diff options
129 files changed, 1463 insertions, 538 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index 205d3977ac46..297e610c9163 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7730,6 +7730,7 @@ Q: https://patchwork.kernel.org/project/linux-nvdimm/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm.git S: Supported F: drivers/nvdimm/* +F: drivers/acpi/nfit/* F: include/linux/nd.h F: include/linux/libnvdimm.h F: include/uapi/linux/ndctl.h @@ -7741,7 +7742,6 @@ Q: https://patchwork.kernel.org/project/linux-nvdimm/list/ S: Supported F: drivers/nvdimm/blk.c F: drivers/nvdimm/region_devs.c -F: drivers/acpi/nfit* LIBNVDIMM BTT: BLOCK TRANSLATION TABLE M: Vishal Verma <vishal.l.verma@intel.com> @@ -10868,6 +10868,14 @@ L: linux-scsi@vger.kernel.org S: Supported F: drivers/scsi/qedf/ +QLOGIC QL4xxx RDMA DRIVER +M: Ram Amrani <Ram.Amrani@cavium.com> +M: Ariel Elior <Ariel.Elior@cavium.com> +L: linux-rdma@vger.kernel.org +S: Supported +F: drivers/infiniband/hw/qedr/ +F: include/uapi/rdma/qedr-abi.h + QNX4 FILESYSTEM M: Anders Larsen <al@alarsen.net> W: http://www.alarsen.net/linux/qnx4fs/ diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h index d69bebf697e7..74504b154256 100644 --- a/arch/arm/include/asm/cacheflush.h +++ b/arch/arm/include/asm/cacheflush.h @@ -116,7 +116,7 @@ struct cpu_cache_fns { void (*dma_unmap_area)(const void *, size_t, int); void (*dma_flush_range)(const void *, const void *); -}; +} __no_randomize_layout; /* * Select the calling method diff --git a/arch/blackfin/kernel/flat.c b/arch/blackfin/kernel/flat.c index d29ab6a2e909..8ebc54daaa8e 100644 --- a/arch/blackfin/kernel/flat.c +++ b/arch/blackfin/kernel/flat.c @@ -32,7 +32,7 @@ unsigned long bfin_get_addr_from_rp(u32 *ptr, break; case FLAT_BFIN_RELOC_TYPE_32_BIT: - pr_debug("*ptr = %lx", get_unaligned(ptr)); + pr_debug("*ptr = %x", get_unaligned(ptr)); val = get_unaligned(ptr); break; @@ -77,7 +77,7 @@ void bfin_put_addr_at_rp(u32 *ptr, u32 addr, u32 relval) case FLAT_BFIN_RELOC_TYPE_32_BIT: put_unaligned(addr, ptr); - pr_debug("new ptr =%lx", get_unaligned(ptr)); + pr_debug("new ptr =%x", get_unaligned(ptr)); break; } } diff --git a/arch/sparc/include/asm/trap_block.h b/arch/sparc/include/asm/trap_block.h index ec9c04de3664..ff05992dae7a 100644 --- a/arch/sparc/include/asm/trap_block.h +++ b/arch/sparc/include/asm/trap_block.h @@ -54,6 +54,7 @@ extern struct trap_per_cpu trap_block[NR_CPUS]; void init_cur_cpu_trap(struct thread_info *); void setup_tba(void); extern int ncpus_probed; +extern u64 cpu_mondo_counter[NR_CPUS]; unsigned long real_hard_smp_processor_id(void); diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c index 24f21c726dfa..f10e2f712394 100644 --- a/arch/sparc/kernel/pci_sun4v.c +++ b/arch/sparc/kernel/pci_sun4v.c @@ -673,12 +673,14 @@ static void dma_4v_unmap_sg(struct device *dev, struct scatterlist *sglist, static int dma_4v_supported(struct device *dev, u64 device_mask) { struct iommu *iommu = dev->archdata.iommu; - u64 dma_addr_mask; + u64 dma_addr_mask = iommu->dma_addr_mask; - if (device_mask > DMA_BIT_MASK(32) && iommu->atu) - dma_addr_mask = iommu->atu->dma_addr_mask; - else - dma_addr_mask = iommu->dma_addr_mask; + if (device_mask > DMA_BIT_MASK(32)) { + if (iommu->atu) + dma_addr_mask = iommu->atu->dma_addr_mask; + else + return 0; + } if ((device_mask & dma_addr_mask) == dma_addr_mask) return 1; diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index fdf31040a7dc..3218bc43302e 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -622,22 +622,48 @@ retry: } } -/* Multi-cpu list version. */ +#define CPU_MONDO_COUNTER(cpuid) (cpu_mondo_counter[cpuid]) +#define MONDO_USEC_WAIT_MIN 2 +#define MONDO_USEC_WAIT_MAX 100 +#define MONDO_RETRY_LIMIT 500000 + +/* Multi-cpu list version. + * + * Deliver xcalls to 'cnt' number of cpus in 'cpu_list'. + * Sometimes not all cpus receive the mondo, requiring us to re-send + * the mondo until all cpus have received, or cpus are truly stuck + * unable to receive mondo, and we timeout. + * Occasionally a target cpu strand is borrowed briefly by hypervisor to + * perform guest service, such as PCIe error handling. Consider the + * service time, 1 second overall wait is reasonable for 1 cpu. + * Here two in-between mondo check wait time are defined: 2 usec for + * single cpu quick turn around and up to 100usec for large cpu count. + * Deliver mondo to large number of cpus could take longer, we adjusts + * the retry count as long as target cpus are making forward progress. + */ static void hypervisor_xcall_deliver(struct trap_per_cpu *tb, int cnt) { - int retries, this_cpu, prev_sent, i, saw_cpu_error; + int this_cpu, tot_cpus, prev_sent, i, rem; + int usec_wait, retries, tot_retries; + u16 first_cpu = 0xffff; + unsigned long xc_rcvd = 0; unsigned long status; + int ecpuerror_id = 0; + int enocpu_id = 0; u16 *cpu_list; + u16 cpu; this_cpu = smp_processor_id(); - cpu_list = __va(tb->cpu_list_pa); - - saw_cpu_error = 0; - retries = 0; + usec_wait = cnt * MONDO_USEC_WAIT_MIN; + if (usec_wait > MONDO_USEC_WAIT_MAX) + usec_wait = MONDO_USEC_WAIT_MAX; + retries = tot_retries = 0; + tot_cpus = cnt; prev_sent = 0; + do { - int forward_progress, n_sent; + int n_sent, mondo_delivered, target_cpu_busy; status = sun4v_cpu_mondo_send(cnt, tb->cpu_list_pa, @@ -645,94 +671,113 @@ static void hypervisor_xcall_deliver(struct trap_per_cpu *tb, int cnt) /* HV_EOK means all cpus received the xcall, we're done. */ if (likely(status == HV_EOK)) - break; + goto xcall_done; + + /* If not these non-fatal errors, panic */ + if (unlikely((status != HV_EWOULDBLOCK) && + (status != HV_ECPUERROR) && + (status != HV_ENOCPU))) + goto fatal_errors; /* First, see if we made any forward progress. * + * Go through the cpu_list, count the target cpus that have + * received our mondo (n_sent), and those that did not (rem). + * Re-pack cpu_list with the cpus remain to be retried in the + * front - this simplifies tracking the truly stalled cpus. + * * The hypervisor indicates successful sends by setting * cpu list entries to the value 0xffff. + * + * EWOULDBLOCK means some target cpus did not receive the + * mondo and retry usually helps. + * + * ECPUERROR means at least one target cpu is in error state, + * it's usually safe to skip the faulty cpu and retry. + * + * ENOCPU means one of the target cpu doesn't belong to the + * domain, perhaps offlined which is unexpected, but not + * fatal and it's okay to skip the offlined cpu. */ + rem = 0; n_sent = 0; for (i = 0; i < cnt; i++) { - if (likely(cpu_list[i] == 0xffff)) + cpu = cpu_list[i]; + if (likely(cpu == 0xffff)) { n_sent++; + } else if ((status == HV_ECPUERROR) && + (sun4v_cpu_state(cpu) == HV_CPU_STATE_ERROR)) { + ecpuerror_id = cpu + 1; + } else if (status == HV_ENOCPU && !cpu_online(cpu)) { + enocpu_id = cpu + 1; + } else { + cpu_list[rem++] = cpu; + } } - forward_progress = 0; - if (n_sent > prev_sent) - forward_progress = 1; + /* No cpu remained, we're done. */ + if (rem == 0) + break; - prev_sent = n_sent; + /* Otherwise, update the cpu count for retry. */ + cnt = rem; - /* If we get a HV_ECPUERROR, then one or more of the cpus - * in the list are in error state. Use the cpu_state() - * hypervisor call to find out which cpus are in error state. + /* Record the overall number of mondos received by the + * first of the remaining cpus. */ - if (unlikely(status == HV_ECPUERROR)) { - for (i = 0; i < cnt; i++) { - long err; - u16 cpu; + if (first_cpu != cpu_list[0]) { + first_cpu = cpu_list[0]; + xc_rcvd = CPU_MONDO_COUNTER(first_cpu); + } - cpu = cpu_list[i]; - if (cpu == 0xffff) - continue; + /* Was any mondo delivered successfully? */ + mondo_delivered = (n_sent > prev_sent); + prev_sent = n_sent; - err = sun4v_cpu_state(cpu); - if (err == HV_CPU_STATE_ERROR) { - saw_cpu_error = (cpu + 1); - cpu_list[i] = 0xffff; - } - } - } else if (unlikely(status != HV_EWOULDBLOCK)) - goto fatal_mondo_error; + /* or, was any target cpu busy processing other mondos? */ + target_cpu_busy = (xc_rcvd < CPU_MONDO_COUNTER(first_cpu)); + xc_rcvd = CPU_MONDO_COUNTER(first_cpu); - /* Don't bother rewriting the CPU list, just leave the - * 0xffff and non-0xffff entries in there and the - * hypervisor will do the right thing. - * - * Only advance timeout state if we didn't make any - * forward progress. + /* Retry count is for no progress. If we're making progress, + * reset the retry count. */ - if (unlikely(!forward_progress)) { - if (unlikely(++retries > 10000)) - goto fatal_mondo_timeout; - - /* Delay a little bit to let other cpus catch up - * on their cpu mondo queue work. - */ - udelay(2 * cnt); + if (likely(mondo_delivered || target_cpu_busy)) { + tot_retries += retries; + retries = 0; + } else if (unlikely(retries > MONDO_RETRY_LIMIT)) { + goto fatal_mondo_timeout; } - } while (1); - if (unlikely(saw_cpu_error)) - goto fatal_mondo_cpu_error; + /* Delay a little bit to let other cpus catch up on + * their cpu mondo queue work. + */ + if (!mondo_delivered) + udelay(usec_wait); - return; + retries++; + } while (1); -fatal_mondo_cpu_error: - printk(KERN_CRIT "CPU[%d]: SUN4V mondo cpu error, some target cpus " - "(including %d) were in error state\n", - this_cpu, saw_cpu_error - 1); +xcall_done: + if (unlikely(ecpuerror_id > 0)) { + pr_crit("CPU[%d]: SUN4V mondo cpu error, target cpu(%d) was in error state\n", + this_cpu, ecpuerror_id - 1); + } else if (unlikely(enocpu_id > 0)) { + pr_crit("CPU[%d]: SUN4V mondo cpu error, target cpu(%d) does not belong to the domain\n", + this_cpu, enocpu_id - 1); + } return; +fatal_errors: + /* fatal errors include bad alignment, etc */ + pr_crit("CPU[%d]: Args were cnt(%d) cpulist_pa(%lx) mondo_block_pa(%lx)\n", + this_cpu, tot_cpus, tb->cpu_list_pa, tb->cpu_mondo_block_pa); + panic("Unexpected SUN4V mondo error %lu\n", status); + fatal_mondo_timeout: - printk(KERN_CRIT "CPU[%d]: SUN4V mondo timeout, no forward " - " progress after %d retries.\n", - this_cpu, retries); - goto dump_cpu_list_and_out; - -fatal_mondo_error: - printk(KERN_CRIT "CPU[%d]: Unexpected SUN4V mondo error %lu\n", - this_cpu, status); - printk(KERN_CRIT "CPU[%d]: Args were cnt(%d) cpulist_pa(%lx) " - "mondo_block_pa(%lx)\n", - this_cpu, cnt, tb->cpu_list_pa, tb->cpu_mondo_block_pa); - -dump_cpu_list_and_out: - printk(KERN_CRIT "CPU[%d]: CPU list [ ", this_cpu); - for (i = 0; i < cnt; i++) - printk("%u ", cpu_list[i]); - printk("]\n"); + /* some cpus being non-responsive to the cpu mondo */ + pr_crit("CPU[%d]: SUN4V mondo timeout, cpu(%d) made no forward progress after %d retries. Total target cpus(%d).\n", + this_cpu, first_cpu, (tot_retries + retries), tot_cpus); + panic("SUN4V mondo timeout panic\n"); } static void (*xcall_deliver_impl)(struct trap_per_cpu *, int); diff --git a/arch/sparc/kernel/sun4v_ivec.S b/arch/sparc/kernel/sun4v_ivec.S index 559bc5e9c199..34631995859a 100644 --- a/arch/sparc/kernel/sun4v_ivec.S +++ b/arch/sparc/kernel/sun4v_ivec.S @@ -26,6 +26,21 @@ sun4v_cpu_mondo: ldxa [%g0] ASI_SCRATCHPAD, %g4 sub %g4, TRAP_PER_CPU_FAULT_INFO, %g4 + /* Get smp_processor_id() into %g3 */ + sethi %hi(trap_block), %g5 + or %g5, %lo(trap_block), %g5 + sub %g4, %g5, %g3 + srlx %g3, TRAP_BLOCK_SZ_SHIFT, %g3 + + /* Increment cpu_mondo_counter[smp_processor_id()] */ + sethi %hi(cpu_mondo_counter), %g5 + or %g5, %lo(cpu_mondo_counter), %g5 + sllx %g3, 3, %g3 + add %g5, %g3, %g5 + ldx [%g5], %g3 + add %g3, 1, %g3 + stx %g3, [%g5] + /* Get CPU mondo queue base phys address into %g7. */ ldx [%g4 + TRAP_PER_CPU_CPU_MONDO_PA], %g7 diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c index 196ee5eb4d48..ad31af1dd726 100644 --- a/arch/sparc/kernel/traps_64.c +++ b/arch/sparc/kernel/traps_64.c @@ -2733,6 +2733,7 @@ void do_getpsr(struct pt_regs *regs) } } +u64 cpu_mondo_counter[NR_CPUS] = {0}; struct trap_per_cpu trap_block[NR_CPUS]; EXPORT_SYMBOL(trap_block); diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index cb976bab6299..9ffc36bfe4cd 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -84,7 +84,7 @@ struct pv_init_ops { */ unsigned (*patch)(u8 type, u16 clobber, void *insnbuf, unsigned long addr, unsigned len); -}; +} __no_randomize_layout; struct pv_lazy_ops { @@ -92,12 +92,12 @@ struct pv_lazy_ops { void (*enter)(void); void (*leave)(void); void (*flush)(void); -}; +} __no_randomize_layout; struct pv_time_ops { unsigned long long (*sched_clock)(void); unsigned long long (*steal_clock)(int cpu); -}; +} __no_randomize_layout; struct pv_cpu_ops { /* hooks for various privileged instructions */ @@ -176,7 +176,7 @@ struct pv_cpu_ops { void (*start_context_switch)(struct task_struct *prev); void (*end_context_switch)(struct task_struct *next); -}; +} __no_randomize_layout; struct pv_irq_ops { /* @@ -199,7 +199,7 @@ struct pv_irq_ops { #ifdef CONFIG_X86_64 void (*adjust_exception_frame)(void); #endif -}; +} __no_randomize_layout; struct pv_mmu_ops { unsigned long (*read_cr2)(void); @@ -305,7 +305,7 @@ struct pv_mmu_ops { an mfn. We can tell which is which from the index. */ void (*set_fixmap)(unsigned /* enum fixed_addresses */ idx, phys_addr_t phys, pgprot_t flags); -}; +} __no_randomize_layout; struct arch_spinlock; #ifdef CONFIG_SMP @@ -322,7 +322,7 @@ struct pv_lock_ops { void (*kick)(int cpu); struct paravirt_callee_save vcpu_is_preempted; -}; +} __no_randomize_layout; /* This contains all the paravirt structures: we get a convenient * number for each function using the offset which we use to indicate @@ -334,7 +334,7 @@ struct paravirt_patch_template { struct pv_irq_ops pv_irq_ops; struct pv_mmu_ops pv_mmu_ops; struct pv_lock_ops pv_lock_ops; -}; +} __no_randomize_layout; extern struct pv_info pv_info; extern struct pv_init_ops pv_init_ops; diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 6a79547e8ee0..028245e1c42b 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -129,7 +129,7 @@ struct cpuinfo_x86 { /* Index into per_cpu list: */ u16 cpu_index; u32 microcode; -}; +} __randomize_layout; struct cpuid_regs { u32 eax, ebx, ecx, edx; diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index b75b734ee73a..19182d091587 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -3160,6 +3160,8 @@ static struct acpi_driver acpi_nfit_driver = { static __init int nfit_init(void) { + int ret; + BUILD_BUG_ON(sizeof(struct acpi_table_nfit) != 40); BUILD_BUG_ON(sizeof(struct acpi_nfit_system_address) != 56); BUILD_BUG_ON(sizeof(struct acpi_nfit_memory_map) != 48); @@ -3187,8 +3189,14 @@ static __init int nfit_init(void) return -ENOMEM; nfit_mce_register(); + ret = acpi_bus_register_driver(&acpi_nfit_driver); + if (ret) { + nfit_mce_unregister(); + destroy_workqueue(nfit_wq); + } + + return ret; - return acpi_bus_register_driver(&acpi_nfit_driver); } static __exit void nfit_exit(void) diff --git a/drivers/base/regmap/regmap-w1.c b/drivers/base/regmap/regmap-w1.c index 5f04e7bf063e..e6c64b0be5b2 100644 --- a/drivers/base/regmap/regmap-w1.c +++ b/drivers/base/regmap/regmap-w1.c @@ -1,7 +1,7 @@ /* * Register map access API - W1 (1-Wire) support * - * Copyright (C) 2017 OAO Radioavionica + * Copyright (c) 2017 Radioavionica Corporation * Author: Alex A. Mihaylov <minimumlaw@rambler.ru> * * This program is free software; you can redistribute it and/or modify @@ -11,7 +11,7 @@ #include <linux/regmap.h> #include <linux/module.h> -#include "../../w1/w1.h" +#include <linux/w1.h> #include "internal.h" diff --git a/drivers/dax/device-dax.h b/drivers/dax/device-dax.h index fdcd9769ffde..688b051750bd 100644 --- a/drivers/dax/device-dax.h +++ b/drivers/dax/device-dax.h @@ -21,5 +21,5 @@ struct dax_region *alloc_dax_region(struct device *parent, int region_id, struct resource *res, unsigned int align, void *addr, unsigned long flags); struct dev_dax *devm_create_dev_dax(struct dax_region *dax_region, - struct resource *res, int count); + int id, struct resource *res, int count); #endif /* __DEVICE_DAX_H__ */ diff --git a/drivers/dax/device.c b/drivers/dax/device.c index 12943d19bfc4..e9f3b3e4bbf4 100644 --- a/drivers/dax/device.c +++ b/drivers/dax/device.c @@ -529,7 +529,8 @@ static void dev_dax_release(struct device *dev) struct dax_region *dax_region = dev_dax->region; struct dax_device *dax_dev = dev_dax->dax_dev; - ida_simple_remove(&dax_region->ida, dev_dax->id); + if (dev_dax->id >= 0) + ida_simple_remove(&dax_region->ida, dev_dax->id); dax_region_put(dax_region); put_dax(dax_dev); kfree(dev_dax); @@ -559,7 +560,7 @@ static void unregister_dev_dax(void *dev) } struct dev_dax *devm_create_dev_dax(struct dax_region *dax_region, - struct resource *res, int count) + int id, struct resource *res, int count) { struct device *parent = dax_region->dev; struct dax_device *dax_dev; @@ -567,7 +568,10 @@ struct dev_dax *devm_create_dev_dax(struct dax_region *dax_region, struct inode *inode; struct device *dev; struct cdev *cdev; - int rc = 0, i; + int rc, i; + + if (!count) + return ERR_PTR(-EINVAL); dev_dax = kzalloc(sizeof(*dev_dax) + sizeof(*res) * count, GFP_KERNEL); if (!dev_dax) @@ -587,10 +591,16 @@ struct dev_dax *devm_create_dev_dax(struct dax_region *dax_region, if (i < count) goto err_id; - dev_dax->id = ida_simple_get(&dax_region->ida, 0, 0, GFP_KERNEL); - if (dev_dax->id < 0) { - rc = dev_dax->id; - goto err_id; + if (id < 0) { + id = ida_simple_get(&dax_region->ida, 0, 0, GFP_KERNEL); + dev_dax->id = id; + if (id < 0) { + rc = id; + goto err_id; + } + } else { + /* region provider owns @id lifetime */ + dev_dax->id = -1; } /* @@ -598,8 +608,10 @@ struct dev_dax *devm_create_dev_dax(struct dax_region *dax_region, * device outside of mmap of the resulting character device. */ dax_dev = alloc_dax(dev_dax, NULL, NULL); - if (!dax_dev) + if (!dax_dev) { + rc = -ENOMEM; goto err_dax; + } /* from here on we're committed to teardown via dax_dev_release() */ dev = &dev_dax->dev; @@ -620,7 +632,7 @@ struct dev_dax *devm_create_dev_dax(struct dax_region *dax_region, dev->parent = parent; dev->groups = dax_attribute_groups; dev->release = dev_dax_release; - dev_set_name(dev, "dax%d.%d", dax_region->id, dev_dax->id); + dev_set_name(dev, "dax%d.%d", dax_region->id, id); rc = cdev_device_add(cdev, dev); if (rc) { @@ -636,7 +648,8 @@ struct dev_dax *devm_create_dev_dax(struct dax_region *dax_region, return dev_dax; err_dax: - ida_simple_remove(&dax_region->ida, dev_dax->id); + if (dev_dax->id >= 0) + ida_simple_remove(&dax_region->ida, dev_dax->id); err_id: kfree(dev_dax); diff --git a/drivers/dax/pmem.c b/drivers/dax/pmem.c index 9f2a0b4fd801..8d8c852ba8f2 100644 --- a/drivers/dax/pmem.c +++ b/drivers/dax/pmem.c @@ -58,13 +58,12 @@ static void dax_pmem_percpu_kill(void *data) static int dax_pmem_probe(struct device *dev) { - int rc; void *addr; struct resource res; + int rc, id, region_id; struct nd_pfn_sb *pfn_sb; struct dev_dax *dev_dax; struct dax_pmem *dax_pmem; - struct nd_region *nd_region; struct nd_namespace_io *nsio; struct dax_region *dax_region; struct nd_namespace_common *ndns; @@ -123,14 +122,17 @@ static int dax_pmem_probe(struct device *dev) /* adjust the dax_region resource to the start of data */ res.start += le64_to_cpu(pfn_sb->dataoff); - nd_region = to_nd_region(dev->parent); - dax_region = alloc_dax_region(dev, nd_region->id, &res, + rc = sscanf(dev_name(&ndns->dev), "namespace%d.%d", ®ion_id, &id); + if (rc != 2) + return -EINVAL; + + dax_region = alloc_dax_region(dev, region_id, &res, le32_to_cpu(pfn_sb->align), addr, PFN_DEV|PFN_MAP); if (!dax_region) return -ENOMEM; /* TODO: support for subdividing a dax region... */ - dev_dax = devm_create_dev_dax(dax_region, &res, 1); + dev_dax = devm_create_dev_dax(dax_region, id, &res, 1); /* child dev_dax instances now own the lifetime of the dax_region */ dax_region_put(dax_region); diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index 41b39464ded8..501e16a9227d 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -2732,6 +2732,9 @@ static int hidpp_initialize_battery(struct hidpp_device *hidpp) hidpp_battery_props, sizeof(hidpp_battery_props), GFP_KERNEL); + if (!battery_props) + return -ENOMEM; + num_battery_props = ARRAY_SIZE(hidpp_battery_props) - 2; if (hidpp->capabilities & HIDPP_CAPABILITY_BATTERY_MILEAGE) diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index f3e35e7a189d..aff20f4b6d97 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -620,16 +620,6 @@ static int mt_touch_input_mapping(struct hid_device *hdev, struct hid_input *hi, return 0; } -static int mt_touch_input_mapped(struct hid_device *hdev, struct hid_input *hi, - struct hid_field *field, struct hid_usage *usage, - unsigned long **bit, int *max) -{ - if (usage->type == EV_KEY || usage->type == EV_ABS) - set_bit(usage->type, hi->input->evbit); - - return -1; -} - static int mt_compute_slot(struct mt_device *td, struct input_dev *input) { __s32 quirks = td->mtclass.quirks; @@ -969,8 +959,10 @@ static int mt_input_mapped(struct hid_device *hdev, struct hid_input *hi, return 0; if (field->application == HID_DG_TOUCHSCREEN || - field->application == HID_DG_TOUCHPAD) - return mt_touch_input_mapped(hdev, hi, field, usage, bit, max); + field->application == HID_DG_TOUCHPAD) { + /* We own these mappings, tell hid-input to ignore them */ + return -1; + } /* let hid-core decide for the others */ return 0; diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c index a6cb379a4ebc..01236cef7bfb 100644 --- a/drivers/infiniband/core/addr.c +++ b/drivers/infiniband/core/addr.c @@ -268,6 +268,7 @@ int rdma_translate_ip(const struct sockaddr *addr, return ret; ret = rdma_copy_addr(dev_addr, dev, NULL); + dev_addr->bound_dev_if = dev->ifindex; if (vlan_id) *vlan_id = rdma_vlan_dev_vlan_id(dev); dev_put(dev); @@ -280,6 +281,7 @@ int rdma_translate_ip(const struct sockaddr *addr, &((const struct sockaddr_in6 *)addr)->sin6_addr, dev, 1)) { ret = rdma_copy_addr(dev_addr, dev, NULL); + dev_addr->bound_dev_if = dev->ifindex; if (vlan_id) *vlan_id = rdma_vlan_dev_vlan_id(dev); break; @@ -405,10 +407,10 @@ static int addr4_resolve(struct sockaddr_in *src_in, fl4.saddr = src_ip; fl4.flowi4_oif = addr->bound_dev_if; rt = ip_route_output_key(addr->net, &fl4); - if (IS_ERR(rt)) { - ret = PTR_ERR(rt); - goto out; - } + ret = PTR_ERR_OR_ZERO(rt); + if (ret) + return ret; + src_in->sin_family = AF_INET; src_in->sin_addr.s_addr = fl4.saddr; @@ -423,8 +425,6 @@ static int addr4_resolve(struct sockaddr_in *src_in, *prt = rt; return 0; -out: - return ret; } #if IS_ENABLED(CONFIG_IPV6) @@ -509,6 +509,11 @@ static int addr_resolve(struct sockaddr *src_in, struct dst_entry *dst; int ret; + if (!addr->net) { + pr_warn_ratelimited("%s: missing namespace\n", __func__); + return -EINVAL; + } + if (src_in->sa_family == AF_INET) { struct rtable *rt = NULL; const struct sockaddr_in *dst_in4 = @@ -522,8 +527,12 @@ static int addr_resolve(struct sockaddr *src_in, if (resolve_neigh) ret = addr_resolve_neigh(&rt->dst, dst_in, addr, seq); - ndev = rt->dst.dev; - dev_hold(ndev); + if (addr->bound_dev_if) { + ndev = dev_get_by_index(addr->net, addr->bound_dev_if); + } else { + ndev = rt->dst.dev; + dev_hold(ndev); + } ip_rt_put(rt); } else { @@ -539,14 +548,27 @@ static int addr_resolve(struct sockaddr *src_in, if (resolve_neigh) ret = addr_resolve_neigh(dst, dst_in, addr, seq); - ndev = dst->dev; - dev_hold(ndev); + if (addr->bound_dev_if) { + ndev = dev_get_by_index(addr->net, addr->bound_dev_if); + } else { + ndev = dst->dev; + dev_hold(ndev); + } dst_release(dst); } - addr->bound_dev_if = ndev->ifindex; - addr->net = dev_net(ndev); + if (ndev->flags & IFF_LOOPBACK) { + ret = rdma_translate_ip(dst_in, addr, NULL); + /* + * Put the loopback device and get the translated + * device instead. + */ + dev_put(ndev); + ndev = dev_get_by_index(addr->net, addr->bound_dev_if); + } else { + addr->bound_dev_if = ndev->ifindex; + } dev_put(ndev); return ret; diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 31bb82d8ecd7..11aff923b633 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -623,22 +623,11 @@ static inline int cma_validate_port(struct ib_device *device, u8 port, if ((dev_type != ARPHRD_INFINIBAND) && rdma_protocol_ib(device, port)) return ret; - if (dev_type == ARPHRD_ETHER && rdma_protocol_roce(device, port)) { + if (dev_type == ARPHRD_ETHER && rdma_protocol_roce(device, port)) ndev = dev_get_by_index(&init_net, bound_if_index); - if (ndev && ndev->flags & IFF_LOOPBACK) { - pr_info("detected loopback device\n"); - dev_put(ndev); - - if (!device->get_netdev) - return -EOPNOTSUPP; - - ndev = device->get_netdev(device, port); - if (!ndev) - return -ENODEV; - } - } else { + else gid_type = IB_GID_TYPE_IB; - } + ret = ib_find_cached_gid_by_port(device, gid, gid_type, port, ndev, NULL); @@ -2569,21 +2558,6 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv) goto err2; } - if (ndev->flags & IFF_LOOPBACK) { - dev_put(ndev); - if (!id_priv->id.device->get_netdev) { - ret = -EOPNOTSUPP; - goto err2; - } - - ndev = id_priv->id.device->get_netdev(id_priv->id.device, - id_priv->id.port_num); - if (!ndev) { - ret = -ENODEV; - goto err2; - } - } - supported_gids = roce_gid_type_mask_support(id_priv->id.device, id_priv->id.port_num); gid_type = cma_route_gid_type(addr->dev_addr.network, diff --git a/drivers/infiniband/core/roce_gid_mgmt.c b/drivers/infiniband/core/roce_gid_mgmt.c index db958d3207ef..94a9eefb3cfc 100644 --- a/drivers/infiniband/core/roce_gid_mgmt.c +++ b/drivers/infiniband/core/roce_gid_mgmt.c @@ -42,6 +42,8 @@ #include <rdma/ib_cache.h> #include <rdma/ib_addr.h> +static struct workqueue_struct *gid_cache_wq; + enum gid_op_type { GID_DEL = 0, GID_ADD @@ -560,7 +562,7 @@ static int netdevice_queue_work(struct netdev_event_work_cmd *cmds, } INIT_WORK(&ndev_work->work, netdevice_event_work_handler); - queue_work(ib_wq, &ndev_work->work); + queue_work(gid_cache_wq, &ndev_work->work); return NOTIFY_DONE; } @@ -693,7 +695,7 @@ static int addr_event(struct notifier_block *this, unsigned long event, dev_hold(ndev); work->gid_attr.ndev = ndev; - queue_work(ib_wq, &work->work); + queue_work(gid_cache_wq, &work->work); return NOTIFY_DONE; } @@ -740,6 +742,10 @@ static struct notifier_block nb_inet6addr = { int __init roce_gid_mgmt_init(void) { + gid_cache_wq = alloc_ordered_workqueue("gid-cache-wq", 0); + if (!gid_cache_wq) + return -ENOMEM; + register_inetaddr_notifier(&nb_inetaddr); if (IS_ENABLED(CONFIG_IPV6)) register_inet6addr_notifier(&nb_inet6addr); @@ -764,4 +770,5 @@ void __exit roce_gid_mgmt_cleanup(void) * ib-core is removed, all physical devices have been removed, * so no issue with remaining hardware contexts. */ + destroy_workqueue(gid_cache_wq); } diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index 8ba9bfb073d1..3f55d18a3791 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -2005,28 +2005,13 @@ static int modify_qp(struct ib_uverbs_file *file, rdma_ah_set_port_num(&attr->alt_ah_attr, cmd->base.alt_dest.port_num); - if (qp->real_qp == qp) { - if (cmd->base.attr_mask & IB_QP_AV) { - ret = ib_resolve_eth_dmac(qp->device, &attr->ah_attr); - if (ret) - goto release_qp; - } - ret = ib_security_modify_qp(qp, - attr, - modify_qp_mask(qp->qp_type, - cmd->base.attr_mask), - udata); - } else { - ret = ib_security_modify_qp(qp, - attr, - modify_qp_mask(qp->qp_type, - cmd->base.attr_mask), - NULL); - } + ret = ib_modify_qp_with_udata(qp, attr, + modify_qp_mask(qp->qp_type, + cmd->base.attr_mask), + udata); release_qp: uobj_put_obj_read(qp); - out: kfree(attr); diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index c973a83c898b..fb98ed67d5bc 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -452,6 +452,19 @@ int ib_get_gids_from_rdma_hdr(const union rdma_network_hdr *hdr, } EXPORT_SYMBOL(ib_get_gids_from_rdma_hdr); +/* + * This function creates ah from the incoming packet. + * Incoming packet has dgid of the receiver node on which this code is + * getting executed and, sgid contains the GID of the sender. + * + * When resolving mac address of destination, the arrived dgid is used + * as sgid and, sgid is used as dgid because sgid contains destinations + * GID whom to respond to. + * + * This is why when calling rdma_addr_find_l2_eth_by_grh() function, the + * position of arguments dgid and sgid do not match the order of the + * parameters. + */ int ib_init_ah_from_wc(struct ib_device *device, u8 port_num, const struct ib_wc *wc, const struct ib_grh *grh, struct rdma_ah_attr *ah_attr) @@ -507,11 +520,6 @@ int ib_init_ah_from_wc(struct ib_device *device, u8 port_num, } resolved_dev = dev_get_by_index(&init_net, if_index); - if (resolved_dev->flags & IFF_LOOPBACK) { - dev_put(resolved_dev); - resolved_dev = idev; - dev_hold(resolved_dev); - } rcu_read_lock(); if (resolved_dev != idev && !rdma_is_upper_dev_rcu(idev, resolved_dev)) @@ -887,6 +895,7 @@ static const struct { } qp_state_table[IB_QPS_ERR + 1][IB_QPS_ERR + 1] = { [IB_QPS_RESET] = { [IB_QPS_RESET] = { .valid = 1 }, + [IB_QPS_ERR] = { .valid = 1 }, [IB_QPS_INIT] = { .valid = 1, .req_param = { @@ -1268,20 +1277,36 @@ out: } EXPORT_SYMBOL(ib_resolve_eth_dmac); -int ib_modify_qp(struct ib_qp *qp, - struct ib_qp_attr *qp_attr, - int qp_attr_mask) +/** + * ib_modify_qp_with_udata - Modifies the attributes for the specified QP. + * @qp: The QP to modify. + * @attr: On input, specifies the QP attributes to modify. On output, + * the current values of selected QP attributes are returned. + * @attr_mask: A bit-mask used to specify which attributes of the QP + * are being modified. + * @udata: pointer to user's input output buffer information + * are being modified. + * It returns 0 on success and returns appropriate error code on error. + */ +int ib_modify_qp_with_udata(struct ib_qp *qp, struct ib_qp_attr *attr, + int attr_mask, struct ib_udata *udata) { + int ret; - if (qp_attr_mask & IB_QP_AV) { - int ret; - - ret = ib_resolve_eth_dmac(qp->device, &qp_attr->ah_attr); + if (attr_mask & IB_QP_AV) { + ret = ib_resolve_eth_dmac(qp->device, &attr->ah_attr); if (ret) return ret; } + return ib_security_modify_qp(qp, attr, attr_mask, udata); +} +EXPORT_SYMBOL(ib_modify_qp_with_udata); - return ib_security_modify_qp(qp->real_qp, qp_attr, qp_attr_mask, NULL); +int ib_modify_qp(struct ib_qp *qp, + struct ib_qp_attr *qp_attr, + int qp_attr_mask) +{ + return ib_modify_qp_with_udata(qp, qp_attr, qp_attr_mask, NULL); } EXPORT_SYMBOL(ib_modify_qp); diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c index 2ba00b89df6a..94b54850ec75 100644 --- a/drivers/infiniband/hw/hfi1/chip.c +++ b/drivers/infiniband/hw/hfi1/chip.c @@ -12847,7 +12847,12 @@ static void remap_intr(struct hfi1_devdata *dd, int isrc, int msix_intr) /* clear from the handled mask of the general interrupt */ m = isrc / 64; n = isrc % 64; - dd->gi_mask[m] &= ~((u64)1 << n); + if (likely(m < CCE_NUM_INT_CSRS)) { + dd->gi_mask[m] &= ~((u64)1 << n); + } else { + dd_dev_err(dd, "remap interrupt err\n"); + return; + } /* direct the chip source to the given MSI-X interrupt */ m = isrc / 8; diff --git a/drivers/infiniband/hw/hfi1/qp.c b/drivers/infiniband/hw/hfi1/qp.c index 650305cc0373..1a7af9f60c13 100644 --- a/drivers/infiniband/hw/hfi1/qp.c +++ b/drivers/infiniband/hw/hfi1/qp.c @@ -647,18 +647,17 @@ void qp_iter_print(struct seq_file *s, struct qp_iter *iter) qp->pid); } -void *qp_priv_alloc(struct rvt_dev_info *rdi, struct rvt_qp *qp, - gfp_t gfp) +void *qp_priv_alloc(struct rvt_dev_info *rdi, struct rvt_qp *qp) { struct hfi1_qp_priv *priv; - priv = kzalloc_node(sizeof(*priv), gfp, rdi->dparms.node); + priv = kzalloc_node(sizeof(*priv), GFP_KERNEL, rdi->dparms.node); if (!priv) return ERR_PTR(-ENOMEM); priv->owner = qp; - priv->s_ahg = kzalloc_node(sizeof(*priv->s_ahg), gfp, + priv->s_ahg = kzalloc_node(sizeof(*priv->s_ahg), GFP_KERNEL, rdi->dparms.node); if (!priv->s_ahg) { kfree(priv); diff --git a/drivers/infiniband/hw/hfi1/qp.h b/drivers/infiniband/hw/hfi1/qp.h index 1eb9cd7b8c19..6fe542b6a927 100644 --- a/drivers/infiniband/hw/hfi1/qp.h +++ b/drivers/infiniband/hw/hfi1/qp.h @@ -123,8 +123,7 @@ void hfi1_migrate_qp(struct rvt_qp *qp); /* * Functions provided by hfi1 driver for rdmavt to use */ -void *qp_priv_alloc(struct rvt_dev_info *rdi, struct rvt_qp *qp, - gfp_t gfp); +void *qp_priv_alloc(struct rvt_dev_info *rdi, struct rvt_qp *qp); void qp_priv_free(struct rvt_dev_info *rdi, struct rvt_qp *qp); unsigned free_all_qps(struct rvt_dev_info *rdi); void notify_qp_reset(struct rvt_qp *qp); diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c index 37d5d29597a4..23fad6d96944 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c @@ -228,14 +228,14 @@ int hns_roce_v1_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, switch (wr->opcode) { case IB_WR_RDMA_READ: ps_opcode = HNS_ROCE_WQE_OPCODE_RDMA_READ; - set_raddr_seg(wqe, atomic_wr(wr)->remote_addr, - atomic_wr(wr)->rkey); + set_raddr_seg(wqe, rdma_wr(wr)->remote_addr, + rdma_wr(wr)->rkey); break; case IB_WR_RDMA_WRITE: case IB_WR_RDMA_WRITE_WITH_IMM: ps_opcode = HNS_ROCE_WQE_OPCODE_RDMA_WRITE; - set_raddr_seg(wqe, atomic_wr(wr)->remote_addr, - atomic_wr(wr)->rkey); + set_raddr_seg(wqe, rdma_wr(wr)->remote_addr, + rdma_wr(wr)->rkey); break; case IB_WR_SEND: case IB_WR_SEND_WITH_INV: @@ -661,9 +661,11 @@ static int hns_roce_v1_rsv_lp_qp(struct hns_roce_dev *hr_dev) union ib_gid dgid; u64 subnet_prefix; int attr_mask = 0; - int i; + int i, j; int ret; + u8 queue_en[HNS_ROCE_V1_RESV_QP] = { 0 }; u8 phy_port; + u8 port = 0; u8 sl; priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv; @@ -709,11 +711,27 @@ static int hns_roce_v1_rsv_lp_qp(struct hns_roce_dev *hr_dev) attr.rnr_retry = 7; attr.timeout = 0x12; attr.path_mtu = IB_MTU_256; + attr.ah_attr.type = RDMA_AH_ATTR_TYPE_ROCE; rdma_ah_set_grh(&attr.ah_attr, NULL, 0, 0, 1, 0); rdma_ah_set_static_rate(&attr.ah_attr, 3); subnet_prefix = cpu_to_be64(0xfe80000000000000LL); for (i = 0; i < HNS_ROCE_V1_RESV_QP; i++) { + phy_port = (i >= HNS_ROCE_MAX_PORTS) ? (i - 2) : + (i % HNS_ROCE_MAX_PORTS); + sl = i / HNS_ROCE_MAX_PORTS; + + for (j = 0; j < caps->num_ports; j++) { + if (hr_dev->iboe.phy_port[j] == phy_port) { + queue_en[i] = 1; + port = j; + break; + } + } + + if (!queue_en[i]) + continue; + free_mr->mr_free_qp[i] = hns_roce_v1_create_lp_qp(hr_dev, pd); if (IS_ERR(free_mr->mr_free_qp[i])) { dev_err(dev, "Create loop qp failed!\n"); @@ -721,15 +739,7 @@ static int hns_roce_v1_rsv_lp_qp(struct hns_roce_dev *hr_dev) } hr_qp = free_mr->mr_free_qp[i]; - sl = i / caps->num_ports; - - if (caps->num_ports == HNS_ROCE_MAX_PORTS) - phy_port = (i >= HNS_ROCE_MAX_PORTS) ? (i - 2) : - (i % caps->num_ports); - else - phy_port = i % caps->num_ports; - - hr_qp->port = phy_port + 1; + hr_qp->port = port; hr_qp->phy_port = phy_port; hr_qp->ibqp.qp_type = IB_QPT_RC; hr_qp->ibqp.device = &hr_dev->ib_dev; @@ -739,23 +749,22 @@ static int hns_roce_v1_rsv_lp_qp(struct hns_roce_dev *hr_dev) hr_qp->ibqp.recv_cq = cq; hr_qp->ibqp.send_cq = cq; - rdma_ah_set_port_num(&attr.ah_attr, phy_port + 1); - rdma_ah_set_sl(&attr.ah_attr, phy_port + 1); - attr.port_num = phy_port + 1; + rdma_ah_set_port_num(&attr.ah_attr, port + 1); + rdma_ah_set_sl(&attr.ah_attr, sl); + attr.port_num = port + 1; attr.dest_qp_num = hr_qp->qpn; memcpy(rdma_ah_retrieve_dmac(&attr.ah_attr), - hr_dev->dev_addr[phy_port], + hr_dev->dev_addr[port], MAC_ADDR_OCTET_NUM); memcpy(&dgid.raw, &subnet_prefix, sizeof(u64)); - memcpy(&dgid.raw[8], hr_dev->dev_addr[phy_port], 3); - memcpy(&dgid.raw[13], hr_dev->dev_addr[phy_port] + 3, 3); + memcpy(&dgid.raw[8], hr_dev->dev_addr[port], 3); + memcpy(&dgid.raw[13], hr_dev->dev_addr[port] + 3, 3); dgid.raw[11] = 0xff; dgid.raw[12] = 0xfe; dgid.raw[8] ^= 2; rdma_ah_set_dgid_raw(&attr.ah_attr, dgid.raw); - attr_mask |= IB_QP_PORT; ret = hr_dev->hw->modify_qp(&hr_qp->ibqp, &attr, attr_mask, IB_QPS_RESET, IB_QPS_INIT); @@ -812,6 +821,9 @@ static void hns_roce_v1_release_lp_qp(struct hns_roce_dev *hr_dev) for (i = 0; i < HNS_ROCE_V1_RESV_QP; i++) { hr_qp = free_mr->mr_free_qp[i]; + if (!hr_qp) + continue; + ret = hns_roce_v1_destroy_qp(&hr_qp->ibqp); if (ret) dev_err(dev, "Destroy qp %d for mr free failed(%d)!\n", @@ -963,7 +975,7 @@ static void hns_roce_v1_mr_free_work_fn(struct work_struct *work) msecs_to_jiffies(HNS_ROCE_V1_FREE_MR_TIMEOUT_MSECS) + jiffies; int i; int ret; - int ne; + int ne = 0; mr_work = container_of(work, struct hns_roce_mr_free_work, work); hr_mr = (struct hns_roce_mr *)mr_work->mr; @@ -976,6 +988,10 @@ static void hns_roce_v1_mr_free_work_fn(struct work_struct *work) for (i = 0; i < HNS_ROCE_V1_RESV_QP; i++) { hr_qp = free_mr->mr_free_qp[i]; + if (!hr_qp) + continue; + ne++; + ret = hns_roce_v1_send_lp_wqe(hr_qp); if (ret) { dev_err(dev, @@ -985,7 +1001,6 @@ static void hns_roce_v1_mr_free_work_fn(struct work_struct *work) } } - ne = HNS_ROCE_V1_RESV_QP; do { ret = hns_roce_v1_poll_cq(&mr_free_cq->ib_cq, ne, wc); if (ret < 0) { @@ -995,7 +1010,8 @@ static void hns_roce_v1_mr_free_work_fn(struct work_struct *work) goto free_work; } ne -= ret; - msleep(HNS_ROCE_V1_FREE_MR_WAIT_VALUE); + usleep_range(HNS_ROCE_V1_FREE_MR_WAIT_VALUE * 1000, + (1 + HNS_ROCE_V1_FREE_MR_WAIT_VALUE) * 1000); } while (ne && time_before_eq(jiffies, end)); if (ne != 0) @@ -2181,7 +2197,7 @@ static int hns_roce_v1_poll_one(struct hns_roce_cq *hr_cq, } wc->wr_id = wq->wrid[wq->tail & (wq->wqe_cnt - 1)]; ++wq->tail; - } else { + } else { /* RQ conrespond to CQE */ wc->byte_len = le32_to_cpu(cqe->byte_cnt); opcode = roce_get_field(cqe->cqe_byte_4, @@ -3533,10 +3549,12 @@ static int check_qp_db_process_status(struct hns_roce_dev *hr_dev, old_cnt = roce_get_field(old_send, ROCEE_SDB_SEND_PTR_SDB_SEND_PTR_M, ROCEE_SDB_SEND_PTR_SDB_SEND_PTR_S); - if (cur_cnt - old_cnt > SDB_ST_CMP_VAL) + if (cur_cnt - old_cnt > + SDB_ST_CMP_VAL) { success_flags = 1; - else { - send_ptr = roce_get_field(old_send, + } else { + send_ptr = + roce_get_field(old_send, ROCEE_SDB_SEND_PTR_SDB_SEND_PTR_M, ROCEE_SDB_SEND_PTR_SDB_SEND_PTR_S) + roce_get_field(sdb_retry_cnt, @@ -3641,6 +3659,7 @@ static void hns_roce_v1_destroy_qp_work_fn(struct work_struct *work) struct hns_roce_dev *hr_dev; struct hns_roce_qp *hr_qp; struct device *dev; + unsigned long qpn; int ret; qp_work_entry = container_of(work, struct hns_roce_qp_work, work); @@ -3648,8 +3667,9 @@ static void hns_roce_v1_destroy_qp_work_fn(struct work_struct *work) dev = &hr_dev->pdev->dev; priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv; hr_qp = qp_work_entry->qp; + qpn = hr_qp->qpn; - dev_dbg(dev, "Schedule destroy QP(0x%lx) work.\n", hr_qp->qpn); + dev_dbg(dev, "Schedule destroy QP(0x%lx) work.\n", qpn); qp_work_entry->sche_cnt++; @@ -3660,7 +3680,7 @@ static void hns_roce_v1_destroy_qp_work_fn(struct work_struct *work) &qp_work_entry->db_wait_stage); if (ret) { dev_err(dev, "Check QP(0x%lx) db process status failed!\n", - hr_qp->qpn); + qpn); return; } @@ -3674,7 +3694,7 @@ static void hns_roce_v1_destroy_qp_work_fn(struct work_struct *work) ret = hns_roce_v1_modify_qp(&hr_qp->ibqp, NULL, 0, hr_qp->state, IB_QPS_RESET); if (ret) { - dev_err(dev, "Modify QP(0x%lx) to RST failed!\n", hr_qp->qpn); + dev_err(dev, "Modify QP(0x%lx) to RST failed!\n", qpn); return; } @@ -3683,14 +3703,14 @@ static void hns_roce_v1_destroy_qp_work_fn(struct work_struct *work) if (hr_qp->ibqp.qp_type == IB_QPT_RC) { /* RC QP, release QPN */ - hns_roce_release_range_qp(hr_dev, hr_qp->qpn, 1); + hns_roce_release_range_qp(hr_dev, qpn, 1); kfree(hr_qp); } else kfree(hr_to_hr_sqp(hr_qp)); kfree(qp_work_entry); - dev_dbg(dev, "Accomplished destroy QP(0x%lx) work.\n", hr_qp->qpn); + dev_dbg(dev, "Accomplished destroy QP(0x%lx) work.\n", qpn); } int hns_roce_v1_destroy_qp(struct ib_qp *ibqp) diff --git a/drivers/infiniband/hw/hns/hns_roce_main.c b/drivers/infiniband/hw/hns/hns_roce_main.c index c3b41f95e70a..d9777b662eba 100644 --- a/drivers/infiniband/hw/hns/hns_roce_main.c +++ b/drivers/infiniband/hw/hns/hns_roce_main.c @@ -125,8 +125,6 @@ static int handle_en_event(struct hns_roce_dev *hr_dev, u8 port, return -ENODEV; } - spin_lock_bh(&hr_dev->iboe.lock); - switch (event) { case NETDEV_UP: case NETDEV_CHANGE: @@ -144,7 +142,6 @@ static int handle_en_event(struct hns_roce_dev *hr_dev, u8 port, break; } - spin_unlock_bh(&hr_dev->iboe.lock); return 0; } diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c index 4f5a143fc0a7..ff931c580557 100644 --- a/drivers/infiniband/hw/mlx4/cq.c +++ b/drivers/infiniband/hw/mlx4/cq.c @@ -102,7 +102,7 @@ static int mlx4_ib_alloc_cq_buf(struct mlx4_ib_dev *dev, struct mlx4_ib_cq_buf * int err; err = mlx4_buf_alloc(dev->dev, nent * dev->dev->caps.cqe_size, - PAGE_SIZE * 2, &buf->buf, GFP_KERNEL); + PAGE_SIZE * 2, &buf->buf); if (err) goto out; @@ -113,7 +113,7 @@ static int mlx4_ib_alloc_cq_buf(struct mlx4_ib_dev *dev, struct mlx4_ib_cq_buf * if (err) goto err_buf; - err = mlx4_buf_write_mtt(dev->dev, &buf->mtt, &buf->buf, GFP_KERNEL); + err = mlx4_buf_write_mtt(dev->dev, &buf->mtt, &buf->buf); if (err) goto err_mtt; @@ -219,7 +219,7 @@ struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev, uar = &to_mucontext(context)->uar; } else { - err = mlx4_db_alloc(dev->dev, &cq->db, 1, GFP_KERNEL); + err = mlx4_db_alloc(dev->dev, &cq->db, 1); if (err) goto err_cq; diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index 75b2f7d4cd95..d1b43cbbfea7 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -1155,7 +1155,7 @@ static void mlx4_ib_disassociate_ucontext(struct ib_ucontext *ibcontext) * call to mlx4_ib_vma_close. */ put_task_struct(owning_process); - msleep(1); + usleep_range(1000, 2000); owning_process = get_pid_task(ibcontext->tgid, PIDTYPE_PID); if (!owning_process || diff --git a/drivers/infiniband/hw/mlx4/mcg.c b/drivers/infiniband/hw/mlx4/mcg.c index 3405e947dc1e..b73f89700ef9 100644 --- a/drivers/infiniband/hw/mlx4/mcg.c +++ b/drivers/infiniband/hw/mlx4/mcg.c @@ -1091,7 +1091,7 @@ static void _mlx4_ib_mcg_port_cleanup(struct mlx4_ib_demux_ctx *ctx, int destroy if (!count) break; - msleep(1); + usleep_range(1000, 2000); } while (time_after(end, jiffies)); flush_workqueue(ctx->mcg_wq); diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h index c2b9cbf4da05..9db82e67e959 100644 --- a/drivers/infiniband/hw/mlx4/mlx4_ib.h +++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h @@ -185,7 +185,6 @@ enum mlx4_ib_qp_flags { MLX4_IB_QP_LSO = IB_QP_CREATE_IPOIB_UD_LSO, MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK = IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK, MLX4_IB_QP_NETIF = IB_QP_CREATE_NETIF_QP, - MLX4_IB_QP_CREATE_USE_GFP_NOIO = IB_QP_CREATE_USE_GFP_NOIO, /* Mellanox specific flags start from IB_QP_CREATE_RESERVED_START */ MLX4_IB_ROCE_V2_GSI_QP = MLX4_IB_QP_CREATE_ROCE_V2_GSI, diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index 996e9058e515..75c0e6c5dd56 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -634,8 +634,8 @@ static void mlx4_ib_free_qp_counter(struct mlx4_ib_dev *dev, static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd, struct ib_qp_init_attr *init_attr, - struct ib_udata *udata, int sqpn, struct mlx4_ib_qp **caller_qp, - gfp_t gfp) + struct ib_udata *udata, int sqpn, + struct mlx4_ib_qp **caller_qp) { int qpn; int err; @@ -691,14 +691,14 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd, if (qp_type == MLX4_IB_QPT_SMI || qp_type == MLX4_IB_QPT_GSI || (qp_type & (MLX4_IB_QPT_PROXY_SMI | MLX4_IB_QPT_PROXY_SMI_OWNER | MLX4_IB_QPT_PROXY_GSI | MLX4_IB_QPT_TUN_SMI_OWNER))) { - sqp = kzalloc(sizeof (struct mlx4_ib_sqp), gfp); + sqp = kzalloc(sizeof(struct mlx4_ib_sqp), GFP_KERNEL); if (!sqp) return -ENOMEM; qp = &sqp->qp; qp->pri.vid = 0xFFFF; qp->alt.vid = 0xFFFF; } else { - qp = kzalloc(sizeof (struct mlx4_ib_qp), gfp); + qp = kzalloc(sizeof(struct mlx4_ib_qp), GFP_KERNEL); if (!qp) return -ENOMEM; qp->pri.vid = 0xFFFF; @@ -780,7 +780,7 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd, goto err; if (qp_has_rq(init_attr)) { - err = mlx4_db_alloc(dev->dev, &qp->db, 0, gfp); + err = mlx4_db_alloc(dev->dev, &qp->db, 0); if (err) goto err; @@ -788,7 +788,7 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd, } if (mlx4_buf_alloc(dev->dev, qp->buf_size, qp->buf_size, - &qp->buf, gfp)) { + &qp->buf)) { memcpy(&init_attr->cap, &backup_cap, sizeof(backup_cap)); err = set_kernel_sq_size(dev, &init_attr->cap, qp_type, @@ -797,7 +797,7 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd, goto err_db; if (mlx4_buf_alloc(dev->dev, qp->buf_size, - PAGE_SIZE * 2, &qp->buf, gfp)) { + PAGE_SIZE * 2, &qp->buf)) { err = -ENOMEM; goto err_db; } @@ -808,20 +808,20 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd, if (err) goto err_buf; - err = mlx4_buf_write_mtt(dev->dev, &qp->mtt, &qp->buf, gfp); + err = mlx4_buf_write_mtt(dev->dev, &qp->mtt, &qp->buf); if (err) goto err_mtt; qp->sq.wrid = kmalloc_array(qp->sq.wqe_cnt, sizeof(u64), - gfp | __GFP_NOWARN); + GFP_KERNEL | __GFP_NOWARN); if (!qp->sq.wrid) qp->sq.wrid = __vmalloc(qp->sq.wqe_cnt * sizeof(u64), - gfp, PAGE_KERNEL); + GFP_KERNEL, PAGE_KERNEL); qp->rq.wrid = kmalloc_array(qp->rq.wqe_cnt, sizeof(u64), - gfp | __GFP_NOWARN); + GFP_KERNEL | __GFP_NOWARN); if (!qp->rq.wrid) qp->rq.wrid = __vmalloc(qp->rq.wqe_cnt * sizeof(u64), - gfp, PAGE_KERNEL); + GFP_KERNEL, PAGE_KERNEL); if (!qp->sq.wrid || !qp->rq.wrid) { err = -ENOMEM; goto err_wrid; @@ -859,7 +859,7 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd, if (init_attr->create_flags & IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK) qp->flags |= MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK; - err = mlx4_qp_alloc(dev->dev, qpn, &qp->mqp, gfp); + err = mlx4_qp_alloc(dev->dev, qpn, &qp->mqp); if (err) goto err_qpn; @@ -1127,10 +1127,7 @@ static struct ib_qp *_mlx4_ib_create_qp(struct ib_pd *pd, int err; int sup_u_create_flags = MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK; u16 xrcdn = 0; - gfp_t gfp; - gfp = (init_attr->create_flags & MLX4_IB_QP_CREATE_USE_GFP_NOIO) ? - GFP_NOIO : GFP_KERNEL; /* * We only support LSO, vendor flag1, and multicast loopback blocking, * and only for kernel UD QPs. @@ -1140,8 +1137,7 @@ static struct ib_qp *_mlx4_ib_create_qp(struct ib_pd *pd, MLX4_IB_SRIOV_TUNNEL_QP | MLX4_IB_SRIOV_SQP | MLX4_IB_QP_NETIF | - MLX4_IB_QP_CREATE_ROCE_V2_GSI | - MLX4_IB_QP_CREATE_USE_GFP_NOIO)) + MLX4_IB_QP_CREATE_ROCE_V2_GSI)) return ERR_PTR(-EINVAL); if (init_attr->create_flags & IB_QP_CREATE_NETIF_QP) { @@ -1154,7 +1150,6 @@ static struct ib_qp *_mlx4_ib_create_qp(struct ib_pd *pd, return ERR_PTR(-EINVAL); if ((init_attr->create_flags & ~(MLX4_IB_SRIOV_SQP | - MLX4_IB_QP_CREATE_USE_GFP_NOIO | MLX4_IB_QP_CREATE_ROCE_V2_GSI | MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK) && init_attr->qp_type != IB_QPT_UD) || @@ -1179,7 +1174,7 @@ static struct ib_qp *_mlx4_ib_create_qp(struct ib_pd *pd, case IB_QPT_RC: case IB_QPT_UC: case IB_QPT_RAW_PACKET: - qp = kzalloc(sizeof *qp, gfp); + qp = kzalloc(sizeof(*qp), GFP_KERNEL); if (!qp) return ERR_PTR(-ENOMEM); qp->pri.vid = 0xFFFF; @@ -1188,7 +1183,7 @@ static struct ib_qp *_mlx4_ib_create_qp(struct ib_pd *pd, case IB_QPT_UD: { err = create_qp_common(to_mdev(pd->device), pd, init_attr, - udata, 0, &qp, gfp); + udata, 0, &qp); if (err) { kfree(qp); return ERR_PTR(err); @@ -1217,8 +1212,7 @@ static struct ib_qp *_mlx4_ib_create_qp(struct ib_pd *pd, } err = create_qp_common(to_mdev(pd->device), pd, init_attr, udata, - sqpn, - &qp, gfp); + sqpn, &qp); if (err) return ERR_PTR(err); diff --git a/drivers/infiniband/hw/mlx4/srq.c b/drivers/infiniband/hw/mlx4/srq.c index e32dd58937a8..0facaf5f6d23 100644 --- a/drivers/infiniband/hw/mlx4/srq.c +++ b/drivers/infiniband/hw/mlx4/srq.c @@ -135,14 +135,14 @@ struct ib_srq *mlx4_ib_create_srq(struct ib_pd *pd, if (err) goto err_mtt; } else { - err = mlx4_db_alloc(dev->dev, &srq->db, 0, GFP_KERNEL); + err = mlx4_db_alloc(dev->dev, &srq->db, 0); if (err) goto err_srq; *srq->db.db = 0; - if (mlx4_buf_alloc(dev->dev, buf_size, PAGE_SIZE * 2, &srq->buf, - GFP_KERNEL)) { + if (mlx4_buf_alloc(dev->dev, buf_size, PAGE_SIZE * 2, + &srq->buf)) { err = -ENOMEM; goto err_db; } @@ -167,7 +167,7 @@ struct ib_srq *mlx4_ib_create_srq(struct ib_pd *pd, if (err) goto err_buf; - err = mlx4_buf_write_mtt(dev->dev, &srq->mtt, &srq->buf, GFP_KERNEL); + err = mlx4_buf_write_mtt(dev->dev, &srq->mtt, &srq->buf); if (err) goto err_mtt; diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 763bb5b36144..8ab2f1360a45 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -582,6 +582,15 @@ static void clean_keys(struct mlx5_ib_dev *dev, int c) } } +static void mlx5_mr_cache_debugfs_cleanup(struct mlx5_ib_dev *dev) +{ + if (!mlx5_debugfs_root) + return; + + debugfs_remove_recursive(dev->cache.root); + dev->cache.root = NULL; +} + static int mlx5_mr_cache_debugfs_init(struct mlx5_ib_dev *dev) { struct mlx5_mr_cache *cache = &dev->cache; @@ -600,38 +609,34 @@ static int mlx5_mr_cache_debugfs_init(struct mlx5_ib_dev *dev) sprintf(ent->name, "%d", ent->order); ent->dir = debugfs_create_dir(ent->name, cache->root); if (!ent->dir) - return -ENOMEM; + goto err; ent->fsize = debugfs_create_file("size", 0600, ent->dir, ent, &size_fops); if (!ent->fsize) - return -ENOMEM; + goto err; ent->flimit = debugfs_create_file("limit", 0600, ent->dir, ent, &limit_fops); if (!ent->flimit) - return -ENOMEM; + goto err; ent->fcur = debugfs_create_u32("cur", 0400, ent->dir, &ent->cur); if (!ent->fcur) - return -ENOMEM; + goto err; ent->fmiss = debugfs_create_u32("miss", 0600, ent->dir, &ent->miss); if (!ent->fmiss) - return -ENOMEM; + goto err; } return 0; -} - -static void mlx5_mr_cache_debugfs_cleanup(struct mlx5_ib_dev *dev) -{ - if (!mlx5_debugfs_root) - return; +err: + mlx5_mr_cache_debugfs_cleanup(dev); - debugfs_remove_recursive(dev->cache.root); + return -ENOMEM; } static void delay_time_func(unsigned long ctx) @@ -692,6 +697,11 @@ int mlx5_mr_cache_init(struct mlx5_ib_dev *dev) if (err) mlx5_ib_warn(dev, "cache debugfs failure\n"); + /* + * We don't want to fail driver if debugfs failed to initialize, + * so we are not forwarding error to the user. + */ + return 0; } @@ -1779,7 +1789,7 @@ mlx5_ib_sg_to_klms(struct mlx5_ib_mr *mr, mr->ndescs = sg_nents; for_each_sg(sgl, sg, sg_nents, i) { - if (unlikely(i > mr->max_descs)) + if (unlikely(i >= mr->max_descs)) break; klms[i].va = cpu_to_be64(sg_dma_address(sg) + sg_offset); klms[i].bcount = cpu_to_be32(sg_dma_len(sg) - sg_offset); diff --git a/drivers/infiniband/hw/nes/nes_hw.c b/drivers/infiniband/hw/nes/nes_hw.c index 8f9d8b4ad583..b0adf65e4bdb 100644 --- a/drivers/infiniband/hw/nes/nes_hw.c +++ b/drivers/infiniband/hw/nes/nes_hw.c @@ -551,7 +551,7 @@ struct nes_adapter *nes_init_adapter(struct nes_device *nesdev, u8 hw_rev) { if ((0x0F000100 == (pcs_control_status0 & 0x0F000100)) || (0x0F000100 == (pcs_control_status1 & 0x0F000100))) int_cnt++; - msleep(1); + usleep_range(1000, 2000); } if (int_cnt > 1) { spin_lock_irqsave(&nesadapter->phy_lock, flags); @@ -592,7 +592,7 @@ struct nes_adapter *nes_init_adapter(struct nes_device *nesdev, u8 hw_rev) { break; } } - msleep(1); + usleep_range(1000, 2000); } } } diff --git a/drivers/infiniband/hw/qib/qib_qp.c b/drivers/infiniband/hw/qib/qib_qp.c index 5984981e7dd4..a343e3b5d4cb 100644 --- a/drivers/infiniband/hw/qib/qib_qp.c +++ b/drivers/infiniband/hw/qib/qib_qp.c @@ -104,10 +104,9 @@ const struct rvt_operation_params qib_post_parms[RVT_OPERATION_MAX] = { }; -static void get_map_page(struct rvt_qpn_table *qpt, struct rvt_qpn_map *map, - gfp_t gfp) +static void get_map_page(struct rvt_qpn_table *qpt, struct rvt_qpn_map *map) { - unsigned long page = get_zeroed_page(gfp); + unsigned long page = get_zeroed_page(GFP_KERNEL); /* * Free the page if someone raced with us installing it. @@ -126,7 +125,7 @@ static void get_map_page(struct rvt_qpn_table *qpt, struct rvt_qpn_map *map, * zero/one for QP type IB_QPT_SMI/IB_QPT_GSI. */ int qib_alloc_qpn(struct rvt_dev_info *rdi, struct rvt_qpn_table *qpt, - enum ib_qp_type type, u8 port, gfp_t gfp) + enum ib_qp_type type, u8 port) { u32 i, offset, max_scan, qpn; struct rvt_qpn_map *map; @@ -160,7 +159,7 @@ int qib_alloc_qpn(struct rvt_dev_info *rdi, struct rvt_qpn_table *qpt, max_scan = qpt->nmaps - !offset; for (i = 0;;) { if (unlikely(!map->page)) { - get_map_page(qpt, map, gfp); + get_map_page(qpt, map); if (unlikely(!map->page)) break; } @@ -317,16 +316,16 @@ u32 qib_mtu_from_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp, u32 pmtu) return ib_mtu_enum_to_int(pmtu); } -void *qib_qp_priv_alloc(struct rvt_dev_info *rdi, struct rvt_qp *qp, gfp_t gfp) +void *qib_qp_priv_alloc(struct rvt_dev_info *rdi, struct rvt_qp *qp) { struct qib_qp_priv *priv; - priv = kzalloc(sizeof(*priv), gfp); + priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (!priv) return ERR_PTR(-ENOMEM); priv->owner = qp; - priv->s_hdr = kzalloc(sizeof(*priv->s_hdr), gfp); + priv->s_hdr = kzalloc(sizeof(*priv->s_hdr), GFP_KERNEL); if (!priv->s_hdr) { kfree(priv); return ERR_PTR(-ENOMEM); diff --git a/drivers/infiniband/hw/qib/qib_verbs.h b/drivers/infiniband/hw/qib/qib_verbs.h index da0db5485ddc..a52fc67b40d7 100644 --- a/drivers/infiniband/hw/qib/qib_verbs.h +++ b/drivers/infiniband/hw/qib/qib_verbs.h @@ -274,11 +274,11 @@ int qib_get_counters(struct qib_pportdata *ppd, * Functions provided by qib driver for rdmavt to use */ unsigned qib_free_all_qps(struct rvt_dev_info *rdi); -void *qib_qp_priv_alloc(struct rvt_dev_info *rdi, struct rvt_qp *qp, gfp_t gfp); +void *qib_qp_priv_alloc(struct rvt_dev_info *rdi, struct rvt_qp *qp); void qib_qp_priv_free(struct rvt_dev_info *rdi, struct rvt_qp *qp); void qib_notify_qp_reset(struct rvt_qp *qp); int qib_alloc_qpn(struct rvt_dev_info *rdi, struct rvt_qpn_table *qpt, - enum ib_qp_type type, u8 port, gfp_t gfp); + enum ib_qp_type type, u8 port); void qib_restart_rc(struct rvt_qp *qp, u32 psn, int wait); #ifdef CONFIG_DEBUG_FS diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index 727e81cc2c8f..459865439a0b 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -118,10 +118,9 @@ const int ib_rvt_state_ops[IB_QPS_ERR + 1] = { EXPORT_SYMBOL(ib_rvt_state_ops); static void get_map_page(struct rvt_qpn_table *qpt, - struct rvt_qpn_map *map, - gfp_t gfp) + struct rvt_qpn_map *map) { - unsigned long page = get_zeroed_page(gfp); + unsigned long page = get_zeroed_page(GFP_KERNEL); /* * Free the page if someone raced with us installing it. @@ -173,7 +172,7 @@ static int init_qpn_table(struct rvt_dev_info *rdi, struct rvt_qpn_table *qpt) rdi->dparms.qpn_res_start, rdi->dparms.qpn_res_end); for (i = rdi->dparms.qpn_res_start; i <= rdi->dparms.qpn_res_end; i++) { if (!map->page) { - get_map_page(qpt, map, GFP_KERNEL); + get_map_page(qpt, map); if (!map->page) { ret = -ENOMEM; break; @@ -342,14 +341,14 @@ static inline unsigned mk_qpn(struct rvt_qpn_table *qpt, * Return: The queue pair number */ static int alloc_qpn(struct rvt_dev_info *rdi, struct rvt_qpn_table *qpt, - enum ib_qp_type type, u8 port_num, gfp_t gfp) + enum ib_qp_type type, u8 port_num) { u32 i, offset, max_scan, qpn; struct rvt_qpn_map *map; u32 ret; if (rdi->driver_f.alloc_qpn) - return rdi->driver_f.alloc_qpn(rdi, qpt, type, port_num, gfp); + return rdi->driver_f.alloc_qpn(rdi, qpt, type, port_num); if (type == IB_QPT_SMI || type == IB_QPT_GSI) { unsigned n; @@ -374,7 +373,7 @@ static int alloc_qpn(struct rvt_dev_info *rdi, struct rvt_qpn_table *qpt, max_scan = qpt->nmaps - !offset; for (i = 0;;) { if (unlikely(!map->page)) { - get_map_page(qpt, map, gfp); + get_map_page(qpt, map); if (unlikely(!map->page)) break; } @@ -672,7 +671,6 @@ struct ib_qp *rvt_create_qp(struct ib_pd *ibpd, struct ib_qp *ret = ERR_PTR(-ENOMEM); struct rvt_dev_info *rdi = ib_to_rvt(ibpd->device); void *priv = NULL; - gfp_t gfp; size_t sqsize; if (!rdi) @@ -680,18 +678,9 @@ struct ib_qp *rvt_create_qp(struct ib_pd *ibpd, if (init_attr->cap.max_send_sge > rdi->dparms.props.max_sge || init_attr->cap.max_send_wr > rdi->dparms.props.max_qp_wr || - init_attr->create_flags & ~(IB_QP_CREATE_USE_GFP_NOIO)) + init_attr->create_flags) return ERR_PTR(-EINVAL); - /* GFP_NOIO is applicable to RC QP's only */ - - if (init_attr->create_flags & IB_QP_CREATE_USE_GFP_NOIO && - init_attr->qp_type != IB_QPT_RC) - return ERR_PTR(-EINVAL); - - gfp = init_attr->create_flags & IB_QP_CREATE_USE_GFP_NOIO ? - GFP_NOIO : GFP_KERNEL; - /* Check receive queue parameters if no SRQ is specified. */ if (!init_attr->srq) { if (init_attr->cap.max_recv_sge > rdi->dparms.props.max_sge || @@ -719,14 +708,7 @@ struct ib_qp *rvt_create_qp(struct ib_pd *ibpd, sz = sizeof(struct rvt_sge) * init_attr->cap.max_send_sge + sizeof(struct rvt_swqe); - if (gfp == GFP_NOIO) - swq = __vmalloc( - sqsize * sz, - gfp | __GFP_ZERO, PAGE_KERNEL); - else - swq = vzalloc_node( - sqsize * sz, - rdi->dparms.node); + swq = vzalloc_node(sqsize * sz, rdi->dparms.node); if (!swq) return ERR_PTR(-ENOMEM); @@ -741,7 +723,8 @@ struct ib_qp *rvt_create_qp(struct ib_pd *ibpd, } else if (init_attr->cap.max_recv_sge > 1) sg_list_sz = sizeof(*qp->r_sg_list) * (init_attr->cap.max_recv_sge - 1); - qp = kzalloc_node(sz + sg_list_sz, gfp, rdi->dparms.node); + qp = kzalloc_node(sz + sg_list_sz, GFP_KERNEL, + rdi->dparms.node); if (!qp) goto bail_swq; @@ -751,7 +734,7 @@ struct ib_qp *rvt_create_qp(struct ib_pd *ibpd, kzalloc_node( sizeof(*qp->s_ack_queue) * rvt_max_atomic(rdi), - gfp, + GFP_KERNEL, rdi->dparms.node); if (!qp->s_ack_queue) goto bail_qp; @@ -766,7 +749,7 @@ struct ib_qp *rvt_create_qp(struct ib_pd *ibpd, * Driver needs to set up it's private QP structure and do any * initialization that is needed. */ - priv = rdi->driver_f.qp_priv_alloc(rdi, qp, gfp); + priv = rdi->driver_f.qp_priv_alloc(rdi, qp); if (IS_ERR(priv)) { ret = priv; goto bail_qp; @@ -786,11 +769,6 @@ struct ib_qp *rvt_create_qp(struct ib_pd *ibpd, qp->r_rq.wq = vmalloc_user( sizeof(struct rvt_rwq) + qp->r_rq.size * sz); - else if (gfp == GFP_NOIO) - qp->r_rq.wq = __vmalloc( - sizeof(struct rvt_rwq) + - qp->r_rq.size * sz, - gfp | __GFP_ZERO, PAGE_KERNEL); else qp->r_rq.wq = vzalloc_node( sizeof(struct rvt_rwq) + @@ -824,7 +802,7 @@ struct ib_qp *rvt_create_qp(struct ib_pd *ibpd, err = alloc_qpn(rdi, &rdi->qp_dev->qpn_table, init_attr->qp_type, - init_attr->port_num, gfp); + init_attr->port_num); if (err < 0) { ret = ERR_PTR(err); goto bail_rq_wq; diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c index c3a140ed4df2..08f3f90d2912 100644 --- a/drivers/infiniband/sw/rxe/rxe_net.c +++ b/drivers/infiniband/sw/rxe/rxe_net.c @@ -441,6 +441,8 @@ static void rxe_skb_tx_dtor(struct sk_buff *skb) if (unlikely(qp->need_req_skb && skb_out < RXE_INFLIGHT_SKBS_PER_QP_LOW)) rxe_run_task(&qp->req.task, 1); + + rxe_drop_ref(qp); } int rxe_send(struct rxe_dev *rxe, struct rxe_pkt_info *pkt, struct sk_buff *skb) @@ -473,6 +475,7 @@ int rxe_send(struct rxe_dev *rxe, struct rxe_pkt_info *pkt, struct sk_buff *skb) return -EAGAIN; } + rxe_add_ref(pkt->qp); atomic_inc(&pkt->qp->skb_out); kfree_skb(skb); diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c index 073e66783f1d..07511718d98d 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.c +++ b/drivers/infiniband/sw/rxe/rxe_verbs.c @@ -1240,6 +1240,8 @@ int rxe_register_device(struct rxe_dev *rxe) addrconf_addr_eui48((unsigned char *)&dev->node_guid, rxe->ndev->dev_addr); dev->dev.dma_ops = &dma_virt_ops; + dma_coerce_mask_and_coherent(&dev->dev, + dma_get_required_mask(dev->dev.parent)); dev->uverbs_abi_ver = RXE_UVERBS_ABI_VERSION; dev->uverbs_cmd_mask = BIT_ULL(IB_USER_VERBS_CMD_GET_CONTEXT) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c index 7cbcfdac6529..f87d104837dc 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c @@ -39,6 +39,7 @@ #include <linux/vmalloc.h> #include <linux/moduleparam.h> #include <linux/sched/signal.h> +#include <linux/sched/mm.h> #include "ipoib.h" @@ -954,7 +955,7 @@ void ipoib_cm_dev_stop(struct net_device *dev) break; } spin_unlock_irq(&priv->lock); - msleep(1); + usleep_range(1000, 2000); ipoib_drain_cq(dev); spin_lock_irq(&priv->lock); } @@ -1047,9 +1048,8 @@ static struct ib_qp *ipoib_cm_create_tx_qp(struct net_device *dev, struct ipoib_ .sq_sig_type = IB_SIGNAL_ALL_WR, .qp_type = IB_QPT_RC, .qp_context = tx, - .create_flags = IB_QP_CREATE_USE_GFP_NOIO + .create_flags = 0 }; - struct ib_qp *tx_qp; if (dev->features & NETIF_F_SG) @@ -1057,10 +1057,6 @@ static struct ib_qp *ipoib_cm_create_tx_qp(struct net_device *dev, struct ipoib_ min_t(u32, priv->ca->attrs.max_sge, MAX_SKB_FRAGS + 1); tx_qp = ib_create_qp(priv->pd, &attr); - if (PTR_ERR(tx_qp) == -EINVAL) { - attr.create_flags &= ~IB_QP_CREATE_USE_GFP_NOIO; - tx_qp = ib_create_qp(priv->pd, &attr); - } tx->max_send_sge = attr.cap.max_send_sge; return tx_qp; } @@ -1131,10 +1127,11 @@ static int ipoib_cm_tx_init(struct ipoib_cm_tx *p, u32 qpn, struct sa_path_rec *pathrec) { struct ipoib_dev_priv *priv = ipoib_priv(p->dev); + unsigned int noio_flag; int ret; - p->tx_ring = __vmalloc(ipoib_sendq_size * sizeof *p->tx_ring, - GFP_NOIO, PAGE_KERNEL); + noio_flag = memalloc_noio_save(); + p->tx_ring = vzalloc(ipoib_sendq_size * sizeof(*p->tx_ring)); if (!p->tx_ring) { ret = -ENOMEM; goto err_tx; @@ -1142,9 +1139,10 @@ static int ipoib_cm_tx_init(struct ipoib_cm_tx *p, u32 qpn, memset(p->tx_ring, 0, ipoib_sendq_size * sizeof *p->tx_ring); p->qp = ipoib_cm_create_tx_qp(p->dev, p); + memalloc_noio_restore(noio_flag); if (IS_ERR(p->qp)) { ret = PTR_ERR(p->qp); - ipoib_warn(priv, "failed to allocate tx qp: %d\n", ret); + ipoib_warn(priv, "failed to create tx qp: %d\n", ret); goto err_qp; } @@ -1206,7 +1204,7 @@ static void ipoib_cm_tx_destroy(struct ipoib_cm_tx *p) goto timeout; } - msleep(1); + usleep_range(1000, 2000); } } diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c index efe7402f4885..57a9655e844d 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c @@ -770,7 +770,7 @@ int ipoib_ib_dev_stop_default(struct net_device *dev) ipoib_drain_cq(dev); - msleep(1); + usleep_range(1000, 2000); } ipoib_dbg(priv, "All sends and receives done.\n"); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index 6e86eeee370e..70dacaf9044e 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -233,6 +233,7 @@ static netdev_features_t ipoib_fix_features(struct net_device *dev, netdev_featu static int ipoib_change_mtu(struct net_device *dev, int new_mtu) { struct ipoib_dev_priv *priv = ipoib_priv(dev); + int ret = 0; /* dev->mtu > 2K ==> connected mode */ if (ipoib_cm_admin_enabled(dev)) { @@ -256,9 +257,34 @@ static int ipoib_change_mtu(struct net_device *dev, int new_mtu) ipoib_dbg(priv, "MTU must be smaller than the underlying " "link layer MTU - 4 (%u)\n", priv->mcast_mtu); - dev->mtu = min(priv->mcast_mtu, priv->admin_mtu); + new_mtu = min(priv->mcast_mtu, priv->admin_mtu); - return 0; + if (priv->rn_ops->ndo_change_mtu) { + bool carrier_status = netif_carrier_ok(dev); + + netif_carrier_off(dev); + + /* notify lower level on the real mtu */ + ret = priv->rn_ops->ndo_change_mtu(dev, new_mtu); + + if (carrier_status) + netif_carrier_on(dev); + } else { + dev->mtu = new_mtu; + } + + return ret; +} + +static void ipoib_get_stats(struct net_device *dev, + struct rtnl_link_stats64 *stats) +{ + struct ipoib_dev_priv *priv = ipoib_priv(dev); + + if (priv->rn_ops->ndo_get_stats64) + priv->rn_ops->ndo_get_stats64(dev, stats); + else + netdev_stats_to_stats64(stats, &dev->stats); } /* Called with an RCU read lock taken */ @@ -1808,6 +1834,7 @@ static const struct net_device_ops ipoib_netdev_ops_pf = { .ndo_get_vf_stats = ipoib_get_vf_stats, .ndo_set_vf_guid = ipoib_set_vf_guid, .ndo_set_mac_address = ipoib_set_mac, + .ndo_get_stats64 = ipoib_get_stats, }; static const struct net_device_ops ipoib_netdev_ops_vf = { diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.c b/drivers/infiniband/ulp/iser/iscsi_iser.c index 5a887efb4bdf..37b33d708c2d 100644 --- a/drivers/infiniband/ulp/iser/iscsi_iser.c +++ b/drivers/infiniband/ulp/iser/iscsi_iser.c @@ -83,6 +83,7 @@ static struct scsi_host_template iscsi_iser_sht; static struct iscsi_transport iscsi_iser_transport; static struct scsi_transport_template *iscsi_iser_scsi_transport; static struct workqueue_struct *release_wq; +static DEFINE_MUTEX(unbind_iser_conn_mutex); struct iser_global ig; int iser_debug_level = 0; @@ -550,12 +551,14 @@ iscsi_iser_conn_stop(struct iscsi_cls_conn *cls_conn, int flag) */ if (iser_conn) { mutex_lock(&iser_conn->state_mutex); + mutex_lock(&unbind_iser_conn_mutex); iser_conn_terminate(iser_conn); iscsi_conn_stop(cls_conn, flag); /* unbind */ iser_conn->iscsi_conn = NULL; conn->dd_data = NULL; + mutex_unlock(&unbind_iser_conn_mutex); complete(&iser_conn->stop_completion); mutex_unlock(&iser_conn->state_mutex); @@ -977,13 +980,21 @@ static int iscsi_iser_slave_alloc(struct scsi_device *sdev) struct iser_conn *iser_conn; struct ib_device *ib_dev; + mutex_lock(&unbind_iser_conn_mutex); + session = starget_to_session(scsi_target(sdev))->dd_data; iser_conn = session->leadconn->dd_data; + if (!iser_conn) { + mutex_unlock(&unbind_iser_conn_mutex); + return -ENOTCONN; + } ib_dev = iser_conn->ib_conn.device->ib_device; if (!(ib_dev->attrs.device_cap_flags & IB_DEVICE_SG_GAPS_REG)) blk_queue_virt_boundary(sdev->request_queue, ~MASK_4K); + mutex_unlock(&unbind_iser_conn_mutex); + return 0; } diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c index c538a38c91ce..26a004e97ae0 100644 --- a/drivers/infiniband/ulp/iser/iser_verbs.c +++ b/drivers/infiniband/ulp/iser/iser_verbs.c @@ -708,8 +708,14 @@ iser_calc_scsi_params(struct iser_conn *iser_conn, unsigned short sg_tablesize, sup_sg_tablesize; sg_tablesize = DIV_ROUND_UP(max_sectors * 512, SIZE_4K); - sup_sg_tablesize = min_t(unsigned, ISCSI_ISER_MAX_SG_TABLESIZE, - device->ib_device->attrs.max_fast_reg_page_list_len); + if (device->ib_device->attrs.device_cap_flags & + IB_DEVICE_MEM_MGT_EXTENSIONS) + sup_sg_tablesize = + min_t( + uint, ISCSI_ISER_MAX_SG_TABLESIZE, + device->ib_device->attrs.max_fast_reg_page_list_len); + else + sup_sg_tablesize = ISCSI_ISER_MAX_SG_TABLESIZE; iser_conn->scsi_sg_tablesize = min(sg_tablesize, sup_sg_tablesize); } diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c index f4eace5ea184..40f3cd7eab0f 100644 --- a/drivers/md/bitmap.c +++ b/drivers/md/bitmap.c @@ -156,7 +156,8 @@ static int read_sb_page(struct mddev *mddev, loff_t offset, rdev_for_each(rdev, mddev) { if (! test_bit(In_sync, &rdev->flags) - || test_bit(Faulty, &rdev->flags)) + || test_bit(Faulty, &rdev->flags) + || test_bit(Bitmap_sync, &rdev->flags)) continue; target = offset + index * (PAGE_SIZE/512); diff --git a/drivers/md/md.h b/drivers/md/md.h index 991f0fe2dcc6..b50eb4ac1b82 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -134,7 +134,9 @@ enum flag_bits { Faulty, /* device is known to have a fault */ In_sync, /* device is in_sync with rest of array */ Bitmap_sync, /* ..actually, not quite In_sync. Need a - * bitmap-based recovery to get fully in sync + * bitmap-based recovery to get fully in sync. + * The bit is only meaningful before device + * has been passed to pers->hot_add_disk. */ WriteMostly, /* Avoid reading if at all possible */ AutoDetected, /* added by auto-detect */ diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c index 77cce3573aa8..44ad5baf3206 100644 --- a/drivers/md/raid5-ppl.c +++ b/drivers/md/raid5-ppl.c @@ -1150,7 +1150,7 @@ int ppl_init_log(struct r5conf *conf) goto err; } - ppl_conf->bs = bioset_create(conf->raid_disks, 0, 0); + ppl_conf->bs = bioset_create(conf->raid_disks, 0, BIOSET_NEED_BVECS); if (!ppl_conf->bs) { ret = -ENOMEM; goto err; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 2ceb338b094b..aeeb8d6854e2 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -7951,12 +7951,10 @@ static void end_reshape(struct r5conf *conf) { if (!test_bit(MD_RECOVERY_INTR, &conf->mddev->recovery)) { - struct md_rdev *rdev; spin_lock_irq(&conf->device_lock); conf->previous_raid_disks = conf->raid_disks; - rdev_for_each(rdev, conf->mddev) - rdev->data_offset = rdev->new_data_offset; + md_finish_reshape(conf->mddev); smp_wmb(); conf->reshape_progress = MaxSector; conf->mddev->reshape_position = MaxSector; diff --git a/drivers/net/ethernet/mellanox/mlx4/alloc.c b/drivers/net/ethernet/mellanox/mlx4/alloc.c index 249a4584401a..d94b3744a5b9 100644 --- a/drivers/net/ethernet/mellanox/mlx4/alloc.c +++ b/drivers/net/ethernet/mellanox/mlx4/alloc.c @@ -578,7 +578,7 @@ out: } static int mlx4_buf_direct_alloc(struct mlx4_dev *dev, int size, - struct mlx4_buf *buf, gfp_t gfp) + struct mlx4_buf *buf) { dma_addr_t t; @@ -587,7 +587,7 @@ static int mlx4_buf_direct_alloc(struct mlx4_dev *dev, int size, buf->page_shift = get_order(size) + PAGE_SHIFT; buf->direct.buf = dma_zalloc_coherent(&dev->persist->pdev->dev, - size, &t, gfp); + size, &t, GFP_KERNEL); if (!buf->direct.buf) return -ENOMEM; @@ -607,10 +607,10 @@ static int mlx4_buf_direct_alloc(struct mlx4_dev *dev, int size, * multiple pages, so we don't require too much contiguous memory. */ int mlx4_buf_alloc(struct mlx4_dev *dev, int size, int max_direct, - struct mlx4_buf *buf, gfp_t gfp) + struct mlx4_buf *buf) { if (size <= max_direct) { - return mlx4_buf_direct_alloc(dev, size, buf, gfp); + return mlx4_buf_direct_alloc(dev, size, buf); } else { dma_addr_t t; int i; @@ -620,14 +620,14 @@ int mlx4_buf_alloc(struct mlx4_dev *dev, int size, int max_direct, buf->npages = buf->nbufs; buf->page_shift = PAGE_SHIFT; buf->page_list = kcalloc(buf->nbufs, sizeof(*buf->page_list), - gfp); + GFP_KERNEL); if (!buf->page_list) return -ENOMEM; for (i = 0; i < buf->nbufs; ++i) { buf->page_list[i].buf = dma_zalloc_coherent(&dev->persist->pdev->dev, - PAGE_SIZE, &t, gfp); + PAGE_SIZE, &t, GFP_KERNEL); if (!buf->page_list[i].buf) goto err_free; @@ -663,12 +663,11 @@ void mlx4_buf_free(struct mlx4_dev *dev, int size, struct mlx4_buf *buf) } EXPORT_SYMBOL_GPL(mlx4_buf_free); -static struct mlx4_db_pgdir *mlx4_alloc_db_pgdir(struct device *dma_device, - gfp_t gfp) +static struct mlx4_db_pgdir *mlx4_alloc_db_pgdir(struct device *dma_device) { struct mlx4_db_pgdir *pgdir; - pgdir = kzalloc(sizeof *pgdir, gfp); + pgdir = kzalloc(sizeof(*pgdir), GFP_KERNEL); if (!pgdir) return NULL; @@ -676,7 +675,7 @@ static struct mlx4_db_pgdir *mlx4_alloc_db_pgdir(struct device *dma_device, pgdir->bits[0] = pgdir->order0; pgdir->bits[1] = pgdir->order1; pgdir->db_page = dma_alloc_coherent(dma_device, PAGE_SIZE, - &pgdir->db_dma, gfp); + &pgdir->db_dma, GFP_KERNEL); if (!pgdir->db_page) { kfree(pgdir); return NULL; @@ -716,7 +715,7 @@ found: return 0; } -int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, int order, gfp_t gfp) +int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, int order) { struct mlx4_priv *priv = mlx4_priv(dev); struct mlx4_db_pgdir *pgdir; @@ -728,7 +727,7 @@ int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, int order, gfp_t gfp if (!mlx4_alloc_db_from_pgdir(pgdir, db, order)) goto out; - pgdir = mlx4_alloc_db_pgdir(&dev->persist->pdev->dev, gfp); + pgdir = mlx4_alloc_db_pgdir(&dev->persist->pdev->dev); if (!pgdir) { ret = -ENOMEM; goto out; @@ -780,13 +779,13 @@ int mlx4_alloc_hwq_res(struct mlx4_dev *dev, struct mlx4_hwq_resources *wqres, { int err; - err = mlx4_db_alloc(dev, &wqres->db, 1, GFP_KERNEL); + err = mlx4_db_alloc(dev, &wqres->db, 1); if (err) return err; *wqres->db.db = 0; - err = mlx4_buf_direct_alloc(dev, size, &wqres->buf, GFP_KERNEL); + err = mlx4_buf_direct_alloc(dev, size, &wqres->buf); if (err) goto err_db; @@ -795,7 +794,7 @@ int mlx4_alloc_hwq_res(struct mlx4_dev *dev, struct mlx4_hwq_resources *wqres, if (err) goto err_buf; - err = mlx4_buf_write_mtt(dev, &wqres->mtt, &wqres->buf, GFP_KERNEL); + err = mlx4_buf_write_mtt(dev, &wqres->mtt, &wqres->buf); if (err) goto err_mtt; diff --git a/drivers/net/ethernet/mellanox/mlx4/cq.c b/drivers/net/ethernet/mellanox/mlx4/cq.c index fa6d2354a0e9..c56a511b918e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cq.c +++ b/drivers/net/ethernet/mellanox/mlx4/cq.c @@ -224,11 +224,11 @@ int __mlx4_cq_alloc_icm(struct mlx4_dev *dev, int *cqn) if (*cqn == -1) return -ENOMEM; - err = mlx4_table_get(dev, &cq_table->table, *cqn, GFP_KERNEL); + err = mlx4_table_get(dev, &cq_table->table, *cqn); if (err) goto err_out; - err = mlx4_table_get(dev, &cq_table->cmpt_table, *cqn, GFP_KERNEL); + err = mlx4_table_get(dev, &cq_table->cmpt_table, *cqn); if (err) goto err_put; return 0; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index e5fb89505a13..436f7689a032 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -1042,7 +1042,7 @@ static int mlx4_en_config_rss_qp(struct mlx4_en_priv *priv, int qpn, if (!context) return -ENOMEM; - err = mlx4_qp_alloc(mdev->dev, qpn, qp, GFP_KERNEL); + err = mlx4_qp_alloc(mdev->dev, qpn, qp); if (err) { en_err(priv, "Failed to allocate qp #%x\n", qpn); goto out; @@ -1086,7 +1086,7 @@ int mlx4_en_create_drop_qp(struct mlx4_en_priv *priv) en_err(priv, "Failed reserving drop qpn\n"); return err; } - err = mlx4_qp_alloc(priv->mdev->dev, qpn, &priv->drop_qp, GFP_KERNEL); + err = mlx4_qp_alloc(priv->mdev->dev, qpn, &priv->drop_qp); if (err) { en_err(priv, "Failed allocating drop qp\n"); mlx4_qp_release_range(priv->mdev->dev, qpn, 1); @@ -1158,8 +1158,7 @@ int mlx4_en_config_rss_steer(struct mlx4_en_priv *priv) } /* Configure RSS indirection qp */ - err = mlx4_qp_alloc(mdev->dev, priv->base_qpn, rss_map->indir_qp, - GFP_KERNEL); + err = mlx4_qp_alloc(mdev->dev, priv->base_qpn, rss_map->indir_qp); if (err) { en_err(priv, "Failed to allocate RSS indirection QP\n"); goto rss_err; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 4f3a9b27ce4a..73faa3d77921 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -111,7 +111,7 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv, goto err_hwq_res; } - err = mlx4_qp_alloc(mdev->dev, ring->qpn, &ring->sp_qp, GFP_KERNEL); + err = mlx4_qp_alloc(mdev->dev, ring->qpn, &ring->sp_qp); if (err) { en_err(priv, "Failed allocating qp %d\n", ring->qpn); goto err_reserve; diff --git a/drivers/net/ethernet/mellanox/mlx4/icm.c b/drivers/net/ethernet/mellanox/mlx4/icm.c index e1f9e7cebf8f..5a7816e7c7b4 100644 --- a/drivers/net/ethernet/mellanox/mlx4/icm.c +++ b/drivers/net/ethernet/mellanox/mlx4/icm.c @@ -251,8 +251,7 @@ int mlx4_UNMAP_ICM_AUX(struct mlx4_dev *dev) MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE); } -int mlx4_table_get(struct mlx4_dev *dev, struct mlx4_icm_table *table, u32 obj, - gfp_t gfp) +int mlx4_table_get(struct mlx4_dev *dev, struct mlx4_icm_table *table, u32 obj) { u32 i = (obj & (table->num_obj - 1)) / (MLX4_TABLE_CHUNK_SIZE / table->obj_size); @@ -266,7 +265,7 @@ int mlx4_table_get(struct mlx4_dev *dev, struct mlx4_icm_table *table, u32 obj, } table->icm[i] = mlx4_alloc_icm(dev, MLX4_TABLE_CHUNK_SIZE >> PAGE_SHIFT, - (table->lowmem ? gfp : GFP_HIGHUSER) | + (table->lowmem ? GFP_KERNEL : GFP_HIGHUSER) | __GFP_NOWARN, table->coherent); if (!table->icm[i]) { ret = -ENOMEM; @@ -363,7 +362,7 @@ int mlx4_table_get_range(struct mlx4_dev *dev, struct mlx4_icm_table *table, u32 i; for (i = start; i <= end; i += inc) { - err = mlx4_table_get(dev, table, i, GFP_KERNEL); + err = mlx4_table_get(dev, table, i); if (err) goto fail; } diff --git a/drivers/net/ethernet/mellanox/mlx4/icm.h b/drivers/net/ethernet/mellanox/mlx4/icm.h index 0c7364550150..dee67fa39107 100644 --- a/drivers/net/ethernet/mellanox/mlx4/icm.h +++ b/drivers/net/ethernet/mellanox/mlx4/icm.h @@ -71,8 +71,7 @@ struct mlx4_icm *mlx4_alloc_icm(struct mlx4_dev *dev, int npages, gfp_t gfp_mask, int coherent); void mlx4_free_icm(struct mlx4_dev *dev, struct mlx4_icm *icm, int coherent); -int mlx4_table_get(struct mlx4_dev *dev, struct mlx4_icm_table *table, u32 obj, - gfp_t gfp); +int mlx4_table_get(struct mlx4_dev *dev, struct mlx4_icm_table *table, u32 obj); void mlx4_table_put(struct mlx4_dev *dev, struct mlx4_icm_table *table, u32 obj); int mlx4_table_get_range(struct mlx4_dev *dev, struct mlx4_icm_table *table, u32 start, u32 end); diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index 30616cd0140d..706d7f21ac5c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -969,7 +969,7 @@ void mlx4_cleanup_cq_table(struct mlx4_dev *dev); void mlx4_cleanup_qp_table(struct mlx4_dev *dev); void mlx4_cleanup_srq_table(struct mlx4_dev *dev); void mlx4_cleanup_mcg_table(struct mlx4_dev *dev); -int __mlx4_qp_alloc_icm(struct mlx4_dev *dev, int qpn, gfp_t gfp); +int __mlx4_qp_alloc_icm(struct mlx4_dev *dev, int qpn); void __mlx4_qp_free_icm(struct mlx4_dev *dev, int qpn); int __mlx4_cq_alloc_icm(struct mlx4_dev *dev, int *cqn); void __mlx4_cq_free_icm(struct mlx4_dev *dev, int cqn); @@ -977,7 +977,7 @@ int __mlx4_srq_alloc_icm(struct mlx4_dev *dev, int *srqn); void __mlx4_srq_free_icm(struct mlx4_dev *dev, int srqn); int __mlx4_mpt_reserve(struct mlx4_dev *dev); void __mlx4_mpt_release(struct mlx4_dev *dev, u32 index); -int __mlx4_mpt_alloc_icm(struct mlx4_dev *dev, u32 index, gfp_t gfp); +int __mlx4_mpt_alloc_icm(struct mlx4_dev *dev, u32 index); void __mlx4_mpt_free_icm(struct mlx4_dev *dev, u32 index); u32 __mlx4_alloc_mtt_range(struct mlx4_dev *dev, int order); void __mlx4_free_mtt_range(struct mlx4_dev *dev, u32 first_seg, int order); diff --git a/drivers/net/ethernet/mellanox/mlx4/mr.c b/drivers/net/ethernet/mellanox/mlx4/mr.c index ce852ca22a96..24282cd017d3 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mr.c +++ b/drivers/net/ethernet/mellanox/mlx4/mr.c @@ -479,14 +479,14 @@ static void mlx4_mpt_release(struct mlx4_dev *dev, u32 index) __mlx4_mpt_release(dev, index); } -int __mlx4_mpt_alloc_icm(struct mlx4_dev *dev, u32 index, gfp_t gfp) +int __mlx4_mpt_alloc_icm(struct mlx4_dev *dev, u32 index) { struct mlx4_mr_table *mr_table = &mlx4_priv(dev)->mr_table; - return mlx4_table_get(dev, &mr_table->dmpt_table, index, gfp); + return mlx4_table_get(dev, &mr_table->dmpt_table, index); } -static int mlx4_mpt_alloc_icm(struct mlx4_dev *dev, u32 index, gfp_t gfp) +static int mlx4_mpt_alloc_icm(struct mlx4_dev *dev, u32 index) { u64 param = 0; @@ -497,7 +497,7 @@ static int mlx4_mpt_alloc_icm(struct mlx4_dev *dev, u32 index, gfp_t gfp) MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED); } - return __mlx4_mpt_alloc_icm(dev, index, gfp); + return __mlx4_mpt_alloc_icm(dev, index); } void __mlx4_mpt_free_icm(struct mlx4_dev *dev, u32 index) @@ -629,7 +629,7 @@ int mlx4_mr_enable(struct mlx4_dev *dev, struct mlx4_mr *mr) struct mlx4_mpt_entry *mpt_entry; int err; - err = mlx4_mpt_alloc_icm(dev, key_to_hw_index(mr->key), GFP_KERNEL); + err = mlx4_mpt_alloc_icm(dev, key_to_hw_index(mr->key)); if (err) return err; @@ -787,14 +787,13 @@ int mlx4_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt, EXPORT_SYMBOL_GPL(mlx4_write_mtt); int mlx4_buf_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt, - struct mlx4_buf *buf, gfp_t gfp) + struct mlx4_buf *buf) { u64 *page_list; int err; int i; - page_list = kmalloc(buf->npages * sizeof *page_list, - gfp); + page_list = kcalloc(buf->npages, sizeof(*page_list), GFP_KERNEL); if (!page_list) return -ENOMEM; @@ -841,7 +840,7 @@ int mlx4_mw_enable(struct mlx4_dev *dev, struct mlx4_mw *mw) struct mlx4_mpt_entry *mpt_entry; int err; - err = mlx4_mpt_alloc_icm(dev, key_to_hw_index(mw->key), GFP_KERNEL); + err = mlx4_mpt_alloc_icm(dev, key_to_hw_index(mw->key)); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c index 5a310d313e94..26747212526b 100644 --- a/drivers/net/ethernet/mellanox/mlx4/qp.c +++ b/drivers/net/ethernet/mellanox/mlx4/qp.c @@ -301,29 +301,29 @@ void mlx4_qp_release_range(struct mlx4_dev *dev, int base_qpn, int cnt) } EXPORT_SYMBOL_GPL(mlx4_qp_release_range); -int __mlx4_qp_alloc_icm(struct mlx4_dev *dev, int qpn, gfp_t gfp) +int __mlx4_qp_alloc_icm(struct mlx4_dev *dev, int qpn) { struct mlx4_priv *priv = mlx4_priv(dev); struct mlx4_qp_table *qp_table = &priv->qp_table; int err; - err = mlx4_table_get(dev, &qp_table->qp_table, qpn, gfp); + err = mlx4_table_get(dev, &qp_table->qp_table, qpn); if (err) goto err_out; - err = mlx4_table_get(dev, &qp_table->auxc_table, qpn, gfp); + err = mlx4_table_get(dev, &qp_table->auxc_table, qpn); if (err) goto err_put_qp; - err = mlx4_table_get(dev, &qp_table->altc_table, qpn, gfp); + err = mlx4_table_get(dev, &qp_table->altc_table, qpn); if (err) goto err_put_auxc; - err = mlx4_table_get(dev, &qp_table->rdmarc_table, qpn, gfp); + err = mlx4_table_get(dev, &qp_table->rdmarc_table, qpn); if (err) goto err_put_altc; - err = mlx4_table_get(dev, &qp_table->cmpt_table, qpn, gfp); + err = mlx4_table_get(dev, &qp_table->cmpt_table, qpn); if (err) goto err_put_rdmarc; @@ -345,7 +345,7 @@ err_out: return err; } -static int mlx4_qp_alloc_icm(struct mlx4_dev *dev, int qpn, gfp_t gfp) +static int mlx4_qp_alloc_icm(struct mlx4_dev *dev, int qpn) { u64 param = 0; @@ -355,7 +355,7 @@ static int mlx4_qp_alloc_icm(struct mlx4_dev *dev, int qpn, gfp_t gfp) MLX4_CMD_ALLOC_RES, MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED); } - return __mlx4_qp_alloc_icm(dev, qpn, gfp); + return __mlx4_qp_alloc_icm(dev, qpn); } void __mlx4_qp_free_icm(struct mlx4_dev *dev, int qpn) @@ -397,7 +397,7 @@ struct mlx4_qp *mlx4_qp_lookup(struct mlx4_dev *dev, u32 qpn) return qp; } -int mlx4_qp_alloc(struct mlx4_dev *dev, int qpn, struct mlx4_qp *qp, gfp_t gfp) +int mlx4_qp_alloc(struct mlx4_dev *dev, int qpn, struct mlx4_qp *qp) { struct mlx4_priv *priv = mlx4_priv(dev); struct mlx4_qp_table *qp_table = &priv->qp_table; @@ -408,7 +408,7 @@ int mlx4_qp_alloc(struct mlx4_dev *dev, int qpn, struct mlx4_qp *qp, gfp_t gfp) qp->qpn = qpn; - err = mlx4_qp_alloc_icm(dev, qpn, gfp); + err = mlx4_qp_alloc_icm(dev, qpn); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index 812783865205..215e21c3dc8a 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -1822,7 +1822,7 @@ static int qp_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd, return err; if (!fw_reserved(dev, qpn)) { - err = __mlx4_qp_alloc_icm(dev, qpn, GFP_KERNEL); + err = __mlx4_qp_alloc_icm(dev, qpn); if (err) { res_abort_move(dev, slave, RES_QP, qpn); return err; @@ -1909,7 +1909,7 @@ static int mpt_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd, if (err) return err; - err = __mlx4_mpt_alloc_icm(dev, mpt->key, GFP_KERNEL); + err = __mlx4_mpt_alloc_icm(dev, mpt->key); if (err) { res_abort_move(dev, slave, RES_MPT, id); return err; diff --git a/drivers/net/ethernet/mellanox/mlx4/srq.c b/drivers/net/ethernet/mellanox/mlx4/srq.c index f44d089e2ca6..bedf52126824 100644 --- a/drivers/net/ethernet/mellanox/mlx4/srq.c +++ b/drivers/net/ethernet/mellanox/mlx4/srq.c @@ -100,11 +100,11 @@ int __mlx4_srq_alloc_icm(struct mlx4_dev *dev, int *srqn) if (*srqn == -1) return -ENOMEM; - err = mlx4_table_get(dev, &srq_table->table, *srqn, GFP_KERNEL); + err = mlx4_table_get(dev, &srq_table->table, *srqn); if (err) goto err_out; - err = mlx4_table_get(dev, &srq_table->cmpt_table, *srqn, GFP_KERNEL); + err = mlx4_table_get(dev, &srq_table->cmpt_table, *srqn); if (err) goto err_put; return 0; diff --git a/drivers/nvdimm/core.c b/drivers/nvdimm/core.c index 7cd99b1f8596..75bc08c6838c 100644 --- a/drivers/nvdimm/core.c +++ b/drivers/nvdimm/core.c @@ -421,14 +421,15 @@ static void set_badblock(struct badblocks *bb, sector_t s, int num) static void __add_badblock_range(struct badblocks *bb, u64 ns_offset, u64 len) { const unsigned int sector_size = 512; - sector_t start_sector; + sector_t start_sector, end_sector; u64 num_sectors; u32 rem; start_sector = div_u64(ns_offset, sector_size); - num_sectors = div_u64_rem(len, sector_size, &rem); + end_sector = div_u64_rem(ns_offset + len, sector_size, &rem); if (rem) - num_sectors++; + end_sector++; + num_sectors = end_sector - start_sector; if (unlikely(num_sectors > (u64)INT_MAX)) { u64 remaining = num_sectors; diff --git a/drivers/scsi/cxlflash/main.c b/drivers/scsi/cxlflash/main.c index 077f62e208aa..6a4367cc9caa 100644 --- a/drivers/scsi/cxlflash/main.c +++ b/drivers/scsi/cxlflash/main.c @@ -3401,9 +3401,10 @@ static int cxlflash_afu_debug(struct cxlflash_cfg *cfg, if (is_write) { req_flags |= SISL_REQ_FLAGS_HOST_WRITE; - rc = copy_from_user(kbuf, ubuf, ulen); - if (unlikely(rc)) + if (copy_from_user(kbuf, ubuf, ulen)) { + rc = -EFAULT; goto out; + } } } @@ -3431,8 +3432,10 @@ static int cxlflash_afu_debug(struct cxlflash_cfg *cfg, goto out; } - if (ulen && !is_write) - rc = copy_to_user(ubuf, kbuf, ulen); + if (ulen && !is_write) { + if (copy_to_user(ubuf, kbuf, ulen)) + rc = -EFAULT; + } out: kfree(buf); dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc); diff --git a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c index 551d103c27f1..2bfea7082e3a 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c @@ -1693,7 +1693,7 @@ static int prep_ssp_v2_hw(struct hisi_hba *hisi_hba, static int parse_trans_tx_err_code_v2_hw(u32 err_msk) { - const u8 trans_tx_err_code_prio[] = { + static const u8 trans_tx_err_code_prio[] = { TRANS_TX_OPEN_FAIL_WITH_IT_NEXUS_LOSS, TRANS_TX_ERR_PHY_NOT_ENABLE, TRANS_TX_OPEN_CNX_ERR_WRONG_DESTINATION, @@ -1738,7 +1738,7 @@ static int parse_trans_tx_err_code_v2_hw(u32 err_msk) static int parse_trans_rx_err_code_v2_hw(u32 err_msk) { - const u8 trans_rx_err_code_prio[] = { + static const u8 trans_rx_err_code_prio[] = { TRANS_RX_ERR_WITH_RXFRAME_CRC_ERR, TRANS_RX_ERR_WITH_RXFIS_8B10B_DISP_ERR, TRANS_RX_ERR_WITH_RXFRAME_HAVE_ERRPRM, @@ -1784,7 +1784,7 @@ static int parse_trans_rx_err_code_v2_hw(u32 err_msk) static int parse_dma_tx_err_code_v2_hw(u32 err_msk) { - const u8 dma_tx_err_code_prio[] = { + static const u8 dma_tx_err_code_prio[] = { DMA_TX_UNEXP_XFER_ERR, DMA_TX_UNEXP_RETRANS_ERR, DMA_TX_XFER_LEN_OVERFLOW, @@ -1810,7 +1810,7 @@ static int parse_dma_tx_err_code_v2_hw(u32 err_msk) static int parse_sipc_rx_err_code_v2_hw(u32 err_msk) { - const u8 sipc_rx_err_code_prio[] = { + static const u8 sipc_rx_err_code_prio[] = { SIPC_RX_FIS_STATUS_ERR_BIT_VLD, SIPC_RX_PIO_WRSETUP_STATUS_DRQ_ERR, SIPC_RX_FIS_STATUS_BSY_BIT_ERR, @@ -1836,7 +1836,7 @@ static int parse_sipc_rx_err_code_v2_hw(u32 err_msk) static int parse_dma_rx_err_code_v2_hw(u32 err_msk) { - const u8 dma_rx_err_code_prio[] = { + static const u8 dma_rx_err_code_prio[] = { DMA_RX_UNKNOWN_FRM_ERR, DMA_RX_DATA_LEN_OVERFLOW, DMA_RX_DATA_LEN_UNDERFLOW, diff --git a/drivers/scsi/isci/request.c b/drivers/scsi/isci/request.c index 47f66e949745..ed197bc8e801 100644 --- a/drivers/scsi/isci/request.c +++ b/drivers/scsi/isci/request.c @@ -213,7 +213,7 @@ static void sci_task_request_build_ssp_task_iu(struct isci_request *ireq) * @task_context: * */ -static void scu_ssp_reqeust_construct_task_context( +static void scu_ssp_request_construct_task_context( struct isci_request *ireq, struct scu_task_context *task_context) { @@ -425,7 +425,7 @@ static void scu_ssp_io_request_construct_task_context(struct isci_request *ireq, u8 prot_type = scsi_get_prot_type(scmd); u8 prot_op = scsi_get_prot_op(scmd); - scu_ssp_reqeust_construct_task_context(ireq, task_context); + scu_ssp_request_construct_task_context(ireq, task_context); task_context->ssp_command_iu_length = sizeof(struct ssp_cmd_iu) / sizeof(u32); @@ -472,7 +472,7 @@ static void scu_ssp_task_request_construct_task_context(struct isci_request *ire { struct scu_task_context *task_context = ireq->tc; - scu_ssp_reqeust_construct_task_context(ireq, task_context); + scu_ssp_request_construct_task_context(ireq, task_context); task_context->control_frame = 1; task_context->priority = SCU_TASK_PRIORITY_HIGH; @@ -495,7 +495,7 @@ static void scu_ssp_task_request_construct_task_context(struct isci_request *ire * the command buffer is complete. none Revisit task context construction to * determine what is common for SSP/SMP/STP task context structures. */ -static void scu_sata_reqeust_construct_task_context( +static void scu_sata_request_construct_task_context( struct isci_request *ireq, struct scu_task_context *task_context) { @@ -562,7 +562,7 @@ static void scu_stp_raw_request_construct_task_context(struct isci_request *ireq { struct scu_task_context *task_context = ireq->tc; - scu_sata_reqeust_construct_task_context(ireq, task_context); + scu_sata_request_construct_task_context(ireq, task_context); task_context->control_frame = 0; task_context->priority = SCU_TASK_PRIORITY_NORMAL; @@ -613,7 +613,7 @@ static void sci_stp_optimized_request_construct(struct isci_request *ireq, struct scu_task_context *task_context = ireq->tc; /* Build the STP task context structure */ - scu_sata_reqeust_construct_task_context(ireq, task_context); + scu_sata_request_construct_task_context(ireq, task_context); /* Copy over the SGL elements */ sci_request_build_sgl(ireq); @@ -1401,7 +1401,7 @@ static enum sci_status sci_stp_request_pio_data_out_transmit_data(struct isci_re * @data_buffer: The buffer of data to be copied. * @length: The length of the data transfer. * - * Copy the data from the buffer for the length specified to the IO reqeust SGL + * Copy the data from the buffer for the length specified to the IO request SGL * specified data region. enum sci_status */ static enum sci_status diff --git a/drivers/scsi/libfc/fc_disc.c b/drivers/scsi/libfc/fc_disc.c index fd501f8dbb11..8660f923ace0 100644 --- a/drivers/scsi/libfc/fc_disc.c +++ b/drivers/scsi/libfc/fc_disc.c @@ -573,7 +573,7 @@ static void fc_disc_gpn_ft_resp(struct fc_seq *sp, struct fc_frame *fp, event = DISC_EV_FAILED; } if (error) - fc_disc_error(disc, fp); + fc_disc_error(disc, ERR_PTR(error)); else if (event != DISC_EV_NONE) fc_disc_done(disc, event); fc_frame_free(fp); diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c index b58bba4604e8..7786c97e033f 100644 --- a/drivers/scsi/qedf/qedf_main.c +++ b/drivers/scsi/qedf/qedf_main.c @@ -1227,7 +1227,7 @@ static void qedf_rport_event_handler(struct fc_lport *lport, if (rdata->spp_type != FC_TYPE_FCP) { QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC, - "Not offlading since since spp type isn't FCP\n"); + "Not offloading since spp type isn't FCP\n"); break; } if (!(rdata->ids.roles & FC_RPORT_ROLE_FCP_TARGET)) { diff --git a/drivers/scsi/qedi/qedi.h b/drivers/scsi/qedi/qedi.h index 32632c9b2276..91d2f51c351b 100644 --- a/drivers/scsi/qedi/qedi.h +++ b/drivers/scsi/qedi/qedi.h @@ -23,11 +23,17 @@ #include <linux/qed/qed_iscsi_if.h> #include <linux/qed/qed_ll2_if.h> #include "qedi_version.h" +#include "qedi_nvm_iscsi_cfg.h" #define QEDI_MODULE_NAME "qedi" struct qedi_endpoint; +#ifndef GET_FIELD2 +#define GET_FIELD2(value, name) \ + (((value) & (name ## _MASK)) >> (name ## _OFFSET)) +#endif + /* * PCI function probe defines */ @@ -66,6 +72,11 @@ struct qedi_endpoint; #define QEDI_HW_DMA_BOUNDARY 0xfff #define QEDI_PATH_HANDLE 0xFE0000000UL +enum qedi_nvm_tgts { + QEDI_NVM_TGT_PRI, + QEDI_NVM_TGT_SEC, +}; + struct qedi_uio_ctrl { /* meta data */ u32 uio_hsi_version; @@ -283,6 +294,8 @@ struct qedi_ctx { void *bdq_pbl_list; dma_addr_t bdq_pbl_list_dma; u8 bdq_pbl_list_num_entries; + struct nvm_iscsi_cfg *iscsi_cfg; + dma_addr_t nvm_buf_dma; void __iomem *bdq_primary_prod; void __iomem *bdq_secondary_prod; u16 bdq_prod_idx; @@ -337,6 +350,10 @@ struct qedi_ctx { bool use_fast_sge; atomic_t num_offloads; +#define SYSFS_FLAG_FW_SEL_BOOT 2 +#define IPV6_LEN 41 +#define IPV4_LEN 17 + struct iscsi_boot_kset *boot_kset; }; struct qedi_work { diff --git a/drivers/scsi/qedi/qedi_fw.c b/drivers/scsi/qedi/qedi_fw.c index 19254bd739d9..93d54acd4a22 100644 --- a/drivers/scsi/qedi/qedi_fw.c +++ b/drivers/scsi/qedi/qedi_fw.c @@ -1411,7 +1411,7 @@ static void qedi_tmf_work(struct work_struct *work) list_work = kzalloc(sizeof(*list_work), GFP_ATOMIC); if (!list_work) { - QEDI_ERR(&qedi->dbg_ctx, "Memory alloction failed\n"); + QEDI_ERR(&qedi->dbg_ctx, "Memory allocation failed\n"); goto abort_ret; } diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c index 5f5a4ef2e529..2c3783684815 100644 --- a/drivers/scsi/qedi/qedi_main.c +++ b/drivers/scsi/qedi/qedi_main.c @@ -19,6 +19,7 @@ #include <linux/mm.h> #include <linux/if_vlan.h> #include <linux/cpu.h> +#include <linux/iscsi_boot_sysfs.h> #include <scsi/scsi_cmnd.h> #include <scsi/scsi_device.h> @@ -1143,6 +1144,30 @@ exit_setup_int: return rc; } +static void qedi_free_nvm_iscsi_cfg(struct qedi_ctx *qedi) +{ + if (qedi->iscsi_cfg) + dma_free_coherent(&qedi->pdev->dev, + sizeof(struct nvm_iscsi_cfg), + qedi->iscsi_cfg, qedi->nvm_buf_dma); +} + +static int qedi_alloc_nvm_iscsi_cfg(struct qedi_ctx *qedi) +{ + qedi->iscsi_cfg = dma_zalloc_coherent(&qedi->pdev->dev, + sizeof(struct nvm_iscsi_cfg), + &qedi->nvm_buf_dma, GFP_KERNEL); + if (!qedi->iscsi_cfg) { + QEDI_ERR(&qedi->dbg_ctx, "Could not allocate NVM BUF.\n"); + return -ENOMEM; + } + QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO, + "NVM BUF addr=0x%p dma=0x%llx.\n", qedi->iscsi_cfg, + qedi->nvm_buf_dma); + + return 0; +} + static void qedi_free_bdq(struct qedi_ctx *qedi) { int i; @@ -1183,6 +1208,7 @@ static void qedi_free_global_queues(struct qedi_ctx *qedi) kfree(gl[i]); } qedi_free_bdq(qedi); + qedi_free_nvm_iscsi_cfg(qedi); } static int qedi_alloc_bdq(struct qedi_ctx *qedi) @@ -1309,6 +1335,11 @@ static int qedi_alloc_global_queues(struct qedi_ctx *qedi) if (rc) goto mem_alloc_failure; + /* Allocate DMA coherent buffers for NVM_ISCSI_CFG */ + rc = qedi_alloc_nvm_iscsi_cfg(qedi); + if (rc) + goto mem_alloc_failure; + /* Allocate a CQ and an associated PBL for each MSI-X * vector. */ @@ -1671,6 +1702,387 @@ void qedi_reset_host_mtu(struct qedi_ctx *qedi, u16 mtu) qedi_ops->ll2->start(qedi->cdev, ¶ms); } +/** + * qedi_get_nvram_block: - Scan through the iSCSI NVRAM block (while accounting + * for gaps) for the matching absolute-pf-id of the QEDI device. + */ +static struct nvm_iscsi_block * +qedi_get_nvram_block(struct qedi_ctx *qedi) +{ + int i; + u8 pf; + u32 flags; + struct nvm_iscsi_block *block; + + pf = qedi->dev_info.common.abs_pf_id; + block = &qedi->iscsi_cfg->block[0]; + for (i = 0; i < NUM_OF_ISCSI_PF_SUPPORTED; i++, block++) { + flags = ((block->id) & NVM_ISCSI_CFG_BLK_CTRL_FLAG_MASK) >> + NVM_ISCSI_CFG_BLK_CTRL_FLAG_OFFSET; + if (flags & (NVM_ISCSI_CFG_BLK_CTRL_FLAG_IS_NOT_EMPTY | + NVM_ISCSI_CFG_BLK_CTRL_FLAG_PF_MAPPED) && + (pf == (block->id & NVM_ISCSI_CFG_BLK_MAPPED_PF_ID_MASK) + >> NVM_ISCSI_CFG_BLK_MAPPED_PF_ID_OFFSET)) + return block; + } + return NULL; +} + +static ssize_t qedi_show_boot_eth_info(void *data, int type, char *buf) +{ + struct qedi_ctx *qedi = data; + struct nvm_iscsi_initiator *initiator; + char *str = buf; + int rc = 1; + u32 ipv6_en, dhcp_en, ip_len; + struct nvm_iscsi_block *block; + char *fmt, *ip, *sub, *gw; + + block = qedi_get_nvram_block(qedi); + if (!block) + return 0; + + initiator = &block->initiator; + ipv6_en = block->generic.ctrl_flags & + NVM_ISCSI_CFG_GEN_IPV6_ENABLED; + dhcp_en = block->generic.ctrl_flags & + NVM_ISCSI_CFG_GEN_DHCP_TCPIP_CONFIG_ENABLED; + /* Static IP assignments. */ + fmt = ipv6_en ? "%pI6\n" : "%pI4\n"; + ip = ipv6_en ? initiator->ipv6.addr.byte : initiator->ipv4.addr.byte; + ip_len = ipv6_en ? IPV6_LEN : IPV4_LEN; + sub = ipv6_en ? initiator->ipv6.subnet_mask.byte : + initiator->ipv4.subnet_mask.byte; + gw = ipv6_en ? initiator->ipv6.gateway.byte : + initiator->ipv4.gateway.byte; + /* DHCP IP adjustments. */ + fmt = dhcp_en ? "%s\n" : fmt; + if (dhcp_en) { + ip = ipv6_en ? "0::0" : "0.0.0.0"; + sub = ip; + gw = ip; + ip_len = ipv6_en ? 5 : 8; + } + + switch (type) { + case ISCSI_BOOT_ETH_IP_ADDR: + rc = snprintf(str, ip_len, fmt, ip); + break; + case ISCSI_BOOT_ETH_SUBNET_MASK: + rc = snprintf(str, ip_len, fmt, sub); + break; + case ISCSI_BOOT_ETH_GATEWAY: + rc = snprintf(str, ip_len, fmt, gw); + break; + case ISCSI_BOOT_ETH_FLAGS: + rc = snprintf(str, 3, "%hhd\n", + SYSFS_FLAG_FW_SEL_BOOT); + break; + case ISCSI_BOOT_ETH_INDEX: + rc = snprintf(str, 3, "0\n"); + break; + case ISCSI_BOOT_ETH_MAC: + rc = sysfs_format_mac(str, qedi->mac, ETH_ALEN); + break; + case ISCSI_BOOT_ETH_VLAN: + rc = snprintf(str, 12, "%d\n", + GET_FIELD2(initiator->generic_cont0, + NVM_ISCSI_CFG_INITIATOR_VLAN)); + break; + case ISCSI_BOOT_ETH_ORIGIN: + if (dhcp_en) + rc = snprintf(str, 3, "3\n"); + break; + default: + rc = 0; + break; + } + + return rc; +} + +static umode_t qedi_eth_get_attr_visibility(void *data, int type) +{ + int rc = 1; + + switch (type) { + case ISCSI_BOOT_ETH_FLAGS: + case ISCSI_BOOT_ETH_MAC: + case ISCSI_BOOT_ETH_INDEX: + case ISCSI_BOOT_ETH_IP_ADDR: + case ISCSI_BOOT_ETH_SUBNET_MASK: + case ISCSI_BOOT_ETH_GATEWAY: + case ISCSI_BOOT_ETH_ORIGIN: + case ISCSI_BOOT_ETH_VLAN: + rc = 0444; + break; + default: + rc = 0; + break; + } + return rc; +} + +static ssize_t qedi_show_boot_ini_info(void *data, int type, char *buf) +{ + struct qedi_ctx *qedi = data; + struct nvm_iscsi_initiator *initiator; + char *str = buf; + int rc; + struct nvm_iscsi_block *block; + + block = qedi_get_nvram_block(qedi); + if (!block) + return 0; + + initiator = &block->initiator; + + switch (type) { + case ISCSI_BOOT_INI_INITIATOR_NAME: + rc = snprintf(str, NVM_ISCSI_CFG_ISCSI_NAME_MAX_LEN, "%s\n", + initiator->initiator_name.byte); + break; + default: + rc = 0; + break; + } + return rc; +} + +static umode_t qedi_ini_get_attr_visibility(void *data, int type) +{ + int rc; + + switch (type) { + case ISCSI_BOOT_INI_INITIATOR_NAME: + rc = 0444; + break; + default: + rc = 0; + break; + } + return rc; +} + +static ssize_t +qedi_show_boot_tgt_info(struct qedi_ctx *qedi, int type, + char *buf, enum qedi_nvm_tgts idx) +{ + char *str = buf; + int rc = 1; + u32 ctrl_flags, ipv6_en, chap_en, mchap_en, ip_len; + struct nvm_iscsi_block *block; + char *chap_name, *chap_secret; + char *mchap_name, *mchap_secret; + + block = qedi_get_nvram_block(qedi); + if (!block) + goto exit_show_tgt_info; + + QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_EVT, + "Port:%d, tgt_idx:%d\n", + GET_FIELD2(block->id, NVM_ISCSI_CFG_BLK_MAPPED_PF_ID), idx); + + ctrl_flags = block->target[idx].ctrl_flags & + NVM_ISCSI_CFG_TARGET_ENABLED; + + if (!ctrl_flags) { + QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_EVT, + "Target disabled\n"); + goto exit_show_tgt_info; + } + + ipv6_en = block->generic.ctrl_flags & + NVM_ISCSI_CFG_GEN_IPV6_ENABLED; + ip_len = ipv6_en ? IPV6_LEN : IPV4_LEN; + chap_en = block->generic.ctrl_flags & + NVM_ISCSI_CFG_GEN_CHAP_ENABLED; + chap_name = chap_en ? block->initiator.chap_name.byte : NULL; + chap_secret = chap_en ? block->initiator.chap_password.byte : NULL; + + mchap_en = block->generic.ctrl_flags & + NVM_ISCSI_CFG_GEN_CHAP_MUTUAL_ENABLED; + mchap_name = mchap_en ? block->target[idx].chap_name.byte : NULL; + mchap_secret = mchap_en ? block->target[idx].chap_password.byte : NULL; + + switch (type) { + case ISCSI_BOOT_TGT_NAME: + rc = snprintf(str, NVM_ISCSI_CFG_ISCSI_NAME_MAX_LEN, "%s\n", + block->target[idx].target_name.byte); + break; + case ISCSI_BOOT_TGT_IP_ADDR: + if (ipv6_en) + rc = snprintf(str, ip_len, "%pI6\n", + block->target[idx].ipv6_addr.byte); + else + rc = snprintf(str, ip_len, "%pI4\n", + block->target[idx].ipv4_addr.byte); + break; + case ISCSI_BOOT_TGT_PORT: + rc = snprintf(str, 12, "%d\n", + GET_FIELD2(block->target[idx].generic_cont0, + NVM_ISCSI_CFG_TARGET_TCP_PORT)); + break; + case ISCSI_BOOT_TGT_LUN: + rc = snprintf(str, 22, "%.*d\n", + block->target[idx].lun.value[1], + block->target[idx].lun.value[0]); + break; + case ISCSI_BOOT_TGT_CHAP_NAME: + rc = snprintf(str, NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN, "%s\n", + chap_name); + break; + case ISCSI_BOOT_TGT_CHAP_SECRET: + rc = snprintf(str, NVM_ISCSI_CFG_CHAP_PWD_MAX_LEN, "%s\n", + chap_secret); + break; + case ISCSI_BOOT_TGT_REV_CHAP_NAME: + rc = snprintf(str, NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN, "%s\n", + mchap_name); + break; + case ISCSI_BOOT_TGT_REV_CHAP_SECRET: + rc = snprintf(str, NVM_ISCSI_CFG_CHAP_PWD_MAX_LEN, "%s\n", + mchap_secret); + break; + case ISCSI_BOOT_TGT_FLAGS: + rc = snprintf(str, 3, "%hhd\n", SYSFS_FLAG_FW_SEL_BOOT); + break; + case ISCSI_BOOT_TGT_NIC_ASSOC: + rc = snprintf(str, 3, "0\n"); + break; + default: + rc = 0; + break; + } + +exit_show_tgt_info: + return rc; +} + +static ssize_t qedi_show_boot_tgt_pri_info(void *data, int type, char *buf) +{ + struct qedi_ctx *qedi = data; + + return qedi_show_boot_tgt_info(qedi, type, buf, QEDI_NVM_TGT_PRI); +} + +static ssize_t qedi_show_boot_tgt_sec_info(void *data, int type, char *buf) +{ + struct qedi_ctx *qedi = data; + + return qedi_show_boot_tgt_info(qedi, type, buf, QEDI_NVM_TGT_SEC); +} + +static umode_t qedi_tgt_get_attr_visibility(void *data, int type) +{ + int rc; + + switch (type) { + case ISCSI_BOOT_TGT_NAME: + case ISCSI_BOOT_TGT_IP_ADDR: + case ISCSI_BOOT_TGT_PORT: + case ISCSI_BOOT_TGT_LUN: + case ISCSI_BOOT_TGT_CHAP_NAME: + case ISCSI_BOOT_TGT_CHAP_SECRET: + case ISCSI_BOOT_TGT_REV_CHAP_NAME: + case ISCSI_BOOT_TGT_REV_CHAP_SECRET: + case ISCSI_BOOT_TGT_NIC_ASSOC: + case ISCSI_BOOT_TGT_FLAGS: + rc = 0444; + break; + default: + rc = 0; + break; + } + return rc; +} + +static void qedi_boot_release(void *data) +{ + struct qedi_ctx *qedi = data; + + scsi_host_put(qedi->shost); +} + +static int qedi_get_boot_info(struct qedi_ctx *qedi) +{ + int ret = 1; + u16 len; + + len = sizeof(struct nvm_iscsi_cfg); + + QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO, + "Get NVM iSCSI CFG image\n"); + ret = qedi_ops->common->nvm_get_image(qedi->cdev, + QED_NVM_IMAGE_ISCSI_CFG, + (char *)qedi->iscsi_cfg, len); + if (ret) + QEDI_ERR(&qedi->dbg_ctx, + "Could not get NVM image. ret = %d\n", ret); + + return ret; +} + +static int qedi_setup_boot_info(struct qedi_ctx *qedi) +{ + struct iscsi_boot_kobj *boot_kobj; + + if (qedi_get_boot_info(qedi)) + return -EPERM; + + qedi->boot_kset = iscsi_boot_create_host_kset(qedi->shost->host_no); + if (!qedi->boot_kset) + goto kset_free; + + if (!scsi_host_get(qedi->shost)) + goto kset_free; + + boot_kobj = iscsi_boot_create_target(qedi->boot_kset, 0, qedi, + qedi_show_boot_tgt_pri_info, + qedi_tgt_get_attr_visibility, + qedi_boot_release); + if (!boot_kobj) + goto put_host; + + if (!scsi_host_get(qedi->shost)) + goto kset_free; + + boot_kobj = iscsi_boot_create_target(qedi->boot_kset, 1, qedi, + qedi_show_boot_tgt_sec_info, + qedi_tgt_get_attr_visibility, + qedi_boot_release); + if (!boot_kobj) + goto put_host; + + if (!scsi_host_get(qedi->shost)) + goto kset_free; + + boot_kobj = iscsi_boot_create_initiator(qedi->boot_kset, 0, qedi, + qedi_show_boot_ini_info, + qedi_ini_get_attr_visibility, + qedi_boot_release); + if (!boot_kobj) + goto put_host; + + if (!scsi_host_get(qedi->shost)) + goto kset_free; + + boot_kobj = iscsi_boot_create_ethernet(qedi->boot_kset, 0, qedi, + qedi_show_boot_eth_info, + qedi_eth_get_attr_visibility, + qedi_boot_release); + if (!boot_kobj) + goto put_host; + + return 0; + +put_host: + scsi_host_put(qedi->shost); +kset_free: + iscsi_boot_destroy_kset(qedi->boot_kset); + return -ENOMEM; +} + static void __qedi_remove(struct pci_dev *pdev, int mode) { struct qedi_ctx *qedi = pci_get_drvdata(pdev); @@ -1724,6 +2136,9 @@ static void __qedi_remove(struct pci_dev *pdev, int mode) qedi->ll2_recv_thread = NULL; } qedi_ll2_free_skbs(qedi); + + if (qedi->boot_kset) + iscsi_boot_destroy_kset(qedi->boot_kset); } } @@ -1967,6 +2382,10 @@ static int __qedi_probe(struct pci_dev *pdev, int mode) /* F/w needs 1st task context memory entry for performance */ set_bit(QEDI_RESERVE_TASK_ID, qedi->task_idx_map); atomic_set(&qedi->num_offloads, 0); + + if (qedi_setup_boot_info(qedi)) + QEDI_ERR(&qedi->dbg_ctx, + "No iSCSI boot target configured\n"); } return 0; diff --git a/drivers/scsi/qedi/qedi_nvm_iscsi_cfg.h b/drivers/scsi/qedi/qedi_nvm_iscsi_cfg.h new file mode 100644 index 000000000000..df39b69b366d --- /dev/null +++ b/drivers/scsi/qedi/qedi_nvm_iscsi_cfg.h @@ -0,0 +1,210 @@ +/* + * QLogic iSCSI Offload Driver + * Copyright (c) 2016 Cavium Inc. + * + * This software is available under the terms of the GNU General Public License + * (GPL) Version 2, available from the file COPYING in the main directory of + * this source tree. + */ + +#ifndef NVM_ISCSI_CFG_H +#define NVM_ISCSI_CFG_H + +#define NUM_OF_ISCSI_TARGET_PER_PF 4 /* Defined as per the + * ISCSI IBFT constraint + */ +#define NUM_OF_ISCSI_PF_SUPPORTED 4 /* One PF per Port - + * assuming 4 port card + */ + +#define NVM_ISCSI_CFG_DHCP_NAME_MAX_LEN 256 + +union nvm_iscsi_dhcp_vendor_id { + u32 value[NVM_ISCSI_CFG_DHCP_NAME_MAX_LEN / 4]; + u8 byte[NVM_ISCSI_CFG_DHCP_NAME_MAX_LEN]; +}; + +#define NVM_ISCSI_IPV4_ADDR_BYTE_LEN 4 +union nvm_iscsi_ipv4_addr { + u32 addr; + u8 byte[NVM_ISCSI_IPV4_ADDR_BYTE_LEN]; +}; + +#define NVM_ISCSI_IPV6_ADDR_BYTE_LEN 16 +union nvm_iscsi_ipv6_addr { + u32 addr[4]; + u8 byte[NVM_ISCSI_IPV6_ADDR_BYTE_LEN]; +}; + +struct nvm_iscsi_initiator_ipv4 { + union nvm_iscsi_ipv4_addr addr; /* 0x0 */ + union nvm_iscsi_ipv4_addr subnet_mask; /* 0x4 */ + union nvm_iscsi_ipv4_addr gateway; /* 0x8 */ + union nvm_iscsi_ipv4_addr primary_dns; /* 0xC */ + union nvm_iscsi_ipv4_addr secondary_dns; /* 0x10 */ + union nvm_iscsi_ipv4_addr dhcp_addr; /* 0x14 */ + + union nvm_iscsi_ipv4_addr isns_server; /* 0x18 */ + union nvm_iscsi_ipv4_addr slp_server; /* 0x1C */ + union nvm_iscsi_ipv4_addr primay_radius_server; /* 0x20 */ + union nvm_iscsi_ipv4_addr secondary_radius_server; /* 0x24 */ + + union nvm_iscsi_ipv4_addr rsvd[4]; /* 0x28 */ +}; + +struct nvm_iscsi_initiator_ipv6 { + union nvm_iscsi_ipv6_addr addr; /* 0x0 */ + union nvm_iscsi_ipv6_addr subnet_mask; /* 0x10 */ + union nvm_iscsi_ipv6_addr gateway; /* 0x20 */ + union nvm_iscsi_ipv6_addr primary_dns; /* 0x30 */ + union nvm_iscsi_ipv6_addr secondary_dns; /* 0x40 */ + union nvm_iscsi_ipv6_addr dhcp_addr; /* 0x50 */ + + union nvm_iscsi_ipv6_addr isns_server; /* 0x60 */ + union nvm_iscsi_ipv6_addr slp_server; /* 0x70 */ + union nvm_iscsi_ipv6_addr primay_radius_server; /* 0x80 */ + union nvm_iscsi_ipv6_addr secondary_radius_server; /* 0x90 */ + + union nvm_iscsi_ipv6_addr rsvd[3]; /* 0xA0 */ + + u32 config; /* 0xD0 */ +#define NVM_ISCSI_CFG_INITIATOR_IPV6_SUBNET_MASK_PREFIX_MASK 0x000000FF +#define NVM_ISCSI_CFG_INITIATOR_IPV6_SUBNET_MASK_PREFIX_OFFSET 0 + + u32 rsvd_1[3]; +}; + +#define NVM_ISCSI_CFG_ISCSI_NAME_MAX_LEN 256 +union nvm_iscsi_name { + u32 value[NVM_ISCSI_CFG_ISCSI_NAME_MAX_LEN / 4]; + u8 byte[NVM_ISCSI_CFG_ISCSI_NAME_MAX_LEN]; +}; + +#define NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN 256 +union nvm_iscsi_chap_name { + u32 value[NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN / 4]; + u8 byte[NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN]; +}; + +#define NVM_ISCSI_CFG_CHAP_PWD_MAX_LEN 16 /* md5 need per RFC1996 + * is 16 octets + */ +union nvm_iscsi_chap_password { + u32 value[NVM_ISCSI_CFG_CHAP_PWD_MAX_LEN / 4]; + u8 byte[NVM_ISCSI_CFG_CHAP_PWD_MAX_LEN]; +}; + +union nvm_iscsi_lun { + u8 byte[8]; + u32 value[2]; +}; + +struct nvm_iscsi_generic { + u32 ctrl_flags; /* 0x0 */ +#define NVM_ISCSI_CFG_GEN_CHAP_ENABLED BIT(0) +#define NVM_ISCSI_CFG_GEN_DHCP_TCPIP_CONFIG_ENABLED BIT(1) +#define NVM_ISCSI_CFG_GEN_DHCP_ISCSI_CONFIG_ENABLED BIT(2) +#define NVM_ISCSI_CFG_GEN_IPV6_ENABLED BIT(3) +#define NVM_ISCSI_CFG_GEN_IPV4_FALLBACK_ENABLED BIT(4) +#define NVM_ISCSI_CFG_GEN_ISNS_WORLD_LOGIN BIT(5) +#define NVM_ISCSI_CFG_GEN_ISNS_SELECTIVE_LOGIN BIT(6) +#define NVM_ISCSI_CFG_GEN_ADDR_REDIRECT_ENABLED BIT(7) +#define NVM_ISCSI_CFG_GEN_CHAP_MUTUAL_ENABLED BIT(8) + + u32 timeout; /* 0x4 */ +#define NVM_ISCSI_CFG_GEN_DHCP_REQUEST_TIMEOUT_MASK 0x0000FFFF +#define NVM_ISCSI_CFG_GEN_DHCP_REQUEST_TIMEOUT_OFFSET 0 +#define NVM_ISCSI_CFG_GEN_PORT_LOGIN_TIMEOUT_MASK 0xFFFF0000 +#define NVM_ISCSI_CFG_GEN_PORT_LOGIN_TIMEOUT_OFFSET 16 + + union nvm_iscsi_dhcp_vendor_id dhcp_vendor_id; /* 0x8 */ + u32 rsvd[62]; /* 0x108 */ +}; + +struct nvm_iscsi_initiator { + struct nvm_iscsi_initiator_ipv4 ipv4; /* 0x0 */ + struct nvm_iscsi_initiator_ipv6 ipv6; /* 0x38 */ + + union nvm_iscsi_name initiator_name; /* 0x118 */ + union nvm_iscsi_chap_name chap_name; /* 0x218 */ + union nvm_iscsi_chap_password chap_password; /* 0x318 */ + + u32 generic_cont0; /* 0x398 */ +#define NVM_ISCSI_CFG_INITIATOR_VLAN_MASK 0x0000FFFF +#define NVM_ISCSI_CFG_INITIATOR_VLAN_OFFSET 0 +#define NVM_ISCSI_CFG_INITIATOR_IP_VERSION_MASK 0x00030000 +#define NVM_ISCSI_CFG_INITIATOR_IP_VERSION_OFFSET 16 +#define NVM_ISCSI_CFG_INITIATOR_IP_VERSION_4 1 +#define NVM_ISCSI_CFG_INITIATOR_IP_VERSION_6 2 +#define NVM_ISCSI_CFG_INITIATOR_IP_VERSION_4_AND_6 3 + + u32 ctrl_flags; +#define NVM_ISCSI_CFG_INITIATOR_IP_VERSION_PRIORITY_V6 BIT(0) +#define NVM_ISCSI_CFG_INITIATOR_VLAN_ENABLED BIT(1) + + u32 rsvd[116]; /* 0x32C */ +}; + +struct nvm_iscsi_target { + u32 ctrl_flags; /* 0x0 */ +#define NVM_ISCSI_CFG_TARGET_ENABLED BIT(0) +#define NVM_ISCSI_CFG_BOOT_TIME_LOGIN_STATUS BIT(1) + + u32 generic_cont0; /* 0x4 */ +#define NVM_ISCSI_CFG_TARGET_TCP_PORT_MASK 0x0000FFFF +#define NVM_ISCSI_CFG_TARGET_TCP_PORT_OFFSET 0 + + u32 ip_ver; +#define NVM_ISCSI_CFG_IPv4 4 +#define NVM_ISCSI_CFG_IPv6 6 + + u32 rsvd_1[7]; /* 0x24 */ + union nvm_iscsi_ipv4_addr ipv4_addr; /* 0x28 */ + union nvm_iscsi_ipv6_addr ipv6_addr; /* 0x2C */ + union nvm_iscsi_lun lun; /* 0x3C */ + + union nvm_iscsi_name target_name; /* 0x44 */ + union nvm_iscsi_chap_name chap_name; /* 0x144 */ + union nvm_iscsi_chap_password chap_password; /* 0x244 */ + + u32 rsvd_2[107]; /* 0x2C4 */ +}; + +struct nvm_iscsi_block { + u32 id; /* 0x0 */ +#define NVM_ISCSI_CFG_BLK_MAPPED_PF_ID_MASK 0x0000000F +#define NVM_ISCSI_CFG_BLK_MAPPED_PF_ID_OFFSET 0 +#define NVM_ISCSI_CFG_BLK_CTRL_FLAG_MASK 0x00000FF0 +#define NVM_ISCSI_CFG_BLK_CTRL_FLAG_OFFSET 4 +#define NVM_ISCSI_CFG_BLK_CTRL_FLAG_IS_NOT_EMPTY BIT(0) +#define NVM_ISCSI_CFG_BLK_CTRL_FLAG_PF_MAPPED BIT(1) + + u32 rsvd_1[5]; /* 0x4 */ + + struct nvm_iscsi_generic generic; /* 0x18 */ + struct nvm_iscsi_initiator initiator; /* 0x218 */ + struct nvm_iscsi_target target[NUM_OF_ISCSI_TARGET_PER_PF]; + /* 0x718 */ + + u32 rsvd_2[58]; /* 0x1718 */ + /* total size - 0x1800 - 6K block */ +}; + +struct nvm_iscsi_cfg { + u32 id; /* 0x0 */ +#define NVM_ISCSI_CFG_BLK_VERSION_MINOR_MASK 0x000000FF +#define NVM_ISCSI_CFG_BLK_VERSION_MAJOR_MASK 0x0000FF00 +#define NVM_ISCSI_CFG_BLK_SIGNATURE_MASK 0xFFFF0000 +#define NVM_ISCSI_CFG_BLK_SIGNATURE 0x49430000 /* IC - Iscsi + * Config + */ + +#define NVM_ISCSI_CFG_BLK_VERSION_MAJOR 0 +#define NVM_ISCSI_CFG_BLK_VERSION_MINOR 10 +#define NVM_ISCSI_CFG_BLK_VERSION ((NVM_ISCSI_CFG_BLK_VERSION_MAJOR << 8) | \ + NVM_ISCSI_CFG_BLK_VERSION_MINOR) + + struct nvm_iscsi_block block[NUM_OF_ISCSI_PF_SUPPORTED]; /* 0x4 */ +}; + +#endif diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index c2dc836dc484..e101cd3043b9 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -3727,7 +3727,7 @@ static struct qla_tgt_cmd *qlt_ctio_to_cmd(struct scsi_qla_host *vha, h &= QLA_CMD_HANDLE_MASK; if (h != QLA_TGT_NULL_HANDLE) { - if (unlikely(h > req->num_outstanding_cmds)) { + if (unlikely(h >= req->num_outstanding_cmds)) { ql_dbg(ql_dbg_tgt, vha, 0xe052, "qla_target(%d): Wrong handle %x received\n", vha->vp_idx, handle); diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 21225d62b0c1..1e82d4128a84 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -758,8 +758,11 @@ static bool sg_is_valid_dxfer(sg_io_hdr_t *hp) if (hp->dxferp || hp->dxfer_len > 0) return false; return true; - case SG_DXFER_TO_DEV: case SG_DXFER_FROM_DEV: + if (hp->dxfer_len < 0) + return false; + return true; + case SG_DXFER_TO_DEV: case SG_DXFER_TO_FROM_DEV: if (!hp->dxferp || hp->dxfer_len == 0) return false; diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c index 8b93197daefe..9be211d68b15 100644 --- a/drivers/scsi/virtio_scsi.c +++ b/drivers/scsi/virtio_scsi.c @@ -837,6 +837,7 @@ static struct scsi_host_template virtscsi_host_template_multi = { .eh_abort_handler = virtscsi_abort, .eh_device_reset_handler = virtscsi_device_reset, .eh_timed_out = virtscsi_eh_timed_out, + .slave_alloc = virtscsi_device_alloc, .can_queue = 1024, .dma_boundary = UINT_MAX, diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index e071d23f6148..ef7240ace576 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -271,6 +271,11 @@ out: if (ret < 0) err = ret; dput(last); + /* last_name no longer match cache index */ + if (fi->readdir_cache_idx >= 0) { + fi->readdir_cache_idx = -1; + fi->dir_release_count = 0; + } } return err; } diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c index a140c5e3dc54..b4b8438c42ef 100644 --- a/fs/f2fs/acl.c +++ b/fs/f2fs/acl.c @@ -211,7 +211,7 @@ static int __f2fs_set_acl(struct inode *inode, int type, switch (type) { case ACL_TYPE_ACCESS: name_index = F2FS_XATTR_INDEX_POSIX_ACL_ACCESS; - if (acl) { + if (acl && !ipage) { error = posix_acl_update_mode(inode, &inode->i_mode, &acl); if (error) return error; diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 56bbf592e487..5b876f6d3f6b 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -879,6 +879,7 @@ int sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type) struct inode *inode; struct f2fs_inode_info *fi; bool is_dir = (type == DIR_INODE); + unsigned long ino = 0; trace_f2fs_sync_dirty_inodes_enter(sbi->sb, is_dir, get_pages(sbi, is_dir ? @@ -901,8 +902,17 @@ retry: inode = igrab(&fi->vfs_inode); spin_unlock(&sbi->inode_lock[type]); if (inode) { + unsigned long cur_ino = inode->i_ino; + filemap_fdatawrite(inode->i_mapping); iput(inode); + /* We need to give cpu to another writers. */ + if (ino == cur_ino) { + congestion_wait(BLK_RW_ASYNC, HZ/50); + cond_resched(); + } else { + ino = cur_ino; + } } else { /* * We should submit bio, since it exists several diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index a0e6d2c65a9e..2706130c261b 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -1538,7 +1538,6 @@ static int f2fs_ioc_setflags(struct file *filp, unsigned long arg) /* Is it quota file? Do not allow user to mess with it */ if (IS_NOQUOTA(inode)) { - inode_unlock(inode); ret = -EPERM; goto unlock_out; } @@ -1549,9 +1548,8 @@ static int f2fs_ioc_setflags(struct file *filp, unsigned long arg) if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL)) { if (!capable(CAP_LINUX_IMMUTABLE)) { - inode_unlock(inode); ret = -EPERM; - goto out; + goto unlock_out; } } @@ -1564,7 +1562,6 @@ static int f2fs_ioc_setflags(struct file *filp, unsigned long arg) f2fs_mark_inode_dirty_sync(inode, false); unlock_out: inode_unlock(inode); -out: mnt_drop_write_file(filp); return ret; } diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index 9adc202fcd6f..71191d89917d 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -11,6 +11,7 @@ */ #include <linux/proc_fs.h> #include <linux/f2fs_fs.h> +#include <linux/seq_file.h> #include "f2fs.h" #include "segment.h" diff --git a/fs/mount.h b/fs/mount.h index de45d9e76748..6790767d1883 100644 --- a/fs/mount.h +++ b/fs/mount.h @@ -16,7 +16,7 @@ struct mnt_namespace { u64 event; unsigned int mounts; /* # of mounts in the namespace */ unsigned int pending_mounts; -}; +} __randomize_layout; struct mnt_pcp { int mnt_count; @@ -69,7 +69,7 @@ struct mount { struct hlist_head mnt_pins; struct fs_pin mnt_umount; struct dentry *mnt_ex_mountpoint; -}; +} __randomize_layout; #define MNT_NS_INTERNAL ERR_PTR(-EINVAL) /* distinct from any mnt_namespace */ diff --git a/fs/namei.c b/fs/namei.c index 88fd38d1e3e7..ddb6a7c2b3d4 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -524,7 +524,7 @@ struct nameidata { struct inode *link_inode; unsigned root_seq; int dfd; -}; +} __randomize_layout; static void set_nameidata(struct nameidata *p, int dfd, struct filename *name) { diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index b45083c0f9ae..49b0a9e7ff18 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -720,8 +720,8 @@ static const struct rpc_version nfs_cb_version4 = { .counts = nfs4_cb_counts, }; -static const struct rpc_version *nfs_cb_version[] = { - &nfs_cb_version4, +static const struct rpc_version *nfs_cb_version[2] = { + [1] = &nfs_cb_version4, }; static const struct rpc_program cb_program; @@ -795,7 +795,7 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c .saddress = (struct sockaddr *) &conn->cb_saddr, .timeout = &timeparms, .program = &cb_program, - .version = 0, + .version = 1, .flags = (RPC_CLNT_CREATE_NOPING | RPC_CLNT_CREATE_QUIET), }; struct rpc_clnt *client; diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 18694598bebf..aa2b89071630 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -51,7 +51,7 @@ struct proc_dir_entry { spinlock_t pde_unload_lock; /* proc_fops checks and pde_users bumps */ u8 namelen; char name[]; -}; +} __randomize_layout; union proc_op { int (*proc_get_link)(struct dentry *, struct path *); @@ -70,7 +70,7 @@ struct proc_inode { struct hlist_node sysctl_inodes; const struct proc_ns_operations *ns_ops; struct inode vfs_inode; -}; +} __randomize_layout; /* * General functions @@ -279,7 +279,7 @@ struct proc_maps_private { #ifdef CONFIG_NUMA struct mempolicy *task_mempolicy; #endif -}; +} __randomize_layout; struct mm_struct *proc_mem_open(struct inode *inode, unsigned int mode); diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 05488da3aee9..3ae9013eeaaa 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -46,7 +46,7 @@ struct linux_binprm { unsigned interp_flags; unsigned interp_data; unsigned long loader, exec; -}; +} __randomize_layout; #define BINPRM_FLAGS_ENFORCE_NONDUMP_BIT 0 #define BINPRM_FLAGS_ENFORCE_NONDUMP (1 << BINPRM_FLAGS_ENFORCE_NONDUMP_BIT) @@ -81,7 +81,7 @@ struct linux_binfmt { int (*load_shlib)(struct file *); int (*core_dump)(struct coredump_params *cprm); unsigned long min_coredump; /* minimal dump size */ -}; +} __randomize_layout; extern void __register_binfmt(struct linux_binfmt *fmt, int insert); diff --git a/include/linux/cdev.h b/include/linux/cdev.h index 408bc09ce497..cb28eb21e3ca 100644 --- a/include/linux/cdev.h +++ b/include/linux/cdev.h @@ -17,7 +17,7 @@ struct cdev { struct list_head list; dev_t dev; unsigned int count; -}; +} __randomize_layout; void cdev_init(struct cdev *, const struct file_operations *); diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index f0f6c537b64c..040dd105c3e7 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -10,14 +10,14 @@ #define CEPH_FEATURE_INCARNATION_2 (1ull<<57) // CEPH_FEATURE_SERVER_JEWEL #define DEFINE_CEPH_FEATURE(bit, incarnation, name) \ - const static uint64_t CEPH_FEATURE_##name = (1ULL<<bit); \ - const static uint64_t CEPH_FEATUREMASK_##name = \ + static const uint64_t CEPH_FEATURE_##name = (1ULL<<bit); \ + static const uint64_t CEPH_FEATUREMASK_##name = \ (1ULL<<bit | CEPH_FEATURE_INCARNATION_##incarnation); /* this bit is ignored but still advertised by release *when* */ #define DEFINE_CEPH_FEATURE_DEPRECATED(bit, incarnation, name, when) \ - const static uint64_t DEPRECATED_CEPH_FEATURE_##name = (1ULL<<bit); \ - const static uint64_t DEPRECATED_CEPH_FEATUREMASK_##name = \ + static const uint64_t DEPRECATED_CEPH_FEATURE_##name = (1ULL<<bit); \ + static const uint64_t DEPRECATED_CEPH_FEATUREMASK_##name = \ (1ULL<<bit | CEPH_FEATURE_INCARNATION_##incarnation); /* diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index cd4bbe8242bd..bdb80c4aef6e 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -235,6 +235,7 @@ #endif /* GCC_VERSION >= 40500 */ #if GCC_VERSION >= 40600 + /* * When used with Link Time Optimization, gcc can optimize away C functions or * variables which are referenced only from assembly code. __visible tells the @@ -242,7 +243,17 @@ * this. */ #define __visible __attribute__((externally_visible)) -#endif + +/* + * RANDSTRUCT_PLUGIN wants to use an anonymous struct, but it is only + * possible since GCC 4.6. To provide as much build testing coverage + * as possible, this is used for all GCC 4.6+ builds, and not just on + * RANDSTRUCT_PLUGIN builds. + */ +#define randomized_struct_fields_start struct { +#define randomized_struct_fields_end } __randomize_layout; + +#endif /* GCC_VERSION >= 40600 */ #if GCC_VERSION >= 40900 && !defined(__CHECKER__) diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 219f82f3ec1a..eca8ad75e28b 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -452,6 +452,11 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s # define __no_randomize_layout #endif +#ifndef randomized_struct_fields_start +# define randomized_struct_fields_start +# define randomized_struct_fields_end +#endif + /* * Tell gcc if a function is cold. The compiler will assume any path * directly leading to the call is unlikely. diff --git a/include/linux/cred.h b/include/linux/cred.h index c728d515e5e2..099058e1178b 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -31,7 +31,7 @@ struct group_info { atomic_t usage; int ngroups; kgid_t gid[0]; -}; +} __randomize_layout; /** * get_group_info - Get a reference to a group info structure @@ -145,7 +145,7 @@ struct cred { struct user_namespace *user_ns; /* user_ns the caps and keyrings are relative to. */ struct group_info *group_info; /* supplementary groups for euid/fsgid */ struct rcu_head rcu; /* RCU deletion hook */ -}; +} __randomize_layout; extern void __put_cred(struct cred *); extern void exit_creds(struct task_struct *); diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 3f3ff4ccdc3f..aae1cdb76851 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -118,7 +118,7 @@ struct dentry { struct hlist_bl_node d_in_lookup_hash; /* only for in-lookup ones */ struct rcu_head d_rcu; } d_u; -}; +} __randomize_layout; /* * dentry->d_lock spinlock nesting subclasses: diff --git a/include/linux/fs.h b/include/linux/fs.h index 7b5d6816542b..6e1fd5d21248 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -296,7 +296,7 @@ struct kiocb { void *private; int ki_flags; enum rw_hint ki_hint; -}; +} __randomize_layout; static inline bool is_sync_kiocb(struct kiocb *kiocb) { @@ -404,7 +404,7 @@ struct address_space { struct list_head private_list; /* ditto */ void *private_data; /* ditto */ errseq_t wb_err; -} __attribute__((aligned(sizeof(long)))); +} __attribute__((aligned(sizeof(long)))) __randomize_layout; /* * On most architectures that alignment is already the case; but * must be enforced here for CRIS, to let the least significant bit @@ -447,7 +447,7 @@ struct block_device { int bd_fsfreeze_count; /* Mutex for freeze */ struct mutex bd_fsfreeze_mutex; -}; +} __randomize_layout; /* * Radix-tree tags, for tagging dirty and writeback pages within the pagecache @@ -666,7 +666,7 @@ struct inode { #endif void *i_private; /* fs or device private pointer */ -}; +} __randomize_layout; static inline unsigned int i_blocksize(const struct inode *node) { @@ -883,7 +883,8 @@ struct file { #endif /* #ifdef CONFIG_EPOLL */ struct address_space *f_mapping; errseq_t f_wb_err; -} __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */ +} __randomize_layout + __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */ struct file_handle { __u32 handle_bytes; @@ -1020,7 +1021,7 @@ struct file_lock { int state; /* state of grant or error if -ve */ } afs; } fl_u; -}; +} __randomize_layout; struct file_lock_context { spinlock_t flc_lock; @@ -1412,7 +1413,7 @@ struct super_block { spinlock_t s_inode_wblist_lock; struct list_head s_inodes_wb; /* writeback inodes */ -}; +} __randomize_layout; /* Helper functions so that in most cases filesystems will * not need to deal directly with kuid_t and kgid_t and can @@ -1698,7 +1699,7 @@ struct file_operations { u64); ssize_t (*dedupe_file_range)(struct file *, u64, u64, struct file *, u64); -}; +} __randomize_layout; struct inode_operations { struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h index 0efc3e62843a..7a026240cbb1 100644 --- a/include/linux/fs_struct.h +++ b/include/linux/fs_struct.h @@ -12,7 +12,7 @@ struct fs_struct { int umask; int in_exec; struct path root, pwd; -}; +} __randomize_layout; extern struct kmem_cache *fs_cachep; diff --git a/include/linux/ipc.h b/include/linux/ipc.h index 5591f055e13f..fadd579d577d 100644 --- a/include/linux/ipc.h +++ b/include/linux/ipc.h @@ -23,6 +23,6 @@ struct kern_ipc_perm { struct rcu_head rcu; atomic_t refcount; -} ____cacheline_aligned_in_smp; +} ____cacheline_aligned_in_smp __randomize_layout; #endif /* _LINUX_IPC_H */ diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index 848e5796400e..65327ee0936b 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -61,7 +61,7 @@ struct ipc_namespace { struct ucounts *ucounts; struct ns_common ns; -}; +} __randomize_layout; extern struct ipc_namespace init_ipc_ns; extern spinlock_t mq_lock; diff --git a/include/linux/key-type.h b/include/linux/key-type.h index 8496cf64575c..9520fc3c3b9a 100644 --- a/include/linux/key-type.h +++ b/include/linux/key-type.h @@ -45,7 +45,7 @@ struct key_preparsed_payload { size_t datalen; /* Raw datalen */ size_t quotalen; /* Quota length for proposed payload */ time_t expiry; /* Expiry time of key */ -}; +} __randomize_layout; typedef int (*request_key_actor_t)(struct key_construction *key, const char *op, void *aux); @@ -158,7 +158,7 @@ struct key_type { /* internal fields */ struct list_head link; /* link in types list */ struct lock_class_key lock_class; /* key->sem lock class */ -}; +} __randomize_layout; extern struct key_type key_type_keyring; diff --git a/include/linux/kmod.h b/include/linux/kmod.h index c4e441e00db5..655082c88fd9 100644 --- a/include/linux/kmod.h +++ b/include/linux/kmod.h @@ -64,7 +64,7 @@ struct subprocess_info { int (*init)(struct subprocess_info *info, struct cred *new); void (*cleanup)(struct subprocess_info *info); void *data; -}; +} __randomize_layout; extern int call_usermodehelper(const char *path, char **argv, char **envp, int wait); diff --git a/include/linux/kobject.h b/include/linux/kobject.h index eeab34b0f589..4d800c79475a 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -172,7 +172,7 @@ struct kset { spinlock_t list_lock; struct kobject kobj; const struct kset_uevent_ops *uevent_ops; -}; +} __randomize_layout; extern void kset_init(struct kset *kset); extern int __must_check kset_register(struct kset *kset); diff --git a/include/linux/llist.h b/include/linux/llist.h index d11738110a7a..1957635e6d5f 100644 --- a/include/linux/llist.h +++ b/include/linux/llist.h @@ -93,6 +93,23 @@ static inline void init_llist_head(struct llist_head *list) container_of(ptr, type, member) /** + * member_address_is_nonnull - check whether the member address is not NULL + * @ptr: the object pointer (struct type * that contains the llist_node) + * @member: the name of the llist_node within the struct. + * + * This macro is conceptually the same as + * &ptr->member != NULL + * but it works around the fact that compilers can decide that taking a member + * address is never a NULL pointer. + * + * Real objects that start at a high address and have a member at NULL are + * unlikely to exist, but such pointers may be returned e.g. by the + * container_of() macro. + */ +#define member_address_is_nonnull(ptr, member) \ + ((uintptr_t)(ptr) + offsetof(typeof(*(ptr)), member) != 0) + +/** * llist_for_each - iterate over some deleted entries of a lock-less list * @pos: the &struct llist_node to use as a loop cursor * @node: the first entry of deleted list entries @@ -145,7 +162,7 @@ static inline void init_llist_head(struct llist_head *list) */ #define llist_for_each_entry(pos, node, member) \ for ((pos) = llist_entry((node), typeof(*(pos)), member); \ - &(pos)->member != NULL; \ + member_address_is_nonnull(pos, member); \ (pos) = llist_entry((pos)->member.next, typeof(*(pos)), member)) /** @@ -167,7 +184,7 @@ static inline void init_llist_head(struct llist_head *list) */ #define llist_for_each_entry_safe(pos, n, node, member) \ for (pos = llist_entry((node), typeof(*pos), member); \ - &pos->member != NULL && \ + member_address_is_nonnull(pos, member) && \ (n = llist_entry(pos->member.next, typeof(*n), member), true); \ pos = n) diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 7a86925ba8f3..3a90febadbe2 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -1912,7 +1912,7 @@ struct security_hook_heads { struct list_head audit_rule_match; struct list_head audit_rule_free; #endif /* CONFIG_AUDIT */ -}; +} __randomize_layout; /* * Security module hook list structure. @@ -1923,7 +1923,7 @@ struct security_hook_list { struct list_head *head; union security_list_options hook; char *lsm; -}; +} __randomize_layout; /* * Initializing a security_hook_list structure takes diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index d5bed0875d30..aad5d81dfb44 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -1068,7 +1068,7 @@ static inline int mlx4_is_eth(struct mlx4_dev *dev, int port) } int mlx4_buf_alloc(struct mlx4_dev *dev, int size, int max_direct, - struct mlx4_buf *buf, gfp_t gfp); + struct mlx4_buf *buf); void mlx4_buf_free(struct mlx4_dev *dev, int size, struct mlx4_buf *buf); static inline void *mlx4_buf_offset(struct mlx4_buf *buf, int offset) { @@ -1105,10 +1105,9 @@ int mlx4_mw_enable(struct mlx4_dev *dev, struct mlx4_mw *mw); int mlx4_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt, int start_index, int npages, u64 *page_list); int mlx4_buf_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt, - struct mlx4_buf *buf, gfp_t gfp); + struct mlx4_buf *buf); -int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, int order, - gfp_t gfp); +int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, int order); void mlx4_db_free(struct mlx4_dev *dev, struct mlx4_db *db); int mlx4_alloc_hwq_res(struct mlx4_dev *dev, struct mlx4_hwq_resources *wqres, @@ -1124,8 +1123,7 @@ int mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align, int *base, u8 flags); void mlx4_qp_release_range(struct mlx4_dev *dev, int base_qpn, int cnt); -int mlx4_qp_alloc(struct mlx4_dev *dev, int qpn, struct mlx4_qp *qp, - gfp_t gfp); +int mlx4_qp_alloc(struct mlx4_dev *dev, int qpn, struct mlx4_qp *qp); void mlx4_qp_free(struct mlx4_dev *dev, struct mlx4_qp *qp); int mlx4_srq_alloc(struct mlx4_dev *dev, u32 pdn, u32 cqn, u16 xrcdn, diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 45cdb27791a3..ff151814a02d 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -342,7 +342,7 @@ struct vm_area_struct { struct mempolicy *vm_policy; /* NUMA policy for the VMA */ #endif struct vm_userfaultfd_ctx vm_userfaultfd_ctx; -}; +} __randomize_layout; struct core_thread { struct task_struct *task; @@ -500,7 +500,7 @@ struct mm_struct { atomic_long_t hugetlb_usage; #endif struct work_struct async_put_work; -}; +} __randomize_layout; extern struct mm_struct init_mm; diff --git a/include/linux/module.h b/include/linux/module.h index 8eb9a1e693e5..e7bdd549e527 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -45,7 +45,7 @@ struct module_kobject { struct kobject *drivers_dir; struct module_param_attrs *mp; struct completion *kobj_completion; -}; +} __randomize_layout; struct module_attribute { struct attribute attr; @@ -475,7 +475,7 @@ struct module { ctor_fn_t *ctors; unsigned int num_ctors; #endif -} ____cacheline_aligned; +} ____cacheline_aligned __randomize_layout; #ifndef MODULE_ARCH_INIT #define MODULE_ARCH_INIT {} #endif diff --git a/include/linux/mount.h b/include/linux/mount.h index 8e0352af06b7..1ce85e6fd95f 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -67,7 +67,7 @@ struct vfsmount { struct dentry *mnt_root; /* root of the mounted tree */ struct super_block *mnt_sb; /* pointer to superblock */ int mnt_flags; -}; +} __randomize_layout; struct file; /* forward dec */ struct path; diff --git a/include/linux/msg.h b/include/linux/msg.h index f3f302f9c197..a001305f5a79 100644 --- a/include/linux/msg.h +++ b/include/linux/msg.h @@ -29,7 +29,7 @@ struct msg_queue { struct list_head q_messages; struct list_head q_receivers; struct list_head q_senders; -}; +} __randomize_layout; /* Helper routines for sys_msgsnd and sys_msgrcv */ extern long do_msgsnd(int msqid, long mtype, void __user *mtext, diff --git a/include/linux/path.h b/include/linux/path.h index d1372186f431..cde895cc4af4 100644 --- a/include/linux/path.h +++ b/include/linux/path.h @@ -7,7 +7,7 @@ struct vfsmount; struct path { struct vfsmount *mnt; struct dentry *dentry; -}; +} __randomize_layout; extern void path_get(const struct path *); extern void path_put(const struct path *); diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index c2a989dee876..b09136f88cf4 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -52,7 +52,7 @@ struct pid_namespace { int hide_pid; int reboot; /* group exit code if this pidns was rebooted */ struct ns_common ns; -}; +} __randomize_layout; extern struct pid_namespace init_pid_ns; diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h index 58ab28d81fc2..06844b54dfc1 100644 --- a/include/linux/proc_ns.h +++ b/include/linux/proc_ns.h @@ -21,7 +21,7 @@ struct proc_ns_operations { int (*install)(struct nsproxy *nsproxy, struct ns_common *ns); struct user_namespace *(*owner)(struct ns_common *ns); struct ns_common *(*get_parent)(struct ns_common *ns); -}; +} __randomize_layout; extern const struct proc_ns_operations netns_operations; extern const struct proc_ns_operations utsns_operations; diff --git a/include/linux/sched.h b/include/linux/sched.h index 2ba9ec93423f..8337e2db0bb2 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -426,7 +426,7 @@ struct sched_rt_entity { /* rq "owned" by this entity/group: */ struct rt_rq *my_q; #endif -}; +} __randomize_layout; struct sched_dl_entity { struct rb_node rb_node; @@ -526,6 +526,13 @@ struct task_struct { #endif /* -1 unrunnable, 0 runnable, >0 stopped: */ volatile long state; + + /* + * This begins the randomizable portion of task_struct. Only + * scheduling-critical items should be added above here. + */ + randomized_struct_fields_start + void *stack; atomic_t usage; /* Per task flags (PF_*), defined further below: */ @@ -1079,6 +1086,13 @@ struct task_struct { /* Used by LSM modules for access restriction: */ void *security; #endif + + /* + * New fields for task_struct should be added above here, so that + * they are included in the randomized portion of task_struct. + */ + randomized_struct_fields_end + /* CPU-specific state of this task: */ struct thread_struct thread; diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index c06d63b3a583..2a0dd40b15db 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -222,7 +222,7 @@ struct signal_struct { struct mutex cred_guard_mutex; /* guard against foreign influences on * credential calculations * (notably. ptrace) */ -}; +} __randomize_layout; /* * Bits in flags field of signal_struct. diff --git a/include/linux/sem.h b/include/linux/sem.h index be5cf2ea14ad..de2deb8676bd 100644 --- a/include/linux/sem.h +++ b/include/linux/sem.h @@ -41,7 +41,7 @@ struct sem_array { unsigned int use_global_lock;/* >0: global lock required */ struct sem sems[]; -}; +} __randomize_layout; #ifdef CONFIG_SYSVIPC diff --git a/include/linux/shm.h b/include/linux/shm.h index 04e881829625..0fb7061ec54c 100644 --- a/include/linux/shm.h +++ b/include/linux/shm.h @@ -22,7 +22,7 @@ struct shmid_kernel /* private to the kernel */ /* The task created the shm object. NULL if the task is dead. */ struct task_struct *shm_creator; struct list_head shm_clist; /* list by creator */ -}; +} __randomize_layout; /* shm_mode upper byte flags */ #define SHM_DEST 01000 /* segment will be destroyed on last detach */ diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 3a89b9ff4cdc..1d4dba490fb6 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -120,7 +120,7 @@ struct ctl_table struct ctl_table_poll *poll; void *extra1; void *extra2; -}; +} __randomize_layout; struct ctl_node { struct rb_node node; diff --git a/include/linux/tty.h b/include/linux/tty.h index 69464c0d8068..79c30daf46a9 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -332,7 +332,7 @@ struct tty_struct { /* If the tty has a pending do_SAK, queue it here - akpm */ struct work_struct SAK_work; struct tty_port *port; -}; +} __randomize_layout; /* Each of a tty's open files has private_data pointing to tty_file_private */ struct tty_file_private { diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index b742b5e47cc2..00b2213f6a35 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -291,7 +291,7 @@ struct tty_operations { void (*poll_put_char)(struct tty_driver *driver, int line, char ch); #endif const struct file_operations *proc_fops; -}; +} __randomize_layout; struct tty_driver { int magic; /* magic number for this structure */ @@ -325,7 +325,7 @@ struct tty_driver { const struct tty_operations *ops; struct list_head tty_drivers; -}; +} __randomize_layout; extern struct list_head tty_drivers; diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 32354b4b4b2b..b3575ce29148 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -66,7 +66,7 @@ struct user_namespace { #endif struct ucounts *ucounts; int ucount_max[UCOUNT_COUNTS]; -}; +} __randomize_layout; struct ucounts { struct hlist_node node; diff --git a/include/linux/utsname.h b/include/linux/utsname.h index 60f0bb83b313..da826ed059cf 100644 --- a/include/linux/utsname.h +++ b/include/linux/utsname.h @@ -26,7 +26,7 @@ struct uts_namespace { struct user_namespace *user_ns; struct ucounts *ucounts; struct ns_common ns; -}; +} __randomize_layout; extern struct uts_namespace init_uts_ns; #ifdef CONFIG_UTS_NS diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 678e4d6fa317..53b1a2cca421 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -37,7 +37,7 @@ struct unix_skb_parms { u32 secid; /* Security ID */ #endif u32 consumed; -}; +} __randomize_layout; #define UNIXCB(skb) (*(struct unix_skb_parms *)&((skb)->cb)) diff --git a/include/net/neighbour.h b/include/net/neighbour.h index afc39e3a3f7c..9816df225af3 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -156,7 +156,7 @@ struct neighbour { struct rcu_head rcu; struct net_device *dev; u8 primary_key[0]; -}; +} __randomize_layout; struct neigh_ops { int family; diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 31a2b51bef2c..1c401bd4c2e0 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -148,7 +148,7 @@ struct net { #endif struct sock *diag_nlsk; atomic_t fnhe_genid; -}; +} __randomize_layout; #include <linux/seq_file_net.h> diff --git a/include/net/sock.h b/include/net/sock.h index f69c8c2782df..7c0632c7e870 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1128,7 +1128,7 @@ struct proto { atomic_t socks; #endif int (*diag_destroy)(struct sock *sk, int err); -}; +} __randomize_layout; int proto_register(struct proto *prot, int alloc_slab); void proto_unregister(struct proto *prot); diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 356953d3dbd1..b5732432bb29 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -1056,7 +1056,7 @@ enum ib_qp_create_flags { IB_QP_CREATE_MANAGED_RECV = 1 << 4, IB_QP_CREATE_NETIF_QP = 1 << 5, IB_QP_CREATE_SIGNATURE_EN = 1 << 6, - IB_QP_CREATE_USE_GFP_NOIO = 1 << 7, + /* FREE = 1 << 7, */ IB_QP_CREATE_SCATTER_FCS = 1 << 8, IB_QP_CREATE_CVLAN_STRIPPING = 1 << 9, /* reserve bits 26-31 for low level drivers' internal use */ @@ -2948,6 +2948,22 @@ struct ib_qp *ib_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *qp_init_attr); /** + * ib_modify_qp_with_udata - Modifies the attributes for the specified QP. + * @qp: The QP to modify. + * @attr: On input, specifies the QP attributes to modify. On output, + * the current values of selected QP attributes are returned. + * @attr_mask: A bit-mask used to specify which attributes of the QP + * are being modified. + * @udata: pointer to user's input output buffer information + * are being modified. + * It returns 0 on success and returns appropriate error code on error. + */ +int ib_modify_qp_with_udata(struct ib_qp *qp, + struct ib_qp_attr *attr, + int attr_mask, + struct ib_udata *udata); + +/** * ib_modify_qp - Modifies the attributes for the specified QP and then * transitions the QP to the given state. * @qp: The QP to modify. diff --git a/include/rdma/rdma_vt.h b/include/rdma/rdma_vt.h index 4878aaf7bdff..55af69271053 100644 --- a/include/rdma/rdma_vt.h +++ b/include/rdma/rdma_vt.h @@ -229,8 +229,7 @@ struct rvt_driver_provided { * ERR_PTR(err). The driver is free to return NULL or a valid * pointer. */ - void * (*qp_priv_alloc)(struct rvt_dev_info *rdi, struct rvt_qp *qp, - gfp_t gfp); + void * (*qp_priv_alloc)(struct rvt_dev_info *rdi, struct rvt_qp *qp); /* * Free the driver's private qp structure. @@ -319,7 +318,7 @@ struct rvt_driver_provided { /* Let the driver pick the next queue pair number*/ int (*alloc_qpn)(struct rvt_dev_info *rdi, struct rvt_qpn_table *qpt, - enum ib_qp_type type, u8 port_num, gfp_t gfp); + enum ib_qp_type type, u8 port_num); /* Determine if its safe or allowed to modify the qp */ int (*check_modify_qp)(struct rvt_qp *qp, struct ib_qp_attr *attr, diff --git a/kernel/audit.c b/kernel/audit.c index 833267bbd80b..6dd556931739 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -641,6 +641,7 @@ static int auditd_send_unicast_skb(struct sk_buff *skb) ac = rcu_dereference(auditd_conn); if (!ac) { rcu_read_unlock(); + kfree_skb(skb); rc = -ECONNREFUSED; goto err; } diff --git a/kernel/cpu.c b/kernel/cpu.c index ab860453841d..eee033134262 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -279,7 +279,8 @@ static int bringup_wait_for_ap(unsigned int cpu) /* Wait for the CPU to reach CPUHP_AP_ONLINE_IDLE */ wait_for_completion(&st->done); - BUG_ON(!cpu_online(cpu)); + if (WARN_ON_ONCE((!cpu_online(cpu)))) + return -ECANCELED; /* Unpark the stopper thread and the hotplug thread of the target cpu */ stop_machine_unpark(cpu); diff --git a/kernel/futex.c b/kernel/futex.c index c934689043b2..16dbe4c93895 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -212,7 +212,7 @@ struct futex_pi_state { atomic_t refcount; union futex_key key; -}; +} __randomize_layout; /** * struct futex_q - The hashed futex queue entry, one per waiting task @@ -246,7 +246,7 @@ struct futex_q { struct rt_mutex_waiter *rt_waiter; union futex_key *requeue_pi_key; u32 bitset; -}; +} __randomize_layout; static const struct futex_q futex_q_init = { /* list gets initialized in queue_me()*/ diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 5624b2dd6b58..1d1a5b945ab4 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1090,6 +1090,16 @@ setup_irq_thread(struct irqaction *new, unsigned int irq, bool secondary) /* * Internal function to register an irqaction - typically used to * allocate special interrupts that are part of the architecture. + * + * Locking rules: + * + * desc->request_mutex Provides serialization against a concurrent free_irq() + * chip_bus_lock Provides serialization for slow bus operations + * desc->lock Provides serialization against hard interrupts + * + * chip_bus_lock and desc->lock are sufficient for all other management and + * interrupt related functions. desc->request_mutex solely serializes + * request/free_irq(). */ static int __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) @@ -1167,20 +1177,35 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) if (desc->irq_data.chip->flags & IRQCHIP_ONESHOT_SAFE) new->flags &= ~IRQF_ONESHOT; + /* + * Protects against a concurrent __free_irq() call which might wait + * for synchronize_irq() to complete without holding the optional + * chip bus lock and desc->lock. + */ mutex_lock(&desc->request_mutex); + + /* + * Acquire bus lock as the irq_request_resources() callback below + * might rely on the serialization or the magic power management + * functions which are abusing the irq_bus_lock() callback, + */ + chip_bus_lock(desc); + + /* First installed action requests resources. */ if (!desc->action) { ret = irq_request_resources(desc); if (ret) { pr_err("Failed to request resources for %s (irq %d) on irqchip %s\n", new->name, irq, desc->irq_data.chip->name); - goto out_mutex; + goto out_bus_unlock; } } - chip_bus_lock(desc); - /* * The following block of code has to be executed atomically + * protected against a concurrent interrupt and any of the other + * management calls which are not serialized via + * desc->request_mutex or the optional bus lock. */ raw_spin_lock_irqsave(&desc->lock, flags); old_ptr = &desc->action; @@ -1286,10 +1311,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) ret = __irq_set_trigger(desc, new->flags & IRQF_TRIGGER_MASK); - if (ret) { - irq_release_resources(desc); + if (ret) goto out_unlock; - } } desc->istate &= ~(IRQS_AUTODETECT | IRQS_SPURIOUS_DISABLED | \ @@ -1385,12 +1408,10 @@ mismatch: out_unlock: raw_spin_unlock_irqrestore(&desc->lock, flags); - chip_bus_sync_unlock(desc); - if (!desc->action) irq_release_resources(desc); - -out_mutex: +out_bus_unlock: + chip_bus_sync_unlock(desc); mutex_unlock(&desc->request_mutex); out_thread: @@ -1472,6 +1493,7 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) WARN(1, "Trying to free already-free IRQ %d\n", irq); raw_spin_unlock_irqrestore(&desc->lock, flags); chip_bus_sync_unlock(desc); + mutex_unlock(&desc->request_mutex); return NULL; } @@ -1498,6 +1520,20 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) #endif raw_spin_unlock_irqrestore(&desc->lock, flags); + /* + * Drop bus_lock here so the changes which were done in the chip + * callbacks above are synced out to the irq chips which hang + * behind a slow bus (I2C, SPI) before calling synchronize_irq(). + * + * Aside of that the bus_lock can also be taken from the threaded + * handler in irq_finalize_oneshot() which results in a deadlock + * because synchronize_irq() would wait forever for the thread to + * complete, which is blocked on the bus lock. + * + * The still held desc->request_mutex() protects against a + * concurrent request_irq() of this irq so the release of resources + * and timing data is properly serialized. + */ chip_bus_sync_unlock(desc); unregister_handler_proc(irq, action); @@ -1530,8 +1566,15 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) } } + /* Last action releases resources */ if (!desc->action) { + /* + * Reaquire bus lock as irq_release_resources() might + * require it to deallocate resources over the slow bus. + */ + chip_bus_lock(desc); irq_release_resources(desc); + chip_bus_sync_unlock(desc); irq_remove_timings(desc); } diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 0c31035bbfee..b7cc615d42ef 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -3203,8 +3203,10 @@ static struct ceph_msg_data *ceph_msg_data_create(enum ceph_msg_data_type type) return NULL; data = kmem_cache_zalloc(ceph_msg_data_cache, GFP_NOFS); - if (data) - data->type = type; + if (!data) + return NULL; + + data->type = type; INIT_LIST_HEAD(&data->links); return data; diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 86a9737d8e3f..901bb8221366 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -5310,7 +5310,10 @@ static int invalidate_authorizer(struct ceph_connection *con) static void osd_reencode_message(struct ceph_msg *msg) { - encode_request_finish(msg); + int type = le16_to_cpu(msg->hdr.type); + + if (type == CEPH_MSG_OSD_OP) + encode_request_finish(msg); } static int osd_sign_message(struct ceph_msg *msg) diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index 864789c5974e..64ae9f89773a 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -338,7 +338,7 @@ static void crush_finalize(struct crush_map *c) static struct crush_map *crush_decode(void *pbyval, void *end) { struct crush_map *c; - int err = -EINVAL; + int err; int i, j; void **p = &pbyval; void *start = pbyval; @@ -407,7 +407,6 @@ static struct crush_map *crush_decode(void *pbyval, void *end) size = sizeof(struct crush_bucket_straw2); break; default: - err = -EINVAL; goto bad; } BUG_ON(size == 0); @@ -439,31 +438,31 @@ static struct crush_map *crush_decode(void *pbyval, void *end) err = crush_decode_uniform_bucket(p, end, (struct crush_bucket_uniform *)b); if (err < 0) - goto bad; + goto fail; break; case CRUSH_BUCKET_LIST: err = crush_decode_list_bucket(p, end, (struct crush_bucket_list *)b); if (err < 0) - goto bad; + goto fail; break; case CRUSH_BUCKET_TREE: err = crush_decode_tree_bucket(p, end, (struct crush_bucket_tree *)b); if (err < 0) - goto bad; + goto fail; break; case CRUSH_BUCKET_STRAW: err = crush_decode_straw_bucket(p, end, (struct crush_bucket_straw *)b); if (err < 0) - goto bad; + goto fail; break; case CRUSH_BUCKET_STRAW2: err = crush_decode_straw2_bucket(p, end, (struct crush_bucket_straw2 *)b); if (err < 0) - goto bad; + goto fail; break; } } @@ -474,7 +473,6 @@ static struct crush_map *crush_decode(void *pbyval, void *end) u32 yes; struct crush_rule *r; - err = -EINVAL; ceph_decode_32_safe(p, end, yes, bad); if (!yes) { dout("crush_decode NO rule %d off %x %p to %p\n", @@ -489,7 +487,6 @@ static struct crush_map *crush_decode(void *pbyval, void *end) /* len */ ceph_decode_32_safe(p, end, yes, bad); #if BITS_PER_LONG == 32 - err = -EINVAL; if (yes > (ULONG_MAX - sizeof(*r)) / sizeof(struct crush_rule_step)) goto bad; @@ -557,7 +554,7 @@ static struct crush_map *crush_decode(void *pbyval, void *end) if (*p != end) { err = decode_choose_args(p, end, c); if (err) - goto bad; + goto fail; } done: @@ -567,10 +564,14 @@ done: badmem: err = -ENOMEM; -bad: +fail: dout("crush_decode fail %d\n", err); crush_destroy(c); return ERR_PTR(err); + +bad: + err = -EINVAL; + goto fail; } int ceph_pg_compare(const struct ceph_pg *lhs, const struct ceph_pg *rhs) @@ -1399,7 +1400,7 @@ static struct ceph_pg_mapping *__decode_pg_upmap_items(void **p, void *end, return ERR_PTR(-EINVAL); ceph_decode_need(p, end, 2 * len * sizeof(u32), e_inval); - pg = kzalloc(sizeof(*pg) + 2 * len * sizeof(u32), GFP_NOIO); + pg = alloc_pg_mapping(2 * len * sizeof(u32)); if (!pg) return ERR_PTR(-ENOMEM); @@ -1544,7 +1545,7 @@ static int osdmap_decode(void **p, void *end, struct ceph_osdmap *map) if (struct_v >= 3) { /* erasure_code_profiles */ ceph_decode_skip_map_of_map(p, end, string, string, string, - bad); + e_inval); } if (struct_v >= 4) { @@ -1825,9 +1826,9 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, if (struct_v >= 3) { /* new_erasure_code_profiles */ ceph_decode_skip_map_of_map(p, end, string, string, string, - bad); + e_inval); /* old_erasure_code_profiles */ - ceph_decode_skip_set(p, end, string, bad); + ceph_decode_skip_set(p, end, string, e_inval); } if (struct_v >= 4) { diff --git a/security/keys/internal.h b/security/keys/internal.h index 91bc6214ae57..1c02c6547038 100644 --- a/security/keys/internal.h +++ b/security/keys/internal.h @@ -198,7 +198,7 @@ struct request_key_auth { void *callout_info; size_t callout_len; pid_t pid; -}; +} __randomize_layout; extern struct key_type key_type_request_key_auth; extern struct key *request_key_auth_new(struct key *target, |