diff options
56 files changed, 478 insertions, 205 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index e3581413420c..810d5d990f4a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -62,7 +62,15 @@ trivial patch so apply some common sense. 7. When sending security related changes or reports to a maintainer please Cc: security@kernel.org, especially if the maintainer - does not respond. + does not respond. Please keep in mind that the security team is + a small set of people who can be efficient only when working on + verified bugs. Please only Cc: this list when you have identified + that the bug would present a short-term risk to other users if it + were publicly disclosed. For example, reports of address leaks do + not represent an immediate threat and are better handled publicly, + and ideally, should come with a patch proposal. Please do not send + automated reports to this list either. Such bugs will be handled + better and faster in the usual public places. 8. Happy hacking. @@ -12233,7 +12241,7 @@ M: Security Officers <security@kernel.org> S: Supported SECURITY SUBSYSTEM -M: James Morris <james.l.morris@oracle.com> +M: James Morris <jmorris@namei.org> M: "Serge E. Hallyn" <serge@hallyn.com> L: linux-security-module@vger.kernel.org (suggested Cc:) T: git git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/linux-security.git diff --git a/arch/sparc/crypto/Makefile b/arch/sparc/crypto/Makefile index 818d3aa5172e..d257186c27d1 100644 --- a/arch/sparc/crypto/Makefile +++ b/arch/sparc/crypto/Makefile @@ -10,7 +10,7 @@ obj-$(CONFIG_CRYPTO_MD5_SPARC64) += md5-sparc64.o obj-$(CONFIG_CRYPTO_AES_SPARC64) += aes-sparc64.o obj-$(CONFIG_CRYPTO_DES_SPARC64) += des-sparc64.o -obj-$(CONFIG_CRYPTO_DES_SPARC64) += camellia-sparc64.o +obj-$(CONFIG_CRYPTO_CAMELLIA_SPARC64) += camellia-sparc64.o obj-$(CONFIG_CRYPTO_CRC32C_SPARC64) += crc32c-sparc64.o diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 81bb565f4497..7e2baf7304ae 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -29,10 +29,13 @@ KASAN_SANITIZE_stacktrace.o := n KASAN_SANITIZE_paravirt.o := n OBJECT_FILES_NON_STANDARD_relocate_kernel_$(BITS).o := y -OBJECT_FILES_NON_STANDARD_ftrace_$(BITS).o := y OBJECT_FILES_NON_STANDARD_test_nx.o := y OBJECT_FILES_NON_STANDARD_paravirt_patch_$(BITS).o := y +ifdef CONFIG_FRAME_POINTER +OBJECT_FILES_NON_STANDARD_ftrace_$(BITS).o := y +endif + # If instrumentation of this dir is enabled, boot hangs during first second. # Probably could be more selective here, but note that files related to irqs, # boot, dumpstack/stacktrace, etc are either non-interesting or can lead to diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S index 7cb8ba08beb9..ef61f540cf0a 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -8,6 +8,7 @@ #include <asm/ftrace.h> #include <asm/export.h> #include <asm/nospec-branch.h> +#include <asm/unwind_hints.h> .code64 .section .entry.text, "ax" @@ -20,7 +21,6 @@ EXPORT_SYMBOL(__fentry__) EXPORT_SYMBOL(mcount) #endif -/* All cases save the original rbp (8 bytes) */ #ifdef CONFIG_FRAME_POINTER # ifdef CC_USING_FENTRY /* Save parent and function stack frames (rip and rbp) */ @@ -31,7 +31,7 @@ EXPORT_SYMBOL(mcount) # endif #else /* No need to save a stack frame */ -# define MCOUNT_FRAME_SIZE 8 +# define MCOUNT_FRAME_SIZE 0 #endif /* CONFIG_FRAME_POINTER */ /* Size of stack used to save mcount regs in save_mcount_regs */ @@ -64,10 +64,10 @@ EXPORT_SYMBOL(mcount) */ .macro save_mcount_regs added=0 - /* Always save the original rbp */ +#ifdef CONFIG_FRAME_POINTER + /* Save the original rbp */ pushq %rbp -#ifdef CONFIG_FRAME_POINTER /* * Stack traces will stop at the ftrace trampoline if the frame pointer * is not set up properly. If fentry is used, we need to save a frame @@ -105,7 +105,11 @@ EXPORT_SYMBOL(mcount) * Save the original RBP. Even though the mcount ABI does not * require this, it helps out callers. */ +#ifdef CONFIG_FRAME_POINTER movq MCOUNT_REG_SIZE-8(%rsp), %rdx +#else + movq %rbp, %rdx +#endif movq %rdx, RBP(%rsp) /* Copy the parent address into %rsi (second parameter) */ @@ -148,7 +152,7 @@ EXPORT_SYMBOL(mcount) ENTRY(function_hook) retq -END(function_hook) +ENDPROC(function_hook) ENTRY(ftrace_caller) /* save_mcount_regs fills in first two parameters */ @@ -184,7 +188,7 @@ GLOBAL(ftrace_graph_call) /* This is weak to keep gas from relaxing the jumps */ WEAK(ftrace_stub) retq -END(ftrace_caller) +ENDPROC(ftrace_caller) ENTRY(ftrace_regs_caller) /* Save the current flags before any operations that can change them */ @@ -255,7 +259,7 @@ GLOBAL(ftrace_regs_caller_end) jmp ftrace_epilogue -END(ftrace_regs_caller) +ENDPROC(ftrace_regs_caller) #else /* ! CONFIG_DYNAMIC_FTRACE */ @@ -313,9 +317,10 @@ ENTRY(ftrace_graph_caller) restore_mcount_regs retq -END(ftrace_graph_caller) +ENDPROC(ftrace_graph_caller) -GLOBAL(return_to_handler) +ENTRY(return_to_handler) + UNWIND_HINT_EMPTY subq $24, %rsp /* Save the return values */ @@ -330,4 +335,5 @@ GLOBAL(return_to_handler) movq (%rsp), %rax addq $24, %rsp JMP_NOSPEC %rdi +END(return_to_handler) #endif diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index be86a865087a..1f9188f5357c 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -74,8 +74,50 @@ static struct orc_entry *orc_module_find(unsigned long ip) } #endif +#ifdef CONFIG_DYNAMIC_FTRACE +static struct orc_entry *orc_find(unsigned long ip); + +/* + * Ftrace dynamic trampolines do not have orc entries of their own. + * But they are copies of the ftrace entries that are static and + * defined in ftrace_*.S, which do have orc entries. + * + * If the undwinder comes across a ftrace trampoline, then find the + * ftrace function that was used to create it, and use that ftrace + * function's orc entrie, as the placement of the return code in + * the stack will be identical. + */ +static struct orc_entry *orc_ftrace_find(unsigned long ip) +{ + struct ftrace_ops *ops; + unsigned long caller; + + ops = ftrace_ops_trampoline(ip); + if (!ops) + return NULL; + + if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) + caller = (unsigned long)ftrace_regs_call; + else + caller = (unsigned long)ftrace_call; + + /* Prevent unlikely recursion */ + if (ip == caller) + return NULL; + + return orc_find(caller); +} +#else +static struct orc_entry *orc_ftrace_find(unsigned long ip) +{ + return NULL; +} +#endif + static struct orc_entry *orc_find(unsigned long ip) { + static struct orc_entry *orc; + if (!orc_init) return NULL; @@ -111,7 +153,11 @@ static struct orc_entry *orc_find(unsigned long ip) __stop_orc_unwind_ip - __start_orc_unwind_ip, ip); /* Module lookup: */ - return orc_module_find(ip); + orc = orc_module_find(ip); + if (orc) + return orc; + + return orc_ftrace_find(ip); } static void orc_sort_swap(void *_a, void *_b, int size) diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index f6a26e3cb476..54ef19e90705 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -662,11 +662,11 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2033, quirk_no_aersid); */ static void pci_amd_enable_64bit_bar(struct pci_dev *dev) { + static const char *name = "PCI Bus 0000:00"; + struct resource *res, *conflict; u32 base, limit, high; struct pci_dev *other; - struct resource *res; unsigned i; - int r; if (!(pci_probe & PCI_BIG_ROOT_WINDOW)) return; @@ -707,21 +707,26 @@ static void pci_amd_enable_64bit_bar(struct pci_dev *dev) * Allocate a 256GB window directly below the 0xfd00000000 hardware * limit (see AMD Family 15h Models 30h-3Fh BKDG, sec 2.4.6). */ - res->name = "PCI Bus 0000:00"; + res->name = name; res->flags = IORESOURCE_PREFETCH | IORESOURCE_MEM | IORESOURCE_MEM_64 | IORESOURCE_WINDOW; res->start = 0xbd00000000ull; res->end = 0xfd00000000ull - 1; - r = request_resource(&iomem_resource, res); - if (r) { + conflict = request_resource_conflict(&iomem_resource, res); + if (conflict) { kfree(res); - return; - } + if (conflict->name != name) + return; - dev_info(&dev->dev, "adding root bus resource %pR (tainting kernel)\n", - res); - add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK); + /* We are resuming from suspend; just reenable the window */ + res = conflict; + } else { + dev_info(&dev->dev, "adding root bus resource %pR (tainting kernel)\n", + res); + add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK); + pci_bus_add_resource(dev->bus, res, 0); + } base = ((res->start >> 8) & AMD_141b_MMIO_BASE_MMIOBASE_MASK) | AMD_141b_MMIO_BASE_RE_MASK | AMD_141b_MMIO_BASE_WE_MASK; @@ -733,13 +738,16 @@ static void pci_amd_enable_64bit_bar(struct pci_dev *dev) pci_write_config_dword(dev, AMD_141b_MMIO_HIGH(i), high); pci_write_config_dword(dev, AMD_141b_MMIO_LIMIT(i), limit); pci_write_config_dword(dev, AMD_141b_MMIO_BASE(i), base); - - pci_bus_add_resource(dev->bus, res, 0); } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x1401, pci_amd_enable_64bit_bar); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x141b, pci_amd_enable_64bit_bar); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x1571, pci_amd_enable_64bit_bar); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x15b1, pci_amd_enable_64bit_bar); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x1601, pci_amd_enable_64bit_bar); +DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x1401, pci_amd_enable_64bit_bar); +DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x141b, pci_amd_enable_64bit_bar); +DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x1571, pci_amd_enable_64bit_bar); +DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x15b1, pci_amd_enable_64bit_bar); +DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x1601, pci_amd_enable_64bit_bar); #endif diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c index d4a548a6a55c..a452d5a1b0f3 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c @@ -111,6 +111,9 @@ static void cxgb4_process_flow_match(struct net_device *dev, ethtype_mask = 0; } + if (ethtype_key == ETH_P_IPV6) + fs->type = 1; + fs->val.ethtype = ethtype_key; fs->mask.ethtype = ethtype_mask; fs->val.proto = key->ip_proto; @@ -205,8 +208,8 @@ static void cxgb4_process_flow_match(struct net_device *dev, VLAN_PRIO_SHIFT); vlan_tci_mask = mask->vlan_id | (mask->vlan_priority << VLAN_PRIO_SHIFT); - fs->val.ivlan = cpu_to_be16(vlan_tci); - fs->mask.ivlan = cpu_to_be16(vlan_tci_mask); + fs->val.ivlan = vlan_tci; + fs->mask.ivlan = vlan_tci_mask; /* Chelsio adapters use ivlan_vld bit to match vlan packets * as 802.1Q. Also, when vlan tag is present in packets, diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index c6e859a27ee6..e180657a02ef 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -4634,6 +4634,15 @@ int be_update_queues(struct be_adapter *adapter) be_schedule_worker(adapter); + /* + * The IF was destroyed and re-created. We need to clear + * all promiscuous flags valid for the destroyed IF. + * Without this promisc mode is not restored during + * be_open() because the driver thinks that it is + * already enabled in HW. + */ + adapter->if_flags &= ~BE_IF_FLAGS_ALL_PROMISCUOUS; + if (netif_running(netdev)) status = be_open(netdev); diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c index 7feff2450ed6..241db3199b88 100644 --- a/drivers/net/ethernet/ibm/emac/core.c +++ b/drivers/net/ethernet/ibm/emac/core.c @@ -494,6 +494,9 @@ static u32 __emac_calc_base_mr1(struct emac_instance *dev, int tx_size, int rx_s case 16384: ret |= EMAC_MR1_RFS_16K; break; + case 8192: + ret |= EMAC4_MR1_RFS_8K; + break; case 4096: ret |= EMAC_MR1_RFS_4K; break; @@ -516,6 +519,9 @@ static u32 __emac4_calc_base_mr1(struct emac_instance *dev, int tx_size, int rx_ case 16384: ret |= EMAC4_MR1_TFS_16K; break; + case 8192: + ret |= EMAC4_MR1_TFS_8K; + break; case 4096: ret |= EMAC4_MR1_TFS_4K; break; diff --git a/drivers/net/ethernet/ibm/emac/emac.h b/drivers/net/ethernet/ibm/emac/emac.h index 5afcc27ceebb..c26d2631ca30 100644 --- a/drivers/net/ethernet/ibm/emac/emac.h +++ b/drivers/net/ethernet/ibm/emac/emac.h @@ -151,9 +151,11 @@ struct emac_regs { #define EMAC4_MR1_RFS_2K 0x00100000 #define EMAC4_MR1_RFS_4K 0x00180000 +#define EMAC4_MR1_RFS_8K 0x00200000 #define EMAC4_MR1_RFS_16K 0x00280000 #define EMAC4_MR1_TFS_2K 0x00020000 #define EMAC4_MR1_TFS_4K 0x00030000 +#define EMAC4_MR1_TFS_8K 0x00040000 #define EMAC4_MR1_TFS_16K 0x00050000 #define EMAC4_MR1_TR 0x00008000 #define EMAC4_MR1_MWSW_001 0x00001000 @@ -242,7 +244,7 @@ struct emac_regs { #define EMAC_STACR_PHYE 0x00004000 #define EMAC_STACR_STAC_MASK 0x00003000 #define EMAC_STACR_STAC_READ 0x00001000 -#define EMAC_STACR_STAC_WRITE 0x00002000 +#define EMAC_STACR_STAC_WRITE 0x00000800 #define EMAC_STACR_OPBC_MASK 0x00000C00 #define EMAC_STACR_OPBC_50 0x00000000 #define EMAC_STACR_OPBC_66 0x00000400 diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index ab2e1917cd04..b65f5f3ac034 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -410,6 +410,10 @@ static int reset_rx_pools(struct ibmvnic_adapter *adapter) struct ibmvnic_rx_pool *rx_pool; int rx_scrqs; int i, j, rc; + u64 *size_array; + + size_array = (u64 *)((u8 *)(adapter->login_rsp_buf) + + be32_to_cpu(adapter->login_rsp_buf->off_rxadd_buff_size)); rx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs); for (i = 0; i < rx_scrqs; i++) { @@ -417,7 +421,17 @@ static int reset_rx_pools(struct ibmvnic_adapter *adapter) netdev_dbg(adapter->netdev, "Re-setting rx_pool[%d]\n", i); - rc = reset_long_term_buff(adapter, &rx_pool->long_term_buff); + if (rx_pool->buff_size != be64_to_cpu(size_array[i])) { + free_long_term_buff(adapter, &rx_pool->long_term_buff); + rx_pool->buff_size = be64_to_cpu(size_array[i]); + alloc_long_term_buff(adapter, &rx_pool->long_term_buff, + rx_pool->size * + rx_pool->buff_size); + } else { + rc = reset_long_term_buff(adapter, + &rx_pool->long_term_buff); + } + if (rc) return rc; @@ -439,14 +453,12 @@ static int reset_rx_pools(struct ibmvnic_adapter *adapter) static void release_rx_pools(struct ibmvnic_adapter *adapter) { struct ibmvnic_rx_pool *rx_pool; - int rx_scrqs; int i, j; if (!adapter->rx_pool) return; - rx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs); - for (i = 0; i < rx_scrqs; i++) { + for (i = 0; i < adapter->num_active_rx_pools; i++) { rx_pool = &adapter->rx_pool[i]; netdev_dbg(adapter->netdev, "Releasing rx_pool[%d]\n", i); @@ -469,6 +481,7 @@ static void release_rx_pools(struct ibmvnic_adapter *adapter) kfree(adapter->rx_pool); adapter->rx_pool = NULL; + adapter->num_active_rx_pools = 0; } static int init_rx_pools(struct net_device *netdev) @@ -493,6 +506,8 @@ static int init_rx_pools(struct net_device *netdev) return -1; } + adapter->num_active_rx_pools = 0; + for (i = 0; i < rxadd_subcrqs; i++) { rx_pool = &adapter->rx_pool[i]; @@ -536,6 +551,8 @@ static int init_rx_pools(struct net_device *netdev) rx_pool->next_free = 0; } + adapter->num_active_rx_pools = rxadd_subcrqs; + return 0; } @@ -586,13 +603,12 @@ static void release_vpd_data(struct ibmvnic_adapter *adapter) static void release_tx_pools(struct ibmvnic_adapter *adapter) { struct ibmvnic_tx_pool *tx_pool; - int i, tx_scrqs; + int i; if (!adapter->tx_pool) return; - tx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs); - for (i = 0; i < tx_scrqs; i++) { + for (i = 0; i < adapter->num_active_tx_pools; i++) { netdev_dbg(adapter->netdev, "Releasing tx_pool[%d]\n", i); tx_pool = &adapter->tx_pool[i]; kfree(tx_pool->tx_buff); @@ -603,6 +619,7 @@ static void release_tx_pools(struct ibmvnic_adapter *adapter) kfree(adapter->tx_pool); adapter->tx_pool = NULL; + adapter->num_active_tx_pools = 0; } static int init_tx_pools(struct net_device *netdev) @@ -619,6 +636,8 @@ static int init_tx_pools(struct net_device *netdev) if (!adapter->tx_pool) return -1; + adapter->num_active_tx_pools = 0; + for (i = 0; i < tx_subcrqs; i++) { tx_pool = &adapter->tx_pool[i]; @@ -666,6 +685,8 @@ static int init_tx_pools(struct net_device *netdev) tx_pool->producer_index = 0; } + adapter->num_active_tx_pools = tx_subcrqs; + return 0; } @@ -860,7 +881,7 @@ static int ibmvnic_get_vpd(struct ibmvnic_adapter *adapter) if (adapter->vpd->buff) len = adapter->vpd->len; - reinit_completion(&adapter->fw_done); + init_completion(&adapter->fw_done); crq.get_vpd_size.first = IBMVNIC_CRQ_CMD; crq.get_vpd_size.cmd = GET_VPD_SIZE; ibmvnic_send_crq(adapter, &crq); @@ -922,6 +943,13 @@ static int init_resources(struct ibmvnic_adapter *adapter) if (!adapter->vpd) return -ENOMEM; + /* Vital Product Data (VPD) */ + rc = ibmvnic_get_vpd(adapter); + if (rc) { + netdev_err(netdev, "failed to initialize Vital Product Data (VPD)\n"); + return rc; + } + adapter->map_id = 1; adapter->napi = kcalloc(adapter->req_rx_queues, sizeof(struct napi_struct), GFP_KERNEL); @@ -995,7 +1023,7 @@ static int __ibmvnic_open(struct net_device *netdev) static int ibmvnic_open(struct net_device *netdev) { struct ibmvnic_adapter *adapter = netdev_priv(netdev); - int rc, vpd; + int rc; mutex_lock(&adapter->reset_lock); @@ -1018,11 +1046,6 @@ static int ibmvnic_open(struct net_device *netdev) rc = __ibmvnic_open(netdev); netif_carrier_on(netdev); - /* Vital Product Data (VPD) */ - vpd = ibmvnic_get_vpd(adapter); - if (vpd) - netdev_err(netdev, "failed to initialize Vital Product Data (VPD)\n"); - mutex_unlock(&adapter->reset_lock); return rc; @@ -1548,6 +1571,7 @@ static int ibmvnic_set_mac(struct net_device *netdev, void *p) static int do_reset(struct ibmvnic_adapter *adapter, struct ibmvnic_rwi *rwi, u32 reset_state) { + u64 old_num_rx_queues, old_num_tx_queues; struct net_device *netdev = adapter->netdev; int i, rc; @@ -1557,6 +1581,9 @@ static int do_reset(struct ibmvnic_adapter *adapter, netif_carrier_off(netdev); adapter->reset_reason = rwi->reset_reason; + old_num_rx_queues = adapter->req_rx_queues; + old_num_tx_queues = adapter->req_tx_queues; + if (rwi->reset_reason == VNIC_RESET_MOBILITY) { rc = ibmvnic_reenable_crq_queue(adapter); if (rc) @@ -1601,6 +1628,12 @@ static int do_reset(struct ibmvnic_adapter *adapter, rc = init_resources(adapter); if (rc) return rc; + } else if (adapter->req_rx_queues != old_num_rx_queues || + adapter->req_tx_queues != old_num_tx_queues) { + release_rx_pools(adapter); + release_tx_pools(adapter); + init_rx_pools(netdev); + init_tx_pools(netdev); } else { rc = reset_tx_pools(adapter); if (rc) @@ -3592,7 +3625,17 @@ static void handle_request_cap_rsp(union ibmvnic_crq *crq, *req_value, (long int)be64_to_cpu(crq->request_capability_rsp. number), name); - *req_value = be64_to_cpu(crq->request_capability_rsp.number); + + if (be16_to_cpu(crq->request_capability_rsp.capability) == + REQ_MTU) { + pr_err("mtu of %llu is not supported. Reverting.\n", + *req_value); + *req_value = adapter->fallback.mtu; + } else { + *req_value = + be64_to_cpu(crq->request_capability_rsp.number); + } + ibmvnic_send_req_caps(adapter, 1); return; default: diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h index 4487f1e2c266..3aec42118db2 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.h +++ b/drivers/net/ethernet/ibm/ibmvnic.h @@ -1091,6 +1091,8 @@ struct ibmvnic_adapter { u64 opt_rxba_entries_per_subcrq; __be64 tx_rx_desc_req; u8 map_id; + u64 num_active_rx_pools; + u64 num_active_tx_pools; struct tasklet_struct tasklet; enum vnic_state state; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 42dcaefc4c19..af792112a2d3 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -7505,6 +7505,8 @@ static int i40e_setup_tc_cls_flower(struct i40e_netdev_priv *np, { struct i40e_vsi *vsi = np->vsi; + if (!tc_can_offload(vsi->netdev)) + return -EOPNOTSUPP; if (cls_flower->common.chain_index) return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c index e401d9d245f3..b69a705fd787 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c @@ -201,9 +201,15 @@ static int mlx5e_am_stats_compare(struct mlx5e_rx_am_stats *curr, return (curr->bpms > prev->bpms) ? MLX5E_AM_STATS_BETTER : MLX5E_AM_STATS_WORSE; + if (!prev->ppms) + return curr->ppms ? MLX5E_AM_STATS_BETTER : + MLX5E_AM_STATS_SAME; + if (IS_SIGNIFICANT_DIFF(curr->ppms, prev->ppms)) return (curr->ppms > prev->ppms) ? MLX5E_AM_STATS_BETTER : MLX5E_AM_STATS_WORSE; + if (!prev->epms) + return MLX5E_AM_STATS_SAME; if (IS_SIGNIFICANT_DIFF(curr->epms, prev->epms)) return (curr->epms < prev->epms) ? MLX5E_AM_STATS_BETTER : diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 6c0391c13fe0..7042c855a5d6 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -1942,11 +1942,8 @@ static void mlxsw_sp_router_neigh_ent_ipv4_process(struct mlxsw_sp *mlxsw_sp, dipn = htonl(dip); dev = mlxsw_sp->router->rifs[rif]->dev; n = neigh_lookup(&arp_tbl, &dipn, dev); - if (!n) { - netdev_err(dev, "Failed to find matching neighbour for IP=%pI4h\n", - &dip); + if (!n) return; - } netdev_dbg(dev, "Updating neighbour with IP=%pI4h\n", &dip); neigh_event_send(n, NULL); @@ -1973,11 +1970,8 @@ static void mlxsw_sp_router_neigh_ent_ipv6_process(struct mlxsw_sp *mlxsw_sp, dev = mlxsw_sp->router->rifs[rif]->dev; n = neigh_lookup(&nd_tbl, &dip, dev); - if (!n) { - netdev_err(dev, "Failed to find matching neighbour for IP=%pI6c\n", - &dip); + if (!n) return; - } netdev_dbg(dev, "Updating neighbour with IP=%pI6c\n", &dip); neigh_event_send(n, NULL); diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c index c8c4b3940564..b7abb8205d3a 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c +++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c @@ -358,10 +358,27 @@ static void qed_rdma_resc_free(struct qed_hwfn *p_hwfn) kfree(p_rdma_info); } +static void qed_rdma_free_tid(void *rdma_cxt, u32 itid) +{ + struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt; + + DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "itid = %08x\n", itid); + + spin_lock_bh(&p_hwfn->p_rdma_info->lock); + qed_bmap_release_id(p_hwfn, &p_hwfn->p_rdma_info->tid_map, itid); + spin_unlock_bh(&p_hwfn->p_rdma_info->lock); +} + +static void qed_rdma_free_reserved_lkey(struct qed_hwfn *p_hwfn) +{ + qed_rdma_free_tid(p_hwfn, p_hwfn->p_rdma_info->dev->reserved_lkey); +} + static void qed_rdma_free(struct qed_hwfn *p_hwfn) { DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "Freeing RDMA\n"); + qed_rdma_free_reserved_lkey(p_hwfn); qed_rdma_resc_free(p_hwfn); } @@ -615,9 +632,6 @@ static int qed_rdma_reserve_lkey(struct qed_hwfn *p_hwfn) { struct qed_rdma_device *dev = p_hwfn->p_rdma_info->dev; - /* The first DPI is reserved for the Kernel */ - __set_bit(0, p_hwfn->p_rdma_info->dpi_map.bitmap); - /* Tid 0 will be used as the key for "reserved MR". * The driver should allocate memory for it so it can be loaded but no * ramrod should be passed on it. @@ -797,17 +811,6 @@ static struct qed_rdma_device *qed_rdma_query_device(void *rdma_cxt) return p_hwfn->p_rdma_info->dev; } -static void qed_rdma_free_tid(void *rdma_cxt, u32 itid) -{ - struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt; - - DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "itid = %08x\n", itid); - - spin_lock_bh(&p_hwfn->p_rdma_info->lock); - qed_bmap_release_id(p_hwfn, &p_hwfn->p_rdma_info->tid_map, itid); - spin_unlock_bh(&p_hwfn->p_rdma_info->lock); -} - static void qed_rdma_cnq_prod_update(void *rdma_cxt, u8 qz_offset, u16 prod) { struct qed_hwfn *p_hwfn; diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c index 4e1da1645b15..5aa59f41bf8c 100644 --- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -842,6 +842,7 @@ static int pppoe_sendmsg(struct socket *sock, struct msghdr *m, struct pppoe_hdr *ph; struct net_device *dev; char *start; + int hlen; lock_sock(sk); if (sock_flag(sk, SOCK_DEAD) || !(sk->sk_state & PPPOX_CONNECTED)) { @@ -860,16 +861,16 @@ static int pppoe_sendmsg(struct socket *sock, struct msghdr *m, if (total_len > (dev->mtu + dev->hard_header_len)) goto end; - - skb = sock_wmalloc(sk, total_len + dev->hard_header_len + 32, - 0, GFP_KERNEL); + hlen = LL_RESERVED_SPACE(dev); + skb = sock_wmalloc(sk, hlen + sizeof(*ph) + total_len + + dev->needed_tailroom, 0, GFP_KERNEL); if (!skb) { error = -ENOMEM; goto end; } /* Reserve space for headers. */ - skb_reserve(skb, dev->hard_header_len); + skb_reserve(skb, hlen); skb_reset_network_header(skb); skb->dev = dev; @@ -930,7 +931,7 @@ static int __pppoe_xmit(struct sock *sk, struct sk_buff *skb) /* Copy the data if there is no space for the header or if it's * read-only. */ - if (skb_cow_head(skb, sizeof(*ph) + dev->hard_header_len)) + if (skb_cow_head(skb, LL_RESERVED_SPACE(dev) + sizeof(*ph))) goto abort; __skb_push(skb, sizeof(*ph)); diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index d56fe32bf48d..8a22ff67b026 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -457,12 +457,10 @@ static enum skb_state defer_bh(struct usbnet *dev, struct sk_buff *skb, void usbnet_defer_kevent (struct usbnet *dev, int work) { set_bit (work, &dev->flags); - if (!schedule_work (&dev->kevent)) { - if (net_ratelimit()) - netdev_err(dev->net, "kevent %d may have been dropped\n", work); - } else { + if (!schedule_work (&dev->kevent)) + netdev_dbg(dev->net, "kevent %d may have been dropped\n", work); + else netdev_dbg(dev->net, "kevent %d scheduled\n", work); - } } EXPORT_SYMBOL_GPL(usbnet_defer_kevent); diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index d1c7029ded7c..cf95290b160c 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -1616,7 +1616,6 @@ static void vmxnet3_rq_destroy(struct vmxnet3_rx_queue *rq, rq->rx_ring[i].basePA); rq->rx_ring[i].base = NULL; } - rq->buf_info[i] = NULL; } if (rq->data_ring.base) { @@ -1638,6 +1637,7 @@ static void vmxnet3_rq_destroy(struct vmxnet3_rx_queue *rq, (rq->rx_ring[0].size + rq->rx_ring[1].size); dma_free_coherent(&adapter->pdev->dev, sz, rq->buf_info[0], rq->buf_info_pa); + rq->buf_info[0] = rq->buf_info[1] = NULL; } } diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 33ac2b186b85..5727b186b3ca 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -904,7 +904,7 @@ static void vhost_dev_lock_vqs(struct vhost_dev *d) { int i = 0; for (i = 0; i < d->nvqs; ++i) - mutex_lock(&d->vqs[i]->mutex); + mutex_lock_nested(&d->vqs[i]->mutex, i); } static void vhost_dev_unlock_vqs(struct vhost_dev *d) @@ -1015,6 +1015,10 @@ static int vhost_process_iotlb_msg(struct vhost_dev *dev, vhost_iotlb_notify_vq(dev, msg); break; case VHOST_IOTLB_INVALIDATE: + if (!dev->iotlb) { + ret = -EFAULT; + break; + } vhost_vq_meta_reset(dev); vhost_del_umem_range(dev->iotlb, msg->iova, msg->iova + msg->size - 1); diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 056276101c63..a6226cd6063c 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1633,28 +1633,18 @@ void btrfs_readdir_put_delayed_items(struct inode *inode, int btrfs_should_delete_dir_index(struct list_head *del_list, u64 index) { - struct btrfs_delayed_item *curr, *next; - int ret; - - if (list_empty(del_list)) - return 0; + struct btrfs_delayed_item *curr; + int ret = 0; - list_for_each_entry_safe(curr, next, del_list, readdir_list) { + list_for_each_entry(curr, del_list, readdir_list) { if (curr->key.offset > index) break; - - list_del(&curr->readdir_list); - ret = (curr->key.offset == index); - - if (refcount_dec_and_test(&curr->refs)) - kfree(curr); - - if (ret) - return 1; - else - continue; + if (curr->key.offset == index) { + ret = 1; + break; + } } - return 0; + return ret; } /* diff --git a/fs/nfsd/auth.c b/fs/nfsd/auth.c index f650e475d8f0..fdf2aad73470 100644 --- a/fs/nfsd/auth.c +++ b/fs/nfsd/auth.c @@ -60,10 +60,10 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp) gi->gid[i] = exp->ex_anon_gid; else gi->gid[i] = rqgi->gid[i]; - - /* Each thread allocates its own gi, no race */ - groups_sort(gi); } + + /* Each thread allocates its own gi, no race */ + groups_sort(gi); } else { gi = get_group_info(rqgi); } diff --git a/fs/orangefs/devorangefs-req.c b/fs/orangefs/devorangefs-req.c index ded456f17de6..c584ad8d023c 100644 --- a/fs/orangefs/devorangefs-req.c +++ b/fs/orangefs/devorangefs-req.c @@ -162,7 +162,7 @@ static ssize_t orangefs_devreq_read(struct file *file, struct orangefs_kernel_op_s *op, *temp; __s32 proto_ver = ORANGEFS_KERNEL_PROTO_VERSION; static __s32 magic = ORANGEFS_DEVREQ_MAGIC; - struct orangefs_kernel_op_s *cur_op = NULL; + struct orangefs_kernel_op_s *cur_op; unsigned long ret; /* We do not support blocking IO. */ @@ -186,6 +186,7 @@ static ssize_t orangefs_devreq_read(struct file *file, return -EAGAIN; restart: + cur_op = NULL; /* Get next op (if any) from top of list. */ spin_lock(&orangefs_request_list_lock); list_for_each_entry_safe(op, temp, &orangefs_request_list, list) { diff --git a/fs/orangefs/waitqueue.c b/fs/orangefs/waitqueue.c index 835c6e148afc..0577d6dba8c8 100644 --- a/fs/orangefs/waitqueue.c +++ b/fs/orangefs/waitqueue.c @@ -29,10 +29,10 @@ static void orangefs_clean_up_interrupted_operation(struct orangefs_kernel_op_s */ void purge_waiting_ops(void) { - struct orangefs_kernel_op_s *op; + struct orangefs_kernel_op_s *op, *tmp; spin_lock(&orangefs_request_list_lock); - list_for_each_entry(op, &orangefs_request_list, list) { + list_for_each_entry_safe(op, tmp, &orangefs_request_list, list) { gossip_debug(GOSSIP_WAIT_DEBUG, "pvfs2-client-core: purging op tag %llu %s\n", llu(op->tag), diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 2bab81951ced..3319df9727aa 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -332,6 +332,8 @@ extern int ftrace_text_reserved(const void *start, const void *end); extern int ftrace_nr_registered_ops(void); +struct ftrace_ops *ftrace_ops_trampoline(unsigned long addr); + bool is_ftrace_trampoline(unsigned long addr); /* diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 9c5a2628d6ce..1d3877c39a00 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -124,6 +124,11 @@ static inline bool is_write_device_private_entry(swp_entry_t entry) return unlikely(swp_type(entry) == SWP_DEVICE_WRITE); } +static inline unsigned long device_private_entry_to_pfn(swp_entry_t entry) +{ + return swp_offset(entry); +} + static inline struct page *device_private_entry_to_page(swp_entry_t entry) { return pfn_to_page(swp_offset(entry)); @@ -154,6 +159,11 @@ static inline bool is_write_device_private_entry(swp_entry_t entry) return false; } +static inline unsigned long device_private_entry_to_pfn(swp_entry_t entry) +{ + return 0; +} + static inline struct page *device_private_entry_to_page(swp_entry_t entry) { return NULL; @@ -189,6 +199,11 @@ static inline int is_write_migration_entry(swp_entry_t entry) return unlikely(swp_type(entry) == SWP_MIGRATION_WRITE); } +static inline unsigned long migration_entry_to_pfn(swp_entry_t entry) +{ + return swp_offset(entry); +} + static inline struct page *migration_entry_to_page(swp_entry_t entry) { struct page *p = pfn_to_page(swp_offset(entry)); @@ -218,6 +233,12 @@ static inline int is_migration_entry(swp_entry_t swp) { return 0; } + +static inline unsigned long migration_entry_to_pfn(swp_entry_t entry) +{ + return 0; +} + static inline struct page *migration_entry_to_page(swp_entry_t entry) { return NULL; diff --git a/include/linux/vermagic.h b/include/linux/vermagic.h index 853291714ae0..bae807eb2933 100644 --- a/include/linux/vermagic.h +++ b/include/linux/vermagic.h @@ -31,17 +31,11 @@ #else #define MODULE_RANDSTRUCT_PLUGIN #endif -#ifdef RETPOLINE -#define MODULE_VERMAGIC_RETPOLINE "retpoline " -#else -#define MODULE_VERMAGIC_RETPOLINE "" -#endif #define VERMAGIC_STRING \ UTS_RELEASE " " \ MODULE_VERMAGIC_SMP MODULE_VERMAGIC_PREEMPT \ MODULE_VERMAGIC_MODULE_UNLOAD MODULE_VERMAGIC_MODVERSIONS \ MODULE_ARCH_VERMAGIC \ - MODULE_RANDSTRUCT_PLUGIN \ - MODULE_VERMAGIC_RETPOLINE + MODULE_RANDSTRUCT_PLUGIN diff --git a/include/net/ipv6.h b/include/net/ipv6.h index f73797e2fa60..221238254eb7 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -331,6 +331,7 @@ int ipv6_flowlabel_opt_get(struct sock *sk, struct in6_flowlabel_req *freq, int flags); int ip6_flowlabel_init(void); void ip6_flowlabel_cleanup(void); +bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np); static inline void fl6_sock_release(struct ip6_flowlabel *fl) { diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 8e08b6da72f3..753ac9361154 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -522,7 +522,7 @@ static inline unsigned char * tcf_get_base_ptr(struct sk_buff *skb, int layer) { switch (layer) { case TCF_LAYER_LINK: - return skb->data; + return skb_mac_header(skb); case TCF_LAYER_NETWORK: return skb_network_header(skb); case TCF_LAYER_TRANSPORT: diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index ccdf3664e4a9..554b517c61a0 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1119,15 +1119,11 @@ static struct ftrace_ops global_ops = { }; /* - * This is used by __kernel_text_address() to return true if the - * address is on a dynamically allocated trampoline that would - * not return true for either core_kernel_text() or - * is_module_text_address(). + * Used by the stack undwinder to know about dynamic ftrace trampolines. */ -bool is_ftrace_trampoline(unsigned long addr) +struct ftrace_ops *ftrace_ops_trampoline(unsigned long addr) { - struct ftrace_ops *op; - bool ret = false; + struct ftrace_ops *op = NULL; /* * Some of the ops may be dynamically allocated, @@ -1144,15 +1140,24 @@ bool is_ftrace_trampoline(unsigned long addr) if (op->trampoline && op->trampoline_size) if (addr >= op->trampoline && addr < op->trampoline + op->trampoline_size) { - ret = true; - goto out; + preempt_enable_notrace(); + return op; } } while_for_each_ftrace_op(op); - - out: preempt_enable_notrace(); - return ret; + return NULL; +} + +/* + * This is used by __kernel_text_address() to return true if the + * address is on a dynamically allocated trampoline that would + * not return true for either core_kernel_text() or + * is_module_text_address(). + */ +bool is_ftrace_trampoline(unsigned long addr) +{ + return ftrace_ops_trampoline(addr) != NULL; } struct ftrace_page { diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 2a8d8a294345..8e3f20a18a06 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2374,6 +2374,15 @@ void trace_event_buffer_commit(struct trace_event_buffer *fbuffer) } EXPORT_SYMBOL_GPL(trace_event_buffer_commit); +/* + * Skip 3: + * + * trace_buffer_unlock_commit_regs() + * trace_event_buffer_commit() + * trace_event_raw_event_xxx() +*/ +# define STACK_SKIP 3 + void trace_buffer_unlock_commit_regs(struct trace_array *tr, struct ring_buffer *buffer, struct ring_buffer_event *event, @@ -2383,16 +2392,12 @@ void trace_buffer_unlock_commit_regs(struct trace_array *tr, __buffer_unlock_commit(buffer, event); /* - * If regs is not set, then skip the following callers: - * trace_buffer_unlock_commit_regs - * event_trigger_unlock_commit - * trace_event_buffer_commit - * trace_event_raw_event_sched_switch + * If regs is not set, then skip the necessary functions. * Note, we can still get here via blktrace, wakeup tracer * and mmiotrace, but that's ok if they lose a function or - * two. They are that meaningful. + * two. They are not that meaningful. */ - ftrace_trace_stack(tr, buffer, flags, regs ? 0 : 4, pc, regs); + ftrace_trace_stack(tr, buffer, flags, regs ? 0 : STACK_SKIP, pc, regs); ftrace_trace_userstack(buffer, flags, pc); } @@ -2579,11 +2584,13 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer, trace.skip = skip; /* - * Add two, for this function and the call to save_stack_trace() + * Add one, for this function and the call to save_stack_trace() * If regs is set, then these functions will not be in the way. */ +#ifndef CONFIG_UNWINDER_ORC if (!regs) - trace.skip += 2; + trace.skip++; +#endif /* * Since events can happen in NMIs there's no safe way to @@ -2711,11 +2718,10 @@ void trace_dump_stack(int skip) local_save_flags(flags); - /* - * Skip 3 more, seems to get us at the caller of - * this function. - */ - skip += 3; +#ifndef CONFIG_UNWINDER_ORC + /* Skip 1 to skip this function. */ + skip++; +#endif __ftrace_trace_stack(global_trace.trace_buffer.buffer, flags, skip, preempt_count(), NULL); } diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index f2ac9d44f6c4..87411482a46f 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -1123,13 +1123,22 @@ static __init int register_trigger_snapshot_cmd(void) { return 0; } #endif /* CONFIG_TRACER_SNAPSHOT */ #ifdef CONFIG_STACKTRACE +#ifdef CONFIG_UNWINDER_ORC +/* Skip 2: + * event_triggers_post_call() + * trace_event_raw_event_xxx() + */ +# define STACK_SKIP 2 +#else /* - * Skip 3: + * Skip 4: * stacktrace_trigger() * event_triggers_post_call() + * trace_event_buffer_commit() * trace_event_raw_event_xxx() */ -#define STACK_SKIP 3 +#define STACK_SKIP 4 +#endif static void stacktrace_trigger(struct event_trigger_data *data, void *rec) diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index 27f7ad12c4b1..b611cd36e22d 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -154,6 +154,24 @@ function_trace_call(unsigned long ip, unsigned long parent_ip, preempt_enable_notrace(); } +#ifdef CONFIG_UNWINDER_ORC +/* + * Skip 2: + * + * function_stack_trace_call() + * ftrace_call() + */ +#define STACK_SKIP 2 +#else +/* + * Skip 3: + * __trace_stack() + * function_stack_trace_call() + * ftrace_call() + */ +#define STACK_SKIP 3 +#endif + static void function_stack_trace_call(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct pt_regs *pt_regs) @@ -180,15 +198,7 @@ function_stack_trace_call(unsigned long ip, unsigned long parent_ip, if (likely(disabled == 1)) { pc = preempt_count(); trace_function(tr, ip, parent_ip, flags, pc); - /* - * skip over 5 funcs: - * __ftrace_trace_stack, - * __trace_stack, - * function_stack_trace_call - * ftrace_list_func - * ftrace_call - */ - __trace_stack(tr, flags, 5, pc); + __trace_stack(tr, flags, STACK_SKIP, pc); } atomic_dec(&data->disabled); @@ -367,14 +377,27 @@ ftrace_traceoff(unsigned long ip, unsigned long parent_ip, tracer_tracing_off(tr); } +#ifdef CONFIG_UNWINDER_ORC /* - * Skip 4: + * Skip 3: + * + * function_trace_probe_call() + * ftrace_ops_assist_func() + * ftrace_call() + */ +#define FTRACE_STACK_SKIP 3 +#else +/* + * Skip 5: + * + * __trace_stack() * ftrace_stacktrace() * function_trace_probe_call() - * ftrace_ops_list_func() + * ftrace_ops_assist_func() * ftrace_call() */ -#define STACK_SKIP 4 +#define FTRACE_STACK_SKIP 5 +#endif static __always_inline void trace_stack(struct trace_array *tr) { @@ -384,7 +407,7 @@ static __always_inline void trace_stack(struct trace_array *tr) local_save_flags(flags); pc = preempt_count(); - __trace_stack(tr, flags, STACK_SKIP, pc); + __trace_stack(tr, flags, FTRACE_STACK_SKIP, pc); } static void diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index d22b84310f6d..ae3c2a35d61b 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -30,10 +30,37 @@ static bool map_pte(struct page_vma_mapped_walk *pvmw) return true; } +static inline bool pfn_in_hpage(struct page *hpage, unsigned long pfn) +{ + unsigned long hpage_pfn = page_to_pfn(hpage); + + /* THP can be referenced by any subpage */ + return pfn >= hpage_pfn && pfn - hpage_pfn < hpage_nr_pages(hpage); +} + +/** + * check_pte - check if @pvmw->page is mapped at the @pvmw->pte + * + * page_vma_mapped_walk() found a place where @pvmw->page is *potentially* + * mapped. check_pte() has to validate this. + * + * @pvmw->pte may point to empty PTE, swap PTE or PTE pointing to arbitrary + * page. + * + * If PVMW_MIGRATION flag is set, returns true if @pvmw->pte contains migration + * entry that points to @pvmw->page or any subpage in case of THP. + * + * If PVMW_MIGRATION flag is not set, returns true if @pvmw->pte points to + * @pvmw->page or any subpage in case of THP. + * + * Otherwise, return false. + * + */ static bool check_pte(struct page_vma_mapped_walk *pvmw) { + unsigned long pfn; + if (pvmw->flags & PVMW_MIGRATION) { -#ifdef CONFIG_MIGRATION swp_entry_t entry; if (!is_swap_pte(*pvmw->pte)) return false; @@ -41,38 +68,25 @@ static bool check_pte(struct page_vma_mapped_walk *pvmw) if (!is_migration_entry(entry)) return false; - if (migration_entry_to_page(entry) - pvmw->page >= - hpage_nr_pages(pvmw->page)) { - return false; - } - if (migration_entry_to_page(entry) < pvmw->page) - return false; -#else - WARN_ON_ONCE(1); -#endif - } else { - if (is_swap_pte(*pvmw->pte)) { - swp_entry_t entry; - entry = pte_to_swp_entry(*pvmw->pte); - if (is_device_private_entry(entry) && - device_private_entry_to_page(entry) == pvmw->page) - return true; - } + pfn = migration_entry_to_pfn(entry); + } else if (is_swap_pte(*pvmw->pte)) { + swp_entry_t entry; - if (!pte_present(*pvmw->pte)) + /* Handle un-addressable ZONE_DEVICE memory */ + entry = pte_to_swp_entry(*pvmw->pte); + if (!is_device_private_entry(entry)) return false; - /* THP can be referenced by any subpage */ - if (pte_page(*pvmw->pte) - pvmw->page >= - hpage_nr_pages(pvmw->page)) { - return false; - } - if (pte_page(*pvmw->pte) < pvmw->page) + pfn = device_private_entry_to_pfn(entry); + } else { + if (!pte_present(*pvmw->pte)) return false; + + pfn = pte_pfn(*pvmw->pte); } - return true; + return pfn_in_hpage(pvmw->page, pfn); } /** diff --git a/net/core/dev.c b/net/core/dev.c index 0e0ba36eeac9..613fb4066be7 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3151,10 +3151,21 @@ static void qdisc_pkt_len_init(struct sk_buff *skb) hdr_len = skb_transport_header(skb) - skb_mac_header(skb); /* + transport layer */ - if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) - hdr_len += tcp_hdrlen(skb); - else - hdr_len += sizeof(struct udphdr); + if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) { + const struct tcphdr *th; + struct tcphdr _tcphdr; + + th = skb_header_pointer(skb, skb_transport_offset(skb), + sizeof(_tcphdr), &_tcphdr); + if (likely(th)) + hdr_len += __tcp_hdrlen(th); + } else { + struct udphdr _udphdr; + + if (skb_header_pointer(skb, skb_transport_offset(skb), + sizeof(_udphdr), &_udphdr)) + hdr_len += sizeof(struct udphdr); + } if (shinfo->gso_type & SKB_GSO_DODGY) gso_segs = DIV_ROUND_UP(skb->len - hdr_len, diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index b1338e576d00..29b333a62ab0 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -122,6 +122,9 @@ static struct sk_buff *esp4_gso_segment(struct sk_buff *skb, if (!xo) goto out; + if (!(skb_shinfo(skb)->gso_type & SKB_GSO_ESP)) + goto out; + seq = xo->seq.low; x = skb->sp->xvec[skb->sp->len - 1]; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 726f6b608274..2d49717a7421 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -332,7 +332,7 @@ static __be32 igmpv3_get_srcaddr(struct net_device *dev, return htonl(INADDR_ANY); for_ifa(in_dev) { - if (inet_ifa_match(fl4->saddr, ifa)) + if (fl4->saddr == ifa->ifa_local) return fl4->saddr; } endfor_ifa(in_dev); diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index b6a2aa1dcf56..4d58e2ce0b5b 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -32,6 +32,9 @@ static void tcp_gso_tstamp(struct sk_buff *skb, unsigned int ts_seq, static struct sk_buff *tcp4_gso_segment(struct sk_buff *skb, netdev_features_t features) { + if (!(skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4)) + return ERR_PTR(-EINVAL); + if (!pskb_may_pull(skb, sizeof(struct tcphdr))) return ERR_PTR(-EINVAL); diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 01801b77bd0d..ea6e6e7df0ee 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -203,6 +203,9 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, goto out; } + if (!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP)) + goto out; + if (!pskb_may_pull(skb, sizeof(struct udphdr))) goto out; diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index e6265e2c274e..20ca486b3cad 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -92,6 +92,7 @@ static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) skb_reset_network_header(skb); skb_mac_header_rebuild(skb); + eth_hdr(skb)->h_proto = skb->protocol; err = 0; diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index dd9627490c7c..f52c314d4c97 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -149,6 +149,9 @@ static struct sk_buff *esp6_gso_segment(struct sk_buff *skb, if (!xo) goto out; + if (!(skb_shinfo(skb)->gso_type & SKB_GSO_ESP)) + goto out; + seq = xo->seq.low; x = skb->sp->xvec[skb->sp->len - 1]; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 4f7d8de56611..3763dc01e374 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -166,7 +166,7 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb) !(IP6CB(skb)->flags & IP6SKB_REROUTED)); } -static bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np) +bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np) { if (!np->autoflowlabel_set) return ip6_default_np_autolabel(net); diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 2d4680e0376f..e8ffb5b5d84e 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -1336,7 +1336,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, break; case IPV6_AUTOFLOWLABEL: - val = np->autoflowlabel; + val = ip6_autoflowlabel(sock_net(sk), np); break; case IPV6_RECVFRAGSIZE: diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c index d883c9204c01..278e49cd67d4 100644 --- a/net/ipv6/tcpv6_offload.c +++ b/net/ipv6/tcpv6_offload.c @@ -46,6 +46,9 @@ static struct sk_buff *tcp6_gso_segment(struct sk_buff *skb, { struct tcphdr *th; + if (!(skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)) + return ERR_PTR(-EINVAL); + if (!pskb_may_pull(skb, sizeof(*th))) return ERR_PTR(-EINVAL); diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index a0f89ad76f9d..2a04dc9c781b 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -42,6 +42,9 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, const struct ipv6hdr *ipv6h; struct udphdr *uh; + if (!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP)) + goto out; + if (!pskb_may_pull(skb, sizeof(struct udphdr))) goto out; diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c index 02556e356f87..dc93002ff9d1 100644 --- a/net/ipv6/xfrm6_mode_tunnel.c +++ b/net/ipv6/xfrm6_mode_tunnel.c @@ -92,6 +92,7 @@ static int xfrm6_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) skb_reset_network_header(skb); skb_mac_header_rebuild(skb); + eth_hdr(skb)->h_proto = skb->protocol; err = 0; diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index d4e98f20fc2a..4a8d407f8902 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -1387,8 +1387,13 @@ static int kcm_attach(struct socket *sock, struct socket *csock, if (!csk) return -EINVAL; - /* We must prevent loops or risk deadlock ! */ - if (csk->sk_family == PF_KCM) + /* Only allow TCP sockets to be attached for now */ + if ((csk->sk_family != AF_INET && csk->sk_family != AF_INET6) || + csk->sk_protocol != IPPROTO_TCP) + return -EOPNOTSUPP; + + /* Don't allow listeners or closed sockets */ + if (csk->sk_state == TCP_LISTEN || csk->sk_state == TCP_CLOSE) return -EOPNOTSUPP; psock = kmem_cache_zalloc(kcm_psockp, GFP_KERNEL); @@ -1405,9 +1410,18 @@ static int kcm_attach(struct socket *sock, struct socket *csock, return err; } - sock_hold(csk); - write_lock_bh(&csk->sk_callback_lock); + + /* Check if sk_user_data is aready by KCM or someone else. + * Must be done under lock to prevent race conditions. + */ + if (csk->sk_user_data) { + write_unlock_bh(&csk->sk_callback_lock); + strp_done(&psock->strp); + kmem_cache_free(kcm_psockp, psock); + return -EALREADY; + } + psock->save_data_ready = csk->sk_data_ready; psock->save_write_space = csk->sk_write_space; psock->save_state_change = csk->sk_state_change; @@ -1415,8 +1429,11 @@ static int kcm_attach(struct socket *sock, struct socket *csock, csk->sk_data_ready = psock_data_ready; csk->sk_write_space = psock_write_space; csk->sk_state_change = psock_state_change; + write_unlock_bh(&csk->sk_callback_lock); + sock_hold(csk); + /* Finished initialization, now add the psock to the MUX. */ spin_lock_bh(&mux->lock); head = &mux->psocks; diff --git a/net/rds/tcp.c b/net/rds/tcp.c index 6b7ee71f40c6..ab7356e0ba83 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -90,9 +90,10 @@ void rds_tcp_nonagle(struct socket *sock) sizeof(val)); } -u32 rds_tcp_snd_nxt(struct rds_tcp_connection *tc) +u32 rds_tcp_write_seq(struct rds_tcp_connection *tc) { - return tcp_sk(tc->t_sock->sk)->snd_nxt; + /* seq# of the last byte of data in tcp send buffer */ + return tcp_sk(tc->t_sock->sk)->write_seq; } u32 rds_tcp_snd_una(struct rds_tcp_connection *tc) diff --git a/net/rds/tcp.h b/net/rds/tcp.h index 1aafbf7c3011..864ca7d8f019 100644 --- a/net/rds/tcp.h +++ b/net/rds/tcp.h @@ -54,7 +54,7 @@ void rds_tcp_set_callbacks(struct socket *sock, struct rds_conn_path *cp); void rds_tcp_reset_callbacks(struct socket *sock, struct rds_conn_path *cp); void rds_tcp_restore_callbacks(struct socket *sock, struct rds_tcp_connection *tc); -u32 rds_tcp_snd_nxt(struct rds_tcp_connection *tc); +u32 rds_tcp_write_seq(struct rds_tcp_connection *tc); u32 rds_tcp_snd_una(struct rds_tcp_connection *tc); u64 rds_tcp_map_seq(struct rds_tcp_connection *tc, u32 seq); extern struct rds_transport rds_tcp_transport; diff --git a/net/rds/tcp_send.c b/net/rds/tcp_send.c index dc860d1bb608..9b76e0fa1722 100644 --- a/net/rds/tcp_send.c +++ b/net/rds/tcp_send.c @@ -86,7 +86,7 @@ int rds_tcp_xmit(struct rds_connection *conn, struct rds_message *rm, * m_ack_seq is set to the sequence number of the last byte of * header and data. see rds_tcp_is_acked(). */ - tc->t_last_sent_nxt = rds_tcp_snd_nxt(tc); + tc->t_last_sent_nxt = rds_tcp_write_seq(tc); rm->m_ack_seq = tc->t_last_sent_nxt + sizeof(struct rds_header) + be32_to_cpu(rm->m_inc.i_hdr.h_len) - 1; @@ -98,7 +98,7 @@ int rds_tcp_xmit(struct rds_connection *conn, struct rds_message *rm, rm->m_inc.i_hdr.h_flags |= RDS_FLAG_RETRANSMITTED; rdsdebug("rm %p tcp nxt %u ack_seq %llu\n", - rm, rds_tcp_snd_nxt(tc), + rm, rds_tcp_write_seq(tc), (unsigned long long)rm->m_ack_seq); } diff --git a/net/sched/em_nbyte.c b/net/sched/em_nbyte.c index df3110d69585..07c10bac06a0 100644 --- a/net/sched/em_nbyte.c +++ b/net/sched/em_nbyte.c @@ -51,7 +51,7 @@ static int em_nbyte_match(struct sk_buff *skb, struct tcf_ematch *em, if (!tcf_valid_offset(skb, ptr, nbyte->hdr.len)) return 0; - return !memcmp(ptr + nbyte->hdr.off, nbyte->pattern, nbyte->hdr.len); + return !memcmp(ptr, nbyte->pattern, nbyte->hdr.len); } static struct tcf_ematch_ops em_nbyte_ops = { diff --git a/net/sctp/offload.c b/net/sctp/offload.c index 275925b93b29..35bc7106d182 100644 --- a/net/sctp/offload.c +++ b/net/sctp/offload.c @@ -45,6 +45,9 @@ static struct sk_buff *sctp_gso_segment(struct sk_buff *skb, struct sk_buff *segs = ERR_PTR(-EINVAL); struct sctphdr *sh; + if (!(skb_shinfo(skb)->gso_type & SKB_GSO_SCTP)) + goto out; + sh = sctp_hdr(skb); if (!pskb_may_pull(skb, sizeof(*sh))) goto out; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 61f394d369bf..0a9b72fbd761 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -577,6 +577,8 @@ alloc_payload: get_page(page); sg = ctx->sg_plaintext_data + ctx->sg_plaintext_num_elem; sg_set_page(sg, page, copy, offset); + sg_unmark_end(sg); + ctx->sg_plaintext_num_elem++; sk_mem_charge(sk, copy); diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 30e5746085b8..ac9477189d1c 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -102,6 +102,7 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, err = dev->xfrmdev_ops->xdo_dev_state_add(x); if (err) { + xso->dev = NULL; dev_put(dev); return err; } diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 429957412633..a3785f538018 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -317,7 +317,7 @@ retry: if (!type && try_load) { request_module("xfrm-offload-%d-%d", family, proto); - try_load = 0; + try_load = false; goto retry; } @@ -2272,8 +2272,6 @@ int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload) goto error; } - x->km.state = XFRM_STATE_VALID; - error: return err; } @@ -2282,7 +2280,13 @@ EXPORT_SYMBOL(__xfrm_init_state); int xfrm_init_state(struct xfrm_state *x) { - return __xfrm_init_state(x, true, false); + int err; + + err = __xfrm_init_state(x, true, false); + if (!err) + x->km.state = XFRM_STATE_VALID; + + return err; } EXPORT_SYMBOL(xfrm_init_state); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index bdb48e5dba04..7f52b8eb177d 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -598,13 +598,6 @@ static struct xfrm_state *xfrm_state_construct(struct net *net, goto error; } - if (attrs[XFRMA_OFFLOAD_DEV]) { - err = xfrm_dev_state_add(net, x, - nla_data(attrs[XFRMA_OFFLOAD_DEV])); - if (err) - goto error; - } - if ((err = xfrm_alloc_replay_state_esn(&x->replay_esn, &x->preplay_esn, attrs[XFRMA_REPLAY_ESN_VAL]))) goto error; @@ -620,6 +613,14 @@ static struct xfrm_state *xfrm_state_construct(struct net *net, /* override default values from above */ xfrm_update_ae_params(x, attrs, 0); + /* configure the hardware if offload is requested */ + if (attrs[XFRMA_OFFLOAD_DEV]) { + err = xfrm_dev_state_add(net, x, + nla_data(attrs[XFRMA_OFFLOAD_DEV])); + if (err) + goto error; + } + return x; error: @@ -662,6 +663,9 @@ static int xfrm_add_sa(struct sk_buff *skb, struct nlmsghdr *nlh, goto out; } + if (x->km.state == XFRM_STATE_VOID) + x->km.state = XFRM_STATE_VALID; + c.seq = nlh->nlmsg_seq; c.portid = nlh->nlmsg_pid; c.event = nlh->nlmsg_type; |