diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 13d80111bc1f..188a7db8501b 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3788,6 +3788,13 @@ 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, mba. diff --git a/Makefile b/Makefile index be7290af771e..eefd21f3d1ec 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 4 PATCHLEVEL = 14 -SUBLEVEL = 140 +SUBLEVEL = 141 EXTRAVERSION = NAME = Petit Gorille

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 3280953a82cf..09af857ca099 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -134,7 +134,7 @@ _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 @@ -190,7 +190,7 @@ _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/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 7f1c8448d595..fda3bf75de6c 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 f1ddf3a1f307..f6b496d11097 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 ae410f7585f1..f8f9cfded97d 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -723,7 +723,7 @@ 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) { @@ -807,7 +807,8 @@ 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; @@ -838,28 +839,64 @@ 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; @@ -912,10 +949,11 @@ 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 bbebcd7a781e..3914f9218a6b 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -772,6 +772,64 @@ 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; @@ -786,6 +844,13 @@ 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) @@ -828,6 +893,7 @@ 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/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index bf5777bc04d3..eb0c4ee20525 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1804,6 +1804,21 @@ 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 @@ -1848,6 +1863,8 @@ 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: @@ -1862,6 +1879,8 @@ 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: @@ -1872,6 +1891,8 @@ 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 cc2f2e35f4c2..8c36ff0c2dd4 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -704,6 +704,10 @@ 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;

@@ -729,6 +733,8 @@ 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/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 25351b6b1e34..562e90bf73c9 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -971,9 +971,11 @@ 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/vmwgfx/vmwgfx_msg.c b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c index 97000996b8dc..50cc060cc552 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c @@ -300,8 +300,10 @@ 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-tmff.c b/drivers/hid/hid-tmff.c index b83376077d72..cfa0cb22c9b3 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 60e2d4cf1fe3..2e593874f5e0 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/isdn/hardware/mISDN/hfcsusb.c b/drivers/isdn/hardware/mISDN/hfcsusb.c index 35983c7c3137..87588198d68f 100644 --- a/drivers/isdn/hardware/mISDN/hfcsusb.c +++ b/drivers/isdn/hardware/mISDN/hfcsusb.c @@ -1402,6 +1402,7 @@ 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; @@ -1700,13 +1701,23 @@ 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 b7d3b62dae7f..1e17e6421da3 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -1630,7 +1630,9 @@ 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-kcopyd.c b/drivers/md/dm-kcopyd.c index b9d1897bcf5b..bd9a45b94b55 100644 --- a/drivers/md/dm-kcopyd.c +++ b/drivers/md/dm-kcopyd.c @@ -545,8 +545,10 @@ 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);

@@ -598,6 +600,7 @@ 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-table.c b/drivers/md/dm-table.c index d76e685206b3..8f070debe498 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -1308,7 +1308,7 @@ 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; } @@ -1333,6 +1333,9 @@ 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 597098a43aba..b322821a6323 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 44a119e12f1a..a9f84a998476 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) @@ -217,7 +220,7 @@ static int dmz_reclaim_buf(struct dmz_reclaim *zrc, struct dm_zone *dzone)

dmz_unlock_flush(zmd);

- return 0; + return ret; }

/* @@ -261,7 +264,7 @@ static int dmz_reclaim_seq_data(struct dmz_reclaim *zrc, struct dm_zone *dzone)

dmz_unlock_flush(zmd);

- return 0; + return ret; }

/* @@ -314,7 +317,7 @@ static int dmz_reclaim_rnd_data(struct dmz_reclaim *zrc, struct dm_zone *dzone)

dmz_unlock_flush(zmd);

- return 0; + return ret; }

/* @@ -336,7 +339,7 @@ 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; @@ -346,8 +349,8 @@ 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;

@@ -393,13 +396,20 @@ 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; }

/* @@ -444,6 +454,10 @@ 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); @@ -473,7 +487,17 @@ 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 532bfce7f072..1e004d975e78 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; } @@ -855,6 +903,9 @@ static int dmz_prepare_ioctl(struct dm_target *ti, { 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 4aed69d9dd17..b23cac2c4738 100644 --- a/drivers/md/persistent-data/dm-space-map-metadata.c +++ b/drivers/md/persistent-data/dm-space-map-metadata.c @@ -248,7 +248,7 @@ 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 60d0c270af85..c1eeba1906fd 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -2153,6 +2153,15 @@ 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 7d61d8801220..d92113db4fb9 100644 --- a/drivers/net/can/dev.c +++ b/drivers/net/can/dev.c @@ -1217,6 +1217,8 @@ 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 dd56133cc461..fc9f8b01ecae 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/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c index d68c79f9a4b9..059282a6065c 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c @@ -881,7 +881,7 @@ 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 79053d2ce7a3..338683e5ef1e 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; @@ -3390,6 +3390,9 @@ 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 c27054b8ce81..1bfe9544b3c1 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/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c index 7746417130bd..c5d9f290ec4c 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 1e13dea66989..c9258aabca2d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c +++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c @@ -398,7 +398,7 @@ 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/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 4b0144b2a252..e2050afaab7a 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1220,6 +1220,7 @@ 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/nfc/st-nci/se.c b/drivers/nfc/st-nci/se.c index 56f2112e0cd8..85df2e009310 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 3a98563d4a12..eac608a457f0 100644 --- a/drivers/nfc/st21nfca/se.c +++ b/drivers/nfc/st21nfca/se.c @@ -326,6 +326,8 @@ 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/locks.c b/fs/ceph/locks.c index e7cce412f2cf..cb647c8c7b68 100644 --- a/fs/ceph/locks.c +++ b/fs/ceph/locks.c @@ -78,8 +78,7 @@ static int ceph_lock_message(u8 lock_type, u16 operation, struct file *file, 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 23326b0cd562..58a502e622aa 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -2168,7 +2168,15 @@ fill_transform_hdr(struct smb2_transform_hdr *tr_hdr, struct smb_rqst *old_rq) 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)); }

static struct scatterlist * diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index a73144b3cb8c..22cff39cca29 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -433,7 +433,8 @@ 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 8f96f6548dc8..0924b68b5657 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -739,9 +739,12 @@ 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 85ec07e4aa91..f92bfc787c5f 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -614,24 +614,39 @@ 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); } @@ -1782,12 +1797,13 @@ 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; @@ -1816,6 +1832,7 @@ 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/userfaultfd.c b/fs/userfaultfd.c index 7a908d683258..a609d480606d 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -854,6 +854,7 @@ 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;

ACCESS_ONCE(ctx->released) = true;

@@ -869,8 +870,7 @@ 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(); @@ -881,19 +881,20 @@ 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/xfs_iops.c b/fs/xfs/xfs_iops.c index 1daa965f1e08..4e6f2c8574f7 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -789,6 +789,7 @@ 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/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index aa08d4184608..92784b290564 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -277,6 +277,18 @@ 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; @@ -307,6 +319,7 @@ 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 */

@@ -420,7 +433,7 @@ 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 930f2aa3bb4d..1adc2e6c50f9 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> @@ -2387,6 +2388,9 @@ 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 685049a9048d..c5317a7f05e9 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -52,6 +52,7 @@ #include <linux/zpool.h> #include <linux/mount.h> #include <linux/migrate.h> +#include <linux/wait.h> #include <linux/pagemap.h>

#define ZSPAGE_MAGIC 0x58 @@ -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 };

@@ -1878,6 +1883,31 @@ 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) { @@ -1947,6 +1977,7 @@ 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); }

@@ -2046,8 +2077,16 @@ 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); @@ -2093,13 +2132,12 @@ 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); } @@ -2123,8 +2161,36 @@ 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); } @@ -2365,6 +2431,8 @@ 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 f9c6e8ca1fcb..100b4f88179a 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -2273,8 +2273,10 @@ 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/ceph/osd_client.c b/net/ceph/osd_client.c index 53ea2d48896c..92b2641ab93b 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -1330,7 +1330,7 @@ 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, @@ -1426,15 +1426,14 @@ 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_core.c b/net/netfilter/ipset/ip_set_core.c index a3f1dc7cf538..dbf17d3596a6 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1128,7 +1128,7 @@ 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/sound/soc/davinci/davinci-mcasp.c b/sound/soc/davinci/davinci-mcasp.c index 9aa741d27279..0480ec4c8035 100644 --- a/sound/soc/davinci/davinci-mcasp.c +++ b/sound/soc/davinci/davinci-mcasp.c @@ -1158,6 +1158,28 @@ 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, @@ -1251,7 +1273,7 @@ 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 */ @@ -1280,6 +1302,7 @@ 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 @@ -1305,20 +1328,22 @@ 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/soc-core.c b/sound/soc/soc-core.c index 42c2a3065b77..ff5206f5455d 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -1757,8 +1757,11 @@ 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 b4c8ba412a5c..104d5f487c7d 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -1152,8 +1152,8 @@ 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) { @@ -1190,8 +1190,8 @@ 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 997875c770b1..275f1c3c73b6 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 25a42acabee1..13a33fb71a6d 100644 --- a/tools/perf/builtin-ftrace.c +++ b/tools/perf/builtin-ftrace.c @@ -162,7 +162,7 @@ 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 d51dc9ca8861..94a7cabe9b82 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -346,6 +346,7 @@ 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/tests/parse-events.c b/tools/perf/tests/parse-events.c index 424b82a7d078..f0679613bd18 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -19,32 +19,6 @@ #define PERF_TP_SAMPLE_TYPE (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | \ PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD)

-#if defined(__s390x__) -/* Return true if kvm module is available and loaded. Test this - * and retun success when trace point kvm_s390_create_vm - * exists. Otherwise this test always fails. - */ -static bool kvm_s390_create_vm_valid(void) -{ - char *eventfile; - bool rc = false; - - eventfile = get_events_file("kvm-s390"); - - if (eventfile) { - DIR *mydir = opendir(eventfile); - - if (mydir) { - rc = true; - closedir(mydir); - } - put_events_file(eventfile); - } - - return rc; -} -#endif - static int test__checkevent_tracepoint(struct perf_evlist *evlist) { struct perf_evsel *evsel = perf_evlist__first(evlist); @@ -1626,7 +1600,6 @@ static struct evlist_test test__events[] = { { .name = "kvm-s390:kvm_s390_create_vm", .check = test__checkevent_tracepoint, - .valid = kvm_s390_create_vm_valid, .id = 100, }, #endif 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/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