diff --git a/Documentation/networking/netdevices.rst b/Documentation/networking/netdevices.rst index 5a85fcc80c765..557b974834371 100644 --- a/Documentation/networking/netdevices.rst +++ b/Documentation/networking/netdevices.rst @@ -10,18 +10,177 @@ Introduction The following is a random collection of documentation regarding network devices. -struct net_device allocation rules -================================== +struct net_device lifetime rules +================================ Network device structures need to persist even after module is unloaded and must be allocated with alloc_netdev_mqs() and friends. If device has registered successfully, it will be freed on last use -by free_netdev(). This is required to handle the pathologic case cleanly -(example: rmmod mydriver needs_free_netdev = true; + } + + static void my_destructor(struct net_device *dev) + { + some_obj_destroy(priv->obj); + some_uninit(priv); + } + + int create_link() + { + struct my_device_priv *priv; + int err; + + ASSERT_RTNL(); + + dev = alloc_netdev(sizeof(*priv), "net%d", NET_NAME_UNKNOWN, my_setup); + if (!dev) + return -ENOMEM; + priv = netdev_priv(dev); + + /* Implicit constructor */ + err = some_init(priv); + if (err) + goto err_free_dev; + + priv->obj = some_obj_create(); + if (!priv->obj) { + err = -ENOMEM; + goto err_some_uninit; + } + /* End of constructor, set the destructor: */ + dev->priv_destructor = my_destructor; + + err = register_netdevice(dev); + if (err) + /* register_netdevice() calls destructor on failure */ + goto err_free_dev; + + /* If anything fails now unregister_netdevice() (or unregister_netdev()) + * will take care of calling my_destructor and free_netdev(). + */ + + return 0; + + err_some_uninit: + some_uninit(priv); + err_free_dev: + free_netdev(dev); + return err; + } + +If struct net_device.priv_destructor is set it will be called by the core +some time after unregister_netdevice(), it will also be called if +register_netdevice() fails. The callback may be invoked with or without +``rtnl_lock`` held. + +There is no explicit constructor callback, driver "constructs" the private +netdev state after allocating it and before registration. + +Setting struct net_device.needs_free_netdev makes core call free_netdevice() +automatically after unregister_netdevice() when all references to the device +are gone. It only takes effect after a successful call to register_netdevice() +so if register_netdevice() fails driver is responsible for calling +free_netdev(). + +free_netdev() is safe to call on error paths right after unregister_netdevice() +or when register_netdevice() fails. Parts of netdev (de)registration process +happen after ``rtnl_lock`` is released, therefore in those cases free_netdev() +will defer some of the processing until ``rtnl_lock`` is released. + +Devices spawned from struct rtnl_link_ops should never free the +struct net_device directly. + +.ndo_init and .ndo_uninit +~~~~~~~~~~~~~~~~~~~~~~~~~ + +``.ndo_init`` and ``.ndo_uninit`` callbacks are called during net_device +registration and de-registration, under ``rtnl_lock``. Drivers can use +those e.g. when parts of their init process need to run under ``rtnl_lock``. + +``.ndo_init`` runs before device is visible in the system, ``.ndo_uninit`` +runs during de-registering after device is closed but other subsystems +may still have outstanding references to the netdevice. MTU === diff --git a/Makefile b/Makefile index fbd330e58c3b8..00dddc2ac804a 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 10 -SUBLEVEL = 133 +SUBLEVEL = 134 EXTRAVERSION = NAME = Dare mighty things diff --git a/arch/alpha/kernel/srmcons.c b/arch/alpha/kernel/srmcons.c index 438b10c44d732..2b7a314b84522 100644 --- a/arch/alpha/kernel/srmcons.c +++ b/arch/alpha/kernel/srmcons.c @@ -59,7 +59,7 @@ srmcons_do_receive_chars(struct tty_port *port) } while((result.bits.status & 1) && (++loops < 10)); if (count) - tty_schedule_flip(port); + tty_flip_buffer_push(port); return count; } diff --git a/arch/m68k/Kconfig.bus b/arch/m68k/Kconfig.bus index d1e93a39cd3bc..f1be832e2b746 100644 --- a/arch/m68k/Kconfig.bus +++ b/arch/m68k/Kconfig.bus @@ -63,7 +63,7 @@ source "drivers/zorro/Kconfig" endif -if COLDFIRE +if !MMU config ISA_DMA_API def_bool !M5272 diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index db9505c658eab..3d3016092b31c 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -73,6 +73,7 @@ ifeq ($(CONFIG_PERF_EVENTS),y) endif KBUILD_CFLAGS_MODULE += $(call cc-option,-mno-relax) +KBUILD_AFLAGS_MODULE += $(call as-option,-Wa$(comma)-mno-relax) # GCC versions that support the "-mstrict-align" option default to allowing # unaligned accesses. While unaligned accesses are explicitly allowed in the diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index e077f4fe7c6d4..2a51ee2f5a0f0 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -298,6 +298,7 @@ #define X86_FEATURE_RETPOLINE_LFENCE (11*32+13) /* "" Use LFENCE for Spectre variant 2 */ #define X86_FEATURE_RETHUNK (11*32+14) /* "" Use REturn THUNK */ #define X86_FEATURE_UNRET (11*32+15) /* "" AMD BTB untrain return */ +#define X86_FEATURE_USE_IBPB_FW (11*32+16) /* "" Use IBPB during runtime firmware calls */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 30f76b9668579..871a8b06d4304 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -247,13 +247,6 @@ bool hv_vcpu_is_preempted(int vcpu); static inline void hv_apic_init(void) {} #endif -static inline void hv_set_msi_entry_from_desc(union hv_msi_entry *msi_entry, - struct msi_desc *msi_desc) -{ - msi_entry->address = msi_desc->msg.address_lo; - msi_entry->data = msi_desc->msg.data; -} - #else /* CONFIG_HYPERV */ static inline void hyperv_init(void) {} static inline void hyperv_setup_mmu_ops(void) {} diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 6f2adaf53f467..c3e8e50633ea2 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -298,6 +298,8 @@ do { \ alternative_msr_write(MSR_IA32_SPEC_CTRL, \ spec_ctrl_current() | SPEC_CTRL_IBRS, \ X86_FEATURE_USE_IBRS_FW); \ + alternative_msr_write(MSR_IA32_PRED_CMD, PRED_CMD_IBPB, \ + X86_FEATURE_USE_IBPB_FW); \ } while (0) #define firmware_restrict_branch_speculation_end() \ diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 77eefa0b0f324..a85fb17f11804 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -709,7 +709,9 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end) dest = addr + insn.length + insn.immediate.value; if (__static_call_fixup(addr, op, dest) || - WARN_ON_ONCE(dest != &__x86_return_thunk)) + WARN_ONCE(dest != &__x86_return_thunk, + "missing return thunk: %pS-%pS: %*ph", + addr, dest, 5, addr)) continue; DPRINTK("return thunk at: %pS (%px) len: %d to: %pS", diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index bc6382f5ec27b..7896b67dda420 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -931,6 +931,7 @@ static inline const char *spectre_v2_module_string(void) { return ""; } #define SPECTRE_V2_LFENCE_MSG "WARNING: LFENCE mitigation is not recommended for this CPU, data leaks possible!\n" #define SPECTRE_V2_EIBRS_EBPF_MSG "WARNING: Unprivileged eBPF is enabled with eIBRS on, data leaks possible via Spectre v2 BHB attacks!\n" #define SPECTRE_V2_EIBRS_LFENCE_EBPF_SMT_MSG "WARNING: Unprivileged eBPF is enabled with eIBRS+LFENCE mitigation and SMT, data leaks possible via Spectre v2 BHB attacks!\n" +#define SPECTRE_V2_IBRS_PERF_MSG "WARNING: IBRS mitigation selected on Enhanced IBRS CPU, this may cause unnecessary performance loss\n" #ifdef CONFIG_BPF_SYSCALL void unpriv_ebpf_notify(int new_state) @@ -1371,6 +1372,8 @@ static void __init spectre_v2_select_mitigation(void) case SPECTRE_V2_IBRS: setup_force_cpu_cap(X86_FEATURE_KERNEL_IBRS); + if (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED)) + pr_warn(SPECTRE_V2_IBRS_PERF_MSG); break; case SPECTRE_V2_LFENCE: @@ -1472,7 +1475,16 @@ static void __init spectre_v2_select_mitigation(void) * the CPU supports Enhanced IBRS, kernel might un-intentionally not * enable IBRS around firmware calls. */ - if (boot_cpu_has(X86_FEATURE_IBRS) && !spectre_v2_in_ibrs_mode(mode)) { + if (boot_cpu_has_bug(X86_BUG_RETBLEED) && + (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)) { + + if (retbleed_cmd != RETBLEED_CMD_IBPB) { + setup_force_cpu_cap(X86_FEATURE_USE_IBPB_FW); + pr_info("Enabling Speculation Barrier for firmware calls\n"); + } + + } else if (boot_cpu_has(X86_FEATURE_IBRS) && !spectre_v2_in_ibrs_mode(mode)) { setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW); pr_info("Enabling Restricted Speculation for firmware calls\n"); } diff --git a/drivers/accessibility/speakup/spk_ttyio.c b/drivers/accessibility/speakup/spk_ttyio.c index 6284aff434a1a..da3a24557a031 100644 --- a/drivers/accessibility/speakup/spk_ttyio.c +++ b/drivers/accessibility/speakup/spk_ttyio.c @@ -88,7 +88,7 @@ static int spk_ttyio_receive_buf2(struct tty_struct *tty, } if (!ldisc_data->buf_free) - /* ttyio_in will tty_schedule_flip */ + /* ttyio_in will tty_flip_buffer_push */ return 0; /* Make sure the consumer has read buf before we have seen @@ -334,7 +334,7 @@ static unsigned char ttyio_in(int timeout) mb(); ldisc_data->buf_free = true; /* Let TTY push more characters */ - tty_schedule_flip(speakup_tty->port); + tty_flip_buffer_push(speakup_tty->port); return rv; } diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c index bb4ca064447e9..957be5f69406a 100644 --- a/drivers/gpio/gpio-pca953x.c +++ b/drivers/gpio/gpio-pca953x.c @@ -350,6 +350,9 @@ static const struct regmap_config pca953x_i2c_regmap = { .reg_bits = 8, .val_bits = 8, + .use_single_read = true, + .use_single_write = true, + .readable_reg = pca953x_readable_register, .writeable_reg = pca953x_writeable_register, .volatile_reg = pca953x_volatile_register, @@ -893,15 +896,18 @@ static int pca953x_irq_setup(struct pca953x_chip *chip, static int device_pca95xx_init(struct pca953x_chip *chip, u32 invert) { DECLARE_BITMAP(val, MAX_LINE); + u8 regaddr; int ret; - ret = regcache_sync_region(chip->regmap, chip->regs->output, - chip->regs->output + NBANK(chip)); + regaddr = pca953x_recalc_addr(chip, chip->regs->output, 0); + ret = regcache_sync_region(chip->regmap, regaddr, + regaddr + NBANK(chip) - 1); if (ret) goto out; - ret = regcache_sync_region(chip->regmap, chip->regs->direction, - chip->regs->direction + NBANK(chip)); + regaddr = pca953x_recalc_addr(chip, chip->regs->direction, 0); + ret = regcache_sync_region(chip->regmap, regaddr, + regaddr + NBANK(chip) - 1); if (ret) goto out; @@ -1114,14 +1120,14 @@ static int pca953x_regcache_sync(struct device *dev) * sync these registers first and only then sync the rest. */ regaddr = pca953x_recalc_addr(chip, chip->regs->direction, 0); - ret = regcache_sync_region(chip->regmap, regaddr, regaddr + NBANK(chip)); + ret = regcache_sync_region(chip->regmap, regaddr, regaddr + NBANK(chip) - 1); if (ret) { dev_err(dev, "Failed to sync GPIO dir registers: %d\n", ret); return ret; } regaddr = pca953x_recalc_addr(chip, chip->regs->output, 0); - ret = regcache_sync_region(chip->regmap, regaddr, regaddr + NBANK(chip)); + ret = regcache_sync_region(chip->regmap, regaddr, regaddr + NBANK(chip) - 1); if (ret) { dev_err(dev, "Failed to sync GPIO out registers: %d\n", ret); return ret; @@ -1131,7 +1137,7 @@ static int pca953x_regcache_sync(struct device *dev) if (chip->driver_data & PCA_PCAL) { regaddr = pca953x_recalc_addr(chip, PCAL953X_IN_LATCH, 0); ret = regcache_sync_region(chip->regmap, regaddr, - regaddr + NBANK(chip)); + regaddr + NBANK(chip) - 1); if (ret) { dev_err(dev, "Failed to sync INT latch registers: %d\n", ret); @@ -1140,7 +1146,7 @@ static int pca953x_regcache_sync(struct device *dev) regaddr = pca953x_recalc_addr(chip, PCAL953X_INT_MASK, 0); ret = regcache_sync_region(chip->regmap, regaddr, - regaddr + NBANK(chip)); + regaddr + NBANK(chip) - 1); if (ret) { dev_err(dev, "Failed to sync INT mask registers: %d\n", ret); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index f069d0faba64b..55ecc67592ebc 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -922,6 +922,37 @@ static void amdgpu_check_debugfs_connector_property_change(struct amdgpu_device } } +struct amdgpu_stutter_quirk { + u16 chip_vendor; + u16 chip_device; + u16 subsys_vendor; + u16 subsys_device; + u8 revision; +}; + +static const struct amdgpu_stutter_quirk amdgpu_stutter_quirk_list[] = { + /* https://bugzilla.kernel.org/show_bug.cgi?id=214417 */ + { 0x1002, 0x15dd, 0x1002, 0x15dd, 0xc8 }, + { 0, 0, 0, 0, 0 }, +}; + +static bool dm_should_disable_stutter(struct pci_dev *pdev) +{ + const struct amdgpu_stutter_quirk *p = amdgpu_stutter_quirk_list; + + while (p && p->chip_device != 0) { + if (pdev->vendor == p->chip_vendor && + pdev->device == p->chip_device && + pdev->subsystem_vendor == p->subsys_vendor && + pdev->subsystem_device == p->subsys_device && + pdev->revision == p->revision) { + return true; + } + ++p; + } + return false; +} + static int amdgpu_dm_init(struct amdgpu_device *adev) { struct dc_init_data init_data; @@ -1014,6 +1045,8 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) if (adev->asic_type != CHIP_CARRIZO && adev->asic_type != CHIP_STONEY) adev->dm.dc->debug.disable_stutter = amdgpu_pp_feature_mask & PP_STUTTER_MODE ? false : true; + if (dm_should_disable_stutter(adev->pdev)) + adev->dm.dc->debug.disable_stutter = true; if (amdgpu_dc_debug_mask & DC_DISABLE_STUTTER) adev->dm.dc->debug.disable_stutter = true; diff --git a/drivers/gpu/drm/imx/dcss/dcss-dev.c b/drivers/gpu/drm/imx/dcss/dcss-dev.c index c849533ca83e3..3f5750cc2673e 100644 --- a/drivers/gpu/drm/imx/dcss/dcss-dev.c +++ b/drivers/gpu/drm/imx/dcss/dcss-dev.c @@ -207,6 +207,7 @@ struct dcss_dev *dcss_dev_create(struct device *dev, bool hdmi_output) ret = dcss_submodules_init(dcss); if (ret) { + of_node_put(dcss->of_port); dev_err(dev, "submodules initialization failed\n"); goto clks_err; } @@ -237,6 +238,8 @@ void dcss_dev_destroy(struct dcss_dev *dcss) dcss_clocks_disable(dcss); } + of_node_put(dcss->of_port); + pm_runtime_disable(dcss->dev); dcss_submodules_stop(dcss); diff --git a/drivers/gpu/drm/imx/dcss/dcss-plane.c b/drivers/gpu/drm/imx/dcss/dcss-plane.c index f54087ac44d35..46a188dd02adc 100644 --- a/drivers/gpu/drm/imx/dcss/dcss-plane.c +++ b/drivers/gpu/drm/imx/dcss/dcss-plane.c @@ -268,7 +268,6 @@ static void dcss_plane_atomic_update(struct drm_plane *plane, struct dcss_plane *dcss_plane = to_dcss_plane(plane); struct dcss_dev *dcss = plane->dev->dev_private; struct drm_framebuffer *fb = state->fb; - u32 pixel_format; struct drm_crtc_state *crtc_state; bool modifiers_present; u32 src_w, src_h, dst_w, dst_h; @@ -279,7 +278,6 @@ static void dcss_plane_atomic_update(struct drm_plane *plane, if (!fb || !state->crtc || !state->visible) return; - pixel_format = state->fb->format->format; crtc_state = state->crtc->state; modifiers_present = !!(fb->flags & DRM_MODE_FB_MODIFIERS); diff --git a/drivers/i2c/busses/i2c-cadence.c b/drivers/i2c/busses/i2c-cadence.c index 01564bd96c624..0abce487ead72 100644 --- a/drivers/i2c/busses/i2c-cadence.c +++ b/drivers/i2c/busses/i2c-cadence.c @@ -386,9 +386,9 @@ static irqreturn_t cdns_i2c_slave_isr(void *ptr) */ static irqreturn_t cdns_i2c_master_isr(void *ptr) { - unsigned int isr_status, avail_bytes, updatetx; + unsigned int isr_status, avail_bytes; unsigned int bytes_to_send; - bool hold_quirk; + bool updatetx; struct cdns_i2c *id = ptr; /* Signal completion only after everything is updated */ int done_flag = 0; @@ -408,11 +408,7 @@ static irqreturn_t cdns_i2c_master_isr(void *ptr) * Check if transfer size register needs to be updated again for a * large data receive operation. */ - updatetx = 0; - if (id->recv_count > id->curr_recv_count) - updatetx = 1; - - hold_quirk = (id->quirks & CDNS_I2C_BROKEN_HOLD_BIT) && updatetx; + updatetx = id->recv_count > id->curr_recv_count; /* When receiving, handle data interrupt and completion interrupt */ if (id->p_recv_buf && @@ -443,7 +439,7 @@ static irqreturn_t cdns_i2c_master_isr(void *ptr) break; } - if (cdns_is_holdquirk(id, hold_quirk)) + if (cdns_is_holdquirk(id, updatetx)) break; } @@ -454,7 +450,7 @@ static irqreturn_t cdns_i2c_master_isr(void *ptr) * maintain transfer size non-zero while performing a large * receive operation. */ - if (cdns_is_holdquirk(id, hold_quirk)) { + if (cdns_is_holdquirk(id, updatetx)) { /* wait while fifo is full */ while (cdns_i2c_readreg(CDNS_I2C_XFER_SIZE_OFFSET) != (id->curr_recv_count - CDNS_I2C_FIFO_DEPTH)) @@ -476,22 +472,6 @@ static irqreturn_t cdns_i2c_master_isr(void *ptr) CDNS_I2C_XFER_SIZE_OFFSET); id->curr_recv_count = id->recv_count; } - } else if (id->recv_count && !hold_quirk && - !id->curr_recv_count) { - - /* Set the slave address in address register*/ - cdns_i2c_writereg(id->p_msg->addr & CDNS_I2C_ADDR_MASK, - CDNS_I2C_ADDR_OFFSET); - - if (id->recv_count > CDNS_I2C_TRANSFER_SIZE) { - cdns_i2c_writereg(CDNS_I2C_TRANSFER_SIZE, - CDNS_I2C_XFER_SIZE_OFFSET); - id->curr_recv_count = CDNS_I2C_TRANSFER_SIZE; - } else { - cdns_i2c_writereg(id->recv_count, - CDNS_I2C_XFER_SIZE_OFFSET); - id->curr_recv_count = id->recv_count; - } } /* Clear hold (if not repeated start) and signal completion */ diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c index 51e071c20e397..cd6e016e62103 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c @@ -1235,8 +1235,8 @@ static struct sock *chtls_recv_sock(struct sock *lsk, csk->sndbuf = newsk->sk_sndbuf; csk->smac_idx = ((struct port_info *)netdev_priv(ndev))->smt_idx; RCV_WSCALE(tp) = select_rcv_wscale(tcp_full_space(newsk), - sock_net(newsk)-> - ipv4.sysctl_tcp_window_scaling, + READ_ONCE(sock_net(newsk)-> + ipv4.sysctl_tcp_window_scaling), tp->window_clamp); neigh_release(n); inet_inherit_port(&tcp_hashinfo, lsk, newsk); @@ -1383,7 +1383,7 @@ static void chtls_pass_accept_request(struct sock *sk, #endif } if (req->tcpopt.wsf <= 14 && - sock_net(sk)->ipv4.sysctl_tcp_window_scaling) { + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_window_scaling)) { inet_rsk(oreq)->wscale_ok = 1; inet_rsk(oreq)->snd_wscale = req->tcpopt.wsf; } diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c index 649c5c429bd7c..1288b5e3d2201 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.c +++ b/drivers/net/ethernet/emulex/benet/be_cmds.c @@ -2287,7 +2287,7 @@ err: /* Uses sync mcc */ int be_cmd_read_port_transceiver_data(struct be_adapter *adapter, - u8 page_num, u8 *data) + u8 page_num, u32 off, u32 len, u8 *data) { struct be_dma_mem cmd; struct be_mcc_wrb *wrb; @@ -2321,10 +2321,10 @@ int be_cmd_read_port_transceiver_data(struct be_adapter *adapter, req->port = cpu_to_le32(adapter->hba_port_num); req->page_num = cpu_to_le32(page_num); status = be_mcc_notify_wait(adapter); - if (!status) { + if (!status && len > 0) { struct be_cmd_resp_port_type *resp = cmd.va; - memcpy(data, resp->page_data, PAGE_DATA_LEN); + memcpy(data, resp->page_data + off, len); } err: mutex_unlock(&adapter->mcc_lock); @@ -2415,7 +2415,7 @@ int be_cmd_query_cable_type(struct be_adapter *adapter) int status; status = be_cmd_read_port_transceiver_data(adapter, TR_PAGE_A0, - page_data); + 0, PAGE_DATA_LEN, page_data); if (!status) { switch (adapter->phy.interface_type) { case PHY_TYPE_QSFP: @@ -2440,7 +2440,7 @@ int be_cmd_query_sfp_info(struct be_adapter *adapter) int status; status = be_cmd_read_port_transceiver_data(adapter, TR_PAGE_A0, - page_data); + 0, PAGE_DATA_LEN, page_data); if (!status) { strlcpy(adapter->phy.vendor_name, page_data + SFP_VENDOR_NAME_OFFSET, SFP_VENDOR_NAME_LEN - 1); diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h index c30d6d6f0f3a0..9e17d6a7ab8cd 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.h +++ b/drivers/net/ethernet/emulex/benet/be_cmds.h @@ -2427,7 +2427,7 @@ int be_cmd_set_beacon_state(struct be_adapter *adapter, u8 port_num, u8 beacon, int be_cmd_get_beacon_state(struct be_adapter *adapter, u8 port_num, u32 *state); int be_cmd_read_port_transceiver_data(struct be_adapter *adapter, - u8 page_num, u8 *data); + u8 page_num, u32 off, u32 len, u8 *data); int be_cmd_query_cable_type(struct be_adapter *adapter); int be_cmd_query_sfp_info(struct be_adapter *adapter); int lancer_cmd_read_object(struct be_adapter *adapter, struct be_dma_mem *cmd, diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c index 99cc1c46fb301..d90bf457e49cc 100644 --- a/drivers/net/ethernet/emulex/benet/be_ethtool.c +++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c @@ -1338,7 +1338,7 @@ static int be_get_module_info(struct net_device *netdev, return -EOPNOTSUPP; status = be_cmd_read_port_transceiver_data(adapter, TR_PAGE_A0, - page_data); + 0, PAGE_DATA_LEN, page_data); if (!status) { if (!page_data[SFP_PLUS_SFF_8472_COMP]) { modinfo->type = ETH_MODULE_SFF_8079; @@ -1356,25 +1356,32 @@ static int be_get_module_eeprom(struct net_device *netdev, { struct be_adapter *adapter = netdev_priv(netdev); int status; + u32 begin, end; if (!check_privilege(adapter, MAX_PRIVILEGES)) return -EOPNOTSUPP; - status = be_cmd_read_port_transceiver_data(adapter, TR_PAGE_A0, - data); - if (status) - goto err; + begin = eeprom->offset; + end = eeprom->offset + eeprom->len; + + if (begin < PAGE_DATA_LEN) { + status = be_cmd_read_port_transceiver_data(adapter, TR_PAGE_A0, begin, + min_t(u32, end, PAGE_DATA_LEN) - begin, + data); + if (status) + goto err; + + data += PAGE_DATA_LEN - begin; + begin = PAGE_DATA_LEN; + } - if (eeprom->offset + eeprom->len > PAGE_DATA_LEN) { - status = be_cmd_read_port_transceiver_data(adapter, - TR_PAGE_A2, - data + - PAGE_DATA_LEN); + if (end > PAGE_DATA_LEN) { + status = be_cmd_read_port_transceiver_data(adapter, TR_PAGE_A2, + begin - PAGE_DATA_LEN, + end - begin, data); if (status) goto err; } - if (eeprom->offset) - memcpy(data, data + eeprom->offset, eeprom->len); err: return be_cmd_status(status); } diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 58453f7958df9..11d4e3ba9af4c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -10187,7 +10187,7 @@ static int i40e_reset(struct i40e_pf *pf) **/ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) { - int old_recovery_mode_bit = test_bit(__I40E_RECOVERY_MODE, pf->state); + const bool is_recovery_mode_reported = i40e_check_recovery_mode(pf); struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi]; struct i40e_hw *hw = &pf->hw; i40e_status ret; @@ -10195,13 +10195,11 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) int v; if (test_bit(__I40E_EMP_RESET_INTR_RECEIVED, pf->state) && - i40e_check_recovery_mode(pf)) { + is_recovery_mode_reported) i40e_set_ethtool_ops(pf->vsi[pf->lan_vsi]->netdev); - } if (test_bit(__I40E_DOWN, pf->state) && - !test_bit(__I40E_RECOVERY_MODE, pf->state) && - !old_recovery_mode_bit) + !test_bit(__I40E_RECOVERY_MODE, pf->state)) goto clear_recovery; dev_dbg(&pf->pdev->dev, "Rebuilding internal switch\n"); @@ -10228,13 +10226,12 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) * accordingly with regard to resources initialization * and deinitialization */ - if (test_bit(__I40E_RECOVERY_MODE, pf->state) || - old_recovery_mode_bit) { + if (test_bit(__I40E_RECOVERY_MODE, pf->state)) { if (i40e_get_capabilities(pf, i40e_aqc_opc_list_func_capabilities)) goto end_unlock; - if (test_bit(__I40E_RECOVERY_MODE, pf->state)) { + if (is_recovery_mode_reported) { /* we're staying in recovery mode so we'll reinitialize * misc vector here */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c index 256fa07d54d5d..99983f7a0ce0b 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c @@ -1263,11 +1263,10 @@ static struct iavf_rx_buffer *iavf_get_rx_buffer(struct iavf_ring *rx_ring, { struct iavf_rx_buffer *rx_buffer; - if (!size) - return NULL; - rx_buffer = &rx_ring->rx_bi[rx_ring->next_to_clean]; prefetchw(rx_buffer->page); + if (!size) + return rx_buffer; /* we are reusing so sync this buffer for CPU use */ dma_sync_single_range_for_cpu(rx_ring->dev, diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 53e31002ce52a..e7ffe63925fd2 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -4933,6 +4933,9 @@ u32 igc_rd32(struct igc_hw *hw, u32 reg) u8 __iomem *hw_addr = READ_ONCE(hw->hw_addr); u32 value = 0; + if (IGC_REMOVED(hw_addr)) + return ~value; + value = readl(&hw_addr[reg]); /* reads should not return all F's */ diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h index b52dd9d737e87..a273e1c33b3fd 100644 --- a/drivers/net/ethernet/intel/igc/igc_regs.h +++ b/drivers/net/ethernet/intel/igc/igc_regs.h @@ -252,7 +252,8 @@ u32 igc_rd32(struct igc_hw *hw, u32 reg); #define wr32(reg, val) \ do { \ u8 __iomem *hw_addr = READ_ONCE((hw)->hw_addr); \ - writel((val), &hw_addr[(reg)]); \ + if (!IGC_REMOVED(hw_addr)) \ + writel((val), &hw_addr[(reg)]); \ } while (0) #define rd32(reg) (igc_rd32(hw, reg)) @@ -264,4 +265,6 @@ do { \ #define array_rd32(reg, offset) (igc_rd32(hw, (reg) + ((offset) << 2))) +#define IGC_REMOVED(h) unlikely(!(h)) + #endif diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index de0fc6ecf491f..27c6f911737bf 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -769,6 +769,7 @@ struct ixgbe_adapter { #ifdef CONFIG_IXGBE_IPSEC struct ixgbe_ipsec *ipsec; #endif /* CONFIG_IXGBE_IPSEC */ + spinlock_t vfs_lock; }; static inline u8 ixgbe_max_rss_indices(struct ixgbe_adapter *adapter) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index a3a02e2f92f64..b5b8be4672aa4 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -6403,6 +6403,9 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter, /* n-tuple support exists, always init our spinlock */ spin_lock_init(&adapter->fdir_perfect_lock); + /* init spinlock to avoid concurrency of VF resources */ + spin_lock_init(&adapter->vfs_lock); + #ifdef CONFIG_IXGBE_DCB ixgbe_init_dcb(adapter); #endif diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c index aaebdae8b5fff..0078ae5926164 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c @@ -204,10 +204,13 @@ void ixgbe_enable_sriov(struct ixgbe_adapter *adapter, unsigned int max_vfs) int ixgbe_disable_sriov(struct ixgbe_adapter *adapter) { unsigned int num_vfs = adapter->num_vfs, vf; + unsigned long flags; int rss; + spin_lock_irqsave(&adapter->vfs_lock, flags); /* set num VFs to 0 to prevent access to vfinfo */ adapter->num_vfs = 0; + spin_unlock_irqrestore(&adapter->vfs_lock, flags); /* put the reference to all of the vf devices */ for (vf = 0; vf < num_vfs; ++vf) { @@ -1305,8 +1308,10 @@ static void ixgbe_rcv_ack_from_vf(struct ixgbe_adapter *adapter, u32 vf) void ixgbe_msg_task(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; + unsigned long flags; u32 vf; + spin_lock_irqsave(&adapter->vfs_lock, flags); for (vf = 0; vf < adapter->num_vfs; vf++) { /* process any reset requests */ if (!ixgbe_check_for_rst(hw, vf)) @@ -1320,6 +1325,7 @@ void ixgbe_msg_task(struct ixgbe_adapter *adapter) if (!ixgbe_check_for_ack(hw, vf)) ixgbe_rcv_ack_from_vf(adapter, vf); } + spin_unlock_irqrestore(&adapter->vfs_lock, flags); } void ixgbe_disable_tx_rx(struct ixgbe_adapter *adapter) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 53128382fc2e0..d2887ae508bb8 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -4003,7 +4003,7 @@ static bool mlxsw_sp_fi_is_gateway(const struct mlxsw_sp *mlxsw_sp, { const struct fib_nh *nh = fib_info_nh(fi, 0); - return nh->fib_nh_scope == RT_SCOPE_LINK || + return nh->fib_nh_gw_family || mlxsw_sp_nexthop4_ipip_type(mlxsw_sp, nh, NULL); } @@ -8038,13 +8038,14 @@ static int mlxsw_sp_dscp_init(struct mlxsw_sp *mlxsw_sp) static int __mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp) { struct net *net = mlxsw_sp_net(mlxsw_sp); - bool usp = net->ipv4.sysctl_ip_fwd_update_priority; char rgcr_pl[MLXSW_REG_RGCR_LEN]; u64 max_rifs; + bool usp; if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_RIFS)) return -EIO; max_rifs = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); + usp = READ_ONCE(net->ipv4.sysctl_ip_fwd_update_priority); mlxsw_reg_rgcr_pack(rgcr_pl, true, true); mlxsw_reg_rgcr_max_router_interfaces_set(rgcr_pl, max_rifs); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index 16c538cfaf59d..2e71e510e127d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -215,6 +215,9 @@ static void dwmac4_map_mtl_dma(struct mac_device_info *hw, u32 queue, u32 chan) if (queue == 0 || queue == 4) { value &= ~MTL_RXQ_DMA_Q04MDMACH_MASK; value |= MTL_RXQ_DMA_Q04MDMACH(chan); + } else if (queue > 4) { + value &= ~MTL_RXQ_DMA_QXMDMACH_MASK(queue - 4); + value |= MTL_RXQ_DMA_QXMDMACH(chan, queue - 4); } else { value &= ~MTL_RXQ_DMA_QXMDMACH_MASK(queue); value |= MTL_RXQ_DMA_QXMDMACH(chan, queue); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index e9aa9a5eba6be..27b7bb64a0281 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -738,19 +738,10 @@ int stmmac_init_tstamp_counter(struct stmmac_priv *priv, u32 systime_flags) struct timespec64 now; u32 sec_inc = 0; u64 temp = 0; - int ret; if (!(priv->dma_cap.time_stamp || priv->dma_cap.atime_stamp)) return -EOPNOTSUPP; - ret = clk_prepare_enable(priv->plat->clk_ptp_ref); - if (ret < 0) { - netdev_warn(priv->dev, - "failed to enable PTP reference clock: %pe\n", - ERR_PTR(ret)); - return ret; - } - stmmac_config_hw_tstamping(priv, priv->ptpaddr, systime_flags); priv->systime_flags = systime_flags; @@ -2755,6 +2746,14 @@ static int stmmac_hw_setup(struct net_device *dev, bool ptp_register) stmmac_mmc_setup(priv); + if (ptp_register) { + ret = clk_prepare_enable(priv->plat->clk_ptp_ref); + if (ret < 0) + netdev_warn(priv->dev, + "failed to enable PTP reference clock: %pe\n", + ERR_PTR(ret)); + } + ret = stmmac_init_ptp(priv); if (ret == -EOPNOTSUPP) netdev_warn(priv->dev, "PTP not supported by HW\n"); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index b40b962055fa5..f70d8d1ce3298 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -814,7 +814,13 @@ static int __maybe_unused stmmac_pltfr_noirq_resume(struct device *dev) if (ret) return ret; - stmmac_init_tstamp_counter(priv, priv->systime_flags); + ret = clk_prepare_enable(priv->plat->clk_ptp_ref); + if (ret < 0) { + netdev_warn(priv->dev, + "failed to enable PTP reference clock: %pe\n", + ERR_PTR(ret)); + return ret; + } } return 0; diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index 79a53fe245e5c..0ac4f59e3f186 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -1796,7 +1796,7 @@ static const struct driver_info ax88179_info = { .link_reset = ax88179_link_reset, .reset = ax88179_reset, .stop = ax88179_stop, - .flags = FLAG_ETHER | FLAG_FRAMING_AX, + .flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_SEND_ZLP, .rx_fixup = ax88179_rx_fixup, .tx_fixup = ax88179_tx_fixup, }; @@ -1809,7 +1809,7 @@ static const struct driver_info ax88178a_info = { .link_reset = ax88179_link_reset, .reset = ax88179_reset, .stop = ax88179_stop, - .flags = FLAG_ETHER | FLAG_FRAMING_AX, + .flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_SEND_ZLP, .rx_fixup = ax88179_rx_fixup, .tx_fixup = ax88179_tx_fixup, }; @@ -1822,7 +1822,7 @@ static const struct driver_info cypress_GX3_info = { .link_reset = ax88179_link_reset, .reset = ax88179_reset, .stop = ax88179_stop, - .flags = FLAG_ETHER | FLAG_FRAMING_AX, + .flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_SEND_ZLP, .rx_fixup = ax88179_rx_fixup, .tx_fixup = ax88179_tx_fixup, }; @@ -1835,7 +1835,7 @@ static const struct driver_info dlink_dub1312_info = { .link_reset = ax88179_link_reset, .reset = ax88179_reset, .stop = ax88179_stop, - .flags = FLAG_ETHER | FLAG_FRAMING_AX, + .flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_SEND_ZLP, .rx_fixup = ax88179_rx_fixup, .tx_fixup = ax88179_tx_fixup, }; @@ -1848,7 +1848,7 @@ static const struct driver_info sitecom_info = { .link_reset = ax88179_link_reset, .reset = ax88179_reset, .stop = ax88179_stop, - .flags = FLAG_ETHER | FLAG_FRAMING_AX, + .flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_SEND_ZLP, .rx_fixup = ax88179_rx_fixup, .tx_fixup = ax88179_tx_fixup, }; @@ -1861,7 +1861,7 @@ static const struct driver_info samsung_info = { .link_reset = ax88179_link_reset, .reset = ax88179_reset, .stop = ax88179_stop, - .flags = FLAG_ETHER | FLAG_FRAMING_AX, + .flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_SEND_ZLP, .rx_fixup = ax88179_rx_fixup, .tx_fixup = ax88179_tx_fixup, }; @@ -1874,7 +1874,7 @@ static const struct driver_info lenovo_info = { .link_reset = ax88179_link_reset, .reset = ax88179_reset, .stop = ax88179_stop, - .flags = FLAG_ETHER | FLAG_FRAMING_AX, + .flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_SEND_ZLP, .rx_fixup = ax88179_rx_fixup, .tx_fixup = ax88179_tx_fixup, }; @@ -1887,7 +1887,7 @@ static const struct driver_info belkin_info = { .link_reset = ax88179_link_reset, .reset = ax88179_reset, .stop = ax88179_stop, - .flags = FLAG_ETHER | FLAG_FRAMING_AX, + .flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_SEND_ZLP, .rx_fixup = ax88179_rx_fixup, .tx_fixup = ax88179_tx_fixup, }; @@ -1900,7 +1900,7 @@ static const struct driver_info toshiba_info = { .link_reset = ax88179_link_reset, .reset = ax88179_reset, .stop = ax88179_stop, - .flags = FLAG_ETHER | FLAG_FRAMING_AX, + .flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_SEND_ZLP, .rx_fixup = ax88179_rx_fixup, .tx_fixup = ax88179_tx_fixup, }; @@ -1913,7 +1913,7 @@ static const struct driver_info mct_info = { .link_reset = ax88179_link_reset, .reset = ax88179_reset, .stop = ax88179_stop, - .flags = FLAG_ETHER | FLAG_FRAMING_AX, + .flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_SEND_ZLP, .rx_fixup = ax88179_rx_fixup, .tx_fixup = ax88179_tx_fixup, }; diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index a070e69bb49cd..4353443b89d81 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -1118,6 +1118,10 @@ static void hv_int_desc_free(struct hv_pci_dev *hpdev, u8 buffer[sizeof(struct pci_delete_interrupt)]; } ctxt; + if (!int_desc->vector_count) { + kfree(int_desc); + return; + } memset(&ctxt, 0, sizeof(ctxt)); int_pkt = (struct pci_delete_interrupt *)&ctxt.pkt.message; int_pkt->message_type.type = @@ -1180,6 +1184,28 @@ static void hv_irq_mask(struct irq_data *data) pci_msi_mask_irq(data); } +static unsigned int hv_msi_get_int_vector(struct irq_data *data) +{ + struct irq_cfg *cfg = irqd_cfg(data); + + return cfg->vector; +} + +static int hv_msi_prepare(struct irq_domain *domain, struct device *dev, + int nvec, msi_alloc_info_t *info) +{ + int ret = pci_msi_prepare(domain, dev, nvec, info); + + /* + * By using the interrupt remapper in the hypervisor IOMMU, contiguous + * CPU vectors is not needed for multi-MSI + */ + if (info->type == X86_IRQ_ALLOC_TYPE_PCI_MSI) + info->flags &= ~X86_IRQ_ALLOC_CONTIGUOUS_VECTORS; + + return ret; +} + /** * hv_irq_unmask() - "Unmask" the IRQ by setting its current * affinity. @@ -1195,6 +1221,7 @@ static void hv_irq_unmask(struct irq_data *data) struct msi_desc *msi_desc = irq_data_get_msi_desc(data); struct irq_cfg *cfg = irqd_cfg(data); struct hv_retarget_device_interrupt *params; + struct tran_int_desc *int_desc; struct hv_pcibus_device *hbus; struct cpumask *dest; cpumask_var_t tmp; @@ -1209,6 +1236,7 @@ static void hv_irq_unmask(struct irq_data *data) pdev = msi_desc_to_pci_dev(msi_desc); pbus = pdev->bus; hbus = container_of(pbus->sysdata, struct hv_pcibus_device, sysdata); + int_desc = data->chip_data; spin_lock_irqsave(&hbus->retarget_msi_interrupt_lock, flags); @@ -1216,7 +1244,8 @@ static void hv_irq_unmask(struct irq_data *data) memset(params, 0, sizeof(*params)); params->partition_id = HV_PARTITION_ID_SELF; params->int_entry.source = 1; /* MSI(-X) */ - hv_set_msi_entry_from_desc(¶ms->int_entry.msi_entry, msi_desc); + params->int_entry.msi_entry.address = int_desc->address & 0xffffffff; + params->int_entry.msi_entry.data = int_desc->data; params->device_id = (hbus->hdev->dev_instance.b[5] << 24) | (hbus->hdev->dev_instance.b[4] << 16) | (hbus->hdev->dev_instance.b[7] << 8) | @@ -1317,12 +1346,12 @@ static void hv_pci_compose_compl(void *context, struct pci_response *resp, static u32 hv_compose_msi_req_v1( struct pci_create_interrupt *int_pkt, struct cpumask *affinity, - u32 slot, u8 vector) + u32 slot, u8 vector, u8 vector_count) { int_pkt->message_type.type = PCI_CREATE_INTERRUPT_MESSAGE; int_pkt->wslot.slot = slot; int_pkt->int_desc.vector = vector; - int_pkt->int_desc.vector_count = 1; + int_pkt->int_desc.vector_count = vector_count; int_pkt->int_desc.delivery_mode = dest_Fixed; /* @@ -1336,14 +1365,14 @@ static u32 hv_compose_msi_req_v1( static u32 hv_compose_msi_req_v2( struct pci_create_interrupt2 *int_pkt, struct cpumask *affinity, - u32 slot, u8 vector) + u32 slot, u8 vector, u8 vector_count) { int cpu; int_pkt->message_type.type = PCI_CREATE_INTERRUPT_MESSAGE2; int_pkt->wslot.slot = slot; int_pkt->int_desc.vector = vector; - int_pkt->int_desc.vector_count = 1; + int_pkt->int_desc.vector_count = vector_count; int_pkt->int_desc.delivery_mode = dest_Fixed; /* @@ -1371,7 +1400,6 @@ static u32 hv_compose_msi_req_v2( */ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) { - struct irq_cfg *cfg = irqd_cfg(data); struct hv_pcibus_device *hbus; struct vmbus_channel *channel; struct hv_pci_dev *hpdev; @@ -1380,6 +1408,8 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) struct cpumask *dest; struct compose_comp_ctxt comp; struct tran_int_desc *int_desc; + struct msi_desc *msi_desc; + u8 vector, vector_count; struct { struct pci_packet pci_pkt; union { @@ -1391,7 +1421,17 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) u32 size; int ret; - pdev = msi_desc_to_pci_dev(irq_data_get_msi_desc(data)); + /* Reuse the previous allocation */ + if (data->chip_data) { + int_desc = data->chip_data; + msg->address_hi = int_desc->address >> 32; + msg->address_lo = int_desc->address & 0xffffffff; + msg->data = int_desc->data; + return; + } + + msi_desc = irq_data_get_msi_desc(data); + pdev = msi_desc_to_pci_dev(msi_desc); dest = irq_data_get_effective_affinity_mask(data); pbus = pdev->bus; hbus = container_of(pbus->sysdata, struct hv_pcibus_device, sysdata); @@ -1400,17 +1440,40 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) if (!hpdev) goto return_null_message; - /* Free any previous message that might have already been composed. */ - if (data->chip_data) { - int_desc = data->chip_data; - data->chip_data = NULL; - hv_int_desc_free(hpdev, int_desc); - } - int_desc = kzalloc(sizeof(*int_desc), GFP_ATOMIC); if (!int_desc) goto drop_reference; + if (!msi_desc->msi_attrib.is_msix && msi_desc->nvec_used > 1) { + /* + * If this is not the first MSI of Multi MSI, we already have + * a mapping. Can exit early. + */ + if (msi_desc->irq != data->irq) { + data->chip_data = int_desc; + int_desc->address = msi_desc->msg.address_lo | + (u64)msi_desc->msg.address_hi << 32; + int_desc->data = msi_desc->msg.data + + (data->irq - msi_desc->irq); + msg->address_hi = msi_desc->msg.address_hi; + msg->address_lo = msi_desc->msg.address_lo; + msg->data = int_desc->data; + put_pcichild(hpdev); + return; + } + /* + * The vector we select here is a dummy value. The correct + * value gets sent to the hypervisor in unmask(). This needs + * to be aligned with the count, and also not zero. Multi-msi + * is powers of 2 up to 32, so 32 will always work here. + */ + vector = 32; + vector_count = msi_desc->nvec_used; + } else { + vector = hv_msi_get_int_vector(data); + vector_count = 1; + } + memset(&ctxt, 0, sizeof(ctxt)); init_completion(&comp.comp_pkt.host_event); ctxt.pci_pkt.completion_func = hv_pci_compose_compl; @@ -1421,7 +1484,8 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) size = hv_compose_msi_req_v1(&ctxt.int_pkts.v1, dest, hpdev->desc.win_slot.slot, - cfg->vector); + vector, + vector_count); break; case PCI_PROTOCOL_VERSION_1_2: @@ -1429,7 +1493,8 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) size = hv_compose_msi_req_v2(&ctxt.int_pkts.v2, dest, hpdev->desc.win_slot.slot, - cfg->vector); + vector, + vector_count); break; default: @@ -1545,7 +1610,7 @@ static struct irq_chip hv_msi_irq_chip = { }; static struct msi_domain_ops hv_msi_ops = { - .msi_prepare = pci_msi_prepare, + .msi_prepare = hv_msi_prepare, .msi_free = hv_msi_free, }; diff --git a/drivers/pinctrl/stm32/pinctrl-stm32.c b/drivers/pinctrl/stm32/pinctrl-stm32.c index b017dd400c460..60406f1f8337e 100644 --- a/drivers/pinctrl/stm32/pinctrl-stm32.c +++ b/drivers/pinctrl/stm32/pinctrl-stm32.c @@ -1303,15 +1303,17 @@ static int stm32_gpiolib_register_bank(struct stm32_pinctrl *pctl, bank->bank_ioport_nr = bank_ioport_nr; spin_lock_init(&bank->lock); - /* create irq hierarchical domain */ - bank->fwnode = of_node_to_fwnode(np); + if (pctl->domain) { + /* create irq hierarchical domain */ + bank->fwnode = of_node_to_fwnode(np); - bank->domain = irq_domain_create_hierarchy(pctl->domain, 0, - STM32_GPIO_IRQ_LINE, bank->fwnode, - &stm32_gpio_domain_ops, bank); + bank->domain = irq_domain_create_hierarchy(pctl->domain, 0, STM32_GPIO_IRQ_LINE, + bank->fwnode, &stm32_gpio_domain_ops, + bank); - if (!bank->domain) - return -ENODEV; + if (!bank->domain) + return -ENODEV; + } err = gpiochip_add_data(&bank->gpio_chip, bank); if (err) { @@ -1481,6 +1483,8 @@ int stm32_pctl_probe(struct platform_device *pdev) pctl->domain = stm32_pctrl_get_irq_domain(np); if (IS_ERR(pctl->domain)) return PTR_ERR(pctl->domain); + if (!pctl->domain) + dev_warn(dev, "pinctrl without interrupt support\n"); /* hwspinlock is optional */ hwlock_id = of_hwspin_lock_get_id(pdev->dev.of_node, 0); diff --git a/drivers/power/reset/arm-versatile-reboot.c b/drivers/power/reset/arm-versatile-reboot.c index 08d0a07b58ef2..c7624d7611a7e 100644 --- a/drivers/power/reset/arm-versatile-reboot.c +++ b/drivers/power/reset/arm-versatile-reboot.c @@ -146,6 +146,7 @@ static int __init versatile_reboot_probe(void) versatile_reboot_type = (enum versatile_reboot)reboot_id->data; syscon_regmap = syscon_node_to_regmap(np); + of_node_put(np); if (IS_ERR(syscon_regmap)) return PTR_ERR(syscon_regmap); diff --git a/drivers/s390/char/keyboard.h b/drivers/s390/char/keyboard.h index c467589c7f452..c06d399b9b1f1 100644 --- a/drivers/s390/char/keyboard.h +++ b/drivers/s390/char/keyboard.h @@ -56,7 +56,7 @@ static inline void kbd_put_queue(struct tty_port *port, int ch) { tty_insert_flip_char(port, ch, 0); - tty_schedule_flip(port); + tty_flip_buffer_push(port); } static inline void @@ -64,5 +64,5 @@ kbd_puts_queue(struct tty_port *port, char *cp) { while (*cp) tty_insert_flip_char(port, *cp++, 0); - tty_schedule_flip(port); + tty_flip_buffer_push(port); } diff --git a/drivers/spi/spi-bcm2835.c b/drivers/spi/spi-bcm2835.c index 33c32e9317675..bb9d8386ba3b5 100644 --- a/drivers/spi/spi-bcm2835.c +++ b/drivers/spi/spi-bcm2835.c @@ -1174,10 +1174,14 @@ static void bcm2835_spi_handle_err(struct spi_controller *ctlr, struct bcm2835_spi *bs = spi_controller_get_devdata(ctlr); /* if an error occurred and we have an active dma, then terminate */ - dmaengine_terminate_sync(ctlr->dma_tx); - bs->tx_dma_active = false; - dmaengine_terminate_sync(ctlr->dma_rx); - bs->rx_dma_active = false; + if (ctlr->dma_tx) { + dmaengine_terminate_sync(ctlr->dma_tx); + bs->tx_dma_active = false; + } + if (ctlr->dma_rx) { + dmaengine_terminate_sync(ctlr->dma_rx); + bs->rx_dma_active = false; + } bcm2835_spi_undo_prologue(bs); /* and reset */ diff --git a/drivers/staging/mt7621-pinctrl/pinctrl-rt2880.c b/drivers/staging/mt7621-pinctrl/pinctrl-rt2880.c index 09b0b8a16e994..2e971cbe2d7a7 100644 --- a/drivers/staging/mt7621-pinctrl/pinctrl-rt2880.c +++ b/drivers/staging/mt7621-pinctrl/pinctrl-rt2880.c @@ -267,6 +267,8 @@ static int rt2880_pinmux_pins(struct rt2880_priv *p) p->func[i]->pin_count, sizeof(int), GFP_KERNEL); + if (!p->func[i]->pins) + return -ENOMEM; for (j = 0; j < p->func[i]->pin_count; j++) p->func[i]->pins[j] = p->func[i]->pin_first + j; diff --git a/drivers/tty/cyclades.c b/drivers/tty/cyclades.c index 097266342e5e3..4bcaab250676f 100644 --- a/drivers/tty/cyclades.c +++ b/drivers/tty/cyclades.c @@ -556,7 +556,7 @@ static void cyy_chip_rx(struct cyclades_card *cinfo, int chip, } info->idle_stats.recv_idle = jiffies; } - tty_schedule_flip(port); + tty_flip_buffer_push(port); /* end of service */ cyy_writeb(info, CyRIR, save_xir & 0x3f); @@ -996,7 +996,7 @@ static void cyz_handle_rx(struct cyclades_port *info) mod_timer(&info->rx_full_timer, jiffies + 1); #endif info->idle_stats.recv_idle = jiffies; - tty_schedule_flip(&info->port); + tty_flip_buffer_push(&info->port); /* Update rx_get */ cy_writel(&buf_ctrl->rx_get, new_rx_get); @@ -1172,7 +1172,7 @@ static void cyz_handle_cmd(struct cyclades_card *cinfo) if (delta_count) wake_up_interruptible(&info->port.delta_msr_wait); if (special_count) - tty_schedule_flip(&info->port); + tty_flip_buffer_push(&info->port); } } diff --git a/drivers/tty/goldfish.c b/drivers/tty/goldfish.c index 9180ca5e4dcd4..d6e82eb61fc2d 100644 --- a/drivers/tty/goldfish.c +++ b/drivers/tty/goldfish.c @@ -151,7 +151,7 @@ static irqreturn_t goldfish_tty_interrupt(int irq, void *dev_id) address = (unsigned long)(void *)buf; goldfish_tty_rw(qtty, address, count, 0); - tty_schedule_flip(&qtty->port); + tty_flip_buffer_push(&qtty->port); return IRQ_HANDLED; } diff --git a/drivers/tty/moxa.c b/drivers/tty/moxa.c index f9f14104bd2c0..d6528f3bb9b99 100644 --- a/drivers/tty/moxa.c +++ b/drivers/tty/moxa.c @@ -1385,7 +1385,7 @@ static int moxa_poll_port(struct moxa_port *p, unsigned int handle, if (inited && !tty_throttled(tty) && MoxaPortRxQueue(p) > 0) { /* RX */ MoxaPortReadData(p); - tty_schedule_flip(&p->port); + tty_flip_buffer_push(&p->port); } } else { clear_bit(EMPTYWAIT, &p->statusflags); @@ -1410,7 +1410,7 @@ static int moxa_poll_port(struct moxa_port *p, unsigned int handle, if (tty && (intr & IntrBreak) && !I_IGNBRK(tty)) { /* BREAK */ tty_insert_flip_char(&p->port, 0, TTY_BREAK); - tty_schedule_flip(&p->port); + tty_flip_buffer_push(&p->port); } if (intr & IntrLine) diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c index 23368cec7ee84..16498f5fba64d 100644 --- a/drivers/tty/pty.c +++ b/drivers/tty/pty.c @@ -111,21 +111,11 @@ static void pty_unthrottle(struct tty_struct *tty) static int pty_write(struct tty_struct *tty, const unsigned char *buf, int c) { struct tty_struct *to = tty->link; - unsigned long flags; - if (tty->stopped) + if (tty->stopped || !c) return 0; - if (c > 0) { - spin_lock_irqsave(&to->port->lock, flags); - /* Stuff the data into the input queue of the other end */ - c = tty_insert_flip_string(to->port, buf, c); - spin_unlock_irqrestore(&to->port->lock, flags); - /* And shovel */ - if (c) - tty_flip_buffer_push(to->port); - } - return c; + return tty_insert_flip_string_and_push_buffer(to->port, buf, c); } /** diff --git a/drivers/tty/serial/lpc32xx_hs.c b/drivers/tty/serial/lpc32xx_hs.c index b5898c9320361..a9802308ff608 100644 --- a/drivers/tty/serial/lpc32xx_hs.c +++ b/drivers/tty/serial/lpc32xx_hs.c @@ -344,7 +344,7 @@ static irqreturn_t serial_lpc32xx_interrupt(int irq, void *dev_id) LPC32XX_HSUART_IIR(port->membase)); port->icount.overrun++; tty_insert_flip_char(tport, 0, TTY_OVERRUN); - tty_schedule_flip(tport); + tty_flip_buffer_push(tport); } /* Data received? */ diff --git a/drivers/tty/serial/mvebu-uart.c b/drivers/tty/serial/mvebu-uart.c index 34ff2181afd1a..e941f57de9533 100644 --- a/drivers/tty/serial/mvebu-uart.c +++ b/drivers/tty/serial/mvebu-uart.c @@ -443,13 +443,13 @@ static void mvebu_uart_shutdown(struct uart_port *port) } } -static int mvebu_uart_baud_rate_set(struct uart_port *port, unsigned int baud) +static unsigned int mvebu_uart_baud_rate_set(struct uart_port *port, unsigned int baud) { unsigned int d_divisor, m_divisor; u32 brdv, osamp; if (!port->uartclk) - return -EOPNOTSUPP; + return 0; /* * The baudrate is derived from the UART clock thanks to two divisors: @@ -473,7 +473,7 @@ static int mvebu_uart_baud_rate_set(struct uart_port *port, unsigned int baud) osamp &= ~OSAMP_DIVISORS_MASK; writel(osamp, port->membase + UART_OSAMP); - return 0; + return DIV_ROUND_CLOSEST(port->uartclk, d_divisor * m_divisor); } static void mvebu_uart_set_termios(struct uart_port *port, @@ -510,15 +510,11 @@ static void mvebu_uart_set_termios(struct uart_port *port, max_baud = 230400; baud = uart_get_baud_rate(port, termios, old, min_baud, max_baud); - if (mvebu_uart_baud_rate_set(port, baud)) { - /* No clock available, baudrate cannot be changed */ - if (old) - baud = uart_get_baud_rate(port, old, NULL, - min_baud, max_baud); - } else { - tty_termios_encode_baud_rate(termios, baud, baud); - uart_update_timeout(port, termios->c_cflag, baud); - } + baud = mvebu_uart_baud_rate_set(port, baud); + + /* In case baudrate cannot be changed, report previous old value */ + if (baud == 0 && old) + baud = tty_termios_baud_rate(old); /* Only the following flag changes are supported */ if (old) { @@ -529,6 +525,11 @@ static void mvebu_uart_set_termios(struct uart_port *port, termios->c_cflag |= CS8; } + if (baud != 0) { + tty_termios_encode_baud_rate(termios, baud, baud); + uart_update_timeout(port, termios->c_cflag, baud); + } + spin_unlock_irqrestore(&port->lock, flags); } diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c index 6c4a50addadd8..5bbc2e010b483 100644 --- a/drivers/tty/tty_buffer.c +++ b/drivers/tty/tty_buffer.c @@ -394,27 +394,6 @@ int __tty_insert_flip_char(struct tty_port *port, unsigned char ch, char flag) } EXPORT_SYMBOL(__tty_insert_flip_char); -/** - * tty_schedule_flip - push characters to ldisc - * @port: tty port to push from - * - * Takes any pending buffers and transfers their ownership to the - * ldisc side of the queue. It then schedules those characters for - * processing by the line discipline. - */ - -void tty_schedule_flip(struct tty_port *port) -{ - struct tty_bufhead *buf = &port->buf; - - /* paired w/ acquire in flush_to_ldisc(); ensures - * flush_to_ldisc() sees buffer data. - */ - smp_store_release(&buf->tail->commit, buf->tail->used); - queue_work(system_unbound_wq, &buf->work); -} -EXPORT_SYMBOL(tty_schedule_flip); - /** * tty_prepare_flip_string - make room for characters * @port: tty port @@ -544,6 +523,15 @@ static void flush_to_ldisc(struct work_struct *work) } +static inline void tty_flip_buffer_commit(struct tty_buffer *tail) +{ + /* + * Paired w/ acquire in flush_to_ldisc(); ensures flush_to_ldisc() sees + * buffer data. + */ + smp_store_release(&tail->commit, tail->used); +} + /** * tty_flip_buffer_push - terminal * @port: tty port to push @@ -557,10 +545,44 @@ static void flush_to_ldisc(struct work_struct *work) void tty_flip_buffer_push(struct tty_port *port) { - tty_schedule_flip(port); + struct tty_bufhead *buf = &port->buf; + + tty_flip_buffer_commit(buf->tail); + queue_work(system_unbound_wq, &buf->work); } EXPORT_SYMBOL(tty_flip_buffer_push); +/** + * tty_insert_flip_string_and_push_buffer - add characters to the tty buffer and + * push + * @port: tty port + * @chars: characters + * @size: size + * + * The function combines tty_insert_flip_string() and tty_flip_buffer_push() + * with the exception of properly holding the @port->lock. + * + * To be used only internally (by pty currently). + * + * Returns: the number added. + */ +int tty_insert_flip_string_and_push_buffer(struct tty_port *port, + const unsigned char *chars, size_t size) +{ + struct tty_bufhead *buf = &port->buf; + unsigned long flags; + + spin_lock_irqsave(&port->lock, flags); + size = tty_insert_flip_string(port, chars, size); + if (size) + tty_flip_buffer_commit(buf->tail); + spin_unlock_irqrestore(&port->lock, flags); + + queue_work(system_unbound_wq, &buf->work); + + return size; +} + /** * tty_buffer_init - prepare a tty buffer structure * @port: tty port to initialise diff --git a/drivers/tty/vt/keyboard.c b/drivers/tty/vt/keyboard.c index 78acc270e39ac..aa0026a9839c8 100644 --- a/drivers/tty/vt/keyboard.c +++ b/drivers/tty/vt/keyboard.c @@ -311,7 +311,7 @@ int kbd_rate(struct kbd_repeat *rpt) static void put_queue(struct vc_data *vc, int ch) { tty_insert_flip_char(&vc->port, ch, 0); - tty_schedule_flip(&vc->port); + tty_flip_buffer_push(&vc->port); } static void puts_queue(struct vc_data *vc, char *cp) @@ -320,7 +320,7 @@ static void puts_queue(struct vc_data *vc, char *cp) tty_insert_flip_char(&vc->port, *cp, 0); cp++; } - tty_schedule_flip(&vc->port); + tty_flip_buffer_push(&vc->port); } static void applkey(struct vc_data *vc, int key, char mode) @@ -565,7 +565,7 @@ static void fn_inc_console(struct vc_data *vc) static void fn_send_intr(struct vc_data *vc) { tty_insert_flip_char(&vc->port, 0, TTY_BREAK); - tty_schedule_flip(&vc->port); + tty_flip_buffer_push(&vc->port); } static void fn_scroll_forw(struct vc_data *vc) diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index f043fd7e0f924..2ebe73b116dc7 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -1834,7 +1834,7 @@ static void csi_m(struct vc_data *vc) static void respond_string(const char *p, size_t len, struct tty_port *port) { tty_insert_flip_string(port, p, len); - tty_schedule_flip(port); + tty_flip_buffer_push(port); } static void cursor_report(struct vc_data *vc, struct tty_struct *tty) diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c index f415c056ff8ab..54fee4087bf10 100644 --- a/drivers/xen/gntdev.c +++ b/drivers/xen/gntdev.c @@ -401,7 +401,8 @@ static void __unmap_grant_pages_done(int result, unsigned int offset = data->unmap_ops - map->unmap_ops; for (i = 0; i < data->count; i++) { - WARN_ON(map->unmap_ops[offset+i].status); + WARN_ON(map->unmap_ops[offset+i].status && + map->unmap_ops[offset+i].handle != -1); pr_debug("unmap handle=%d st=%d\n", map->unmap_ops[offset+i].handle, map->unmap_ops[offset+i].status); diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c index 2ce96a9ce63c0..eaa28d654e9f0 100644 --- a/fs/dlm/lock.c +++ b/fs/dlm/lock.c @@ -4067,13 +4067,14 @@ static void send_repeat_remove(struct dlm_ls *ls, char *ms_name, int len) rv = _create_message(ls, sizeof(struct dlm_message) + len, dir_nodeid, DLM_MSG_REMOVE, &ms, &mh); if (rv) - return; + goto out; memcpy(ms->m_extra, name, len); ms->m_hash = hash; send_message(mh, ms); +out: spin_lock(&ls->ls_remove_spin); ls->ls_remove_len = 0; memset(ls->ls_remove_name, 0, DLM_RESNAME_MAXLEN); diff --git a/fs/io_uring.c b/fs/io_uring.c index 023c3eb34dcca..a952288b2ab8e 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1325,7 +1325,7 @@ static void io_req_clean_work(struct io_kiocb *req) */ static bool io_identity_cow(struct io_kiocb *req) { - struct io_uring_task *tctx = current->io_uring; + struct io_uring_task *tctx = req->task->io_uring; const struct cred *creds = NULL; struct io_identity *id; diff --git a/include/linux/bitfield.h b/include/linux/bitfield.h index 4e035aca6f7e6..6093fa6db2600 100644 --- a/include/linux/bitfield.h +++ b/include/linux/bitfield.h @@ -41,6 +41,22 @@ #define __bf_shf(x) (__builtin_ffsll(x) - 1) +#define __scalar_type_to_unsigned_cases(type) \ + unsigned type: (unsigned type)0, \ + signed type: (unsigned type)0 + +#define __unsigned_scalar_typeof(x) typeof( \ + _Generic((x), \ + char: (unsigned char)0, \ + __scalar_type_to_unsigned_cases(char), \ + __scalar_type_to_unsigned_cases(short), \ + __scalar_type_to_unsigned_cases(int), \ + __scalar_type_to_unsigned_cases(long), \ + __scalar_type_to_unsigned_cases(long long), \ + default: (x))) + +#define __bf_cast_unsigned(type, x) ((__unsigned_scalar_typeof(type))(x)) + #define __BF_FIELD_CHECK(_mask, _reg, _val, _pfx) \ ({ \ BUILD_BUG_ON_MSG(!__builtin_constant_p(_mask), \ @@ -49,7 +65,8 @@ BUILD_BUG_ON_MSG(__builtin_constant_p(_val) ? \ ~((_mask) >> __bf_shf(_mask)) & (_val) : 0, \ _pfx "value too large for the field"); \ - BUILD_BUG_ON_MSG((_mask) > (typeof(_reg))~0ull, \ + BUILD_BUG_ON_MSG(__bf_cast_unsigned(_mask, _mask) > \ + __bf_cast_unsigned(_reg, ~0ull), \ _pfx "type of reg too small for mask"); \ __BUILD_BUG_ON_NOT_POWER_OF_2((_mask) + \ (1ULL << __bf_shf(_mask))); \ diff --git a/include/linux/tty_flip.h b/include/linux/tty_flip.h index 767f62086bd9b..c326bfdb5ec2c 100644 --- a/include/linux/tty_flip.h +++ b/include/linux/tty_flip.h @@ -12,7 +12,6 @@ extern int tty_insert_flip_string_fixed_flag(struct tty_port *port, extern int tty_prepare_flip_string(struct tty_port *port, unsigned char **chars, size_t size); extern void tty_flip_buffer_push(struct tty_port *port); -void tty_schedule_flip(struct tty_port *port); int __tty_insert_flip_char(struct tty_port *port, unsigned char ch, char flag); static inline int tty_insert_flip_char(struct tty_port *port, @@ -40,4 +39,7 @@ static inline int tty_insert_flip_string(struct tty_port *port, extern void tty_buffer_lock_exclusive(struct tty_port *port); extern void tty_buffer_unlock_exclusive(struct tty_port *port); +int tty_insert_flip_string_and_push_buffer(struct tty_port *port, + const unsigned char *chars, size_t cnt); + #endif /* _LINUX_TTY_FLIP_H */ diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index 3fecc4a411a13..355835639ae58 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -422,6 +422,71 @@ out: return NULL; } +/* Shall not be called with lock_sock held */ +static inline struct sk_buff *bt_skb_sendmsg(struct sock *sk, + struct msghdr *msg, + size_t len, size_t mtu, + size_t headroom, size_t tailroom) +{ + struct sk_buff *skb; + size_t size = min_t(size_t, len, mtu); + int err; + + skb = bt_skb_send_alloc(sk, size + headroom + tailroom, + msg->msg_flags & MSG_DONTWAIT, &err); + if (!skb) + return ERR_PTR(err); + + skb_reserve(skb, headroom); + skb_tailroom_reserve(skb, mtu, tailroom); + + if (!copy_from_iter_full(skb_put(skb, size), size, &msg->msg_iter)) { + kfree_skb(skb); + return ERR_PTR(-EFAULT); + } + + skb->priority = sk->sk_priority; + + return skb; +} + +/* Similar to bt_skb_sendmsg but can split the msg into multiple fragments + * accourding to the MTU. + */ +static inline struct sk_buff *bt_skb_sendmmsg(struct sock *sk, + struct msghdr *msg, + size_t len, size_t mtu, + size_t headroom, size_t tailroom) +{ + struct sk_buff *skb, **frag; + + skb = bt_skb_sendmsg(sk, msg, len, mtu, headroom, tailroom); + if (IS_ERR_OR_NULL(skb)) + return skb; + + len -= skb->len; + if (!len) + return skb; + + /* Add remaining data over MTU as continuation fragments */ + frag = &skb_shinfo(skb)->frag_list; + while (len) { + struct sk_buff *tmp; + + tmp = bt_skb_sendmsg(sk, msg, len, mtu, headroom, tailroom); + if (IS_ERR(tmp)) { + return skb; + } + + len -= tmp->len; + + *frag = tmp; + frag = &(*frag)->next; + } + + return skb; +} + int bt_to_errno(u16 code); void hci_sock_set_flag(struct sock *sk, int nr); diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 89163ef8cf4be..3c039d4b0e480 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -107,7 +107,8 @@ static inline struct inet_request_sock *inet_rsk(const struct request_sock *sk) static inline u32 inet_request_mark(const struct sock *sk, struct sk_buff *skb) { - if (!sk->sk_mark && sock_net(sk)->ipv4.sysctl_tcp_fwmark_accept) + if (!sk->sk_mark && + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fwmark_accept)) return skb->mark; return sk->sk_mark; @@ -369,7 +370,7 @@ static inline bool inet_get_convert_csum(struct sock *sk) static inline bool inet_can_nonlocal_bind(struct net *net, struct inet_sock *inet) { - return net->ipv4.sysctl_ip_nonlocal_bind || + return READ_ONCE(net->ipv4.sysctl_ip_nonlocal_bind) || inet->freebind || inet->transparent; } diff --git a/include/net/ip.h b/include/net/ip.h index 76aaa7eb5b823..c5822d7824cd0 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -352,7 +352,7 @@ static inline bool sysctl_dev_name_is_allowed(const char *name) static inline bool inet_port_requires_bind_service(struct net *net, unsigned short port) { - return port < net->ipv4.sysctl_ip_prot_sock; + return port < READ_ONCE(net->ipv4.sysctl_ip_prot_sock); } #else @@ -379,7 +379,7 @@ void ipfrag_init(void); void ip_static_sysctl_init(void); #define IP4_REPLY_MARK(net, mark) \ - ((net)->ipv4.sysctl_fwmark_reflect ? (mark) : 0) + (READ_ONCE((net)->ipv4.sysctl_fwmark_reflect) ? (mark) : 0) static inline bool ip_is_fragment(const struct iphdr *iph) { @@ -440,7 +440,7 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst, struct net *net = dev_net(dst->dev); unsigned int mtu; - if (net->ipv4.sysctl_ip_fwd_use_pmtu || + if (READ_ONCE(net->ipv4.sysctl_ip_fwd_use_pmtu) || ip_mtu_locked(dst) || !forwarding) return dst_mtu(dst); diff --git a/include/net/tcp.h b/include/net/tcp.h index 2a28e09255735..44bfb22069c1f 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1380,8 +1380,8 @@ static inline void tcp_slow_start_after_idle_check(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); s32 delta; - if (!sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle || tp->packets_out || - ca_ops->cong_control) + if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle) || + tp->packets_out || ca_ops->cong_control) return; delta = tcp_jiffies32 - tp->lsndtime; if (delta > inet_csk(sk)->icsk_rto) @@ -1447,21 +1447,24 @@ static inline int keepalive_intvl_when(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); - return tp->keepalive_intvl ? : net->ipv4.sysctl_tcp_keepalive_intvl; + return tp->keepalive_intvl ? : + READ_ONCE(net->ipv4.sysctl_tcp_keepalive_intvl); } static inline int keepalive_time_when(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); - return tp->keepalive_time ? : net->ipv4.sysctl_tcp_keepalive_time; + return tp->keepalive_time ? : + READ_ONCE(net->ipv4.sysctl_tcp_keepalive_time); } static inline int keepalive_probes(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); - return tp->keepalive_probes ? : net->ipv4.sysctl_tcp_keepalive_probes; + return tp->keepalive_probes ? : + READ_ONCE(net->ipv4.sysctl_tcp_keepalive_probes); } static inline u32 keepalive_time_elapsed(const struct tcp_sock *tp) @@ -1474,7 +1477,8 @@ static inline u32 keepalive_time_elapsed(const struct tcp_sock *tp) static inline int tcp_fin_time(const struct sock *sk) { - int fin_timeout = tcp_sk(sk)->linger2 ? : sock_net(sk)->ipv4.sysctl_tcp_fin_timeout; + int fin_timeout = tcp_sk(sk)->linger2 ? : + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fin_timeout); const int rto = inet_csk(sk)->icsk_rto; if (fin_timeout < (rto << 2) - (rto >> 1)) @@ -1969,7 +1973,7 @@ void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr); static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); - return tp->notsent_lowat ?: net->ipv4.sysctl_tcp_notsent_lowat; + return tp->notsent_lowat ?: READ_ONCE(net->ipv4.sysctl_tcp_notsent_lowat); } /* @wake is one when sk_stream_write_space() calls us. diff --git a/include/net/udp.h b/include/net/udp.h index 4017f257628f3..010bc324f860b 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -259,7 +259,7 @@ static inline bool udp_sk_bound_dev_eq(struct net *net, int bound_dev_if, int dif, int sdif) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) - return inet_bound_dev_eq(!!net->ipv4.sysctl_udp_l3mdev_accept, + return inet_bound_dev_eq(!!READ_ONCE(net->ipv4.sysctl_udp_l3mdev_accept), bound_dev_if, dif, sdif); #else return inet_bound_dev_eq(true, bound_dev_if, dif, sdif); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 845a4c0524332..fd2aa6b9909ec 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -66,11 +66,13 @@ void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, uns { u8 *ptr = NULL; - if (k >= SKF_NET_OFF) + if (k >= SKF_NET_OFF) { ptr = skb_network_header(skb) + k - SKF_NET_OFF; - else if (k >= SKF_LL_OFF) + } else if (k >= SKF_LL_OFF) { + if (unlikely(!skb_mac_header_was_set(skb))) + return NULL; ptr = skb_mac_header(skb) + k - SKF_LL_OFF; - + } if (ptr >= skb->head && ptr + size <= skb_tail_pointer(skb)) return ptr; diff --git a/kernel/events/core.c b/kernel/events/core.c index 8ba155a7b59ed..0e01216f4e5af 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -6228,10 +6228,10 @@ again: if (!atomic_inc_not_zero(&event->rb->mmap_count)) { /* - * Raced against perf_mmap_close() through - * perf_event_set_output(). Try again, hope for better - * luck. + * Raced against perf_mmap_close(); remove the + * event and try again. */ + ring_buffer_attach(event, NULL); mutex_unlock(&event->mmap_mutex); goto again; } @@ -11587,14 +11587,25 @@ err_size: goto out; } +static void mutex_lock_double(struct mutex *a, struct mutex *b) +{ + if (b < a) + swap(a, b); + + mutex_lock(a); + mutex_lock_nested(b, SINGLE_DEPTH_NESTING); +} + static int perf_event_set_output(struct perf_event *event, struct perf_event *output_event) { struct perf_buffer *rb = NULL; int ret = -EINVAL; - if (!output_event) + if (!output_event) { + mutex_lock(&event->mmap_mutex); goto set; + } /* don't allow circular references */ if (event == output_event) @@ -11632,8 +11643,15 @@ perf_event_set_output(struct perf_event *event, struct perf_event *output_event) event->pmu != output_event->pmu) goto out; + /* + * Hold both mmap_mutex to serialize against perf_mmap_close(). Since + * output_event is already on rb->event_list, and the list iteration + * restarts after every removal, it is guaranteed this new event is + * observed *OR* if output_event is already removed, it's guaranteed we + * observe !rb->mmap_count. + */ + mutex_lock_double(&event->mmap_mutex, &output_event->mmap_mutex); set: - mutex_lock(&event->mmap_mutex); /* Can't redirect output if we've got an active mmap() */ if (atomic_read(&event->mmap_count)) goto unlock; @@ -11643,6 +11661,12 @@ set: rb = ring_buffer_get(output_event); if (!rb) goto unlock; + + /* did we race against perf_mmap_close() */ + if (!atomic_read(&rb->mmap_count)) { + ring_buffer_put(rb); + goto unlock; + } } ring_buffer_attach(event, rb); @@ -11650,20 +11674,13 @@ set: ret = 0; unlock: mutex_unlock(&event->mmap_mutex); + if (output_event) + mutex_unlock(&output_event->mmap_mutex); out: return ret; } -static void mutex_lock_double(struct mutex *a, struct mutex *b) -{ - if (b < a) - swap(a, b); - - mutex_lock(a); - mutex_lock_nested(b, SINGLE_DEPTH_NESTING); -} - static int perf_event_set_clock(struct perf_event *event, clockid_t clk_id) { bool nmi_safe = false; diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index a3ae00c348a8b..933706106b983 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -1563,7 +1563,10 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) * the throttle. */ p->dl.dl_throttled = 0; - BUG_ON(!is_dl_boosted(&p->dl) || flags != ENQUEUE_REPLENISH); + if (!(flags & ENQUEUE_REPLENISH)) + printk_deferred_once("sched: DL de-boosted task PID %d: REPLENISH flag missing\n", + task_pid_nr(p)); + return; } diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c index 249ed32591449..e5d22af43fa0b 100644 --- a/kernel/watch_queue.c +++ b/kernel/watch_queue.c @@ -34,6 +34,27 @@ MODULE_LICENSE("GPL"); #define WATCH_QUEUE_NOTE_SIZE 128 #define WATCH_QUEUE_NOTES_PER_PAGE (PAGE_SIZE / WATCH_QUEUE_NOTE_SIZE) +/* + * This must be called under the RCU read-lock, which makes + * sure that the wqueue still exists. It can then take the lock, + * and check that the wqueue hasn't been destroyed, which in + * turn makes sure that the notification pipe still exists. + */ +static inline bool lock_wqueue(struct watch_queue *wqueue) +{ + spin_lock_bh(&wqueue->lock); + if (unlikely(wqueue->defunct)) { + spin_unlock_bh(&wqueue->lock); + return false; + } + return true; +} + +static inline void unlock_wqueue(struct watch_queue *wqueue) +{ + spin_unlock_bh(&wqueue->lock); +} + static void watch_queue_pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { @@ -69,6 +90,10 @@ static const struct pipe_buf_operations watch_queue_pipe_buf_ops = { /* * Post a notification to a watch queue. + * + * Must be called with the RCU lock for reading, and the + * watch_queue lock held, which guarantees that the pipe + * hasn't been released. */ static bool post_one_notification(struct watch_queue *wqueue, struct watch_notification *n) @@ -85,9 +110,6 @@ static bool post_one_notification(struct watch_queue *wqueue, spin_lock_irq(&pipe->rd_wait.lock); - if (wqueue->defunct) - goto out; - mask = pipe->ring_size - 1; head = pipe->head; tail = pipe->tail; @@ -203,7 +225,10 @@ void __post_watch_notification(struct watch_list *wlist, if (security_post_notification(watch->cred, cred, n) < 0) continue; - post_one_notification(wqueue, n); + if (lock_wqueue(wqueue)) { + post_one_notification(wqueue, n); + unlock_wqueue(wqueue); + } } rcu_read_unlock(); @@ -465,11 +490,12 @@ int add_watch_to_object(struct watch *watch, struct watch_list *wlist) return -EAGAIN; } - spin_lock_bh(&wqueue->lock); - kref_get(&wqueue->usage); - kref_get(&watch->usage); - hlist_add_head(&watch->queue_node, &wqueue->watches); - spin_unlock_bh(&wqueue->lock); + if (lock_wqueue(wqueue)) { + kref_get(&wqueue->usage); + kref_get(&watch->usage); + hlist_add_head(&watch->queue_node, &wqueue->watches); + unlock_wqueue(wqueue); + } hlist_add_head(&watch->list_node, &wlist->watchers); return 0; @@ -523,20 +549,15 @@ found: wqueue = rcu_dereference(watch->queue); - /* We don't need the watch list lock for the next bit as RCU is - * protecting *wqueue from deallocation. - */ - if (wqueue) { + if (lock_wqueue(wqueue)) { post_one_notification(wqueue, &n.watch); - spin_lock_bh(&wqueue->lock); - if (!hlist_unhashed(&watch->queue_node)) { hlist_del_init_rcu(&watch->queue_node); put_watch(watch); } - spin_unlock_bh(&wqueue->lock); + unlock_wqueue(wqueue); } if (wlist->release_watch) { diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 7315b978e834b..f9f47449e8dda 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -374,7 +374,7 @@ static void mpol_rebind_preferred(struct mempolicy *pol, */ static void mpol_rebind_policy(struct mempolicy *pol, const nodemask_t *newmask) { - if (!pol) + if (!pol || pol->mode == MPOL_LOCAL) return; if (!mpol_store_user_nodemask(pol) && !(pol->flags & MPOL_F_LOCAL) && nodes_equal(pol->w.cpuset_mems_allowed, *newmask)) diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index d12c9a8a9953e..64a94c9812da1 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -278,9 +278,7 @@ static int register_vlan_device(struct net_device *real_dev, u16 vlan_id) return 0; out_free_newdev: - if (new_dev->reg_state == NETREG_UNINITIALIZED || - new_dev->reg_state == NETREG_UNREGISTERED) - free_netdev(new_dev); + free_netdev(new_dev); return err; } diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index f2bacb464ccf3..7324764384b67 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -549,22 +549,58 @@ struct rfcomm_dlc *rfcomm_dlc_exists(bdaddr_t *src, bdaddr_t *dst, u8 channel) return dlc; } +static int rfcomm_dlc_send_frag(struct rfcomm_dlc *d, struct sk_buff *frag) +{ + int len = frag->len; + + BT_DBG("dlc %p mtu %d len %d", d, d->mtu, len); + + if (len > d->mtu) + return -EINVAL; + + rfcomm_make_uih(frag, d->addr); + __skb_queue_tail(&d->tx_queue, frag); + + return len; +} + int rfcomm_dlc_send(struct rfcomm_dlc *d, struct sk_buff *skb) { - int len = skb->len; + unsigned long flags; + struct sk_buff *frag, *next; + int len; if (d->state != BT_CONNECTED) return -ENOTCONN; - BT_DBG("dlc %p mtu %d len %d", d, d->mtu, len); + frag = skb_shinfo(skb)->frag_list; + skb_shinfo(skb)->frag_list = NULL; - if (len > d->mtu) - return -EINVAL; + /* Queue all fragments atomically. */ + spin_lock_irqsave(&d->tx_queue.lock, flags); - rfcomm_make_uih(skb, d->addr); - skb_queue_tail(&d->tx_queue, skb); + len = rfcomm_dlc_send_frag(d, skb); + if (len < 0 || !frag) + goto unlock; + + for (; frag; frag = next) { + int ret; + + next = frag->next; + + ret = rfcomm_dlc_send_frag(d, frag); + if (ret < 0) { + kfree_skb(frag); + goto unlock; + } + + len += ret; + } + +unlock: + spin_unlock_irqrestore(&d->tx_queue.lock, flags); - if (!test_bit(RFCOMM_TX_THROTTLED, &d->flags)) + if (len > 0 && !test_bit(RFCOMM_TX_THROTTLED, &d->flags)) rfcomm_schedule(); return len; } diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index ae6f807305617..4cf1fa9900cae 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -575,46 +575,20 @@ static int rfcomm_sock_sendmsg(struct socket *sock, struct msghdr *msg, lock_sock(sk); sent = bt_sock_wait_ready(sk, msg->msg_flags); - if (sent) - goto done; - - while (len) { - size_t size = min_t(size_t, len, d->mtu); - int err; - - skb = sock_alloc_send_skb(sk, size + RFCOMM_SKB_RESERVE, - msg->msg_flags & MSG_DONTWAIT, &err); - if (!skb) { - if (sent == 0) - sent = err; - break; - } - skb_reserve(skb, RFCOMM_SKB_HEAD_RESERVE); - - err = memcpy_from_msg(skb_put(skb, size), msg, size); - if (err) { - kfree_skb(skb); - if (sent == 0) - sent = err; - break; - } - skb->priority = sk->sk_priority; + release_sock(sk); - err = rfcomm_dlc_send(d, skb); - if (err < 0) { - kfree_skb(skb); - if (sent == 0) - sent = err; - break; - } + if (sent) + return sent; - sent += size; - len -= size; - } + skb = bt_skb_sendmmsg(sk, msg, len, d->mtu, RFCOMM_SKB_HEAD_RESERVE, + RFCOMM_SKB_TAIL_RESERVE); + if (IS_ERR(skb)) + return PTR_ERR(skb); -done: - release_sock(sk); + sent = rfcomm_dlc_send(d, skb); + if (sent < 0) + kfree_skb(skb); return sent; } diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index df254c7de2dd6..8244d3ae185bf 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -280,12 +280,10 @@ static int sco_connect(struct hci_dev *hdev, struct sock *sk) return err; } -static int sco_send_frame(struct sock *sk, void *buf, int len, - unsigned int msg_flags) +static int sco_send_frame(struct sock *sk, struct sk_buff *skb) { struct sco_conn *conn = sco_pi(sk)->conn; - struct sk_buff *skb; - int err; + int len = skb->len; /* Check outgoing MTU */ if (len > conn->mtu) @@ -293,11 +291,6 @@ static int sco_send_frame(struct sock *sk, void *buf, int len, BT_DBG("sk %p len %d", sk, len); - skb = bt_skb_send_alloc(sk, len, msg_flags & MSG_DONTWAIT, &err); - if (!skb) - return err; - - memcpy(skb_put(skb, len), buf, len); hci_send_sco(conn->hcon, skb); return len; @@ -727,7 +720,7 @@ static int sco_sock_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; - void *buf; + struct sk_buff *skb; int err; BT_DBG("sock %p, sk %p", sock, sk); @@ -739,24 +732,21 @@ static int sco_sock_sendmsg(struct socket *sock, struct msghdr *msg, if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; - buf = kmalloc(len, GFP_KERNEL); - if (!buf) - return -ENOMEM; - - if (memcpy_from_msg(buf, msg, len)) { - kfree(buf); - return -EFAULT; - } + skb = bt_skb_sendmsg(sk, msg, len, len, 0, 0); + if (IS_ERR(skb)) + return PTR_ERR(skb); lock_sock(sk); if (sk->sk_state == BT_CONNECTED) - err = sco_send_frame(sk, buf, len, msg->msg_flags); + err = sco_send_frame(sk, skb); else err = -ENOTCONN; release_sock(sk); - kfree(buf); + + if (err < 0) + kfree_skb(skb); return err; } diff --git a/net/core/dev.c b/net/core/dev.c index af52050b0f383..637bc576fbd26 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5750,7 +5750,7 @@ static void flush_all_backlogs(void) } /* we can have in flight packet[s] on the cpus we are not flushing, - * synchronize_net() in rollback_registered_many() will take care of + * synchronize_net() in unregister_netdevice_many() will take care of * them */ for_each_cpu(cpu, &flush_cpus) @@ -9508,106 +9508,6 @@ static void net_set_todo(struct net_device *dev) dev_net(dev)->dev_unreg_count++; } -static void rollback_registered_many(struct list_head *head) -{ - struct net_device *dev, *tmp; - LIST_HEAD(close_head); - - BUG_ON(dev_boot_phase); - ASSERT_RTNL(); - - list_for_each_entry_safe(dev, tmp, head, unreg_list) { - /* Some devices call without registering - * for initialization unwind. Remove those - * devices and proceed with the remaining. - */ - if (dev->reg_state == NETREG_UNINITIALIZED) { - pr_debug("unregister_netdevice: device %s/%p never was registered\n", - dev->name, dev); - - WARN_ON(1); - list_del(&dev->unreg_list); - continue; - } - dev->dismantle = true; - BUG_ON(dev->reg_state != NETREG_REGISTERED); - } - - /* If device is running, close it first. */ - list_for_each_entry(dev, head, unreg_list) - list_add_tail(&dev->close_list, &close_head); - dev_close_many(&close_head, true); - - list_for_each_entry(dev, head, unreg_list) { - /* And unlink it from device chain. */ - unlist_netdevice(dev); - - dev->reg_state = NETREG_UNREGISTERING; - } - flush_all_backlogs(); - - synchronize_net(); - - list_for_each_entry(dev, head, unreg_list) { - struct sk_buff *skb = NULL; - - /* Shutdown queueing discipline. */ - dev_shutdown(dev); - - dev_xdp_uninstall(dev); - - /* Notify protocols, that we are about to destroy - * this device. They should clean all the things. - */ - call_netdevice_notifiers(NETDEV_UNREGISTER, dev); - - if (!dev->rtnl_link_ops || - dev->rtnl_link_state == RTNL_LINK_INITIALIZED) - skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, 0, - GFP_KERNEL, NULL, 0); - - /* - * Flush the unicast and multicast chains - */ - dev_uc_flush(dev); - dev_mc_flush(dev); - - netdev_name_node_alt_flush(dev); - netdev_name_node_free(dev->name_node); - - if (dev->netdev_ops->ndo_uninit) - dev->netdev_ops->ndo_uninit(dev); - - if (skb) - rtmsg_ifinfo_send(skb, dev, GFP_KERNEL); - - /* Notifier chain MUST detach us all upper devices. */ - WARN_ON(netdev_has_any_upper_dev(dev)); - WARN_ON(netdev_has_any_lower_dev(dev)); - - /* Remove entries from kobject tree */ - netdev_unregister_kobject(dev); -#ifdef CONFIG_XPS - /* Remove XPS queueing entries */ - netif_reset_xps_queues_gt(dev, 0); -#endif - } - - synchronize_net(); - - list_for_each_entry(dev, head, unreg_list) - dev_put(dev); -} - -static void rollback_registered(struct net_device *dev) -{ - LIST_HEAD(single); - - list_add(&dev->unreg_list, &single); - rollback_registered_many(&single); - list_del(&single); -} - static netdev_features_t netdev_sync_upper_features(struct net_device *lower, struct net_device *upper, netdev_features_t features) { @@ -10144,17 +10044,10 @@ int register_netdevice(struct net_device *dev) ret = call_netdevice_notifiers(NETDEV_REGISTER, dev); ret = notifier_to_errno(ret); if (ret) { - rollback_registered(dev); - rcu_barrier(); - - dev->reg_state = NETREG_UNREGISTERED; - /* We should put the kobject that hold in - * netdev_unregister_kobject(), otherwise - * the net device cannot be freed when - * driver calls free_netdev(), because the - * kobject is being hold. - */ - kobject_put(&dev->dev.kobj); + /* Expect explicit free_netdev() on failure */ + dev->needs_free_netdev = false; + unregister_netdevice_queue(dev, NULL); + goto out; } /* * Prevent userspace races by waiting until the network @@ -10683,6 +10576,17 @@ void free_netdev(struct net_device *dev) struct napi_struct *p, *n; might_sleep(); + + /* When called immediately after register_netdevice() failed the unwind + * handling may still be dismantling the device. Handle that case by + * deferring the free. + */ + if (dev->reg_state == NETREG_UNREGISTERING) { + ASSERT_RTNL(); + dev->needs_free_netdev = true; + return; + } + netif_free_tx_queues(dev); netif_free_rx_queues(dev); @@ -10749,9 +10653,10 @@ void unregister_netdevice_queue(struct net_device *dev, struct list_head *head) if (head) { list_move_tail(&dev->unreg_list, head); } else { - rollback_registered(dev); - /* Finish processing unregister after unlock */ - net_set_todo(dev); + LIST_HEAD(single); + + list_add(&dev->unreg_list, &single); + unregister_netdevice_many(&single); } } EXPORT_SYMBOL(unregister_netdevice_queue); @@ -10765,14 +10670,100 @@ EXPORT_SYMBOL(unregister_netdevice_queue); */ void unregister_netdevice_many(struct list_head *head) { - struct net_device *dev; + struct net_device *dev, *tmp; + LIST_HEAD(close_head); + + BUG_ON(dev_boot_phase); + ASSERT_RTNL(); - if (!list_empty(head)) { - rollback_registered_many(head); - list_for_each_entry(dev, head, unreg_list) - net_set_todo(dev); - list_del(head); + if (list_empty(head)) + return; + + list_for_each_entry_safe(dev, tmp, head, unreg_list) { + /* Some devices call without registering + * for initialization unwind. Remove those + * devices and proceed with the remaining. + */ + if (dev->reg_state == NETREG_UNINITIALIZED) { + pr_debug("unregister_netdevice: device %s/%p never was registered\n", + dev->name, dev); + + WARN_ON(1); + list_del(&dev->unreg_list); + continue; + } + dev->dismantle = true; + BUG_ON(dev->reg_state != NETREG_REGISTERED); } + + /* If device is running, close it first. */ + list_for_each_entry(dev, head, unreg_list) + list_add_tail(&dev->close_list, &close_head); + dev_close_many(&close_head, true); + + list_for_each_entry(dev, head, unreg_list) { + /* And unlink it from device chain. */ + unlist_netdevice(dev); + + dev->reg_state = NETREG_UNREGISTERING; + } + flush_all_backlogs(); + + synchronize_net(); + + list_for_each_entry(dev, head, unreg_list) { + struct sk_buff *skb = NULL; + + /* Shutdown queueing discipline. */ + dev_shutdown(dev); + + dev_xdp_uninstall(dev); + + /* Notify protocols, that we are about to destroy + * this device. They should clean all the things. + */ + call_netdevice_notifiers(NETDEV_UNREGISTER, dev); + + if (!dev->rtnl_link_ops || + dev->rtnl_link_state == RTNL_LINK_INITIALIZED) + skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, 0, + GFP_KERNEL, NULL, 0); + + /* + * Flush the unicast and multicast chains + */ + dev_uc_flush(dev); + dev_mc_flush(dev); + + netdev_name_node_alt_flush(dev); + netdev_name_node_free(dev->name_node); + + if (dev->netdev_ops->ndo_uninit) + dev->netdev_ops->ndo_uninit(dev); + + if (skb) + rtmsg_ifinfo_send(skb, dev, GFP_KERNEL); + + /* Notifier chain MUST detach us all upper devices. */ + WARN_ON(netdev_has_any_upper_dev(dev)); + WARN_ON(netdev_has_any_lower_dev(dev)); + + /* Remove entries from kobject tree */ + netdev_unregister_kobject(dev); +#ifdef CONFIG_XPS + /* Remove XPS queueing entries */ + netif_reset_xps_queues_gt(dev, 0); +#endif + } + + synchronize_net(); + + list_for_each_entry(dev, head, unreg_list) { + dev_put(dev); + net_set_todo(dev); + } + + list_del(head); } EXPORT_SYMBOL(unregister_netdevice_many); diff --git a/net/core/filter.c b/net/core/filter.c index 34ae30503ac4f..e2b491665775f 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -6507,7 +6507,7 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN) return -EINVAL; - if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies) + if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies)) return -EINVAL; if (!th->ack || th->rst || th->syn) @@ -6582,7 +6582,7 @@ BPF_CALL_5(bpf_tcp_gen_syncookie, struct sock *, sk, void *, iph, u32, iph_len, if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN) return -EINVAL; - if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies) + if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies)) return -ENOENT; if (!th->syn || th->ack || th->fin || th->rst) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 873081cda9507..3c9c2d6e3b92e 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3442,26 +3442,15 @@ replay: dev->ifindex = ifm->ifi_index; - if (ops->newlink) { + if (ops->newlink) err = ops->newlink(link_net ? : net, dev, tb, data, extack); - /* Drivers should call free_netdev() in ->destructor - * and unregister it on failure after registration - * so that device could be finally freed in rtnl_unlock. - */ - if (err < 0) { - /* If device is not registered at all, free it now */ - if (dev->reg_state == NETREG_UNINITIALIZED || - dev->reg_state == NETREG_UNREGISTERED) - free_netdev(dev); - goto out; - } - } else { + else err = register_netdevice(dev); - if (err < 0) { - free_netdev(dev); - goto out; - } + if (err < 0) { + free_netdev(dev); + goto out; } + err = rtnl_configure_link(dev, ifm); if (err < 0) goto out_unregister; diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index 7131cd1fb2ad5..189eea1372d5d 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -64,7 +64,7 @@ u32 secure_tcpv6_ts_off(const struct net *net, .daddr = *(struct in6_addr *)daddr, }; - if (net->ipv4.sysctl_tcp_timestamps != 1) + if (READ_ONCE(net->ipv4.sysctl_tcp_timestamps) != 1) return 0; ts_secret_init(); @@ -120,7 +120,7 @@ EXPORT_SYMBOL(secure_ipv6_port_ephemeral); #ifdef CONFIG_INET u32 secure_tcp_ts_off(const struct net *net, __be32 saddr, __be32 daddr) { - if (net->ipv4.sysctl_tcp_timestamps != 1) + if (READ_ONCE(net->ipv4.sysctl_tcp_timestamps) != 1) return 0; ts_secret_init(); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index e77283069c7b7..a733ce1a3f8f4 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -220,7 +220,7 @@ int inet_listen(struct socket *sock, int backlog) * because the socket was in TCP_LISTEN state previously but * was shutdown() rather than close(). */ - tcp_fastopen = sock_net(sk)->ipv4.sysctl_tcp_fastopen; + tcp_fastopen = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen); if ((tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) && (tcp_fastopen & TFO_SERVER_ENABLE) && !inet_csk(sk)->icsk_accept_queue.fastopenq.max_qlen) { @@ -338,7 +338,7 @@ lookup_protocol: inet->hdrincl = 1; } - if (net->ipv4.sysctl_ip_no_pmtu_disc) + if (READ_ONCE(net->ipv4.sysctl_ip_no_pmtu_disc)) inet->pmtudisc = IP_PMTUDISC_DONT; else inet->pmtudisc = IP_PMTUDISC_WANT; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 70c866308abea..3824b7abecf7e 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -2232,7 +2232,7 @@ void fib_select_multipath(struct fib_result *res, int hash) } change_nexthops(fi) { - if (net->ipv4.sysctl_fib_multipath_use_neigh) { + if (READ_ONCE(net->ipv4.sysctl_fib_multipath_use_neigh)) { if (!fib_good_nh(nexthop_nh)) continue; if (!first) { diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 0fa0da1d71f57..a1aacf5e75a6a 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -887,7 +887,7 @@ static bool icmp_unreach(struct sk_buff *skb) * values please see * Documentation/networking/ip-sysctl.rst */ - switch (net->ipv4.sysctl_ip_no_pmtu_disc) { + switch (READ_ONCE(net->ipv4.sysctl_ip_no_pmtu_disc)) { default: net_dbg_ratelimited("%pI4: fragmentation needed and DF set\n", &iph->daddr); diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 3817988a5a1d4..428cc3a4c36f1 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -467,7 +467,8 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, if (pmc->multiaddr == IGMP_ALL_HOSTS) return skb; - if (ipv4_is_local_multicast(pmc->multiaddr) && !net->ipv4.sysctl_igmp_llm_reports) + if (ipv4_is_local_multicast(pmc->multiaddr) && + !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return skb; mtu = READ_ONCE(dev->mtu); @@ -593,7 +594,7 @@ static int igmpv3_send_report(struct in_device *in_dev, struct ip_mc_list *pmc) if (pmc->multiaddr == IGMP_ALL_HOSTS) continue; if (ipv4_is_local_multicast(pmc->multiaddr) && - !net->ipv4.sysctl_igmp_llm_reports) + !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) continue; spin_lock_bh(&pmc->lock); if (pmc->sfcount[MCAST_EXCLUDE]) @@ -736,7 +737,8 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, if (type == IGMPV3_HOST_MEMBERSHIP_REPORT) return igmpv3_send_report(in_dev, pmc); - if (ipv4_is_local_multicast(group) && !net->ipv4.sysctl_igmp_llm_reports) + if (ipv4_is_local_multicast(group) && + !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return 0; if (type == IGMP_HOST_LEAVE_MESSAGE) @@ -920,7 +922,8 @@ static bool igmp_heard_report(struct in_device *in_dev, __be32 group) if (group == IGMP_ALL_HOSTS) return false; - if (ipv4_is_local_multicast(group) && !net->ipv4.sysctl_igmp_llm_reports) + if (ipv4_is_local_multicast(group) && + !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return false; rcu_read_lock(); @@ -1045,7 +1048,7 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, if (im->multiaddr == IGMP_ALL_HOSTS) continue; if (ipv4_is_local_multicast(im->multiaddr) && - !net->ipv4.sysctl_igmp_llm_reports) + !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) continue; spin_lock_bh(&im->lock); if (im->tm_running) @@ -1296,7 +1299,8 @@ static void __igmp_group_dropped(struct ip_mc_list *im, gfp_t gfp) #ifdef CONFIG_IP_MULTICAST if (im->multiaddr == IGMP_ALL_HOSTS) return; - if (ipv4_is_local_multicast(im->multiaddr) && !net->ipv4.sysctl_igmp_llm_reports) + if (ipv4_is_local_multicast(im->multiaddr) && + !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return; reporter = im->reporter; @@ -1338,7 +1342,8 @@ static void igmp_group_added(struct ip_mc_list *im) #ifdef CONFIG_IP_MULTICAST if (im->multiaddr == IGMP_ALL_HOSTS) return; - if (ipv4_is_local_multicast(im->multiaddr) && !net->ipv4.sysctl_igmp_llm_reports) + if (ipv4_is_local_multicast(im->multiaddr) && + !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return; if (in_dev->dead) @@ -1642,7 +1647,7 @@ static void ip_mc_rejoin_groups(struct in_device *in_dev) if (im->multiaddr == IGMP_ALL_HOSTS) continue; if (ipv4_is_local_multicast(im->multiaddr) && - !net->ipv4.sysctl_igmp_llm_reports) + !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) continue; /* a failover is happening and switches @@ -2192,7 +2197,7 @@ static int __ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr, count++; } err = -ENOBUFS; - if (count >= net->ipv4.sysctl_igmp_max_memberships) + if (count >= READ_ONCE(net->ipv4.sysctl_igmp_max_memberships)) goto done; iml = sock_kmalloc(sk, sizeof(*iml), GFP_KERNEL); if (!iml) @@ -2379,7 +2384,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct } /* else, add a new source to the filter */ - if (psl && psl->sl_count >= net->ipv4.sysctl_igmp_max_msf) { + if (psl && psl->sl_count >= READ_ONCE(net->ipv4.sysctl_igmp_max_msf)) { err = -ENOBUFS; goto done; } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 7785a4775e58a..4d97133240036 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -251,7 +251,7 @@ next_port: goto other_half_scan; } - if (net->ipv4.sysctl_ip_autobind_reuse && !relax) { + if (READ_ONCE(net->ipv4.sysctl_ip_autobind_reuse) && !relax) { /* We still have a chance to connect to different destinations */ relax = true; goto ports_exhausted; diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 00ec819f949b5..29730edda220a 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -151,7 +151,7 @@ int ip_forward(struct sk_buff *skb) !skb_sec_path(skb)) ip_rt_send_redirect(skb); - if (net->ipv4.sysctl_ip_fwd_update_priority) + if (READ_ONCE(net->ipv4.sysctl_ip_fwd_update_priority)) skb->priority = rt_tos2priority(iph->tos); return NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD, diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index ec6036713e2c2..22507a6a3f71c 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -783,7 +783,7 @@ static int ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, int optlen) /* numsrc >= (4G-140)/128 overflow in 32 bits */ err = -ENOBUFS; if (gsf->gf_numsrc >= 0x1ffffff || - gsf->gf_numsrc > sock_net(sk)->ipv4.sysctl_igmp_max_msf) + gsf->gf_numsrc > READ_ONCE(sock_net(sk)->ipv4.sysctl_igmp_max_msf)) goto out_free_gsf; err = -EINVAL; @@ -832,7 +832,7 @@ static int compat_ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, /* numsrc >= (4G-140)/128 overflow in 32 bits */ err = -ENOBUFS; - if (n > sock_net(sk)->ipv4.sysctl_igmp_max_msf) + if (n > READ_ONCE(sock_net(sk)->ipv4.sysctl_igmp_max_msf)) goto out_free_gsf; err = set_mcast_msfilter(sk, gf32->gf_interface, n, gf32->gf_fmode, &gf32->gf_group, gf32->gf_slist); @@ -1242,7 +1242,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, int optname, } /* numsrc >= (1G-4) overflow in 32 bits */ if (msf->imsf_numsrc >= 0x3ffffffcU || - msf->imsf_numsrc > net->ipv4.sysctl_igmp_max_msf) { + msf->imsf_numsrc > READ_ONCE(net->ipv4.sysctl_igmp_max_msf)) { kfree(msf); err = -ENOBUFS; break; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index aab8ac383d5d1..374647693d7ac 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1442,7 +1442,7 @@ u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr) struct fib_info *fi = res->fi; u32 mtu = 0; - if (dev_net(dev)->ipv4.sysctl_ip_fwd_use_pmtu || + if (READ_ONCE(dev_net(dev)->ipv4.sysctl_ip_fwd_use_pmtu) || fi->fib_metrics->metrics[RTAX_LOCK - 1] & (1 << RTAX_MTU)) mtu = fi->fib_mtu; diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 10b469aee4920..41afc9155f311 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -249,12 +249,12 @@ bool cookie_timestamp_decode(const struct net *net, return true; } - if (!net->ipv4.sysctl_tcp_timestamps) + if (!READ_ONCE(net->ipv4.sysctl_tcp_timestamps)) return false; tcp_opt->sack_ok = (options & TS_OPT_SACK) ? TCP_SACK_SEEN : 0; - if (tcp_opt->sack_ok && !net->ipv4.sysctl_tcp_sack) + if (tcp_opt->sack_ok && !READ_ONCE(net->ipv4.sysctl_tcp_sack)) return false; if ((options & TS_OPT_WSCALE_MASK) == TS_OPT_WSCALE_MASK) @@ -263,7 +263,7 @@ bool cookie_timestamp_decode(const struct net *net, tcp_opt->wscale_ok = 1; tcp_opt->snd_wscale = options & TS_OPT_WSCALE_MASK; - return net->ipv4.sysctl_tcp_window_scaling != 0; + return READ_ONCE(net->ipv4.sysctl_tcp_window_scaling) != 0; } EXPORT_SYMBOL(cookie_timestamp_decode); @@ -342,7 +342,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) struct flowi4 fl4; u32 tsoff = 0; - if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies || !th->ack || th->rst) + if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies) || + !th->ack || th->rst) goto out; if (tcp_synq_no_recent_overflow(sk)) diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 08829809e88b7..86f553864f98f 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -95,7 +95,7 @@ static int ipv4_local_port_range(struct ctl_table *table, int write, * port limit. */ if ((range[1] < range[0]) || - (range[0] < net->ipv4.sysctl_ip_prot_sock)) + (range[0] < READ_ONCE(net->ipv4.sysctl_ip_prot_sock))) ret = -EINVAL; else set_local_port_range(net, range); @@ -121,7 +121,7 @@ static int ipv4_privileged_ports(struct ctl_table *table, int write, .extra2 = &ip_privileged_port_max, }; - pports = net->ipv4.sysctl_ip_prot_sock; + pports = READ_ONCE(net->ipv4.sysctl_ip_prot_sock); ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); @@ -133,7 +133,7 @@ static int ipv4_privileged_ports(struct ctl_table *table, int write, if (range[0] < pports) ret = -EINVAL; else - net->ipv4.sysctl_ip_prot_sock = pports; + WRITE_ONCE(net->ipv4.sysctl_ip_prot_sock, pports); } return ret; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 19c13ad5c121b..f1fd26bb199ce 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -440,7 +440,7 @@ void tcp_init_sock(struct sock *sk) tp->snd_cwnd_clamp = ~0; tp->mss_cache = TCP_MSS_DEFAULT; - tp->reordering = sock_net(sk)->ipv4.sysctl_tcp_reordering; + tp->reordering = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reordering); tcp_assign_congestion_control(sk); tp->tsoffset = 0; @@ -1148,7 +1148,8 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, struct sockaddr *uaddr = msg->msg_name; int err, flags; - if (!(sock_net(sk)->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) || + if (!(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen) & + TFO_CLIENT_ENABLE) || (uaddr && msg->msg_namelen >= sizeof(uaddr->sa_family) && uaddr->sa_family == AF_UNSPEC)) return -EOPNOTSUPP; @@ -3390,7 +3391,8 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int optname, case TCP_FASTOPEN_CONNECT: if (val > 1 || val < 0) { err = -EINVAL; - } else if (net->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) { + } else if (READ_ONCE(net->ipv4.sysctl_tcp_fastopen) & + TFO_CLIENT_ENABLE) { if (sk->sk_state == TCP_CLOSE) tp->fastopen_connect = val; else @@ -3727,7 +3729,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level, case TCP_LINGER2: val = tp->linger2; if (val >= 0) - val = (val ? : net->ipv4.sysctl_tcp_fin_timeout) / HZ; + val = (val ? : READ_ONCE(net->ipv4.sysctl_tcp_fin_timeout)) / HZ; break; case TCP_DEFER_ACCEPT: val = retrans_to_secs(icsk->icsk_accept_queue.rskq_defer_accept, diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 1071119843843..39fb037ce5f3f 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -349,7 +349,7 @@ static bool tcp_fastopen_no_cookie(const struct sock *sk, const struct dst_entry *dst, int flag) { - return (sock_net(sk)->ipv4.sysctl_tcp_fastopen & flag) || + return (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen) & flag) || tcp_sk(sk)->fastopen_no_cookie || (dst && dst_metric(dst, RTAX_FASTOPEN_NO_COOKIE)); } @@ -364,7 +364,7 @@ struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, const struct dst_entry *dst) { bool syn_data = TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1; - int tcp_fastopen = sock_net(sk)->ipv4.sysctl_tcp_fastopen; + int tcp_fastopen = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen); struct tcp_fastopen_cookie valid_foc = { .len = -1 }; struct sock *child; int ret = 0; @@ -506,7 +506,7 @@ void tcp_fastopen_active_disable(struct sock *sk) { struct net *net = sock_net(sk); - if (!sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout) + if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout)) return; /* Paired with READ_ONCE() in tcp_fastopen_active_should_disable() */ @@ -527,7 +527,8 @@ void tcp_fastopen_active_disable(struct sock *sk) */ bool tcp_fastopen_active_should_disable(struct sock *sk) { - unsigned int tfo_bh_timeout = sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout; + unsigned int tfo_bh_timeout = + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout); unsigned long timeout; int tfo_da_times; int multiplier; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 54ed68e05b66a..d817f8c31c9ce 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1011,7 +1011,7 @@ static void tcp_check_sack_reordering(struct sock *sk, const u32 low_seq, tp->undo_marker ? tp->undo_retrans : 0); #endif tp->reordering = min_t(u32, (metric + mss - 1) / mss, - sock_net(sk)->ipv4.sysctl_tcp_max_reordering); + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_max_reordering)); } /* This exciting event is worth to be remembered. 8) */ @@ -1990,7 +1990,7 @@ static void tcp_check_reno_reordering(struct sock *sk, const int addend) return; tp->reordering = min_t(u32, tp->packets_out + addend, - sock_net(sk)->ipv4.sysctl_tcp_max_reordering); + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_max_reordering)); tp->reord_seen++; NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRENOREORDER); } @@ -2055,7 +2055,8 @@ static inline void tcp_init_undo(struct tcp_sock *tp) static bool tcp_is_rack(const struct sock *sk) { - return sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_LOSS_DETECTION; + return READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_recovery) & + TCP_RACK_LOSS_DETECTION; } /* If we detect SACK reneging, forget all SACK information @@ -2099,6 +2100,7 @@ void tcp_enter_loss(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); bool new_recovery = icsk->icsk_ca_state < TCP_CA_Recovery; + u8 reordering; tcp_timeout_mark_lost(sk); @@ -2119,10 +2121,12 @@ void tcp_enter_loss(struct sock *sk) /* Timeout in disordered state after receiving substantial DUPACKs * suggests that the degree of reordering is over-estimated. */ + reordering = READ_ONCE(net->ipv4.sysctl_tcp_reordering); if (icsk->icsk_ca_state <= TCP_CA_Disorder && - tp->sacked_out >= net->ipv4.sysctl_tcp_reordering) + tp->sacked_out >= reordering) tp->reordering = min_t(unsigned int, tp->reordering, - net->ipv4.sysctl_tcp_reordering); + reordering); + tcp_set_ca_state(sk, TCP_CA_Loss); tp->high_seq = tp->snd_nxt; tcp_ecn_queue_cwr(tp); @@ -3411,7 +3415,8 @@ static inline bool tcp_may_raise_cwnd(const struct sock *sk, const int flag) * new SACK or ECE mark may first advance cwnd here and later reduce * cwnd in tcp_fastretrans_alert() based on more states. */ - if (tcp_sk(sk)->reordering > sock_net(sk)->ipv4.sysctl_tcp_reordering) + if (tcp_sk(sk)->reordering > + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reordering)) return flag & FLAG_FORWARD_PROGRESS; return flag & FLAG_DATA_ACKED; @@ -4003,7 +4008,7 @@ void tcp_parse_options(const struct net *net, break; case TCPOPT_WINDOW: if (opsize == TCPOLEN_WINDOW && th->syn && - !estab && net->ipv4.sysctl_tcp_window_scaling) { + !estab && READ_ONCE(net->ipv4.sysctl_tcp_window_scaling)) { __u8 snd_wscale = *(__u8 *)ptr; opt_rx->wscale_ok = 1; if (snd_wscale > TCP_MAX_WSCALE) { @@ -4019,7 +4024,7 @@ void tcp_parse_options(const struct net *net, case TCPOPT_TIMESTAMP: if ((opsize == TCPOLEN_TIMESTAMP) && ((estab && opt_rx->tstamp_ok) || - (!estab && net->ipv4.sysctl_tcp_timestamps))) { + (!estab && READ_ONCE(net->ipv4.sysctl_tcp_timestamps)))) { opt_rx->saw_tstamp = 1; opt_rx->rcv_tsval = get_unaligned_be32(ptr); opt_rx->rcv_tsecr = get_unaligned_be32(ptr + 4); @@ -4027,7 +4032,7 @@ void tcp_parse_options(const struct net *net, break; case TCPOPT_SACK_PERM: if (opsize == TCPOLEN_SACK_PERM && th->syn && - !estab && net->ipv4.sysctl_tcp_sack) { + !estab && READ_ONCE(net->ipv4.sysctl_tcp_sack)) { opt_rx->sack_ok = TCP_SACK_SEEN; tcp_sack_reset(opt_rx); } @@ -5487,7 +5492,7 @@ static void tcp_check_urg(struct sock *sk, const struct tcphdr *th) struct tcp_sock *tp = tcp_sk(sk); u32 ptr = ntohs(th->urg_ptr); - if (ptr && !sock_net(sk)->ipv4.sysctl_tcp_stdurg) + if (ptr && !READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_stdurg)) ptr--; ptr += ntohl(th->seq); @@ -6683,11 +6688,14 @@ static bool tcp_syn_flood_action(const struct sock *sk, const char *proto) { struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; const char *msg = "Dropping request"; - bool want_cookie = false; struct net *net = sock_net(sk); + bool want_cookie = false; + u8 syncookies; + + syncookies = READ_ONCE(net->ipv4.sysctl_tcp_syncookies); #ifdef CONFIG_SYN_COOKIES - if (net->ipv4.sysctl_tcp_syncookies) { + if (syncookies) { msg = "Sending cookies"; want_cookie = true; __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPREQQFULLDOCOOKIES); @@ -6695,8 +6703,7 @@ static bool tcp_syn_flood_action(const struct sock *sk, const char *proto) #endif __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPREQQFULLDROP); - if (!queue->synflood_warned && - net->ipv4.sysctl_tcp_syncookies != 2 && + if (!queue->synflood_warned && syncookies != 2 && xchg(&queue->synflood_warned, 1) == 0) net_info_ratelimited("%s: Possible SYN flooding on port %d. %s. Check SNMP counters.\n", proto, sk->sk_num, msg); @@ -6745,7 +6752,7 @@ u16 tcp_get_syncookie_mss(struct request_sock_ops *rsk_ops, struct tcp_sock *tp = tcp_sk(sk); u16 mss; - if (sock_net(sk)->ipv4.sysctl_tcp_syncookies != 2 && + if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies) != 2 && !inet_csk_reqsk_queue_is_full(sk)) return 0; @@ -6779,13 +6786,15 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, bool want_cookie = false; struct dst_entry *dst; struct flowi fl; + u8 syncookies; + + syncookies = READ_ONCE(net->ipv4.sysctl_tcp_syncookies); /* TW buckets are converted to open requests without * limitations, they conserve resources and peer is * evidently real one. */ - if ((net->ipv4.sysctl_tcp_syncookies == 2 || - inet_csk_reqsk_queue_is_full(sk)) && !isn) { + if ((syncookies == 2 || inet_csk_reqsk_queue_is_full(sk)) && !isn) { want_cookie = tcp_syn_flood_action(sk, rsk_ops->slab_name); if (!want_cookie) goto drop; @@ -6839,10 +6848,12 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, goto drop_and_free; if (!want_cookie && !isn) { + int max_syn_backlog = READ_ONCE(net->ipv4.sysctl_max_syn_backlog); + /* Kill the following clause, if you dislike this way. */ - if (!net->ipv4.sysctl_tcp_syncookies && - (net->ipv4.sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) < - (net->ipv4.sysctl_max_syn_backlog >> 2)) && + if (!syncookies && + (max_syn_backlog - inet_csk_reqsk_queue_len(sk) < + (max_syn_backlog >> 2)) && !tcp_peer_is_proven(req, dst)) { /* Without syncookies last quarter of * backlog is filled with destinations, diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 32c60122db9c8..d5f13ff7d9004 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -106,10 +106,10 @@ static u32 tcp_v4_init_ts_off(const struct net *net, const struct sk_buff *skb) int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) { + int reuse = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_tw_reuse); const struct inet_timewait_sock *tw = inet_twsk(sktw); const struct tcp_timewait_sock *tcptw = tcp_twsk(sktw); struct tcp_sock *tp = tcp_sk(sk); - int reuse = sock_net(sk)->ipv4.sysctl_tcp_tw_reuse; if (reuse == 2) { /* Still does not detect *everything* that goes through diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 6b27c481fe18b..8d7e32f4abf67 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -428,7 +428,8 @@ void tcp_update_metrics(struct sock *sk) if (!tcp_metric_locked(tm, TCP_METRIC_REORDERING)) { val = tcp_metric_get(tm, TCP_METRIC_REORDERING); if (val < tp->reordering && - tp->reordering != net->ipv4.sysctl_tcp_reordering) + tp->reordering != + READ_ONCE(net->ipv4.sysctl_tcp_reordering)) tcp_metric_set(tm, TCP_METRIC_REORDERING, tp->reordering); } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 62f5ef9e6f938..e42312321191b 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -180,7 +180,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, * Oh well... nobody has a sufficient solution to this * protocol bug yet. */ - if (twsk_net(tw)->ipv4.sysctl_tcp_rfc1337 == 0) { + if (!READ_ONCE(twsk_net(tw)->ipv4.sysctl_tcp_rfc1337)) { kill: inet_twsk_deschedule_put(tw); return TCP_TW_SUCCESS; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 8634a5c853f51..9b67c61576e4c 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -789,18 +789,18 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, opts->mss = tcp_advertise_mss(sk); remaining -= TCPOLEN_MSS_ALIGNED; - if (likely(sock_net(sk)->ipv4.sysctl_tcp_timestamps && !*md5)) { + if (likely(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_timestamps) && !*md5)) { opts->options |= OPTION_TS; opts->tsval = tcp_skb_timestamp(skb) + tp->tsoffset; opts->tsecr = tp->rx_opt.ts_recent; remaining -= TCPOLEN_TSTAMP_ALIGNED; } - if (likely(sock_net(sk)->ipv4.sysctl_tcp_window_scaling)) { + if (likely(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_window_scaling))) { opts->ws = tp->rx_opt.rcv_wscale; opts->options |= OPTION_WSCALE; remaining -= TCPOLEN_WSCALE_ALIGNED; } - if (likely(sock_net(sk)->ipv4.sysctl_tcp_sack)) { + if (likely(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_sack))) { opts->options |= OPTION_SACK_ADVERTISE; if (unlikely(!(OPTION_TS & opts->options))) remaining -= TCPOLEN_SACKPERM_ALIGNED; @@ -1720,7 +1720,8 @@ static inline int __tcp_mtu_to_mss(struct sock *sk, int pmtu) mss_now -= icsk->icsk_ext_hdr_len; /* Then reserve room for full set of TCP options and 8 bytes of data */ - mss_now = max(mss_now, sock_net(sk)->ipv4.sysctl_tcp_min_snd_mss); + mss_now = max(mss_now, + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_snd_mss)); return mss_now; } @@ -1763,10 +1764,10 @@ void tcp_mtup_init(struct sock *sk) struct inet_connection_sock *icsk = inet_csk(sk); struct net *net = sock_net(sk); - icsk->icsk_mtup.enabled = net->ipv4.sysctl_tcp_mtu_probing > 1; + icsk->icsk_mtup.enabled = READ_ONCE(net->ipv4.sysctl_tcp_mtu_probing) > 1; icsk->icsk_mtup.search_high = tp->rx_opt.mss_clamp + sizeof(struct tcphdr) + icsk->icsk_af_ops->net_header_len; - icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, net->ipv4.sysctl_tcp_base_mss); + icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, READ_ONCE(net->ipv4.sysctl_tcp_base_mss)); icsk->icsk_mtup.probe_size = 0; if (icsk->icsk_mtup.enabled) icsk->icsk_mtup.probe_timestamp = tcp_jiffies32; @@ -1898,7 +1899,7 @@ static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited) if (tp->packets_out > tp->snd_cwnd_used) tp->snd_cwnd_used = tp->packets_out; - if (sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle && + if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle) && (s32)(tcp_jiffies32 - tp->snd_cwnd_stamp) >= inet_csk(sk)->icsk_rto && !ca_ops->cong_control) tcp_cwnd_application_limited(sk); @@ -2277,7 +2278,7 @@ static inline void tcp_mtu_check_reprobe(struct sock *sk) u32 interval; s32 delta; - interval = net->ipv4.sysctl_tcp_probe_interval; + interval = READ_ONCE(net->ipv4.sysctl_tcp_probe_interval); delta = tcp_jiffies32 - icsk->icsk_mtup.probe_timestamp; if (unlikely(delta >= interval * HZ)) { int mss = tcp_current_mss(sk); @@ -2359,7 +2360,7 @@ static int tcp_mtu_probe(struct sock *sk) * probing process by not resetting search range to its orignal. */ if (probe_size > tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_high) || - interval < net->ipv4.sysctl_tcp_probe_threshold) { + interval < READ_ONCE(net->ipv4.sysctl_tcp_probe_threshold)) { /* Check whether enough time has elaplased for * another round of probing. */ @@ -2734,7 +2735,7 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto) if (rcu_access_pointer(tp->fastopen_rsk)) return false; - early_retrans = sock_net(sk)->ipv4.sysctl_tcp_early_retrans; + early_retrans = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_early_retrans); /* Schedule a loss probe in 2*RTT for SACK capable connections * not in loss recovery, that are either limited by cwnd or application. */ @@ -3099,7 +3100,7 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to, struct sk_buff *skb = to, *tmp; bool first = true; - if (!sock_net(sk)->ipv4.sysctl_tcp_retrans_collapse) + if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_retrans_collapse)) return; if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN) return; @@ -3647,7 +3648,7 @@ static void tcp_connect_init(struct sock *sk) * See tcp_input.c:tcp_rcv_state_process case TCP_SYN_SENT. */ tp->tcp_header_len = sizeof(struct tcphdr); - if (sock_net(sk)->ipv4.sysctl_tcp_timestamps) + if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_timestamps)) tp->tcp_header_len += TCPOLEN_TSTAMP_ALIGNED; #ifdef CONFIG_TCP_MD5SIG @@ -3683,7 +3684,7 @@ static void tcp_connect_init(struct sock *sk) tp->advmss - (tp->rx_opt.ts_recent_stamp ? tp->tcp_header_len - sizeof(struct tcphdr) : 0), &tp->rcv_wnd, &tp->window_clamp, - sock_net(sk)->ipv4.sysctl_tcp_window_scaling, + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_window_scaling), &rcv_wscale, rcv_wnd); @@ -4091,7 +4092,7 @@ void tcp_send_probe0(struct sock *sk) icsk->icsk_probes_out++; if (err <= 0) { - if (icsk->icsk_backoff < net->ipv4.sysctl_tcp_retries2) + if (icsk->icsk_backoff < READ_ONCE(net->ipv4.sysctl_tcp_retries2)) icsk->icsk_backoff++; timeout = tcp_probe0_when(sk, TCP_RTO_MAX); } else { diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c index 31fc178f42c02..21fc9859d421e 100644 --- a/net/ipv4/tcp_recovery.c +++ b/net/ipv4/tcp_recovery.c @@ -19,7 +19,8 @@ static u32 tcp_rack_reo_wnd(const struct sock *sk) return 0; if (tp->sacked_out >= tp->reordering && - !(sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_NO_DUPTHRESH)) + !(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_recovery) & + TCP_RACK_NO_DUPTHRESH)) return 0; } @@ -190,7 +191,8 @@ void tcp_rack_update_reo_wnd(struct sock *sk, struct rate_sample *rs) { struct tcp_sock *tp = tcp_sk(sk); - if (sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_STATIC_REO_WND || + if ((READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_recovery) & + TCP_RACK_STATIC_REO_WND) || !rs->prior_delivered) return; diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 4ef08079ccfa9..888683f2ff3ee 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -143,7 +143,7 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset) */ static int tcp_orphan_retries(struct sock *sk, bool alive) { - int retries = sock_net(sk)->ipv4.sysctl_tcp_orphan_retries; /* May be zero. */ + int retries = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_orphan_retries); /* May be zero. */ /* We know from an ICMP that something is wrong. */ if (sk->sk_err_soft && !alive) @@ -163,7 +163,7 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk) int mss; /* Black hole detection */ - if (!net->ipv4.sysctl_tcp_mtu_probing) + if (!READ_ONCE(net->ipv4.sysctl_tcp_mtu_probing)) return; if (!icsk->icsk_mtup.enabled) { @@ -171,9 +171,9 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk) icsk->icsk_mtup.probe_timestamp = tcp_jiffies32; } else { mss = tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low) >> 1; - mss = min(net->ipv4.sysctl_tcp_base_mss, mss); - mss = max(mss, net->ipv4.sysctl_tcp_mtu_probe_floor); - mss = max(mss, net->ipv4.sysctl_tcp_min_snd_mss); + mss = min(READ_ONCE(net->ipv4.sysctl_tcp_base_mss), mss); + mss = max(mss, READ_ONCE(net->ipv4.sysctl_tcp_mtu_probe_floor)); + mss = max(mss, READ_ONCE(net->ipv4.sysctl_tcp_min_snd_mss)); icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss); } tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); @@ -242,14 +242,14 @@ static int tcp_write_timeout(struct sock *sk) retry_until = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries; expired = icsk->icsk_retransmits >= retry_until; } else { - if (retransmits_timed_out(sk, net->ipv4.sysctl_tcp_retries1, 0)) { + if (retransmits_timed_out(sk, READ_ONCE(net->ipv4.sysctl_tcp_retries1), 0)) { /* Black hole detection */ tcp_mtu_probing(icsk, sk); __dst_negative_advice(sk); } - retry_until = net->ipv4.sysctl_tcp_retries2; + retry_until = READ_ONCE(net->ipv4.sysctl_tcp_retries2); if (sock_flag(sk, SOCK_DEAD)) { const bool alive = icsk->icsk_rto < TCP_RTO_MAX; @@ -380,7 +380,7 @@ static void tcp_probe_timer(struct sock *sk) msecs_to_jiffies(icsk->icsk_user_timeout)) goto abort; - max_probes = sock_net(sk)->ipv4.sysctl_tcp_retries2; + max_probes = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_retries2); if (sock_flag(sk, SOCK_DEAD)) { const bool alive = inet_csk_rto_backoff(icsk, TCP_RTO_MAX) < TCP_RTO_MAX; @@ -574,7 +574,7 @@ out_reset_timer: * linear-timeout retransmissions into a black hole */ if (sk->sk_state == TCP_ESTABLISHED && - (tp->thin_lto || net->ipv4.sysctl_tcp_thin_linear_timeouts) && + (tp->thin_lto || READ_ONCE(net->ipv4.sysctl_tcp_thin_linear_timeouts)) && tcp_stream_is_thin(tp) && icsk->icsk_retransmits <= TCP_THIN_LINEAR_RETRIES) { icsk->icsk_backoff = 0; @@ -585,7 +585,7 @@ out_reset_timer: } inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, tcp_clamp_rto_to_user_timeout(sk), TCP_RTO_MAX); - if (retransmits_timed_out(sk, net->ipv4.sysctl_tcp_retries1 + 1, 0)) + if (retransmits_timed_out(sk, READ_ONCE(net->ipv4.sysctl_tcp_retries1) + 1, 0)) __sk_dst_reset(sk); out:; diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 890a9cfc6ce27..d30c9d949c1b5 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -225,7 +225,7 @@ lookup_protocol: inet->mc_list = NULL; inet->rcv_tos = 0; - if (net->ipv4.sysctl_ip_no_pmtu_disc) + if (READ_ONCE(net->ipv4.sysctl_ip_no_pmtu_disc)) inet->pmtudisc = IP_PMTUDISC_DONT; else inet->pmtudisc = IP_PMTUDISC_WANT; diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index ca92dd6981dea..12ae817aaf2ec 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -141,7 +141,8 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) __u8 rcv_wscale; u32 tsoff = 0; - if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies || !th->ack || th->rst) + if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies) || + !th->ack || th->rst) goto out; if (tcp_synq_no_recent_overflow(sk)) diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 940f1e257a90a..6e4ca837e91dd 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -358,7 +358,7 @@ static int sctp_v4_available(union sctp_addr *addr, struct sctp_sock *sp) if (addr->v4.sin_addr.s_addr != htonl(INADDR_ANY) && ret != RTN_LOCAL && !sp->inet.freebind && - !net->ipv4.sysctl_ip_nonlocal_bind) + !READ_ONCE(net->ipv4.sysctl_ip_nonlocal_bind)) return 0; if (ipv6_only_sock(sctp_opt2sk(sp))) diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index ee1f0fdba0855..0ef15f8fba902 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -1787,7 +1787,7 @@ void smc_llc_lgr_init(struct smc_link_group *lgr, struct smc_sock *smc) init_waitqueue_head(&lgr->llc_flow_waiter); init_waitqueue_head(&lgr->llc_msg_waiter); mutex_init(&lgr->llc_conf_mutex); - lgr->llc_testlink_time = net->ipv4.sysctl_tcp_keepalive_time; + lgr->llc_testlink_time = READ_ONCE(net->ipv4.sysctl_tcp_keepalive_time); } /* called after lgr was removed from lgr_list */ diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 6ae2ce411b4bf..23eab7ac43ee5 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -97,13 +97,16 @@ static void tls_device_queue_ctx_destruction(struct tls_context *ctx) unsigned long flags; spin_lock_irqsave(&tls_device_lock, flags); + if (unlikely(!refcount_dec_and_test(&ctx->refcount))) + goto unlock; + list_move_tail(&ctx->list, &tls_device_gc_list); /* schedule_work inside the spinlock * to make sure tls_device_down waits for that work. */ schedule_work(&tls_device_gc_work); - +unlock: spin_unlock_irqrestore(&tls_device_lock, flags); } @@ -194,8 +197,7 @@ void tls_device_sk_destruct(struct sock *sk) clean_acked_data_disable(inet_csk(sk)); } - if (refcount_dec_and_test(&tls_ctx->refcount)) - tls_device_queue_ctx_destruction(tls_ctx); + tls_device_queue_ctx_destruction(tls_ctx); } EXPORT_SYMBOL_GPL(tls_device_sk_destruct); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 93cbcc8f9b39e..603b05ed7eb4c 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2680,8 +2680,10 @@ static int xfrm_expand_policies(const struct flowi *fl, u16 family, *num_xfrms = 0; return 0; } - if (IS_ERR(pols[0])) + if (IS_ERR(pols[0])) { + *num_pols = 0; return PTR_ERR(pols[0]); + } *num_xfrms = pols[0]->xfrm_nr; @@ -2696,6 +2698,7 @@ static int xfrm_expand_policies(const struct flowi *fl, u16 family, if (pols[1]) { if (IS_ERR(pols[1])) { xfrm_pols_put(pols, *num_pols); + *num_pols = 0; return PTR_ERR(pols[1]); } (*num_pols)++; diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 717db5ecd0bd4..bc0bbb1571cef 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -2587,7 +2587,7 @@ int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload) int err; if (family == AF_INET && - xs_net(x)->ipv4.sysctl_ip_no_pmtu_disc) + READ_ONCE(xs_net(x)->ipv4.sysctl_ip_no_pmtu_disc)) x->props.flags |= XFRM_STATE_NOPMTUDISC; err = -EPROTONOSUPPORT; diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c index e737c216efc49..18569adcb4fe7 100644 --- a/security/integrity/ima/ima_policy.c +++ b/security/integrity/ima/ima_policy.c @@ -1805,6 +1805,10 @@ bool ima_appraise_signature(enum kernel_read_file_id id) if (id >= READING_MAX_ID) return false; + if (id == READING_KEXEC_IMAGE && !(ima_appraise & IMA_APPRAISE_ENFORCE) + && security_locked_down(LOCKDOWN_KEXEC)) + return false; + func = read_idmap[id] ?: FILE_CHECK; rcu_read_lock(); diff --git a/sound/core/memalloc.c b/sound/core/memalloc.c index 0f335162f87c7..966bef5acc750 100644 --- a/sound/core/memalloc.c +++ b/sound/core/memalloc.c @@ -133,6 +133,7 @@ int snd_dma_alloc_pages(int type, struct device *device, size_t size, if (WARN_ON(!dmab)) return -ENXIO; + size = PAGE_ALIGN(size); dmab->dev.type = type; dmab->dev.dev = device; dmab->bytes = 0; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 9cd8ca2d8bc16..c5dbac10c3720 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -3644,8 +3644,11 @@ static int kvm_ioctl_create_device(struct kvm *kvm, kvm_put_kvm_no_destroy(kvm); mutex_lock(&kvm->lock); list_del(&dev->vm_node); + if (ops->release) + ops->release(dev); mutex_unlock(&kvm->lock); - ops->destroy(dev); + if (ops->destroy) + ops->destroy(dev); return ret; }