); + }

reset_page(page); put_page(page); @@ -2097,13 +2136,12 @@ static void zs_page_putback(struct page *page) spin_lock(&class->lock); dec_zspage_isolation(zspage); if (!is_zspage_isolated(zspage)) { - fg = putback_zspage(class, zspage); /* * Due to page_lock, we cannot free zspage immediately * so let's defer. */ - if (fg == ZS_EMPTY) - schedule_work(&pool->free_work); + putback_zspage_deferred(pool, class, zspage); + zs_pool_dec_isolated(pool); } spin_unlock(&class->lock); } @@ -2127,8 +2165,36 @@ static int zs_register_migration(struct zs_pool *pool) return 0; }

+static bool pool_isolated_are_drained(struct zs_pool *pool) +{ + return atomic_long_read(&pool->isolated_pages) == 0; +} + +/* Function for resolving migration */ +static void wait_for_isolated_drain(struct zs_pool *pool) +{ + + /* + * We're in the process of destroying the pool, so there are no + * active allocations. zs_page_isolate() fails for completely free + * zspages, so we need only wait for the zs_pool's isolated + * count to hit zero. + */ + wait_event(pool->migration_wait, + pool_isolated_are_drained(pool)); +} + static void zs_unregister_migration(struct zs_pool *pool) { + pool->destroying = true; + /* + * We need a memory barrier here to ensure global visibility of + * pool->destroying. Thus pool->isolated pages will either be 0 in which + * case we don't care, or it will be > 0 and pool->destroying will + * ensure that we wake up once isolation hits 0. + */ + smp_mb(); + wait_for_isolated_drain(pool); /* This can block */ flush_work(&pool->free_work); iput(pool->inode); } @@ -2366,6 +2432,8 @@ struct zs_pool *zs_create_pool(const char *name) if (!pool->name) goto err;

+ init_waitqueue_head(&pool->migration_wait); + if (create_cache(pool)) goto err;

diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 995b3842ba7c..62ffc989a44a 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -2274,8 +2274,10 @@ static int compat_do_replace(struct net *net, void __user *user, state.buf_kern_len = size64;

ret = compat_copy_entries(entries_tmp, tmp.entries_size, &state); - if (WARN_ON(ret < 0)) + if (WARN_ON(ret < 0)) { + vfree(entries_tmp); goto out_unlock; + }

vfree(entries_tmp); tmp.entries_size = size64; diff --git a/net/can/gw.c b/net/can/gw.c index 53859346dc9a..bd2161470e45 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -1046,32 +1046,50 @@ static __init int cgw_module_init(void) pr_info("can: netlink gateway (rev " CAN_GW_VERSION ") max_hops=%d\n", max_hops);

- register_pernet_subsys(&cangw_pernet_ops); + ret = register_pernet_subsys(&cangw_pernet_ops); + if (ret) + return ret; + + ret = -ENOMEM; cgw_cache = kmem_cache_create("can_gw", sizeof(struct cgw_job), 0, 0, NULL); - if (!cgw_cache) - return -ENOMEM; + goto out_cache_create;

/* set notifier */ notifier.notifier_call = cgw_notifier; - register_netdevice_notifier(&notifier); + ret = register_netdevice_notifier(&notifier); + if (ret) + goto out_register_notifier;

ret = rtnl_register_module(THIS_MODULE, PF_CAN, RTM_GETROUTE, NULL, cgw_dump_jobs, 0); - if (ret) { - unregister_netdevice_notifier(&notifier); - kmem_cache_destroy(cgw_cache); - return -ENOBUFS; - } - - /* Only the first call to rtnl_register_module can fail */ - rtnl_register_module(THIS_MODULE, PF_CAN, RTM_NEWROUTE, - cgw_create_job, NULL, 0); - rtnl_register_module(THIS_MODULE, PF_CAN, RTM_DELROUTE, - cgw_remove_job, NULL, 0); + if (ret) + goto out_rtnl_register1; + + ret = rtnl_register_module(THIS_MODULE, PF_CAN, RTM_NEWROUTE, + cgw_create_job, NULL, 0); + if (ret) + goto out_rtnl_register2; + ret = rtnl_register_module(THIS_MODULE, PF_CAN, RTM_DELROUTE, + cgw_remove_job, NULL, 0); + if (ret) + goto out_rtnl_register3;

return 0; + +out_rtnl_register3: + rtnl_unregister(PF_CAN, RTM_NEWROUTE); +out_rtnl_register2: + rtnl_unregister(PF_CAN, RTM_GETROUTE); +out_rtnl_register1: + unregister_netdevice_notifier(&notifier); +out_register_notifier: + kmem_cache_destroy(cgw_cache); +out_cache_create: + unregister_pernet_subsys(&cangw_pernet_ops); + + return ret; }

static __exit void cgw_module_exit(void) diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 60934bd8796c..76c41a84550e 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -1423,7 +1423,7 @@ static enum calc_target_result calc_target(struct ceph_osd_client *osdc, struct ceph_osds up, acting; bool force_resend = false; bool unpaused = false; - bool legacy_change; + bool legacy_change = false; bool split = false; bool sort_bitwise = ceph_osdmap_flag(osdc, CEPH_OSDMAP_SORTBITWISE); bool recovery_deletes = ceph_osdmap_flag(osdc, @@ -1511,15 +1511,14 @@ static enum calc_target_result calc_target(struct ceph_osd_client *osdc, t->osd = acting.primary; }

- if (unpaused || legacy_change || force_resend || - (split && con && CEPH_HAVE_FEATURE(con->peer_features, - RESEND_ON_SPLIT))) + if (unpaused || legacy_change || force_resend || split) ct_res = CALC_TARGET_NEED_RESEND; else ct_res = CALC_TARGET_NO_ACTION;

out: - dout("%s t %p -> ct_res %d osd %d\n", __func__, t, ct_res, t->osd); + dout("%s t %p -> %d%d%d%d ct_res %d osd%d\n", __func__, t, unpaused, + legacy_change, force_resend, split, ct_res, t->osd); return ct_res; }

diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c index 13ade5782847..4f01321e793c 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c +++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c @@ -230,7 +230,7 @@ bitmap_ipmac_kadt(struct ip_set *set, const struct sk_buff *skb,

e.id = ip_to_id(map, ip);

- if (opt->flags & IPSET_DIM_ONE_SRC) + if (opt->flags & IPSET_DIM_TWO_SRC) ether_addr_copy(e.ether, eth_hdr(skb)->h_source); else ether_addr_copy(e.ether, eth_hdr(skb)->h_dest); diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 1577f2f76060..e2538c578671 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1157,7 +1157,7 @@ static int ip_set_rename(struct net *net, struct sock *ctnl, return -ENOENT;

write_lock_bh(&ip_set_ref_lock); - if (set->ref != 0) { + if (set->ref != 0 || set->ref_netlink != 0) { ret = -IPSET_ERR_REFERENCED; goto out; } diff --git a/net/netfilter/ipset/ip_set_hash_ipmac.c b/net/netfilter/ipset/ip_set_hash_ipmac.c index fd87de3ed55b..16ec822e4044 100644 --- a/net/netfilter/ipset/ip_set_hash_ipmac.c +++ b/net/netfilter/ipset/ip_set_hash_ipmac.c @@ -95,15 +95,11 @@ hash_ipmac4_kadt(struct ip_set *set, const struct sk_buff *skb, struct hash_ipmac4_elem e = { .ip = 0, { .foo[0] = 0, .foo[1] = 0 } }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);

- /* MAC can be src only */ - if (!(opt->flags & IPSET_DIM_TWO_SRC)) - return 0; - if (skb_mac_header(skb) < skb->head || (skb_mac_header(skb) + ETH_HLEN) > skb->data) return -EINVAL;

- if (opt->flags & IPSET_DIM_ONE_SRC) + if (opt->flags & IPSET_DIM_TWO_SRC) ether_addr_copy(e.ether, eth_hdr(skb)->h_source); else ether_addr_copy(e.ether, eth_hdr(skb)->h_dest); diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index d76e5e58905d..7319d3ca30e9 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -195,7 +195,7 @@ static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len)

service_in_use: write_unlock(&local->services_lock); - rxrpc_put_local(local); + rxrpc_unuse_local(local); ret = -EADDRINUSE; error_unlock: release_sock(&rx->sk); @@ -908,7 +908,7 @@ static int rxrpc_release_sock(struct sock *sk) rxrpc_queue_work(&rxnet->service_conn_reaper); rxrpc_queue_work(&rxnet->client_conn_reaper);

- rxrpc_put_local(rx->local); + rxrpc_unuse_local(rx->local); rx->local = NULL; key_put(rx->key); rx->key = NULL; diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 03e0fc8c183f..dfd9eab77cc8 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -258,7 +258,8 @@ struct rxrpc_security { */ struct rxrpc_local { struct rcu_head rcu; - atomic_t usage; + atomic_t active_users; /* Number of users of the local endpoint */ + atomic_t usage; /* Number of references to the structure */ struct rxrpc_net *rxnet; /* The network ns in which this resides */ struct list_head link; struct socket *socket; /* my UDP socket */ @@ -998,6 +999,8 @@ struct rxrpc_local *rxrpc_lookup_local(struct net *, const struct sockaddr_rxrpc struct rxrpc_local *rxrpc_get_local(struct rxrpc_local *); struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *); void rxrpc_put_local(struct rxrpc_local *); +struct rxrpc_local *rxrpc_use_local(struct rxrpc_local *); +void rxrpc_unuse_local(struct rxrpc_local *); void rxrpc_queue_local(struct rxrpc_local *); void rxrpc_destroy_all_locals(struct rxrpc_net *);

@@ -1057,6 +1060,7 @@ void rxrpc_destroy_all_peers(struct rxrpc_net *); struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *); struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *); void rxrpc_put_peer(struct rxrpc_peer *); +void rxrpc_put_peer_locked(struct rxrpc_peer *);

/* * proc.c diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index d591f54cb91f..7965600ee5de 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -1106,8 +1106,12 @@ static void rxrpc_post_packet_to_local(struct rxrpc_local *local, { _enter("%p,%p", local, skb);

- skb_queue_tail(&local->event_queue, skb); - rxrpc_queue_local(local); + if (rxrpc_get_local_maybe(local)) { + skb_queue_tail(&local->event_queue, skb); + rxrpc_queue_local(local); + } else { + rxrpc_free_skb(skb, rxrpc_skb_rx_freed); + } }

/* @@ -1117,8 +1121,12 @@ static void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb) { CHECK_SLAB_OKAY(&local->usage);

- skb_queue_tail(&local->reject_queue, skb); - rxrpc_queue_local(local); + if (rxrpc_get_local_maybe(local)) { + skb_queue_tail(&local->reject_queue, skb); + rxrpc_queue_local(local); + } else { + rxrpc_free_skb(skb, rxrpc_skb_rx_freed); + } }

/* diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index 10317dbdab5f..c752ad487067 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -83,6 +83,7 @@ static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet, local = kzalloc(sizeof(struct rxrpc_local), GFP_KERNEL); if (local) { atomic_set(&local->usage, 1); + atomic_set(&local->active_users, 1); local->rxnet = rxnet; INIT_LIST_HEAD(&local->link); INIT_WORK(&local->processor, rxrpc_local_processor); @@ -96,7 +97,7 @@ static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet, local->debug_id = atomic_inc_return(&rxrpc_debug_id); memcpy(&local->srx, srx, sizeof(*srx)); local->srx.srx_service = 0; - trace_rxrpc_local(local, rxrpc_local_new, 1, NULL); + trace_rxrpc_local(local->debug_id, rxrpc_local_new, 1, NULL); }

_leave(" = %p", local); @@ -270,11 +271,8 @@ struct rxrpc_local *rxrpc_lookup_local(struct net *net, * bind the transport socket may still fail if we're attempting * to use a local address that the dying object is still using. */ - if (!rxrpc_get_local_maybe(local)) { - cursor = cursor->next; - list_del_init(&local->link); + if (!rxrpc_use_local(local)) break; - }

age = "old"; goto found; @@ -288,7 +286,10 @@ struct rxrpc_local *rxrpc_lookup_local(struct net *net, if (ret < 0) goto sock_error;

- list_add_tail(&local->link, cursor); + if (cursor != &rxnet->local_endpoints) + list_replace_init(cursor, &local->link); + else + list_add_tail(&local->link, cursor); age = "new";

found: @@ -324,7 +325,7 @@ struct rxrpc_local *rxrpc_get_local(struct rxrpc_local *local) int n;

n = atomic_inc_return(&local->usage); - trace_rxrpc_local(local, rxrpc_local_got, n, here); + trace_rxrpc_local(local->debug_id, rxrpc_local_got, n, here); return local; }

@@ -338,7 +339,8 @@ struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *local) if (local) { int n = atomic_fetch_add_unless(&local->usage, 1, 0); if (n > 0) - trace_rxrpc_local(local, rxrpc_local_got, n + 1, here); + trace_rxrpc_local(local->debug_id, rxrpc_local_got, + n + 1, here); else local = NULL; } @@ -346,24 +348,18 @@ struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *local) }

/* - * Queue a local endpoint. + * Queue a local endpoint and pass the caller's reference to the work item. */ void rxrpc_queue_local(struct rxrpc_local *local) { const void *here = __builtin_return_address(0); + unsigned int debug_id = local->debug_id; + int n = atomic_read(&local->usage);

if (rxrpc_queue_work(&local->processor)) - trace_rxrpc_local(local, rxrpc_local_queued, - atomic_read(&local->usage), here); -} - -/* - * A local endpoint reached its end of life. - */ -static void __rxrpc_put_local(struct rxrpc_local *local) -{ - _enter("%d", local->debug_id); - rxrpc_queue_work(&local->processor); + trace_rxrpc_local(debug_id, rxrpc_local_queued, n, here); + else + rxrpc_put_local(local); }

/* @@ -376,10 +372,47 @@ void rxrpc_put_local(struct rxrpc_local *local)

if (local) { n = atomic_dec_return(&local->usage); - trace_rxrpc_local(local, rxrpc_local_put, n, here); + trace_rxrpc_local(local->debug_id, rxrpc_local_put, n, here);

if (n == 0) - __rxrpc_put_local(local); + call_rcu(&local->rcu, rxrpc_local_rcu); + } +} + +/* + * Start using a local endpoint. + */ +struct rxrpc_local *rxrpc_use_local(struct rxrpc_local *local) +{ + unsigned int au; + + local = rxrpc_get_local_maybe(local); + if (!local) + return NULL; + + au = atomic_fetch_add_unless(&local->active_users, 1, 0); + if (au == 0) { + rxrpc_put_local(local); + return NULL; + } + + return local; +} + +/* + * Cease using a local endpoint. Once the number of active users reaches 0, we + * start the closure of the transport in the work processor. + */ +void rxrpc_unuse_local(struct rxrpc_local *local) +{ + unsigned int au; + + if (local) { + au = atomic_dec_return(&local->active_users); + if (au == 0) + rxrpc_queue_local(local); + else + rxrpc_put_local(local); } }

@@ -397,16 +430,6 @@ static void rxrpc_local_destroyer(struct rxrpc_local *local)

_enter("%d", local->debug_id);

- /* We can get a race between an incoming call packet queueing the - * processor again and the work processor starting the destruction - * process which will shut down the UDP socket. - */ - if (local->dead) { - _leave(" [already dead]"); - return; - } - local->dead = true; - mutex_lock(&rxnet->local_mutex); list_del_init(&local->link); mutex_unlock(&rxnet->local_mutex); @@ -426,13 +449,11 @@ static void rxrpc_local_destroyer(struct rxrpc_local *local) */ rxrpc_purge_queue(&local->reject_queue); rxrpc_purge_queue(&local->event_queue); - - _debug("rcu local %d", local->debug_id); - call_rcu(&local->rcu, rxrpc_local_rcu); }

/* - * Process events on an endpoint + * Process events on an endpoint. The work item carries a ref which + * we must release. */ static void rxrpc_local_processor(struct work_struct *work) { @@ -440,13 +461,15 @@ static void rxrpc_local_processor(struct work_struct *work) container_of(work, struct rxrpc_local, processor); bool again;

- trace_rxrpc_local(local, rxrpc_local_processing, + trace_rxrpc_local(local->debug_id, rxrpc_local_processing, atomic_read(&local->usage), NULL);

do { again = false; - if (atomic_read(&local->usage) == 0) - return rxrpc_local_destroyer(local); + if (atomic_read(&local->active_users) == 0) { + rxrpc_local_destroyer(local); + break; + }

if (!skb_queue_empty(&local->reject_queue)) { rxrpc_reject_packets(local); @@ -458,6 +481,8 @@ static void rxrpc_local_processor(struct work_struct *work) again = true; } } while (again); + + rxrpc_put_local(local); }

/* diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index bd2fa3b7caa7..dc7fdaf20445 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -375,7 +375,7 @@ static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet, spin_lock_bh(&rxnet->peer_hash_lock); list_add_tail(&peer->keepalive_link, &rxnet->peer_keepalive[slot & mask]); - rxrpc_put_peer(peer); + rxrpc_put_peer_locked(peer); }

spin_unlock_bh(&rxnet->peer_hash_lock); diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index 5691b7d266ca..71547e8673b9 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -440,6 +440,24 @@ void rxrpc_put_peer(struct rxrpc_peer *peer) } }

+/* + * Drop a ref on a peer record where the caller already holds the + * peer_hash_lock. + */ +void rxrpc_put_peer_locked(struct rxrpc_peer *peer) +{ + const void *here = __builtin_return_address(0); + int n; + + n = atomic_dec_return(&peer->usage); + trace_rxrpc_peer(peer, rxrpc_peer_put, n, here); + if (n == 0) { + hash_del_rcu(&peer->hash_link); + list_del_init(&peer->keepalive_link); + kfree_rcu(peer, rcu); + } +} + /* * Make sure all peer records have been discarded. */ diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index be01f9c5d963..5d6ab4f6fd7a 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -230,6 +230,7 @@ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, 0, ret); + rxrpc_notify_socket(call); goto out; } _debug("need instant resend %d", ret); diff --git a/sound/soc/davinci/davinci-mcasp.c b/sound/soc/davinci/davinci-mcasp.c index 160b2764b2ad..6a8c279a4b20 100644 --- a/sound/soc/davinci/davinci-mcasp.c +++ b/sound/soc/davinci/davinci-mcasp.c @@ -1150,6 +1150,28 @@ static int davinci_mcasp_trigger(struct snd_pcm_substream *substream, return ret; }

+static int davinci_mcasp_hw_rule_slot_width(struct snd_pcm_hw_params *params, + struct snd_pcm_hw_rule *rule) +{ + struct davinci_mcasp_ruledata *rd = rule->private; + struct snd_mask *fmt = hw_param_mask(params, SNDRV_PCM_HW_PARAM_FORMAT); + struct snd_mask nfmt; + int i, slot_width; + + snd_mask_none(&nfmt); + slot_width = rd->mcasp->slot_width; + + for (i = 0; i <= SNDRV_PCM_FORMAT_LAST; i++) { + if (snd_mask_test(fmt, i)) { + if (snd_pcm_format_width(i) <= slot_width) { + snd_mask_set(&nfmt, i); + } + } + } + + return snd_mask_refine(fmt, &nfmt); +} + static const unsigned int davinci_mcasp_dai_rates[] = { 8000, 11025, 16000, 22050, 32000, 44100, 48000, 64000, 88200, 96000, 176400, 192000, @@ -1257,7 +1279,7 @@ static int davinci_mcasp_startup(struct snd_pcm_substream *substream, struct davinci_mcasp_ruledata *ruledata = &mcasp->ruledata[substream->stream]; u32 max_channels = 0; - int i, dir; + int i, dir, ret; int tdm_slots = mcasp->tdm_slots;

/* Do not allow more then one stream per direction */ @@ -1286,6 +1308,7 @@ static int davinci_mcasp_startup(struct snd_pcm_substream *substream, max_channels++; } ruledata->serializers = max_channels; + ruledata->mcasp = mcasp; max_channels *= tdm_slots; /* * If the already active stream has less channels than the calculated @@ -1311,20 +1334,22 @@ static int davinci_mcasp_startup(struct snd_pcm_substream *substream, 0, SNDRV_PCM_HW_PARAM_CHANNELS, &mcasp->chconstr[substream->stream]);

- if (mcasp->slot_width) - snd_pcm_hw_constraint_minmax(substream->runtime, - SNDRV_PCM_HW_PARAM_SAMPLE_BITS, - 8, mcasp->slot_width); + if (mcasp->slot_width) { + /* Only allow formats require <= slot_width bits on the bus */ + ret = snd_pcm_hw_rule_add(substream->runtime, 0, + SNDRV_PCM_HW_PARAM_FORMAT, + davinci_mcasp_hw_rule_slot_width, + ruledata, + SNDRV_PCM_HW_PARAM_FORMAT, -1); + if (ret) + return ret; + }

/* * If we rely on implicit BCLK divider setting we should * set constraints based on what we can provide. */ if (mcasp->bclk_master && mcasp->bclk_div == 0 && mcasp->sysclk_freq) { - int ret; - - ruledata->mcasp = mcasp; - ret = snd_pcm_hw_rule_add(substream->runtime, 0, SNDRV_PCM_HW_PARAM_RATE, davinci_mcasp_hw_rule_rate, diff --git a/sound/soc/rockchip/rockchip_i2s.c b/sound/soc/rockchip/rockchip_i2s.c index 60d43d53a8f5..11399f81c92f 100644 --- a/sound/soc/rockchip/rockchip_i2s.c +++ b/sound/soc/rockchip/rockchip_i2s.c @@ -329,7 +329,6 @@ static int rockchip_i2s_hw_params(struct snd_pcm_substream *substream, val |= I2S_CHN_4; break; case 2: - case 1: val |= I2S_CHN_2; break; default: @@ -462,7 +461,7 @@ static struct snd_soc_dai_driver rockchip_i2s_dai = { }, .capture = { .stream_name = "Capture", - .channels_min = 1, + .channels_min = 2, .channels_max = 2, .rates = SNDRV_PCM_RATE_8000_192000, .formats = (SNDRV_PCM_FMTBIT_S8 | @@ -662,7 +661,7 @@ static int rockchip_i2s_probe(struct platform_device *pdev) }

if (!of_property_read_u32(node, "rockchip,capture-channels", &val)) { - if (val >= 1 && val <= 8) + if (val >= 2 && val <= 8) soc_dai->capture.channels_max = val; }

diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index 62aa320c2070..dafc3b7f8d72 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -1513,8 +1513,11 @@ static int soc_probe_link_dais(struct snd_soc_card *card, } }

- if (dai_link->dai_fmt) - snd_soc_runtime_set_dai_fmt(rtd, dai_link->dai_fmt); + if (dai_link->dai_fmt) { + ret = snd_soc_runtime_set_dai_fmt(rtd, dai_link->dai_fmt); + if (ret) + return ret; + }

ret = soc_post_component_init(rtd, dai_link->name); if (ret) diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index 3bfc788372f3..4ce57510b623 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -1145,8 +1145,8 @@ static __always_inline int is_connected_ep(struct snd_soc_dapm_widget *widget, list_add_tail(&widget->work_list, list);

if (custom_stop_condition && custom_stop_condition(widget, dir)) { - widget->endpoints[dir] = 1; - return widget->endpoints[dir]; + list = NULL; + custom_stop_condition = NULL; }

if ((widget->is_ep & SND_SOC_DAPM_DIR_TO_EP(dir)) && widget->connected) { @@ -1183,8 +1183,8 @@ static __always_inline int is_connected_ep(struct snd_soc_dapm_widget *widget, * * Optionally, can be supplied with a function acting as a stopping condition. * This function takes the dapm widget currently being examined and the walk - * direction as an arguments, it should return true if the walk should be - * stopped and false otherwise. + * direction as an arguments, it should return true if widgets from that point + * in the graph onwards should not be added to the widget list. */ static int is_connected_output_ep(struct snd_soc_dapm_widget *widget, struct list_head *list, diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c index fa56fde6e8d8..91c0a4434da2 100644 --- a/tools/perf/bench/numa.c +++ b/tools/perf/bench/numa.c @@ -378,8 +378,10 @@ static u8 *alloc_data(ssize_t bytes0, int map_flags,

/* Allocate and initialize all memory on CPU#0: */ if (init_cpu0) { - orig_mask = bind_to_node(0); - bind_to_memnode(0); + int node = numa_node_of_cpu(0); + + orig_mask = bind_to_node(node); + bind_to_memnode(node); }

bytes = bytes0 + HPSIZE; diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c index f42f228e8899..137955197ba8 100644 --- a/tools/perf/builtin-ftrace.c +++ b/tools/perf/builtin-ftrace.c @@ -174,7 +174,7 @@ static int set_tracing_cpumask(struct cpu_map *cpumap) int last_cpu;

last_cpu = cpu_map__cpu(cpumap, cpumap->nr - 1); - mask_size = (last_cpu + 3) / 4 + 1; + mask_size = last_cpu / 4 + 2; /* one more byte for EOS */ mask_size += last_cpu / 32; /* ',' is needed for every 32th cpus */

cpumask = malloc(mask_size); diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index 68c92bb599ee..6b36b7110669 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -450,6 +450,7 @@ static struct fixed { { "inst_retired.any_p", "event=0xc0" }, { "cpu_clk_unhalted.ref", "event=0x0,umask=0x03" }, { "cpu_clk_unhalted.thread", "event=0x3c" }, + { "cpu_clk_unhalted.core", "event=0x3c" }, { "cpu_clk_unhalted.thread_any", "event=0x3c,any=1" }, { NULL, NULL}, }; diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 383674f448fc..f93846edc1e0 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -701,7 +701,10 @@ size_t cpu_map__snprint_mask(struct cpu_map *map, char *buf, size_t size) unsigned char *bitmap; int last_cpu = cpu_map__cpu(map, map->nr - 1);

- bitmap = zalloc((last_cpu + 7) / 8); + if (buf == NULL) + return 0; + + bitmap = zalloc(last_cpu / 8 + 1); if (bitmap == NULL) { buf[0] = '\0'; return 0; diff --git a/tools/testing/selftests/bpf/sendmsg6_prog.c b/tools/testing/selftests/bpf/sendmsg6_prog.c index 5aeaa284fc47..a68062820410 100644 --- a/tools/testing/selftests/bpf/sendmsg6_prog.c +++ b/tools/testing/selftests/bpf/sendmsg6_prog.c @@ -41,8 +41,7 @@ int sendmsg_v6_prog(struct bpf_sock_addr *ctx) }

/* Rewrite destination. */ - if ((ctx->user_ip6[0] & 0xFFFF) == bpf_htons(0xFACE) && - ctx->user_ip6[0] >> 16 == bpf_htons(0xB00C)) { + if (ctx->user_ip6[0] == bpf_htonl(0xFACEB00C)) { ctx->user_ip6[0] = bpf_htonl(DST_REWRITE_IP6_0); ctx->user_ip6[1] = bpf_htonl(DST_REWRITE_IP6_1); ctx->user_ip6[2] = bpf_htonl(DST_REWRITE_IP6_2); diff --git a/tools/testing/selftests/kvm/config b/tools/testing/selftests/kvm/config new file mode 100644 index 000000000000..63ed533f73d6 --- /dev/null +++ b/tools/testing/selftests/kvm/config @@ -0,0 +1,3 @@ +CONFIG_KVM=y +CONFIG_KVM_INTEL=y +CONFIG_KVM_AMD=y diff --git a/tools/testing/selftests/net/forwarding/gre_multipath.sh b/tools/testing/selftests/net/forwarding/gre_multipath.sh index cca2baa03fb8..a8d8e8b3dc81 100755 --- a/tools/testing/selftests/net/forwarding/gre_multipath.sh +++ b/tools/testing/selftests/net/forwarding/gre_multipath.sh @@ -93,18 +93,10 @@ sw1_create() ip route add vrf v$ol1 192.0.2.16/28 \ nexthop dev g1a \ nexthop dev g1b - - tc qdisc add dev $ul1 clsact - tc filter add dev $ul1 egress pref 111 prot ipv4 \ - flower dst_ip 192.0.2.66 action pass - tc filter add dev $ul1 egress pref 222 prot ipv4 \ - flower dst_ip 192.0.2.82 action pass }

sw1_destroy() { - tc qdisc del dev $ul1 clsact - ip route del vrf v$ol1 192.0.2.16/28

ip route del vrf v$ol1 192.0.2.82/32 via 192.0.2.146 @@ -139,10 +131,18 @@ sw2_create() ip route add vrf v$ol2 192.0.2.0/28 \ nexthop dev g2a \ nexthop dev g2b + + tc qdisc add dev $ul2 clsact + tc filter add dev $ul2 ingress pref 111 prot 802.1Q \ + flower vlan_id 111 action pass + tc filter add dev $ul2 ingress pref 222 prot 802.1Q \ + flower vlan_id 222 action pass }

sw2_destroy() { + tc qdisc del dev $ul2 clsact + ip route del vrf v$ol2 192.0.2.0/28

ip route del vrf v$ol2 192.0.2.81/32 via 192.0.2.145 @@ -187,12 +187,16 @@ setup_prepare() sw1_create sw2_create h2_create + + forwarding_enable }

cleanup() { pre_cleanup

+ forwarding_restore + h2_destroy sw2_destroy sw1_destroy @@ -211,15 +215,15 @@ multipath4_test() nexthop dev g1a weight $weight1 \ nexthop dev g1b weight $weight2

- local t0_111=$(tc_rule_stats_get $ul1 111 egress) - local t0_222=$(tc_rule_stats_get $ul1 222 egress) + local t0_111=$(tc_rule_stats_get $ul2 111 ingress) + local t0_222=$(tc_rule_stats_get $ul2 222 ingress)

ip vrf exec v$h1 \ $MZ $h1 -q -p 64 -A 192.0.2.1 -B 192.0.2.18 \ -d 1msec -t udp "sp=1024,dp=0-32768"

- local t1_111=$(tc_rule_stats_get $ul1 111 egress) - local t1_222=$(tc_rule_stats_get $ul1 222 egress) + local t1_111=$(tc_rule_stats_get $ul2 111 ingress) + local t1_222=$(tc_rule_stats_get $ul2 222 ingress)

local d111=$((t1_111 - t0_111)) local d222=$((t1_222 - t0_222))