diff options
80 files changed, 1968 insertions, 643 deletions
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index b23c76b42d6e..165ecdd24d22 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -43,6 +43,7 @@ config SPARC select ARCH_HAS_SG_CHAIN select CPU_NO_EFFICIENT_FFS select HAVE_ARCH_HARDENED_USERCOPY + select PROVE_LOCKING_SMALL if PROVE_LOCKING config SPARC32 def_bool !64BIT @@ -89,6 +90,14 @@ config ARCH_DEFCONFIG config ARCH_PROC_KCORE_TEXT def_bool y +config ARCH_ATU + bool + default y if SPARC64 + +config ARCH_DMA_ADDR_T_64BIT + bool + default y if ARCH_ATU + config IOMMU_HELPER bool default y if SPARC64 @@ -304,6 +313,20 @@ config ARCH_SPARSEMEM_ENABLE config ARCH_SPARSEMEM_DEFAULT def_bool y if SPARC64 +config FORCE_MAX_ZONEORDER + int "Maximum zone order" + default "13" + help + The kernel memory allocator divides physically contiguous memory + blocks into "zones", where each zone is a power of two number of + pages. This option selects the largest power of two that the kernel + keeps in the memory allocator. If you need to allocate very large + blocks of physically contiguous memory, then you may need to + increase this value. + + This config option is actually maximum order plus one. For example, + a value of 13 means that the largest free memory block is 2^12 pages. + source "mm/Kconfig" if SPARC64 diff --git a/arch/sparc/include/asm/hypervisor.h b/arch/sparc/include/asm/hypervisor.h index 666d5ba230d2..73cb8978df58 100644 --- a/arch/sparc/include/asm/hypervisor.h +++ b/arch/sparc/include/asm/hypervisor.h @@ -2335,6 +2335,348 @@ unsigned long sun4v_vintr_set_target(unsigned long dev_handle, */ #define HV_FAST_PCI_MSG_SETVALID 0xd3 +/* PCI IOMMU v2 definitions and services + * + * While the PCI IO definitions above is valid IOMMU v2 adds new PCI IO + * definitions and services. + * + * CTE Clump Table Entry. First level table entry in the ATU. + * + * pci_device_list + * A 32-bit aligned list of pci_devices. + * + * pci_device_listp + * real address of a pci_device_list. 32-bit aligned. + * + * iotte IOMMU translation table entry. + * + * iotte_attributes + * IO Attributes for IOMMU v2 mappings. In addition to + * read, write IOMMU v2 supports relax ordering + * + * io_page_list A 64-bit aligned list of real addresses. Each real + * address in an io_page_list must be properly aligned + * to the pagesize of the given IOTSB. + * + * io_page_list_p Real address of an io_page_list, 64-bit aligned. + * + * IOTSB IO Translation Storage Buffer. An aligned table of + * IOTTEs. Each IOTSB has a pagesize, table size, and + * virtual address associated with it that must match + * a pagesize and table size supported by the un-derlying + * hardware implementation. The alignment requirements + * for an IOTSB depend on the pagesize used for that IOTSB. + * Each IOTTE in an IOTSB maps one pagesize-sized page. + * The size of the IOTSB dictates how large of a virtual + * address space the IOTSB is capable of mapping. + * + * iotsb_handle An opaque identifier for an IOTSB. A devhandle plus + * iotsb_handle represents a binding of an IOTSB to a + * PCI root complex. + * + * iotsb_index Zero-based IOTTE number within an IOTSB. + */ + +/* The index_count argument consists of two fields: + * bits 63:48 #iottes and bits 47:0 iotsb_index + */ +#define HV_PCI_IOTSB_INDEX_COUNT(__iottes, __iotsb_index) \ + (((u64)(__iottes) << 48UL) | ((u64)(__iotsb_index))) + +/* pci_iotsb_conf() + * TRAP: HV_FAST_TRAP + * FUNCTION: HV_FAST_PCI_IOTSB_CONF + * ARG0: devhandle + * ARG1: r_addr + * ARG2: size + * ARG3: pagesize + * ARG4: iova + * RET0: status + * RET1: iotsb_handle + * ERRORS: EINVAL Invalid devhandle, size, iova, or pagesize + * EBADALIGN r_addr is not properly aligned + * ENORADDR r_addr is not a valid real address + * ETOOMANY No further IOTSBs may be configured + * EBUSY Duplicate devhandle, raddir, iova combination + * + * Create an IOTSB suitable for the PCI root complex identified by devhandle, + * for the DMA virtual address defined by the argument iova. + * + * r_addr is the properly aligned base address of the IOTSB and size is the + * IOTSB (table) size in bytes.The IOTSB is required to be zeroed prior to + * being configured. If it contains any values other than zeros then the + * behavior is undefined. + * + * pagesize is the size of each page in the IOTSB. Note that the combination of + * size (table size) and pagesize must be valid. + * + * virt is the DMA virtual address this IOTSB will map. + * + * If successful, the opaque 64-bit handle iotsb_handle is returned in ret1. + * Once configured, privileged access to the IOTSB memory is prohibited and + * creates undefined behavior. The only permitted access is indirect via these + * services. + */ +#define HV_FAST_PCI_IOTSB_CONF 0x190 + +/* pci_iotsb_info() + * TRAP: HV_FAST_TRAP + * FUNCTION: HV_FAST_PCI_IOTSB_INFO + * ARG0: devhandle + * ARG1: iotsb_handle + * RET0: status + * RET1: r_addr + * RET2: size + * RET3: pagesize + * RET4: iova + * RET5: #bound + * ERRORS: EINVAL Invalid devhandle or iotsb_handle + * + * This service returns configuration information about an IOTSB previously + * created with pci_iotsb_conf. + * + * iotsb_handle value 0 may be used with this service to inquire about the + * legacy IOTSB that may or may not exist. If the service succeeds, the return + * values describe the legacy IOTSB and I/O virtual addresses mapped by that + * table. However, the table base address r_addr may contain the value -1 which + * indicates a memory range that cannot be accessed or be reclaimed. + * + * The return value #bound contains the number of PCI devices that iotsb_handle + * is currently bound to. + */ +#define HV_FAST_PCI_IOTSB_INFO 0x191 + +/* pci_iotsb_unconf() + * TRAP: HV_FAST_TRAP + * FUNCTION: HV_FAST_PCI_IOTSB_UNCONF + * ARG0: devhandle + * ARG1: iotsb_handle + * RET0: status + * ERRORS: EINVAL Invalid devhandle or iotsb_handle + * EBUSY The IOTSB is bound and may not be unconfigured + * + * This service unconfigures the IOTSB identified by the devhandle and + * iotsb_handle arguments, previously created with pci_iotsb_conf. + * The IOTSB must not be currently bound to any device or the service will fail + * + * If the call succeeds, iotsb_handle is no longer valid. + */ +#define HV_FAST_PCI_IOTSB_UNCONF 0x192 + +/* pci_iotsb_bind() + * TRAP: HV_FAST_TRAP + * FUNCTION: HV_FAST_PCI_IOTSB_BIND + * ARG0: devhandle + * ARG1: iotsb_handle + * ARG2: pci_device + * RET0: status + * ERRORS: EINVAL Invalid devhandle, iotsb_handle, or pci_device + * EBUSY A PCI function is already bound to an IOTSB at the same + * address range as specified by devhandle, iotsb_handle. + * + * This service binds the PCI function specified by the argument pci_device to + * the IOTSB specified by the arguments devhandle and iotsb_handle. + * + * The PCI device function is bound to the specified IOTSB with the IOVA range + * specified when the IOTSB was configured via pci_iotsb_conf. If the function + * is already bound then it is unbound first. + */ +#define HV_FAST_PCI_IOTSB_BIND 0x193 + +/* pci_iotsb_unbind() + * TRAP: HV_FAST_TRAP + * FUNCTION: HV_FAST_PCI_IOTSB_UNBIND + * ARG0: devhandle + * ARG1: iotsb_handle + * ARG2: pci_device + * RET0: status + * ERRORS: EINVAL Invalid devhandle, iotsb_handle, or pci_device + * ENOMAP The PCI function was not bound to the specified IOTSB + * + * This service unbinds the PCI device specified by the argument pci_device + * from the IOTSB identified * by the arguments devhandle and iotsb_handle. + * + * If the PCI device is not bound to the specified IOTSB then this service will + * fail with status ENOMAP + */ +#define HV_FAST_PCI_IOTSB_UNBIND 0x194 + +/* pci_iotsb_get_binding() + * TRAP: HV_FAST_TRAP + * FUNCTION: HV_FAST_PCI_IOTSB_GET_BINDING + * ARG0: devhandle + * ARG1: iotsb_handle + * ARG2: iova + * RET0: status + * RET1: iotsb_handle + * ERRORS: EINVAL Invalid devhandle, pci_device, or iova + * ENOMAP The PCI function is not bound to an IOTSB at iova + * + * This service returns the IOTSB binding, iotsb_handle, for a given pci_device + * and DMA virtual address, iova. + * + * iova must be the base address of a DMA virtual address range as defined by + * the iommu-address-ranges property in the root complex device node defined + * by the argument devhandle. + */ +#define HV_FAST_PCI_IOTSB_GET_BINDING 0x195 + +/* pci_iotsb_map() + * TRAP: HV_FAST_TRAP + * FUNCTION: HV_FAST_PCI_IOTSB_MAP + * ARG0: devhandle + * ARG1: iotsb_handle + * ARG2: index_count + * ARG3: iotte_attributes + * ARG4: io_page_list_p + * RET0: status + * RET1: #mapped + * ERRORS: EINVAL Invalid devhandle, iotsb_handle, #iottes, + * iotsb_index or iotte_attributes + * EBADALIGN Improperly aligned io_page_list_p or I/O page + * address in the I/O page list. + * ENORADDR Invalid io_page_list_p or I/O page address in + * the I/O page list. + * + * This service creates and flushes mappings in the IOTSB defined by the + * arguments devhandle, iotsb. + * + * The index_count argument consists of two fields. Bits 63:48 contain #iotte + * and bits 47:0 contain iotsb_index + * + * The first mapping is created in the IOTSB index specified by iotsb_index. + * Subsequent mappings are created at iotsb_index+1 and so on. + * + * The attributes of each mapping are defined by the argument iotte_attributes. + * + * The io_page_list_p specifies the real address of the 64-bit-aligned list of + * #iottes I/O page addresses. Each page address must be a properly aligned + * real address of a page to be mapped in the IOTSB. The first entry in the I/O + * page list contains the real address of the first page, the 2nd entry for the + * 2nd page, and so on. + * + * #iottes must be greater than zero. + * + * The return value #mapped is the actual number of mappings created, which may + * be less than or equal to the argument #iottes. If the function returns + * successfully with a #mapped value less than the requested #iottes then the + * caller should continue to invoke the service with updated iotsb_index, + * #iottes, and io_page_list_p arguments until all pages are mapped. + * + * This service must not be used to demap a mapping. In other words, all + * mappings must be valid and have one or both of the RW attribute bits set. + * + * Note: + * It is implementation-defined whether I/O page real address validity checking + * is done at time mappings are established or deferred until they are + * accessed. + */ +#define HV_FAST_PCI_IOTSB_MAP 0x196 + +/* pci_iotsb_map_one() + * TRAP: HV_FAST_TRAP + * FUNCTION: HV_FAST_PCI_IOTSB_MAP_ONE + * ARG0: devhandle + * ARG1: iotsb_handle + * ARG2: iotsb_index + * ARG3: iotte_attributes + * ARG4: r_addr + * RET0: status + * ERRORS: EINVAL Invalid devhandle,iotsb_handle, iotsb_index + * or iotte_attributes + * EBADALIGN Improperly aligned r_addr + * ENORADDR Invalid r_addr + * + * This service creates and flushes a single mapping in the IOTSB defined by the + * arguments devhandle, iotsb. + * + * The mapping for the page at r_addr is created at the IOTSB index specified by + * iotsb_index with the attributes iotte_attributes. + * + * This service must not be used to demap a mapping. In other words, the mapping + * must be valid and have one or both of the RW attribute bits set. + * + * Note: + * It is implementation-defined whether I/O page real address validity checking + * is done at time mappings are established or deferred until they are + * accessed. + */ +#define HV_FAST_PCI_IOTSB_MAP_ONE 0x197 + +/* pci_iotsb_demap() + * TRAP: HV_FAST_TRAP + * FUNCTION: HV_FAST_PCI_IOTSB_DEMAP + * ARG0: devhandle + * ARG1: iotsb_handle + * ARG2: iotsb_index + * ARG3: #iottes + * RET0: status + * RET1: #unmapped + * ERRORS: EINVAL Invalid devhandle, iotsb_handle, iotsb_index or #iottes + * + * This service unmaps and flushes up to #iottes mappings starting at index + * iotsb_index from the IOTSB defined by the arguments devhandle, iotsb. + * + * #iottes must be greater than zero. + * + * The actual number of IOTTEs unmapped is returned in #unmapped and may be less + * than or equal to the requested number of IOTTEs, #iottes. + * + * If #unmapped is less than #iottes, the caller should continue to invoke this + * service with updated iotsb_index and #iottes arguments until all pages are + * demapped. + */ +#define HV_FAST_PCI_IOTSB_DEMAP 0x198 + +/* pci_iotsb_getmap() + * TRAP: HV_FAST_TRAP + * FUNCTION: HV_FAST_PCI_IOTSB_GETMAP + * ARG0: devhandle + * ARG1: iotsb_handle + * ARG2: iotsb_index + * RET0: status + * RET1: r_addr + * RET2: iotte_attributes + * ERRORS: EINVAL Invalid devhandle, iotsb_handle, or iotsb_index + * ENOMAP No mapping was found + * + * This service returns the mapping specified by index iotsb_index from the + * IOTSB defined by the arguments devhandle, iotsb. + * + * Upon success, the real address of the mapping shall be returned in + * r_addr and thethe IOTTE mapping attributes shall be returned in + * iotte_attributes. + * + * The return value iotte_attributes may not include optional features used in + * the call to create the mapping. + */ +#define HV_FAST_PCI_IOTSB_GETMAP 0x199 + +/* pci_iotsb_sync_mappings() + * TRAP: HV_FAST_TRAP + * FUNCTION: HV_FAST_PCI_IOTSB_SYNC_MAPPINGS + * ARG0: devhandle + * ARG1: iotsb_handle + * ARG2: iotsb_index + * ARG3: #iottes + * RET0: status + * RET1: #synced + * ERROS: EINVAL Invalid devhandle, iotsb_handle, iotsb_index, or #iottes + * + * This service synchronizes #iottes mappings starting at index iotsb_index in + * the IOTSB defined by the arguments devhandle, iotsb. + * + * #iottes must be greater than zero. + * + * The actual number of IOTTEs synchronized is returned in #synced, which may + * be less than or equal to the requested number, #iottes. + * + * Upon a successful return, #synced is less than #iottes, the caller should + * continue to invoke this service with updated iotsb_index and #iottes + * arguments until all pages are synchronized. + */ +#define HV_FAST_PCI_IOTSB_SYNC_MAPPINGS 0x19a + /* Logical Domain Channel services. */ #define LDC_CHANNEL_DOWN 0 @@ -2993,6 +3335,7 @@ unsigned long sun4v_m7_set_perfreg(unsigned long reg_num, #define HV_GRP_SDIO 0x0108 #define HV_GRP_SDIO_ERR 0x0109 #define HV_GRP_REBOOT_DATA 0x0110 +#define HV_GRP_ATU 0x0111 #define HV_GRP_M7_PERF 0x0114 #define HV_GRP_NIAG_PERF 0x0200 #define HV_GRP_FIRE_PERF 0x0201 diff --git a/arch/sparc/include/asm/iommu_64.h b/arch/sparc/include/asm/iommu_64.h index cd0d69fa7592..f24f356f2503 100644 --- a/arch/sparc/include/asm/iommu_64.h +++ b/arch/sparc/include/asm/iommu_64.h @@ -24,8 +24,36 @@ struct iommu_arena { unsigned int limit; }; +#define ATU_64_SPACE_SIZE 0x800000000 /* 32G */ + +/* Data structures for SPARC ATU architecture */ +struct atu_iotsb { + void *table; /* IOTSB table base virtual addr*/ + u64 ra; /* IOTSB table real addr */ + u64 dvma_size; /* ranges[3].size or OS slected 32G size */ + u64 dvma_base; /* ranges[3].base */ + u64 table_size; /* IOTSB table size */ + u64 page_size; /* IO PAGE size for IOTSB */ + u32 iotsb_num; /* tsbnum is same as iotsb_handle */ +}; + +struct atu_ranges { + u64 base; + u64 size; +}; + +struct atu { + struct atu_ranges *ranges; + struct atu_iotsb *iotsb; + struct iommu_map_table tbl; + u64 base; + u64 size; + u64 dma_addr_mask; +}; + struct iommu { struct iommu_map_table tbl; + struct atu *atu; spinlock_t lock; u32 dma_addr_mask; iopte_t *page_table; diff --git a/arch/sparc/kernel/hvapi.c b/arch/sparc/kernel/hvapi.c index 662500fa555f..267731234ce8 100644 --- a/arch/sparc/kernel/hvapi.c +++ b/arch/sparc/kernel/hvapi.c @@ -39,6 +39,7 @@ static struct api_info api_table[] = { { .group = HV_GRP_SDIO, }, { .group = HV_GRP_SDIO_ERR, }, { .group = HV_GRP_REBOOT_DATA, }, + { .group = HV_GRP_ATU, .flags = FLAG_PRE_API }, { .group = HV_GRP_NIAG_PERF, .flags = FLAG_PRE_API }, { .group = HV_GRP_FIRE_PERF, }, { .group = HV_GRP_N2_CPU, }, diff --git a/arch/sparc/kernel/iommu.c b/arch/sparc/kernel/iommu.c index 5c615abff030..852a3291db96 100644 --- a/arch/sparc/kernel/iommu.c +++ b/arch/sparc/kernel/iommu.c @@ -760,8 +760,12 @@ int dma_supported(struct device *dev, u64 device_mask) struct iommu *iommu = dev->archdata.iommu; u64 dma_addr_mask = iommu->dma_addr_mask; - if (device_mask >= (1UL << 32UL)) - return 0; + 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/iommu_common.h b/arch/sparc/kernel/iommu_common.h index b40cec252905..828493329f68 100644 --- a/arch/sparc/kernel/iommu_common.h +++ b/arch/sparc/kernel/iommu_common.h @@ -13,7 +13,6 @@ #include <linux/scatterlist.h> #include <linux/device.h> #include <linux/iommu-helper.h> -#include <linux/scatterlist.h> #include <asm/iommu.h> diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c index db57d8acdc01..06981cc716b6 100644 --- a/arch/sparc/kernel/pci_sun4v.c +++ b/arch/sparc/kernel/pci_sun4v.c @@ -44,6 +44,9 @@ static struct vpci_version vpci_versions[] = { { .major = 1, .minor = 1 }, }; +static unsigned long vatu_major = 1; +static unsigned long vatu_minor = 1; + #define PGLIST_NENTS (PAGE_SIZE / sizeof(u64)) struct iommu_batch { @@ -69,34 +72,57 @@ static inline void iommu_batch_start(struct device *dev, unsigned long prot, uns } /* Interrupts must be disabled. */ -static long iommu_batch_flush(struct iommu_batch *p) +static long iommu_batch_flush(struct iommu_batch *p, u64 mask) { struct pci_pbm_info *pbm = p->dev->archdata.host_controller; + u64 *pglist = p->pglist; + u64 index_count; unsigned long devhandle = pbm->devhandle; unsigned long prot = p->prot; unsigned long entry = p->entry; - u64 *pglist = p->pglist; unsigned long npages = p->npages; + unsigned long iotsb_num; + unsigned long ret; + long num; /* VPCI maj=1, min=[0,1] only supports read and write */ if (vpci_major < 2) prot &= (HV_PCI_MAP_ATTR_READ | HV_PCI_MAP_ATTR_WRITE); while (npages != 0) { - long num; - - num = pci_sun4v_iommu_map(devhandle, HV_PCI_TSBID(0, entry), - npages, prot, __pa(pglist)); - if (unlikely(num < 0)) { - if (printk_ratelimit()) - printk("iommu_batch_flush: IOMMU map of " - "[%08lx:%08llx:%lx:%lx:%lx] failed with " - "status %ld\n", - devhandle, HV_PCI_TSBID(0, entry), - npages, prot, __pa(pglist), num); - return -1; + if (mask <= DMA_BIT_MASK(32)) { + num = pci_sun4v_iommu_map(devhandle, + HV_PCI_TSBID(0, entry), + npages, + prot, + __pa(pglist)); + if (unlikely(num < 0)) { + pr_err_ratelimited("%s: IOMMU map of [%08lx:%08llx:%lx:%lx:%lx] failed with status %ld\n", + __func__, + devhandle, + HV_PCI_TSBID(0, entry), + npages, prot, __pa(pglist), + num); + return -1; + } + } else { + index_count = HV_PCI_IOTSB_INDEX_COUNT(npages, entry), + iotsb_num = pbm->iommu->atu->iotsb->iotsb_num; + ret = pci_sun4v_iotsb_map(devhandle, + iotsb_num, + index_count, + prot, + __pa(pglist), + &num); + if (unlikely(ret != HV_EOK)) { + pr_err_ratelimited("%s: ATU map of [%08lx:%lx:%llx:%lx:%lx] failed with status %ld\n", + __func__, + devhandle, iotsb_num, + index_count, prot, + __pa(pglist), ret); + return -1; + } } - entry += num; npages -= num; pglist += num; @@ -108,19 +134,19 @@ static long iommu_batch_flush(struct iommu_batch *p) return 0; } -static inline void iommu_batch_new_entry(unsigned long entry) +static inline void iommu_batch_new_entry(unsigned long entry, u64 mask) { struct iommu_batch *p = this_cpu_ptr(&iommu_batch); if (p->entry + p->npages == entry) return; if (p->entry != ~0UL) - iommu_batch_flush(p); + iommu_batch_flush(p, mask); p->entry = entry; } /* Interrupts must be disabled. */ -static inline long iommu_batch_add(u64 phys_page) +static inline long iommu_batch_add(u64 phys_page, u64 mask) { struct iommu_batch *p = this_cpu_ptr(&iommu_batch); @@ -128,28 +154,31 @@ static inline long iommu_batch_add(u64 phys_page) p->pglist[p->npages++] = phys_page; if (p->npages == PGLIST_NENTS) - return iommu_batch_flush(p); + return iommu_batch_flush(p, mask); return 0; } /* Interrupts must be disabled. */ -static inline long iommu_batch_end(void) +static inline long iommu_batch_end(u64 mask) { struct iommu_batch *p = this_cpu_ptr(&iommu_batch); BUG_ON(p->npages >= PGLIST_NENTS); - return iommu_batch_flush(p); + return iommu_batch_flush(p, mask); } static void *dma_4v_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addrp, gfp_t gfp, unsigned long attrs) { + u64 mask; unsigned long flags, order, first_page, npages, n; unsigned long prot = 0; struct iommu *iommu; + struct atu *atu; + struct iommu_map_table *tbl; struct page *page; void *ret; long entry; @@ -174,14 +203,21 @@ static void *dma_4v_alloc_coherent(struct device *dev, size_t size, memset((char *)first_page, 0, PAGE_SIZE << order); iommu = dev->archdata.iommu; + atu = iommu->atu; + + mask = dev->coherent_dma_mask; + if (mask <= DMA_BIT_MASK(32)) + tbl = &iommu->tbl; + else + tbl = &atu->tbl; - entry = iommu_tbl_range_alloc(dev, &iommu->tbl, npages, NULL, + entry = iommu_tbl_range_alloc(dev, tbl, npages, NULL, (unsigned long)(-1), 0); if (unlikely(entry == IOMMU_ERROR_CODE)) goto range_alloc_fail; - *dma_addrp = (iommu->tbl.table_map_base + (entry << IO_PAGE_SHIFT)); + *dma_addrp = (tbl->table_map_base + (entry << IO_PAGE_SHIFT)); ret = (void *) first_page; first_page = __pa(first_page); @@ -193,12 +229,12 @@ static void *dma_4v_alloc_coherent(struct device *dev, size_t size, entry); for (n = 0; n < npages; n++) { - long err = iommu_batch_add(first_page + (n * PAGE_SIZE)); + long err = iommu_batch_add(first_page + (n * PAGE_SIZE), mask); if (unlikely(err < 0L)) goto iommu_map_fail; } - if (unlikely(iommu_batch_end() < 0L)) + if (unlikely(iommu_batch_end(mask) < 0L)) goto iommu_map_fail; local_irq_restore(flags); @@ -206,25 +242,71 @@ static void *dma_4v_alloc_coherent(struct device *dev, size_t size, return ret; iommu_map_fail: - iommu_tbl_range_free(&iommu->tbl, *dma_addrp, npages, IOMMU_ERROR_CODE); + iommu_tbl_range_free(tbl, *dma_addrp, npages, IOMMU_ERROR_CODE); range_alloc_fail: free_pages(first_page, order); return NULL; } -static void dma_4v_iommu_demap(void *demap_arg, unsigned long entry, - unsigned long npages) +unsigned long dma_4v_iotsb_bind(unsigned long devhandle, + unsigned long iotsb_num, + struct pci_bus *bus_dev) +{ + struct pci_dev *pdev; + unsigned long err; + unsigned int bus; + unsigned int device; + unsigned int fun; + + list_for_each_entry(pdev, &bus_dev->devices, bus_list) { + if (pdev->subordinate) { + /* No need to bind pci bridge */ + dma_4v_iotsb_bind(devhandle, iotsb_num, + pdev->subordinate); + } else { + bus = bus_dev->number; + device = PCI_SLOT(pdev->devfn); + fun = PCI_FUNC(pdev->devfn); + err = pci_sun4v_iotsb_bind(devhandle, iotsb_num, + HV_PCI_DEVICE_BUILD(bus, + device, + fun)); + + /* If bind fails for one device it is going to fail + * for rest of the devices because we are sharing + * IOTSB. So in case of failure simply return with + * error. + */ + if (err) + return err; + } + } + + return 0; +} + +static void dma_4v_iommu_demap(struct device *dev, unsigned long devhandle, + dma_addr_t dvma, unsigned long iotsb_num, + unsigned long entry, unsigned long npages) { - u32 devhandle = *(u32 *)demap_arg; unsigned long num, flags; + unsigned long ret; local_irq_save(flags); do { - num = pci_sun4v_iommu_demap(devhandle, - HV_PCI_TSBID(0, entry), - npages); - + if (dvma <= DMA_BIT_MASK(32)) { + num = pci_sun4v_iommu_demap(devhandle, + HV_PCI_TSBID(0, entry), + npages); + } else { + ret = pci_sun4v_iotsb_demap(devhandle, iotsb_num, + entry, npages, &num); + if (unlikely(ret != HV_EOK)) { + pr_err_ratelimited("pci_iotsb_demap() failed with error: %ld\n", + ret); + } + } entry += num; npages -= num; } while (npages != 0); @@ -236,16 +318,28 @@ static void dma_4v_free_coherent(struct device *dev, size_t size, void *cpu, { struct pci_pbm_info *pbm; struct iommu *iommu; + struct atu *atu; + struct iommu_map_table *tbl; unsigned long order, npages, entry; + unsigned long iotsb_num; u32 devhandle; npages = IO_PAGE_ALIGN(size) >> IO_PAGE_SHIFT; iommu = dev->archdata.iommu; pbm = dev->archdata.host_controller; + atu = iommu->atu; devhandle = pbm->devhandle; - entry = ((dvma - iommu->tbl.table_map_base) >> IO_PAGE_SHIFT); - dma_4v_iommu_demap(&devhandle, entry, npages); - iommu_tbl_range_free(&iommu->tbl, dvma, npages, IOMMU_ERROR_CODE); + + if (dvma <= DMA_BIT_MASK(32)) { + tbl = &iommu->tbl; + iotsb_num = 0; /* we don't care for legacy iommu */ + } else { + tbl = &atu->tbl; + iotsb_num = atu->iotsb->iotsb_num; + } + entry = ((dvma - tbl->table_map_base) >> IO_PAGE_SHIFT); + dma_4v_iommu_demap(dev, devhandle, dvma, iotsb_num, entry, npages); + iommu_tbl_range_free(tbl, dvma, npages, IOMMU_ERROR_CODE); order = get_order(size); if (order < 10) free_pages((unsigned long)cpu, order); @@ -257,13 +351,17 @@ static dma_addr_t dma_4v_map_page(struct device *dev, struct page *page, unsigned long attrs) { struct iommu *iommu; + struct atu *atu; + struct iommu_map_table *tbl; + u64 mask; unsigned long flags, npages, oaddr; unsigned long i, base_paddr; - u32 bus_addr, ret; unsigned long prot; + dma_addr_t bus_addr, ret; long entry; iommu = dev->archdata.iommu; + atu = iommu->atu; if (unlikely(direction == DMA_NONE)) goto bad; @@ -272,13 +370,19 @@ static dma_addr_t dma_4v_map_page(struct device *dev, struct page *page, npages = IO_PAGE_ALIGN(oaddr + sz) - (oaddr & IO_PAGE_MASK); npages >>= IO_PAGE_SHIFT; - entry = iommu_tbl_range_alloc(dev, &iommu->tbl, npages, NULL, + mask = *dev->dma_mask; + if (mask <= DMA_BIT_MASK(32)) + tbl = &iommu->tbl; + else + tbl = &atu->tbl; + + entry = iommu_tbl_range_alloc(dev, tbl, npages, NULL, (unsigned long)(-1), 0); if (unlikely(entry == IOMMU_ERROR_CODE)) goto bad; - bus_addr = (iommu->tbl.table_map_base + (entry << IO_PAGE_SHIFT)); + bus_addr = (tbl->table_map_base + (entry << IO_PAGE_SHIFT)); ret = bus_addr | (oaddr & ~IO_PAGE_MASK); base_paddr = __pa(oaddr & IO_PAGE_MASK); prot = HV_PCI_MAP_ATTR_READ; @@ -293,11 +397,11 @@ static dma_addr_t dma_4v_map_page(struct device *dev, struct page *page, iommu_batch_start(dev, prot, entry); for (i = 0; i < npages; i++, base_paddr += IO_PAGE_SIZE) { - long err = iommu_batch_add(base_paddr); + long err = iommu_batch_add(base_paddr, mask); if (unlikely(err < 0L)) goto iommu_map_fail; } - if (unlikely(iommu_batch_end() < 0L)) + if (unlikely(iommu_batch_end(mask) < 0L)) goto iommu_map_fail; local_irq_restore(flags); @@ -310,7 +414,7 @@ bad: return DMA_ERROR_CODE; iommu_map_fail: - iommu_tbl_range_free(&iommu->tbl, bus_addr, npages, IOMMU_ERROR_CODE); + iommu_tbl_range_free(tbl, bus_addr, npages, IOMMU_ERROR_CODE); return DMA_ERROR_CODE; } @@ -320,7 +424,10 @@ static void dma_4v_unmap_page(struct device *dev, dma_addr_t bus_addr, { struct pci_pbm_info *pbm; struct iommu *iommu; + struct atu *atu; + struct iommu_map_table *tbl; unsigned long npages; + unsigned long iotsb_num; long entry; u32 devhandle; @@ -332,14 +439,23 @@ static void dma_4v_unmap_page(struct device *dev, dma_addr_t bus_addr, iommu = dev->archdata.iommu; pbm = dev->archdata.host_controller; + atu = iommu->atu; devhandle = pbm->devhandle; npages = IO_PAGE_ALIGN(bus_addr + sz) - (bus_addr & IO_PAGE_MASK); npages >>= IO_PAGE_SHIFT; bus_addr &= IO_PAGE_MASK; - entry = (bus_addr - iommu->tbl.table_map_base) >> IO_PAGE_SHIFT; - dma_4v_iommu_demap(&devhandle, entry, npages); - iommu_tbl_range_free(&iommu->tbl, bus_addr, npages, IOMMU_ERROR_CODE); + + if (bus_addr <= DMA_BIT_MASK(32)) { + iotsb_num = 0; /* we don't care for legacy iommu */ + tbl = &iommu->tbl; + } else { + iotsb_num = atu->iotsb->iotsb_num; + tbl = &atu->tbl; + } + entry = (bus_addr - tbl->table_map_base) >> IO_PAGE_SHIFT; + dma_4v_iommu_demap(dev, devhandle, bus_addr, iotsb_num, entry, npages); + iommu_tbl_range_free(tbl, bus_addr, npages, IOMMU_ERROR_CODE); } static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist, @@ -353,12 +469,17 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist, unsigned long seg_boundary_size; int outcount, incount, i; struct iommu *iommu; + struct atu *atu; + struct iommu_map_table *tbl; + u64 mask; unsigned long base_shift; long err; BUG_ON(direction == DMA_NONE); iommu = dev->archdata.iommu; + atu = iommu->atu; + if (nelems == 0 || !iommu) return 0; @@ -384,7 +505,15 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist, max_seg_size = dma_get_max_seg_size(dev); seg_boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1, IO_PAGE_SIZE) >> IO_PAGE_SHIFT; - base_shift = iommu->tbl.table_map_base >> IO_PAGE_SHIFT; + + mask = *dev->dma_mask; + if (mask <= DMA_BIT_MASK(32)) + tbl = &iommu->tbl; + else + tbl = &atu->tbl; + + base_shift = tbl->table_map_base >> IO_PAGE_SHIFT; + for_each_sg(sglist, s, nelems, i) { unsigned long paddr, npages, entry, out_entry = 0, slen; @@ -397,27 +526,26 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist, /* Allocate iommu entries for that segment */ paddr = (unsigned long) SG_ENT_PHYS_ADDRESS(s); npages = iommu_num_pages(paddr, slen, IO_PAGE_SIZE); - entry = iommu_tbl_range_alloc(dev, &iommu->tbl, npages, + entry = iommu_tbl_range_alloc(dev, tbl, npages, &handle, (unsigned long)(-1), 0); /* Handle failure */ if (unlikely(entry == IOMMU_ERROR_CODE)) { - if (printk_ratelimit()) - printk(KERN_INFO "iommu_alloc failed, iommu %p paddr %lx" - " npages %lx\n", iommu, paddr, npages); + pr_err_ratelimited("iommu_alloc failed, iommu %p paddr %lx npages %lx\n", + tbl, paddr, npages); goto iommu_map_failed; } - iommu_batch_new_entry(entry); + iommu_batch_new_entry(entry, mask); /* Convert entry to a dma_addr_t */ - dma_addr = iommu->tbl.table_map_base + (entry << IO_PAGE_SHIFT); + dma_addr = tbl->table_map_base + (entry << IO_PAGE_SHIFT); dma_addr |= (s->offset & ~IO_PAGE_MASK); /* Insert into HW table */ paddr &= IO_PAGE_MASK; while (npages--) { - err = iommu_batch_add(paddr); + err = iommu_batch_add(paddr, mask); if (unlikely(err < 0L)) goto iommu_map_failed; paddr += IO_PAGE_SIZE; @@ -452,7 +580,7 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist, dma_next = dma_addr + slen; } - err = iommu_batch_end(); + err = iommu_batch_end(mask); if (unlikely(err < 0L)) goto iommu_map_failed; @@ -475,7 +603,7 @@ iommu_map_failed: vaddr = s->dma_address & IO_PAGE_MASK; npages = iommu_num_pages(s->dma_address, s->dma_length, IO_PAGE_SIZE); - iommu_tbl_range_free(&iommu->tbl, vaddr, npages, + iommu_tbl_range_free(tbl, vaddr, npages, IOMMU_ERROR_CODE); /* XXX demap? XXX */ s->dma_address = DMA_ERROR_CODE; @@ -496,13 +624,16 @@ static void dma_4v_unmap_sg(struct device *dev, struct scatterlist *sglist, struct pci_pbm_info *pbm; struct scatterlist *sg; struct iommu *iommu; + struct atu *atu; unsigned long flags, entry; + unsigned long iotsb_num; u32 devhandle; BUG_ON(direction == DMA_NONE); iommu = dev->archdata.iommu; pbm = dev->archdata.host_controller; + atu = iommu->atu; devhandle = pbm->devhandle; local_irq_save(flags); @@ -512,15 +643,24 @@ static void dma_4v_unmap_sg(struct device *dev, struct scatterlist *sglist, dma_addr_t dma_handle = sg->dma_address; unsigned int len = sg->dma_length; unsigned long npages; - struct iommu_map_table *tbl = &iommu->tbl; + struct iommu_map_table *tbl; unsigned long shift = IO_PAGE_SHIFT; if (!len) break; npages = iommu_num_pages(dma_handle, len, IO_PAGE_SIZE); + + if (dma_handle <= DMA_BIT_MASK(32)) { + iotsb_num = 0; /* we don't care for legacy iommu */ + tbl = &iommu->tbl; + } else { + iotsb_num = atu->iotsb->iotsb_num; + tbl = &atu->tbl; + } entry = ((dma_handle - tbl->table_map_base) >> shift); - dma_4v_iommu_demap(&devhandle, entry, npages); - iommu_tbl_range_free(&iommu->tbl, dma_handle, npages, + dma_4v_iommu_demap(dev, devhandle, dma_handle, iotsb_num, + entry, npages); + iommu_tbl_range_free(tbl, dma_handle, npages, IOMMU_ERROR_CODE); sg = sg_next(sg); } @@ -581,6 +721,132 @@ static unsigned long probe_existing_entries(struct pci_pbm_info *pbm, return cnt; } +static int pci_sun4v_atu_alloc_iotsb(struct pci_pbm_info *pbm) +{ + struct atu *atu = pbm->iommu->atu; + struct atu_iotsb *iotsb; + void *table; + u64 table_size; + u64 iotsb_num; + unsigned long order; + unsigned long err; + + iotsb = kzalloc(sizeof(*iotsb), GFP_KERNEL); + if (!iotsb) { + err = -ENOMEM; + goto out_err; + } + atu->iotsb = iotsb; + + /* calculate size of IOTSB */ + table_size = (atu->size / IO_PAGE_SIZE) * 8; + order = get_order(table_size); + table = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, order); + if (!table) { + err = -ENOMEM; + goto table_failed; + } + iotsb->table = table; + iotsb->ra = __pa(table); + iotsb->dvma_size = atu->size; + iotsb->dvma_base = atu->base; + iotsb->table_size = table_size; + iotsb->page_size = IO_PAGE_SIZE; + + /* configure and register IOTSB with HV */ + err = pci_sun4v_iotsb_conf(pbm->devhandle, + iotsb->ra, + iotsb->table_size, + iotsb->page_size, + iotsb->dvma_base, + &iotsb_num); + if (err) { + pr_err(PFX "pci_iotsb_conf failed error: %ld\n", err); + goto iotsb_conf_failed; + } + iotsb->iotsb_num = iotsb_num; + + err = dma_4v_iotsb_bind(pbm->devhandle, iotsb_num, pbm->pci_bus); + if (err) { + pr_err(PFX "pci_iotsb_bind failed error: %ld\n", err); + goto iotsb_conf_failed; + } + + return 0; + +iotsb_conf_failed: + free_pages((unsigned long)table, order); +table_failed: + kfree(iotsb); +out_err: + return err; +} + +static int pci_sun4v_atu_init(struct pci_pbm_info *pbm) +{ + struct atu *atu = pbm->iommu->atu; + unsigned long err; + const u64 *ranges; + u64 map_size, num_iotte; + u64 dma_mask; + const u32 *page_size; + int len; + + ranges = of_get_property(pbm->op->dev.of_node, "iommu-address-ranges", + &len); + if (!ranges) { + pr_err(PFX "No iommu-address-ranges\n"); + return -EINVAL; + } + + page_size = of_get_property(pbm->op->dev.of_node, "iommu-pagesizes", + NULL); + if (!page_size) { + pr_err(PFX "No iommu-pagesizes\n"); + return -EINVAL; + } + + /* There are 4 iommu-address-ranges supported. Each range is pair of + * {base, size}. The ranges[0] and ranges[1] are 32bit address space + * while ranges[2] and ranges[3] are 64bit space. We want to use 64bit + * address ranges to support 64bit addressing. Because 'size' for + * address ranges[2] and ranges[3] are same we can select either of + * ranges[2] or ranges[3] for mapping. However due to 'size' is too + * large for OS to allocate IOTSB we are using fix size 32G + * (ATU_64_SPACE_SIZE) which is more than enough for all PCIe devices + * to share. + */ + atu->ranges = (struct atu_ranges *)ranges; + atu->base = atu->ranges[3].base; + atu->size = ATU_64_SPACE_SIZE; + + /* Create IOTSB */ + err = pci_sun4v_atu_alloc_iotsb(pbm); + if (err) { + pr_err(PFX "Error creating ATU IOTSB\n"); + return err; + } + + /* Create ATU iommu map. + * One bit represents one iotte in IOTSB table. + */ + dma_mask = (roundup_pow_of_two(atu->size) - 1UL); + num_iotte = atu->size / IO_PAGE_SIZE; + map_size = num_iotte / 8; + atu->tbl.table_map_base = atu->base; + atu->dma_addr_mask = dma_mask; + atu->tbl.map = kzalloc(map_size, GFP_KERNEL); + if (!atu->tbl.map) + return -ENOMEM; + + iommu_tbl_pool_init(&atu->tbl, num_iotte, IO_PAGE_SHIFT, + NULL, false /* no large_pool */, + 0 /* default npools */, + false /* want span boundary checking */); + + return 0; +} + static int pci_sun4v_iommu_init(struct pci_pbm_info *pbm) { static const u32 vdma_default[] = { 0x80000000, 0x80000000 }; @@ -918,6 +1184,18 @@ static int pci_sun4v_pbm_init(struct pci_pbm_info *pbm, pci_sun4v_scan_bus(pbm, &op->dev); + /* if atu_init fails its not complete failure. + * we can still continue using legacy iommu. + */ + if (pbm->iommu->atu) { + err = pci_sun4v_atu_init(pbm); + if (err) { + kfree(pbm->iommu->atu); + pbm->iommu->atu = NULL; + pr_err(PFX "ATU init failed, err=%d\n", err); + } + } + pbm->next = pci_pbm_root; pci_pbm_root = pbm; @@ -931,8 +1209,10 @@ static int pci_sun4v_probe(struct platform_device *op) struct pci_pbm_info *pbm; struct device_node *dp; struct iommu *iommu; + struct atu *atu; u32 devhandle; int i, err = -ENODEV; + static bool hv_atu = true; dp = op->dev.of_node; @@ -954,6 +1234,19 @@ static int pci_sun4v_probe(struct platform_device *op) pr_info(PFX "Registered hvapi major[%lu] minor[%lu]\n", vpci_major, vpci_minor); + err = sun4v_hvapi_register(HV_GRP_ATU, vatu_major, &vatu_minor); + if (err) { + /* don't return an error if we fail to register the + * ATU group, but ATU hcalls won't be available. + */ + hv_atu = false; + pr_err(PFX "Could not register hvapi ATU err=%d\n", + err); + } else { + pr_info(PFX "Registered hvapi ATU major[%lu] minor[%lu]\n", + vatu_major, vatu_minor); + } + dma_ops = &sun4v_dma_ops; } @@ -991,6 +1284,14 @@ static int pci_sun4v_probe(struct platform_device *op) } pbm->iommu = iommu; + iommu->atu = NULL; + if (hv_atu) { + atu = kzalloc(sizeof(*atu), GFP_KERNEL); + if (!atu) + pr_err(PFX "Could not allocate atu\n"); + else + iommu->atu = atu; + } err = pci_sun4v_pbm_init(pbm, op, devhandle); if (err) @@ -1001,6 +1302,7 @@ static int pci_sun4v_probe(struct platform_device *op) return 0; out_free_iommu: + kfree(iommu->atu); kfree(pbm->iommu); out_free_controller: diff --git a/arch/sparc/kernel/pci_sun4v.h b/arch/sparc/kernel/pci_sun4v.h index 5642212390b2..22603a4e48bf 100644 --- a/arch/sparc/kernel/pci_sun4v.h +++ b/arch/sparc/kernel/pci_sun4v.h @@ -89,4 +89,25 @@ unsigned long pci_sun4v_msg_setvalid(unsigned long devhandle, unsigned long msinum, unsigned long valid); +/* Sun4v HV IOMMU v2 APIs */ +unsigned long pci_sun4v_iotsb_conf(unsigned long devhandle, + unsigned long ra, + unsigned long table_size, + unsigned long page_size, + unsigned long dvma_base, + u64 *iotsb_num); +unsigned long pci_sun4v_iotsb_bind(unsigned long devhandle, + unsigned long iotsb_num, + unsigned int pci_device); +unsigned long pci_sun4v_iotsb_map(unsigned long devhandle, + unsigned long iotsb_num, + unsigned long iotsb_index_iottes, + unsigned long io_attributes, + unsigned long io_page_list_pa, + long *mapped); +unsigned long pci_sun4v_iotsb_demap(unsigned long devhandle, + unsigned long iotsb_num, + unsigned long iotsb_index, + unsigned long iottes, + unsigned long *demapped); #endif /* !(_PCI_SUN4V_H) */ diff --git a/arch/sparc/kernel/pci_sun4v_asm.S b/arch/sparc/kernel/pci_sun4v_asm.S index e606d46c6815..578f09657916 100644 --- a/arch/sparc/kernel/pci_sun4v_asm.S +++ b/arch/sparc/kernel/pci_sun4v_asm.S @@ -360,3 +360,71 @@ ENTRY(pci_sun4v_msg_setvalid) mov %o0, %o0 ENDPROC(pci_sun4v_msg_setvalid) + /* + * %o0: devhandle + * %o1: r_addr + * %o2: size + * %o3: pagesize + * %o4: virt + * %o5: &iotsb_num/&iotsb_handle + * + * returns %o0: status + * %o1: iotsb_num/iotsb_handle + */ +ENTRY(pci_sun4v_iotsb_conf) + mov %o5, %g1 + mov HV_FAST_PCI_IOTSB_CONF, %o5 + ta HV_FAST_TRAP + retl + stx %o1, [%g1] +ENDPROC(pci_sun4v_iotsb_conf) + + /* + * %o0: devhandle + * %o1: iotsb_num/iotsb_handle + * %o2: pci_device + * + * returns %o0: status + */ +ENTRY(pci_sun4v_iotsb_bind) + mov HV_FAST_PCI_IOTSB_BIND, %o5 + ta HV_FAST_TRAP + retl + nop +ENDPROC(pci_sun4v_iotsb_bind) + + /* + * %o0: devhandle + * %o1: iotsb_num/iotsb_handle + * %o2: index_count + * %o3: iotte_attributes + * %o4: io_page_list_p + * %o5: &mapped + * + * returns %o0: status + * %o1: #mapped + */ +ENTRY(pci_sun4v_iotsb_map) + mov %o5, %g1 + mov HV_FAST_PCI_IOTSB_MAP, %o5 + ta HV_FAST_TRAP + retl + stx %o1, [%g1] +ENDPROC(pci_sun4v_iotsb_map) + + /* + * %o0: devhandle + * %o1: iotsb_num/iotsb_handle + * %o2: iotsb_index + * %o3: #iottes + * %o4: &demapped + * + * returns %o0: status + * %o1: #demapped + */ +ENTRY(pci_sun4v_iotsb_demap) + mov HV_FAST_PCI_IOTSB_DEMAP, %o5 + ta HV_FAST_TRAP + retl + stx %o1, [%o4] +ENDPROC(pci_sun4v_iotsb_demap) diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c index c3c12efe0bc0..9c0c8fd0b292 100644 --- a/arch/sparc/kernel/signal_32.c +++ b/arch/sparc/kernel/signal_32.c @@ -89,7 +89,7 @@ asmlinkage void do_sigreturn(struct pt_regs *regs) sf = (struct signal_frame __user *) regs->u_regs[UREG_FP]; /* 1. Make sure we are not getting garbage from the user */ - if (!invalid_frame_pointer(sf, sizeof(*sf))) + if (invalid_frame_pointer(sf, sizeof(*sf))) goto segv_and_exit; if (get_user(ufp, &sf->info.si_regs.u_regs[UREG_FP])) @@ -150,7 +150,7 @@ asmlinkage void do_rt_sigreturn(struct pt_regs *regs) synchronize_user_stack(); sf = (struct rt_signal_frame __user *) regs->u_regs[UREG_FP]; - if (!invalid_frame_pointer(sf, sizeof(*sf))) + if (invalid_frame_pointer(sf, sizeof(*sf))) goto segv; if (get_user(ufp, &sf->regs.u_regs[UREG_FP])) diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 439784b7b7ac..37aa537b3ad8 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -802,8 +802,10 @@ struct mdesc_mblock { }; static struct mdesc_mblock *mblocks; static int num_mblocks; +static int find_numa_node_for_addr(unsigned long pa, + struct node_mem_mask *pnode_mask); -static unsigned long ra_to_pa(unsigned long addr) +static unsigned long __init ra_to_pa(unsigned long addr) { int i; @@ -819,8 +821,11 @@ static unsigned long ra_to_pa(unsigned long addr) return addr; } -static int find_node(unsigned long addr) +static int __init find_node(unsigned long addr) { + static bool search_mdesc = true; + static struct node_mem_mask last_mem_mask = { ~0UL, ~0UL }; + static int last_index; int i; addr = ra_to_pa(addr); @@ -830,13 +835,30 @@ static int find_node(unsigned long addr) if ((addr & p->mask) == p->val) return i; } - /* The following condition has been observed on LDOM guests.*/ - WARN_ONCE(1, "find_node: A physical address doesn't match a NUMA node" - " rule. Some physical memory will be owned by node 0."); - return 0; + /* The following condition has been observed on LDOM guests because + * node_masks only contains the best latency mask and value. + * LDOM guest's mdesc can contain a single latency group to + * cover multiple address range. Print warning message only if the + * address cannot be found in node_masks nor mdesc. + */ + if ((search_mdesc) && + ((addr & last_mem_mask.mask) != last_mem_mask.val)) { + /* find the available node in the mdesc */ + last_index = find_numa_node_for_addr(addr, &last_mem_mask); + numadbg("find_node: latency group for address 0x%lx is %d\n", + addr, last_index); + if ((last_index < 0) || (last_index >= num_node_masks)) { + /* WARN_ONCE() and use default group 0 */ + WARN_ONCE(1, "find_node: A physical address doesn't match a NUMA node rule. Some physical memory will be owned by node 0."); + search_mdesc = false; + last_index = 0; + } + } + + return last_index; } -static u64 memblock_nid_range(u64 start, u64 end, int *nid) +static u64 __init memblock_nid_range(u64 start, u64 end, int *nid) { *nid = find_node(start); start += PAGE_SIZE; @@ -1160,6 +1182,41 @@ int __node_distance(int from, int to) return numa_latency[from][to]; } +static int find_numa_node_for_addr(unsigned long pa, + struct node_mem_mask *pnode_mask) +{ + struct mdesc_handle *md = mdesc_grab(); + u64 node, arc; + int i = 0; + + node = mdesc_node_by_name(md, MDESC_NODE_NULL, "latency-groups"); + if (node == MDESC_NODE_NULL) + goto out; + + mdesc_for_each_node_by_name(md, node, "group") { + mdesc_for_each_arc(arc, md, node, MDESC_ARC_TYPE_FWD) { + u64 target = mdesc_arc_target(md, arc); + struct mdesc_mlgroup *m = find_mlgroup(target); + + if (!m) + continue; + if ((pa & m->mask) == m->match) { + if (pnode_mask) { + pnode_mask->mask = m->mask; + pnode_mask->val = m->match; + } + mdesc_release(md); + return i; + } + } + i++; + } + +out: + mdesc_release(md); + return -1; +} + static int __init find_best_numa_node_for_mlgroup(struct mdesc_mlgroup *grp) { int i; diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 7717b19dc806..947adda3397d 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -962,9 +962,10 @@ static void b53_vlan_add(struct dsa_switch *ds, int port, vl->members |= BIT(port) | BIT(cpu_port); if (untagged) - vl->untag |= BIT(port) | BIT(cpu_port); + vl->untag |= BIT(port); else - vl->untag &= ~(BIT(port) | BIT(cpu_port)); + vl->untag &= ~BIT(port); + vl->untag &= ~BIT(cpu_port); b53_set_vlan_entry(dev, vid, vl); b53_fast_age_vlan(dev, vid); @@ -973,8 +974,6 @@ static void b53_vlan_add(struct dsa_switch *ds, int port, if (pvid) { b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(port), vlan->vid_end); - b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(cpu_port), - vlan->vid_end); b53_fast_age_vlan(dev, vid); } } @@ -984,7 +983,6 @@ static int b53_vlan_del(struct dsa_switch *ds, int port, { struct b53_device *dev = ds->priv; bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED; - unsigned int cpu_port = dev->cpu_port; struct b53_vlan *vl; u16 vid; u16 pvid; @@ -997,8 +995,6 @@ static int b53_vlan_del(struct dsa_switch *ds, int port, b53_get_vlan_entry(dev, vid, vl); vl->members &= ~BIT(port); - if ((vl->members & BIT(cpu_port)) == BIT(cpu_port)) - vl->members = 0; if (pvid == vid) { if (is5325(dev) || is5365(dev)) @@ -1007,18 +1003,14 @@ static int b53_vlan_del(struct dsa_switch *ds, int port, pvid = 0; } - if (untagged) { + if (untagged) vl->untag &= ~(BIT(port)); - if ((vl->untag & BIT(cpu_port)) == BIT(cpu_port)) - vl->untag = 0; - } b53_set_vlan_entry(dev, vid, vl); b53_fast_age_vlan(dev, vid); } b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(port), pvid); - b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(cpu_port), pvid); b53_fast_age_vlan(dev, pvid); return 0; diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c index b0da9693f28a..be865b4dada2 100644 --- a/drivers/net/ethernet/arc/emac_main.c +++ b/drivers/net/ethernet/arc/emac_main.c @@ -460,7 +460,7 @@ static void arc_emac_set_rx_mode(struct net_device *ndev) if (ndev->flags & IFF_ALLMULTI) { arc_reg_set(priv, R_LAFL, ~0); arc_reg_set(priv, R_LAFH, ~0); - } else { + } else if (ndev->flags & IFF_MULTICAST) { struct netdev_hw_addr *ha; unsigned int filter[2] = { 0, 0 }; int bit; @@ -472,6 +472,9 @@ static void arc_emac_set_rx_mode(struct net_device *ndev) arc_reg_set(priv, R_LAFL, filter[0]); arc_reg_set(priv, R_LAFH, filter[1]); + } else { + arc_reg_set(priv, R_LAFL, 0); + arc_reg_set(priv, R_LAFH, 0); } } } @@ -764,8 +767,6 @@ int arc_emac_probe(struct net_device *ndev, int interface) ndev->netdev_ops = &arc_emac_netdev_ops; ndev->ethtool_ops = &arc_emac_ethtool_ops; ndev->watchdog_timeo = TX_TIMEOUT; - /* FIXME :: no multicast support yet */ - ndev->flags &= ~IFF_MULTICAST; priv = netdev_priv(ndev); priv->dev = dev; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index c6909660e097..e18635b2a002 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -4934,6 +4934,10 @@ static void bnxt_del_napi(struct bnxt *bp) napi_hash_del(&bnapi->napi); netif_napi_del(&bnapi->napi); } + /* We called napi_hash_del() before netif_napi_del(), we need + * to respect an RCU grace period before freeing napi structures. + */ + synchronize_net(); } static void bnxt_init_napi(struct bnxt *bp) diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c index b32444a3ed79..533653bd7aec 100644 --- a/drivers/net/ethernet/cadence/macb.c +++ b/drivers/net/ethernet/cadence/macb.c @@ -2673,6 +2673,12 @@ static int at91ether_start_xmit(struct sk_buff *skb, struct net_device *dev) lp->skb_length = skb->len; lp->skb_physaddr = dma_map_single(NULL, skb->data, skb->len, DMA_TO_DEVICE); + if (dma_mapping_error(NULL, lp->skb_physaddr)) { + dev_kfree_skb_any(skb); + dev->stats.tx_dropped++; + netdev_err(dev, "%s: DMA mapping error\n", __func__); + return NETDEV_TX_OK; + } /* Set address of the data in the Transmit Address register */ macb_writel(lp, TAR, lp->skb_physaddr); diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h index 30426109711c..86bd93ce2ea3 100644 --- a/drivers/net/ethernet/cavium/thunder/nic.h +++ b/drivers/net/ethernet/cavium/thunder/nic.h @@ -47,7 +47,7 @@ /* Min/Max packet size */ #define NIC_HW_MIN_FRS 64 -#define NIC_HW_MAX_FRS 9200 /* 9216 max packet including FCS */ +#define NIC_HW_MAX_FRS 9190 /* Excluding L2 header and FCS */ /* Max pkinds */ #define NIC_MAX_PKIND 16 @@ -178,11 +178,11 @@ enum tx_stats_reg_offset { struct nicvf_hw_stats { u64 rx_bytes; + u64 rx_frames; u64 rx_ucast_frames; u64 rx_bcast_frames; u64 rx_mcast_frames; - u64 rx_fcs_errors; - u64 rx_l2_errors; + u64 rx_drops; u64 rx_drop_red; u64 rx_drop_red_bytes; u64 rx_drop_overrun; @@ -191,6 +191,19 @@ struct nicvf_hw_stats { u64 rx_drop_mcast; u64 rx_drop_l3_bcast; u64 rx_drop_l3_mcast; + u64 rx_fcs_errors; + u64 rx_l2_errors; + + u64 tx_bytes; + u64 tx_frames; + u64 tx_ucast_frames; + u64 tx_bcast_frames; + u64 tx_mcast_frames; + u64 tx_drops; +}; + +struct nicvf_drv_stats { + /* CQE Rx errs */ u64 rx_bgx_truncated_pkts; u64 rx_jabber_errs; u64 rx_fcs_errs; @@ -216,34 +229,30 @@ struct nicvf_hw_stats { u64 rx_l4_pclp; u64 rx_truncated_pkts; - u64 tx_bytes_ok; - u64 tx_ucast_frames_ok; - u64 tx_bcast_frames_ok; - u64 tx_mcast_frames_ok; - u64 tx_drops; -}; - -struct nicvf_drv_stats { - /* Rx */ - u64 rx_frames_ok; - u64 rx_frames_64; - u64 rx_frames_127; - u64 rx_frames_255; - u64 rx_frames_511; - u64 rx_frames_1023; - u64 rx_frames_1518; - u64 rx_frames_jumbo; - u64 rx_drops; - + /* CQE Tx errs */ + u64 tx_desc_fault; + u64 tx_hdr_cons_err; + u64 tx_subdesc_err; + u64 tx_max_size_exceeded; + u64 tx_imm_size_oflow; + u64 tx_data_seq_err; + u64 tx_mem_seq_err; + u64 tx_lock_viol; + u64 tx_data_fault; + u64 tx_tstmp_conflict; + u64 tx_tstmp_timeout; + u64 tx_mem_fault; + u64 tx_csum_overlap; + u64 tx_csum_overflow; + + /* driver debug stats */ u64 rcv_buffer_alloc_failures; - - /* Tx */ - u64 tx_frames_ok; - u64 tx_drops; u64 tx_tso; u64 tx_timeout; u64 txq_stop; u64 txq_wake; + + struct u64_stats_sync syncp; }; struct nicvf { @@ -282,7 +291,6 @@ struct nicvf { u8 node; u8 cpi_alg; - u16 mtu; bool link_up; u8 duplex; u32 speed; @@ -298,7 +306,7 @@ struct nicvf { /* Stats */ struct nicvf_hw_stats hw_stats; - struct nicvf_drv_stats drv_stats; + struct nicvf_drv_stats __percpu *drv_stats; struct bgx_stats bgx_stats; /* MSI-X */ diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c index 2bbf4cbf08b2..6677b96e1f3f 100644 --- a/drivers/net/ethernet/cavium/thunder/nic_main.c +++ b/drivers/net/ethernet/cavium/thunder/nic_main.c @@ -11,6 +11,7 @@ #include <linux/pci.h> #include <linux/etherdevice.h> #include <linux/of.h> +#include <linux/if_vlan.h> #include "nic_reg.h" #include "nic.h" @@ -260,18 +261,31 @@ static void nic_get_bgx_stats(struct nicpf *nic, struct bgx_stats_msg *bgx) /* Update hardware min/max frame size */ static int nic_update_hw_frs(struct nicpf *nic, int new_frs, int vf) { - if ((new_frs > NIC_HW_MAX_FRS) || (new_frs < NIC_HW_MIN_FRS)) { - dev_err(&nic->pdev->dev, - "Invalid MTU setting from VF%d rejected, should be between %d and %d\n", - vf, NIC_HW_MIN_FRS, NIC_HW_MAX_FRS); + int bgx, lmac, lmac_cnt; + u64 lmac_credits; + + if ((new_frs > NIC_HW_MAX_FRS) || (new_frs < NIC_HW_MIN_FRS)) return 1; - } - new_frs += ETH_HLEN; - if (new_frs <= nic->pkind.maxlen) - return 0; - nic->pkind.maxlen = new_frs; - nic_reg_write(nic, NIC_PF_PKIND_0_15_CFG, *(u64 *)&nic->pkind); + bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); + lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); + lmac += bgx * MAX_LMAC_PER_BGX; + + new_frs += VLAN_ETH_HLEN + ETH_FCS_LEN + 4; + + /* Update corresponding LMAC credits */ + lmac_cnt = bgx_get_lmac_count(nic->node, bgx); + lmac_credits = nic_reg_read(nic, NIC_PF_LMAC_0_7_CREDIT + (lmac * 8)); + lmac_credits &= ~(0xFFFFFULL << 12); + lmac_credits |= (((((48 * 1024) / lmac_cnt) - new_frs) / 16) << 12); + nic_reg_write(nic, NIC_PF_LMAC_0_7_CREDIT + (lmac * 8), lmac_credits); + + /* Enforce MTU in HW + * This config is supported only from 88xx pass 2.0 onwards. + */ + if (!pass1_silicon(nic->pdev)) + nic_reg_write(nic, + NIC_PF_LMAC_0_7_CFG2 + (lmac * 8), new_frs); return 0; } @@ -464,7 +478,7 @@ static int nic_init_hw(struct nicpf *nic) /* PKIND configuration */ nic->pkind.minlen = 0; - nic->pkind.maxlen = NIC_HW_MAX_FRS + ETH_HLEN; + nic->pkind.maxlen = NIC_HW_MAX_FRS + VLAN_ETH_HLEN + ETH_FCS_LEN + 4; nic->pkind.lenerr_en = 1; nic->pkind.rx_hdr = 0; nic->pkind.hdr_sl = 0; @@ -837,6 +851,7 @@ static int nic_reset_stat_counters(struct nicpf *nic, nic_reg_write(nic, reg_addr, 0); } } + return 0; } diff --git a/drivers/net/ethernet/cavium/thunder/nic_reg.h b/drivers/net/ethernet/cavium/thunder/nic_reg.h index edf779f5a227..80d46337cf29 100644 --- a/drivers/net/ethernet/cavium/thunder/nic_reg.h +++ b/drivers/net/ethernet/cavium/thunder/nic_reg.h @@ -106,6 +106,7 @@ #define NIC_PF_MPI_0_2047_CFG (0x210000) #define NIC_PF_RSSI_0_4097_RQ (0x220000) #define NIC_PF_LMAC_0_7_CFG (0x240000) +#define NIC_PF_LMAC_0_7_CFG2 (0x240100) #define NIC_PF_LMAC_0_7_SW_XOFF (0x242000) #define NIC_PF_LMAC_0_7_CREDIT (0x244000) #define NIC_PF_CHAN_0_255_TX_CFG (0x400000) diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c index ad4fddb55421..432bf6be57cb 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c @@ -36,11 +36,11 @@ struct nicvf_stat { static const struct nicvf_stat nicvf_hw_stats[] = { NICVF_HW_STAT(rx_bytes), + NICVF_HW_STAT(rx_frames), NICVF_HW_STAT(rx_ucast_frames), NICVF_HW_STAT(rx_bcast_frames), NICVF_HW_STAT(rx_mcast_frames), - NICVF_HW_STAT(rx_fcs_errors), - NICVF_HW_STAT(rx_l2_errors), + NICVF_HW_STAT(rx_drops), NICVF_HW_STAT(rx_drop_red), NICVF_HW_STAT(rx_drop_red_bytes), NICVF_HW_STAT(rx_drop_overrun), @@ -49,50 +49,59 @@ static const struct nicvf_stat nicvf_hw_stats[] = { NICVF_HW_STAT(rx_drop_mcast), NICVF_HW_STAT(rx_drop_l3_bcast), NICVF_HW_STAT(rx_drop_l3_mcast), - NICVF_HW_STAT(rx_bgx_truncated_pkts), - NICVF_HW_STAT(rx_jabber_errs), - NICVF_HW_STAT(rx_fcs_errs), - NICVF_HW_STAT(rx_bgx_errs), - NICVF_HW_STAT(rx_prel2_errs), - NICVF_HW_STAT(rx_l2_hdr_malformed), - NICVF_HW_STAT(rx_oversize), - NICVF_HW_STAT(rx_undersize), - NICVF_HW_STAT(rx_l2_len_mismatch), - NICVF_HW_STAT(rx_l2_pclp), - NICVF_HW_STAT(rx_ip_ver_errs), - NICVF_HW_STAT(rx_ip_csum_errs), - NICVF_HW_STAT(rx_ip_hdr_malformed), - NICVF_HW_STAT(rx_ip_payload_malformed), - NICVF_HW_STAT(rx_ip_ttl_errs), - NICVF_HW_STAT(rx_l3_pclp), - NICVF_HW_STAT(rx_l4_malformed), - NICVF_HW_STAT(rx_l4_csum_errs), - NICVF_HW_STAT(rx_udp_len_errs), - NICVF_HW_STAT(rx_l4_port_errs), - NICVF_HW_STAT(rx_tcp_flag_errs), - NICVF_HW_STAT(rx_tcp_offset_errs), - NICVF_HW_STAT(rx_l4_pclp), - NICVF_HW_STAT(rx_truncated_pkts), - NICVF_HW_STAT(tx_bytes_ok), - NICVF_HW_STAT(tx_ucast_frames_ok), - NICVF_HW_STAT(tx_bcast_frames_ok), - NICVF_HW_STAT(tx_mcast_frames_ok), + NICVF_HW_STAT(rx_fcs_errors), + NICVF_HW_STAT(rx_l2_errors), + NICVF_HW_STAT(tx_bytes), + NICVF_HW_STAT(tx_frames), + NICVF_HW_STAT(tx_ucast_frames), + NICVF_HW_STAT(tx_bcast_frames), + NICVF_HW_STAT(tx_mcast_frames), + NICVF_HW_STAT(tx_drops), }; static const struct nicvf_stat nicvf_drv_stats[] = { - NICVF_DRV_STAT(rx_frames_ok), - NICVF_DRV_STAT(rx_frames_64), - NICVF_DRV_STAT(rx_frames_127), - NICVF_DRV_STAT(rx_frames_255), - NICVF_DRV_STAT(rx_frames_511), - NICVF_DRV_STAT(rx_frames_1023), - NICVF_DRV_STAT(rx_frames_1518), - NICVF_DRV_STAT(rx_frames_jumbo), - NICVF_DRV_STAT(rx_drops), + NICVF_DRV_STAT(rx_bgx_truncated_pkts), + NICVF_DRV_STAT(rx_jabber_errs), + NICVF_DRV_STAT(rx_fcs_errs), + NICVF_DRV_STAT(rx_bgx_errs), + NICVF_DRV_STAT(rx_prel2_errs), + NICVF_DRV_STAT(rx_l2_hdr_malformed), + NICVF_DRV_STAT(rx_oversize), + NICVF_DRV_STAT(rx_undersize), + NICVF_DRV_STAT(rx_l2_len_mismatch), + NICVF_DRV_STAT(rx_l2_pclp), + NICVF_DRV_STAT(rx_ip_ver_errs), + NICVF_DRV_STAT(rx_ip_csum_errs), + NICVF_DRV_STAT(rx_ip_hdr_malformed), + NICVF_DRV_STAT(rx_ip_payload_malformed), + NICVF_DRV_STAT(rx_ip_ttl_errs), + NICVF_DRV_STAT(rx_l3_pclp), + NICVF_DRV_STAT(rx_l4_malformed), + NICVF_DRV_STAT(rx_l4_csum_errs), + NICVF_DRV_STAT(rx_udp_len_errs), + NICVF_DRV_STAT(rx_l4_port_errs), + NICVF_DRV_STAT(rx_tcp_flag_errs), + NICVF_DRV_STAT(rx_tcp_offset_errs), + NICVF_DRV_STAT(rx_l4_pclp), + NICVF_DRV_STAT(rx_truncated_pkts), + + NICVF_DRV_STAT(tx_desc_fault), + NICVF_DRV_STAT(tx_hdr_cons_err), + NICVF_DRV_STAT(tx_subdesc_err), + NICVF_DRV_STAT(tx_max_size_exceeded), + NICVF_DRV_STAT(tx_imm_size_oflow), + NICVF_DRV_STAT(tx_data_seq_err), + NICVF_DRV_STAT(tx_mem_seq_err), + NICVF_DRV_STAT(tx_lock_viol), + NICVF_DRV_STAT(tx_data_fault), + NICVF_DRV_STAT(tx_tstmp_conflict), + NICVF_DRV_STAT(tx_tstmp_timeout), + NICVF_DRV_STAT(tx_mem_fault), + NICVF_DRV_STAT(tx_csum_overlap), + NICVF_DRV_STAT(tx_csum_overflow), + NICVF_DRV_STAT(rcv_buffer_alloc_failures), - NICVF_DRV_STAT(tx_frames_ok), NICVF_DRV_STAT(tx_tso), - NICVF_DRV_STAT(tx_drops), NICVF_DRV_STAT(tx_timeout), NICVF_DRV_STAT(txq_stop), NICVF_DRV_STAT(txq_wake), @@ -278,8 +287,8 @@ static void nicvf_get_ethtool_stats(struct net_device *netdev, struct ethtool_stats *stats, u64 *data) { struct nicvf *nic = netdev_priv(netdev); - int stat; - int sqs; + int stat, tmp_stats; + int sqs, cpu; nicvf_update_stats(nic); @@ -289,9 +298,13 @@ static void nicvf_get_ethtool_stats(struct net_device *netdev, for (stat = 0; stat < nicvf_n_hw_stats; stat++) *(data++) = ((u64 *)&nic->hw_stats) [nicvf_hw_stats[stat].index]; - for (stat = 0; stat < nicvf_n_drv_stats; stat++) - *(data++) = ((u64 *)&nic->drv_stats) - [nicvf_drv_stats[stat].index]; + for (stat = 0; stat < nicvf_n_drv_stats; stat++) { + tmp_stats = 0; + for_each_possible_cpu(cpu) + tmp_stats += ((u64 *)per_cpu_ptr(nic->drv_stats, cpu)) + [nicvf_drv_stats[stat].index]; + *(data++) = tmp_stats; + } nicvf_get_qset_stats(nic, stats, &data); diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index 45a13f718863..8a37012c9c89 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -69,25 +69,6 @@ static inline u8 nicvf_netdev_qidx(struct nicvf *nic, u8 qidx) return qidx; } -static inline void nicvf_set_rx_frame_cnt(struct nicvf *nic, - struct sk_buff *skb) -{ - if (skb->len <= 64) - nic->drv_stats.rx_frames_64++; - else if (skb->len <= 127) - nic->drv_stats.rx_frames_127++; - else if (skb->len <= 255) - nic->drv_stats.rx_frames_255++; - else if (skb->len <= 511) - nic->drv_stats.rx_frames_511++; - else if (skb->len <= 1023) - nic->drv_stats.rx_frames_1023++; - else if (skb->len <= 1518) - nic->drv_stats.rx_frames_1518++; - else - nic->drv_stats.rx_frames_jumbo++; -} - /* The Cavium ThunderX network controller can *only* be found in SoCs * containing the ThunderX ARM64 CPU implementation. All accesses to the device * registers on this platform are implicitly strongly ordered with respect @@ -492,9 +473,6 @@ int nicvf_set_real_num_queues(struct net_device *netdev, static int nicvf_init_resources(struct nicvf *nic) { int err; - union nic_mbx mbx = {}; - - mbx.msg.msg = NIC_MBOX_MSG_CFG_DONE; /* Enable Qset */ nicvf_qset_config(nic, true); @@ -507,14 +485,10 @@ static int nicvf_init_resources(struct nicvf *nic) return err; } - /* Send VF config done msg to PF */ - nicvf_write_to_mbx(nic, &mbx); - return 0; } static void nicvf_snd_pkt_handler(struct net_device *netdev, - struct cmp_queue *cq, struct cqe_send_t *cqe_tx, int cqe_type, int budget, unsigned int *tx_pkts, unsigned int *tx_bytes) @@ -536,7 +510,7 @@ static void nicvf_snd_pkt_handler(struct net_device *netdev, __func__, cqe_tx->sq_qs, cqe_tx->sq_idx, cqe_tx->sqe_ptr, hdr->subdesc_cnt); - nicvf_check_cqe_tx_errs(nic, cq, cqe_tx); + nicvf_check_cqe_tx_errs(nic, cqe_tx); skb = (struct sk_buff *)sq->skbuff[cqe_tx->sqe_ptr]; if (skb) { /* Check for dummy descriptor used for HW TSO offload on 88xx */ @@ -630,8 +604,6 @@ static void nicvf_rcv_pkt_handler(struct net_device *netdev, return; } - nicvf_set_rx_frame_cnt(nic, skb); - nicvf_set_rxhash(netdev, cqe_rx, skb); skb_record_rx_queue(skb, rq_idx); @@ -703,7 +675,7 @@ loop: work_done++; break; case CQE_TYPE_SEND: - nicvf_snd_pkt_handler(netdev, cq, + nicvf_snd_pkt_handler(netdev, (void *)cq_desc, CQE_TYPE_SEND, budget, &tx_pkts, &tx_bytes); tx_done++; @@ -740,7 +712,7 @@ done: nic = nic->pnicvf; if (netif_tx_queue_stopped(txq) && netif_carrier_ok(netdev)) { netif_tx_start_queue(txq); - nic->drv_stats.txq_wake++; + this_cpu_inc(nic->drv_stats->txq_wake); if (netif_msg_tx_err(nic)) netdev_warn(netdev, "%s: Transmit queue wakeup SQ%d\n", @@ -1084,7 +1056,7 @@ static netdev_tx_t nicvf_xmit(struct sk_buff *skb, struct net_device *netdev) if (!netif_tx_queue_stopped(txq) && !nicvf_sq_append_skb(nic, skb)) { netif_tx_stop_queue(txq); - nic->drv_stats.txq_stop++; + this_cpu_inc(nic->drv_stats->txq_stop); if (netif_msg_tx_err(nic)) netdev_warn(netdev, "%s: Transmit ring full, stopping SQ%d\n", @@ -1189,14 +1161,24 @@ int nicvf_stop(struct net_device *netdev) return 0; } +static int nicvf_update_hw_max_frs(struct nicvf *nic, int mtu) +{ + union nic_mbx mbx = {}; + + mbx.frs.msg = NIC_MBOX_MSG_SET_MAX_FRS; + mbx.frs.max_frs = mtu; + mbx.frs.vf_id = nic->vf_id; + + return nicvf_send_msg_to_pf(nic, &mbx); +} + int nicvf_open(struct net_device *netdev) { - int err, qidx; + int cpu, err, qidx; struct nicvf *nic = netdev_priv(netdev); struct queue_set *qs = nic->qs; struct nicvf_cq_poll *cq_poll = NULL; - - nic->mtu = netdev->mtu; + union nic_mbx mbx = {}; netif_carrier_off(netdev); @@ -1248,9 +1230,17 @@ int nicvf_open(struct net_device *netdev) if (nic->sqs_mode) nicvf_get_primary_vf_struct(nic); - /* Configure receive side scaling */ - if (!nic->sqs_mode) + /* Configure receive side scaling and MTU */ + if (!nic->sqs_mode) { nicvf_rss_init(nic); + if (nicvf_update_hw_max_frs(nic, netdev->mtu)) + goto cleanup; + + /* Clear percpu stats */ + for_each_possible_cpu(cpu) + memset(per_cpu_ptr(nic->drv_stats, cpu), 0, + sizeof(struct nicvf_drv_stats)); + } err = nicvf_register_interrupts(nic); if (err) @@ -1276,8 +1266,9 @@ int nicvf_open(struct net_device *netdev) for (qidx = 0; qidx < qs->rbdr_cnt; qidx++) nicvf_enable_intr(nic, NICVF_INTR_RBDR, qidx); - nic->drv_stats.txq_stop = 0; - nic->drv_stats.txq_wake = 0; + /* Send VF config done msg to PF */ + mbx.msg.msg = NIC_MBOX_MSG_CFG_DONE; + nicvf_write_to_mbx(nic, &mbx); return 0; cleanup: @@ -1297,17 +1288,6 @@ napi_del: return err; } -static int nicvf_update_hw_max_frs(struct nicvf *nic, int mtu) -{ - union nic_mbx mbx = {}; - - mbx.frs.msg = NIC_MBOX_MSG_SET_MAX_FRS; - mbx.frs.max_frs = mtu; - mbx.frs.vf_id = nic->vf_id; - - return nicvf_send_msg_to_pf(nic, &mbx); -} - static int nicvf_change_mtu(struct net_device *netdev, int new_mtu) { struct nicvf *nic = netdev_priv(netdev); @@ -1318,10 +1298,13 @@ static int nicvf_change_mtu(struct net_device *netdev, int new_mtu) if (new_mtu < NIC_HW_MIN_FRS) return -EINVAL; + netdev->mtu = new_mtu; + + if (!netif_running(netdev)) + return 0; + if (nicvf_update_hw_max_frs(nic, new_mtu)) return -EINVAL; - netdev->mtu = new_mtu; - nic->mtu = new_mtu; return 0; } @@ -1379,9 +1362,10 @@ void nicvf_update_lmac_stats(struct nicvf *nic) void nicvf_update_stats(struct nicvf *nic) { - int qidx; + int qidx, cpu; + u64 tmp_stats = 0; struct nicvf_hw_stats *stats = &nic->hw_stats; - struct nicvf_drv_stats *drv_stats = &nic->drv_stats; + struct nicvf_drv_stats *drv_stats; struct queue_set *qs = nic->qs; #define GET_RX_STATS(reg) \ @@ -1404,21 +1388,33 @@ void nicvf_update_stats(struct nicvf *nic) stats->rx_drop_l3_bcast = GET_RX_STATS(RX_DRP_L3BCAST); stats->rx_drop_l3_mcast = GET_RX_STATS(RX_DRP_L3MCAST); - stats->tx_bytes_ok = GET_TX_STATS(TX_OCTS); - stats->tx_ucast_frames_ok = GET_TX_STATS(TX_UCAST); - stats->tx_bcast_frames_ok = GET_TX_STATS(TX_BCAST); - stats->tx_mcast_frames_ok = GET_TX_STATS(TX_MCAST); + stats->tx_bytes = GET_TX_STATS(TX_OCTS); + stats->tx_ucast_frames = GET_TX_STATS(TX_UCAST); + stats->tx_bcast_frames = GET_TX_STATS(TX_BCAST); + stats->tx_mcast_frames = GET_TX_STATS(TX_MCAST); stats->tx_drops = GET_TX_STATS(TX_DROP); - drv_stats->tx_frames_ok = stats->tx_ucast_frames_ok + - stats->tx_bcast_frames_ok + - stats->tx_mcast_frames_ok; - drv_stats->rx_frames_ok = stats->rx_ucast_frames + - stats->rx_bcast_frames + - stats->rx_mcast_frames; - drv_stats->rx_drops = stats->rx_drop_red + - stats->rx_drop_overrun; - drv_stats->tx_drops = stats->tx_drops; + /* On T88 pass 2.0, the dummy SQE added for TSO notification + * via CQE has 'dont_send' set. Hence HW drops the pkt pointed + * pointed by dummy SQE and results in tx_drops counter being + * incremented. Subtracting it from tx_tso counter will give + * exact tx_drops counter. + */ + if (nic->t88 && nic->hw_tso) { + for_each_possible_cpu(cpu) { + drv_stats = per_cpu_ptr(nic->drv_stats, cpu); + tmp_stats += drv_stats->tx_tso; + } + stats->tx_drops = tmp_stats - stats->tx_drops; + } + stats->tx_frames = stats->tx_ucast_frames + + stats->tx_bcast_frames + + stats->tx_mcast_frames; + stats->rx_frames = stats->rx_ucast_frames + + stats->rx_bcast_frames + + stats->rx_mcast_frames; + stats->rx_drops = stats->rx_drop_red + + stats->rx_drop_overrun; /* Update RQ and SQ stats */ for (qidx = 0; qidx < qs->rq_cnt; qidx++) @@ -1432,18 +1428,17 @@ static struct rtnl_link_stats64 *nicvf_get_stats64(struct net_device *netdev, { struct nicvf *nic = netdev_priv(netdev); struct nicvf_hw_stats *hw_stats = &nic->hw_stats; - struct nicvf_drv_stats *drv_stats = &nic->drv_stats; nicvf_update_stats(nic); stats->rx_bytes = hw_stats->rx_bytes; - stats->rx_packets = drv_stats->rx_frames_ok; - stats->rx_dropped = drv_stats->rx_drops; + stats->rx_packets = hw_stats->rx_frames; + stats->rx_dropped = hw_stats->rx_drops; stats->multicast = hw_stats->rx_mcast_frames; - stats->tx_bytes = hw_stats->tx_bytes_ok; - stats->tx_packets = drv_stats->tx_frames_ok; - stats->tx_dropped = drv_stats->tx_drops; + stats->tx_bytes = hw_stats->tx_bytes; + stats->tx_packets = hw_stats->tx_frames; + stats->tx_dropped = hw_stats->tx_drops; return stats; } @@ -1456,7 +1451,7 @@ static void nicvf_tx_timeout(struct net_device *dev) netdev_warn(dev, "%s: Transmit timed out, resetting\n", dev->name); - nic->drv_stats.tx_timeout++; + this_cpu_inc(nic->drv_stats->tx_timeout); schedule_work(&nic->reset_task); } @@ -1590,6 +1585,12 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_free_netdev; } + nic->drv_stats = netdev_alloc_pcpu_stats(struct nicvf_drv_stats); + if (!nic->drv_stats) { + err = -ENOMEM; + goto err_free_netdev; + } + err = nicvf_set_qset_resources(nic); if (err) goto err_free_netdev; @@ -1648,6 +1649,8 @@ err_unregister_interrupts: nicvf_unregister_interrupts(nic); err_free_netdev: pci_set_drvdata(pdev, NULL); + if (nic->drv_stats) + free_percpu(nic->drv_stats); free_netdev(netdev); err_release_regions: pci_release_regions(pdev); @@ -1675,6 +1678,8 @@ static void nicvf_remove(struct pci_dev *pdev) unregister_netdev(pnetdev); nicvf_unregister_interrupts(nic); pci_set_drvdata(pdev, NULL); + if (nic->drv_stats) + free_percpu(nic->drv_stats); free_netdev(netdev); pci_release_regions(pdev); pci_disable_device(pdev); diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c index a4fc50155881..747ef0882976 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c @@ -104,7 +104,8 @@ static inline int nicvf_alloc_rcv_buffer(struct nicvf *nic, gfp_t gfp, nic->rb_page = alloc_pages(gfp | __GFP_COMP | __GFP_NOWARN, order); if (!nic->rb_page) { - nic->drv_stats.rcv_buffer_alloc_failures++; + this_cpu_inc(nic->pnicvf->drv_stats-> + rcv_buffer_alloc_failures); return -ENOMEM; } nic->rb_page_offset = 0; @@ -270,7 +271,8 @@ refill: rbdr_idx, new_rb); next_rbdr: /* Re-enable RBDR interrupts only if buffer allocation is success */ - if (!nic->rb_alloc_fail && rbdr->enable) + if (!nic->rb_alloc_fail && rbdr->enable && + netif_running(nic->pnicvf->netdev)) nicvf_enable_intr(nic, NICVF_INTR_RBDR, rbdr_idx); if (rbdr_idx) @@ -361,6 +363,8 @@ static int nicvf_init_snd_queue(struct nicvf *nic, static void nicvf_free_snd_queue(struct nicvf *nic, struct snd_queue *sq) { + struct sk_buff *skb; + if (!sq) return; if (!sq->dmem.base) @@ -371,6 +375,15 @@ static void nicvf_free_snd_queue(struct nicvf *nic, struct snd_queue *sq) sq->dmem.q_len * TSO_HEADER_SIZE, sq->tso_hdrs, sq->tso_hdrs_phys); + /* Free pending skbs in the queue */ + smp_rmb(); + while (sq->head != sq->tail) { + skb = (struct sk_buff *)sq->skbuff[sq->head]; + if (skb) + dev_kfree_skb_any(skb); + sq->head++; + sq->head &= (sq->dmem.q_len - 1); + } kfree(sq->skbuff); nicvf_free_q_desc_mem(nic, &sq->dmem); } @@ -483,9 +496,12 @@ static void nicvf_reset_rcv_queue_stats(struct nicvf *nic) { union nic_mbx mbx = {}; - /* Reset all RXQ's stats */ + /* Reset all RQ/SQ and VF stats */ mbx.reset_stat.msg = NIC_MBOX_MSG_RESET_STAT_COUNTER; + mbx.reset_stat.rx_stat_mask = 0x3FFF; + mbx.reset_stat.tx_stat_mask = 0x1F; mbx.reset_stat.rq_stat_mask = 0xFFFF; + mbx.reset_stat.sq_stat_mask = 0xFFFF; nicvf_send_msg_to_pf(nic, &mbx); } @@ -538,9 +554,12 @@ static void nicvf_rcv_queue_config(struct nicvf *nic, struct queue_set *qs, mbx.rq.cfg = (1ULL << 62) | (RQ_CQ_DROP << 8); nicvf_send_msg_to_pf(nic, &mbx); - nicvf_queue_reg_write(nic, NIC_QSET_RQ_GEN_CFG, 0, 0x00); - if (!nic->sqs_mode) + if (!nic->sqs_mode && (qidx == 0)) { + /* Enable checking L3/L4 length and TCP/UDP checksums */ + nicvf_queue_reg_write(nic, NIC_QSET_RQ_GEN_CFG, 0, + (BIT(24) | BIT(23) | BIT(21))); nicvf_config_vlan_stripping(nic, nic->netdev->features); + } /* Enable Receive queue */ memset(&rq_cfg, 0, sizeof(struct rq_cfg)); @@ -1029,7 +1048,7 @@ nicvf_sq_add_hdr_subdesc(struct nicvf *nic, struct snd_queue *sq, int qentry, hdr->tso_max_paysize = skb_shinfo(skb)->gso_size; /* For non-tunneled pkts, point this to L2 ethertype */ hdr->inner_l3_offset = skb_network_offset(skb) - 2; - nic->drv_stats.tx_tso++; + this_cpu_inc(nic->pnicvf->drv_stats->tx_tso); } } @@ -1161,7 +1180,7 @@ static int nicvf_sq_append_tso(struct nicvf *nic, struct snd_queue *sq, nicvf_sq_doorbell(nic, skb, sq_num, desc_cnt); - nic->drv_stats.tx_tso++; + this_cpu_inc(nic->pnicvf->drv_stats->tx_tso); return 1; } @@ -1422,8 +1441,6 @@ void nicvf_update_sq_stats(struct nicvf *nic, int sq_idx) /* Check for errors in the receive cmp.queue entry */ int nicvf_check_cqe_rx_errs(struct nicvf *nic, struct cqe_rx_t *cqe_rx) { - struct nicvf_hw_stats *stats = &nic->hw_stats; - if (!cqe_rx->err_level && !cqe_rx->err_opcode) return 0; @@ -1435,76 +1452,76 @@ int nicvf_check_cqe_rx_errs(struct nicvf *nic, struct cqe_rx_t *cqe_rx) switch (cqe_rx->err_opcode) { case CQ_RX_ERROP_RE_PARTIAL: - stats->rx_bgx_truncated_pkts++; + this_cpu_inc(nic->drv_stats->rx_bgx_truncated_pkts); break; case CQ_RX_ERROP_RE_JABBER: - stats->rx_jabber_errs++; + this_cpu_inc(nic->drv_stats->rx_jabber_errs); break; case CQ_RX_ERROP_RE_FCS: - stats->rx_fcs_errs++; + this_cpu_inc(nic->drv_stats->rx_fcs_errs); break; case CQ_RX_ERROP_RE_RX_CTL: - stats->rx_bgx_errs++; + this_cpu_inc(nic->drv_stats->rx_bgx_errs); break; case CQ_RX_ERROP_PREL2_ERR: - stats->rx_prel2_errs++; + this_cpu_inc(nic->drv_stats->rx_prel2_errs); break; case CQ_RX_ERROP_L2_MAL: - stats->rx_l2_hdr_malformed++; + this_cpu_inc(nic->drv_stats->rx_l2_hdr_malformed); break; case CQ_RX_ERROP_L2_OVERSIZE: - stats->rx_oversize++; + this_cpu_inc(nic->drv_stats->rx_oversize); break; case CQ_RX_ERROP_L2_UNDERSIZE: - stats->rx_undersize++; + this_cpu_inc(nic->drv_stats->rx_undersize); break; case CQ_RX_ERROP_L2_LENMISM: - stats->rx_l2_len_mismatch++; + this_cpu_inc(nic->drv_stats->rx_l2_len_mismatch); break; case CQ_RX_ERROP_L2_PCLP: - stats->rx_l2_pclp++; + this_cpu_inc(nic->drv_stats->rx_l2_pclp); break; case CQ_RX_ERROP_IP_NOT: - stats->rx_ip_ver_errs++; + this_cpu_inc(nic->drv_stats->rx_ip_ver_errs); break; case CQ_RX_ERROP_IP_CSUM_ERR: - stats->rx_ip_csum_errs++; + this_cpu_inc(nic->drv_stats->rx_ip_csum_errs); break; case CQ_RX_ERROP_IP_MAL: - stats->rx_ip_hdr_malformed++; + this_cpu_inc(nic->drv_stats->rx_ip_hdr_malformed); break; case CQ_RX_ERROP_IP_MALD: - stats->rx_ip_payload_malformed++; + this_cpu_inc(nic->drv_stats->rx_ip_payload_malformed); break; case CQ_RX_ERROP_IP_HOP: - stats->rx_ip_ttl_errs++; + this_cpu_inc(nic->drv_stats->rx_ip_ttl_errs); break; case CQ_RX_ERROP_L3_PCLP: - stats->rx_l3_pclp++; + this_cpu_inc(nic->drv_stats->rx_l3_pclp); break; case CQ_RX_ERROP_L4_MAL: - stats->rx_l4_malformed++; + this_cpu_inc(nic->drv_stats->rx_l4_malformed); break; case CQ_RX_ERROP_L4_CHK: - stats->rx_l4_csum_errs++; + this_cpu_inc(nic->drv_stats->rx_l4_csum_errs); break; case CQ_RX_ERROP_UDP_LEN: - stats->rx_udp_len_errs++; + this_cpu_inc(nic->drv_stats->rx_udp_len_errs); break; case CQ_RX_ERROP_L4_PORT: - stats->rx_l4_port_errs++; + this_cpu_inc(nic->drv_stats->rx_l4_port_errs); break; case CQ_RX_ERROP_TCP_FLAG: - stats->rx_tcp_flag_errs++; + this_cpu_inc(nic->drv_stats->rx_tcp_flag_errs); break; case CQ_RX_ERROP_TCP_OFFSET: - stats->rx_tcp_offset_errs++; + this_cpu_inc(nic->drv_stats->rx_tcp_offset_errs); break; case CQ_RX_ERROP_L4_PCLP: - stats->rx_l4_pclp++; + this_cpu_inc(nic->drv_stats->rx_l4_pclp); break; case CQ_RX_ERROP_RBDR_TRUNC: - stats->rx_truncated_pkts++; + this_cpu_inc(nic->drv_stats->rx_truncated_pkts); break; } @@ -1512,53 +1529,52 @@ int nicvf_check_cqe_rx_errs(struct nicvf *nic, struct cqe_rx_t *cqe_rx) } /* Check for errors in the send cmp.queue entry */ -int nicvf_check_cqe_tx_errs(struct nicvf *nic, - struct cmp_queue *cq, struct cqe_send_t *cqe_tx) +int nicvf_check_cqe_tx_errs(struct nicvf *nic, struct cqe_send_t *cqe_tx) { - struct cmp_queue_stats *stats = &cq->stats; - switch (cqe_tx->send_status) { case CQ_TX_ERROP_GOOD: - stats->tx.good++; return 0; case CQ_TX_ERROP_DESC_FAULT: - stats->tx.desc_fault++; + this_cpu_inc(nic->drv_stats->tx_desc_fault); break; case CQ_TX_ERROP_HDR_CONS_ERR: - stats->tx.hdr_cons_err++; + this_cpu_inc(nic->drv_stats->tx_hdr_cons_err); break; case CQ_TX_ERROP_SUBDC_ERR: - stats->tx.subdesc_err++; + this_cpu_inc(nic->drv_stats->tx_subdesc_err); + break; + case CQ_TX_ERROP_MAX_SIZE_VIOL: + this_cpu_inc(nic->drv_stats->tx_max_size_exceeded); break; case CQ_TX_ERROP_IMM_SIZE_OFLOW: - stats->tx.imm_size_oflow++; + this_cpu_inc(nic->drv_stats->tx_imm_size_oflow); break; case CQ_TX_ERROP_DATA_SEQUENCE_ERR: - stats->tx.data_seq_err++; + this_cpu_inc(nic->drv_stats->tx_data_seq_err); break; case CQ_TX_ERROP_MEM_SEQUENCE_ERR: - stats->tx.mem_seq_err++; + this_cpu_inc(nic->drv_stats->tx_mem_seq_err); break; case CQ_TX_ERROP_LOCK_VIOL: - stats->tx.lock_viol++; + this_cpu_inc(nic->drv_stats->tx_lock_viol); break; case CQ_TX_ERROP_DATA_FAULT: - stats->tx.data_fault++; + this_cpu_inc(nic->drv_stats->tx_data_fault); break; case CQ_TX_ERROP_TSTMP_CONFLICT: - stats->tx.tstmp_conflict++; + this_cpu_inc(nic->drv_stats->tx_tstmp_conflict); break; case CQ_TX_ERROP_TSTMP_TIMEOUT: - stats->tx.tstmp_timeout++; + this_cpu_inc(nic->drv_stats->tx_tstmp_timeout); break; case CQ_TX_ERROP_MEM_FAULT: - stats->tx.mem_fault++; + this_cpu_inc(nic->drv_stats->tx_mem_fault); break; case CQ_TX_ERROP_CK_OVERLAP: - stats->tx.csum_overlap++; + this_cpu_inc(nic->drv_stats->tx_csum_overlap); break; case CQ_TX_ERROP_CK_OFLOW: - stats->tx.csum_overflow++; + this_cpu_inc(nic->drv_stats->tx_csum_overflow); break; } diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h index 869f3386028b..2e3c940c1093 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h +++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h @@ -158,6 +158,7 @@ enum CQ_TX_ERROP_E { CQ_TX_ERROP_DESC_FAULT = 0x10, CQ_TX_ERROP_HDR_CONS_ERR = 0x11, CQ_TX_ERROP_SUBDC_ERR = 0x12, + CQ_TX_ERROP_MAX_SIZE_VIOL = 0x13, CQ_TX_ERROP_IMM_SIZE_OFLOW = 0x80, CQ_TX_ERROP_DATA_SEQUENCE_ERR = 0x81, CQ_TX_ERROP_MEM_SEQUENCE_ERR = 0x82, @@ -171,25 +172,6 @@ enum CQ_TX_ERROP_E { CQ_TX_ERROP_ENUM_LAST = 0x8a, }; -struct cmp_queue_stats { - struct tx_stats { - u64 good; - u64 desc_fault; - u64 hdr_cons_err; - u64 subdesc_err; - u64 imm_size_oflow; - u64 data_seq_err; - u64 mem_seq_err; - u64 lock_viol; - u64 data_fault; - u64 tstmp_conflict; - u64 tstmp_timeout; - u64 mem_fault; - u64 csum_overlap; - u64 csum_overflow; - } tx; -} ____cacheline_aligned_in_smp; - enum RQ_SQ_STATS { RQ_SQ_STATS_OCTS, RQ_SQ_STATS_PKTS, @@ -241,7 +223,6 @@ struct cmp_queue { spinlock_t lock; /* lock to serialize processing CQEs */ void *desc; struct q_desc_mem dmem; - struct cmp_queue_stats stats; int irq; } ____cacheline_aligned_in_smp; @@ -336,6 +317,5 @@ u64 nicvf_queue_reg_read(struct nicvf *nic, void nicvf_update_rq_stats(struct nicvf *nic, int rq_idx); void nicvf_update_sq_stats(struct nicvf *nic, int sq_idx); int nicvf_check_cqe_rx_errs(struct nicvf *nic, struct cqe_rx_t *cqe_rx); -int nicvf_check_cqe_tx_errs(struct nicvf *nic, - struct cmp_queue *cq, struct cqe_send_t *cqe_tx); +int nicvf_check_cqe_tx_errs(struct nicvf *nic, struct cqe_send_t *cqe_tx); #endif /* NICVF_QUEUES_H */ diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index 8bbaedbb7b94..050e21fbb147 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -1242,8 +1242,8 @@ static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pci_read_config_word(pdev, PCI_DEVICE_ID, &sdevid); if (sdevid != PCI_DEVICE_ID_THUNDER_RGX) { - bgx->bgx_id = - (pci_resource_start(pdev, PCI_CFG_REG_BAR_NUM) >> 24) & 1; + bgx->bgx_id = (pci_resource_start(pdev, + PCI_CFG_REG_BAR_NUM) >> 24) & BGX_ID_MASK; bgx->bgx_id += nic_get_node_id(pdev) * MAX_BGX_PER_NODE; bgx->max_lmac = MAX_LMAC_PER_BGX; bgx_vnic[bgx->bgx_id] = bgx; diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h index d59c71e4a000..01cc7c859131 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h @@ -28,6 +28,8 @@ #define MAX_DMAC_PER_LMAC 8 #define MAX_FRAME_SIZE 9216 +#define BGX_ID_MASK 0x3 + #define MAX_DMAC_PER_LMAC_TNS_BYPASS_MODE 2 /* Registers */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index 1e74fd6085df..e19a0ca8e5dd 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -2951,7 +2951,6 @@ void free_rspq_fl(struct adapter *adap, struct sge_rspq *rq, rq->cntxt_id, fl_id, 0xffff); dma_free_coherent(adap->pdev_dev, (rq->size + 1) * rq->iqe_len, rq->desc, rq->phys_addr); - napi_hash_del(&rq->napi); netif_napi_del(&rq->napi); rq->netdev = NULL; rq->cntxt_id = rq->abs_id = 0; diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index cece8a08edca..93aa2939142a 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -2813,7 +2813,6 @@ static void be_evt_queues_destroy(struct be_adapter *adapter) if (eqo->q.created) { be_eq_clean(eqo); be_cmd_q_destroy(adapter, &eqo->q, QTYPE_EQ); - napi_hash_del(&eqo->napi); netif_napi_del(&eqo->napi); free_cpumask_var(eqo->affinity_mask); } diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c index f05ea56dcff2..941c8e2c944e 100644 --- a/drivers/net/ethernet/marvell/sky2.c +++ b/drivers/net/ethernet/marvell/sky2.c @@ -5220,6 +5220,19 @@ static SIMPLE_DEV_PM_OPS(sky2_pm_ops, sky2_suspend, sky2_resume); static void sky2_shutdown(struct pci_dev *pdev) { + struct sky2_hw *hw = pci_get_drvdata(pdev); + int port; + + for (port = 0; port < hw->ports; port++) { + struct net_device *ndev = hw->dev[port]; + + rtnl_lock(); + if (netif_running(ndev)) { + dev_close(ndev); + netif_device_detach(ndev); + } + rtnl_unlock(); + } sky2_suspend(&pdev->dev); pci_wake_from_d3(pdev, device_may_wakeup(&pdev->dev)); pci_set_power_state(pdev, PCI_D3hot); diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig index 3818c5e06eba..4b78168a5f3c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/Kconfig +++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig @@ -107,7 +107,7 @@ config DWMAC_STI config DWMAC_STM32 tristate "STM32 DWMAC support" default ARCH_STM32 - depends on OF && HAS_IOMEM + depends on OF && HAS_IOMEM && (ARCH_STM32 || COMPILE_TEST) select MFD_SYSCON ---help--- Support for ethernet controller on STM32 SOCs. diff --git a/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c b/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c index 2920e2ee3864..489ef146201e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c +++ b/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c @@ -63,8 +63,8 @@ #define TSE_PCS_SGMII_LINK_TIMER_0 0x0D40 #define TSE_PCS_SGMII_LINK_TIMER_1 0x0003 #define TSE_PCS_SW_RESET_TIMEOUT 100 -#define TSE_PCS_USE_SGMII_AN_MASK BIT(2) -#define TSE_PCS_USE_SGMII_ENA BIT(1) +#define TSE_PCS_USE_SGMII_AN_MASK BIT(1) +#define TSE_PCS_USE_SGMII_ENA BIT(0) #define SGMII_ADAPTER_CTRL_REG 0x00 #define SGMII_ADAPTER_DISABLE 0x0001 diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index d3292c4a6eda..6d2de4e01f6d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -120,14 +120,17 @@ struct stmmac_extra_stats { unsigned long ip_csum_bypassed; unsigned long ipv4_pkt_rcvd; unsigned long ipv6_pkt_rcvd; - unsigned long rx_msg_type_ext_no_ptp; - unsigned long rx_msg_type_sync; - unsigned long rx_msg_type_follow_up; - unsigned long rx_msg_type_delay_req; - unsigned long rx_msg_type_delay_resp; - unsigned long rx_msg_type_pdelay_req; - unsigned long rx_msg_type_pdelay_resp; - unsigned long rx_msg_type_pdelay_follow_up; + unsigned long no_ptp_rx_msg_type_ext; + unsigned long ptp_rx_msg_type_sync; + unsigned long ptp_rx_msg_type_follow_up; + unsigned long ptp_rx_msg_type_delay_req; + unsigned long ptp_rx_msg_type_delay_resp; + unsigned long ptp_rx_msg_type_pdelay_req; + unsigned long ptp_rx_msg_type_pdelay_resp; + unsigned long ptp_rx_msg_type_pdelay_follow_up; + unsigned long ptp_rx_msg_type_announce; + unsigned long ptp_rx_msg_type_management; + unsigned long ptp_rx_msg_pkt_reserved_type; unsigned long ptp_frame_type; unsigned long ptp_ver; unsigned long timestamp_dropped; @@ -482,11 +485,12 @@ struct stmmac_ops { /* PTP and HW Timer helpers */ struct stmmac_hwtimestamp { void (*config_hw_tstamping) (void __iomem *ioaddr, u32 data); - u32 (*config_sub_second_increment) (void __iomem *ioaddr, u32 clk_rate); + u32 (*config_sub_second_increment)(void __iomem *ioaddr, u32 ptp_clock, + int gmac4); int (*init_systime) (void __iomem *ioaddr, u32 sec, u32 nsec); int (*config_addend) (void __iomem *ioaddr, u32 addend); int (*adjust_systime) (void __iomem *ioaddr, u32 sec, u32 nsec, - int add_sub); + int add_sub, int gmac4); u64(*get_systime) (void __iomem *ioaddr); }; diff --git a/drivers/net/ethernet/stmicro/stmmac/descs.h b/drivers/net/ethernet/stmicro/stmmac/descs.h index 2e4c171a2b41..e3c86d422109 100644 --- a/drivers/net/ethernet/stmicro/stmmac/descs.h +++ b/drivers/net/ethernet/stmicro/stmmac/descs.h @@ -155,14 +155,18 @@ #define ERDES4_L3_L4_FILT_NO_MATCH_MASK GENMASK(27, 26) /* Extended RDES4 message type definitions */ -#define RDES_EXT_NO_PTP 0 -#define RDES_EXT_SYNC 1 -#define RDES_EXT_FOLLOW_UP 2 -#define RDES_EXT_DELAY_REQ 3 -#define RDES_EXT_DELAY_RESP 4 -#define RDES_EXT_PDELAY_REQ 5 -#define RDES_EXT_PDELAY_RESP 6 -#define RDES_EXT_PDELAY_FOLLOW_UP 7 +#define RDES_EXT_NO_PTP 0x0 +#define RDES_EXT_SYNC 0x1 +#define RDES_EXT_FOLLOW_UP 0x2 +#define RDES_EXT_DELAY_REQ 0x3 +#define RDES_EXT_DELAY_RESP 0x4 +#define RDES_EXT_PDELAY_REQ 0x5 +#define RDES_EXT_PDELAY_RESP 0x6 +#define RDES_EXT_PDELAY_FOLLOW_UP 0x7 +#define RDES_PTP_ANNOUNCE 0x8 +#define RDES_PTP_MANAGEMENT 0x9 +#define RDES_PTP_SIGNALING 0xa +#define RDES_PTP_PKT_RESERVED_TYPE 0xf /* Basic descriptor structure for normal and alternate descriptors */ struct dma_desc { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c index a1b17cd7886b..a601f8d43b75 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c @@ -123,22 +123,29 @@ static int dwmac4_wrback_get_rx_status(void *data, struct stmmac_extra_stats *x, x->ipv4_pkt_rcvd++; if (rdes1 & RDES1_IPV6_HEADER) x->ipv6_pkt_rcvd++; - if (message_type == RDES_EXT_SYNC) - x->rx_msg_type_sync++; + + if (message_type == RDES_EXT_NO_PTP) + x->no_ptp_rx_msg_type_ext++; + else if (message_type == RDES_EXT_SYNC) + x->ptp_rx_msg_type_sync++; else if (message_type == RDES_EXT_FOLLOW_UP) - x->rx_msg_type_follow_up++; + x->ptp_rx_msg_type_follow_up++; else if (message_type == RDES_EXT_DELAY_REQ) - x->rx_msg_type_delay_req++; + x->ptp_rx_msg_type_delay_req++; else if (message_type == RDES_EXT_DELAY_RESP) - x->rx_msg_type_delay_resp++; + x->ptp_rx_msg_type_delay_resp++; else if (message_type == RDES_EXT_PDELAY_REQ) - x->rx_msg_type_pdelay_req++; + x->ptp_rx_msg_type_pdelay_req++; else if (message_type == RDES_EXT_PDELAY_RESP) - x->rx_msg_type_pdelay_resp++; + x->ptp_rx_msg_type_pdelay_resp++; else if (message_type == RDES_EXT_PDELAY_FOLLOW_UP) - x->rx_msg_type_pdelay_follow_up++; - else - x->rx_msg_type_ext_no_ptp++; + x->ptp_rx_msg_type_pdelay_follow_up++; + else if (message_type == RDES_PTP_ANNOUNCE) + x->ptp_rx_msg_type_announce++; + else if (message_type == RDES_PTP_MANAGEMENT) + x->ptp_rx_msg_type_management++; + else if (message_type == RDES_PTP_PKT_RESERVED_TYPE) + x->ptp_rx_msg_pkt_reserved_type++; if (rdes1 & RDES1_PTP_PACKET_TYPE) x->ptp_frame_type++; @@ -204,14 +211,18 @@ static void dwmac4_rd_enable_tx_timestamp(struct dma_desc *p) static int dwmac4_wrback_get_tx_timestamp_status(struct dma_desc *p) { - return (p->des3 & TDES3_TIMESTAMP_STATUS) - >> TDES3_TIMESTAMP_STATUS_SHIFT; + /* Context type from W/B descriptor must be zero */ + if (p->des3 & TDES3_CONTEXT_TYPE) + return -EINVAL; + + /* Tx Timestamp Status is 1 so des0 and des1'll have valid values */ + if (p->des3 & TDES3_TIMESTAMP_STATUS) + return 0; + + return 1; } -/* NOTE: For RX CTX bit has to be checked before - * HAVE a specific function for TX and another one for RX - */ -static u64 dwmac4_wrback_get_timestamp(void *desc, u32 ats) +static inline u64 dwmac4_get_timestamp(void *desc, u32 ats) { struct dma_desc *p = (struct dma_desc *)desc; u64 ns; @@ -223,12 +234,54 @@ static u64 dwmac4_wrback_get_timestamp(void *desc, u32 ats) return ns; } -static int dwmac4_context_get_rx_timestamp_status(void *desc, u32 ats) +static int dwmac4_rx_check_timestamp(void *desc) +{ + struct dma_desc *p = (struct dma_desc *)desc; + u32 own, ctxt; + int ret = 1; + + own = p->des3 & RDES3_OWN; + ctxt = ((p->des3 & RDES3_CONTEXT_DESCRIPTOR) + >> RDES3_CONTEXT_DESCRIPTOR_SHIFT); + + if (likely(!own && ctxt)) { + if ((p->des0 == 0xffffffff) && (p->des1 == 0xffffffff)) + /* Corrupted value */ + ret = -EINVAL; + else + /* A valid Timestamp is ready to be read */ + ret = 0; + } + + /* Timestamp not ready */ + return ret; +} + +static int dwmac4_wrback_get_rx_timestamp_status(void *desc, u32 ats) { struct dma_desc *p = (struct dma_desc *)desc; + int ret = -EINVAL; + + /* Get the status from normal w/b descriptor */ + if (likely(p->des3 & TDES3_RS1V)) { + if (likely(p->des1 & RDES1_TIMESTAMP_AVAILABLE)) { + int i = 0; + + /* Check if timestamp is OK from context descriptor */ + do { + ret = dwmac4_rx_check_timestamp(desc); + if (ret < 0) + goto exit; + i++; - return (p->des1 & RDES1_TIMESTAMP_AVAILABLE) - >> RDES1_TIMESTAMP_AVAILABLE_SHIFT; + } while ((ret == 1) || (i < 10)); + + if (i == 10) + ret = -EBUSY; + } + } +exit: + return ret; } static void dwmac4_rd_init_rx_desc(struct dma_desc *p, int disable_rx_ic, @@ -373,8 +426,8 @@ const struct stmmac_desc_ops dwmac4_desc_ops = { .get_rx_frame_len = dwmac4_wrback_get_rx_frame_len, .enable_tx_timestamp = dwmac4_rd_enable_tx_timestamp, .get_tx_timestamp_status = dwmac4_wrback_get_tx_timestamp_status, - .get_timestamp = dwmac4_wrback_get_timestamp, - .get_rx_timestamp_status = dwmac4_context_get_rx_timestamp_status, + .get_rx_timestamp_status = dwmac4_wrback_get_rx_timestamp_status, + .get_timestamp = dwmac4_get_timestamp, .set_tx_ic = dwmac4_rd_set_tx_ic, .prepare_tx_desc = dwmac4_rd_prepare_tx_desc, .prepare_tso_tx_desc = dwmac4_rd_prepare_tso_tx_desc, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h index 0902a2edeaa9..9736c505211a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h @@ -59,10 +59,13 @@ #define TDES3_CTXT_TCMSSV BIT(26) /* TDES3 Common */ +#define TDES3_RS1V BIT(26) +#define TDES3_RS1V_SHIFT 26 #define TDES3_LAST_DESCRIPTOR BIT(28) #define TDES3_LAST_DESCRIPTOR_SHIFT 28 #define TDES3_FIRST_DESCRIPTOR BIT(29) #define TDES3_CONTEXT_TYPE BIT(30) +#define TDES3_CONTEXT_TYPE_SHIFT 30 /* TDS3 use for both format (read and write back) */ #define TDES3_OWN BIT(31) @@ -117,6 +120,7 @@ #define RDES3_LAST_DESCRIPTOR BIT(28) #define RDES3_FIRST_DESCRIPTOR BIT(29) #define RDES3_CONTEXT_DESCRIPTOR BIT(30) +#define RDES3_CONTEXT_DESCRIPTOR_SHIFT 30 /* RDES3 (read format) */ #define RDES3_BUFFER1_VALID_ADDR BIT(24) diff --git a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c index 38f19c99cf59..e75549327c34 100644 --- a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c +++ b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c @@ -150,22 +150,30 @@ static void enh_desc_get_ext_status(void *data, struct stmmac_extra_stats *x, x->ipv4_pkt_rcvd++; if (rdes4 & ERDES4_IPV6_PKT_RCVD) x->ipv6_pkt_rcvd++; - if (message_type == RDES_EXT_SYNC) - x->rx_msg_type_sync++; + + if (message_type == RDES_EXT_NO_PTP) + x->no_ptp_rx_msg_type_ext++; + else if (message_type == RDES_EXT_SYNC) + x->ptp_rx_msg_type_sync++; else if (message_type == RDES_EXT_FOLLOW_UP) - x->rx_msg_type_follow_up++; + x->ptp_rx_msg_type_follow_up++; else if (message_type == RDES_EXT_DELAY_REQ) - x->rx_msg_type_delay_req++; + x->ptp_rx_msg_type_delay_req++; else if (message_type == RDES_EXT_DELAY_RESP) - x->rx_msg_type_delay_resp++; + x->ptp_rx_msg_type_delay_resp++; else if (message_type == RDES_EXT_PDELAY_REQ) - x->rx_msg_type_pdelay_req++; + x->ptp_rx_msg_type_pdelay_req++; else if (message_type == RDES_EXT_PDELAY_RESP) - x->rx_msg_type_pdelay_resp++; + x->ptp_rx_msg_type_pdelay_resp++; else if (message_type == RDES_EXT_PDELAY_FOLLOW_UP) - x->rx_msg_type_pdelay_follow_up++; - else - x->rx_msg_type_ext_no_ptp++; + x->ptp_rx_msg_type_pdelay_follow_up++; + else if (message_type == RDES_PTP_ANNOUNCE) + x->ptp_rx_msg_type_announce++; + else if (message_type == RDES_PTP_MANAGEMENT) + x->ptp_rx_msg_type_management++; + else if (message_type == RDES_PTP_PKT_RESERVED_TYPE) + x->ptp_rx_msg_pkt_reserved_type++; + if (rdes4 & ERDES4_PTP_FRAME_TYPE) x->ptp_frame_type++; if (rdes4 & ERDES4_PTP_VER) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index b15fc55f1b96..4d2a759b8465 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -129,6 +129,7 @@ struct stmmac_priv { int irq_wake; spinlock_t ptp_lock; void __iomem *mmcaddr; + void __iomem *ptpaddr; u32 rx_tail_addr; u32 tx_tail_addr; u32 mss; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index 1e06173fc9d7..c5d0142adda2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -115,14 +115,17 @@ static const struct stmmac_stats stmmac_gstrings_stats[] = { STMMAC_STAT(ip_csum_bypassed), STMMAC_STAT(ipv4_pkt_rcvd), STMMAC_STAT(ipv6_pkt_rcvd), - STMMAC_STAT(rx_msg_type_ext_no_ptp), - STMMAC_STAT(rx_msg_type_sync), - STMMAC_STAT(rx_msg_type_follow_up), - STMMAC_STAT(rx_msg_type_delay_req), - STMMAC_STAT(rx_msg_type_delay_resp), - STMMAC_STAT(rx_msg_type_pdelay_req), - STMMAC_STAT(rx_msg_type_pdelay_resp), - STMMAC_STAT(rx_msg_type_pdelay_follow_up), + STMMAC_STAT(no_ptp_rx_msg_type_ext), + STMMAC_STAT(ptp_rx_msg_type_sync), + STMMAC_STAT(ptp_rx_msg_type_follow_up), + STMMAC_STAT(ptp_rx_msg_type_delay_req), + STMMAC_STAT(ptp_rx_msg_type_delay_resp), + STMMAC_STAT(ptp_rx_msg_type_pdelay_req), + STMMAC_STAT(ptp_rx_msg_type_pdelay_resp), + STMMAC_STAT(ptp_rx_msg_type_pdelay_follow_up), + STMMAC_STAT(ptp_rx_msg_type_announce), + STMMAC_STAT(ptp_rx_msg_type_management), + STMMAC_STAT(ptp_rx_msg_pkt_reserved_type), STMMAC_STAT(ptp_frame_type), STMMAC_STAT(ptp_ver), STMMAC_STAT(timestamp_dropped), diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c index a77f68918010..10d6059b2f26 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c @@ -34,21 +34,29 @@ static void stmmac_config_hw_tstamping(void __iomem *ioaddr, u32 data) } static u32 stmmac_config_sub_second_increment(void __iomem *ioaddr, - u32 ptp_clock) + u32 ptp_clock, int gmac4) { u32 value = readl(ioaddr + PTP_TCR); unsigned long data; - /* Convert the ptp_clock to nano second - * formula = (2/ptp_clock) * 1000000000 - * where, ptp_clock = 50MHz. + /* For GMAC3.x, 4.x versions, convert the ptp_clock to nano second + * formula = (1/ptp_clock) * 1000000000 + * where ptp_clock is 50MHz if fine method is used to update system */ - data = (2000000000ULL / ptp_clock); + if (value & PTP_TCR_TSCFUPDT) + data = (1000000000ULL / 50000000); + else + data = (1000000000ULL / ptp_clock); /* 0.465ns accuracy */ if (!(value & PTP_TCR_TSCTRLSSR)) data = (data * 1000) / 465; + data &= PTP_SSIR_SSINC_MASK; + + if (gmac4) + data = data << GMAC4_PTP_SSIR_SSINC_SHIFT; + writel(data, ioaddr + PTP_SSIR); return data; @@ -104,14 +112,30 @@ static int stmmac_config_addend(void __iomem *ioaddr, u32 addend) } static int stmmac_adjust_systime(void __iomem *ioaddr, u32 sec, u32 nsec, - int add_sub) + int add_sub, int gmac4) { u32 value; int limit; + if (add_sub) { + /* If the new sec value needs to be subtracted with + * the system time, then MAC_STSUR reg should be + * programmed with (2^32 – <new_sec_value>) + */ + if (gmac4) + sec = (100000000ULL - sec); + + value = readl(ioaddr + PTP_TCR); + if (value & PTP_TCR_TSCTRLSSR) + nsec = (PTP_DIGITAL_ROLLOVER_MODE - nsec); + else + nsec = (PTP_BINARY_ROLLOVER_MODE - nsec); + } + writel(sec, ioaddr + PTP_STSUR); - writel(((add_sub << PTP_STNSUR_ADDSUB_SHIFT) | nsec), - ioaddr + PTP_STNSUR); + value = (add_sub << PTP_STNSUR_ADDSUB_SHIFT) | nsec; + writel(value, ioaddr + PTP_STNSUR); + /* issue command to initialize the system time value */ value = readl(ioaddr + PTP_TCR); value |= PTP_TCR_TSUPDT; @@ -134,8 +158,9 @@ static u64 stmmac_get_systime(void __iomem *ioaddr) { u64 ns; + /* Get the TSSS value */ ns = readl(ioaddr + PTP_STNSR); - /* convert sec time value to nanosecond */ + /* Get the TSS and convert sec time value to nanosecond */ ns += readl(ioaddr + PTP_STSR) * 1000000000ULL; return ns; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index e2c94ec4edd0..1f9ec02fa7f8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -340,18 +340,17 @@ out: /* stmmac_get_tx_hwtstamp - get HW TX timestamps * @priv: driver private structure - * @entry : descriptor index to be used. + * @p : descriptor pointer * @skb : the socket buffer * Description : * This function will read timestamp from the descriptor & pass it to stack. * and also perform some sanity checks. */ static void stmmac_get_tx_hwtstamp(struct stmmac_priv *priv, - unsigned int entry, struct sk_buff *skb) + struct dma_desc *p, struct sk_buff *skb) { struct skb_shared_hwtstamps shhwtstamp; u64 ns; - void *desc = NULL; if (!priv->hwts_tx_en) return; @@ -360,58 +359,55 @@ static void stmmac_get_tx_hwtstamp(struct stmmac_priv *priv, if (likely(!skb || !(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS))) return; - if (priv->adv_ts) - desc = (priv->dma_etx + entry); - else - desc = (priv->dma_tx + entry); - /* check tx tstamp status */ - if (!priv->hw->desc->get_tx_timestamp_status((struct dma_desc *)desc)) - return; + if (!priv->hw->desc->get_tx_timestamp_status(p)) { + /* get the valid tstamp */ + ns = priv->hw->desc->get_timestamp(p, priv->adv_ts); - /* get the valid tstamp */ - ns = priv->hw->desc->get_timestamp(desc, priv->adv_ts); + memset(&shhwtstamp, 0, sizeof(struct skb_shared_hwtstamps)); + shhwtstamp.hwtstamp = ns_to_ktime(ns); - memset(&shhwtstamp, 0, sizeof(struct skb_shared_hwtstamps)); - shhwtstamp.hwtstamp = ns_to_ktime(ns); - /* pass tstamp to stack */ - skb_tstamp_tx(skb, &shhwtstamp); + netdev_info(priv->dev, "get valid TX hw timestamp %llu\n", ns); + /* pass tstamp to stack */ + skb_tstamp_tx(skb, &shhwtstamp); + } return; } /* stmmac_get_rx_hwtstamp - get HW RX timestamps * @priv: driver private structure - * @entry : descriptor index to be used. + * @p : descriptor pointer + * @np : next descriptor pointer * @skb : the socket buffer * Description : * This function will read received packet's timestamp from the descriptor * and pass it to stack. It also perform some sanity checks. */ -static void stmmac_get_rx_hwtstamp(struct stmmac_priv *priv, - unsigned int entry, struct sk_buff *skb) +static void stmmac_get_rx_hwtstamp(struct stmmac_priv *priv, struct dma_desc *p, + struct dma_desc *np, struct sk_buff *skb) { struct skb_shared_hwtstamps *shhwtstamp = NULL; u64 ns; - void *desc = NULL; if (!priv->hwts_rx_en) return; - if (priv->adv_ts) - desc = (priv->dma_erx + entry); - else - desc = (priv->dma_rx + entry); - - /* exit if rx tstamp is not valid */ - if (!priv->hw->desc->get_rx_timestamp_status(desc, priv->adv_ts)) - return; + /* Check if timestamp is available */ + if (!priv->hw->desc->get_rx_timestamp_status(p, priv->adv_ts)) { + /* For GMAC4, the valid timestamp is from CTX next desc. */ + if (priv->plat->has_gmac4) + ns = priv->hw->desc->get_timestamp(np, priv->adv_ts); + else + ns = priv->hw->desc->get_timestamp(p, priv->adv_ts); - /* get valid tstamp */ - ns = priv->hw->desc->get_timestamp(desc, priv->adv_ts); - shhwtstamp = skb_hwtstamps(skb); - memset(shhwtstamp, 0, sizeof(struct skb_shared_hwtstamps)); - shhwtstamp->hwtstamp = ns_to_ktime(ns); + netdev_info(priv->dev, "get valid RX hw timestamp %llu\n", ns); + shhwtstamp = skb_hwtstamps(skb); + memset(shhwtstamp, 0, sizeof(struct skb_shared_hwtstamps)); + shhwtstamp->hwtstamp = ns_to_ktime(ns); + } else { + netdev_err(priv->dev, "cannot get RX hw timestamp\n"); + } } /** @@ -598,17 +594,18 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr) priv->hwts_tx_en = config.tx_type == HWTSTAMP_TX_ON; if (!priv->hwts_tx_en && !priv->hwts_rx_en) - priv->hw->ptp->config_hw_tstamping(priv->ioaddr, 0); + priv->hw->ptp->config_hw_tstamping(priv->ptpaddr, 0); else { value = (PTP_TCR_TSENA | PTP_TCR_TSCFUPDT | PTP_TCR_TSCTRLSSR | tstamp_all | ptp_v2 | ptp_over_ethernet | ptp_over_ipv6_udp | ptp_over_ipv4_udp | ts_event_en | ts_master_en | snap_type_sel); - priv->hw->ptp->config_hw_tstamping(priv->ioaddr, value); + priv->hw->ptp->config_hw_tstamping(priv->ptpaddr, value); /* program Sub Second Increment reg */ sec_inc = priv->hw->ptp->config_sub_second_increment( - priv->ioaddr, priv->clk_ptp_rate); + priv->ptpaddr, priv->clk_ptp_rate, + priv->plat->has_gmac4); temp = div_u64(1000000000ULL, sec_inc); /* calculate default added value: @@ -618,14 +615,14 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr) */ temp = (u64)(temp << 32); priv->default_addend = div_u64(temp, priv->clk_ptp_rate); - priv->hw->ptp->config_addend(priv->ioaddr, + priv->hw->ptp->config_addend(priv->ptpaddr, priv->default_addend); /* initialize system time */ ktime_get_real_ts64(&now); /* lower 32 bits of tv_sec are safe until y2106 */ - priv->hw->ptp->init_systime(priv->ioaddr, (u32)now.tv_sec, + priv->hw->ptp->init_systime(priv->ptpaddr, (u32)now.tv_sec, now.tv_nsec); } @@ -1340,7 +1337,7 @@ static void stmmac_tx_clean(struct stmmac_priv *priv) priv->dev->stats.tx_packets++; priv->xstats.tx_pkt_n++; } - stmmac_get_tx_hwtstamp(priv, entry, skb); + stmmac_get_tx_hwtstamp(priv, p, skb); } if (likely(priv->tx_skbuff_dma[entry].buf)) { @@ -1486,10 +1483,13 @@ static void stmmac_mmc_setup(struct stmmac_priv *priv) unsigned int mode = MMC_CNTRL_RESET_ON_READ | MMC_CNTRL_COUNTER_RESET | MMC_CNTRL_PRESET | MMC_CNTRL_FULL_HALF_PRESET; - if (priv->synopsys_id >= DWMAC_CORE_4_00) + if (priv->synopsys_id >= DWMAC_CORE_4_00) { + priv->ptpaddr = priv->ioaddr + PTP_GMAC4_OFFSET; priv->mmcaddr = priv->ioaddr + MMC_GMAC4_OFFSET; - else + } else { + priv->ptpaddr = priv->ioaddr + PTP_GMAC3_X_OFFSET; priv->mmcaddr = priv->ioaddr + MMC_GMAC3_X_OFFSET; + } dwmac_mmc_intr_all_mask(priv->mmcaddr); @@ -2484,7 +2484,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit) if (netif_msg_rx_status(priv)) { void *rx_head; - pr_debug("%s: descriptor ring:\n", __func__); + pr_info(">>>>>> %s: descriptor ring:\n", __func__); if (priv->extend_desc) rx_head = (void *)priv->dma_erx; else @@ -2495,6 +2495,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit) while (count < limit) { int status; struct dma_desc *p; + struct dma_desc *np; if (priv->extend_desc) p = (struct dma_desc *)(priv->dma_erx + entry); @@ -2514,9 +2515,11 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit) next_entry = priv->cur_rx; if (priv->extend_desc) - prefetch(priv->dma_erx + next_entry); + np = (struct dma_desc *)(priv->dma_erx + next_entry); else - prefetch(priv->dma_rx + next_entry); + np = priv->dma_rx + next_entry; + + prefetch(np); if ((priv->extend_desc) && (priv->hw->desc->rx_extended_status)) priv->hw->desc->rx_extended_status(&priv->dev->stats, @@ -2568,7 +2571,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit) frame_len -= ETH_FCS_LEN; if (netif_msg_rx_status(priv)) { - pr_debug("\tdesc: %p [entry %d] buff=0x%x\n", + pr_info("\tdesc: %p [entry %d] buff=0x%x\n", p, entry, des); if (frame_len > ETH_FRAME_LEN) pr_debug("\tframe size %d, COE: %d\n", @@ -2625,13 +2628,13 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit) DMA_FROM_DEVICE); } - stmmac_get_rx_hwtstamp(priv, entry, skb); - if (netif_msg_pktdata(priv)) { pr_debug("frame received (%dbytes)", frame_len); print_pkt(skb->data, frame_len); } + stmmac_get_rx_hwtstamp(priv, p, np, skb); + stmmac_rx_vlan(priv->dev, skb); skb->protocol = eth_type_trans(skb, priv->dev); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c index 1477471f8d44..3eb281d1db08 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c @@ -54,7 +54,7 @@ static int stmmac_adjust_freq(struct ptp_clock_info *ptp, s32 ppb) spin_lock_irqsave(&priv->ptp_lock, flags); - priv->hw->ptp->config_addend(priv->ioaddr, addend); + priv->hw->ptp->config_addend(priv->ptpaddr, addend); spin_unlock_irqrestore(&priv->ptp_lock, flags); @@ -89,7 +89,8 @@ static int stmmac_adjust_time(struct ptp_clock_info *ptp, s64 delta) spin_lock_irqsave(&priv->ptp_lock, flags); - priv->hw->ptp->adjust_systime(priv->ioaddr, sec, nsec, neg_adj); + priv->hw->ptp->adjust_systime(priv->ptpaddr, sec, nsec, neg_adj, + priv->plat->has_gmac4); spin_unlock_irqrestore(&priv->ptp_lock, flags); @@ -114,7 +115,7 @@ static int stmmac_get_time(struct ptp_clock_info *ptp, struct timespec64 *ts) spin_lock_irqsave(&priv->ptp_lock, flags); - ns = priv->hw->ptp->get_systime(priv->ioaddr); + ns = priv->hw->ptp->get_systime(priv->ptpaddr); spin_unlock_irqrestore(&priv->ptp_lock, flags); @@ -141,7 +142,7 @@ static int stmmac_set_time(struct ptp_clock_info *ptp, spin_lock_irqsave(&priv->ptp_lock, flags); - priv->hw->ptp->init_systime(priv->ioaddr, ts->tv_sec, ts->tv_nsec); + priv->hw->ptp->init_systime(priv->ptpaddr, ts->tv_sec, ts->tv_nsec); spin_unlock_irqrestore(&priv->ptp_lock, flags); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h index 4535df37c227..c06938c47af5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h @@ -22,51 +22,53 @@ Author: Rayagond Kokatanur <rayagond@vayavyalabs.com> ******************************************************************************/ -#ifndef __STMMAC_PTP_H__ -#define __STMMAC_PTP_H__ +#ifndef __STMMAC_PTP_H__ +#define __STMMAC_PTP_H__ -/* IEEE 1588 PTP register offsets */ -#define PTP_TCR 0x0700 /* Timestamp Control Reg */ -#define PTP_SSIR 0x0704 /* Sub-Second Increment Reg */ -#define PTP_STSR 0x0708 /* System Time – Seconds Regr */ -#define PTP_STNSR 0x070C /* System Time – Nanoseconds Reg */ -#define PTP_STSUR 0x0710 /* System Time – Seconds Update Reg */ -#define PTP_STNSUR 0x0714 /* System Time – Nanoseconds Update Reg */ -#define PTP_TAR 0x0718 /* Timestamp Addend Reg */ -#define PTP_TTSR 0x071C /* Target Time Seconds Reg */ -#define PTP_TTNSR 0x0720 /* Target Time Nanoseconds Reg */ -#define PTP_STHWSR 0x0724 /* System Time - Higher Word Seconds Reg */ -#define PTP_TSR 0x0728 /* Timestamp Status */ +#define PTP_GMAC4_OFFSET 0xb00 +#define PTP_GMAC3_X_OFFSET 0x700 -#define PTP_STNSUR_ADDSUB_SHIFT 31 +/* IEEE 1588 PTP register offsets */ +#define PTP_TCR 0x00 /* Timestamp Control Reg */ +#define PTP_SSIR 0x04 /* Sub-Second Increment Reg */ +#define PTP_STSR 0x08 /* System Time – Seconds Regr */ +#define PTP_STNSR 0x0c /* System Time – Nanoseconds Reg */ +#define PTP_STSUR 0x10 /* System Time – Seconds Update Reg */ +#define PTP_STNSUR 0x14 /* System Time – Nanoseconds Update Reg */ +#define PTP_TAR 0x18 /* Timestamp Addend Reg */ -/* PTP TCR defines */ -#define PTP_TCR_TSENA 0x00000001 /* Timestamp Enable */ -#define PTP_TCR_TSCFUPDT 0x00000002 /* Timestamp Fine/Coarse Update */ -#define PTP_TCR_TSINIT 0x00000004 /* Timestamp Initialize */ -#define PTP_TCR_TSUPDT 0x00000008 /* Timestamp Update */ -/* Timestamp Interrupt Trigger Enable */ -#define PTP_TCR_TSTRIG 0x00000010 -#define PTP_TCR_TSADDREG 0x00000020 /* Addend Reg Update */ -#define PTP_TCR_TSENALL 0x00000100 /* Enable Timestamp for All Frames */ -/* Timestamp Digital or Binary Rollover Control */ -#define PTP_TCR_TSCTRLSSR 0x00000200 +#define PTP_STNSUR_ADDSUB_SHIFT 31 +#define PTP_DIGITAL_ROLLOVER_MODE 0x3B9ACA00 /* 10e9-1 ns */ +#define PTP_BINARY_ROLLOVER_MODE 0x80000000 /* ~0.466 ns */ +/* PTP Timestamp control register defines */ +#define PTP_TCR_TSENA BIT(0) /* Timestamp Enable */ +#define PTP_TCR_TSCFUPDT BIT(1) /* Timestamp Fine/Coarse Update */ +#define PTP_TCR_TSINIT BIT(2) /* Timestamp Initialize */ +#define PTP_TCR_TSUPDT BIT(3) /* Timestamp Update */ +#define PTP_TCR_TSTRIG BIT(4) /* Timestamp Interrupt Trigger Enable */ +#define PTP_TCR_TSADDREG BIT(5) /* Addend Reg Update */ +#define PTP_TCR_TSENALL BIT(8) /* Enable Timestamp for All Frames */ +#define PTP_TCR_TSCTRLSSR BIT(9) /* Digital or Binary Rollover Control */ /* Enable PTP packet Processing for Version 2 Format */ -#define PTP_TCR_TSVER2ENA 0x00000400 +#define PTP_TCR_TSVER2ENA BIT(10) /* Enable Processing of PTP over Ethernet Frames */ -#define PTP_TCR_TSIPENA 0x00000800 +#define PTP_TCR_TSIPENA BIT(11) /* Enable Processing of PTP Frames Sent over IPv6-UDP */ -#define PTP_TCR_TSIPV6ENA 0x00001000 +#define PTP_TCR_TSIPV6ENA BIT(12) /* Enable Processing of PTP Frames Sent over IPv4-UDP */ -#define PTP_TCR_TSIPV4ENA 0x00002000 +#define PTP_TCR_TSIPV4ENA BIT(13) /* Enable Timestamp Snapshot for Event Messages */ -#define PTP_TCR_TSEVNTENA 0x00004000 +#define PTP_TCR_TSEVNTENA BIT(14) /* Enable Snapshot for Messages Relevant to Master */ -#define PTP_TCR_TSMSTRENA 0x00008000 +#define PTP_TCR_TSMSTRENA BIT(15) /* Select PTP packets for Taking Snapshots */ -#define PTP_TCR_SNAPTYPSEL_1 0x00010000 +#define PTP_TCR_SNAPTYPSEL_1 GENMASK(17, 16) /* Enable MAC address for PTP Frame Filtering */ -#define PTP_TCR_TSENMACADDR 0x00040000 +#define PTP_TCR_TSENMACADDR BIT(18) + +/* SSIR defines */ +#define PTP_SSIR_SSINC_MASK 0xff +#define GMAC4_PTP_SSIR_SSINC_SHIFT 16 -#endif /* __STMMAC_PTP_H__ */ +#endif /* __STMMAC_PTP_H__ */ diff --git a/drivers/net/ethernet/sun/sunbmac.c b/drivers/net/ethernet/sun/sunbmac.c index aa4f9d2d8fa9..02f452730d52 100644 --- a/drivers/net/ethernet/sun/sunbmac.c +++ b/drivers/net/ethernet/sun/sunbmac.c @@ -623,6 +623,7 @@ static int bigmac_init_hw(struct bigmac *bp, int from_irq) void __iomem *gregs = bp->gregs; void __iomem *cregs = bp->creg; void __iomem *bregs = bp->bregs; + __u32 bblk_dvma = (__u32)bp->bblock_dvma; unsigned char *e = &bp->dev->dev_addr[0]; /* Latch current counters into statistics. */ @@ -671,9 +672,9 @@ static int bigmac_init_hw(struct bigmac *bp, int from_irq) bregs + BMAC_XIFCFG); /* Tell the QEC where the ring descriptors are. */ - sbus_writel(bp->bblock_dvma + bib_offset(be_rxd, 0), + sbus_writel(bblk_dvma + bib_offset(be_rxd, 0), cregs + CREG_RXDS); - sbus_writel(bp->bblock_dvma + bib_offset(be_txd, 0), + sbus_writel(bblk_dvma + bib_offset(be_txd, 0), cregs + CREG_TXDS); /* Setup the FIFO pointers into QEC local memory. */ diff --git a/drivers/net/ethernet/sun/sunbmac.h b/drivers/net/ethernet/sun/sunbmac.h index 06dd21707353..532fc56830cf 100644 --- a/drivers/net/ethernet/sun/sunbmac.h +++ b/drivers/net/ethernet/sun/sunbmac.h @@ -291,7 +291,7 @@ struct bigmac { void __iomem *bregs; /* BigMAC Registers */ void __iomem *tregs; /* BigMAC Transceiver */ struct bmac_init_block *bmac_block; /* RX and TX descriptors */ - __u32 bblock_dvma; /* RX and TX descriptors */ + dma_addr_t bblock_dvma; /* RX and TX descriptors */ spinlock_t lock; diff --git a/drivers/net/ethernet/sun/sunqe.c b/drivers/net/ethernet/sun/sunqe.c index 9b825780b3be..9582948145c1 100644 --- a/drivers/net/ethernet/sun/sunqe.c +++ b/drivers/net/ethernet/sun/sunqe.c @@ -124,7 +124,7 @@ static void qe_init_rings(struct sunqe *qep) { struct qe_init_block *qb = qep->qe_block; struct sunqe_buffers *qbufs = qep->buffers; - __u32 qbufs_dvma = qep->buffers_dvma; + __u32 qbufs_dvma = (__u32)qep->buffers_dvma; int i; qep->rx_new = qep->rx_old = qep->tx_new = qep->tx_old = 0; @@ -144,6 +144,7 @@ static int qe_init(struct sunqe *qep, int from_irq) void __iomem *mregs = qep->mregs; void __iomem *gregs = qecp->gregs; unsigned char *e = &qep->dev->dev_addr[0]; + __u32 qblk_dvma = (__u32)qep->qblock_dvma; u32 tmp; int i; @@ -152,8 +153,8 @@ static int qe_init(struct sunqe *qep, int from_irq) return -EAGAIN; /* Setup initial rx/tx init block pointers. */ - sbus_writel(qep->qblock_dvma + qib_offset(qe_rxd, 0), cregs + CREG_RXDS); - sbus_writel(qep->qblock_dvma + qib_offset(qe_txd, 0), cregs + CREG_TXDS); + sbus_writel(qblk_dvma + qib_offset(qe_rxd, 0), cregs + CREG_RXDS); + sbus_writel(qblk_dvma + qib_offset(qe_txd, 0), cregs + CREG_TXDS); /* Enable/mask the various irq's. */ sbus_writel(0, cregs + CREG_RIMASK); @@ -413,7 +414,7 @@ static void qe_rx(struct sunqe *qep) struct net_device *dev = qep->dev; struct qe_rxd *this; struct sunqe_buffers *qbufs = qep->buffers; - __u32 qbufs_dvma = qep->buffers_dvma; + __u32 qbufs_dvma = (__u32)qep->buffers_dvma; int elem = qep->rx_new; u32 flags; @@ -572,7 +573,7 @@ static int qe_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct sunqe *qep = netdev_priv(dev); struct sunqe_buffers *qbufs = qep->buffers; - __u32 txbuf_dvma, qbufs_dvma = qep->buffers_dvma; + __u32 txbuf_dvma, qbufs_dvma = (__u32)qep->buffers_dvma; unsigned char *txbuf; int len, entry; diff --git a/drivers/net/ethernet/sun/sunqe.h b/drivers/net/ethernet/sun/sunqe.h index 581781b6b2fa..ae190b77431b 100644 --- a/drivers/net/ethernet/sun/sunqe.h +++ b/drivers/net/ethernet/sun/sunqe.h @@ -334,12 +334,12 @@ struct sunqe { void __iomem *qcregs; /* QEC per-channel Registers */ void __iomem *mregs; /* Per-channel MACE Registers */ struct qe_init_block *qe_block; /* RX and TX descriptors */ - __u32 qblock_dvma; /* RX and TX descriptors */ + dma_addr_t qblock_dvma; /* RX and TX descriptors */ spinlock_t lock; /* Protects txfull state */ int rx_new, rx_old; /* RX ring extents */ int tx_new, tx_old; /* TX ring extents */ struct sunqe_buffers *buffers; /* CPU visible address. */ - __u32 buffers_dvma; /* DVMA visible address. */ + dma_addr_t buffers_dvma; /* DVMA visible address. */ struct sunqec *parent; u8 mconfig; /* Base MACE mconfig value */ struct platform_device *op; /* QE's OF device struct */ diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index c6cff3d2ff05..58947aae31c7 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -2375,8 +2375,11 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data, * to the PHY is the Ethernet MAC DT node. */ ret = of_phy_register_fixed_link(slave_node); - if (ret) + if (ret) { + if (ret != -EPROBE_DEFER) + dev_err(&pdev->dev, "failed to register fixed-link phy: %d\n", ret); return ret; + } slave_data->phy_node = of_node_get(slave_node); } else if (parp) { u32 phyid; @@ -2397,6 +2400,7 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data, } snprintf(slave_data->phy_id, sizeof(slave_data->phy_id), PHY_ID_FMT, mdio->name, phyid); + put_device(&mdio->dev); } else { dev_err(&pdev->dev, "No slave[%d] phy_id, phy-handle, or fixed-link property\n", @@ -2440,6 +2444,46 @@ no_phy_slave: return 0; } +static void cpsw_remove_dt(struct platform_device *pdev) +{ + struct net_device *ndev = platform_get_drvdata(pdev); + struct cpsw_common *cpsw = ndev_to_cpsw(ndev); + struct cpsw_platform_data *data = &cpsw->data; + struct device_node *node = pdev->dev.of_node; + struct device_node *slave_node; + int i = 0; + + for_each_available_child_of_node(node, slave_node) { + struct cpsw_slave_data *slave_data = &data->slave_data[i]; + + if (strcmp(slave_node->name, "slave")) + continue; + + if (of_phy_is_fixed_link(slave_node)) { + struct phy_device *phydev; + + phydev = of_phy_find_device(slave_node); + if (phydev) { + fixed_phy_unregister(phydev); + /* Put references taken by + * of_phy_find_device() and + * of_phy_register_fixed_link(). + */ + phy_device_free(phydev); + phy_device_free(phydev); + } + } + + of_node_put(slave_data->phy_node); + + i++; + if (i == data->slaves) + break; + } + + of_platform_depopulate(&pdev->dev); +} + static int cpsw_probe_dual_emac(struct cpsw_priv *priv) { struct cpsw_common *cpsw = priv->cpsw; @@ -2547,6 +2591,9 @@ static int cpsw_probe(struct platform_device *pdev) int irq; cpsw = devm_kzalloc(&pdev->dev, sizeof(struct cpsw_common), GFP_KERNEL); + if (!cpsw) + return -ENOMEM; + cpsw->dev = &pdev->dev; ndev = alloc_etherdev_mq(sizeof(struct cpsw_priv), CPSW_MAX_QUEUES); @@ -2584,11 +2631,19 @@ static int cpsw_probe(struct platform_device *pdev) /* Select default pin state */ pinctrl_pm_select_default_state(&pdev->dev); - if (cpsw_probe_dt(&cpsw->data, pdev)) { - dev_err(&pdev->dev, "cpsw: platform data missing\n"); - ret = -ENODEV; + /* Need to enable clocks with runtime PM api to access module + * registers + */ + ret = pm_runtime_get_sync(&pdev->dev); + if (ret < 0) { + pm_runtime_put_noidle(&pdev->dev); goto clean_runtime_disable_ret; } + + ret = cpsw_probe_dt(&cpsw->data, pdev); + if (ret) + goto clean_dt_ret; + data = &cpsw->data; cpsw->rx_ch_num = 1; cpsw->tx_ch_num = 1; @@ -2608,7 +2663,7 @@ static int cpsw_probe(struct platform_device *pdev) GFP_KERNEL); if (!cpsw->slaves) { ret = -ENOMEM; - goto clean_runtime_disable_ret; + goto clean_dt_ret; } for (i = 0; i < data->slaves; i++) cpsw->slaves[i].slave_num = i; @@ -2620,7 +2675,7 @@ static int cpsw_probe(struct platform_device *pdev) if (IS_ERR(clk)) { dev_err(priv->dev, "fck is not found\n"); ret = -ENODEV; - goto clean_runtime_disable_ret; + goto clean_dt_ret; } cpsw->bus_freq_mhz = clk_get_rate(clk) / 1000000; @@ -2628,26 +2683,17 @@ static int cpsw_probe(struct platform_device *pdev) ss_regs = devm_ioremap_resource(&pdev->dev, ss_res); if (IS_ERR(ss_regs)) { ret = PTR_ERR(ss_regs); - goto clean_runtime_disable_ret; + goto clean_dt_ret; } cpsw->regs = ss_regs; - /* Need to enable clocks with runtime PM api to access module - * registers - */ - ret = pm_runtime_get_sync(&pdev->dev); - if (ret < 0) { - pm_runtime_put_noidle(&pdev->dev); - goto clean_runtime_disable_ret; - } cpsw->version = readl(&cpsw->regs->id_ver); - pm_runtime_put_sync(&pdev->dev); res = platform_get_resource(pdev, IORESOURCE_MEM, 1); cpsw->wr_regs = devm_ioremap_resource(&pdev->dev, res); if (IS_ERR(cpsw->wr_regs)) { ret = PTR_ERR(cpsw->wr_regs); - goto clean_runtime_disable_ret; + goto clean_dt_ret; } memset(&dma_params, 0, sizeof(dma_params)); @@ -2684,7 +2730,7 @@ static int cpsw_probe(struct platform_device *pdev) default: dev_err(priv->dev, "unknown version 0x%08x\n", cpsw->version); ret = -ENODEV; - goto clean_runtime_disable_ret; + goto clean_dt_ret; } for (i = 0; i < cpsw->data.slaves; i++) { struct cpsw_slave *slave = &cpsw->slaves[i]; @@ -2713,7 +2759,7 @@ static int cpsw_probe(struct platform_device *pdev) if (!cpsw->dma) { dev_err(priv->dev, "error initializing dma\n"); ret = -ENOMEM; - goto clean_runtime_disable_ret; + goto clean_dt_ret; } cpsw->txch[0] = cpdma_chan_create(cpsw->dma, 0, cpsw_tx_handler, 0); @@ -2811,16 +2857,23 @@ static int cpsw_probe(struct platform_device *pdev) ret = cpsw_probe_dual_emac(priv); if (ret) { cpsw_err(priv, probe, "error probe slave 2 emac interface\n"); - goto clean_ale_ret; + goto clean_unregister_netdev_ret; } } + pm_runtime_put(&pdev->dev); + return 0; +clean_unregister_netdev_ret: + unregister_netdev(ndev); clean_ale_ret: cpsw_ale_destroy(cpsw->ale); clean_dma_ret: cpdma_ctlr_destroy(cpsw->dma); +clean_dt_ret: + cpsw_remove_dt(pdev); + pm_runtime_put_sync(&pdev->dev); clean_runtime_disable_ret: pm_runtime_disable(&pdev->dev); clean_ndev_ret: @@ -2846,7 +2899,7 @@ static int cpsw_remove(struct platform_device *pdev) cpsw_ale_destroy(cpsw->ale); cpdma_ctlr_destroy(cpsw->dma); - of_platform_depopulate(&pdev->dev); + cpsw_remove_dt(pdev); pm_runtime_put_sync(&pdev->dev); pm_runtime_disable(&pdev->dev); if (cpsw->data.dual_emac) diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c index c649c101bbab..eb5167210681 100644 --- a/drivers/net/phy/fixed_phy.c +++ b/drivers/net/phy/fixed_phy.c @@ -279,7 +279,7 @@ EXPORT_SYMBOL_GPL(fixed_phy_register); void fixed_phy_unregister(struct phy_device *phy) { phy_device_remove(phy); - + of_node_put(phy->mdio.dev.of_node); fixed_phy_del(phy->mdio.addr); } EXPORT_SYMBOL_GPL(fixed_phy_unregister); diff --git a/drivers/net/phy/vitesse.c b/drivers/net/phy/vitesse.c index 2e37eb337d48..24b4a09468dd 100644 --- a/drivers/net/phy/vitesse.c +++ b/drivers/net/phy/vitesse.c @@ -62,6 +62,10 @@ /* Vitesse Extended Page Access Register */ #define MII_VSC82X4_EXT_PAGE_ACCESS 0x1f +/* Vitesse VSC8601 Extended PHY Control Register 1 */ +#define MII_VSC8601_EPHY_CTL 0x17 +#define MII_VSC8601_EPHY_CTL_RGMII_SKEW (1 << 8) + #define PHY_ID_VSC8234 0x000fc620 #define PHY_ID_VSC8244 0x000fc6c0 #define PHY_ID_VSC8514 0x00070670 @@ -111,6 +115,34 @@ static int vsc824x_config_init(struct phy_device *phydev) return err; } +/* This adds a skew for both TX and RX clocks, so the skew should only be + * applied to "rgmii-id" interfaces. It may not work as expected + * on "rgmii-txid", "rgmii-rxid" or "rgmii" interfaces. */ +static int vsc8601_add_skew(struct phy_device *phydev) +{ + int ret; + + ret = phy_read(phydev, MII_VSC8601_EPHY_CTL); + if (ret < 0) + return ret; + + ret |= MII_VSC8601_EPHY_CTL_RGMII_SKEW; + return phy_write(phydev, MII_VSC8601_EPHY_CTL, ret); +} + +static int vsc8601_config_init(struct phy_device *phydev) +{ + int ret = 0; + + if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID) + ret = vsc8601_add_skew(phydev); + + if (ret < 0) + return ret; + + return genphy_config_init(phydev); +} + static int vsc824x_ack_interrupt(struct phy_device *phydev) { int err = 0; @@ -275,7 +307,7 @@ static struct phy_driver vsc82xx_driver[] = { .phy_id_mask = 0x000ffff0, .features = PHY_GBIT_FEATURES, .flags = PHY_HAS_INTERRUPT, - .config_init = &genphy_config_init, + .config_init = &vsc8601_config_init, .config_aneg = &genphy_config_aneg, .read_status = &genphy_read_status, .ack_interrupt = &vsc824x_ack_interrupt, diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index fd8b1e62301f..7276d5a95bd0 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -1497,6 +1497,11 @@ static void virtnet_free_queues(struct virtnet_info *vi) netif_napi_del(&vi->rq[i].napi); } + /* We called napi_hash_del() before netif_napi_del(), + * we need to respect an RCU grace period before freeing vi->rq + */ + synchronize_net(); + kfree(vi->rq); kfree(vi->sq); } diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 431f13b4faf6..d3bad5779376 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -826,7 +826,7 @@ static void mac80211_hwsim_set_tsf(struct ieee80211_hw *hw, data->bcn_delta = do_div(delta, bcn_int); } else { data->tsf_offset -= delta; - data->bcn_delta = -do_div(delta, bcn_int); + data->bcn_delta = -(s64)do_div(delta, bcn_int); } } diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c index b470f7e3521d..5a3145a02547 100644 --- a/drivers/of/of_mdio.c +++ b/drivers/of/of_mdio.c @@ -292,6 +292,7 @@ struct phy_device *of_phy_find_device(struct device_node *phy_np) mdiodev = to_mdio_device(d); if (mdiodev->flags & MDIO_DEVICE_FLAG_PHY) return to_phy_device(d); + put_device(d); } return NULL; @@ -456,8 +457,11 @@ int of_phy_register_fixed_link(struct device_node *np) status.link = 1; status.duplex = of_property_read_bool(fixed_link_node, "full-duplex"); - if (of_property_read_u32(fixed_link_node, "speed", &status.speed)) + if (of_property_read_u32(fixed_link_node, "speed", + &status.speed)) { + of_node_put(fixed_link_node); return -EINVAL; + } status.pause = of_property_read_bool(fixed_link_node, "pause"); status.asym_pause = of_property_read_bool(fixed_link_node, "asym-pause"); diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 7035b997aaa5..6aaf425cebc3 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -14,7 +14,7 @@ * are obviously wrong for any sort of memory access. */ #define BPF_REGISTER_MAX_RANGE (1024 * 1024 * 1024) -#define BPF_REGISTER_MIN_RANGE -(1024 * 1024 * 1024) +#define BPF_REGISTER_MIN_RANGE -1 struct bpf_reg_state { enum bpf_reg_type type; @@ -22,7 +22,8 @@ struct bpf_reg_state { * Used to determine if any memory access using this register will * result in a bad access. */ - u64 min_value, max_value; + s64 min_value; + u64 max_value; union { /* valid when type == CONST_IMM | PTR_TO_STACK | UNKNOWN_VALUE */ s64 imm; diff --git a/include/net/gro_cells.h b/include/net/gro_cells.h index d15214d673b2..2a1abbf8da74 100644 --- a/include/net/gro_cells.h +++ b/include/net/gro_cells.h @@ -68,6 +68,9 @@ static inline int gro_cells_init(struct gro_cells *gcells, struct net_device *de struct gro_cell *cell = per_cpu_ptr(gcells->cells, i); __skb_queue_head_init(&cell->napi_skbs); + + set_bit(NAPI_STATE_NO_BUSY_POLL, &cell->napi.state); + netif_napi_add(dev, &cell->napi, gro_cell_poll, 64); napi_enable(&cell->napi); } diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index b9314b48e39f..f390c3bb05c5 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -243,6 +243,7 @@ int fib_table_dump(struct fib_table *table, struct sk_buff *skb, struct netlink_callback *cb); int fib_table_flush(struct net *net, struct fib_table *table); struct fib_table *fib_trie_unmerge(struct fib_table *main_tb); +void fib_table_flush_external(struct fib_table *table); void fib_free_table(struct fib_table *tb); #ifndef CONFIG_IP_MULTIPLE_TABLES diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index fc4f757107df..0940598c002f 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -170,7 +170,7 @@ static inline struct net *copy_net_ns(unsigned long flags, extern struct list_head net_namespace_list; struct net *get_net_ns_by_pid(pid_t pid); -struct net *get_net_ns_by_fd(int pid); +struct net *get_net_ns_by_fd(int fd); #ifdef CONFIG_SYSCTL void ipx_register_sysctl(void); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 99a7e5b388f2..6a936159c6e0 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -216,8 +216,8 @@ static void print_verifier_state(struct bpf_verifier_state *state) reg->map_ptr->key_size, reg->map_ptr->value_size); if (reg->min_value != BPF_REGISTER_MIN_RANGE) - verbose(",min_value=%llu", - (unsigned long long)reg->min_value); + verbose(",min_value=%lld", + (long long)reg->min_value); if (reg->max_value != BPF_REGISTER_MAX_RANGE) verbose(",max_value=%llu", (unsigned long long)reg->max_value); @@ -758,7 +758,7 @@ static int check_mem_access(struct bpf_verifier_env *env, u32 regno, int off, * index'es we need to make sure that whatever we use * will have a set floor within our range. */ - if ((s64)reg->min_value < 0) { + if (reg->min_value < 0) { verbose("R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n", regno); return -EACCES; @@ -1468,7 +1468,8 @@ static void check_reg_overflow(struct bpf_reg_state *reg) { if (reg->max_value > BPF_REGISTER_MAX_RANGE) reg->max_value = BPF_REGISTER_MAX_RANGE; - if ((s64)reg->min_value < BPF_REGISTER_MIN_RANGE) + if (reg->min_value < BPF_REGISTER_MIN_RANGE || + reg->min_value > BPF_REGISTER_MAX_RANGE) reg->min_value = BPF_REGISTER_MIN_RANGE; } @@ -1476,7 +1477,8 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env, struct bpf_insn *insn) { struct bpf_reg_state *regs = env->cur_state.regs, *dst_reg; - u64 min_val = BPF_REGISTER_MIN_RANGE, max_val = BPF_REGISTER_MAX_RANGE; + s64 min_val = BPF_REGISTER_MIN_RANGE; + u64 max_val = BPF_REGISTER_MAX_RANGE; bool min_set = false, max_set = false; u8 opcode = BPF_OP(insn->code); @@ -1512,22 +1514,43 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env, return; } + /* If one of our values was at the end of our ranges then we can't just + * do our normal operations to the register, we need to set the values + * to the min/max since they are undefined. + */ + if (min_val == BPF_REGISTER_MIN_RANGE) + dst_reg->min_value = BPF_REGISTER_MIN_RANGE; + if (max_val == BPF_REGISTER_MAX_RANGE) + dst_reg->max_value = BPF_REGISTER_MAX_RANGE; + switch (opcode) { case BPF_ADD: - dst_reg->min_value += min_val; - dst_reg->max_value += max_val; + if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE) + dst_reg->min_value += min_val; + if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE) + dst_reg->max_value += max_val; break; case BPF_SUB: - dst_reg->min_value -= min_val; - dst_reg->max_value -= max_val; + if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE) + dst_reg->min_value -= min_val; + if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE) + dst_reg->max_value -= max_val; break; case BPF_MUL: - dst_reg->min_value *= min_val; - dst_reg->max_value *= max_val; + if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE) + dst_reg->min_value *= min_val; + if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE) + dst_reg->max_value *= max_val; break; case BPF_AND: - /* & is special since it could end up with 0 bits set. */ - dst_reg->min_value &= min_val; + /* Disallow AND'ing of negative numbers, ain't nobody got time + * for that. Otherwise the minimum is 0 and the max is the max + * value we could AND against. + */ + if (min_val < 0) + dst_reg->min_value = BPF_REGISTER_MIN_RANGE; + else + dst_reg->min_value = 0; dst_reg->max_value = max_val; break; case BPF_LSH: @@ -1537,24 +1560,25 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env, */ if (min_val > ilog2(BPF_REGISTER_MAX_RANGE)) dst_reg->min_value = BPF_REGISTER_MIN_RANGE; - else + else if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE) dst_reg->min_value <<= min_val; if (max_val > ilog2(BPF_REGISTER_MAX_RANGE)) dst_reg->max_value = BPF_REGISTER_MAX_RANGE; - else + else if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE) dst_reg->max_value <<= max_val; break; case BPF_RSH: - dst_reg->min_value >>= min_val; - dst_reg->max_value >>= max_val; - break; - case BPF_MOD: - /* % is special since it is an unsigned modulus, so the floor - * will always be 0. + /* RSH by a negative number is undefined, and the BPF_RSH is an + * unsigned shift, so make the appropriate casts. */ - dst_reg->min_value = 0; - dst_reg->max_value = max_val - 1; + if (min_val < 0 || dst_reg->min_value < 0) + dst_reg->min_value = BPF_REGISTER_MIN_RANGE; + else + dst_reg->min_value = + (u64)(dst_reg->min_value) >> min_val; + if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE) + dst_reg->max_value >>= max_val; break; default: reset_reg_range_values(regs, insn->dst_reg); diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h index 51c4b24b6328..c2b88490d857 100644 --- a/kernel/locking/lockdep_internals.h +++ b/kernel/locking/lockdep_internals.h @@ -46,6 +46,14 @@ enum { (LOCKF_USED_IN_HARDIRQ_READ | LOCKF_USED_IN_SOFTIRQ_READ) /* + * CONFIG_PROVE_LOCKING_SMALL is defined for sparc. Sparc requires .text, + * .data and .bss to fit in required 32MB limit for the kernel. With + * PROVE_LOCKING we could go over this limit and cause system boot-up problems. + * So, reduce the static allocations for lockdeps related structures so that + * everything fits in current required size limit. + */ +#ifdef CONFIG_PROVE_LOCKING_SMALL +/* * MAX_LOCKDEP_ENTRIES is the maximum number of lock dependencies * we track. * @@ -54,18 +62,24 @@ enum { * table (if it's not there yet), and we check it for lock order * conflicts and deadlocks. */ +#define MAX_LOCKDEP_ENTRIES 16384UL +#define MAX_LOCKDEP_CHAINS_BITS 15 +#define MAX_STACK_TRACE_ENTRIES 262144UL +#else #define MAX_LOCKDEP_ENTRIES 32768UL #define MAX_LOCKDEP_CHAINS_BITS 16 -#define MAX_LOCKDEP_CHAINS (1UL << MAX_LOCKDEP_CHAINS_BITS) - -#define MAX_LOCKDEP_CHAIN_HLOCKS (MAX_LOCKDEP_CHAINS*5) /* * Stack-trace: tightly packed array of stack backtrace * addresses. Protected by the hash_lock. */ #define MAX_STACK_TRACE_ENTRIES 524288UL +#endif + +#define MAX_LOCKDEP_CHAINS (1UL << MAX_LOCKDEP_CHAINS_BITS) + +#define MAX_LOCKDEP_CHAIN_HLOCKS (MAX_LOCKDEP_CHAINS*5) extern struct list_head all_lock_classes; extern struct lock_chain lock_chains[]; diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index b01e547d4d04..a6c8db1d62f6 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1085,6 +1085,9 @@ config PROVE_LOCKING For more details, see Documentation/locking/lockdep-design.txt. +config PROVE_LOCKING_SMALL + bool + config LOCKDEP bool depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index e034afbd1bb0..08ce36147c4c 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -652,6 +652,7 @@ void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface, batadv_softif_destroy_sysfs(hard_iface->soft_iface); } + hard_iface->soft_iface = NULL; batadv_hardif_put(hard_iface); out: diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c index 2333777f919d..8af1611b8ab2 100644 --- a/net/batman-adv/tp_meter.c +++ b/net/batman-adv/tp_meter.c @@ -837,6 +837,7 @@ static int batadv_tp_send(void *arg) primary_if = batadv_primary_if_get_selected(bat_priv); if (unlikely(!primary_if)) { err = BATADV_TP_REASON_DST_UNREACHABLE; + tp_vars->reason = err; goto out; } diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index f61c0e02a413..7001da910c6b 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -219,6 +219,8 @@ int peernet2id_alloc(struct net *net, struct net *peer) bool alloc; int id; + if (atomic_read(&net->count) == 0) + return NETNSA_NSID_NOT_ASSIGNED; spin_lock_irqsave(&net->nsid_lock, flags); alloc = atomic_read(&peer->count) == 0 ? false : true; id = __peernet2id_alloc(net, peer, &alloc); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index db313ec7af32..a99917b5de33 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -840,18 +840,20 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev, if (dev->dev.parent && dev_is_pci(dev->dev.parent) && (ext_filter_mask & RTEXT_FILTER_VF)) { int num_vfs = dev_num_vf(dev->dev.parent); - size_t size = nla_total_size(sizeof(struct nlattr)); - size += nla_total_size(num_vfs * sizeof(struct nlattr)); + size_t size = nla_total_size(0); size += num_vfs * - (nla_total_size(sizeof(struct ifla_vf_mac)) + - nla_total_size(MAX_VLAN_LIST_LEN * - sizeof(struct nlattr)) + + (nla_total_size(0) + + nla_total_size(sizeof(struct ifla_vf_mac)) + + nla_total_size(sizeof(struct ifla_vf_vlan)) + + nla_total_size(0) + /* nest IFLA_VF_VLAN_LIST */ nla_total_size(MAX_VLAN_LIST_LEN * sizeof(struct ifla_vf_vlan_info)) + nla_total_size(sizeof(struct ifla_vf_spoofchk)) + + nla_total_size(sizeof(struct ifla_vf_tx_rate)) + nla_total_size(sizeof(struct ifla_vf_rate)) + nla_total_size(sizeof(struct ifla_vf_link_state)) + nla_total_size(sizeof(struct ifla_vf_rss_query_en)) + + nla_total_size(0) + /* nest IFLA_VF_STATS */ /* IFLA_VF_STATS_RX_PACKETS */ nla_total_size_64bit(sizeof(__u64)) + /* IFLA_VF_STATS_TX_PACKETS */ @@ -899,7 +901,8 @@ static size_t rtnl_port_size(const struct net_device *dev, static size_t rtnl_xdp_size(const struct net_device *dev) { - size_t xdp_size = nla_total_size(1); /* XDP_ATTACHED */ + size_t xdp_size = nla_total_size(0) + /* nest IFLA_XDP */ + nla_total_size(1); /* XDP_ATTACHED */ if (!dev->netdev_ops->ndo_xdp) return 0; @@ -1606,7 +1609,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) head = &net->dev_index_head[h]; hlist_for_each_entry(dev, head, index_hlist) { if (link_dump_filtered(dev, master_idx, kind_ops)) - continue; + goto cont; if (idx < s_idx) goto cont; err = rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK, @@ -2849,7 +2852,10 @@ nla_put_failure: static inline size_t rtnl_fdb_nlmsg_size(void) { - return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(ETH_ALEN); + return NLMSG_ALIGN(sizeof(struct ndmsg)) + + nla_total_size(ETH_ALEN) + /* NDA_LLADDR */ + nla_total_size(sizeof(u16)) + /* NDA_VLAN */ + 0; } static void rtnl_fdb_notify(struct net_device *dev, u8 *addr, u16 vid, int type, diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index c3b80478226e..161fc0f0d752 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -151,7 +151,7 @@ static void fib_replace_table(struct net *net, struct fib_table *old, int fib_unmerge(struct net *net) { - struct fib_table *old, *new; + struct fib_table *old, *new, *main_table; /* attempt to fetch local table if it has been allocated */ old = fib_get_table(net, RT_TABLE_LOCAL); @@ -162,11 +162,21 @@ int fib_unmerge(struct net *net) if (!new) return -ENOMEM; + /* table is already unmerged */ + if (new == old) + return 0; + /* replace merged table with clean table */ - if (new != old) { - fib_replace_table(net, old, new); - fib_free_table(old); - } + fib_replace_table(net, old, new); + fib_free_table(old); + + /* attempt to fetch main table if it has been allocated */ + main_table = fib_get_table(net, RT_TABLE_MAIN); + if (!main_table) + return 0; + + /* flush local entries from main table */ + fib_table_flush_external(main_table); return 0; } diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 4cff74d4133f..026f309c51e9 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1743,8 +1743,10 @@ struct fib_table *fib_trie_unmerge(struct fib_table *oldtb) local_l = fib_find_node(lt, &local_tp, l->key); if (fib_insert_alias(lt, local_tp, local_l, new_fa, - NULL, l->key)) + NULL, l->key)) { + kmem_cache_free(fn_alias_kmem, new_fa); goto out; + } } /* stop loop if key wrapped back to 0 */ @@ -1760,6 +1762,71 @@ out: return NULL; } +/* Caller must hold RTNL */ +void fib_table_flush_external(struct fib_table *tb) +{ + struct trie *t = (struct trie *)tb->tb_data; + struct key_vector *pn = t->kv; + unsigned long cindex = 1; + struct hlist_node *tmp; + struct fib_alias *fa; + + /* walk trie in reverse order */ + for (;;) { + unsigned char slen = 0; + struct key_vector *n; + + if (!(cindex--)) { + t_key pkey = pn->key; + + /* cannot resize the trie vector */ + if (IS_TRIE(pn)) + break; + + /* resize completed node */ + pn = resize(t, pn); + cindex = get_index(pkey, pn); + + continue; + } + + /* grab the next available node */ + n = get_child(pn, cindex); + if (!n) + continue; + + if (IS_TNODE(n)) { + /* record pn and cindex for leaf walking */ + pn = n; + cindex = 1ul << n->bits; + + continue; + } + + hlist_for_each_entry_safe(fa, tmp, &n->leaf, fa_list) { + /* if alias was cloned to local then we just + * need to remove the local copy from main + */ + if (tb->tb_id != fa->tb_id) { + hlist_del_rcu(&fa->fa_list); + alias_free_mem_rcu(fa); + continue; + } + + /* record local slen */ + slen = fa->fa_slen; + } + + /* update leaf slen */ + n->slen = slen; + + if (hlist_empty(&n->leaf)) { + put_child_root(pn, n->key, NULL); + node_free(n); + } + } +} + /* Caller must hold RTNL. */ int fib_table_flush(struct net *net, struct fib_table *tb) { diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 606cc3e85d2b..15db786d50ed 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -162,7 +162,7 @@ static int unsolicited_report_interval(struct in_device *in_dev) } static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im); -static void igmpv3_del_delrec(struct in_device *in_dev, __be32 multiaddr); +static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im); static void igmpv3_clear_delrec(struct in_device *in_dev); static int sf_setstate(struct ip_mc_list *pmc); static void sf_markstate(struct ip_mc_list *pmc); @@ -1130,10 +1130,15 @@ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im) spin_unlock_bh(&in_dev->mc_tomb_lock); } -static void igmpv3_del_delrec(struct in_device *in_dev, __be32 multiaddr) +/* + * restore ip_mc_list deleted records + */ +static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im) { struct ip_mc_list *pmc, *pmc_prev; - struct ip_sf_list *psf, *psf_next; + struct ip_sf_list *psf; + struct net *net = dev_net(in_dev->dev); + __be32 multiaddr = im->multiaddr; spin_lock_bh(&in_dev->mc_tomb_lock); pmc_prev = NULL; @@ -1149,16 +1154,26 @@ static void igmpv3_del_delrec(struct in_device *in_dev, __be32 multiaddr) in_dev->mc_tomb = pmc->next; } spin_unlock_bh(&in_dev->mc_tomb_lock); + + spin_lock_bh(&im->lock); if (pmc) { - for (psf = pmc->tomb; psf; psf = psf_next) { - psf_next = psf->sf_next; - kfree(psf); + im->interface = pmc->interface; + im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; + im->sfmode = pmc->sfmode; + if (pmc->sfmode == MCAST_INCLUDE) { + im->tomb = pmc->tomb; + im->sources = pmc->sources; + for (psf = im->sources; psf; psf = psf->sf_next) + psf->sf_crcount = im->crcount; } in_dev_put(pmc->interface); - kfree(pmc); } + spin_unlock_bh(&im->lock); } +/* + * flush ip_mc_list deleted records + */ static void igmpv3_clear_delrec(struct in_device *in_dev) { struct ip_mc_list *pmc, *nextpmc; @@ -1366,7 +1381,7 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) ip_mc_hash_add(in_dev, im); #ifdef CONFIG_IP_MULTICAST - igmpv3_del_delrec(in_dev, im->multiaddr); + igmpv3_del_delrec(in_dev, im); #endif igmp_group_added(im); if (!in_dev->dead) @@ -1626,8 +1641,12 @@ void ip_mc_remap(struct in_device *in_dev) ASSERT_RTNL(); - for_each_pmc_rtnl(in_dev, pmc) + for_each_pmc_rtnl(in_dev, pmc) { +#ifdef CONFIG_IP_MULTICAST + igmpv3_del_delrec(in_dev, pmc); +#endif igmp_group_added(pmc); + } } /* Device going down */ @@ -1648,7 +1667,6 @@ void ip_mc_down(struct in_device *in_dev) in_dev->mr_gq_running = 0; if (del_timer(&in_dev->mr_gq_timer)) __in_dev_put(in_dev); - igmpv3_clear_delrec(in_dev); #endif ip_mc_dec_group(in_dev, IGMP_ALL_HOSTS); @@ -1688,8 +1706,12 @@ void ip_mc_up(struct in_device *in_dev) #endif ip_mc_inc_group(in_dev, IGMP_ALL_HOSTS); - for_each_pmc_rtnl(in_dev, pmc) + for_each_pmc_rtnl(in_dev, pmc) { +#ifdef CONFIG_IP_MULTICAST + igmpv3_del_delrec(in_dev, pmc); +#endif igmp_group_added(pmc); + } } /* @@ -1704,13 +1726,13 @@ void ip_mc_destroy_dev(struct in_device *in_dev) /* Deactivate timers */ ip_mc_down(in_dev); +#ifdef CONFIG_IP_MULTICAST + igmpv3_clear_delrec(in_dev); +#endif while ((i = rtnl_dereference(in_dev->mc_list)) != NULL) { in_dev->mc_list = i->next_rcu; in_dev->mc_count--; - - /* We've dropped the groups in ip_mc_down already */ - ip_mc_clear_src(i); ip_ma_put(i); } } diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 1294af4e0127..f9038d6b109e 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -200,8 +200,10 @@ static void tcp_reinit_congestion_control(struct sock *sk, icsk->icsk_ca_ops = ca; icsk->icsk_ca_setsockopt = 1; - if (sk->sk_state != TCP_CLOSE) + if (sk->sk_state != TCP_CLOSE) { + memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); tcp_init_congestion_control(sk); + } } /* Manage refcounts on socket close. */ diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index d123d68f4d1d..0de9d5d2b9ae 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1652,10 +1652,10 @@ static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb, if (use_hash2) { hash2_any = udp4_portaddr_hash(net, htonl(INADDR_ANY), hnum) & - udp_table.mask; - hash2 = udp4_portaddr_hash(net, daddr, hnum) & udp_table.mask; + udptable->mask; + hash2 = udp4_portaddr_hash(net, daddr, hnum) & udptable->mask; start_lookup: - hslot = &udp_table.hash2[hash2]; + hslot = &udptable->hash2[hash2]; offset = offsetof(typeof(*sk), __sk_common.skc_portaddr_node); } diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 87784560dc46..0a4759b89da2 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1034,6 +1034,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield, int mtu; unsigned int psh_hlen = sizeof(struct ipv6hdr) + t->encap_hlen; unsigned int max_headroom = psh_hlen; + bool use_cache = false; u8 hop_limit; int err = -1; @@ -1066,7 +1067,15 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield, memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr)); neigh_release(neigh); - } else if (!fl6->flowi6_mark) + } else if (!(t->parms.flags & + (IP6_TNL_F_USE_ORIG_TCLASS | IP6_TNL_F_USE_ORIG_FWMARK))) { + /* enable the cache only only if the routing decision does + * not depend on the current inner header value + */ + use_cache = true; + } + + if (use_cache) dst = dst_cache_get(&t->dst_cache); if (!ip6_tnl_xmit_ctl(t, &fl6->saddr, &fl6->daddr)) @@ -1150,7 +1159,7 @@ route_lookup: if (t->encap.type != TUNNEL_ENCAP_NONE) goto tx_err_dst_release; } else { - if (!fl6->flowi6_mark && ndst) + if (use_cache && ndst) dst_cache_set_ip6(&t->dst_cache, ndst, &fl6->saddr); } skb_dst_set(skb, dst); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index b2ef061e6836..e5056d4873d1 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -706,10 +706,10 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb, if (use_hash2) { hash2_any = udp6_portaddr_hash(net, &in6addr_any, hnum) & - udp_table.mask; - hash2 = udp6_portaddr_hash(net, daddr, hnum) & udp_table.mask; + udptable->mask; + hash2 = udp6_portaddr_hash(net, daddr, hnum) & udptable->mask; start_lookup: - hslot = &udp_table.hash2[hash2]; + hslot = &udptable->hash2[hash2]; offset = offsetof(typeof(*sk), __sk_common.skc_portaddr_node); } diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index 965f7e344cef..3dc97b4f982b 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -97,7 +97,7 @@ static int l2tp_eth_dev_xmit(struct sk_buff *skb, struct net_device *dev) unsigned int len = skb->len; int ret = l2tp_xmit_skb(session, skb, session->hdr_len); - if (likely(ret == NET_XMIT_SUCCESS)) { + if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) { atomic_long_add(len, &priv->tx_bytes); atomic_long_inc(&priv->tx_packets); } else { diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index fce25afb652a..982f6c44ea01 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -251,8 +251,6 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) int ret; int chk_addr_ret; - if (!sock_flag(sk, SOCK_ZAPPED)) - return -EINVAL; if (addr_len < sizeof(struct sockaddr_l2tpip)) return -EINVAL; if (addr->l2tp_family != AF_INET) @@ -267,6 +265,9 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) read_unlock_bh(&l2tp_ip_lock); lock_sock(sk); + if (!sock_flag(sk, SOCK_ZAPPED)) + goto out; + if (sk->sk_state != TCP_CLOSE || addr_len < sizeof(struct sockaddr_l2tpip)) goto out; diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index ad3468c32b53..9978d01ba0ba 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -269,8 +269,6 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) int addr_type; int err; - if (!sock_flag(sk, SOCK_ZAPPED)) - return -EINVAL; if (addr->l2tp_family != AF_INET6) return -EINVAL; if (addr_len < sizeof(*addr)) @@ -296,6 +294,9 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) lock_sock(sk); err = -EINVAL; + if (!sock_flag(sk, SOCK_ZAPPED)) + goto out_unlock; + if (sk->sk_state != TCP_CLOSE) goto out_unlock; diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 78e9ecbc96e6..8e05032689f0 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -688,7 +688,7 @@ static void __sta_info_recalc_tim(struct sta_info *sta, bool ignore_pending) } /* No need to do anything if the driver does all */ - if (!local->ops->set_tim) + if (ieee80211_hw_check(&local->hw, AP_LINK_PS)) return; if (sta->dead) diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 1c56abc49627..bd5f4be89435 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1501,7 +1501,6 @@ static bool ieee80211_queue_skb(struct ieee80211_local *local, struct sta_info *sta, struct sk_buff *skb) { - struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct fq *fq = &local->fq; struct ieee80211_vif *vif; struct txq_info *txqi; @@ -1526,8 +1525,6 @@ static bool ieee80211_queue_skb(struct ieee80211_local *local, if (!txqi) return false; - info->control.vif = vif; - spin_lock_bh(&fq->lock); ieee80211_txq_enqueue(local, txqi, skb); spin_unlock_bh(&fq->lock); @@ -3213,7 +3210,6 @@ static void ieee80211_xmit_fast_finish(struct ieee80211_sub_if_data *sdata, if (hdr->frame_control & cpu_to_le16(IEEE80211_STYPE_QOS_DATA)) { tid = skb->priority & IEEE80211_QOS_CTL_TAG1D_MASK; - *ieee80211_get_qos_ctl(hdr) = tid; hdr->seq_ctrl = ieee80211_tx_next_seq(sta, tid); } else { info->flags |= IEEE80211_TX_CTL_ASSIGN_SEQ; @@ -3338,6 +3334,11 @@ static bool ieee80211_xmit_fast(struct ieee80211_sub_if_data *sdata, (tid_tx ? IEEE80211_TX_CTL_AMPDU : 0); info->control.flags = IEEE80211_TX_CTRL_FAST_XMIT; + if (hdr->frame_control & cpu_to_le16(IEEE80211_STYPE_QOS_DATA)) { + tid = skb->priority & IEEE80211_QOS_CTL_TAG1D_MASK; + *ieee80211_get_qos_ctl(hdr) = tid; + } + __skb_queue_head_init(&tx.skbs); tx.flags = IEEE80211_TX_UNICAST; @@ -3426,6 +3427,11 @@ begin: goto begin; } + if (test_bit(IEEE80211_TXQ_AMPDU, &txqi->flags)) + info->flags |= IEEE80211_TX_CTL_AMPDU; + else + info->flags &= ~IEEE80211_TX_CTL_AMPDU; + if (info->control.flags & IEEE80211_TX_CTRL_FAST_XMIT) { struct sta_info *sta = container_of(txq->sta, struct sta_info, sta); diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index ee715764a828..6832bf6ab69f 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -270,6 +270,22 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, vht_cap->vht_mcs.tx_mcs_map |= cpu_to_le16(peer_tx << i * 2); } + /* + * This is a workaround for VHT-enabled STAs which break the spec + * and have the VHT-MCS Rx map filled in with value 3 for all eight + * spacial streams, an example is AR9462. + * + * As per spec, in section 22.1.1 Introduction to the VHT PHY + * A VHT STA shall support at least single spactial stream VHT-MCSs + * 0 to 7 (transmit and receive) in all supported channel widths. + */ + if (vht_cap->vht_mcs.rx_mcs_map == cpu_to_le16(0xFFFF)) { + vht_cap->vht_supported = false; + sdata_info(sdata, "Ignoring VHT IE from %pM due to invalid rx_mcs_map\n", + sta->addr); + return; + } + /* finally set up the bandwidth */ switch (vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK) { case IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ: diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 2b2a7974e4bb..8e93d4afe5ea 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -112,7 +112,7 @@ static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb, for (it_chain = chain; (tp = rtnl_dereference(*it_chain)) != NULL; it_chain = &tp->next) - tfilter_notify(net, oskb, n, tp, 0, event, false); + tfilter_notify(net, oskb, n, tp, n->nlmsg_flags, event, false); } /* Select new prio value from the range, managed by kernel. */ @@ -430,7 +430,8 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb, if (!skb) return -ENOBUFS; - if (tcf_fill_node(net, skb, tp, fh, portid, n->nlmsg_seq, 0, event) <= 0) { + if (tcf_fill_node(net, skb, tp, fh, portid, n->nlmsg_seq, + n->nlmsg_flags, event) <= 0) { kfree_skb(skb); return -EINVAL; } diff --git a/net/tipc/socket.c b/net/tipc/socket.c index f9f5f3c3dab5..db32777ab591 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1,7 +1,7 @@ /* * net/tipc/socket.c: TIPC socket API * - * Copyright (c) 2001-2007, 2012-2015, Ericsson AB + * Copyright (c) 2001-2007, 2012-2016, Ericsson AB * Copyright (c) 2004-2008, 2010-2013, Wind River Systems * All rights reserved. * @@ -129,54 +129,8 @@ static const struct proto_ops packet_ops; static const struct proto_ops stream_ops; static const struct proto_ops msg_ops; static struct proto tipc_proto; - static const struct rhashtable_params tsk_rht_params; -/* - * Revised TIPC socket locking policy: - * - * Most socket operations take the standard socket lock when they start - * and hold it until they finish (or until they need to sleep). Acquiring - * this lock grants the owner exclusive access to the fields of the socket - * data structures, with the exception of the backlog queue. A few socket - * operations can be done without taking the socket lock because they only - * read socket information that never changes during the life of the socket. - * - * Socket operations may acquire the lock for the associated TIPC port if they - * need to perform an operation on the port. If any routine needs to acquire - * both the socket lock and the port lock it must take the socket lock first - * to avoid the risk of deadlock. - * - * The dispatcher handling incoming messages cannot grab the socket lock in - * the standard fashion, since invoked it runs at the BH level and cannot block. - * Instead, it checks to see if the socket lock is currently owned by someone, - * and either handles the message itself or adds it to the socket's backlog - * queue; in the latter case the queued message is processed once the process - * owning the socket lock releases it. - * - * NOTE: Releasing the socket lock while an operation is sleeping overcomes - * the problem of a blocked socket operation preventing any other operations - * from occurring. However, applications must be careful if they have - * multiple threads trying to send (or receive) on the same socket, as these - * operations might interfere with each other. For example, doing a connect - * and a receive at the same time might allow the receive to consume the - * ACK message meant for the connect. While additional work could be done - * to try and overcome this, it doesn't seem to be worthwhile at the present. - * - * NOTE: Releasing the socket lock while an operation is sleeping also ensures - * that another operation that must be performed in a non-blocking manner is - * not delayed for very long because the lock has already been taken. - * - * NOTE: This code assumes that certain fields of a port/socket pair are - * constant over its lifetime; such fields can be examined without taking - * the socket lock and/or port lock, and do not need to be re-read even - * after resuming processing after waiting. These fields include: - * - socket type - * - pointer to socket sk structure (aka tipc_sock structure) - * - pointer to port structure - * - port reference - */ - static u32 tsk_own_node(struct tipc_sock *tsk) { return msg_prevnode(&tsk->phdr); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 5d1c14a2f268..2358f2690ec5 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2199,7 +2199,8 @@ out: * Sleep until more data has arrived. But check for races.. */ static long unix_stream_data_wait(struct sock *sk, long timeo, - struct sk_buff *last, unsigned int last_len) + struct sk_buff *last, unsigned int last_len, + bool freezable) { struct sk_buff *tail; DEFINE_WAIT(wait); @@ -2220,7 +2221,10 @@ static long unix_stream_data_wait(struct sock *sk, long timeo, sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); unix_state_unlock(sk); - timeo = freezable_schedule_timeout(timeo); + if (freezable) + timeo = freezable_schedule_timeout(timeo); + else + timeo = schedule_timeout(timeo); unix_state_lock(sk); if (sock_flag(sk, SOCK_DEAD)) @@ -2250,7 +2254,8 @@ struct unix_stream_read_state { unsigned int splice_flags; }; -static int unix_stream_read_generic(struct unix_stream_read_state *state) +static int unix_stream_read_generic(struct unix_stream_read_state *state, + bool freezable) { struct scm_cookie scm; struct socket *sock = state->socket; @@ -2330,7 +2335,7 @@ again: mutex_unlock(&u->iolock); timeo = unix_stream_data_wait(sk, timeo, last, - last_len); + last_len, freezable); if (signal_pending(current)) { err = sock_intr_errno(timeo); @@ -2472,7 +2477,7 @@ static int unix_stream_recvmsg(struct socket *sock, struct msghdr *msg, .flags = flags }; - return unix_stream_read_generic(&state); + return unix_stream_read_generic(&state, true); } static int unix_stream_splice_actor(struct sk_buff *skb, @@ -2503,7 +2508,7 @@ static ssize_t unix_stream_splice_read(struct socket *sock, loff_t *ppos, flags & SPLICE_F_NONBLOCK) state.flags = MSG_DONTWAIT; - return unix_stream_read_generic(&state); + return unix_stream_read_generic(&state, false); } static int unix_shutdown(struct socket *sock, int mode) diff --git a/net/wireless/core.h b/net/wireless/core.h index 08d2e948c9ad..f0c0c8a48c92 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -71,6 +71,7 @@ struct cfg80211_registered_device { struct list_head bss_list; struct rb_root bss_tree; u32 bss_generation; + u32 bss_entries; struct cfg80211_scan_request *scan_req; /* protected by RTNL */ struct sk_buff *scan_msg; struct cfg80211_sched_scan_request __rcu *sched_scan_req; diff --git a/net/wireless/scan.c b/net/wireless/scan.c index b5bd58d0f731..35ad69fd0838 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -57,6 +57,19 @@ * also linked into the probe response struct. */ +/* + * Limit the number of BSS entries stored in mac80211. Each one is + * a bit over 4k at most, so this limits to roughly 4-5M of memory. + * If somebody wants to really attack this though, they'd likely + * use small beacons, and only one type of frame, limiting each of + * the entries to a much smaller size (in order to generate more + * entries in total, so overhead is bigger.) + */ +static int bss_entries_limit = 1000; +module_param(bss_entries_limit, int, 0644); +MODULE_PARM_DESC(bss_entries_limit, + "limit to number of scan BSS entries (per wiphy, default 1000)"); + #define IEEE80211_SCAN_RESULT_EXPIRE (30 * HZ) static void bss_free(struct cfg80211_internal_bss *bss) @@ -137,6 +150,10 @@ static bool __cfg80211_unlink_bss(struct cfg80211_registered_device *rdev, list_del_init(&bss->list); rb_erase(&bss->rbn, &rdev->bss_tree); + rdev->bss_entries--; + WARN_ONCE((rdev->bss_entries == 0) ^ list_empty(&rdev->bss_list), + "rdev bss entries[%d]/list[empty:%d] corruption\n", + rdev->bss_entries, list_empty(&rdev->bss_list)); bss_ref_put(rdev, bss); return true; } @@ -163,6 +180,40 @@ static void __cfg80211_bss_expire(struct cfg80211_registered_device *rdev, rdev->bss_generation++; } +static bool cfg80211_bss_expire_oldest(struct cfg80211_registered_device *rdev) +{ + struct cfg80211_internal_bss *bss, *oldest = NULL; + bool ret; + + lockdep_assert_held(&rdev->bss_lock); + + list_for_each_entry(bss, &rdev->bss_list, list) { + if (atomic_read(&bss->hold)) + continue; + + if (!list_empty(&bss->hidden_list) && + !bss->pub.hidden_beacon_bss) + continue; + + if (oldest && time_before(oldest->ts, bss->ts)) + continue; + oldest = bss; + } + + if (WARN_ON(!oldest)) + return false; + + /* + * The callers make sure to increase rdev->bss_generation if anything + * gets removed (and a new entry added), so there's no need to also do + * it here. + */ + + ret = __cfg80211_unlink_bss(rdev, oldest); + WARN_ON(!ret); + return ret; +} + void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev, bool send_message) { @@ -689,6 +740,7 @@ static bool cfg80211_combine_bsses(struct cfg80211_registered_device *rdev, const u8 *ie; int i, ssidlen; u8 fold = 0; + u32 n_entries = 0; ies = rcu_access_pointer(new->pub.beacon_ies); if (WARN_ON(!ies)) @@ -712,6 +764,12 @@ static bool cfg80211_combine_bsses(struct cfg80211_registered_device *rdev, /* This is the bad part ... */ list_for_each_entry(bss, &rdev->bss_list, list) { + /* + * we're iterating all the entries anyway, so take the + * opportunity to validate the list length accounting + */ + n_entries++; + if (!ether_addr_equal(bss->pub.bssid, new->pub.bssid)) continue; if (bss->pub.channel != new->pub.channel) @@ -740,6 +798,10 @@ static bool cfg80211_combine_bsses(struct cfg80211_registered_device *rdev, new->pub.beacon_ies); } + WARN_ONCE(n_entries != rdev->bss_entries, + "rdev bss entries[%d]/list[len:%d] corruption\n", + rdev->bss_entries, n_entries); + return true; } @@ -894,7 +956,14 @@ cfg80211_bss_update(struct cfg80211_registered_device *rdev, } } + if (rdev->bss_entries >= bss_entries_limit && + !cfg80211_bss_expire_oldest(rdev)) { + kfree(new); + goto drop; + } + list_add_tail(&new->list, &rdev->bss_list); + rdev->bss_entries++; rb_insert_bss(rdev, new); found = new; } diff --git a/net/wireless/util.c b/net/wireless/util.c index 5ea12afc7706..659b507b347d 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1158,7 +1158,8 @@ static u32 cfg80211_calculate_bitrate_vht(struct rate_info *rate) 58500000, 65000000, 78000000, - 0, + /* not in the spec, but some devices use this: */ + 86500000, }, { 13500000, 27000000, |