diff options
121 files changed, 2307 insertions, 2283 deletions
diff --git a/Documentation/IPMI.txt b/Documentation/IPMI.txt index 72292308d0f5..6962cab997ef 100644 --- a/Documentation/IPMI.txt +++ b/Documentation/IPMI.txt @@ -257,7 +257,7 @@ and tell you when they come and go. Creating the User -To user the message handler, you must first create a user using +To use the message handler, you must first create a user using ipmi_create_user. The interface number specifies which SMI you want to connect to, and you must supply callback functions to be called when data comes in. The callback function can run at interrupt level, diff --git a/MAINTAINERS b/MAINTAINERS index 846f97aa3508..5a00239fd7b3 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6012,9 +6012,8 @@ F: include/linux/hsi/ F: include/uapi/linux/hsi/ HSO 3G MODEM DRIVER -M: Jan Dumon <j.dumon@option.com> -W: http://www.pharscape.org -S: Maintained +L: linux-usb@vger.kernel.org +S: Orphan F: drivers/net/usb/hso.c HSR NETWORK PROTOCOL diff --git a/drivers/acpi/acpi_ipmi.c b/drivers/acpi/acpi_ipmi.c index f77956c3fd45..747c2ba98534 100644 --- a/drivers/acpi/acpi_ipmi.c +++ b/drivers/acpi/acpi_ipmi.c @@ -56,7 +56,7 @@ struct acpi_ipmi_device { struct ipmi_driver_data { struct list_head ipmi_devices; struct ipmi_smi_watcher bmc_events; - struct ipmi_user_hndl ipmi_hndlrs; + const struct ipmi_user_hndl ipmi_hndlrs; struct mutex ipmi_lock; /* diff --git a/drivers/atm/nicstar.c b/drivers/atm/nicstar.c index cb28579e8a94..d879f3bca107 100644 --- a/drivers/atm/nicstar.c +++ b/drivers/atm/nicstar.c @@ -1980,13 +1980,12 @@ static void dequeue_rx(ns_dev * card, ns_rsqe * rsqe) card->lbfqc = ns_stat_lfbqc_get(stat); id = le32_to_cpu(rsqe->buffer_handle); - skb = idr_find(&card->idr, id); + skb = idr_remove(&card->idr, id); if (!skb) { RXPRINTK(KERN_ERR - "nicstar%d: idr_find() failed!\n", card->index); + "nicstar%d: skb not found!\n", card->index); return; } - idr_remove(&card->idr, id); dma_sync_single_for_cpu(&card->pcidev->dev, NS_PRV_DMA(skb), (NS_PRV_BUFTYPE(skb) == BUF_SM diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 615e5b5178a0..116509852a34 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -2915,11 +2915,9 @@ out_idr_remove_vol: idr_remove(&connection->peer_devices, vnr); out_idr_remove_from_resource: for_each_connection(connection, resource) { - peer_device = idr_find(&connection->peer_devices, vnr); - if (peer_device) { - idr_remove(&connection->peer_devices, vnr); + peer_device = idr_remove(&connection->peer_devices, vnr); + if (peer_device) kref_put(&connection->kref, drbd_destroy_connection); - } } for_each_peer_device_safe(peer_device, tmp_peer_device, device) { list_del(&peer_device->peer_devices); diff --git a/drivers/char/ipmi/Kconfig b/drivers/char/ipmi/Kconfig index 7f816655cbbf..90f3edffb067 100644 --- a/drivers/char/ipmi/Kconfig +++ b/drivers/char/ipmi/Kconfig @@ -78,7 +78,8 @@ config IPMI_POWEROFF endif # IPMI_HANDLER config ASPEED_BT_IPMI_BMC - depends on ARCH_ASPEED + depends on ARCH_ASPEED || COMPILE_TEST + depends on REGMAP && REGMAP_MMIO && MFD_SYSCON tristate "BT IPMI bmc driver" help Provides a driver for the BT (Block Transfer) IPMI interface diff --git a/drivers/char/ipmi/bt-bmc.c b/drivers/char/ipmi/bt-bmc.c index fc9e8891eae3..d6f5d9eb102d 100644 --- a/drivers/char/ipmi/bt-bmc.c +++ b/drivers/char/ipmi/bt-bmc.c @@ -12,10 +12,13 @@ #include <linux/errno.h> #include <linux/interrupt.h> #include <linux/io.h> +#include <linux/mfd/syscon.h> #include <linux/miscdevice.h> #include <linux/module.h> +#include <linux/of.h> #include <linux/platform_device.h> #include <linux/poll.h> +#include <linux/regmap.h> #include <linux/sched.h> #include <linux/timer.h> @@ -60,7 +63,8 @@ struct bt_bmc { struct device dev; struct miscdevice miscdev; - void __iomem *base; + struct regmap *map; + int offset; int irq; wait_queue_head_t queue; struct timer_list poll_timer; @@ -69,14 +73,29 @@ struct bt_bmc { static atomic_t open_count = ATOMIC_INIT(0); +static const struct regmap_config bt_regmap_cfg = { + .reg_bits = 32, + .val_bits = 32, + .reg_stride = 4, +}; + static u8 bt_inb(struct bt_bmc *bt_bmc, int reg) { - return ioread8(bt_bmc->base + reg); + uint32_t val = 0; + int rc; + + rc = regmap_read(bt_bmc->map, bt_bmc->offset + reg, &val); + WARN(rc != 0, "regmap_read() failed: %d\n", rc); + + return rc == 0 ? (u8) val : 0; } static void bt_outb(struct bt_bmc *bt_bmc, u8 data, int reg) { - iowrite8(data, bt_bmc->base + reg); + int rc; + + rc = regmap_write(bt_bmc->map, bt_bmc->offset + reg, data); + WARN(rc != 0, "regmap_write() failed: %d\n", rc); } static void clr_rd_ptr(struct bt_bmc *bt_bmc) @@ -367,14 +386,18 @@ static irqreturn_t bt_bmc_irq(int irq, void *arg) { struct bt_bmc *bt_bmc = arg; u32 reg; + int rc; + + rc = regmap_read(bt_bmc->map, bt_bmc->offset + BT_CR2, ®); + if (rc) + return IRQ_NONE; - reg = ioread32(bt_bmc->base + BT_CR2); reg &= BT_CR2_IRQ_H2B | BT_CR2_IRQ_HBUSY; if (!reg) return IRQ_NONE; /* ack pending IRQs */ - iowrite32(reg, bt_bmc->base + BT_CR2); + regmap_write(bt_bmc->map, bt_bmc->offset + BT_CR2, reg); wake_up(&bt_bmc->queue); return IRQ_HANDLED; @@ -384,7 +407,6 @@ static int bt_bmc_config_irq(struct bt_bmc *bt_bmc, struct platform_device *pdev) { struct device *dev = &pdev->dev; - u32 reg; int rc; bt_bmc->irq = platform_get_irq(pdev, 0); @@ -405,18 +427,17 @@ static int bt_bmc_config_irq(struct bt_bmc *bt_bmc, * will be cleared (along with B2H) when we can write the next * message to the BT buffer */ - reg = ioread32(bt_bmc->base + BT_CR1); - reg |= BT_CR1_IRQ_H2B | BT_CR1_IRQ_HBUSY; - iowrite32(reg, bt_bmc->base + BT_CR1); + rc = regmap_update_bits(bt_bmc->map, bt_bmc->offset + BT_CR1, + (BT_CR1_IRQ_H2B | BT_CR1_IRQ_HBUSY), + (BT_CR1_IRQ_H2B | BT_CR1_IRQ_HBUSY)); - return 0; + return rc; } static int bt_bmc_probe(struct platform_device *pdev) { struct bt_bmc *bt_bmc; struct device *dev; - struct resource *res; int rc; if (!pdev || !pdev->dev.of_node) @@ -431,10 +452,27 @@ static int bt_bmc_probe(struct platform_device *pdev) dev_set_drvdata(&pdev->dev, bt_bmc); - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - bt_bmc->base = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(bt_bmc->base)) - return PTR_ERR(bt_bmc->base); + bt_bmc->map = syscon_node_to_regmap(pdev->dev.parent->of_node); + if (IS_ERR(bt_bmc->map)) { + struct resource *res; + void __iomem *base; + + /* + * Assume it's not the MFD-based devicetree description, in + * which case generate a regmap ourselves + */ + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + base = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(base)) + return PTR_ERR(base); + + bt_bmc->map = devm_regmap_init_mmio(dev, base, &bt_regmap_cfg); + bt_bmc->offset = 0; + } else { + rc = of_property_read_u32(dev->of_node, "reg", &bt_bmc->offset); + if (rc) + return rc; + } mutex_init(&bt_bmc->mutex); init_waitqueue_head(&bt_bmc->queue); @@ -461,12 +499,12 @@ static int bt_bmc_probe(struct platform_device *pdev) add_timer(&bt_bmc->poll_timer); } - iowrite32((BT_IO_BASE << BT_CR0_IO_BASE) | - (BT_IRQ << BT_CR0_IRQ) | - BT_CR0_EN_CLR_SLV_RDP | - BT_CR0_EN_CLR_SLV_WRP | - BT_CR0_ENABLE_IBT, - bt_bmc->base + BT_CR0); + regmap_write(bt_bmc->map, bt_bmc->offset + BT_CR0, + (BT_IO_BASE << BT_CR0_IO_BASE) | + (BT_IRQ << BT_CR0_IRQ) | + BT_CR0_EN_CLR_SLV_RDP | + BT_CR0_EN_CLR_SLV_WRP | + BT_CR0_ENABLE_IBT); clr_b_busy(bt_bmc); diff --git a/drivers/char/ipmi/ipmi_devintf.c b/drivers/char/ipmi/ipmi_devintf.c index a21407de46ae..f45119c5337d 100644 --- a/drivers/char/ipmi/ipmi_devintf.c +++ b/drivers/char/ipmi/ipmi_devintf.c @@ -108,7 +108,7 @@ static int ipmi_fasync(int fd, struct file *file, int on) return (result); } -static struct ipmi_user_hndl ipmi_hndlrs = +static const struct ipmi_user_hndl ipmi_hndlrs = { .ipmi_recv_hndl = file_receive_handler, }; diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c index 92e53acf2cd2..9f699951b75a 100644 --- a/drivers/char/ipmi/ipmi_msghandler.c +++ b/drivers/char/ipmi/ipmi_msghandler.c @@ -102,7 +102,7 @@ struct ipmi_user { struct kref refcount; /* The upper layer that handles receive messages. */ - struct ipmi_user_hndl *handler; + const struct ipmi_user_hndl *handler; void *handler_data; /* The interface this user is bound to. */ @@ -919,7 +919,7 @@ static int intf_err_seq(ipmi_smi_t intf, int ipmi_create_user(unsigned int if_num, - struct ipmi_user_hndl *handler, + const struct ipmi_user_hndl *handler, void *handler_data, ipmi_user_t *user) { diff --git a/drivers/char/ipmi/ipmi_powernv.c b/drivers/char/ipmi/ipmi_powernv.c index 6e658aa114f1..b338a4becbf8 100644 --- a/drivers/char/ipmi/ipmi_powernv.c +++ b/drivers/char/ipmi/ipmi_powernv.c @@ -196,7 +196,7 @@ static void ipmi_powernv_poll(void *send_info) ipmi_powernv_recv(smi); } -static struct ipmi_smi_handlers ipmi_powernv_smi_handlers = { +static const struct ipmi_smi_handlers ipmi_powernv_smi_handlers = { .owner = THIS_MODULE, .start_processing = ipmi_powernv_start_processing, .sender = ipmi_powernv_send, diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c index 4035495f3a86..30b9e83bf1bf 100644 --- a/drivers/char/ipmi/ipmi_watchdog.c +++ b/drivers/char/ipmi/ipmi_watchdog.c @@ -985,7 +985,7 @@ static void ipmi_wdog_pretimeout_handler(void *handler_data) pretimeout_since_last_heartbeat = 1; } -static struct ipmi_user_hndl ipmi_hndlrs = { +static const struct ipmi_user_hndl ipmi_hndlrs = { .ipmi_recv_hndl = ipmi_wdog_msg_handler, .ipmi_watchdog_pretimeout = ipmi_wdog_pretimeout_handler }; diff --git a/drivers/firewire/core-cdev.c b/drivers/firewire/core-cdev.c index aee149bdf4c0..a301fcf46e88 100644 --- a/drivers/firewire/core-cdev.c +++ b/drivers/firewire/core-cdev.c @@ -1307,8 +1307,7 @@ static void iso_resource_work(struct work_struct *work) */ if (r->todo == ISO_RES_REALLOC && !success && !client->in_shutdown && - idr_find(&client->resource_idr, r->resource.handle)) { - idr_remove(&client->resource_idr, r->resource.handle); + idr_remove(&client->resource_idr, r->resource.handle)) { client_put(client); free = true; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c index c02db01f6583..0218cea6be4d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c @@ -70,10 +70,10 @@ static void amdgpu_bo_list_destroy(struct amdgpu_fpriv *fpriv, int id) struct amdgpu_bo_list *list; mutex_lock(&fpriv->bo_list_lock); - list = idr_find(&fpriv->bo_list_handles, id); + list = idr_remove(&fpriv->bo_list_handles, id); if (list) { + /* Another user may have a reference to this list still */ mutex_lock(&list->lock); - idr_remove(&fpriv->bo_list_handles, id); mutex_unlock(&list->lock); amdgpu_bo_list_free(list); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c index 400c66ba4c6b..cf0500671353 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c @@ -135,15 +135,11 @@ static int amdgpu_ctx_free(struct amdgpu_fpriv *fpriv, uint32_t id) struct amdgpu_ctx *ctx; mutex_lock(&mgr->lock); - ctx = idr_find(&mgr->ctx_handles, id); - if (ctx) { - idr_remove(&mgr->ctx_handles, id); + ctx = idr_remove(&mgr->ctx_handles, id); + if (ctx) kref_put(&ctx->refcount, amdgpu_ctx_do_release); - mutex_unlock(&mgr->lock); - return 0; - } mutex_unlock(&mgr->lock); - return -EINVAL; + return ctx ? 0 : -EINVAL; } static int amdgpu_ctx_query(struct amdgpu_device *adev, diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index 04cdac7ab3e3..6130278c5d71 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -1507,7 +1507,7 @@ static ssize_t amd_iommu_show_cap(struct device *dev, struct device_attribute *attr, char *buf) { - struct amd_iommu *iommu = dev_get_drvdata(dev); + struct amd_iommu *iommu = dev_to_amd_iommu(dev); return sprintf(buf, "%x\n", iommu->cap); } static DEVICE_ATTR(cap, S_IRUGO, amd_iommu_show_cap, NULL); @@ -1516,7 +1516,7 @@ static ssize_t amd_iommu_show_features(struct device *dev, struct device_attribute *attr, char *buf) { - struct amd_iommu *iommu = dev_get_drvdata(dev); + struct amd_iommu *iommu = dev_to_amd_iommu(dev); return sprintf(buf, "%llx\n", iommu->features); } static DEVICE_ATTR(features, S_IRUGO, amd_iommu_show_features, NULL); diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h index af00f381a7b1..003f3ceb2661 100644 --- a/drivers/iommu/amd_iommu_types.h +++ b/drivers/iommu/amd_iommu_types.h @@ -569,6 +569,11 @@ struct amd_iommu { volatile u64 __aligned(8) cmd_sem; }; +static inline struct amd_iommu *dev_to_amd_iommu(struct device *dev) +{ + return container_of(dev, struct amd_iommu, iommu.dev); +} + #define ACPIHID_UID_LEN 256 #define ACPIHID_HID_LEN 9 diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index a8f7ae0eb7a4..238ad3447712 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -4730,11 +4730,16 @@ static int intel_iommu_cpu_dead(unsigned int cpu) return 0; } +static inline struct intel_iommu *dev_to_intel_iommu(struct device *dev) +{ + return container_of(dev, struct intel_iommu, iommu.dev); +} + static ssize_t intel_iommu_show_version(struct device *dev, struct device_attribute *attr, char *buf) { - struct intel_iommu *iommu = dev_get_drvdata(dev); + struct intel_iommu *iommu = dev_to_intel_iommu(dev); u32 ver = readl(iommu->reg + DMAR_VER_REG); return sprintf(buf, "%d:%d\n", DMAR_VER_MAJOR(ver), DMAR_VER_MINOR(ver)); @@ -4745,7 +4750,7 @@ static ssize_t intel_iommu_show_address(struct device *dev, struct device_attribute *attr, char *buf) { - struct intel_iommu *iommu = dev_get_drvdata(dev); + struct intel_iommu *iommu = dev_to_intel_iommu(dev); return sprintf(buf, "%llx\n", iommu->reg_phys); } static DEVICE_ATTR(address, S_IRUGO, intel_iommu_show_address, NULL); @@ -4754,7 +4759,7 @@ static ssize_t intel_iommu_show_cap(struct device *dev, struct device_attribute *attr, char *buf) { - struct intel_iommu *iommu = dev_get_drvdata(dev); + struct intel_iommu *iommu = dev_to_intel_iommu(dev); return sprintf(buf, "%llx\n", iommu->cap); } static DEVICE_ATTR(cap, S_IRUGO, intel_iommu_show_cap, NULL); @@ -4763,7 +4768,7 @@ static ssize_t intel_iommu_show_ecap(struct device *dev, struct device_attribute *attr, char *buf) { - struct intel_iommu *iommu = dev_get_drvdata(dev); + struct intel_iommu *iommu = dev_to_intel_iommu(dev); return sprintf(buf, "%llx\n", iommu->ecap); } static DEVICE_ATTR(ecap, S_IRUGO, intel_iommu_show_ecap, NULL); @@ -4772,7 +4777,7 @@ static ssize_t intel_iommu_show_ndoms(struct device *dev, struct device_attribute *attr, char *buf) { - struct intel_iommu *iommu = dev_get_drvdata(dev); + struct intel_iommu *iommu = dev_to_intel_iommu(dev); return sprintf(buf, "%ld\n", cap_ndoms(iommu->cap)); } static DEVICE_ATTR(domains_supported, S_IRUGO, intel_iommu_show_ndoms, NULL); @@ -4781,7 +4786,7 @@ static ssize_t intel_iommu_show_ndoms_used(struct device *dev, struct device_attribute *attr, char *buf) { - struct intel_iommu *iommu = dev_get_drvdata(dev); + struct intel_iommu *iommu = dev_to_intel_iommu(dev); return sprintf(buf, "%d\n", bitmap_weight(iommu->domain_ids, cap_ndoms(iommu->cap))); } diff --git a/drivers/net/ethernet/amd/declance.c b/drivers/net/ethernet/amd/declance.c index 76e5fc7adff5..6c98901f1b89 100644 --- a/drivers/net/ethernet/amd/declance.c +++ b/drivers/net/ethernet/amd/declance.c @@ -1276,18 +1276,6 @@ err_out: return ret; } -static void __exit dec_lance_remove(struct device *bdev) -{ - struct net_device *dev = dev_get_drvdata(bdev); - resource_size_t start, len; - - unregister_netdev(dev); - start = to_tc_dev(bdev)->resource.start; - len = to_tc_dev(bdev)->resource.end - start + 1; - release_mem_region(start, len); - free_netdev(dev); -} - /* Find all the lance cards on the system and initialize them */ static int __init dec_lance_platform_probe(void) { @@ -1320,7 +1308,7 @@ static void __exit dec_lance_platform_remove(void) #ifdef CONFIG_TC static int dec_lance_tc_probe(struct device *dev); -static int __exit dec_lance_tc_remove(struct device *dev); +static int dec_lance_tc_remove(struct device *dev); static const struct tc_device_id dec_lance_tc_table[] = { { "DEC ", "PMAD-AA " }, @@ -1334,7 +1322,7 @@ static struct tc_driver dec_lance_tc_driver = { .name = "declance", .bus = &tc_bus_type, .probe = dec_lance_tc_probe, - .remove = __exit_p(dec_lance_tc_remove), + .remove = dec_lance_tc_remove, }, }; @@ -1346,7 +1334,19 @@ static int dec_lance_tc_probe(struct device *dev) return status; } -static int __exit dec_lance_tc_remove(struct device *dev) +static void dec_lance_remove(struct device *bdev) +{ + struct net_device *dev = dev_get_drvdata(bdev); + resource_size_t start, len; + + unregister_netdev(dev); + start = to_tc_dev(bdev)->resource.start; + len = to_tc_dev(bdev)->resource.end - start + 1; + release_mem_region(start, len); + free_netdev(dev); +} + +static int dec_lance_tc_remove(struct device *dev) { put_device(dev); dec_lance_remove(dev); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c index a7d16db5c4b2..937f37a5dcb2 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c @@ -1323,7 +1323,7 @@ static int xgbe_read_ext_mii_regs(struct xgbe_prv_data *pdata, int addr, static int xgbe_set_ext_mii_mode(struct xgbe_prv_data *pdata, unsigned int port, enum xgbe_mdio_mode mode) { - unsigned int reg_val = 0; + unsigned int reg_val = XGMAC_IOREAD(pdata, MAC_MDIOCL22R); switch (mode) { case XGBE_MDIO_MODE_CL22: diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index 3aa457c8ca21..248f60d171a5 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -1131,12 +1131,12 @@ static void xgbe_stop(struct xgbe_prv_data *pdata) hw_if->disable_tx(pdata); hw_if->disable_rx(pdata); + phy_if->phy_stop(pdata); + xgbe_free_irqs(pdata); xgbe_napi_disable(pdata, 1); - phy_if->phy_stop(pdata); - hw_if->exit(pdata); channel = pdata->channel; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c index 9d8c953083b4..e707c49cc55a 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c @@ -716,6 +716,8 @@ static void xgbe_phy_sfp_phy_settings(struct xgbe_prv_data *pdata) pdata->phy.duplex = DUPLEX_UNKNOWN; pdata->phy.autoneg = AUTONEG_ENABLE; pdata->phy.advertising = pdata->phy.supported; + + return; } pdata->phy.advertising &= ~ADVERTISED_Autoneg; @@ -875,6 +877,16 @@ static int xgbe_phy_find_phy_device(struct xgbe_prv_data *pdata) !phy_data->sfp_phy_avail) return 0; + /* Set the proper MDIO mode for the PHY */ + ret = pdata->hw_if.set_ext_mii_mode(pdata, phy_data->mdio_addr, + phy_data->phydev_mode); + if (ret) { + netdev_err(pdata->netdev, + "mdio port/clause not compatible (%u/%u)\n", + phy_data->mdio_addr, phy_data->phydev_mode); + return ret; + } + /* Create and connect to the PHY device */ phydev = get_phy_device(phy_data->mii, phy_data->mdio_addr, (phy_data->phydev_mode == XGBE_MDIO_MODE_CL45)); @@ -2722,6 +2734,18 @@ static int xgbe_phy_start(struct xgbe_prv_data *pdata) if (ret) return ret; + /* Set the proper MDIO mode for the re-driver */ + if (phy_data->redrv && !phy_data->redrv_if) { + ret = pdata->hw_if.set_ext_mii_mode(pdata, phy_data->redrv_addr, + XGBE_MDIO_MODE_CL22); + if (ret) { + netdev_err(pdata->netdev, + "redriver mdio port not compatible (%u)\n", + phy_data->redrv_addr); + return ret; + } + } + /* Start in highest supported mode */ xgbe_phy_set_mode(pdata, phy_data->start_mode); diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c index e536301acfde..b3568c453b14 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c @@ -1749,6 +1749,12 @@ static int xgene_enet_get_resources(struct xgene_enet_pdata *pdata) pdata->clk = devm_clk_get(&pdev->dev, NULL); if (IS_ERR(pdata->clk)) { + /* Abort if the clock is defined but couldn't be retrived. + * Always abort if the clock is missing on DT system as + * the driver can't cope with this case. + */ + if (PTR_ERR(pdata->clk) != -ENOENT || dev->of_node) + return PTR_ERR(pdata->clk); /* Firmware may have set up the clock already. */ dev_info(dev, "clocks have been setup already\n"); } diff --git a/drivers/net/ethernet/broadcom/sb1250-mac.c b/drivers/net/ethernet/broadcom/sb1250-mac.c index 89d4feba1a9a..55c8e25b43d9 100644 --- a/drivers/net/ethernet/broadcom/sb1250-mac.c +++ b/drivers/net/ethernet/broadcom/sb1250-mac.c @@ -2617,7 +2617,7 @@ out_out: return err; } -static int __exit sbmac_remove(struct platform_device *pldev) +static int sbmac_remove(struct platform_device *pldev) { struct net_device *dev = platform_get_drvdata(pldev); struct sbmac_softc *sc = netdev_priv(dev); @@ -2634,7 +2634,7 @@ static int __exit sbmac_remove(struct platform_device *pldev) static struct platform_driver sbmac_driver = { .probe = sbmac_probe, - .remove = __exit_p(sbmac_remove), + .remove = sbmac_remove, .driver = { .name = sbmac_string, }, diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h index 5fdaa16426c5..fa376444e57c 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h @@ -37,7 +37,7 @@ #define T4FW_VERSION_MAJOR 0x01 #define T4FW_VERSION_MINOR 0x10 -#define T4FW_VERSION_MICRO 0x1A +#define T4FW_VERSION_MICRO 0x21 #define T4FW_VERSION_BUILD 0x00 #define T4FW_MIN_VERSION_MAJOR 0x01 @@ -46,7 +46,7 @@ #define T5FW_VERSION_MAJOR 0x01 #define T5FW_VERSION_MINOR 0x10 -#define T5FW_VERSION_MICRO 0x1A +#define T5FW_VERSION_MICRO 0x21 #define T5FW_VERSION_BUILD 0x00 #define T5FW_MIN_VERSION_MAJOR 0x00 @@ -55,7 +55,7 @@ #define T6FW_VERSION_MAJOR 0x01 #define T6FW_VERSION_MINOR 0x10 -#define T6FW_VERSION_MICRO 0x1A +#define T6FW_VERSION_MICRO 0x21 #define T6FW_VERSION_BUILD 0x00 #define T6FW_MIN_VERSION_MAJOR 0x00 diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c index 262587240c86..928b0df2b8e0 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.c +++ b/drivers/net/ethernet/faraday/ftgmac100.c @@ -1456,7 +1456,7 @@ err_alloc_etherdev: return err; } -static int __exit ftgmac100_remove(struct platform_device *pdev) +static int ftgmac100_remove(struct platform_device *pdev) { struct net_device *netdev; struct ftgmac100 *priv; @@ -1483,7 +1483,7 @@ MODULE_DEVICE_TABLE(of, ftgmac100_of_match); static struct platform_driver ftgmac100_driver = { .probe = ftgmac100_probe, - .remove = __exit_p(ftgmac100_remove), + .remove = ftgmac100_remove, .driver = { .name = DRV_NAME, .of_match_table = ftgmac100_of_match, diff --git a/drivers/net/ethernet/faraday/ftmac100.c b/drivers/net/ethernet/faraday/ftmac100.c index c0ddbbe6c226..6ac336b546e6 100644 --- a/drivers/net/ethernet/faraday/ftmac100.c +++ b/drivers/net/ethernet/faraday/ftmac100.c @@ -1156,7 +1156,7 @@ err_alloc_etherdev: return err; } -static int __exit ftmac100_remove(struct platform_device *pdev) +static int ftmac100_remove(struct platform_device *pdev) { struct net_device *netdev; struct ftmac100 *priv; @@ -1176,7 +1176,7 @@ static int __exit ftmac100_remove(struct platform_device *pdev) static struct platform_driver ftmac100_driver = { .probe = ftmac100_probe, - .remove = __exit_p(ftmac100_remove), + .remove = ftmac100_remove, .driver = { .name = DRV_NAME, }, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index d7ac22d7f940..bd8de6b9be71 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -441,30 +441,40 @@ static int mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr, struct mlxsw_sp_prefix_usage *req_prefix_usage) { - struct mlxsw_sp_lpm_tree *lpm_tree; + struct mlxsw_sp_lpm_tree *lpm_tree = vr->lpm_tree; + struct mlxsw_sp_lpm_tree *new_tree; + int err; - if (mlxsw_sp_prefix_usage_eq(req_prefix_usage, - &vr->lpm_tree->prefix_usage)) + if (mlxsw_sp_prefix_usage_eq(req_prefix_usage, &lpm_tree->prefix_usage)) return 0; - lpm_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, req_prefix_usage, + new_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, req_prefix_usage, vr->proto, false); - if (IS_ERR(lpm_tree)) { + if (IS_ERR(new_tree)) { /* We failed to get a tree according to the required * prefix usage. However, the current tree might be still good * for us if our requirement is subset of the prefixes used * in the tree. */ if (mlxsw_sp_prefix_usage_subset(req_prefix_usage, - &vr->lpm_tree->prefix_usage)) + &lpm_tree->prefix_usage)) return 0; - return PTR_ERR(lpm_tree); + return PTR_ERR(new_tree); } - mlxsw_sp_vr_lpm_tree_unbind(mlxsw_sp, vr); - mlxsw_sp_lpm_tree_put(mlxsw_sp, vr->lpm_tree); + /* Prevent packet loss by overwriting existing binding */ + vr->lpm_tree = new_tree; + err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, vr); + if (err) + goto err_tree_bind; + mlxsw_sp_lpm_tree_put(mlxsw_sp, lpm_tree); + + return 0; + +err_tree_bind: vr->lpm_tree = lpm_tree; - return mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, vr); + mlxsw_sp_lpm_tree_put(mlxsw_sp, new_tree); + return err; } static struct mlxsw_sp_vr *mlxsw_sp_vr_get(struct mlxsw_sp *mlxsw_sp, diff --git a/drivers/net/ethernet/seeq/sgiseeq.c b/drivers/net/ethernet/seeq/sgiseeq.c index ed34196028b8..70347720fdf9 100644 --- a/drivers/net/ethernet/seeq/sgiseeq.c +++ b/drivers/net/ethernet/seeq/sgiseeq.c @@ -807,7 +807,7 @@ err_out: return err; } -static int __exit sgiseeq_remove(struct platform_device *pdev) +static int sgiseeq_remove(struct platform_device *pdev) { struct net_device *dev = platform_get_drvdata(pdev); struct sgiseeq_private *sp = netdev_priv(dev); @@ -822,7 +822,7 @@ static int __exit sgiseeq_remove(struct platform_device *pdev) static struct platform_driver sgiseeq_driver = { .probe = sgiseeq_probe, - .remove = __exit_p(sgiseeq_remove), + .remove = sgiseeq_remove, .driver = { .name = "sgiseeq", } diff --git a/drivers/net/ethernet/sgi/meth.c b/drivers/net/ethernet/sgi/meth.c index 69d2d30e5ef1..ea55abd62ec7 100644 --- a/drivers/net/ethernet/sgi/meth.c +++ b/drivers/net/ethernet/sgi/meth.c @@ -854,7 +854,7 @@ static int meth_probe(struct platform_device *pdev) return 0; } -static int __exit meth_remove(struct platform_device *pdev) +static int meth_remove(struct platform_device *pdev) { struct net_device *dev = platform_get_drvdata(pdev); @@ -866,7 +866,7 @@ static int __exit meth_remove(struct platform_device *pdev) static struct platform_driver meth_driver = { .probe = meth_probe, - .remove = __exit_p(meth_remove), + .remove = meth_remove, .driver = { .name = "meth", } diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 45301cb98bc1..7074b40ebd7f 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -881,12 +881,14 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev) info = &geneve->info; } + rcu_read_lock(); #if IS_ENABLED(CONFIG_IPV6) if (info->mode & IP_TUNNEL_INFO_IPV6) err = geneve6_xmit_skb(skb, dev, geneve, info); else #endif err = geneve_xmit_skb(skb, dev, geneve, info); + rcu_read_unlock(); if (likely(!err)) return NETDEV_TX_OK; diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c index 6e98ede997d3..0dd510604118 100644 --- a/drivers/net/usb/asix_devices.c +++ b/drivers/net/usb/asix_devices.c @@ -346,7 +346,7 @@ static int ax88772_reset(struct usbnet *dev) if (ret < 0) goto out; - asix_write_medium_mode(dev, AX88772_MEDIUM_DEFAULT, 0); + ret = asix_write_medium_mode(dev, AX88772_MEDIUM_DEFAULT, 0); if (ret < 0) goto out; diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index b7911994112a..e375560cc74e 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2105,6 +2105,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, src_port = udp_flow_src_port(dev_net(dev), skb, vxlan->cfg.port_min, vxlan->cfg.port_max, true); + rcu_read_lock(); if (dst->sa.sa_family == AF_INET) { struct vxlan_sock *sock4 = rcu_dereference(vxlan->vn4_sock); struct rtable *rt; @@ -2127,7 +2128,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, dst_port, vni, &rt->dst, rt->rt_flags); if (err) - return; + goto out_unlock; } else if (info->key.tun_flags & TUNNEL_DONT_FRAGMENT) { df = htons(IP_DF); } @@ -2166,7 +2167,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, dst_port, vni, ndst, rt6i_flags); if (err) - return; + goto out_unlock; } tos = ip_tunnel_ecn_encap(tos, old_iph, skb); @@ -2183,6 +2184,8 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, label, src_port, dst_port, !udp_sum); #endif } +out_unlock: + rcu_read_unlock(); return; drop: @@ -2191,6 +2194,7 @@ drop: return; tx_error: + rcu_read_unlock(); if (err == -ELOOP) dev->stats.collisions++; else if (err == -ENETUNREACH) diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 0889fc81ce9e..50c219fb1a52 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -3056,6 +3056,7 @@ static int hwsim_register_received_nl(struct sk_buff *skb_2, static int hwsim_new_radio_nl(struct sk_buff *msg, struct genl_info *info) { struct hwsim_new_radio_params param = { 0 }; + const char *hwname = NULL; param.reg_strict = info->attrs[HWSIM_ATTR_REG_STRICT_REG]; param.p2p_device = info->attrs[HWSIM_ATTR_SUPPORT_P2P_DEVICE]; @@ -3069,8 +3070,14 @@ static int hwsim_new_radio_nl(struct sk_buff *msg, struct genl_info *info) if (info->attrs[HWSIM_ATTR_NO_VIF]) param.no_vif = true; - if (info->attrs[HWSIM_ATTR_RADIO_NAME]) - param.hwname = nla_data(info->attrs[HWSIM_ATTR_RADIO_NAME]); + if (info->attrs[HWSIM_ATTR_RADIO_NAME]) { + hwname = kasprintf(GFP_KERNEL, "%.*s", + nla_len(info->attrs[HWSIM_ATTR_RADIO_NAME]), + (char *)nla_data(info->attrs[HWSIM_ATTR_RADIO_NAME])); + if (!hwname) + return -ENOMEM; + param.hwname = hwname; + } if (info->attrs[HWSIM_ATTR_USE_CHANCTX]) param.use_chanctx = true; @@ -3098,11 +3105,15 @@ static int hwsim_del_radio_nl(struct sk_buff *msg, struct genl_info *info) s64 idx = -1; const char *hwname = NULL; - if (info->attrs[HWSIM_ATTR_RADIO_ID]) + if (info->attrs[HWSIM_ATTR_RADIO_ID]) { idx = nla_get_u32(info->attrs[HWSIM_ATTR_RADIO_ID]); - else if (info->attrs[HWSIM_ATTR_RADIO_NAME]) - hwname = (void *)nla_data(info->attrs[HWSIM_ATTR_RADIO_NAME]); - else + } else if (info->attrs[HWSIM_ATTR_RADIO_NAME]) { + hwname = kasprintf(GFP_KERNEL, "%.*s", + nla_len(info->attrs[HWSIM_ATTR_RADIO_NAME]), + (char *)nla_data(info->attrs[HWSIM_ATTR_RADIO_NAME])); + if (!hwname) + return -ENOMEM; + } else return -EINVAL; spin_lock_bh(&hwsim_radio_lock); @@ -3111,7 +3122,8 @@ static int hwsim_del_radio_nl(struct sk_buff *msg, struct genl_info *info) if (data->idx != idx) continue; } else { - if (strcmp(hwname, wiphy_name(data->hw->wiphy))) + if (!hwname || + strcmp(hwname, wiphy_name(data->hw->wiphy))) continue; } @@ -3122,10 +3134,12 @@ static int hwsim_del_radio_nl(struct sk_buff *msg, struct genl_info *info) spin_unlock_bh(&hwsim_radio_lock); mac80211_hwsim_del_radio(data, wiphy_name(data->hw->wiphy), info); + kfree(hwname); return 0; } spin_unlock_bh(&hwsim_radio_lock); + kfree(hwname); return -ENODEV; } diff --git a/drivers/net/wireless/marvell/mwifiex/txrx.c b/drivers/net/wireless/marvell/mwifiex/txrx.c index abdd0cf710bf..fac28bd8fbee 100644 --- a/drivers/net/wireless/marvell/mwifiex/txrx.c +++ b/drivers/net/wireless/marvell/mwifiex/txrx.c @@ -346,9 +346,7 @@ void mwifiex_parse_tx_status_event(struct mwifiex_private *priv, return; spin_lock_irqsave(&priv->ack_status_lock, flags); - ack_skb = idr_find(&priv->ack_status_frames, tx_status->tx_token_id); - if (ack_skb) - idr_remove(&priv->ack_status_frames, tx_status->tx_token_id); + ack_skb = idr_remove(&priv->ack_status_frames, tx_status->tx_token_id); spin_unlock_irqrestore(&priv->ack_status_lock, flags); if (ack_skb) { diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index 5c1cb2df3a54..c3adefe95e50 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -642,9 +642,7 @@ static unsigned int tcmu_handle_completions(struct tcmu_dev *udev) WARN_ON(tcmu_hdr_get_op(entry->hdr.len_op) != TCMU_OP_CMD); spin_lock(&udev->commands_lock); - cmd = idr_find(&udev->commands, entry->hdr.cmd_id); - if (cmd) - idr_remove(&udev->commands, cmd->cmd_id); + cmd = idr_remove(&udev->commands, entry->hdr.cmd_id); spin_unlock(&udev->commands_lock); if (!cmd) { diff --git a/include/linux/idr.h b/include/linux/idr.h index 3c01b89aed67..bf70b3ef0a07 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -12,47 +12,29 @@ #ifndef __IDR_H__ #define __IDR_H__ -#include <linux/types.h> -#include <linux/bitops.h> -#include <linux/init.h> -#include <linux/rcupdate.h> +#include <linux/radix-tree.h> +#include <linux/gfp.h> +#include <linux/percpu.h> + +struct idr { + struct radix_tree_root idr_rt; + unsigned int idr_next; +}; /* - * Using 6 bits at each layer allows us to allocate 7 layers out of each page. - * 8 bits only gave us 3 layers out of every pair of pages, which is less - * efficient except for trees with a largest element between 192-255 inclusive. + * The IDR API does not expose the tagging functionality of the radix tree + * to users. Use tag 0 to track whether a node has free space below it. */ -#define IDR_BITS 6 -#define IDR_SIZE (1 << IDR_BITS) -#define IDR_MASK ((1 << IDR_BITS)-1) - -struct idr_layer { - int prefix; /* the ID prefix of this idr_layer */ - int layer; /* distance from leaf */ - struct idr_layer __rcu *ary[1<<IDR_BITS]; - int count; /* When zero, we can release it */ - union { - /* A zero bit means "space here" */ - DECLARE_BITMAP(bitmap, IDR_SIZE); - struct rcu_head rcu_head; - }; -}; +#define IDR_FREE 0 -struct idr { - struct idr_layer __rcu *hint; /* the last layer allocated from */ - struct idr_layer __rcu *top; - int layers; /* only valid w/o concurrent changes */ - int cur; /* current pos for cyclic allocation */ - spinlock_t lock; - int id_free_cnt; - struct idr_layer *id_free; -}; +/* Set the IDR flag and the IDR_FREE tag */ +#define IDR_RT_MARKER ((__force gfp_t)(3 << __GFP_BITS_SHIFT)) -#define IDR_INIT(name) \ +#define IDR_INIT \ { \ - .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ + .idr_rt = RADIX_TREE_INIT(IDR_RT_MARKER) \ } -#define DEFINE_IDR(name) struct idr name = IDR_INIT(name) +#define DEFINE_IDR(name) struct idr name = IDR_INIT /** * idr_get_cursor - Return the current position of the cyclic allocator @@ -62,9 +44,9 @@ struct idr { * idr_alloc_cyclic() if it is free (otherwise the search will start from * this position). */ -static inline unsigned int idr_get_cursor(struct idr *idr) +static inline unsigned int idr_get_cursor(const struct idr *idr) { - return READ_ONCE(idr->cur); + return READ_ONCE(idr->idr_next); } /** @@ -77,7 +59,7 @@ static inline unsigned int idr_get_cursor(struct idr *idr) */ static inline void idr_set_cursor(struct idr *idr, unsigned int val) { - WRITE_ONCE(idr->cur, val); + WRITE_ONCE(idr->idr_next, val); } /** @@ -97,22 +79,31 @@ static inline void idr_set_cursor(struct idr *idr, unsigned int val) * period). */ -/* - * This is what we export. - */ - -void *idr_find_slowpath(struct idr *idp, int id); void idr_preload(gfp_t gfp_mask); -int idr_alloc(struct idr *idp, void *ptr, int start, int end, gfp_t gfp_mask); -int idr_alloc_cyclic(struct idr *idr, void *ptr, int start, int end, gfp_t gfp_mask); -int idr_for_each(struct idr *idp, +int idr_alloc(struct idr *, void *entry, int start, int end, gfp_t); +int idr_alloc_cyclic(struct idr *, void *entry, int start, int end, gfp_t); +int idr_for_each(const struct idr *, int (*fn)(int id, void *p, void *data), void *data); -void *idr_get_next(struct idr *idp, int *nextid); -void *idr_replace(struct idr *idp, void *ptr, int id); -void idr_remove(struct idr *idp, int id); -void idr_destroy(struct idr *idp); -void idr_init(struct idr *idp); -bool idr_is_empty(struct idr *idp); +void *idr_get_next(struct idr *, int *nextid); +void *idr_replace(struct idr *, void *, int id); +void idr_destroy(struct idr *); + +static inline void *idr_remove(struct idr *idr, int id) +{ + return radix_tree_delete_item(&idr->idr_rt, id, NULL); +} + +static inline void idr_init(struct idr *idr) +{ + INIT_RADIX_TREE(&idr->idr_rt, IDR_RT_MARKER); + idr->idr_next = 0; +} + +static inline bool idr_is_empty(const struct idr *idr) +{ + return radix_tree_empty(&idr->idr_rt) && + radix_tree_tagged(&idr->idr_rt, IDR_FREE); +} /** * idr_preload_end - end preload section started with idr_preload() @@ -137,19 +128,14 @@ static inline void idr_preload_end(void) * This function can be called under rcu_read_lock(), given that the leaf * pointers lifetimes are correctly managed. */ -static inline void *idr_find(struct idr *idr, int id) +static inline void *idr_find(const struct idr *idr, int id) { - struct idr_layer *hint = rcu_dereference_raw(idr->hint); - - if (hint && (id & ~IDR_MASK) == hint->prefix) - return rcu_dereference_raw(hint->ary[id & IDR_MASK]); - - return idr_find_slowpath(idr, id); + return radix_tree_lookup(&idr->idr_rt, id); } /** * idr_for_each_entry - iterate over an idr's elements of a given type - * @idp: idr handle + * @idr: idr handle * @entry: the type * to use as cursor * @id: id entry's key * @@ -157,57 +143,60 @@ static inline void *idr_find(struct idr *idr, int id) * after normal terminatinon @entry is left with the value NULL. This * is convenient for a "not found" value. */ -#define idr_for_each_entry(idp, entry, id) \ - for (id = 0; ((entry) = idr_get_next(idp, &(id))) != NULL; ++id) +#define idr_for_each_entry(idr, entry, id) \ + for (id = 0; ((entry) = idr_get_next(idr, &(id))) != NULL; ++id) /** - * idr_for_each_entry - continue iteration over an idr's elements of a given type - * @idp: idr handle + * idr_for_each_entry_continue - continue iteration over an idr's elements of a given type + * @idr: idr handle * @entry: the type * to use as cursor * @id: id entry's key * * Continue to iterate over list of given type, continuing after * the current position. */ -#define idr_for_each_entry_continue(idp, entry, id) \ - for ((entry) = idr_get_next((idp), &(id)); \ +#define idr_for_each_entry_continue(idr, entry, id) \ + for ((entry) = idr_get_next((idr), &(id)); \ entry; \ - ++id, (entry) = idr_get_next((idp), &(id))) + ++id, (entry) = idr_get_next((idr), &(id))) /* * IDA - IDR based id allocator, use when translation from id to * pointer isn't necessary. - * - * IDA_BITMAP_LONGS is calculated to be one less to accommodate - * ida_bitmap->nr_busy so that the whole struct fits in 128 bytes. */ #define IDA_CHUNK_SIZE 128 /* 128 bytes per chunk */ -#define IDA_BITMAP_LONGS (IDA_CHUNK_SIZE / sizeof(long) - 1) +#define IDA_BITMAP_LONGS (IDA_CHUNK_SIZE / sizeof(long)) #define IDA_BITMAP_BITS (IDA_BITMAP_LONGS * sizeof(long) * 8) struct ida_bitmap { - long nr_busy; unsigned long bitmap[IDA_BITMAP_LONGS]; }; +DECLARE_PER_CPU(struct ida_bitmap *, ida_bitmap); + struct ida { - struct idr idr; - struct ida_bitmap *free_bitmap; + struct radix_tree_root ida_rt; }; -#define IDA_INIT(name) { .idr = IDR_INIT((name).idr), .free_bitmap = NULL, } -#define DEFINE_IDA(name) struct ida name = IDA_INIT(name) +#define IDA_INIT { \ + .ida_rt = RADIX_TREE_INIT(IDR_RT_MARKER | GFP_NOWAIT), \ +} +#define DEFINE_IDA(name) struct ida name = IDA_INIT int ida_pre_get(struct ida *ida, gfp_t gfp_mask); int ida_get_new_above(struct ida *ida, int starting_id, int *p_id); void ida_remove(struct ida *ida, int id); void ida_destroy(struct ida *ida); -void ida_init(struct ida *ida); int ida_simple_get(struct ida *ida, unsigned int start, unsigned int end, gfp_t gfp_mask); void ida_simple_remove(struct ida *ida, unsigned int id); +static inline void ida_init(struct ida *ida) +{ + INIT_RADIX_TREE(&ida->ida_rt, IDR_RT_MARKER | GFP_NOWAIT); +} + /** * ida_get_new - allocate new ID * @ida: idr handle @@ -220,11 +209,8 @@ static inline int ida_get_new(struct ida *ida, int *p_id) return ida_get_new_above(ida, 0, p_id); } -static inline bool ida_is_empty(struct ida *ida) +static inline bool ida_is_empty(const struct ida *ida) { - return idr_is_empty(&ida->idr); + return radix_tree_empty(&ida->ida_rt); } - -void __init idr_init_cache(void); - #endif /* __IDR_H__ */ diff --git a/include/linux/ipmi.h b/include/linux/ipmi.h index 78c5d5ae3857..f1045b2c6a00 100644 --- a/include/linux/ipmi.h +++ b/include/linux/ipmi.h @@ -100,7 +100,7 @@ struct ipmi_user_hndl { /* Create a new user of the IPMI layer on the given interface number. */ int ipmi_create_user(unsigned int if_num, - struct ipmi_user_hndl *handler, + const struct ipmi_user_hndl *handler, void *handler_data, ipmi_user_t *user); diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h index e965e5090d96..a858bcb6220b 100644 --- a/include/linux/mlx4/driver.h +++ b/include/linux/mlx4/driver.h @@ -109,7 +109,7 @@ static inline void mlx4_u64_to_mac(u8 *addr, u64 mac) int i; for (i = ETH_ALEN; i > 0; i--) { - addr[i - 1] = mac && 0xFF; + addr[i - 1] = mac & 0xFF; mac >>= 8; } } diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f40f0ab3847a..97456b2539e4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -330,6 +330,7 @@ struct napi_struct { enum { NAPI_STATE_SCHED, /* Poll is scheduled */ + NAPI_STATE_MISSED, /* reschedule a napi */ NAPI_STATE_DISABLE, /* Disable pending */ NAPI_STATE_NPSVC, /* Netpoll - don't dequeue from poll_list */ NAPI_STATE_HASHED, /* In NAPI hash (busy polling possible) */ @@ -338,12 +339,13 @@ enum { }; enum { - NAPIF_STATE_SCHED = (1UL << NAPI_STATE_SCHED), - NAPIF_STATE_DISABLE = (1UL << NAPI_STATE_DISABLE), - NAPIF_STATE_NPSVC = (1UL << NAPI_STATE_NPSVC), - NAPIF_STATE_HASHED = (1UL << NAPI_STATE_HASHED), - NAPIF_STATE_NO_BUSY_POLL = (1UL << NAPI_STATE_NO_BUSY_POLL), - NAPIF_STATE_IN_BUSY_POLL = (1UL << NAPI_STATE_IN_BUSY_POLL), + NAPIF_STATE_SCHED = BIT(NAPI_STATE_SCHED), + NAPIF_STATE_MISSED = BIT(NAPI_STATE_MISSED), + NAPIF_STATE_DISABLE = BIT(NAPI_STATE_DISABLE), + NAPIF_STATE_NPSVC = BIT(NAPI_STATE_NPSVC), + NAPIF_STATE_HASHED = BIT(NAPI_STATE_HASHED), + NAPIF_STATE_NO_BUSY_POLL = BIT(NAPI_STATE_NO_BUSY_POLL), + NAPIF_STATE_IN_BUSY_POLL = BIT(NAPI_STATE_IN_BUSY_POLL), }; enum gro_result { @@ -414,20 +416,7 @@ static inline bool napi_disable_pending(struct napi_struct *n) return test_bit(NAPI_STATE_DISABLE, &n->state); } -/** - * napi_schedule_prep - check if NAPI can be scheduled - * @n: NAPI context - * - * Test if NAPI routine is already running, and if not mark - * it as running. This is used as a condition variable to - * insure only one NAPI poll instance runs. We also make - * sure there is no pending NAPI disable. - */ -static inline bool napi_schedule_prep(struct napi_struct *n) -{ - return !napi_disable_pending(n) && - !test_and_set_bit(NAPI_STATE_SCHED, &n->state); -} +bool napi_schedule_prep(struct napi_struct *n); /** * napi_schedule - schedule NAPI poll diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 52bda854593b..3e5735064b71 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -22,11 +22,13 @@ #define _LINUX_RADIX_TREE_H #include <linux/bitops.h> -#include <linux/preempt.h> -#include <linux/types.h> #include <linux/bug.h> #include <linux/kernel.h> +#include <linux/list.h> +#include <linux/preempt.h> #include <linux/rcupdate.h> +#include <linux/spinlock.h> +#include <linux/types.h> /* * The bottom two bits of the slot determine how the remaining bits in the @@ -94,7 +96,7 @@ struct radix_tree_node { unsigned char count; /* Total entry count */ unsigned char exceptional; /* Exceptional entry count */ struct radix_tree_node *parent; /* Used when ascending tree */ - void *private_data; /* For tree user */ + struct radix_tree_root *root; /* The tree we belong to */ union { struct list_head private_list; /* For tree user */ struct rcu_head rcu_head; /* Used when freeing node */ @@ -103,7 +105,10 @@ struct radix_tree_node { unsigned long tags[RADIX_TREE_MAX_TAGS][RADIX_TREE_TAG_LONGS]; }; -/* root tags are stored in gfp_mask, shifted by __GFP_BITS_SHIFT */ +/* The top bits of gfp_mask are used to store the root tags and the IDR flag */ +#define ROOT_IS_IDR ((__force gfp_t)(1 << __GFP_BITS_SHIFT)) +#define ROOT_TAG_SHIFT (__GFP_BITS_SHIFT + 1) + struct radix_tree_root { gfp_t gfp_mask; struct radix_tree_node __rcu *rnode; @@ -123,7 +128,7 @@ do { \ (root)->rnode = NULL; \ } while (0) -static inline bool radix_tree_empty(struct radix_tree_root *root) +static inline bool radix_tree_empty(const struct radix_tree_root *root) { return root->rnode == NULL; } @@ -216,10 +221,8 @@ static inline unsigned int iter_shift(const struct radix_tree_iter *iter) */ /** - * radix_tree_deref_slot - dereference a slot - * @pslot: pointer to slot, returned by radix_tree_lookup_slot - * Returns: item that was stored in that slot with any direct pointer flag - * removed. + * radix_tree_deref_slot - dereference a slot + * @slot: slot pointer, returned by radix_tree_lookup_slot * * For use with radix_tree_lookup_slot(). Caller must hold tree at least read * locked across slot lookup and dereference. Not required if write lock is @@ -227,26 +230,27 @@ static inline unsigned int iter_shift(const struct radix_tree_iter *iter) * * radix_tree_deref_retry must be used to confirm validity of the pointer if * only the read lock is held. + * + * Return: entry stored in that slot. */ -static inline void *radix_tree_deref_slot(void **pslot) +static inline void *radix_tree_deref_slot(void __rcu **slot) { - return rcu_dereference(*pslot); + return rcu_dereference(*slot); } /** - * radix_tree_deref_slot_protected - dereference a slot without RCU lock but with tree lock held - * @pslot: pointer to slot, returned by radix_tree_lookup_slot - * Returns: item that was stored in that slot with any direct pointer flag - * removed. - * - * Similar to radix_tree_deref_slot but only used during migration when a pages - * mapping is being moved. The caller does not hold the RCU read lock but it - * must hold the tree lock to prevent parallel updates. + * radix_tree_deref_slot_protected - dereference a slot with tree lock held + * @slot: slot pointer, returned by radix_tree_lookup_slot + * + * Similar to radix_tree_deref_slot. The caller does not hold the RCU read + * lock but it must hold the tree lock to prevent parallel updates. + * + * Return: entry stored in that slot. */ -static inline void *radix_tree_deref_slot_protected(void **pslot, +static inline void *radix_tree_deref_slot_protected(void __rcu **slot, spinlock_t *treelock) { - return rcu_dereference_protected(*pslot, lockdep_is_held(treelock)); + return rcu_dereference_protected(*slot, lockdep_is_held(treelock)); } /** @@ -282,9 +286,9 @@ static inline int radix_tree_exception(void *arg) return unlikely((unsigned long)arg & RADIX_TREE_ENTRY_MASK); } -int __radix_tree_create(struct radix_tree_root *root, unsigned long index, +int __radix_tree_create(struct radix_tree_root *, unsigned long index, unsigned order, struct radix_tree_node **nodep, - void ***slotp); + void __rcu ***slotp); int __radix_tree_insert(struct radix_tree_root *, unsigned long index, unsigned order, void *); static inline int radix_tree_insert(struct radix_tree_root *root, @@ -292,55 +296,56 @@ static inline int radix_tree_insert(struct radix_tree_root *root, { return __radix_tree_insert(root, index, 0, entry); } -void *__radix_tree_lookup(struct radix_tree_root *root, unsigned long index, - struct radix_tree_node **nodep, void ***slotp); -void *radix_tree_lookup(struct radix_tree_root *, unsigned long); -void **radix_tree_lookup_slot(struct radix_tree_root *, unsigned long); +void *__radix_tree_lookup(const struct radix_tree_root *, unsigned long index, + struct radix_tree_node **nodep, void __rcu ***slotp); +void *radix_tree_lookup(const struct radix_tree_root *, unsigned long); +void __rcu **radix_tree_lookup_slot(const struct radix_tree_root *, + unsigned long index); typedef void (*radix_tree_update_node_t)(struct radix_tree_node *, void *); -void __radix_tree_replace(struct radix_tree_root *root, - struct radix_tree_node *node, - void **slot, void *item, +void __radix_tree_replace(struct radix_tree_root *, struct radix_tree_node *, + void __rcu **slot, void *entry, radix_tree_update_node_t update_node, void *private); void radix_tree_iter_replace(struct radix_tree_root *, - const struct radix_tree_iter *, void **slot, void *item); -void radix_tree_replace_slot(struct radix_tree_root *root, - void **slot, void *item); -void __radix_tree_delete_node(struct radix_tree_root *root, - struct radix_tree_node *node, + const struct radix_tree_iter *, void __rcu **slot, void *entry); +void radix_tree_replace_slot(struct radix_tree_root *, + void __rcu **slot, void *entry); +void __radix_tree_delete_node(struct radix_tree_root *, + struct radix_tree_node *, radix_tree_update_node_t update_node, void *private); +void radix_tree_iter_delete(struct radix_tree_root *, + struct radix_tree_iter *iter, void __rcu **slot); void *radix_tree_delete_item(struct radix_tree_root *, unsigned long, void *); void *radix_tree_delete(struct radix_tree_root *, unsigned long); -void radix_tree_clear_tags(struct radix_tree_root *root, - struct radix_tree_node *node, - void **slot); -unsigned int radix_tree_gang_lookup(struct radix_tree_root *root, +void radix_tree_clear_tags(struct radix_tree_root *, struct radix_tree_node *, + void __rcu **slot); +unsigned int radix_tree_gang_lookup(const struct radix_tree_root *, void **results, unsigned long first_index, unsigned int max_items); -unsigned int radix_tree_gang_lookup_slot(struct radix_tree_root *root, - void ***results, unsigned long *indices, +unsigned int radix_tree_gang_lookup_slot(const struct radix_tree_root *, + void __rcu ***results, unsigned long *indices, unsigned long first_index, unsigned int max_items); int radix_tree_preload(gfp_t gfp_mask); int radix_tree_maybe_preload(gfp_t gfp_mask); int radix_tree_maybe_preload_order(gfp_t gfp_mask, int order); void radix_tree_init(void); -void *radix_tree_tag_set(struct radix_tree_root *root, +void *radix_tree_tag_set(struct radix_tree_root *, unsigned long index, unsigned int tag); -void *radix_tree_tag_clear(struct radix_tree_root *root, +void *radix_tree_tag_clear(struct radix_tree_root *, unsigned long index, unsigned int tag); -int radix_tree_tag_get(struct radix_tree_root *root, +int radix_tree_tag_get(const struct radix_tree_root *, unsigned long index, unsigned int tag); -void radix_tree_iter_tag_set(struct radix_tree_root *root, +void radix_tree_iter_tag_set(struct radix_tree_root *, + const struct radix_tree_iter *iter, unsigned int tag); +void radix_tree_iter_tag_clear(struct radix_tree_root *, const struct radix_tree_iter *iter, unsigned int tag); -unsigned int -radix_tree_gang_lookup_tag(struct radix_tree_root *root, void **results, - unsigned long first_index, unsigned int max_items, - unsigned int tag); -unsigned int -radix_tree_gang_lookup_tag_slot(struct radix_tree_root *root, void ***results, - unsigned long first_index, unsigned int max_items, - unsigned int tag); -int radix_tree_tagged(struct radix_tree_root *root, unsigned int tag); +unsigned int radix_tree_gang_lookup_tag(const struct radix_tree_root *, + void **results, unsigned long first_index, + unsigned int max_items, unsigned int tag); +unsigned int radix_tree_gang_lookup_tag_slot(const struct radix_tree_root *, + void __rcu ***results, unsigned long first_index, + unsigned int max_items, unsigned int tag); +int radix_tree_tagged(const struct radix_tree_root *, unsigned int tag); static inline void radix_tree_preload_end(void) { @@ -352,10 +357,14 @@ int radix_tree_split(struct radix_tree_root *, unsigned long index, unsigned new_order); int radix_tree_join(struct radix_tree_root *, unsigned long index, unsigned new_order, void *); +void __rcu **idr_get_free(struct radix_tree_root *, struct radix_tree_iter *, + gfp_t, int end); -#define RADIX_TREE_ITER_TAG_MASK 0x00FF /* tag index in lower byte */ -#define RADIX_TREE_ITER_TAGGED 0x0100 /* lookup tagged slots */ -#define RADIX_TREE_ITER_CONTIG 0x0200 /* stop at first hole */ +enum { + RADIX_TREE_ITER_TAG_MASK = 0x0f, /* tag index in lower nybble */ + RADIX_TREE_ITER_TAGGED = 0x10, /* lookup tagged slots */ + RADIX_TREE_ITER_CONTIG = 0x20, /* stop at first hole */ +}; /** * radix_tree_iter_init - initialize radix tree iterator @@ -364,7 +373,7 @@ int radix_tree_join(struct radix_tree_root *, unsigned long index, * @start: iteration starting index * Returns: NULL */ -static __always_inline void ** +static __always_inline void __rcu ** radix_tree_iter_init(struct radix_tree_iter *iter, unsigned long start) { /* @@ -393,10 +402,46 @@ radix_tree_iter_init(struct radix_tree_iter *iter, unsigned long start) * Also it fills @iter with data about chunk: position in the tree (index), * its end (next_index), and constructs a bit mask for tagged iterating (tags). */ -void **radix_tree_next_chunk(struct radix_tree_root *root, +void __rcu **radix_tree_next_chunk(const struct radix_tree_root *, struct radix_tree_iter *iter, unsigned flags); /** + * radix_tree_iter_lookup - look up an index in the radix tree + * @root: radix tree root + * @iter: iterator state + * @index: key to look up + * + * If @index is present in the radix tree, this function returns the slot + * containing it and updates @iter to describe the entry. If @index is not + * present, it returns NULL. + */ +static inline void __rcu ** +radix_tree_iter_lookup(const struct radix_tree_root *root, + struct radix_tree_iter *iter, unsigned long index) +{ + radix_tree_iter_init(iter, index); + return radix_tree_next_chunk(root, iter, RADIX_TREE_ITER_CONTIG); +} + +/** + * radix_tree_iter_find - find a present entry + * @root: radix tree root + * @iter: iterator state + * @index: start location + * + * This function returns the slot containing the entry with the lowest index + * which is at least @index. If @index is larger than any present entry, this + * function returns NULL. The @iter is updated to describe the entry found. + */ +static inline void __rcu ** +radix_tree_iter_find(const struct radix_tree_root *root, + struct radix_tree_iter *iter, unsigned long index) +{ + radix_tree_iter_init(iter, index); + return radix_tree_next_chunk(root, iter, 0); +} + +/** * radix_tree_iter_retry - retry this chunk of the iteration * @iter: iterator state * @@ -406,7 +451,7 @@ void **radix_tree_next_chunk(struct radix_tree_root *root, * and continue the iteration. */ static inline __must_check -void **radix_tree_iter_retry(struct radix_tree_iter *iter) +void __rcu **radix_tree_iter_retry(struct radix_tree_iter *iter) { iter->next_index = iter->index; iter->tags = 0; @@ -429,7 +474,7 @@ __radix_tree_iter_add(struct radix_tree_iter *iter, unsigned long slots) * have been invalidated by an insertion or deletion. Call this function * before releasing the lock to continue the iteration from the next index. */ -void **__must_check radix_tree_iter_resume(void **slot, +void __rcu **__must_check radix_tree_iter_resume(void __rcu **slot, struct radix_tree_iter *iter); /** @@ -445,11 +490,11 @@ radix_tree_chunk_size(struct radix_tree_iter *iter) } #ifdef CONFIG_RADIX_TREE_MULTIORDER -void ** __radix_tree_next_slot(void **slot, struct radix_tree_iter *iter, - unsigned flags); +void __rcu **__radix_tree_next_slot(void __rcu **slot, + struct radix_tree_iter *iter, unsigned flags); #else /* Can't happen without sibling entries, but the compiler can't tell that */ -static inline void ** __radix_tree_next_slot(void **slot, +static inline void __rcu **__radix_tree_next_slot(void __rcu **slot, struct radix_tree_iter *iter, unsigned flags) { return slot; @@ -475,8 +520,8 @@ static inline void ** __radix_tree_next_slot(void **slot, * b) we are doing non-tagged iteration, and iter->index and iter->next_index * have been set up so that radix_tree_chunk_size() returns 1 or 0. */ -static __always_inline void ** -radix_tree_next_slot(void **slot, struct radix_tree_iter *iter, unsigned flags) +static __always_inline void __rcu **radix_tree_next_slot(void __rcu **slot, + struct radix_tree_iter *iter, unsigned flags) { if (flags & RADIX_TREE_ITER_TAGGED) { iter->tags >>= 1; @@ -514,7 +559,7 @@ radix_tree_next_slot(void **slot, struct radix_tree_iter *iter, unsigned flags) return NULL; found: - if (unlikely(radix_tree_is_internal_node(*slot))) + if (unlikely(radix_tree_is_internal_node(rcu_dereference_raw(*slot)))) return __radix_tree_next_slot(slot, iter, flags); return slot; } diff --git a/include/net/sock.h b/include/net/sock.h index 9ccefa5c5487..5e5997654db6 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1526,6 +1526,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, void sk_free(struct sock *sk); void sk_destruct(struct sock *sk); struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority); +void sk_free_unlock_clone(struct sock *sk); struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, gfp_t priority); diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 593f586545eb..39123c06a566 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -119,6 +119,7 @@ enum rxrpc_recvmsg_trace { rxrpc_recvmsg_full, rxrpc_recvmsg_hole, rxrpc_recvmsg_next, + rxrpc_recvmsg_requeue, rxrpc_recvmsg_return, rxrpc_recvmsg_terminal, rxrpc_recvmsg_to_be_accepted, @@ -277,6 +278,7 @@ enum rxrpc_congest_change { EM(rxrpc_recvmsg_full, "FULL") \ EM(rxrpc_recvmsg_hole, "HOLE") \ EM(rxrpc_recvmsg_next, "NEXT") \ + EM(rxrpc_recvmsg_requeue, "REQU") \ EM(rxrpc_recvmsg_return, "RETN") \ EM(rxrpc_recvmsg_terminal, "TERM") \ EM(rxrpc_recvmsg_to_be_accepted, "TBAC") \ diff --git a/init/main.c b/init/main.c index 47ea22d181ef..ae9f2008fb86 100644 --- a/init/main.c +++ b/init/main.c @@ -554,7 +554,7 @@ asmlinkage __visible void __init start_kernel(void) if (WARN(!irqs_disabled(), "Interrupts were enabled *very* early, fixing it\n")) local_irq_disable(); - idr_init_cache(); + radix_tree_init(); /* * Allow workqueue creation and work item queueing/cancelling @@ -569,7 +569,6 @@ asmlinkage __visible void __init start_kernel(void) trace_init(); context_tracking_init(); - radix_tree_init(); /* init some links before init_ISA_irqs() */ early_irq_init(); init_IRQ(); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 3fc6e39b223e..796b68d00119 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -33,7 +33,7 @@ * - out of bounds or malformed jumps * The second pass is all possible path descent from the 1st insn. * Since it's analyzing all pathes through the program, the length of the - * analysis is limited to 32k insn, which may be hit even if total number of + * analysis is limited to 64k insn, which may be hit even if total number of * insn is less then 4K, but there are too many branches that change stack/regs. * Number of 'branches to be analyzed' is limited to 1k * diff --git a/lib/Makefile b/lib/Makefile index 469b2392893a..320ac46a8725 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -25,6 +25,9 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \ earlycpio.o seq_buf.o siphash.o \ nmi_backtrace.o nodemask.o win_minmax.o +CFLAGS_radix-tree.o += -DCONFIG_SPARSE_RCU_POINTER +CFLAGS_idr.o += -DCONFIG_SPARSE_RCU_POINTER + lib-$(CONFIG_MMU) += ioremap.o lib-$(CONFIG_SMP) += cpumask.o lib-$(CONFIG_DMA_NOOP_OPS) += dma-noop.o diff --git a/lib/idr.c b/lib/idr.c index 52d2979a05e8..b13682bb0a1c 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -1,1068 +1,409 @@ -/* - * 2002-10-18 written by Jim Houston jim.houston@ccur.com - * Copyright (C) 2002 by Concurrent Computer Corporation - * Distributed under the GNU GPL license version 2. - * - * Modified by George Anzinger to reuse immediately and to use - * find bit instructions. Also removed _irq on spinlocks. - * - * Modified by Nadia Derbey to make it RCU safe. - * - * Small id to pointer translation service. - * - * It uses a radix tree like structure as a sparse array indexed - * by the id to obtain the pointer. The bitmap makes allocating - * a new id quick. - * - * You call it to allocate an id (an int) an associate with that id a - * pointer or what ever, we treat it as a (void *). You can pass this - * id to a user for him to pass back at a later time. You then pass - * that id to this code and it returns your pointer. - */ - -#ifndef TEST // to test in user space... -#include <linux/slab.h> -#include <linux/init.h> +#include <linux/bitmap.h> #include <linux/export.h> -#endif -#include <linux/err.h> -#include <linux/string.h> #include <linux/idr.h> +#include <linux/slab.h> #include <linux/spinlock.h> -#include <linux/percpu.h> - -#define MAX_IDR_SHIFT (sizeof(int) * 8 - 1) -#define MAX_IDR_BIT (1U << MAX_IDR_SHIFT) - -/* Leave the possibility of an incomplete final layer */ -#define MAX_IDR_LEVEL ((MAX_IDR_SHIFT + IDR_BITS - 1) / IDR_BITS) -/* Number of id_layer structs to leave in free list */ -#define MAX_IDR_FREE (MAX_IDR_LEVEL * 2) - -static struct kmem_cache *idr_layer_cache; -static DEFINE_PER_CPU(struct idr_layer *, idr_preload_head); -static DEFINE_PER_CPU(int, idr_preload_cnt); +DEFINE_PER_CPU(struct ida_bitmap *, ida_bitmap); static DEFINE_SPINLOCK(simple_ida_lock); -/* the maximum ID which can be allocated given idr->layers */ -static int idr_max(int layers) -{ - int bits = min_t(int, layers * IDR_BITS, MAX_IDR_SHIFT); - - return (1 << bits) - 1; -} - -/* - * Prefix mask for an idr_layer at @layer. For layer 0, the prefix mask is - * all bits except for the lower IDR_BITS. For layer 1, 2 * IDR_BITS, and - * so on. - */ -static int idr_layer_prefix_mask(int layer) -{ - return ~idr_max(layer + 1); -} - -static struct idr_layer *get_from_free_list(struct idr *idp) -{ - struct idr_layer *p; - unsigned long flags; - - spin_lock_irqsave(&idp->lock, flags); - if ((p = idp->id_free)) { - idp->id_free = p->ary[0]; - idp->id_free_cnt--; - p->ary[0] = NULL; - } - spin_unlock_irqrestore(&idp->lock, flags); - return(p); -} - /** - * idr_layer_alloc - allocate a new idr_layer - * @gfp_mask: allocation mask - * @layer_idr: optional idr to allocate from - * - * If @layer_idr is %NULL, directly allocate one using @gfp_mask or fetch - * one from the per-cpu preload buffer. If @layer_idr is not %NULL, fetch - * an idr_layer from @idr->id_free. - * - * @layer_idr is to maintain backward compatibility with the old alloc - * interface - idr_pre_get() and idr_get_new*() - and will be removed - * together with per-pool preload buffer. - */ -static struct idr_layer *idr_layer_alloc(gfp_t gfp_mask, struct idr *layer_idr) -{ - struct idr_layer *new; - - /* this is the old path, bypass to get_from_free_list() */ - if (layer_idr) - return get_from_free_list(layer_idr); - - /* - * Try to allocate directly from kmem_cache. We want to try this - * before preload buffer; otherwise, non-preloading idr_alloc() - * users will end up taking advantage of preloading ones. As the - * following is allowed to fail for preloaded cases, suppress - * warning this time. - */ - new = kmem_cache_zalloc(idr_layer_cache, gfp_mask | __GFP_NOWARN); - if (new) - return new; - - /* - * Try to fetch one from the per-cpu preload buffer if in process - * context. See idr_preload() for details. - */ - if (!in_interrupt()) { - preempt_disable(); - new = __this_cpu_read(idr_preload_head); - if (new) { - __this_cpu_write(idr_preload_head, new->ary[0]); - __this_cpu_dec(idr_preload_cnt); - new->ary[0] = NULL; - } - preempt_enable(); - if (new) - return new; - } - - /* - * Both failed. Try kmem_cache again w/o adding __GFP_NOWARN so - * that memory allocation failure warning is printed as intended. - */ - return kmem_cache_zalloc(idr_layer_cache, gfp_mask); -} - -static void idr_layer_rcu_free(struct rcu_head *head) -{ - struct idr_layer *layer; - - layer = container_of(head, struct idr_layer, rcu_head); - kmem_cache_free(idr_layer_cache, layer); -} - -static inline void free_layer(struct idr *idr, struct idr_layer *p) -{ - if (idr->hint == p) - RCU_INIT_POINTER(idr->hint, NULL); - call_rcu(&p->rcu_head, idr_layer_rcu_free); -} - -/* only called when idp->lock is held */ -static void __move_to_free_list(struct idr *idp, struct idr_layer *p) -{ - p->ary[0] = idp->id_free; - idp->id_free = p; - idp->id_free_cnt++; -} - -static void move_to_free_list(struct idr *idp, struct idr_layer *p) -{ - unsigned long flags; - - /* - * Depends on the return element being zeroed. - */ - spin_lock_irqsave(&idp->lock, flags); - __move_to_free_list(idp, p); - spin_unlock_irqrestore(&idp->lock, flags); -} - -static void idr_mark_full(struct idr_layer **pa, int id) -{ - struct idr_layer *p = pa[0]; - int l = 0; - - __set_bit(id & IDR_MASK, p->bitmap); - /* - * If this layer is full mark the bit in the layer above to - * show that this part of the radix tree is full. This may - * complete the layer above and require walking up the radix - * tree. - */ - while (bitmap_full(p->bitmap, IDR_SIZE)) { - if (!(p = pa[++l])) - break; - id = id >> IDR_BITS; - __set_bit((id & IDR_MASK), p->bitmap); - } -} - -static int __idr_pre_get(struct idr *idp, gfp_t gfp_mask) -{ - while (idp->id_free_cnt < MAX_IDR_FREE) { - struct idr_layer *new; - new = kmem_cache_zalloc(idr_layer_cache, gfp_mask); - if (new == NULL) - return (0); - move_to_free_list(idp, new); - } - return 1; -} - -/** - * sub_alloc - try to allocate an id without growing the tree depth - * @idp: idr handle - * @starting_id: id to start search at - * @pa: idr_layer[MAX_IDR_LEVEL] used as backtrack buffer - * @gfp_mask: allocation mask for idr_layer_alloc() - * @layer_idr: optional idr passed to idr_layer_alloc() - * - * Allocate an id in range [@starting_id, INT_MAX] from @idp without - * growing its depth. Returns - * - * the allocated id >= 0 if successful, - * -EAGAIN if the tree needs to grow for allocation to succeed, - * -ENOSPC if the id space is exhausted, - * -ENOMEM if more idr_layers need to be allocated. - */ -static int sub_alloc(struct idr *idp, int *starting_id, struct idr_layer **pa, - gfp_t gfp_mask, struct idr *layer_idr) -{ - int n, m, sh; - struct idr_layer *p, *new; - int l, id, oid; - - id = *starting_id; - restart: - p = idp->top; - l = idp->layers; - pa[l--] = NULL; - while (1) { - /* - * We run around this while until we reach the leaf node... - */ - n = (id >> (IDR_BITS*l)) & IDR_MASK; - m = find_next_zero_bit(p->bitmap, IDR_SIZE, n); - if (m == IDR_SIZE) { - /* no space available go back to previous layer. */ - l++; - oid = id; - id = (id | ((1 << (IDR_BITS * l)) - 1)) + 1; - - /* if already at the top layer, we need to grow */ - if (id > idr_max(idp->layers)) { - *starting_id = id; - return -EAGAIN; - } - p = pa[l]; - BUG_ON(!p); - - /* If we need to go up one layer, continue the - * loop; otherwise, restart from the top. - */ - sh = IDR_BITS * (l + 1); - if (oid >> sh == id >> sh) - continue; - else - goto restart; - } - if (m != n) { - sh = IDR_BITS*l; - id = ((id >> sh) ^ n ^ m) << sh; - } - if ((id >= MAX_IDR_BIT) || (id < 0)) - return -ENOSPC; - if (l == 0) - break; - /* - * Create the layer below if it is missing. - */ - if (!p->ary[m]) { - new = idr_layer_alloc(gfp_mask, layer_idr); - if (!new) - return -ENOMEM; - new->layer = l-1; - new->prefix = id & idr_layer_prefix_mask(new->layer); - rcu_assign_pointer(p->ary[m], new); - p->count++; - } - pa[l--] = p; - p = p->ary[m]; - } - - pa[l] = p; - return id; -} - -static int idr_get_empty_slot(struct idr *idp, int starting_id, - struct idr_layer **pa, gfp_t gfp_mask, - struct idr *layer_idr) -{ - struct idr_layer *p, *new; - int layers, v, id; - unsigned long flags; - - id = starting_id; -build_up: - p = idp->top; - layers = idp->layers; - if (unlikely(!p)) { - if (!(p = idr_layer_alloc(gfp_mask, layer_idr))) - return -ENOMEM; - p->layer = 0; - layers = 1; - } - /* - * Add a new layer to the top of the tree if the requested - * id is larger than the currently allocated space. - */ - while (id > idr_max(layers)) { - layers++; - if (!p->count) { - /* special case: if the tree is currently empty, - * then we grow the tree by moving the top node - * upwards. - */ - p->layer++; - WARN_ON_ONCE(p->prefix); - continue; - } - if (!(new = idr_layer_alloc(gfp_mask, layer_idr))) { - /* - * The allocation failed. If we built part of - * the structure tear it down. - */ - spin_lock_irqsave(&idp->lock, flags); - for (new = p; p && p != idp->top; new = p) { - p = p->ary[0]; - new->ary[0] = NULL; - new->count = 0; - bitmap_clear(new->bitmap, 0, IDR_SIZE); - __move_to_free_list(idp, new); - } - spin_unlock_irqrestore(&idp->lock, flags); - return -ENOMEM; - } - new->ary[0] = p; - new->count = 1; - new->layer = layers-1; - new->prefix = id & idr_layer_prefix_mask(new->layer); - if (bitmap_full(p->bitmap, IDR_SIZE)) - __set_bit(0, new->bitmap); - p = new; - } - rcu_assign_pointer(idp->top, p); - idp->layers = layers; - v = sub_alloc(idp, &id, pa, gfp_mask, layer_idr); - if (v == -EAGAIN) - goto build_up; - return(v); -} - -/* - * @id and @pa are from a successful allocation from idr_get_empty_slot(). - * Install the user pointer @ptr and mark the slot full. - */ -static void idr_fill_slot(struct idr *idr, void *ptr, int id, - struct idr_layer **pa) -{ - /* update hint used for lookup, cleared from free_layer() */ - rcu_assign_pointer(idr->hint, pa[0]); - - rcu_assign_pointer(pa[0]->ary[id & IDR_MASK], (struct idr_layer *)ptr); - pa[0]->count++; - idr_mark_full(pa, id); -} - - -/** - * idr_preload - preload for idr_alloc() - * @gfp_mask: allocation mask to use for preloading - * - * Preload per-cpu layer buffer for idr_alloc(). Can only be used from - * process context and each idr_preload() invocation should be matched with - * idr_preload_end(). Note that preemption is disabled while preloaded. - * - * The first idr_alloc() in the preloaded section can be treated as if it - * were invoked with @gfp_mask used for preloading. This allows using more - * permissive allocation masks for idrs protected by spinlocks. - * - * For example, if idr_alloc() below fails, the failure can be treated as - * if idr_alloc() were called with GFP_KERNEL rather than GFP_NOWAIT. - * - * idr_preload(GFP_KERNEL); - * spin_lock(lock); - * - * id = idr_alloc(idr, ptr, start, end, GFP_NOWAIT); - * - * spin_unlock(lock); - * idr_preload_end(); - * if (id < 0) - * error; - */ -void idr_preload(gfp_t gfp_mask) -{ - /* - * Consuming preload buffer from non-process context breaks preload - * allocation guarantee. Disallow usage from those contexts. - */ - WARN_ON_ONCE(in_interrupt()); - might_sleep_if(gfpflags_allow_blocking(gfp_mask)); - - preempt_disable(); - - /* - * idr_alloc() is likely to succeed w/o full idr_layer buffer and - * return value from idr_alloc() needs to be checked for failure - * anyway. Silently give up if allocation fails. The caller can - * treat failures from idr_alloc() as if idr_alloc() were called - * with @gfp_mask which should be enough. - */ - while (__this_cpu_read(idr_preload_cnt) < MAX_IDR_FREE) { - struct idr_layer *new; - - preempt_enable(); - new = kmem_cache_zalloc(idr_layer_cache, gfp_mask); - preempt_disable(); - if (!new) - break; - - /* link the new one to per-cpu preload list */ - new->ary[0] = __this_cpu_read(idr_preload_head); - __this_cpu_write(idr_preload_head, new); - __this_cpu_inc(idr_preload_cnt); - } -} -EXPORT_SYMBOL(idr_preload); - -/** - * idr_alloc - allocate new idr entry - * @idr: the (initialized) idr + * idr_alloc - allocate an id + * @idr: idr handle * @ptr: pointer to be associated with the new id * @start: the minimum id (inclusive) - * @end: the maximum id (exclusive, <= 0 for max) - * @gfp_mask: memory allocation flags + * @end: the maximum id (exclusive) + * @gfp: memory allocation flags * - * Allocate an id in [start, end) and associate it with @ptr. If no ID is - * available in the specified range, returns -ENOSPC. On memory allocation - * failure, returns -ENOMEM. + * Allocates an unused ID in the range [start, end). Returns -ENOSPC + * if there are no unused IDs in that range. * * Note that @end is treated as max when <= 0. This is to always allow * using @start + N as @end as long as N is inside integer range. * - * The user is responsible for exclusively synchronizing all operations - * which may modify @idr. However, read-only accesses such as idr_find() - * or iteration can be performed under RCU read lock provided the user - * destroys @ptr in RCU-safe way after removal from idr. + * Simultaneous modifications to the @idr are not allowed and should be + * prevented by the user, usually with a lock. idr_alloc() may be called + * concurrently with read-only accesses to the @idr, such as idr_find() and + * idr_for_each_entry(). */ -int idr_alloc(struct idr *idr, void *ptr, int start, int end, gfp_t gfp_mask) +int idr_alloc(struct idr *idr, void *ptr, int start, int end, gfp_t gfp) { - int max = end > 0 ? end - 1 : INT_MAX; /* inclusive upper limit */ - struct idr_layer *pa[MAX_IDR_LEVEL + 1]; - int id; + void __rcu **slot; + struct radix_tree_iter iter; - might_sleep_if(gfpflags_allow_blocking(gfp_mask)); - - /* sanity checks */ if (WARN_ON_ONCE(start < 0)) return -EINVAL; - if (unlikely(max < start)) - return -ENOSPC; + if (WARN_ON_ONCE(radix_tree_is_internal_node(ptr))) + return -EINVAL; - /* allocate id */ - id = idr_get_empty_slot(idr, start, pa, gfp_mask, NULL); - if (unlikely(id < 0)) - return id; - if (unlikely(id > max)) - return -ENOSPC; + radix_tree_iter_init(&iter, start); + slot = idr_get_free(&idr->idr_rt, &iter, gfp, end); + if (IS_ERR(slot)) + return PTR_ERR(slot); - idr_fill_slot(idr, ptr, id, pa); - return id; + radix_tree_iter_replace(&idr->idr_rt, &iter, slot, ptr); + radix_tree_iter_tag_clear(&idr->idr_rt, &iter, IDR_FREE); + return iter.index; } EXPORT_SYMBOL_GPL(idr_alloc); /** * idr_alloc_cyclic - allocate new idr entry in a cyclical fashion - * @idr: the (initialized) idr + * @idr: idr handle * @ptr: pointer to be associated with the new id * @start: the minimum id (inclusive) - * @end: the maximum id (exclusive, <= 0 for max) - * @gfp_mask: memory allocation flags - * - * Essentially the same as idr_alloc, but prefers to allocate progressively - * higher ids if it can. If the "cur" counter wraps, then it will start again - * at the "start" end of the range and allocate one that has already been used. - */ -int idr_alloc_cyclic(struct idr *idr, void *ptr, int start, int end, - gfp_t gfp_mask) -{ - int id; - - id = idr_alloc(idr, ptr, max(start, idr->cur), end, gfp_mask); - if (id == -ENOSPC) - id = idr_alloc(idr, ptr, start, end, gfp_mask); - - if (likely(id >= 0)) - idr->cur = id + 1; - return id; -} -EXPORT_SYMBOL(idr_alloc_cyclic); - -static void idr_remove_warning(int id) -{ - WARN(1, "idr_remove called for id=%d which is not allocated.\n", id); -} - -static void sub_remove(struct idr *idp, int shift, int id) -{ - struct idr_layer *p = idp->top; - struct idr_layer **pa[MAX_IDR_LEVEL + 1]; - struct idr_layer ***paa = &pa[0]; - struct idr_layer *to_free; - int n; - - *paa = NULL; - *++paa = &idp->top; - - while ((shift > 0) && p) { - n = (id >> shift) & IDR_MASK; - __clear_bit(n, p->bitmap); - *++paa = &p->ary[n]; - p = p->ary[n]; - shift -= IDR_BITS; - } - n = id & IDR_MASK; - if (likely(p != NULL && test_bit(n, p->bitmap))) { - __clear_bit(n, p->bitmap); - RCU_INIT_POINTER(p->ary[n], NULL); - to_free = NULL; - while(*paa && ! --((**paa)->count)){ - if (to_free) - free_layer(idp, to_free); - to_free = **paa; - **paa-- = NULL; - } - if (!*paa) - idp->layers = 0; - if (to_free) - free_layer(idp, to_free); - } else - idr_remove_warning(id); -} - -/** - * idr_remove - remove the given id and free its slot - * @idp: idr handle - * @id: unique key - */ -void idr_remove(struct idr *idp, int id) -{ - struct idr_layer *p; - struct idr_layer *to_free; - - if (id < 0) - return; - - if (id > idr_max(idp->layers)) { - idr_remove_warning(id); - return; - } - - sub_remove(idp, (idp->layers - 1) * IDR_BITS, id); - if (idp->top && idp->top->count == 1 && (idp->layers > 1) && - idp->top->ary[0]) { - /* - * Single child at leftmost slot: we can shrink the tree. - * This level is not needed anymore since when layers are - * inserted, they are inserted at the top of the existing - * tree. - */ - to_free = idp->top; - p = idp->top->ary[0]; - rcu_assign_pointer(idp->top, p); - --idp->layers; - to_free->count = 0; - bitmap_clear(to_free->bitmap, 0, IDR_SIZE); - free_layer(idp, to_free); - } -} -EXPORT_SYMBOL(idr_remove); - -static void __idr_remove_all(struct idr *idp) -{ - int n, id, max; - int bt_mask; - struct idr_layer *p; - struct idr_layer *pa[MAX_IDR_LEVEL + 1]; - struct idr_layer **paa = &pa[0]; - - n = idp->layers * IDR_BITS; - *paa = idp->top; - RCU_INIT_POINTER(idp->top, NULL); - max = idr_max(idp->layers); - - id = 0; - while (id >= 0 && id <= max) { - p = *paa; - while (n > IDR_BITS && p) { - n -= IDR_BITS; - p = p->ary[(id >> n) & IDR_MASK]; - *++paa = p; - } - - bt_mask = id; - id += 1 << n; - /* Get the highest bit that the above add changed from 0->1. */ - while (n < fls(id ^ bt_mask)) { - if (*paa) - free_layer(idp, *paa); - n += IDR_BITS; - --paa; - } - } - idp->layers = 0; -} - -/** - * idr_destroy - release all cached layers within an idr tree - * @idp: idr handle - * - * Free all id mappings and all idp_layers. After this function, @idp is - * completely unused and can be freed / recycled. The caller is - * responsible for ensuring that no one else accesses @idp during or after - * idr_destroy(). + * @end: the maximum id (exclusive) + * @gfp: memory allocation flags * - * A typical clean-up sequence for objects stored in an idr tree will use - * idr_for_each() to free all objects, if necessary, then idr_destroy() to - * free up the id mappings and cached idr_layers. + * Allocates an ID larger than the last ID allocated if one is available. + * If not, it will attempt to allocate the smallest ID that is larger or + * equal to @start. */ -void idr_destroy(struct idr *idp) +int idr_alloc_cyclic(struct idr *idr, void *ptr, int start, int end, gfp_t gfp) { - __idr_remove_all(idp); + int id, curr = idr->idr_next; - while (idp->id_free_cnt) { - struct idr_layer *p = get_from_free_list(idp); - kmem_cache_free(idr_layer_cache, p); - } -} -EXPORT_SYMBOL(idr_destroy); + if (curr < start) + curr = start; -void *idr_find_slowpath(struct idr *idp, int id) -{ - int n; - struct idr_layer *p; - - if (id < 0) - return NULL; - - p = rcu_dereference_raw(idp->top); - if (!p) - return NULL; - n = (p->layer+1) * IDR_BITS; + id = idr_alloc(idr, ptr, curr, end, gfp); + if ((id == -ENOSPC) && (curr > start)) + id = idr_alloc(idr, ptr, start, curr, gfp); - if (id > idr_max(p->layer + 1)) - return NULL; - BUG_ON(n == 0); + if (id >= 0) + idr->idr_next = id + 1U; - while (n > 0 && p) { - n -= IDR_BITS; - BUG_ON(n != p->layer*IDR_BITS); - p = rcu_dereference_raw(p->ary[(id >> n) & IDR_MASK]); - } - return((void *)p); + return id; } -EXPORT_SYMBOL(idr_find_slowpath); +EXPORT_SYMBOL(idr_alloc_cyclic); /** * idr_for_each - iterate through all stored pointers - * @idp: idr handle + * @idr: idr handle * @fn: function to be called for each pointer - * @data: data passed back to callback function + * @data: data passed to callback function * - * Iterate over the pointers registered with the given idr. The - * callback function will be called for each pointer currently - * registered, passing the id, the pointer and the data pointer passed - * to this function. It is not safe to modify the idr tree while in - * the callback, so functions such as idr_get_new and idr_remove are - * not allowed. + * The callback function will be called for each entry in @idr, passing + * the id, the pointer and the data pointer passed to this function. * - * We check the return of @fn each time. If it returns anything other - * than %0, we break out and return that value. + * If @fn returns anything other than %0, the iteration stops and that + * value is returned from this function. * - * The caller must serialize idr_for_each() vs idr_get_new() and idr_remove(). + * idr_for_each() can be called concurrently with idr_alloc() and + * idr_remove() if protected by RCU. Newly added entries may not be + * seen and deleted entries may be seen, but adding and removing entries + * will not cause other entries to be skipped, nor spurious ones to be seen. */ -int idr_for_each(struct idr *idp, - int (*fn)(int id, void *p, void *data), void *data) +int idr_for_each(const struct idr *idr, + int (*fn)(int id, void *p, void *data), void *data) { - int n, id, max, error = 0; - struct idr_layer *p; - struct idr_layer *pa[MAX_IDR_LEVEL + 1]; - struct idr_layer **paa = &pa[0]; - - n = idp->layers * IDR_BITS; - *paa = rcu_dereference_raw(idp->top); - max = idr_max(idp->layers); + struct radix_tree_iter iter; + void __rcu **slot; - id = 0; - while (id >= 0 && id <= max) { - p = *paa; - while (n > 0 && p) { - n -= IDR_BITS; - p = rcu_dereference_raw(p->ary[(id >> n) & IDR_MASK]); - *++paa = p; - } - - if (p) { - error = fn(id, (void *)p, data); - if (error) - break; - } - - id += 1 << n; - while (n < fls(id)) { - n += IDR_BITS; - --paa; - } + radix_tree_for_each_slot(slot, &idr->idr_rt, &iter, 0) { + int ret = fn(iter.index, rcu_dereference_raw(*slot), data); + if (ret) + return ret; } - return error; + return 0; } EXPORT_SYMBOL(idr_for_each); /** - * idr_get_next - lookup next object of id to given id. - * @idp: idr handle - * @nextidp: pointer to lookup key - * - * Returns pointer to registered object with id, which is next number to - * given id. After being looked up, *@nextidp will be updated for the next - * iteration. - * - * This function can be called under rcu_read_lock(), given that the leaf - * pointers lifetimes are correctly managed. + * idr_get_next - Find next populated entry + * @idr: idr handle + * @nextid: Pointer to lowest possible ID to return + * + * Returns the next populated entry in the tree with an ID greater than + * or equal to the value pointed to by @nextid. On exit, @nextid is updated + * to the ID of the found value. To use in a loop, the value pointed to by + * nextid must be incremented by the user. */ -void *idr_get_next(struct idr *idp, int *nextidp) +void *idr_get_next(struct idr *idr, int *nextid) { - struct idr_layer *p, *pa[MAX_IDR_LEVEL + 1]; - struct idr_layer **paa = &pa[0]; - int id = *nextidp; - int n, max; + struct radix_tree_iter iter; + void __rcu **slot; - /* find first ent */ - p = *paa = rcu_dereference_raw(idp->top); - if (!p) + slot = radix_tree_iter_find(&idr->idr_rt, &iter, *nextid); + if (!slot) return NULL; - n = (p->layer + 1) * IDR_BITS; - max = idr_max(p->layer + 1); - - while (id >= 0 && id <= max) { - p = *paa; - while (n > 0 && p) { - n -= IDR_BITS; - p = rcu_dereference_raw(p->ary[(id >> n) & IDR_MASK]); - *++paa = p; - } - - if (p) { - *nextidp = id; - return p; - } - /* - * Proceed to the next layer at the current level. Unlike - * idr_for_each(), @id isn't guaranteed to be aligned to - * layer boundary at this point and adding 1 << n may - * incorrectly skip IDs. Make sure we jump to the - * beginning of the next layer using round_up(). - */ - id = round_up(id + 1, 1 << n); - while (n < fls(id)) { - n += IDR_BITS; - --paa; - } - } - return NULL; + *nextid = iter.index; + return rcu_dereference_raw(*slot); } EXPORT_SYMBOL(idr_get_next); - /** * idr_replace - replace pointer for given id - * @idp: idr handle - * @ptr: pointer you want associated with the id - * @id: lookup key + * @idr: idr handle + * @ptr: New pointer to associate with the ID + * @id: Lookup key * - * Replace the pointer registered with an id and return the old value. - * A %-ENOENT return indicates that @id was not found. - * A %-EINVAL return indicates that @id was not within valid constraints. + * Replace the pointer registered with an ID and return the old value. + * This function can be called under the RCU read lock concurrently with + * idr_alloc() and idr_remove() (as long as the ID being removed is not + * the one being replaced!). * - * The caller must serialize with writers. + * Returns: 0 on success. %-ENOENT indicates that @id was not found. + * %-EINVAL indicates that @id or @ptr were not valid. */ -void *idr_replace(struct idr *idp, void *ptr, int id) +void *idr_replace(struct idr *idr, void *ptr, int id) { - int n; - struct idr_layer *p, *old_p; + struct radix_tree_node *node; + void __rcu **slot = NULL; + void *entry; - if (id < 0) + if (WARN_ON_ONCE(id < 0)) + return ERR_PTR(-EINVAL); + if (WARN_ON_ONCE(radix_tree_is_internal_node(ptr))) return ERR_PTR(-EINVAL); - p = idp->top; - if (!p) - return ERR_PTR(-ENOENT); - - if (id > idr_max(p->layer + 1)) - return ERR_PTR(-ENOENT); - - n = p->layer * IDR_BITS; - while ((n > 0) && p) { - p = p->ary[(id >> n) & IDR_MASK]; - n -= IDR_BITS; - } - - n = id & IDR_MASK; - if (unlikely(p == NULL || !test_bit(n, p->bitmap))) + entry = __radix_tree_lookup(&idr->idr_rt, id, &node, &slot); + if (!slot || radix_tree_tag_get(&idr->idr_rt, id, IDR_FREE)) return ERR_PTR(-ENOENT); - old_p = p->ary[n]; - rcu_assign_pointer(p->ary[n], ptr); + __radix_tree_replace(&idr->idr_rt, node, slot, ptr, NULL, NULL); - return old_p; + return entry; } EXPORT_SYMBOL(idr_replace); -void __init idr_init_cache(void) -{ - idr_layer_cache = kmem_cache_create("idr_layer_cache", - sizeof(struct idr_layer), 0, SLAB_PANIC, NULL); -} - -/** - * idr_init - initialize idr handle - * @idp: idr handle - * - * This function is use to set up the handle (@idp) that you will pass - * to the rest of the functions. - */ -void idr_init(struct idr *idp) -{ - memset(idp, 0, sizeof(struct idr)); - spin_lock_init(&idp->lock); -} -EXPORT_SYMBOL(idr_init); - -static int idr_has_entry(int id, void *p, void *data) -{ - return 1; -} - -bool idr_is_empty(struct idr *idp) -{ - return !idr_for_each(idp, idr_has_entry, NULL); -} -EXPORT_SYMBOL(idr_is_empty); - /** * DOC: IDA description - * IDA - IDR based ID allocator * - * This is id allocator without id -> pointer translation. Memory - * usage is much lower than full blown idr because each id only - * occupies a bit. ida uses a custom leaf node which contains - * IDA_BITMAP_BITS slots. - * - * 2007-04-25 written by Tejun Heo <htejun@gmail.com> + * The IDA is an ID allocator which does not provide the ability to + * associate an ID with a pointer. As such, it only needs to store one + * bit per ID, and so is more space efficient than an IDR. To use an IDA, + * define it using DEFINE_IDA() (or embed a &struct ida in a data structure, + * then initialise it using ida_init()). To allocate a new ID, call + * ida_simple_get(). To free an ID, call ida_simple_remove(). + * + * If you have more complex locking requirements, use a loop around + * ida_pre_get() and ida_get_new() to allocate a new ID. Then use + * ida_remove() to free an ID. You must make sure that ida_get_new() and + * ida_remove() cannot be called at the same time as each other for the + * same IDA. + * + * You can also use ida_get_new_above() if you need an ID to be allocated + * above a particular number. ida_destroy() can be used to dispose of an + * IDA without needing to free the individual IDs in it. You can use + * ida_is_empty() to find out whether the IDA has any IDs currently allocated. + * + * IDs are currently limited to the range [0-INT_MAX]. If this is an awkward + * limitation, it should be quite straightforward to raise the maximum. */ -static void free_bitmap(struct ida *ida, struct ida_bitmap *bitmap) -{ - unsigned long flags; - - if (!ida->free_bitmap) { - spin_lock_irqsave(&ida->idr.lock, flags); - if (!ida->free_bitmap) { - ida->free_bitmap = bitmap; - bitmap = NULL; - } - spin_unlock_irqrestore(&ida->idr.lock, flags); - } - - kfree(bitmap); -} - -/** - * ida_pre_get - reserve resources for ida allocation - * @ida: ida handle - * @gfp_mask: memory allocation flag - * - * This function should be called prior to locking and calling the - * following function. It preallocates enough memory to satisfy the - * worst possible allocation. - * - * If the system is REALLY out of memory this function returns %0, - * otherwise %1. +/* + * Developer's notes: + * + * The IDA uses the functionality provided by the IDR & radix tree to store + * bitmaps in each entry. The IDR_FREE tag means there is at least one bit + * free, unlike the IDR where it means at least one entry is free. + * + * I considered telling the radix tree that each slot is an order-10 node + * and storing the bit numbers in the radix tree, but the radix tree can't + * allow a single multiorder entry at index 0, which would significantly + * increase memory consumption for the IDA. So instead we divide the index + * by the number of bits in the leaf bitmap before doing a radix tree lookup. + * + * As an optimisation, if there are only a few low bits set in any given + * leaf, instead of allocating a 128-byte bitmap, we use the 'exceptional + * entry' functionality of the radix tree to store BITS_PER_LONG - 2 bits + * directly in the entry. By being really tricksy, we could store + * BITS_PER_LONG - 1 bits, but there're diminishing returns after optimising + * for 0-3 allocated IDs. + * + * We allow the radix tree 'exceptional' count to get out of date. Nothing + * in the IDA nor the radix tree code checks it. If it becomes important + * to maintain an accurate exceptional count, switch the rcu_assign_pointer() + * calls to radix_tree_iter_replace() which will correct the exceptional + * count. + * + * The IDA always requires a lock to alloc/free. If we add a 'test_bit' + * equivalent, it will still need locking. Going to RCU lookup would require + * using RCU to free bitmaps, and that's not trivial without embedding an + * RCU head in the bitmap, which adds a 2-pointer overhead to each 128-byte + * bitmap, which is excessive. */ -int ida_pre_get(struct ida *ida, gfp_t gfp_mask) -{ - /* allocate idr_layers */ - if (!__idr_pre_get(&ida->idr, gfp_mask)) - return 0; - /* allocate free_bitmap */ - if (!ida->free_bitmap) { - struct ida_bitmap *bitmap; - - bitmap = kmalloc(sizeof(struct ida_bitmap), gfp_mask); - if (!bitmap) - return 0; - - free_bitmap(ida, bitmap); - } - - return 1; -} -EXPORT_SYMBOL(ida_pre_get); +#define IDA_MAX (0x80000000U / IDA_BITMAP_BITS) /** * ida_get_new_above - allocate new ID above or equal to a start id - * @ida: ida handle - * @starting_id: id to start search at - * @p_id: pointer to the allocated handle + * @ida: ida handle + * @start: id to start search at + * @id: pointer to the allocated handle * - * Allocate new ID above or equal to @starting_id. It should be called - * with any required locks. + * Allocate new ID above or equal to @start. It should be called + * with any required locks to ensure that concurrent calls to + * ida_get_new_above() / ida_get_new() / ida_remove() are not allowed. + * Consider using ida_simple_get() if you do not have complex locking + * requirements. * * If memory is required, it will return %-EAGAIN, you should unlock * and go back to the ida_pre_get() call. If the ida is full, it will - * return %-ENOSPC. - * - * Note that callers must ensure that concurrent access to @ida is not possible. - * See ida_simple_get() for a varaint which takes care of locking. + * return %-ENOSPC. On success, it will return 0. * - * @p_id returns a value in the range @starting_id ... %0x7fffffff. + * @id returns a value in the range @start ... %0x7fffffff. */ -int ida_get_new_above(struct ida *ida, int starting_id, int *p_id) +int ida_get_new_above(struct ida *ida, int start, int *id) { - struct idr_layer *pa[MAX_IDR_LEVEL + 1]; + struct radix_tree_root *root = &ida->ida_rt; + void __rcu **slot; + struct radix_tree_iter iter; struct ida_bitmap *bitmap; - unsigned long flags; - int idr_id = starting_id / IDA_BITMAP_BITS; - int offset = starting_id % IDA_BITMAP_BITS; - int t, id; - - restart: - /* get vacant slot */ - t = idr_get_empty_slot(&ida->idr, idr_id, pa, 0, &ida->idr); - if (t < 0) - return t == -ENOMEM ? -EAGAIN : t; - - if (t * IDA_BITMAP_BITS >= MAX_IDR_BIT) - return -ENOSPC; - - if (t != idr_id) - offset = 0; - idr_id = t; - - /* if bitmap isn't there, create a new one */ - bitmap = (void *)pa[0]->ary[idr_id & IDR_MASK]; - if (!bitmap) { - spin_lock_irqsave(&ida->idr.lock, flags); - bitmap = ida->free_bitmap; - ida->free_bitmap = NULL; - spin_unlock_irqrestore(&ida->idr.lock, flags); - - if (!bitmap) - return -EAGAIN; - - memset(bitmap, 0, sizeof(struct ida_bitmap)); - rcu_assign_pointer(pa[0]->ary[idr_id & IDR_MASK], - (void *)bitmap); - pa[0]->count++; - } - - /* lookup for empty slot */ - t = find_next_zero_bit(bitmap->bitmap, IDA_BITMAP_BITS, offset); - if (t == IDA_BITMAP_BITS) { - /* no empty slot after offset, continue to the next chunk */ - idr_id++; - offset = 0; - goto restart; - } - - id = idr_id * IDA_BITMAP_BITS + t; - if (id >= MAX_IDR_BIT) - return -ENOSPC; + unsigned long index; + unsigned bit, ebit; + int new; + + index = start / IDA_BITMAP_BITS; + bit = start % IDA_BITMAP_BITS; + ebit = bit + RADIX_TREE_EXCEPTIONAL_SHIFT; + + slot = radix_tree_iter_init(&iter, index); + for (;;) { + if (slot) + slot = radix_tree_next_slot(slot, &iter, + RADIX_TREE_ITER_TAGGED); + if (!slot) { + slot = idr_get_free(root, &iter, GFP_NOWAIT, IDA_MAX); + if (IS_ERR(slot)) { + if (slot == ERR_PTR(-ENOMEM)) + return -EAGAIN; + return PTR_ERR(slot); + } + } + if (iter.index > index) { + bit = 0; + ebit = RADIX_TREE_EXCEPTIONAL_SHIFT; + } + new = iter.index * IDA_BITMAP_BITS; + bitmap = rcu_dereference_raw(*slot); + if (radix_tree_exception(bitmap)) { + unsigned long tmp = (unsigned long)bitmap; + ebit = find_next_zero_bit(&tmp, BITS_PER_LONG, ebit); + if (ebit < BITS_PER_LONG) { + tmp |= 1UL << ebit; + rcu_assign_pointer(*slot, (void *)tmp); + *id = new + ebit - RADIX_TREE_EXCEPTIONAL_SHIFT; + return 0; + } + bitmap = this_cpu_xchg(ida_bitmap, NULL); + if (!bitmap) + return -EAGAIN; + memset(bitmap, 0, sizeof(*bitmap)); + bitmap->bitmap[0] = tmp >> RADIX_TREE_EXCEPTIONAL_SHIFT; + rcu_assign_pointer(*slot, bitmap); + } - __set_bit(t, bitmap->bitmap); - if (++bitmap->nr_busy == IDA_BITMAP_BITS) - idr_mark_full(pa, idr_id); + if (bitmap) { + bit = find_next_zero_bit(bitmap->bitmap, + IDA_BITMAP_BITS, bit); + new += bit; + if (new < 0) + return -ENOSPC; + if (bit == IDA_BITMAP_BITS) + continue; - *p_id = id; + __set_bit(bit, bitmap->bitmap); + if (bitmap_full(bitmap->bitmap, IDA_BITMAP_BITS)) + radix_tree_iter_tag_clear(root, &iter, + IDR_FREE); + } else { + new += bit; + if (new < 0) + return -ENOSPC; + if (ebit < BITS_PER_LONG) { + bitmap = (void *)((1UL << ebit) | + RADIX_TREE_EXCEPTIONAL_ENTRY); + radix_tree_iter_replace(root, &iter, slot, + bitmap); + *id = new; + return 0; + } + bitmap = this_cpu_xchg(ida_bitmap, NULL); + if (!bitmap) + return -EAGAIN; + memset(bitmap, 0, sizeof(*bitmap)); + __set_bit(bit, bitmap->bitmap); + radix_tree_iter_replace(root, &iter, slot, bitmap); + } - /* Each leaf node can handle nearly a thousand slots and the - * whole idea of ida is to have small memory foot print. - * Throw away extra resources one by one after each successful - * allocation. - */ - if (ida->idr.id_free_cnt || ida->free_bitmap) { - struct idr_layer *p = get_from_free_list(&ida->idr); - if (p) - kmem_cache_free(idr_layer_cache, p); + *id = new; + return 0; } - - return 0; } EXPORT_SYMBOL(ida_get_new_above); /** - * ida_remove - remove the given ID - * @ida: ida handle - * @id: ID to free + * ida_remove - Free the given ID + * @ida: ida handle + * @id: ID to free + * + * This function should not be called at the same time as ida_get_new_above(). */ void ida_remove(struct ida *ida, int id) { - struct idr_layer *p = ida->idr.top; - int shift = (ida->idr.layers - 1) * IDR_BITS; - int idr_id = id / IDA_BITMAP_BITS; - int offset = id % IDA_BITMAP_BITS; - int n; + unsigned long index = id / IDA_BITMAP_BITS; + unsigned offset = id % IDA_BITMAP_BITS; struct ida_bitmap *bitmap; + unsigned long *btmp; + struct radix_tree_iter iter; + void __rcu **slot; - if (idr_id > idr_max(ida->idr.layers)) + slot = radix_tree_iter_lookup(&ida->ida_rt, &iter, index); + if (!slot) goto err; - /* clear full bits while looking up the leaf idr_layer */ - while ((shift > 0) && p) { - n = (idr_id >> shift) & IDR_MASK; - __clear_bit(n, p->bitmap); - p = p->ary[n]; - shift -= IDR_BITS; + bitmap = rcu_dereference_raw(*slot); + if (radix_tree_exception(bitmap)) { + btmp = (unsigned long *)slot; + offset += RADIX_TREE_EXCEPTIONAL_SHIFT; + if (offset >= BITS_PER_LONG) + goto err; + } else { + btmp = bitmap->bitmap; } - - if (p == NULL) - goto err; - - n = idr_id & IDR_MASK; - __clear_bit(n, p->bitmap); - - bitmap = (void *)p->ary[n]; - if (!bitmap || !test_bit(offset, bitmap->bitmap)) + if (!test_bit(offset, btmp)) goto err; - /* update bitmap and remove it if empty */ - __clear_bit(offset, bitmap->bitmap); - if (--bitmap->nr_busy == 0) { - __set_bit(n, p->bitmap); /* to please idr_remove() */ - idr_remove(&ida->idr, idr_id); - free_bitmap(ida, bitmap); + __clear_bit(offset, btmp); + radix_tree_iter_tag_set(&ida->ida_rt, &iter, IDR_FREE); + if (radix_tree_exception(bitmap)) { + if (rcu_dereference_raw(*slot) == + (void *)RADIX_TREE_EXCEPTIONAL_ENTRY) + radix_tree_iter_delete(&ida->ida_rt, &iter, slot); + } else if (bitmap_empty(btmp, IDA_BITMAP_BITS)) { + kfree(bitmap); + radix_tree_iter_delete(&ida->ida_rt, &iter, slot); } - return; - err: WARN(1, "ida_remove called for id=%d which is not allocated.\n", id); } EXPORT_SYMBOL(ida_remove); /** - * ida_destroy - release all cached layers within an ida tree - * @ida: ida handle + * ida_destroy - Free the contents of an ida + * @ida: ida handle + * + * Calling this function releases all resources associated with an IDA. When + * this call returns, the IDA is empty and can be reused or freed. The caller + * should not allow ida_remove() or ida_get_new_above() to be called at the + * same time. */ void ida_destroy(struct ida *ida) { - idr_destroy(&ida->idr); - kfree(ida->free_bitmap); + struct radix_tree_iter iter; + void __rcu **slot; + + radix_tree_for_each_slot(slot, &ida->ida_rt, &iter, 0) { + struct ida_bitmap *bitmap = rcu_dereference_raw(*slot); + if (!radix_tree_exception(bitmap)) + kfree(bitmap); + radix_tree_iter_delete(&ida->ida_rt, &iter, slot); + } } EXPORT_SYMBOL(ida_destroy); @@ -1141,18 +482,3 @@ void ida_simple_remove(struct ida *ida, unsigned int id) spin_unlock_irqrestore(&simple_ida_lock, flags); } EXPORT_SYMBOL(ida_simple_remove); - -/** - * ida_init - initialize ida handle - * @ida: ida handle - * - * This function is use to set up the handle (@ida) that you will pass - * to the rest of the functions. - */ -void ida_init(struct ida *ida) -{ - memset(ida, 0, sizeof(struct ida)); - idr_init(&ida->idr); - -} -EXPORT_SYMBOL(ida_init); diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 72fab4999c00..5ed506d648c4 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -22,20 +22,21 @@ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ +#include <linux/bitmap.h> +#include <linux/bitops.h> #include <linux/cpu.h> #include <linux/errno.h> +#include <linux/export.h> +#include <linux/idr.h> #include <linux/init.h> #include <linux/kernel.h> -#include <linux/export.h> -#include <linux/radix-tree.h> +#include <linux/kmemleak.h> #include <linux/percpu.h> +#include <linux/preempt.h> /* in_interrupt() */ +#include <linux/radix-tree.h> +#include <linux/rcupdate.h> #include <linux/slab.h> -#include <linux/kmemleak.h> -#include <linux/cpu.h> #include <linux/string.h> -#include <linux/bitops.h> -#include <linux/rcupdate.h> -#include <linux/preempt.h> /* in_interrupt() */ /* Number of nodes in fully populated tree of given height */ @@ -60,11 +61,28 @@ static struct kmem_cache *radix_tree_node_cachep; #define RADIX_TREE_PRELOAD_SIZE (RADIX_TREE_MAX_PATH * 2 - 1) /* + * The IDR does not have to be as high as the radix tree since it uses + * signed integers, not unsigned longs. + */ +#define IDR_INDEX_BITS (8 /* CHAR_BIT */ * sizeof(int) - 1) +#define IDR_MAX_PATH (DIV_ROUND_UP(IDR_INDEX_BITS, \ + RADIX_TREE_MAP_SHIFT)) +#define IDR_PRELOAD_SIZE (IDR_MAX_PATH * 2 - 1) + +/* + * The IDA is even shorter since it uses a bitmap at the last level. + */ +#define IDA_INDEX_BITS (8 * sizeof(int) - 1 - ilog2(IDA_BITMAP_BITS)) +#define IDA_MAX_PATH (DIV_ROUND_UP(IDA_INDEX_BITS, \ + RADIX_TREE_MAP_SHIFT)) +#define IDA_PRELOAD_SIZE (IDA_MAX_PATH * 2 - 1) + +/* * Per-cpu pool of preloaded nodes */ struct radix_tree_preload { unsigned nr; - /* nodes->private_data points to next preallocated node */ + /* nodes->parent points to next preallocated node */ struct radix_tree_node *nodes; }; static DEFINE_PER_CPU(struct radix_tree_preload, radix_tree_preloads) = { 0, }; @@ -83,35 +101,38 @@ static inline void *node_to_entry(void *ptr) #ifdef CONFIG_RADIX_TREE_MULTIORDER /* Sibling slots point directly to another slot in the same node */ -static inline bool is_sibling_entry(struct radix_tree_node *parent, void *node) +static inline +bool is_sibling_entry(const struct radix_tree_node *parent, void *node) { - void **ptr = node; + void __rcu **ptr = node; return (parent->slots <= ptr) && (ptr < parent->slots + RADIX_TREE_MAP_SIZE); } #else -static inline bool is_sibling_entry(struct radix_tree_node *parent, void *node) +static inline +bool is_sibling_entry(const struct radix_tree_node *parent, void *node) { return false; } #endif -static inline unsigned long get_slot_offset(struct radix_tree_node *parent, - void **slot) +static inline unsigned long +get_slot_offset(const struct radix_tree_node *parent, void __rcu **slot) { return slot - parent->slots; } -static unsigned int radix_tree_descend(struct radix_tree_node *parent, +static unsigned int radix_tree_descend(const struct radix_tree_node *parent, struct radix_tree_node **nodep, unsigned long index) { unsigned int offset = (index >> parent->shift) & RADIX_TREE_MAP_MASK; - void **entry = rcu_dereference_raw(parent->slots[offset]); + void __rcu **entry = rcu_dereference_raw(parent->slots[offset]); #ifdef CONFIG_RADIX_TREE_MULTIORDER if (radix_tree_is_internal_node(entry)) { if (is_sibling_entry(parent, entry)) { - void **sibentry = (void **) entry_to_node(entry); + void __rcu **sibentry; + sibentry = (void __rcu **) entry_to_node(entry); offset = get_slot_offset(parent, sibentry); entry = rcu_dereference_raw(*sibentry); } @@ -122,7 +143,7 @@ static unsigned int radix_tree_descend(struct radix_tree_node *parent, return offset; } -static inline gfp_t root_gfp_mask(struct radix_tree_root *root) +static inline gfp_t root_gfp_mask(const struct radix_tree_root *root) { return root->gfp_mask & __GFP_BITS_MASK; } @@ -139,42 +160,48 @@ static inline void tag_clear(struct radix_tree_node *node, unsigned int tag, __clear_bit(offset, node->tags[tag]); } -static inline int tag_get(struct radix_tree_node *node, unsigned int tag, +static inline int tag_get(const struct radix_tree_node *node, unsigned int tag, int offset) { return test_bit(offset, node->tags[tag]); } -static inline void root_tag_set(struct radix_tree_root *root, unsigned int tag) +static inline void root_tag_set(struct radix_tree_root *root, unsigned tag) { - root->gfp_mask |= (__force gfp_t)(1 << (tag + __GFP_BITS_SHIFT)); + root->gfp_mask |= (__force gfp_t)(1 << (tag + ROOT_TAG_SHIFT)); } static inline void root_tag_clear(struct radix_tree_root *root, unsigned tag) { - root->gfp_mask &= (__force gfp_t)~(1 << (tag + __GFP_BITS_SHIFT)); + root->gfp_mask &= (__force gfp_t)~(1 << (tag + ROOT_TAG_SHIFT)); } static inline void root_tag_clear_all(struct radix_tree_root *root) { - root->gfp_mask &= __GFP_BITS_MASK; + root->gfp_mask &= (1 << ROOT_TAG_SHIFT) - 1; +} + +static inline int root_tag_get(const struct radix_tree_root *root, unsigned tag) +{ + return (__force int)root->gfp_mask & (1 << (tag + ROOT_TAG_SHIFT)); } -static inline int root_tag_get(struct radix_tree_root *root, unsigned int tag) +static inline unsigned root_tags_get(const struct radix_tree_root *root) { - return (__force int)root->gfp_mask & (1 << (tag + __GFP_BITS_SHIFT)); + return (__force unsigned)root->gfp_mask >> ROOT_TAG_SHIFT; } -static inline unsigned root_tags_get(struct radix_tree_root *root) +static inline bool is_idr(const struct radix_tree_root *root) { - return (__force unsigned)root->gfp_mask >> __GFP_BITS_SHIFT; + return !!(root->gfp_mask & ROOT_IS_IDR); } /* * Returns 1 if any slot in the node has this tag set. * Otherwise returns 0. */ -static inline int any_tag_set(struct radix_tree_node *node, unsigned int tag) +static inline int any_tag_set(const struct radix_tree_node *node, + unsigned int tag) { unsigned idx; for (idx = 0; idx < RADIX_TREE_TAG_LONGS; idx++) { @@ -184,6 +211,11 @@ static inline int any_tag_set(struct radix_tree_node *node, unsigned int tag) return 0; } +static inline void all_tag_set(struct radix_tree_node *node, unsigned int tag) +{ + bitmap_fill(node->tags[tag], RADIX_TREE_MAP_SIZE); +} + /** * radix_tree_find_next_bit - find the next set bit in a memory region * @@ -232,11 +264,18 @@ static inline unsigned long shift_maxindex(unsigned int shift) return (RADIX_TREE_MAP_SIZE << shift) - 1; } -static inline unsigned long node_maxindex(struct radix_tree_node *node) +static inline unsigned long node_maxindex(const struct radix_tree_node *node) { return shift_maxindex(node->shift); } +static unsigned long next_index(unsigned long index, + const struct radix_tree_node *node, + unsigned long offset) +{ + return (index & ~node_maxindex(node)) + (offset << node->shift); +} + #ifndef __KERNEL__ static void dump_node(struct radix_tree_node *node, unsigned long index) { @@ -275,11 +314,59 @@ static void radix_tree_dump(struct radix_tree_root *root) { pr_debug("radix root: %p rnode %p tags %x\n", root, root->rnode, - root->gfp_mask >> __GFP_BITS_SHIFT); + root->gfp_mask >> ROOT_TAG_SHIFT); if (!radix_tree_is_internal_node(root->rnode)) return; dump_node(entry_to_node(root->rnode), 0); } + +static void dump_ida_node(void *entry, unsigned long index) +{ + unsigned long i; + + if (!entry) + return; + + if (radix_tree_is_internal_node(entry)) { + struct radix_tree_node *node = entry_to_node(entry); + + pr_debug("ida node: %p offset %d indices %lu-%lu parent %p free %lx shift %d count %d\n", + node, node->offset, index * IDA_BITMAP_BITS, + ((index | node_maxindex(node)) + 1) * + IDA_BITMAP_BITS - 1, + node->parent, node->tags[0][0], node->shift, + node->count); + for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) + dump_ida_node(node->slots[i], + index | (i << node->shift)); + } else if (radix_tree_exceptional_entry(entry)) { + pr_debug("ida excp: %p offset %d indices %lu-%lu data %lx\n", + entry, (int)(index & RADIX_TREE_MAP_MASK), + index * IDA_BITMAP_BITS, + index * IDA_BITMAP_BITS + BITS_PER_LONG - + RADIX_TREE_EXCEPTIONAL_SHIFT, + (unsigned long)entry >> + RADIX_TREE_EXCEPTIONAL_SHIFT); + } else { + struct ida_bitmap *bitmap = entry; + + pr_debug("ida btmp: %p offset %d indices %lu-%lu data", bitmap, + (int)(index & RADIX_TREE_MAP_MASK), + index * IDA_BITMAP_BITS, + (index + 1) * IDA_BITMAP_BITS - 1); + for (i = 0; i < IDA_BITMAP_LONGS; i++) + pr_cont(" %lx", bitmap->bitmap[i]); + pr_cont("\n"); + } +} + +static void ida_dump(struct ida *ida) +{ + struct radix_tree_root *root = &ida->ida_rt; + pr_debug("ida: %p node %p free %d\n", ida, root->rnode, + root->gfp_mask >> ROOT_TAG_SHIFT); + dump_ida_node(root->rnode, 0); +} #endif /* @@ -287,13 +374,12 @@ static void radix_tree_dump(struct radix_tree_root *root) * that the caller has pinned this thread of control to the current CPU. */ static struct radix_tree_node * -radix_tree_node_alloc(struct radix_tree_root *root, - struct radix_tree_node *parent, +radix_tree_node_alloc(gfp_t gfp_mask, struct radix_tree_node *parent, + struct radix_tree_root *root, unsigned int shift, unsigned int offset, unsigned int count, unsigned int exceptional) { struct radix_tree_node *ret = NULL; - gfp_t gfp_mask = root_gfp_mask(root); /* * Preload code isn't irq safe and it doesn't make sense to use @@ -321,8 +407,7 @@ radix_tree_node_alloc(struct radix_tree_root *root, rtp = this_cpu_ptr(&radix_tree_preloads); if (rtp->nr) { ret = rtp->nodes; - rtp->nodes = ret->private_data; - ret->private_data = NULL; + rtp->nodes = ret->parent; rtp->nr--; } /* @@ -336,11 +421,12 @@ radix_tree_node_alloc(struct radix_tree_root *root, out: BUG_ON(radix_tree_is_internal_node(ret)); if (ret) { - ret->parent = parent; ret->shift = shift; ret->offset = offset; ret->count = count; ret->exceptional = exceptional; + ret->parent = parent; + ret->root = root; } return ret; } @@ -399,7 +485,7 @@ static int __radix_tree_preload(gfp_t gfp_mask, unsigned nr) preempt_disable(); rtp = this_cpu_ptr(&radix_tree_preloads); if (rtp->nr < nr) { - node->private_data = rtp->nodes; + node->parent = rtp->nodes; rtp->nodes = node; rtp->nr++; } else { @@ -510,7 +596,7 @@ int radix_tree_maybe_preload_order(gfp_t gfp_mask, int order) return __radix_tree_preload(gfp_mask, nr_nodes); } -static unsigned radix_tree_load_root(struct radix_tree_root *root, +static unsigned radix_tree_load_root(const struct radix_tree_root *root, struct radix_tree_node **nodep, unsigned long *maxindex) { struct radix_tree_node *node = rcu_dereference_raw(root->rnode); @@ -530,10 +616,10 @@ static unsigned radix_tree_load_root(struct radix_tree_root *root, /* * Extend a radix tree so it can store key @index. */ -static int radix_tree_extend(struct radix_tree_root *root, +static int radix_tree_extend(struct radix_tree_root *root, gfp_t gfp, unsigned long index, unsigned int shift) { - struct radix_tree_node *slot; + void *entry; unsigned int maxshift; int tag; @@ -542,32 +628,44 @@ static int radix_tree_extend(struct radix_tree_root *root, while (index > shift_maxindex(maxshift)) maxshift += RADIX_TREE_MAP_SHIFT; - slot = root->rnode; - if (!slot) + entry = rcu_dereference_raw(root->rnode); + if (!entry && (!is_idr(root) || root_tag_get(root, IDR_FREE))) goto out; do { - struct radix_tree_node *node = radix_tree_node_alloc(root, - NULL, shift, 0, 1, 0); + struct radix_tree_node *node = radix_tree_node_alloc(gfp, NULL, + root, shift, 0, 1, 0); if (!node) return -ENOMEM; - /* Propagate the aggregated tag info into the new root */ - for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) { - if (root_tag_get(root, tag)) - tag_set(node, tag, 0); + if (is_idr(root)) { + all_tag_set(node, IDR_FREE); + if (!root_tag_get(root, IDR_FREE)) { + tag_clear(node, IDR_FREE, 0); + root_tag_set(root, IDR_FREE); + } + } else { + /* Propagate the aggregated tag info to the new child */ + for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) { + if (root_tag_get(root, tag)) + tag_set(node, tag, 0); + } } BUG_ON(shift > BITS_PER_LONG); - if (radix_tree_is_internal_node(slot)) { - entry_to_node(slot)->parent = node; - } else if (radix_tree_exceptional_entry(slot)) { + if (radix_tree_is_internal_node(entry)) { + entry_to_node(entry)->parent = node; + } else if (radix_tree_exceptional_entry(entry)) { /* Moving an exceptional root->rnode to a node */ node->exceptional = 1; } - node->slots[0] = slot; - slot = node_to_entry(node); - rcu_assign_pointer(root->rnode, slot); + /* + * entry was already in the radix tree, so we do not need + * rcu_assign_pointer here + */ + node->slots[0] = (void __rcu *)entry; + entry = node_to_entry(node); + rcu_assign_pointer(root->rnode, entry); shift += RADIX_TREE_MAP_SHIFT; } while (shift <= maxshift); out: @@ -578,12 +676,14 @@ out: * radix_tree_shrink - shrink radix tree to minimum height * @root radix tree root */ -static inline void radix_tree_shrink(struct radix_tree_root *root, +static inline bool radix_tree_shrink(struct radix_tree_root *root, radix_tree_update_node_t update_node, void *private) { + bool shrunk = false; + for (;;) { - struct radix_tree_node *node = root->rnode; + struct radix_tree_node *node = rcu_dereference_raw(root->rnode); struct radix_tree_node *child; if (!radix_tree_is_internal_node(node)) @@ -597,7 +697,7 @@ static inline void radix_tree_shrink(struct radix_tree_root *root, */ if (node->count != 1) break; - child = node->slots[0]; + child = rcu_dereference_raw(node->slots[0]); if (!child) break; if (!radix_tree_is_internal_node(child) && node->shift) @@ -613,7 +713,9 @@ static inline void radix_tree_shrink(struct radix_tree_root *root, * (node->slots[0]), it will be safe to dereference the new * one (root->rnode) as far as dependent read barriers go. */ - root->rnode = child; + root->rnode = (void __rcu *)child; + if (is_idr(root) && !tag_get(node, IDR_FREE, 0)) + root_tag_clear(root, IDR_FREE); /* * We have a dilemma here. The node's slot[0] must not be @@ -635,27 +737,34 @@ static inline void radix_tree_shrink(struct radix_tree_root *root, */ node->count = 0; if (!radix_tree_is_internal_node(child)) { - node->slots[0] = RADIX_TREE_RETRY; + node->slots[0] = (void __rcu *)RADIX_TREE_RETRY; if (update_node) update_node(node, private); } WARN_ON_ONCE(!list_empty(&node->private_list)); radix_tree_node_free(node); + shrunk = true; } + + return shrunk; } -static void delete_node(struct radix_tree_root *root, +static bool delete_node(struct radix_tree_root *root, struct radix_tree_node *node, radix_tree_update_node_t update_node, void *private) { + bool deleted = false; + do { struct radix_tree_node *parent; if (node->count) { - if (node == entry_to_node(root->rnode)) - radix_tree_shrink(root, update_node, private); - return; + if (node_to_entry(node) == + rcu_dereference_raw(root->rnode)) + deleted |= radix_tree_shrink(root, update_node, + private); + return deleted; } parent = node->parent; @@ -663,15 +772,23 @@ static void delete_node(struct radix_tree_root *root, parent->slots[node->offset] = NULL; parent->count--; } else { - root_tag_clear_all(root); + /* + * Shouldn't the tags already have all been cleared + * by the caller? + */ + if (!is_idr(root)) + root_tag_clear_all(root); root->rnode = NULL; } WARN_ON_ONCE(!list_empty(&node->private_list)); radix_tree_node_free(node); + deleted = true; node = parent; } while (node); + + return deleted; } /** @@ -693,13 +810,14 @@ static void delete_node(struct radix_tree_root *root, */ int __radix_tree_create(struct radix_tree_root *root, unsigned long index, unsigned order, struct radix_tree_node **nodep, - void ***slotp) + void __rcu ***slotp) { struct radix_tree_node *node = NULL, *child; - void **slot = (void **)&root->rnode; + void __rcu **slot = (void __rcu **)&root->rnode; unsigned long maxindex; unsigned int shift, offset = 0; unsigned long max = index | ((1UL << order) - 1); + gfp_t gfp = root_gfp_mask(root); shift = radix_tree_load_root(root, &child, &maxindex); @@ -707,18 +825,18 @@ int __radix_tree_create(struct radix_tree_root *root, unsigned long index, if (order > 0 && max == ((1UL << order) - 1)) max++; if (max > maxindex) { - int error = radix_tree_extend(root, max, shift); + int error = radix_tree_extend(root, gfp, max, shift); if (error < 0) return error; shift = error; - child = root->rnode; + child = rcu_dereference_raw(root->rnode); } while (shift > order) { shift -= RADIX_TREE_MAP_SHIFT; if (child == NULL) { /* Have to add a child node. */ - child = radix_tree_node_alloc(root, node, shift, + child = radix_tree_node_alloc(gfp, node, root, shift, offset, 0, 0); if (!child) return -ENOMEM; @@ -741,7 +859,6 @@ int __radix_tree_create(struct radix_tree_root *root, unsigned long index, return 0; } -#ifdef CONFIG_RADIX_TREE_MULTIORDER /* * Free any nodes below this node. The tree is presumed to not need * shrinking, and any user data in the tree is presumed to not need a @@ -757,7 +874,7 @@ static void radix_tree_free_nodes(struct radix_tree_node *node) struct radix_tree_node *child = entry_to_node(node); for (;;) { - void *entry = child->slots[offset]; + void *entry = rcu_dereference_raw(child->slots[offset]); if (radix_tree_is_internal_node(entry) && !is_sibling_entry(child, entry)) { child = entry_to_node(entry); @@ -777,8 +894,9 @@ static void radix_tree_free_nodes(struct radix_tree_node *node) } } -static inline int insert_entries(struct radix_tree_node *node, void **slot, - void *item, unsigned order, bool replace) +#ifdef CONFIG_RADIX_TREE_MULTIORDER +static inline int insert_entries(struct radix_tree_node *node, + void __rcu **slot, void *item, unsigned order, bool replace) { struct radix_tree_node *child; unsigned i, n, tag, offset, tags = 0; @@ -813,7 +931,7 @@ static inline int insert_entries(struct radix_tree_node *node, void **slot, } for (i = 0; i < n; i++) { - struct radix_tree_node *old = slot[i]; + struct radix_tree_node *old = rcu_dereference_raw(slot[i]); if (i) { rcu_assign_pointer(slot[i], child); for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) @@ -840,8 +958,8 @@ static inline int insert_entries(struct radix_tree_node *node, void **slot, return n; } #else -static inline int insert_entries(struct radix_tree_node *node, void **slot, - void *item, unsigned order, bool replace) +static inline int insert_entries(struct radix_tree_node *node, + void __rcu **slot, void *item, unsigned order, bool replace) { if (*slot) return -EEXIST; @@ -868,7 +986,7 @@ int __radix_tree_insert(struct radix_tree_root *root, unsigned long index, unsigned order, void *item) { struct radix_tree_node *node; - void **slot; + void __rcu **slot; int error; BUG_ON(radix_tree_is_internal_node(item)); @@ -908,16 +1026,17 @@ EXPORT_SYMBOL(__radix_tree_insert); * allocated and @root->rnode is used as a direct slot instead of * pointing to a node, in which case *@nodep will be NULL. */ -void *__radix_tree_lookup(struct radix_tree_root *root, unsigned long index, - struct radix_tree_node **nodep, void ***slotp) +void *__radix_tree_lookup(const struct radix_tree_root *root, + unsigned long index, struct radix_tree_node **nodep, + void __rcu ***slotp) { struct radix_tree_node *node, *parent; unsigned long maxindex; - void **slot; + void __rcu **slot; restart: parent = NULL; - slot = (void **)&root->rnode; + slot = (void __rcu **)&root->rnode; radix_tree_load_root(root, &node, &maxindex); if (index > maxindex) return NULL; @@ -952,9 +1071,10 @@ void *__radix_tree_lookup(struct radix_tree_root *root, unsigned long index, * exclusive from other writers. Any dereference of the slot must be done * using radix_tree_deref_slot. */ -void **radix_tree_lookup_slot(struct radix_tree_root *root, unsigned long index) +void __rcu **radix_tree_lookup_slot(const struct radix_tree_root *root, + unsigned long index) { - void **slot; + void __rcu **slot; if (!__radix_tree_lookup(root, index, NULL, &slot)) return NULL; @@ -974,75 +1094,76 @@ EXPORT_SYMBOL(radix_tree_lookup_slot); * them safely). No RCU barriers are required to access or modify the * returned item, however. */ -void *radix_tree_lookup(struct radix_tree_root *root, unsigned long index) +void *radix_tree_lookup(const struct radix_tree_root *root, unsigned long index) { return __radix_tree_lookup(root, index, NULL, NULL); } EXPORT_SYMBOL(radix_tree_lookup); -static inline int slot_count(struct radix_tree_node *node, - void **slot) +static inline void replace_sibling_entries(struct radix_tree_node *node, + void __rcu **slot, int count, int exceptional) { - int n = 1; #ifdef CONFIG_RADIX_TREE_MULTIORDER void *ptr = node_to_entry(slot); - unsigned offset = get_slot_offset(node, slot); - int i; + unsigned offset = get_slot_offset(node, slot) + 1; - for (i = 1; offset + i < RADIX_TREE_MAP_SIZE; i++) { - if (node->slots[offset + i] != ptr) + while (offset < RADIX_TREE_MAP_SIZE) { + if (rcu_dereference_raw(node->slots[offset]) != ptr) break; - n++; + if (count < 0) { + node->slots[offset] = NULL; + node->count--; + } + node->exceptional += exceptional; + offset++; } #endif - return n; } -static void replace_slot(struct radix_tree_root *root, - struct radix_tree_node *node, - void **slot, void *item, - bool warn_typeswitch) +static void replace_slot(void __rcu **slot, void *item, + struct radix_tree_node *node, int count, int exceptional) { - void *old = rcu_dereference_raw(*slot); - int count, exceptional; - - WARN_ON_ONCE(radix_tree_is_internal_node(item)); - - count = !!item - !!old; - exceptional = !!radix_tree_exceptional_entry(item) - - !!radix_tree_exceptional_entry(old); - - WARN_ON_ONCE(warn_typeswitch && (count || exceptional)); + if (WARN_ON_ONCE(radix_tree_is_internal_node(item))) + return; - if (node) { + if (node && (count || exceptional)) { node->count += count; - if (exceptional) { - exceptional *= slot_count(node, slot); - node->exceptional += exceptional; - } + node->exceptional += exceptional; + replace_sibling_entries(node, slot, count, exceptional); } rcu_assign_pointer(*slot, item); } -static inline void delete_sibling_entries(struct radix_tree_node *node, - void **slot) +static bool node_tag_get(const struct radix_tree_root *root, + const struct radix_tree_node *node, + unsigned int tag, unsigned int offset) { -#ifdef CONFIG_RADIX_TREE_MULTIORDER - bool exceptional = radix_tree_exceptional_entry(*slot); - void *ptr = node_to_entry(slot); - unsigned offset = get_slot_offset(node, slot); - int i; + if (node) + return tag_get(node, tag, offset); + return root_tag_get(root, tag); +} - for (i = 1; offset + i < RADIX_TREE_MAP_SIZE; i++) { - if (node->slots[offset + i] != ptr) - break; - node->slots[offset + i] = NULL; - node->count--; - if (exceptional) - node->exceptional--; +/* + * IDR users want to be able to store NULL in the tree, so if the slot isn't + * free, don't adjust the count, even if it's transitioning between NULL and + * non-NULL. For the IDA, we mark slots as being IDR_FREE while they still + * have empty bits, but it only stores NULL in slots when they're being + * deleted. + */ +static int calculate_count(struct radix_tree_root *root, + struct radix_tree_node *node, void __rcu **slot, + void *item, void *old) +{ + if (is_idr(root)) { + unsigned offset = get_slot_offset(node, slot); + bool free = node_tag_get(root, node, IDR_FREE, offset); + if (!free) + return 0; + if (!old) + return 1; } -#endif + return !!item - !!old; } /** @@ -1059,18 +1180,22 @@ static inline void delete_sibling_entries(struct radix_tree_node *node, */ void __radix_tree_replace(struct radix_tree_root *root, struct radix_tree_node *node, - void **slot, void *item, + void __rcu **slot, void *item, radix_tree_update_node_t update_node, void *private) { - if (!item) - delete_sibling_entries(node, slot); + void *old = rcu_dereference_raw(*slot); + int exceptional = !!radix_tree_exceptional_entry(item) - + !!radix_tree_exceptional_entry(old); + int count = calculate_count(root, node, slot, item, old); + /* * This function supports replacing exceptional entries and * deleting entries, but that needs accounting against the * node unless the slot is root->rnode. */ - replace_slot(root, node, slot, item, - !node && slot != (void **)&root->rnode); + WARN_ON_ONCE(!node && (slot != (void __rcu **)&root->rnode) && + (count || exceptional)); + replace_slot(slot, item, node, count, exceptional); if (!node) return; @@ -1098,9 +1223,9 @@ void __radix_tree_replace(struct radix_tree_root *root, * radix_tree_iter_replace(). */ void radix_tree_replace_slot(struct radix_tree_root *root, - void **slot, void *item) + void __rcu **slot, void *item) { - replace_slot(root, NULL, slot, item, true); + __radix_tree_replace(root, NULL, slot, item, NULL, NULL); } EXPORT_SYMBOL(radix_tree_replace_slot); @@ -1114,7 +1239,8 @@ EXPORT_SYMBOL(radix_tree_replace_slot); * Caller must hold tree write locked across split and replacement. */ void radix_tree_iter_replace(struct radix_tree_root *root, - const struct radix_tree_iter *iter, void **slot, void *item) + const struct radix_tree_iter *iter, + void __rcu **slot, void *item) { __radix_tree_replace(root, iter->node, slot, item, NULL, NULL); } @@ -1138,7 +1264,7 @@ int radix_tree_join(struct radix_tree_root *root, unsigned long index, unsigned order, void *item) { struct radix_tree_node *node; - void **slot; + void __rcu **slot; int error; BUG_ON(radix_tree_is_internal_node(item)); @@ -1173,9 +1299,10 @@ int radix_tree_split(struct radix_tree_root *root, unsigned long index, unsigned order) { struct radix_tree_node *parent, *node, *child; - void **slot; + void __rcu **slot; unsigned int offset, end; unsigned n, tag, tags = 0; + gfp_t gfp = root_gfp_mask(root); if (!__radix_tree_lookup(root, index, &parent, &slot)) return -ENOENT; @@ -1189,7 +1316,8 @@ int radix_tree_split(struct radix_tree_root *root, unsigned long index, tags |= 1 << tag; for (end = offset + 1; end < RADIX_TREE_MAP_SIZE; end++) { - if (!is_sibling_entry(parent, parent->slots[end])) + if (!is_sibling_entry(parent, + rcu_dereference_raw(parent->slots[end]))) break; for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) if (tags & (1 << tag)) @@ -1213,14 +1341,15 @@ int radix_tree_split(struct radix_tree_root *root, unsigned long index, for (;;) { if (node->shift > order) { - child = radix_tree_node_alloc(root, node, + child = radix_tree_node_alloc(gfp, node, root, node->shift - RADIX_TREE_MAP_SHIFT, offset, 0, 0); if (!child) goto nomem; if (node != parent) { node->count++; - node->slots[offset] = node_to_entry(child); + rcu_assign_pointer(node->slots[offset], + node_to_entry(child)); for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) if (tags & (1 << tag)) tag_set(node, tag, offset); @@ -1262,6 +1391,22 @@ int radix_tree_split(struct radix_tree_root *root, unsigned long index, } #endif +static void node_tag_set(struct radix_tree_root *root, + struct radix_tree_node *node, + unsigned int tag, unsigned int offset) +{ + while (node) { + if (tag_get(node, tag, offset)) + return; + tag_set(node, tag, offset); + offset = node->offset; + node = node->parent; + } + + if (!root_tag_get(root, tag)) + root_tag_set(root, tag); +} + /** * radix_tree_tag_set - set a tag on a radix tree node * @root: radix tree root @@ -1303,6 +1448,18 @@ void *radix_tree_tag_set(struct radix_tree_root *root, } EXPORT_SYMBOL(radix_tree_tag_set); +/** + * radix_tree_iter_tag_set - set a tag on the current iterator entry + * @root: radix tree root + * @iter: iterator state + * @tag: tag to set + */ +void radix_tree_iter_tag_set(struct radix_tree_root *root, + const struct radix_tree_iter *iter, unsigned int tag) +{ + node_tag_set(root, iter->node, tag, iter_offset(iter)); +} + static void node_tag_clear(struct radix_tree_root *root, struct radix_tree_node *node, unsigned int tag, unsigned int offset) @@ -1323,34 +1480,6 @@ static void node_tag_clear(struct radix_tree_root *root, root_tag_clear(root, tag); } -static void node_tag_set(struct radix_tree_root *root, - struct radix_tree_node *node, - unsigned int tag, unsigned int offset) -{ - while (node) { - if (tag_get(node, tag, offset)) - return; - tag_set(node, tag, offset); - offset = node->offset; - node = node->parent; - } - - if (!root_tag_get(root, tag)) - root_tag_set(root, tag); -} - -/** - * radix_tree_iter_tag_set - set a tag on the current iterator entry - * @root: radix tree root - * @iter: iterator state - * @tag: tag to set - */ -void radix_tree_iter_tag_set(struct radix_tree_root *root, - const struct radix_tree_iter *iter, unsigned int tag) -{ - node_tag_set(root, iter->node, tag, iter_offset(iter)); -} - /** * radix_tree_tag_clear - clear a tag on a radix tree node * @root: radix tree root @@ -1391,6 +1520,18 @@ void *radix_tree_tag_clear(struct radix_tree_root *root, EXPORT_SYMBOL(radix_tree_tag_clear); /** + * radix_tree_iter_tag_clear - clear a tag on the current iterator entry + * @root: radix tree root + * @iter: iterator state + * @tag: tag to clear + */ +void radix_tree_iter_tag_clear(struct radix_tree_root *root, + const struct radix_tree_iter *iter, unsigned int tag) +{ + node_tag_clear(root, iter->node, tag, iter_offset(iter)); +} + +/** * radix_tree_tag_get - get a tag on a radix tree node * @root: radix tree root * @index: index key @@ -1405,7 +1546,7 @@ EXPORT_SYMBOL(radix_tree_tag_clear); * the RCU lock is held, unless tag modification and node deletion are excluded * from concurrency. */ -int radix_tree_tag_get(struct radix_tree_root *root, +int radix_tree_tag_get(const struct radix_tree_root *root, unsigned long index, unsigned int tag) { struct radix_tree_node *node, *parent; @@ -1417,8 +1558,6 @@ int radix_tree_tag_get(struct radix_tree_root *root, radix_tree_load_root(root, &node, &maxindex); if (index > maxindex) return 0; - if (node == NULL) - return 0; while (radix_tree_is_internal_node(node)) { unsigned offset; @@ -1426,8 +1565,6 @@ int radix_tree_tag_get(struct radix_tree_root *root, parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); - if (!node) - return 0; if (!tag_get(parent, tag, offset)) return 0; if (node == RADIX_TREE_RETRY) @@ -1454,6 +1591,11 @@ static void set_iter_tags(struct radix_tree_iter *iter, unsigned tag_long = offset / BITS_PER_LONG; unsigned tag_bit = offset % BITS_PER_LONG; + if (!node) { + iter->tags = 1; + return; + } + iter->tags = node->tags[tag][tag_long] >> tag_bit; /* This never happens if RADIX_TREE_TAG_LONGS == 1 */ @@ -1468,8 +1610,8 @@ static void set_iter_tags(struct radix_tree_iter *iter, } #ifdef CONFIG_RADIX_TREE_MULTIORDER -static void **skip_siblings(struct radix_tree_node **nodep, - void **slot, struct radix_tree_iter *iter) +static void __rcu **skip_siblings(struct radix_tree_node **nodep, + void __rcu **slot, struct radix_tree_iter *iter) { void *sib = node_to_entry(slot - 1); @@ -1486,8 +1628,8 @@ static void **skip_siblings(struct radix_tree_node **nodep, return NULL; } -void ** __radix_tree_next_slot(void **slot, struct radix_tree_iter *iter, - unsigned flags) +void __rcu **__radix_tree_next_slot(void __rcu **slot, + struct radix_tree_iter *iter, unsigned flags) { unsigned tag = flags & RADIX_TREE_ITER_TAG_MASK; struct radix_tree_node *node = rcu_dereference_raw(*slot); @@ -1540,20 +1682,20 @@ void ** __radix_tree_next_slot(void **slot, struct radix_tree_iter *iter, } EXPORT_SYMBOL(__radix_tree_next_slot); #else -static void **skip_siblings(struct radix_tree_node **nodep, - void **slot, struct radix_tree_iter *iter) +static void __rcu **skip_siblings(struct radix_tree_node **nodep, + void __rcu **slot, struct radix_tree_iter *iter) { return slot; } #endif -void **radix_tree_iter_resume(void **slot, struct radix_tree_iter *iter) +void __rcu **radix_tree_iter_resume(void __rcu **slot, + struct radix_tree_iter *iter) { struct radix_tree_node *node; slot++; iter->index = __radix_tree_iter_add(iter, 1); - node = rcu_dereference_raw(*slot); skip_siblings(&node, slot, iter); iter->next_index = iter->index; iter->tags = 0; @@ -1569,7 +1711,7 @@ EXPORT_SYMBOL(radix_tree_iter_resume); * @flags: RADIX_TREE_ITER_* flags and tag index * Returns: pointer to chunk first slot, or NULL if iteration is over */ -void **radix_tree_next_chunk(struct radix_tree_root *root, +void __rcu **radix_tree_next_chunk(const struct radix_tree_root *root, struct radix_tree_iter *iter, unsigned flags) { unsigned tag = flags & RADIX_TREE_ITER_TAG_MASK; @@ -1606,7 +1748,7 @@ void **radix_tree_next_chunk(struct radix_tree_root *root, iter->tags = 1; iter->node = NULL; __set_iter_shift(iter, 0); - return (void **)&root->rnode; + return (void __rcu **)&root->rnode; } do { @@ -1624,7 +1766,8 @@ void **radix_tree_next_chunk(struct radix_tree_root *root, offset + 1); else while (++offset < RADIX_TREE_MAP_SIZE) { - void *slot = node->slots[offset]; + void *slot = rcu_dereference_raw( + node->slots[offset]); if (is_sibling_entry(node, slot)) continue; if (slot) @@ -1680,11 +1823,11 @@ EXPORT_SYMBOL(radix_tree_next_chunk); * stored in 'results'. */ unsigned int -radix_tree_gang_lookup(struct radix_tree_root *root, void **results, +radix_tree_gang_lookup(const struct radix_tree_root *root, void **results, unsigned long first_index, unsigned int max_items) { struct radix_tree_iter iter; - void **slot; + void __rcu **slot; unsigned int ret = 0; if (unlikely(!max_items)) @@ -1725,12 +1868,12 @@ EXPORT_SYMBOL(radix_tree_gang_lookup); * protection, radix_tree_deref_slot may fail requiring a retry. */ unsigned int -radix_tree_gang_lookup_slot(struct radix_tree_root *root, - void ***results, unsigned long *indices, +radix_tree_gang_lookup_slot(const struct radix_tree_root *root, + void __rcu ***results, unsigned long *indices, unsigned long first_index, unsigned int max_items) { struct radix_tree_iter iter; - void **slot; + void __rcu **slot; unsigned int ret = 0; if (unlikely(!max_items)) @@ -1762,12 +1905,12 @@ EXPORT_SYMBOL(radix_tree_gang_lookup_slot); * returns the number of items which were placed at *@results. */ unsigned int -radix_tree_gang_lookup_tag(struct radix_tree_root *root, void **results, +radix_tree_gang_lookup_tag(const struct radix_tree_root *root, void **results, unsigned long first_index, unsigned int max_items, unsigned int tag) { struct radix_tree_iter iter; - void **slot; + void __rcu **slot; unsigned int ret = 0; if (unlikely(!max_items)) @@ -1803,12 +1946,12 @@ EXPORT_SYMBOL(radix_tree_gang_lookup_tag); * returns the number of slots which were placed at *@results. */ unsigned int -radix_tree_gang_lookup_tag_slot(struct radix_tree_root *root, void ***results, - unsigned long first_index, unsigned int max_items, - unsigned int tag) +radix_tree_gang_lookup_tag_slot(const struct radix_tree_root *root, + void __rcu ***results, unsigned long first_index, + unsigned int max_items, unsigned int tag) { struct radix_tree_iter iter; - void **slot; + void __rcu **slot; unsigned int ret = 0; if (unlikely(!max_items)) @@ -1843,59 +1986,83 @@ void __radix_tree_delete_node(struct radix_tree_root *root, delete_node(root, node, update_node, private); } +static bool __radix_tree_delete(struct radix_tree_root *root, + struct radix_tree_node *node, void __rcu **slot) +{ + void *old = rcu_dereference_raw(*slot); + int exceptional = radix_tree_exceptional_entry(old) ? -1 : 0; + unsigned offset = get_slot_offset(node, slot); + int tag; + + if (is_idr(root)) + node_tag_set(root, node, IDR_FREE, offset); + else + for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) + node_tag_clear(root, node, tag, offset); + + replace_slot(slot, NULL, node, -1, exceptional); + return node && delete_node(root, node, NULL, NULL); +} + /** - * radix_tree_delete_item - delete an item from a radix tree - * @root: radix tree root - * @index: index key - * @item: expected item + * radix_tree_iter_delete - delete the entry at this iterator position + * @root: radix tree root + * @iter: iterator state + * @slot: pointer to slot * - * Remove @item at @index from the radix tree rooted at @root. + * Delete the entry at the position currently pointed to by the iterator. + * This may result in the current node being freed; if it is, the iterator + * is advanced so that it will not reference the freed memory. This + * function may be called without any locking if there are no other threads + * which can access this tree. + */ +void radix_tree_iter_delete(struct radix_tree_root *root, + struct radix_tree_iter *iter, void __rcu **slot) +{ + if (__radix_tree_delete(root, iter->node, slot)) + iter->index = iter->next_index; +} + +/** + * radix_tree_delete_item - delete an item from a radix tree + * @root: radix tree root + * @index: index key + * @item: expected item * - * Returns the address of the deleted item, or NULL if it was not present - * or the entry at the given @index was not @item. + * Remove @item at @index from the radix tree rooted at @root. + * + * Return: the deleted entry, or %NULL if it was not present + * or the entry at the given @index was not @item. */ void *radix_tree_delete_item(struct radix_tree_root *root, unsigned long index, void *item) { - struct radix_tree_node *node; - unsigned int offset; - void **slot; + struct radix_tree_node *node = NULL; + void __rcu **slot; void *entry; - int tag; entry = __radix_tree_lookup(root, index, &node, &slot); - if (!entry) + if (!entry && (!is_idr(root) || node_tag_get(root, node, IDR_FREE, + get_slot_offset(node, slot)))) return NULL; if (item && entry != item) return NULL; - if (!node) { - root_tag_clear_all(root); - root->rnode = NULL; - return entry; - } - - offset = get_slot_offset(node, slot); - - /* Clear all tags associated with the item to be deleted. */ - for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) - node_tag_clear(root, node, tag, offset); - - __radix_tree_replace(root, node, slot, NULL, NULL, NULL); + __radix_tree_delete(root, node, slot); return entry; } EXPORT_SYMBOL(radix_tree_delete_item); /** - * radix_tree_delete - delete an item from a radix tree - * @root: radix tree root - * @index: index key + * radix_tree_delete - delete an entry from a radix tree + * @root: radix tree root + * @index: index key * - * Remove the item at @index from the radix tree rooted at @root. + * Remove the entry at @index from the radix tree rooted at @root. * - * Returns the address of the deleted item, or NULL if it was not present. + * Return: The deleted entry, or %NULL if it was not present. */ void *radix_tree_delete(struct radix_tree_root *root, unsigned long index) { @@ -1905,15 +2072,14 @@ EXPORT_SYMBOL(radix_tree_delete); void radix_tree_clear_tags(struct radix_tree_root *root, struct radix_tree_node *node, - void **slot) + void __rcu **slot) { if (node) { unsigned int tag, offset = get_slot_offset(node, slot); for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) node_tag_clear(root, node, tag, offset); } else { - /* Clear root node tags */ - root->gfp_mask &= __GFP_BITS_MASK; + root_tag_clear_all(root); } } @@ -1922,12 +2088,147 @@ void radix_tree_clear_tags(struct radix_tree_root *root, * @root: radix tree root * @tag: tag to test */ -int radix_tree_tagged(struct radix_tree_root *root, unsigned int tag) +int radix_tree_tagged(const struct radix_tree_root *root, unsigned int tag) { return root_tag_get(root, tag); } EXPORT_SYMBOL(radix_tree_tagged); +/** + * idr_preload - preload for idr_alloc() + * @gfp_mask: allocation mask to use for preloading + * + * Preallocate memory to use for the next call to idr_alloc(). This function + * returns with preemption disabled. It will be enabled by idr_preload_end(). + */ +void idr_preload(gfp_t gfp_mask) +{ + __radix_tree_preload(gfp_mask, IDR_PRELOAD_SIZE); +} +EXPORT_SYMBOL(idr_preload); + +/** + * ida_pre_get - reserve resources for ida allocation + * @ida: ida handle + * @gfp: memory allocation flags + * + * This function should be called before calling ida_get_new_above(). If it + * is unable to allocate memory, it will return %0. On success, it returns %1. + */ +int ida_pre_get(struct ida *ida, gfp_t gfp) +{ + __radix_tree_preload(gfp, IDA_PRELOAD_SIZE); + /* + * The IDA API has no preload_end() equivalent. Instead, + * ida_get_new() can return -EAGAIN, prompting the caller + * to return to the ida_pre_get() step. + */ + preempt_enable(); + + if (!this_cpu_read(ida_bitmap)) { + struct ida_bitmap *bitmap = kmalloc(sizeof(*bitmap), gfp); + if (!bitmap) + return 0; + bitmap = this_cpu_cmpxchg(ida_bitmap, NULL, bitmap); + kfree(bitmap); + } + + return 1; +} +EXPORT_SYMBOL(ida_pre_get); + +void __rcu **idr_get_free(struct radix_tree_root *root, + struct radix_tree_iter *iter, gfp_t gfp, int end) +{ + struct radix_tree_node *node = NULL, *child; + void __rcu **slot = (void __rcu **)&root->rnode; + unsigned long maxindex, start = iter->next_index; + unsigned long max = end > 0 ? end - 1 : INT_MAX; + unsigned int shift, offset = 0; + + grow: + shift = radix_tree_load_root(root, &child, &maxindex); + if (!radix_tree_tagged(root, IDR_FREE)) + start = max(start, maxindex + 1); + if (start > max) + return ERR_PTR(-ENOSPC); + + if (start > maxindex) { + int error = radix_tree_extend(root, gfp, start, shift); + if (error < 0) + return ERR_PTR(error); + shift = error; + child = rcu_dereference_raw(root->rnode); + } + + while (shift) { + shift -= RADIX_TREE_MAP_SHIFT; + if (child == NULL) { + /* Have to add a child node. */ + child = radix_tree_node_alloc(gfp, node, root, shift, + offset, 0, 0); + if (!child) + return ERR_PTR(-ENOMEM); + all_tag_set(child, IDR_FREE); + rcu_assign_pointer(*slot, node_to_entry(child)); + if (node) + node->count++; + } else if (!radix_tree_is_internal_node(child)) + break; + + node = entry_to_node(child); + offset = radix_tree_descend(node, &child, start); + if (!tag_get(node, IDR_FREE, offset)) { + offset = radix_tree_find_next_bit(node, IDR_FREE, + offset + 1); + start = next_index(start, node, offset); + if (start > max) + return ERR_PTR(-ENOSPC); + while (offset == RADIX_TREE_MAP_SIZE) { + offset = node->offset + 1; + node = node->parent; + if (!node) + goto grow; + shift = node->shift; + } + child = rcu_dereference_raw(node->slots[offset]); + } + slot = &node->slots[offset]; + } + + iter->index = start; + if (node) + iter->next_index = 1 + min(max, (start | node_maxindex(node))); + else + iter->next_index = 1; + iter->node = node; + __set_iter_shift(iter, shift); + set_iter_tags(iter, node, offset, IDR_FREE); + + return slot; +} + +/** + * idr_destroy - release all internal memory from an IDR + * @idr: idr handle + * + * After this function is called, the IDR is empty, and may be reused or + * the data structure containing it may be freed. + * + * A typical clean-up sequence for objects stored in an idr tree will use + * idr_for_each() to free all objects, if necessary, then idr_destroy() to + * free the memory used to keep track of those objects. + */ +void idr_destroy(struct idr *idr) +{ + struct radix_tree_node *node = rcu_dereference_raw(idr->idr_rt.rnode); + if (radix_tree_is_internal_node(node)) + radix_tree_free_nodes(node); + idr->idr_rt.rnode = NULL; + root_tag_set(&idr->idr_rt, IDR_FREE); +} +EXPORT_SYMBOL(idr_destroy); + static void radix_tree_node_ctor(void *arg) { @@ -1971,10 +2272,12 @@ static int radix_tree_cpu_dead(unsigned int cpu) rtp = &per_cpu(radix_tree_preloads, cpu); while (rtp->nr) { node = rtp->nodes; - rtp->nodes = node->private_data; + rtp->nodes = node->parent; kmem_cache_free(radix_tree_node_cachep, node); rtp->nr--; } + kfree(per_cpu(ida_bitmap, cpu)); + per_cpu(ida_bitmap, cpu) = NULL; return 0; } diff --git a/mm/workingset.c b/mm/workingset.c index 79ed5364375d..ac839fca0e76 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -355,10 +355,8 @@ void workingset_update_node(struct radix_tree_node *node, void *private) * as node->private_list is protected by &mapping->tree_lock. */ if (node->count && node->count == node->exceptional) { - if (list_empty(&node->private_list)) { - node->private_data = mapping; + if (list_empty(&node->private_list)) list_lru_add(&shadow_nodes, &node->private_list); - } } else { if (!list_empty(&node->private_list)) list_lru_del(&shadow_nodes, &node->private_list); @@ -436,7 +434,7 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, */ node = container_of(item, struct radix_tree_node, private_list); - mapping = node->private_data; + mapping = container_of(node->root, struct address_space, page_tree); /* Coming from the list, invert the lock order */ if (!spin_trylock(&mapping->tree_lock)) { diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index ead18ca836de..11a23fd6e1a0 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -239,8 +239,10 @@ err_unlock: spin_unlock_bh(&chain->lock); err: - if (!ret) + if (!ret) { kfree(frag_entry_new); + kfree_skb(skb); + } return ret; } @@ -313,7 +315,7 @@ free: * * There are three possible outcomes: 1) Packet is merged: Return true and * set *skb to merged packet; 2) Packet is buffered: Return true and set *skb - * to NULL; 3) Error: Return false and leave skb as is. + * to NULL; 3) Error: Return false and free skb. * * Return: true when packet is merged or buffered, false when skb is not not * used. @@ -338,9 +340,9 @@ bool batadv_frag_skb_buffer(struct sk_buff **skb, goto out_err; out: - *skb = skb_out; ret = true; out_err: + *skb = skb_out; return ret; } @@ -499,6 +501,12 @@ int batadv_frag_send_packet(struct sk_buff *skb, /* Eat and send fragments from the tail of skb */ while (skb->len > max_fragment_size) { + /* The initial check in this function should cover this case */ + if (unlikely(frag_header.no == BATADV_FRAG_MAX_FRAGMENTS - 1)) { + ret = -EINVAL; + goto put_primary_if; + } + skb_fragment = batadv_frag_create(skb, &frag_header, mtu); if (!skb_fragment) { ret = -ENOMEM; @@ -515,12 +523,6 @@ int batadv_frag_send_packet(struct sk_buff *skb, } frag_header.no++; - - /* The initial check in this function should cover this case */ - if (frag_header.no == BATADV_FRAG_MAX_FRAGMENTS - 1) { - ret = -EINVAL; - goto put_primary_if; - } } /* Make room for the fragment header. */ diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 6bfac29318f2..902af6ba481c 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -186,8 +186,9 @@ void br_flood(struct net_bridge *br, struct sk_buff *skb, /* Do not flood unicast traffic to ports that turn it off */ if (pkt_type == BR_PKT_UNICAST && !(p->flags & BR_FLOOD)) continue; + /* Do not flood if mc off, except for traffic we originate */ if (pkt_type == BR_PKT_MULTICAST && - !(p->flags & BR_MCAST_FLOOD)) + !(p->flags & BR_MCAST_FLOOD) && skb->dev != br->dev) continue; /* Do not flood to ports that enable proxy ARP */ diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 62e68c0dc687..b838213c408e 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -997,10 +997,10 @@ err_vlan_add: RCU_INIT_POINTER(p->vlgrp, NULL); synchronize_rcu(); vlan_tunnel_deinit(vg); -err_vlan_enabled: err_tunnel_init: rhashtable_destroy(&vg->vlan_hash); err_rhtbl: +err_vlan_enabled: kfree(vg); goto out; diff --git a/net/core/dev.c b/net/core/dev.c index 304f2deae5f9..8637b2b71f3d 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1698,27 +1698,54 @@ EXPORT_SYMBOL_GPL(net_dec_egress_queue); static struct static_key netstamp_needed __read_mostly; #ifdef HAVE_JUMP_LABEL static atomic_t netstamp_needed_deferred; +static atomic_t netstamp_wanted; static void netstamp_clear(struct work_struct *work) { int deferred = atomic_xchg(&netstamp_needed_deferred, 0); + int wanted; - while (deferred--) - static_key_slow_dec(&netstamp_needed); + wanted = atomic_add_return(deferred, &netstamp_wanted); + if (wanted > 0) + static_key_enable(&netstamp_needed); + else + static_key_disable(&netstamp_needed); } static DECLARE_WORK(netstamp_work, netstamp_clear); #endif void net_enable_timestamp(void) { +#ifdef HAVE_JUMP_LABEL + int wanted; + + while (1) { + wanted = atomic_read(&netstamp_wanted); + if (wanted <= 0) + break; + if (atomic_cmpxchg(&netstamp_wanted, wanted, wanted + 1) == wanted) + return; + } + atomic_inc(&netstamp_needed_deferred); + schedule_work(&netstamp_work); +#else static_key_slow_inc(&netstamp_needed); +#endif } EXPORT_SYMBOL(net_enable_timestamp); void net_disable_timestamp(void) { #ifdef HAVE_JUMP_LABEL - /* net_disable_timestamp() can be called from non process context */ - atomic_inc(&netstamp_needed_deferred); + int wanted; + + while (1) { + wanted = atomic_read(&netstamp_wanted); + if (wanted <= 1) + break; + if (atomic_cmpxchg(&netstamp_wanted, wanted, wanted - 1) == wanted) + return; + } + atomic_dec(&netstamp_needed_deferred); schedule_work(&netstamp_work); #else static_key_slow_dec(&netstamp_needed); @@ -4884,6 +4911,39 @@ void __napi_schedule(struct napi_struct *n) EXPORT_SYMBOL(__napi_schedule); /** + * napi_schedule_prep - check if napi can be scheduled + * @n: napi context + * + * Test if NAPI routine is already running, and if not mark + * it as running. This is used as a condition variable + * insure only one NAPI poll instance runs. We also make + * sure there is no pending NAPI disable. + */ +bool napi_schedule_prep(struct napi_struct *n) +{ + unsigned long val, new; + + do { + val = READ_ONCE(n->state); + if (unlikely(val & NAPIF_STATE_DISABLE)) + return false; + new = val | NAPIF_STATE_SCHED; + + /* Sets STATE_MISSED bit if STATE_SCHED was already set + * This was suggested by Alexander Duyck, as compiler + * emits better code than : + * if (val & NAPIF_STATE_SCHED) + * new |= NAPIF_STATE_MISSED; + */ + new |= (val & NAPIF_STATE_SCHED) / NAPIF_STATE_SCHED * + NAPIF_STATE_MISSED; + } while (cmpxchg(&n->state, val, new) != val); + + return !(val & NAPIF_STATE_SCHED); +} +EXPORT_SYMBOL(napi_schedule_prep); + +/** * __napi_schedule_irqoff - schedule for receive * @n: entry to schedule * @@ -4897,7 +4957,7 @@ EXPORT_SYMBOL(__napi_schedule_irqoff); bool napi_complete_done(struct napi_struct *n, int work_done) { - unsigned long flags; + unsigned long flags, val, new; /* * 1) Don't let napi dequeue from the cpu poll list @@ -4927,7 +4987,27 @@ bool napi_complete_done(struct napi_struct *n, int work_done) list_del_init(&n->poll_list); local_irq_restore(flags); } - WARN_ON_ONCE(!test_and_clear_bit(NAPI_STATE_SCHED, &n->state)); + + do { + val = READ_ONCE(n->state); + + WARN_ON_ONCE(!(val & NAPIF_STATE_SCHED)); + + new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED); + + /* If STATE_MISSED was set, leave STATE_SCHED set, + * because we will call napi->poll() one more time. + * This C code was suggested by Alexander Duyck to help gcc. + */ + new |= (val & NAPIF_STATE_MISSED) / NAPIF_STATE_MISSED * + NAPIF_STATE_SCHED; + } while (cmpxchg(&n->state, val, new) != val); + + if (unlikely(val & NAPIF_STATE_MISSED)) { + __napi_schedule(n); + return false; + } + return true; } EXPORT_SYMBOL(napi_complete_done); @@ -4953,6 +5033,16 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock) { int rc; + /* Busy polling means there is a high chance device driver hard irq + * could not grab NAPI_STATE_SCHED, and that NAPI_STATE_MISSED was + * set in napi_schedule_prep(). + * Since we are about to call napi->poll() once more, we can safely + * clear NAPI_STATE_MISSED. + * + * Note: x86 could use a single "lock and ..." instruction + * to perform these two clear_bit() + */ + clear_bit(NAPI_STATE_MISSED, &napi->state); clear_bit(NAPI_STATE_IN_BUSY_POLL, &napi->state); local_bh_disable(); @@ -5088,8 +5178,13 @@ static enum hrtimer_restart napi_watchdog(struct hrtimer *timer) struct napi_struct *napi; napi = container_of(timer, struct napi_struct, timer); - if (napi->gro_list) - napi_schedule_irqoff(napi); + + /* Note : we use a relaxed variant of napi_schedule_prep() not setting + * NAPI_STATE_MISSED, since we do not react to a device IRQ. + */ + if (napi->gro_list && !napi_disable_pending(napi) && + !test_and_set_bit(NAPI_STATE_SCHED, &napi->state)) + __napi_schedule_irqoff(napi); return HRTIMER_NORESTART; } diff --git a/net/core/sock.c b/net/core/sock.c index e7d74940e863..f6fd79f33097 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1539,11 +1539,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) is_charged = sk_filter_charge(newsk, filter); if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk, sk))) { - /* It is still raw copy of parent, so invalidate - * destructor and make plain sk_free() */ - newsk->sk_destruct = NULL; - bh_unlock_sock(newsk); - sk_free(newsk); + sk_free_unlock_clone(newsk); newsk = NULL; goto out; } @@ -1592,6 +1588,16 @@ out: } EXPORT_SYMBOL_GPL(sk_clone_lock); +void sk_free_unlock_clone(struct sock *sk) +{ + /* It is still raw copy of parent, so invalidate + * destructor and make plain sk_free() */ + sk->sk_destruct = NULL; + bh_unlock_sock(sk); + sk_free(sk); +} +EXPORT_SYMBOL_GPL(sk_free_unlock_clone); + void sk_setup_caps(struct sock *sk, struct dst_entry *dst) { u32 max_segs = 1; diff --git a/net/dccp/input.c b/net/dccp/input.c index 8fedc2d49770..4a05d7876850 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -577,6 +577,7 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, struct dccp_sock *dp = dccp_sk(sk); struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb); const int old_state = sk->sk_state; + bool acceptable; int queued = 0; /* @@ -603,8 +604,13 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, */ if (sk->sk_state == DCCP_LISTEN) { if (dh->dccph_type == DCCP_PKT_REQUEST) { - if (inet_csk(sk)->icsk_af_ops->conn_request(sk, - skb) < 0) + /* It is possible that we process SYN packets from backlog, + * so we need to make sure to disable BH right there. + */ + local_bh_disable(); + acceptable = inet_csk(sk)->icsk_af_ops->conn_request(sk, skb) >= 0; + local_bh_enable(); + if (!acceptable) return 1; consume_skb(skb); return 0; diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index 53eddf99e4f6..e267e6f4c9a5 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -119,10 +119,7 @@ struct sock *dccp_create_openreq_child(const struct sock *sk, * Activate features: initialise CCIDs, sequence windows etc. */ if (dccp_feat_activate_values(newsk, &dreq->dreq_featneg)) { - /* It is still raw copy of parent, so invalidate - * destructor and make plain sk_free() */ - newsk->sk_destruct = NULL; - sk_free(newsk); + sk_free_unlock_clone(newsk); return NULL; } dccp_init_xmit_timers(newsk); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index b39a791f6756..42bfd08109dd 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -622,6 +622,7 @@ const struct nla_policy rtm_ipv4_policy[RTA_MAX + 1] = { [RTA_ENCAP_TYPE] = { .type = NLA_U16 }, [RTA_ENCAP] = { .type = NLA_NESTED }, [RTA_UID] = { .type = NLA_U32 }, + [RTA_MARK] = { .type = NLA_U32 }, }; static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index da385ae997a3..cf4555581282 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1110,9 +1110,14 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0; err = __inet_stream_connect(sk->sk_socket, msg->msg_name, msg->msg_namelen, flags, 1); - inet->defer_connect = 0; - *copied = tp->fastopen_req->copied; - tcp_free_fastopen_req(tp); + /* fastopen_req could already be freed in __inet_stream_connect + * if the connection times out or gets rst + */ + if (tp->fastopen_req) { + *copied = tp->fastopen_req->copied; + tcp_free_fastopen_req(tp); + inet->defer_connect = 0; + } return err; } @@ -2318,6 +2323,10 @@ int tcp_disconnect(struct sock *sk, int flags) memset(&tp->rx_opt, 0, sizeof(tp->rx_opt)); __sk_dst_reset(sk); + /* Clean up fastopen related fields */ + tcp_free_fastopen_req(tp); + inet->defer_connect = 0; + WARN_ON(inet->inet_num && !icsk->icsk_bind_hash); sk->sk_error_report(sk); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2c0ff327b6df..39c393cc0fd3 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5886,9 +5886,15 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) if (th->syn) { if (th->fin) goto discard; - if (icsk->icsk_af_ops->conn_request(sk, skb) < 0) - return 1; + /* It is possible that we process SYN packets from backlog, + * so we need to make sure to disable BH right there. + */ + local_bh_disable(); + acceptable = icsk->icsk_af_ops->conn_request(sk, skb) >= 0; + local_bh_enable(); + if (!acceptable) + return 1; consume_skb(skb); return 0; } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 3a2025f5bf2c..cfc485a8e1c0 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -5692,13 +5692,18 @@ static int addrconf_sysctl_addr_gen_mode(struct ctl_table *ctl, int write, struct inet6_dev *idev = (struct inet6_dev *)ctl->extra1; struct net *net = (struct net *)ctl->extra2; + if (!rtnl_trylock()) + return restart_syscall(); + ret = proc_dointvec(ctl, write, buffer, lenp, ppos); if (write) { new_val = *((int *)ctl->data); - if (check_addr_gen_mode(new_val) < 0) - return -EINVAL; + if (check_addr_gen_mode(new_val) < 0) { + ret = -EINVAL; + goto out; + } /* request for default */ if (&net->ipv6.devconf_dflt->addr_gen_mode == ctl->data) { @@ -5707,20 +5712,23 @@ static int addrconf_sysctl_addr_gen_mode(struct ctl_table *ctl, int write, /* request for individual net device */ } else { if (!idev) - return ret; + goto out; - if (check_stable_privacy(idev, net, new_val) < 0) - return -EINVAL; + if (check_stable_privacy(idev, net, new_val) < 0) { + ret = -EINVAL; + goto out; + } if (idev->cnf.addr_gen_mode != new_val) { idev->cnf.addr_gen_mode = new_val; - rtnl_lock(); addrconf_dev_config(idev->dev); - rtnl_unlock(); } } } +out: + rtnl_unlock(); + return ret; } diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 9948b5ce52da..986d4ca38832 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -589,6 +589,7 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) hdr = ipv6_hdr(skb); fhdr = (struct frag_hdr *)skb_transport_header(skb); + skb_orphan(skb); fq = fq_find(net, fhdr->identification, user, &hdr->saddr, &hdr->daddr, skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr)); if (fq == NULL) { diff --git a/net/ipv6/route.c b/net/ipv6/route.c index f54f4265b37f..229bfcc451ef 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2169,10 +2169,13 @@ int ip6_del_rt(struct rt6_info *rt) static int __ip6_del_rt_siblings(struct rt6_info *rt, struct fib6_config *cfg) { struct nl_info *info = &cfg->fc_nlinfo; + struct net *net = info->nl_net; struct sk_buff *skb = NULL; struct fib6_table *table; - int err; + int err = -ENOENT; + if (rt == net->ipv6.ip6_null_entry) + goto out_put; table = rt->rt6i_table; write_lock_bh(&table->tb6_lock); @@ -2184,7 +2187,7 @@ static int __ip6_del_rt_siblings(struct rt6_info *rt, struct fib6_config *cfg) if (skb) { u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0; - if (rt6_fill_node(info->nl_net, skb, rt, + if (rt6_fill_node(net, skb, rt, NULL, NULL, 0, RTM_DELROUTE, info->portid, seq, 0) < 0) { kfree_skb(skb); @@ -2198,17 +2201,18 @@ static int __ip6_del_rt_siblings(struct rt6_info *rt, struct fib6_config *cfg) rt6i_siblings) { err = fib6_del(sibling, info); if (err) - goto out; + goto out_unlock; } } err = fib6_del(rt, info); -out: +out_unlock: write_unlock_bh(&table->tb6_lock); +out_put: ip6_rt_put(rt); if (skb) { - rtnl_notify(skb, info->nl_net, info->portid, RTNLGRP_IPV6_ROUTE, + rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE, info->nlh, gfp_any()); } return err; @@ -2891,6 +2895,7 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = { [RTA_ENCAP] = { .type = NLA_NESTED }, [RTA_EXPIRES] = { .type = NLA_U32 }, [RTA_UID] = { .type = NLA_U32 }, + [RTA_MARK] = { .type = NLA_U32 }, }; static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, @@ -3627,6 +3632,12 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh) rt = (struct rt6_info *)ip6_route_output(net, NULL, &fl6); } + if (rt == net->ipv6.ip6_null_entry) { + err = rt->dst.error; + ip6_rt_put(rt); + goto errout; + } + skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) { ip6_rt_put(rt); diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 3b5fd4188f2a..4456559cb056 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -85,7 +85,7 @@ void ___ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid, ht_dbg(sta->sdata, "Rx BA session stop requested for %pM tid %u %s reason: %d\n", sta->sta.addr, tid, - initiator == WLAN_BACK_RECIPIENT ? "recipient" : "inititator", + initiator == WLAN_BACK_RECIPIENT ? "recipient" : "initiator", (int)reason); if (drv_ampdu_action(local, sta->sdata, ¶ms)) @@ -398,6 +398,7 @@ void __ieee80211_start_rx_ba_session(struct sta_info *sta, tid_agg_rx->timeout = timeout; tid_agg_rx->stored_mpdu_num = 0; tid_agg_rx->auto_seq = auto_seq; + tid_agg_rx->started = false; tid_agg_rx->reorder_buf_filtered = 0; status = WLAN_STATUS_SUCCESS; diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c index 28a3a0957c9e..76a8bcd8ef11 100644 --- a/net/mac80211/pm.c +++ b/net/mac80211/pm.c @@ -168,6 +168,7 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan) break; } + flush_delayed_work(&sdata->dec_tailroom_needed_wk); drv_remove_interface(local, sdata); } diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 50ca3828b124..e48724a6725e 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -4,7 +4,7 @@ * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2007-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH - * Copyright(c) 2015 - 2016 Intel Deutschland GmbH + * Copyright(c) 2015 - 2017 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -1034,6 +1034,18 @@ static bool ieee80211_sta_manage_reorder_buf(struct ieee80211_sub_if_data *sdata buf_size = tid_agg_rx->buf_size; head_seq_num = tid_agg_rx->head_seq_num; + /* + * If the current MPDU's SN is smaller than the SSN, it shouldn't + * be reordered. + */ + if (unlikely(!tid_agg_rx->started)) { + if (ieee80211_sn_less(mpdu_seq_num, head_seq_num)) { + ret = false; + goto out; + } + tid_agg_rx->started = true; + } + /* frame with out of date sequence number */ if (ieee80211_sn_less(mpdu_seq_num, head_seq_num)) { dev_kfree_skb(skb); @@ -3880,6 +3892,7 @@ static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx, stats->last_rate = sta_stats_encode_rate(status); stats->fragments++; + stats->packets++; if (!(status->flag & RX_FLAG_NO_SIGNAL_VAL)) { stats->last_signal = status->signal; @@ -4073,15 +4086,17 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, ieee80211_is_beacon(hdr->frame_control))) ieee80211_scan_rx(local, skb); - if (pubsta) { - rx.sta = container_of(pubsta, struct sta_info, sta); - rx.sdata = rx.sta->sdata; - if (ieee80211_prepare_and_rx_handle(&rx, skb, true)) - return; - goto out; - } else if (ieee80211_is_data(fc)) { + if (ieee80211_is_data(fc)) { struct sta_info *sta, *prev_sta; + if (pubsta) { + rx.sta = container_of(pubsta, struct sta_info, sta); + rx.sdata = rx.sta->sdata; + if (ieee80211_prepare_and_rx_handle(&rx, skb, true)) + return; + goto out; + } + prev_sta = NULL; for_each_sta_info(local, hdr->addr2, sta, tmp) { diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 4774e663a411..3323a2fb289b 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -688,7 +688,7 @@ static void __sta_info_recalc_tim(struct sta_info *sta, bool ignore_pending) } /* No need to do anything if the driver does all */ - if (ieee80211_hw_check(&local->hw, AP_LINK_PS)) + if (ieee80211_hw_check(&local->hw, AP_LINK_PS) && !local->ops->set_tim) return; if (sta->dead) @@ -1264,7 +1264,7 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta) sta_info_recalc_tim(sta); ps_dbg(sdata, - "STA %pM aid %d sending %d filtered/%d PS frames since STA not sleeping anymore\n", + "STA %pM aid %d sending %d filtered/%d PS frames since STA woke up\n", sta->sta.addr, sta->sta.aid, filtered, buffered); ieee80211_check_fast_xmit(sta); diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index dd06ef0b8861..15599c70a38f 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -189,6 +189,7 @@ struct tid_ampdu_tx { * @auto_seq: used for offloaded BA sessions to automatically pick head_seq_and * and ssn. * @removed: this session is removed (but might have been found due to RCU) + * @started: this session has started (head ssn or higher was received) * * This structure's lifetime is managed by RCU, assignments to * the array holding it must hold the aggregation mutex. @@ -212,8 +213,9 @@ struct tid_ampdu_rx { u16 ssn; u16 buf_size; u16 timeout; - bool auto_seq; - bool removed; + u8 auto_seq:1, + removed:1, + started:1; }; /** diff --git a/net/mac80211/status.c b/net/mac80211/status.c index a3af6e1bfd98..83b8b11f24ea 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -51,7 +51,8 @@ static void ieee80211_handle_filtered_frame(struct ieee80211_local *local, struct ieee80211_hdr *hdr = (void *)skb->data; int ac; - if (info->flags & IEEE80211_TX_CTL_NO_PS_BUFFER) { + if (info->flags & (IEEE80211_TX_CTL_NO_PS_BUFFER | + IEEE80211_TX_CTL_AMPDU)) { ieee80211_free_txskb(&local->hw, skb); return; } @@ -462,9 +463,7 @@ static void ieee80211_report_ack_skb(struct ieee80211_local *local, unsigned long flags; spin_lock_irqsave(&local->ack_status_lock, flags); - skb = idr_find(&local->ack_status_frames, info->ack_frame_id); - if (skb) - idr_remove(&local->ack_status_frames, info->ack_frame_id); + skb = idr_remove(&local->ack_status_frames, info->ack_frame_id); spin_unlock_irqrestore(&local->ack_status_lock, flags); if (!skb) diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index b1beb2b94ec7..c82301ce3fff 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -796,9 +796,8 @@ static void ovs_fragment(struct net *net, struct vport *vport, unsigned long orig_dst; struct rt6_info ovs_rt; - if (!v6ops) { + if (!v6ops) goto err; - } prepare_frag(vport, skb, orig_network_offset, ovs_key_mac_proto(key)); diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 85cd59526670..e0a87776a010 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -485,7 +485,6 @@ static int handle_fragments(struct net *net, struct sw_flow_key *key, } else if (key->eth.type == htons(ETH_P_IPV6)) { enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone; - skb_orphan(skb); memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm)); err = nf_ct_frag6_gather(net, skb, user); if (err) { diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 2bd0d1949312..a0dbe7ca8f72 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3103,7 +3103,7 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sock *sk = sock->sk; - char name[15]; + char name[sizeof(uaddr->sa_data) + 1]; /* * Check legality @@ -3111,7 +3111,11 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, if (addr_len != sizeof(struct sockaddr)) return -EINVAL; - strlcpy(name, uaddr->sa_data, sizeof(name)); + /* uaddr->sa_data comes from the userspace, it's not guaranteed to be + * zero-terminated. + */ + memcpy(name, uaddr->sa_data, sizeof(uaddr->sa_data)); + name[sizeof(uaddr->sa_data)] = 0; return packet_do_bind(sk, name, 0, pkt_sk(sk)->num); } diff --git a/net/rds/ib.c b/net/rds/ib.c index 91fe46f1e4cc..0f557b243311 100644 --- a/net/rds/ib.c +++ b/net/rds/ib.c @@ -45,8 +45,8 @@ #include "ib.h" #include "ib_mr.h" -unsigned int rds_ib_mr_1m_pool_size = RDS_MR_1M_POOL_SIZE; -unsigned int rds_ib_mr_8k_pool_size = RDS_MR_8K_POOL_SIZE; +static unsigned int rds_ib_mr_1m_pool_size = RDS_MR_1M_POOL_SIZE; +static unsigned int rds_ib_mr_8k_pool_size = RDS_MR_8K_POOL_SIZE; unsigned int rds_ib_retry_count = RDS_IB_DEFAULT_RETRY_COUNT; module_param(rds_ib_mr_1m_pool_size, int, 0444); diff --git a/net/rds/ib_mr.h b/net/rds/ib_mr.h index 24c086db4511..5d6e98a79a5e 100644 --- a/net/rds/ib_mr.h +++ b/net/rds/ib_mr.h @@ -107,8 +107,6 @@ struct rds_ib_mr_pool { }; extern struct workqueue_struct *rds_ib_mr_wq; -extern unsigned int rds_ib_mr_1m_pool_size; -extern unsigned int rds_ib_mr_8k_pool_size; extern bool prefer_frmr; struct rds_ib_mr_pool *rds_ib_create_mr_pool(struct rds_ib_device *rds_dev, diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 199b46e93e64..7fb59c3f1542 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -290,10 +290,11 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, cp.exclusive = false; cp.service_id = srx->srx_service; call = rxrpc_new_client_call(rx, &cp, srx, user_call_ID, gfp); + /* The socket has been unlocked. */ if (!IS_ERR(call)) call->notify_rx = notify_rx; - release_sock(&rx->sk); + mutex_unlock(&call->user_mutex); _leave(" = %p", call); return call; } @@ -310,7 +311,10 @@ EXPORT_SYMBOL(rxrpc_kernel_begin_call); void rxrpc_kernel_end_call(struct socket *sock, struct rxrpc_call *call) { _enter("%d{%d}", call->debug_id, atomic_read(&call->usage)); + + mutex_lock(&call->user_mutex); rxrpc_release_call(rxrpc_sk(sock->sk), call); + mutex_unlock(&call->user_mutex); rxrpc_put_call(call, rxrpc_call_put_kernel); } EXPORT_SYMBOL(rxrpc_kernel_end_call); @@ -450,14 +454,16 @@ static int rxrpc_sendmsg(struct socket *sock, struct msghdr *m, size_t len) case RXRPC_SERVER_BOUND: case RXRPC_SERVER_LISTENING: ret = rxrpc_do_sendmsg(rx, m, len); - break; + /* The socket has been unlocked */ + goto out; default: ret = -EINVAL; - break; + goto error_unlock; } error_unlock: release_sock(&rx->sk); +out: _leave(" = %d", ret); return ret; } diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 12be432be9b2..26a7b1db1361 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -467,6 +467,7 @@ struct rxrpc_call { struct rxrpc_connection *conn; /* connection carrying call */ struct rxrpc_peer *peer; /* Peer record for remote address */ struct rxrpc_sock __rcu *socket; /* socket responsible */ + struct mutex user_mutex; /* User access mutex */ ktime_t ack_at; /* When deferred ACK needs to happen */ ktime_t resend_at; /* When next resend needs to happen */ ktime_t ping_at; /* When next to send a ping */ diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 7c4c64ab8da2..0ed181f53f32 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -323,6 +323,8 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, * * If we want to report an error, we mark the skb with the packet type and * abort code and return NULL. + * + * The call is returned with the user access mutex held. */ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, struct rxrpc_connection *conn, @@ -371,6 +373,18 @@ found_service: trace_rxrpc_receive(call, rxrpc_receive_incoming, sp->hdr.serial, sp->hdr.seq); + /* Lock the call to prevent rxrpc_kernel_send/recv_data() and + * sendmsg()/recvmsg() inconveniently stealing the mutex once the + * notification is generated. + * + * The BUG should never happen because the kernel should be well + * behaved enough not to access the call before the first notification + * event and userspace is prevented from doing so until the state is + * appropriate. + */ + if (!mutex_trylock(&call->user_mutex)) + BUG(); + /* Make the call live. */ rxrpc_incoming_call(rx, call, skb); conn = call->conn; @@ -429,10 +443,12 @@ out: /* * handle acceptance of a call by userspace * - assign the user call ID to the call at the front of the queue + * - called with the socket locked. */ struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *rx, unsigned long user_call_ID, rxrpc_notify_rx_t notify_rx) + __releases(&rx->sk.sk_lock.slock) { struct rxrpc_call *call; struct rb_node *parent, **pp; @@ -446,6 +462,7 @@ struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *rx, if (list_empty(&rx->to_be_accepted)) { write_unlock(&rx->call_lock); + release_sock(&rx->sk); kleave(" = -ENODATA [empty]"); return ERR_PTR(-ENODATA); } @@ -470,10 +487,39 @@ struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *rx, */ call = list_entry(rx->to_be_accepted.next, struct rxrpc_call, accept_link); + write_unlock(&rx->call_lock); + + /* We need to gain the mutex from the interrupt handler without + * upsetting lockdep, so we have to release it there and take it here. + * We are, however, still holding the socket lock, so other accepts + * must wait for us and no one can add the user ID behind our backs. + */ + if (mutex_lock_interruptible(&call->user_mutex) < 0) { + release_sock(&rx->sk); + kleave(" = -ERESTARTSYS"); + return ERR_PTR(-ERESTARTSYS); + } + + write_lock(&rx->call_lock); list_del_init(&call->accept_link); sk_acceptq_removed(&rx->sk); rxrpc_see_call(call); + /* Find the user ID insertion point. */ + pp = &rx->calls.rb_node; + parent = NULL; + while (*pp) { + parent = *pp; + call = rb_entry(parent, struct rxrpc_call, sock_node); + + if (user_call_ID < call->user_call_ID) + pp = &(*pp)->rb_left; + else if (user_call_ID > call->user_call_ID) + pp = &(*pp)->rb_right; + else + BUG(); + } + write_lock_bh(&call->state_lock); switch (call->state) { case RXRPC_CALL_SERVER_ACCEPTING: @@ -499,6 +545,7 @@ struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *rx, write_unlock(&rx->call_lock); rxrpc_notify_socket(call); rxrpc_service_prealloc(rx, GFP_KERNEL); + release_sock(&rx->sk); _leave(" = %p{%d}", call, call->debug_id); return call; @@ -515,6 +562,7 @@ id_in_use: write_unlock(&rx->call_lock); out: rxrpc_service_prealloc(rx, GFP_KERNEL); + release_sock(&rx->sk); _leave(" = %d", ret); return ERR_PTR(ret); } diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 8b94db3c9b2e..d79cd36987a9 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -115,6 +115,7 @@ struct rxrpc_call *rxrpc_alloc_call(gfp_t gfp) if (!call->rxtx_annotations) goto nomem_2; + mutex_init(&call->user_mutex); setup_timer(&call->timer, rxrpc_call_timer_expired, (unsigned long)call); INIT_WORK(&call->processor, &rxrpc_process_call); @@ -194,14 +195,16 @@ static void rxrpc_start_call_timer(struct rxrpc_call *call) } /* - * set up a call for the given data - * - called in process context with IRQs enabled + * Set up a call for the given parameters. + * - Called with the socket lock held, which it must release. + * - If it returns a call, the call's lock will need releasing by the caller. */ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, struct rxrpc_conn_parameters *cp, struct sockaddr_rxrpc *srx, unsigned long user_call_ID, gfp_t gfp) + __releases(&rx->sk.sk_lock.slock) { struct rxrpc_call *call, *xcall; struct rb_node *parent, **pp; @@ -212,6 +215,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, call = rxrpc_alloc_client_call(srx, gfp); if (IS_ERR(call)) { + release_sock(&rx->sk); _leave(" = %ld", PTR_ERR(call)); return call; } @@ -219,6 +223,11 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, trace_rxrpc_call(call, rxrpc_call_new_client, atomic_read(&call->usage), here, (const void *)user_call_ID); + /* We need to protect a partially set up call against the user as we + * will be acting outside the socket lock. + */ + mutex_lock(&call->user_mutex); + /* Publish the call, even though it is incompletely set up as yet */ write_lock(&rx->call_lock); @@ -250,6 +259,9 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, list_add_tail(&call->link, &rxrpc_calls); write_unlock(&rxrpc_call_lock); + /* From this point on, the call is protected by its own lock. */ + release_sock(&rx->sk); + /* Set up or get a connection record and set the protocol parameters, * including channel number and call ID. */ @@ -279,6 +291,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, */ error_dup_user_ID: write_unlock(&rx->call_lock); + release_sock(&rx->sk); ret = -EEXIST; error: @@ -287,6 +300,7 @@ error: trace_rxrpc_call(call, rxrpc_call_error, atomic_read(&call->usage), here, ERR_PTR(ret)); rxrpc_release_call(rx, call); + mutex_unlock(&call->user_mutex); rxrpc_put_call(call, rxrpc_call_put); _leave(" = %d", ret); return ERR_PTR(ret); diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 78ec33477adf..9f4cfa25af7c 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -1194,6 +1194,7 @@ void rxrpc_data_ready(struct sock *udp_sk) goto reject_packet; } rxrpc_send_ping(call, skb, skew); + mutex_unlock(&call->user_mutex); } rxrpc_input_call_packet(call, skb, skew); diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index f3a688e10843..22447dbcc380 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -487,6 +487,20 @@ try_again: trace_rxrpc_recvmsg(call, rxrpc_recvmsg_dequeue, 0, 0, 0, 0); + /* We're going to drop the socket lock, so we need to lock the call + * against interference by sendmsg. + */ + if (!mutex_trylock(&call->user_mutex)) { + ret = -EWOULDBLOCK; + if (flags & MSG_DONTWAIT) + goto error_requeue_call; + ret = -ERESTARTSYS; + if (mutex_lock_interruptible(&call->user_mutex) < 0) + goto error_requeue_call; + } + + release_sock(&rx->sk); + if (test_bit(RXRPC_CALL_RELEASED, &call->flags)) BUG(); @@ -502,7 +516,7 @@ try_again: &call->user_call_ID); } if (ret < 0) - goto error; + goto error_unlock_call; } if (msg->msg_name) { @@ -533,12 +547,12 @@ try_again: } if (ret < 0) - goto error; + goto error_unlock_call; if (call->state == RXRPC_CALL_COMPLETE) { ret = rxrpc_recvmsg_term(call, msg); if (ret < 0) - goto error; + goto error_unlock_call; if (!(flags & MSG_PEEK)) rxrpc_release_call(rx, call); msg->msg_flags |= MSG_EOR; @@ -551,8 +565,21 @@ try_again: msg->msg_flags &= ~MSG_MORE; ret = copied; -error: +error_unlock_call: + mutex_unlock(&call->user_mutex); rxrpc_put_call(call, rxrpc_call_put); + trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, 0, 0, 0, ret); + return ret; + +error_requeue_call: + if (!(flags & MSG_PEEK)) { + write_lock_bh(&rx->recvmsg_lock); + list_add(&call->recvmsg_link, &rx->recvmsg_q); + write_unlock_bh(&rx->recvmsg_lock); + trace_rxrpc_recvmsg(call, rxrpc_recvmsg_requeue, 0, 0, 0, 0); + } else { + rxrpc_put_call(call, rxrpc_call_put); + } error_no_call: release_sock(&rx->sk); trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, 0, 0, 0, ret); @@ -609,7 +636,7 @@ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call, iov.iov_len = size - *_offset; iov_iter_kvec(&iter, ITER_KVEC | READ, &iov, 1, size - *_offset); - lock_sock(sock->sk); + mutex_lock(&call->user_mutex); switch (call->state) { case RXRPC_CALL_CLIENT_RECV_REPLY: @@ -648,7 +675,7 @@ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call, read_phase_complete: ret = 1; out: - release_sock(sock->sk); + mutex_unlock(&call->user_mutex); _leave(" = %d [%zu,%d]", ret, *_offset, *_abort); return ret; diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 0a6ef217aa8a..31c1538c1a8d 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -59,9 +59,12 @@ static int rxrpc_wait_for_tx_window(struct rxrpc_sock *rx, } trace_rxrpc_transmit(call, rxrpc_transmit_wait); - release_sock(&rx->sk); + mutex_unlock(&call->user_mutex); *timeo = schedule_timeout(*timeo); - lock_sock(&rx->sk); + if (mutex_lock_interruptible(&call->user_mutex) < 0) { + ret = sock_intr_errno(*timeo); + break; + } } remove_wait_queue(&call->waitq, &myself); @@ -171,7 +174,7 @@ static void rxrpc_queue_packet(struct rxrpc_call *call, struct sk_buff *skb, /* * send data through a socket * - must be called in process context - * - caller holds the socket locked + * - The caller holds the call user access mutex, but not the socket lock. */ static int rxrpc_send_data(struct rxrpc_sock *rx, struct rxrpc_call *call, @@ -437,10 +440,13 @@ static int rxrpc_sendmsg_cmsg(struct msghdr *msg, /* * Create a new client call for sendmsg(). + * - Called with the socket lock held, which it must release. + * - If it returns a call, the call's lock will need releasing by the caller. */ static struct rxrpc_call * rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, unsigned long user_call_ID, bool exclusive) + __releases(&rx->sk.sk_lock.slock) { struct rxrpc_conn_parameters cp; struct rxrpc_call *call; @@ -450,8 +456,10 @@ rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, _enter(""); - if (!msg->msg_name) + if (!msg->msg_name) { + release_sock(&rx->sk); return ERR_PTR(-EDESTADDRREQ); + } key = rx->key; if (key && !rx->key->payload.data[0]) @@ -464,6 +472,7 @@ rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, cp.exclusive = rx->exclusive | exclusive; cp.service_id = srx->srx_service; call = rxrpc_new_client_call(rx, &cp, srx, user_call_ID, GFP_KERNEL); + /* The socket is now unlocked */ _leave(" = %p\n", call); return call; @@ -475,6 +484,7 @@ rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, * - the socket may be either a client socket or a server socket */ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) + __releases(&rx->sk.sk_lock.slock) { enum rxrpc_command cmd; struct rxrpc_call *call; @@ -488,12 +498,14 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) ret = rxrpc_sendmsg_cmsg(msg, &user_call_ID, &cmd, &abort_code, &exclusive); if (ret < 0) - return ret; + goto error_release_sock; if (cmd == RXRPC_CMD_ACCEPT) { + ret = -EINVAL; if (rx->sk.sk_state != RXRPC_SERVER_LISTENING) - return -EINVAL; + goto error_release_sock; call = rxrpc_accept_call(rx, user_call_ID, NULL); + /* The socket is now unlocked. */ if (IS_ERR(call)) return PTR_ERR(call); rxrpc_put_call(call, rxrpc_call_put); @@ -502,12 +514,29 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) call = rxrpc_find_call_by_user_ID(rx, user_call_ID); if (!call) { + ret = -EBADSLT; if (cmd != RXRPC_CMD_SEND_DATA) - return -EBADSLT; + goto error_release_sock; + ret = -EBUSY; + if (call->state == RXRPC_CALL_UNINITIALISED || + call->state == RXRPC_CALL_CLIENT_AWAIT_CONN || + call->state == RXRPC_CALL_SERVER_PREALLOC || + call->state == RXRPC_CALL_SERVER_SECURING || + call->state == RXRPC_CALL_SERVER_ACCEPTING) + goto error_release_sock; call = rxrpc_new_client_call_for_sendmsg(rx, msg, user_call_ID, exclusive); + /* The socket is now unlocked... */ if (IS_ERR(call)) return PTR_ERR(call); + /* ... and we have the call lock. */ + } else { + ret = mutex_lock_interruptible(&call->user_mutex); + release_sock(&rx->sk); + if (ret < 0) { + ret = -ERESTARTSYS; + goto error_put; + } } _debug("CALL %d USR %lx ST %d on CONN %p", @@ -535,9 +564,15 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) ret = rxrpc_send_data(rx, call, msg, len); } + mutex_unlock(&call->user_mutex); +error_put: rxrpc_put_call(call, rxrpc_call_put); _leave(" = %d", ret); return ret; + +error_release_sock: + release_sock(&rx->sk); + return ret; } /** @@ -562,7 +597,7 @@ int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call, ASSERTCMP(msg->msg_name, ==, NULL); ASSERTCMP(msg->msg_control, ==, NULL); - lock_sock(sock->sk); + mutex_lock(&call->user_mutex); _debug("CALL %d USR %lx ST %d on CONN %p", call->debug_id, call->user_call_ID, call->state, call->conn); @@ -577,7 +612,7 @@ int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call, ret = rxrpc_send_data(rxrpc_sk(sock->sk), call, msg, len); } - release_sock(sock->sk); + mutex_unlock(&call->user_mutex); _leave(" = %d", ret); return ret; } @@ -598,12 +633,12 @@ void rxrpc_kernel_abort_call(struct socket *sock, struct rxrpc_call *call, { _enter("{%d},%d,%d,%s", call->debug_id, abort_code, error, why); - lock_sock(sock->sk); + mutex_lock(&call->user_mutex); if (rxrpc_abort_call(why, call, 0, abort_code, error)) rxrpc_send_abort_packet(call); - release_sock(sock->sk); + mutex_unlock(&call->user_mutex); _leave(""); } diff --git a/net/sctp/input.c b/net/sctp/input.c index fc458968fe4b..2a28ab20487f 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -884,14 +884,17 @@ int sctp_hash_transport(struct sctp_transport *t) arg.paddr = &t->ipaddr; arg.lport = htons(t->asoc->base.bind_addr.port); + rcu_read_lock(); list = rhltable_lookup(&sctp_transport_hashtable, &arg, sctp_hash_params); rhl_for_each_entry_rcu(transport, tmp, list, node) if (transport->asoc->ep == t->asoc->ep) { + rcu_read_unlock(); err = -EEXIST; goto out; } + rcu_read_unlock(); err = rhltable_insert_key(&sctp_transport_hashtable, &arg, &t->node, sctp_hash_params); diff --git a/tools/include/asm-generic/bitops/atomic.h b/tools/include/asm-generic/bitops/atomic.h index 18663f59d72f..68b8c1516c5a 100644 --- a/tools/include/asm-generic/bitops/atomic.h +++ b/tools/include/asm-generic/bitops/atomic.h @@ -20,4 +20,7 @@ static __always_inline int test_bit(unsigned int nr, const unsigned long *addr) (((unsigned long *)addr)[nr / __BITS_PER_LONG])) != 0; } +#define __set_bit(nr, addr) set_bit(nr, addr) +#define __clear_bit(nr, addr) clear_bit(nr, addr) + #endif /* _TOOLS_LINUX_ASM_GENERIC_BITOPS_ATOMIC_H_ */ diff --git a/tools/include/asm/bug.h b/tools/include/asm/bug.h index beda1a884b50..4790f047a89c 100644 --- a/tools/include/asm/bug.h +++ b/tools/include/asm/bug.h @@ -12,6 +12,14 @@ unlikely(__ret_warn_on); \ }) +#define WARN_ON(condition) ({ \ + int __ret_warn_on = !!(condition); \ + if (unlikely(__ret_warn_on)) \ + __WARN_printf("assertion failed at %s:%d\n", \ + __FILE__, __LINE__); \ + unlikely(__ret_warn_on); \ +}) + #define WARN_ON_ONCE(condition) ({ \ static int __warned; \ int __ret_warn_once = !!(condition); \ diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h index eef41d500e9e..e8b9f518e36b 100644 --- a/tools/include/linux/bitmap.h +++ b/tools/include/linux/bitmap.h @@ -4,6 +4,7 @@ #include <string.h> #include <linux/bitops.h> #include <stdlib.h> +#include <linux/kernel.h> #define DECLARE_BITMAP(name,bits) \ unsigned long name[BITS_TO_LONGS(bits)] diff --git a/tools/include/linux/bitops.h b/tools/include/linux/bitops.h index fc446343ff41..1aecad369af5 100644 --- a/tools/include/linux/bitops.h +++ b/tools/include/linux/bitops.h @@ -2,7 +2,6 @@ #define _TOOLS_LINUX_BITOPS_H_ #include <asm/types.h> -#include <linux/kernel.h> #include <linux/compiler.h> #ifndef __WORDSIZE diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h index 6326ede9aece..8de163b17c0d 100644 --- a/tools/include/linux/compiler.h +++ b/tools/include/linux/compiler.h @@ -25,6 +25,8 @@ #endif #define __user +#define __rcu +#define __read_mostly #ifndef __attribute_const__ # define __attribute_const__ @@ -54,6 +56,8 @@ # define unlikely(x) __builtin_expect(!!(x), 0) #endif +#define uninitialized_var(x) x = *(&(x)) + #define ACCESS_ONCE(x) (*(volatile typeof(x) *)&(x)) #include <linux/types.h> diff --git a/tools/include/linux/spinlock.h b/tools/include/linux/spinlock.h new file mode 100644 index 000000000000..58397dcb19d6 --- /dev/null +++ b/tools/include/linux/spinlock.h @@ -0,0 +1,5 @@ +#define spinlock_t pthread_mutex_t +#define DEFINE_SPINLOCK(x) pthread_mutex_t x = PTHREAD_MUTEX_INITIALIZER; + +#define spin_lock_irqsave(x, f) (void)f, pthread_mutex_lock(x) +#define spin_unlock_irqrestore(x, f) (void)f, pthread_mutex_unlock(x) diff --git a/tools/testing/radix-tree/.gitignore b/tools/testing/radix-tree/.gitignore index 11d888ca6a92..d4706c0ffceb 100644 --- a/tools/testing/radix-tree/.gitignore +++ b/tools/testing/radix-tree/.gitignore @@ -1,2 +1,6 @@ +generated/map-shift.h +idr.c +idr-test main +multiorder radix-tree.c diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile index 3635e4d3eca7..f11315bedefc 100644 --- a/tools/testing/radix-tree/Makefile +++ b/tools/testing/radix-tree/Makefile @@ -1,29 +1,47 @@ -CFLAGS += -I. -I../../include -g -O2 -Wall -D_LGPL_SOURCE +CFLAGS += -I. -I../../include -g -O2 -Wall -D_LGPL_SOURCE -fsanitize=address LDFLAGS += -lpthread -lurcu -TARGETS = main -OFILES = main.o radix-tree.o linux.o test.o tag_check.o find_next_bit.o \ - regression1.o regression2.o regression3.o multiorder.o \ - iteration_check.o benchmark.o +TARGETS = main idr-test multiorder +CORE_OFILES := radix-tree.o idr.o linux.o test.o find_bit.o +OFILES = main.o $(CORE_OFILES) regression1.o regression2.o regression3.o \ + tag_check.o multiorder.o idr-test.o iteration_check.o benchmark.o -ifdef BENCHMARK - CFLAGS += -DBENCHMARK=1 +ifndef SHIFT + SHIFT=3 endif -targets: $(TARGETS) +targets: mapshift $(TARGETS) main: $(OFILES) - $(CC) $(CFLAGS) $(LDFLAGS) $(OFILES) -o main + $(CC) $(CFLAGS) $(LDFLAGS) $^ -o main + +idr-test: idr-test.o $(CORE_OFILES) + $(CC) $(CFLAGS) $(LDFLAGS) $^ -o idr-test + +multiorder: multiorder.o $(CORE_OFILES) + $(CC) $(CFLAGS) $(LDFLAGS) $^ -o multiorder clean: - $(RM) -f $(TARGETS) *.o radix-tree.c + $(RM) $(TARGETS) *.o radix-tree.c idr.c generated/map-shift.h -find_next_bit.o: ../../lib/find_bit.c - $(CC) $(CFLAGS) -c -o $@ $< +vpath %.c ../../lib -$(OFILES): *.h */*.h \ +$(OFILES): *.h */*.h generated/map-shift.h \ ../../include/linux/*.h \ - ../../../include/linux/radix-tree.h + ../../include/asm/*.h \ + ../../../include/linux/radix-tree.h \ + ../../../include/linux/idr.h radix-tree.c: ../../../lib/radix-tree.c sed -e 's/^static //' -e 's/__always_inline //' -e 's/inline //' < $< > $@ + +idr.c: ../../../lib/idr.c + sed -e 's/^static //' -e 's/__always_inline //' -e 's/inline //' < $< > $@ + +.PHONY: mapshift + +mapshift: + @if ! grep -qw $(SHIFT) generated/map-shift.h; then \ + echo "#define RADIX_TREE_MAP_SHIFT $(SHIFT)" > \ + generated/map-shift.h; \ + fi diff --git a/tools/testing/radix-tree/benchmark.c b/tools/testing/radix-tree/benchmark.c index 215ca86c7605..9b09ddfe462f 100644 --- a/tools/testing/radix-tree/benchmark.c +++ b/tools/testing/radix-tree/benchmark.c @@ -71,7 +71,7 @@ static void benchmark_size(unsigned long size, unsigned long step, int order) tagged = benchmark_iter(&tree, true); normal = benchmark_iter(&tree, false); - printf("Size %ld, step %6ld, order %d tagged %10lld ns, normal %10lld ns\n", + printv(2, "Size %ld, step %6ld, order %d tagged %10lld ns, normal %10lld ns\n", size, step, order, tagged, normal); item_kill_tree(&tree); @@ -85,8 +85,8 @@ void benchmark(void) 128, 256, 512, 12345, 0}; int c, s; - printf("starting benchmarks\n"); - printf("RADIX_TREE_MAP_SHIFT = %d\n", RADIX_TREE_MAP_SHIFT); + printv(1, "starting benchmarks\n"); + printv(1, "RADIX_TREE_MAP_SHIFT = %d\n", RADIX_TREE_MAP_SHIFT); for (c = 0; size[c]; c++) for (s = 0; step[s]; s++) diff --git a/tools/testing/radix-tree/generated/autoconf.h b/tools/testing/radix-tree/generated/autoconf.h index ad18cf5a2a3a..cf88dc5b8832 100644 --- a/tools/testing/radix-tree/generated/autoconf.h +++ b/tools/testing/radix-tree/generated/autoconf.h @@ -1,3 +1 @@ #define CONFIG_RADIX_TREE_MULTIORDER 1 -#define CONFIG_SHMEM 1 -#define CONFIG_SWAP 1 diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c new file mode 100644 index 000000000000..a26098c6123d --- /dev/null +++ b/tools/testing/radix-tree/idr-test.c @@ -0,0 +1,444 @@ +/* + * idr-test.c: Test the IDR API + * Copyright (c) 2016 Matthew Wilcox <willy@infradead.org> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ +#include <linux/bitmap.h> +#include <linux/idr.h> +#include <linux/slab.h> +#include <linux/kernel.h> +#include <linux/errno.h> + +#include "test.h" + +#define DUMMY_PTR ((void *)0x12) + +int item_idr_free(int id, void *p, void *data) +{ + struct item *item = p; + assert(item->index == id); + free(p); + + return 0; +} + +void item_idr_remove(struct idr *idr, int id) +{ + struct item *item = idr_find(idr, id); + assert(item->index == id); + idr_remove(idr, id); + free(item); +} + +void idr_alloc_test(void) +{ + unsigned long i; + DEFINE_IDR(idr); + + assert(idr_alloc_cyclic(&idr, DUMMY_PTR, 0, 0x4000, GFP_KERNEL) == 0); + assert(idr_alloc_cyclic(&idr, DUMMY_PTR, 0x3ffd, 0x4000, GFP_KERNEL) == 0x3ffd); + idr_remove(&idr, 0x3ffd); + idr_remove(&idr, 0); + + for (i = 0x3ffe; i < 0x4003; i++) { + int id; + struct item *item; + + if (i < 0x4000) + item = item_create(i, 0); + else + item = item_create(i - 0x3fff, 0); + + id = idr_alloc_cyclic(&idr, item, 1, 0x4000, GFP_KERNEL); + assert(id == item->index); + } + + idr_for_each(&idr, item_idr_free, &idr); + idr_destroy(&idr); +} + +void idr_replace_test(void) +{ + DEFINE_IDR(idr); + + idr_alloc(&idr, (void *)-1, 10, 11, GFP_KERNEL); + idr_replace(&idr, &idr, 10); + + idr_destroy(&idr); +} + +/* + * Unlike the radix tree, you can put a NULL pointer -- with care -- into + * the IDR. Some interfaces, like idr_find() do not distinguish between + * "present, value is NULL" and "not present", but that's exactly what some + * users want. + */ +void idr_null_test(void) +{ + int i; + DEFINE_IDR(idr); + + assert(idr_is_empty(&idr)); + + assert(idr_alloc(&idr, NULL, 0, 0, GFP_KERNEL) == 0); + assert(!idr_is_empty(&idr)); + idr_remove(&idr, 0); + assert(idr_is_empty(&idr)); + + assert(idr_alloc(&idr, NULL, 0, 0, GFP_KERNEL) == 0); + assert(!idr_is_empty(&idr)); + idr_destroy(&idr); + assert(idr_is_empty(&idr)); + + for (i = 0; i < 10; i++) { + assert(idr_alloc(&idr, NULL, 0, 0, GFP_KERNEL) == i); + } + + assert(idr_replace(&idr, DUMMY_PTR, 3) == NULL); + assert(idr_replace(&idr, DUMMY_PTR, 4) == NULL); + assert(idr_replace(&idr, NULL, 4) == DUMMY_PTR); + assert(idr_replace(&idr, DUMMY_PTR, 11) == ERR_PTR(-ENOENT)); + idr_remove(&idr, 5); + assert(idr_alloc(&idr, NULL, 0, 0, GFP_KERNEL) == 5); + idr_remove(&idr, 5); + + for (i = 0; i < 9; i++) { + idr_remove(&idr, i); + assert(!idr_is_empty(&idr)); + } + idr_remove(&idr, 8); + assert(!idr_is_empty(&idr)); + idr_remove(&idr, 9); + assert(idr_is_empty(&idr)); + + assert(idr_alloc(&idr, NULL, 0, 0, GFP_KERNEL) == 0); + assert(idr_replace(&idr, DUMMY_PTR, 3) == ERR_PTR(-ENOENT)); + assert(idr_replace(&idr, DUMMY_PTR, 0) == NULL); + assert(idr_replace(&idr, NULL, 0) == DUMMY_PTR); + + idr_destroy(&idr); + assert(idr_is_empty(&idr)); + + for (i = 1; i < 10; i++) { + assert(idr_alloc(&idr, NULL, 1, 0, GFP_KERNEL) == i); + } + + idr_destroy(&idr); + assert(idr_is_empty(&idr)); +} + +void idr_nowait_test(void) +{ + unsigned int i; + DEFINE_IDR(idr); + + idr_preload(GFP_KERNEL); + + for (i = 0; i < 3; i++) { + struct item *item = item_create(i, 0); + assert(idr_alloc(&idr, item, i, i + 1, GFP_NOWAIT) == i); + } + + idr_preload_end(); + + idr_for_each(&idr, item_idr_free, &idr); + idr_destroy(&idr); +} + +void idr_checks(void) +{ + unsigned long i; + DEFINE_IDR(idr); + + for (i = 0; i < 10000; i++) { + struct item *item = item_create(i, 0); + assert(idr_alloc(&idr, item, 0, 20000, GFP_KERNEL) == i); + } + + assert(idr_alloc(&idr, DUMMY_PTR, 5, 30, GFP_KERNEL) < 0); + + for (i = 0; i < 5000; i++) + item_idr_remove(&idr, i); + + idr_remove(&idr, 3); + + idr_for_each(&idr, item_idr_free, &idr); + idr_destroy(&idr); + + assert(idr_is_empty(&idr)); + + idr_remove(&idr, 3); + idr_remove(&idr, 0); + + for (i = INT_MAX - 3UL; i < INT_MAX + 1UL; i++) { + struct item *item = item_create(i, 0); + assert(idr_alloc(&idr, item, i, i + 10, GFP_KERNEL) == i); + } + assert(idr_alloc(&idr, DUMMY_PTR, i - 2, i, GFP_KERNEL) == -ENOSPC); + + idr_for_each(&idr, item_idr_free, &idr); + idr_destroy(&idr); + idr_destroy(&idr); + + assert(idr_is_empty(&idr)); + + for (i = 1; i < 10000; i++) { + struct item *item = item_create(i, 0); + assert(idr_alloc(&idr, item, 1, 20000, GFP_KERNEL) == i); + } + + idr_for_each(&idr, item_idr_free, &idr); + idr_destroy(&idr); + + idr_replace_test(); + idr_alloc_test(); + idr_null_test(); + idr_nowait_test(); +} + +/* + * Check that we get the correct error when we run out of memory doing + * allocations. To ensure we run out of memory, just "forget" to preload. + * The first test is for not having a bitmap available, and the second test + * is for not being able to allocate a level of the radix tree. + */ +void ida_check_nomem(void) +{ + DEFINE_IDA(ida); + int id, err; + + err = ida_get_new_above(&ida, 256, &id); + assert(err == -EAGAIN); + err = ida_get_new_above(&ida, 1UL << 30, &id); + assert(err == -EAGAIN); +} + +/* + * Check what happens when we fill a leaf and then delete it. This may + * discover mishandling of IDR_FREE. + */ +void ida_check_leaf(void) +{ + DEFINE_IDA(ida); + int id; + unsigned long i; + + for (i = 0; i < IDA_BITMAP_BITS; i++) { + assert(ida_pre_get(&ida, GFP_KERNEL)); + assert(!ida_get_new(&ida, &id)); + assert(id == i); + } + + ida_destroy(&ida); + assert(ida_is_empty(&ida)); + + assert(ida_pre_get(&ida, GFP_KERNEL)); + assert(!ida_get_new(&ida, &id)); + assert(id == 0); + ida_destroy(&ida); + assert(ida_is_empty(&ida)); +} + +/* + * Check handling of conversions between exceptional entries and full bitmaps. + */ +void ida_check_conv(void) +{ + DEFINE_IDA(ida); + int id; + unsigned long i; + + for (i = 0; i < IDA_BITMAP_BITS * 2; i += IDA_BITMAP_BITS) { + assert(ida_pre_get(&ida, GFP_KERNEL)); + assert(!ida_get_new_above(&ida, i + 1, &id)); + assert(id == i + 1); + assert(!ida_get_new_above(&ida, i + BITS_PER_LONG, &id)); + assert(id == i + BITS_PER_LONG); + ida_remove(&ida, i + 1); + ida_remove(&ida, i + BITS_PER_LONG); + assert(ida_is_empty(&ida)); + } + + assert(ida_pre_get(&ida, GFP_KERNEL)); + + for (i = 0; i < IDA_BITMAP_BITS * 2; i++) { + assert(ida_pre_get(&ida, GFP_KERNEL)); + assert(!ida_get_new(&ida, &id)); + assert(id == i); + } + + for (i = IDA_BITMAP_BITS * 2; i > 0; i--) { + ida_remove(&ida, i - 1); + } + assert(ida_is_empty(&ida)); + + for (i = 0; i < IDA_BITMAP_BITS + BITS_PER_LONG - 4; i++) { + assert(ida_pre_get(&ida, GFP_KERNEL)); + assert(!ida_get_new(&ida, &id)); + assert(id == i); + } + + for (i = IDA_BITMAP_BITS + BITS_PER_LONG - 4; i > 0; i--) { + ida_remove(&ida, i - 1); + } + assert(ida_is_empty(&ida)); + + radix_tree_cpu_dead(1); + for (i = 0; i < 1000000; i++) { + int err = ida_get_new(&ida, &id); + if (err == -EAGAIN) { + assert((i % IDA_BITMAP_BITS) == (BITS_PER_LONG - 2)); + assert(ida_pre_get(&ida, GFP_KERNEL)); + err = ida_get_new(&ida, &id); + } else { + assert((i % IDA_BITMAP_BITS) != (BITS_PER_LONG - 2)); + } + assert(!err); + assert(id == i); + } + ida_destroy(&ida); +} + +/* + * Check allocations up to and slightly above the maximum allowed (2^31-1) ID. + * Allocating up to 2^31-1 should succeed, and then allocating the next one + * should fail. + */ +void ida_check_max(void) +{ + DEFINE_IDA(ida); + int id, err; + unsigned long i, j; + + for (j = 1; j < 65537; j *= 2) { + unsigned long base = (1UL << 31) - j; + for (i = 0; i < j; i++) { + assert(ida_pre_get(&ida, GFP_KERNEL)); + assert(!ida_get_new_above(&ida, base, &id)); + assert(id == base + i); + } + assert(ida_pre_get(&ida, GFP_KERNEL)); + err = ida_get_new_above(&ida, base, &id); + assert(err == -ENOSPC); + ida_destroy(&ida); + assert(ida_is_empty(&ida)); + rcu_barrier(); + } +} + +void ida_check_random(void) +{ + DEFINE_IDA(ida); + DECLARE_BITMAP(bitmap, 2048); + int id; + unsigned int i; + time_t s = time(NULL); + + repeat: + memset(bitmap, 0, sizeof(bitmap)); + for (i = 0; i < 100000; i++) { + int i = rand(); + int bit = i & 2047; + if (test_bit(bit, bitmap)) { + __clear_bit(bit, bitmap); + ida_remove(&ida, bit); + } else { + __set_bit(bit, bitmap); + ida_pre_get(&ida, GFP_KERNEL); + assert(!ida_get_new_above(&ida, bit, &id)); + assert(id == bit); + } + } + ida_destroy(&ida); + if (time(NULL) < s + 10) + goto repeat; +} + +void ida_checks(void) +{ + DEFINE_IDA(ida); + int id; + unsigned long i; + + radix_tree_cpu_dead(1); + ida_check_nomem(); + + for (i = 0; i < 10000; i++) { + assert(ida_pre_get(&ida, GFP_KERNEL)); + assert(!ida_get_new(&ida, &id)); + assert(id == i); + } + + ida_remove(&ida, 20); + ida_remove(&ida, 21); + for (i = 0; i < 3; i++) { + assert(ida_pre_get(&ida, GFP_KERNEL)); + assert(!ida_get_new(&ida, &id)); + if (i == 2) + assert(id == 10000); + } + + for (i = 0; i < 5000; i++) + ida_remove(&ida, i); + + assert(ida_pre_get(&ida, GFP_KERNEL)); + assert(!ida_get_new_above(&ida, 5000, &id)); + assert(id == 10001); + + ida_destroy(&ida); + + assert(ida_is_empty(&ida)); + + assert(ida_pre_get(&ida, GFP_KERNEL)); + assert(!ida_get_new_above(&ida, 1, &id)); + assert(id == 1); + + ida_remove(&ida, id); + assert(ida_is_empty(&ida)); + ida_destroy(&ida); + assert(ida_is_empty(&ida)); + + assert(ida_pre_get(&ida, GFP_KERNEL)); + assert(!ida_get_new_above(&ida, 1, &id)); + ida_destroy(&ida); + assert(ida_is_empty(&ida)); + + assert(ida_pre_get(&ida, GFP_KERNEL)); + assert(!ida_get_new_above(&ida, 1, &id)); + assert(id == 1); + assert(ida_pre_get(&ida, GFP_KERNEL)); + assert(!ida_get_new_above(&ida, 1025, &id)); + assert(id == 1025); + assert(ida_pre_get(&ida, GFP_KERNEL)); + assert(!ida_get_new_above(&ida, 10000, &id)); + assert(id == 10000); + ida_remove(&ida, 1025); + ida_destroy(&ida); + assert(ida_is_empty(&ida)); + + ida_check_leaf(); + ida_check_max(); + ida_check_conv(); + ida_check_random(); + + radix_tree_cpu_dead(1); +} + +int __weak main(void) +{ + radix_tree_init(); + idr_checks(); + ida_checks(); + rcu_barrier(); + if (nr_allocated) + printf("nr_allocated = %d\n", nr_allocated); + return 0; +} diff --git a/tools/testing/radix-tree/iteration_check.c b/tools/testing/radix-tree/iteration_check.c index 7572b7ed930e..a92bab513701 100644 --- a/tools/testing/radix-tree/iteration_check.c +++ b/tools/testing/radix-tree/iteration_check.c @@ -177,7 +177,7 @@ void iteration_test(unsigned order, unsigned test_duration) { int i; - printf("Running %siteration tests for %d seconds\n", + printv(1, "Running %siteration tests for %d seconds\n", order > 0 ? "multiorder " : "", test_duration); max_order = order; diff --git a/tools/testing/radix-tree/linux.c b/tools/testing/radix-tree/linux.c index d31ea7c9abec..cf48c8473f48 100644 --- a/tools/testing/radix-tree/linux.c +++ b/tools/testing/radix-tree/linux.c @@ -5,7 +5,7 @@ #include <unistd.h> #include <assert.h> -#include <linux/mempool.h> +#include <linux/gfp.h> #include <linux/poison.h> #include <linux/slab.h> #include <linux/radix-tree.h> @@ -13,6 +13,8 @@ int nr_allocated; int preempt_count; +int kmalloc_verbose; +int test_verbose; struct kmem_cache { pthread_mutex_t lock; @@ -22,27 +24,6 @@ struct kmem_cache { void (*ctor)(void *); }; -void *mempool_alloc(mempool_t *pool, int gfp_mask) -{ - return pool->alloc(gfp_mask, pool->data); -} - -void mempool_free(void *element, mempool_t *pool) -{ - pool->free(element, pool->data); -} - -mempool_t *mempool_create(int min_nr, mempool_alloc_t *alloc_fn, - mempool_free_t *free_fn, void *pool_data) -{ - mempool_t *ret = malloc(sizeof(*ret)); - - ret->alloc = alloc_fn; - ret->free = free_fn; - ret->data = pool_data; - return ret; -} - void *kmem_cache_alloc(struct kmem_cache *cachep, int flags) { struct radix_tree_node *node; @@ -54,9 +35,9 @@ void *kmem_cache_alloc(struct kmem_cache *cachep, int flags) if (cachep->nr_objs) { cachep->nr_objs--; node = cachep->objs; - cachep->objs = node->private_data; + cachep->objs = node->parent; pthread_mutex_unlock(&cachep->lock); - node->private_data = NULL; + node->parent = NULL; } else { pthread_mutex_unlock(&cachep->lock); node = malloc(cachep->size); @@ -65,6 +46,8 @@ void *kmem_cache_alloc(struct kmem_cache *cachep, int flags) } uatomic_inc(&nr_allocated); + if (kmalloc_verbose) + printf("Allocating %p from slab\n", node); return node; } @@ -72,6 +55,8 @@ void kmem_cache_free(struct kmem_cache *cachep, void *objp) { assert(objp); uatomic_dec(&nr_allocated); + if (kmalloc_verbose) + printf("Freeing %p to slab\n", objp); pthread_mutex_lock(&cachep->lock); if (cachep->nr_objs > 10) { memset(objp, POISON_FREE, cachep->size); @@ -79,7 +64,7 @@ void kmem_cache_free(struct kmem_cache *cachep, void *objp) } else { struct radix_tree_node *node = objp; cachep->nr_objs++; - node->private_data = cachep->objs; + node->parent = cachep->objs; cachep->objs = node; } pthread_mutex_unlock(&cachep->lock); @@ -89,6 +74,8 @@ void *kmalloc(size_t size, gfp_t gfp) { void *ret = malloc(size); uatomic_inc(&nr_allocated); + if (kmalloc_verbose) + printf("Allocating %p from malloc\n", ret); return ret; } @@ -97,6 +84,8 @@ void kfree(void *p) if (!p) return; uatomic_dec(&nr_allocated); + if (kmalloc_verbose) + printf("Freeing %p to malloc\n", p); free(p); } diff --git a/tools/testing/radix-tree/linux/bitops.h b/tools/testing/radix-tree/linux/bitops.h deleted file mode 100644 index a13e9bc76eec..000000000000 --- a/tools/testing/radix-tree/linux/bitops.h +++ /dev/null @@ -1,160 +0,0 @@ -#ifndef _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ -#define _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ - -#include <linux/types.h> -#include <linux/bitops/find.h> -#include <linux/bitops/hweight.h> -#include <linux/kernel.h> - -#define BIT_MASK(nr) (1UL << ((nr) % BITS_PER_LONG)) -#define BIT_WORD(nr) ((nr) / BITS_PER_LONG) -#define BITS_PER_BYTE 8 -#define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long)) - -/** - * __set_bit - Set a bit in memory - * @nr: the bit to set - * @addr: the address to start counting from - * - * Unlike set_bit(), this function is non-atomic and may be reordered. - * If it's called on the same region of memory simultaneously, the effect - * may be that only one operation succeeds. - */ -static inline void __set_bit(int nr, volatile unsigned long *addr) -{ - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); - - *p |= mask; -} - -static inline void __clear_bit(int nr, volatile unsigned long *addr) -{ - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); - - *p &= ~mask; -} - -/** - * __change_bit - Toggle a bit in memory - * @nr: the bit to change - * @addr: the address to start counting from - * - * Unlike change_bit(), this function is non-atomic and may be reordered. - * If it's called on the same region of memory simultaneously, the effect - * may be that only one operation succeeds. - */ -static inline void __change_bit(int nr, volatile unsigned long *addr) -{ - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); - - *p ^= mask; -} - -/** - * __test_and_set_bit - Set a bit and return its old value - * @nr: Bit to set - * @addr: Address to count from - * - * This operation is non-atomic and can be reordered. - * If two examples of this operation race, one can appear to succeed - * but actually fail. You must protect multiple accesses with a lock. - */ -static inline int __test_and_set_bit(int nr, volatile unsigned long *addr) -{ - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); - unsigned long old = *p; - - *p = old | mask; - return (old & mask) != 0; -} - -/** - * __test_and_clear_bit - Clear a bit and return its old value - * @nr: Bit to clear - * @addr: Address to count from - * - * This operation is non-atomic and can be reordered. - * If two examples of this operation race, one can appear to succeed - * but actually fail. You must protect multiple accesses with a lock. - */ -static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr) -{ - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); - unsigned long old = *p; - - *p = old & ~mask; - return (old & mask) != 0; -} - -/* WARNING: non atomic and it can be reordered! */ -static inline int __test_and_change_bit(int nr, - volatile unsigned long *addr) -{ - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); - unsigned long old = *p; - - *p = old ^ mask; - return (old & mask) != 0; -} - -/** - * test_bit - Determine whether a bit is set - * @nr: bit number to test - * @addr: Address to start counting from - */ -static inline int test_bit(int nr, const volatile unsigned long *addr) -{ - return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1))); -} - -/** - * __ffs - find first bit in word. - * @word: The word to search - * - * Undefined if no bit exists, so code should check against 0 first. - */ -static inline unsigned long __ffs(unsigned long word) -{ - int num = 0; - - if ((word & 0xffffffff) == 0) { - num += 32; - word >>= 32; - } - if ((word & 0xffff) == 0) { - num += 16; - word >>= 16; - } - if ((word & 0xff) == 0) { - num += 8; - word >>= 8; - } - if ((word & 0xf) == 0) { - num += 4; - word >>= 4; - } - if ((word & 0x3) == 0) { - num += 2; - word >>= 2; - } - if ((word & 0x1) == 0) - num += 1; - return num; -} - -unsigned long find_next_bit(const unsigned long *addr, - unsigned long size, - unsigned long offset); - -static inline unsigned long hweight_long(unsigned long w) -{ - return sizeof(w) == 4 ? hweight32(w) : hweight64(w); -} - -#endif /* _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ */ diff --git a/tools/testing/radix-tree/linux/bitops/__ffs.h b/tools/testing/radix-tree/linux/bitops/__ffs.h deleted file mode 100644 index 9a3274aecf83..000000000000 --- a/tools/testing/radix-tree/linux/bitops/__ffs.h +++ /dev/null @@ -1,43 +0,0 @@ -#ifndef _ASM_GENERIC_BITOPS___FFS_H_ -#define _ASM_GENERIC_BITOPS___FFS_H_ - -#include <asm/types.h> - -/** - * __ffs - find first bit in word. - * @word: The word to search - * - * Undefined if no bit exists, so code should check against 0 first. - */ -static inline unsigned long __ffs(unsigned long word) -{ - int num = 0; - -#if BITS_PER_LONG == 64 - if ((word & 0xffffffff) == 0) { - num += 32; - word >>= 32; - } -#endif - if ((word & 0xffff) == 0) { - num += 16; - word >>= 16; - } - if ((word & 0xff) == 0) { - num += 8; - word >>= 8; - } - if ((word & 0xf) == 0) { - num += 4; - word >>= 4; - } - if ((word & 0x3) == 0) { - num += 2; - word >>= 2; - } - if ((word & 0x1) == 0) - num += 1; - return num; -} - -#endif /* _ASM_GENERIC_BITOPS___FFS_H_ */ diff --git a/tools/testing/radix-tree/linux/bitops/ffs.h b/tools/testing/radix-tree/linux/bitops/ffs.h deleted file mode 100644 index fbbb43af7dc0..000000000000 --- a/tools/testing/radix-tree/linux/bitops/ffs.h +++ /dev/null @@ -1,41 +0,0 @@ -#ifndef _ASM_GENERIC_BITOPS_FFS_H_ -#define _ASM_GENERIC_BITOPS_FFS_H_ - -/** - * ffs - find first bit set - * @x: the word to search - * - * This is defined the same way as - * the libc and compiler builtin ffs routines, therefore - * differs in spirit from the above ffz (man ffs). - */ -static inline int ffs(int x) -{ - int r = 1; - - if (!x) - return 0; - if (!(x & 0xffff)) { - x >>= 16; - r += 16; - } - if (!(x & 0xff)) { - x >>= 8; - r += 8; - } - if (!(x & 0xf)) { - x >>= 4; - r += 4; - } - if (!(x & 3)) { - x >>= 2; - r += 2; - } - if (!(x & 1)) { - x >>= 1; - r += 1; - } - return r; -} - -#endif /* _ASM_GENERIC_BITOPS_FFS_H_ */ diff --git a/tools/testing/radix-tree/linux/bitops/ffz.h b/tools/testing/radix-tree/linux/bitops/ffz.h deleted file mode 100644 index 6744bd4cdf46..000000000000 --- a/tools/testing/radix-tree/linux/bitops/ffz.h +++ /dev/null @@ -1,12 +0,0 @@ -#ifndef _ASM_GENERIC_BITOPS_FFZ_H_ -#define _ASM_GENERIC_BITOPS_FFZ_H_ - -/* - * ffz - find first zero in word. - * @word: The word to search - * - * Undefined if no zero exists, so code should check against ~0UL first. - */ -#define ffz(x) __ffs(~(x)) - -#endif /* _ASM_GENERIC_BITOPS_FFZ_H_ */ diff --git a/tools/testing/radix-tree/linux/bitops/find.h b/tools/testing/radix-tree/linux/bitops/find.h deleted file mode 100644 index 72a51e5a12ef..000000000000 --- a/tools/testing/radix-tree/linux/bitops/find.h +++ /dev/null @@ -1,13 +0,0 @@ -#ifndef _ASM_GENERIC_BITOPS_FIND_H_ -#define _ASM_GENERIC_BITOPS_FIND_H_ - -extern unsigned long find_next_bit(const unsigned long *addr, unsigned long - size, unsigned long offset); - -extern unsigned long find_next_zero_bit(const unsigned long *addr, unsigned - long size, unsigned long offset); - -#define find_first_bit(addr, size) find_next_bit((addr), (size), 0) -#define find_first_zero_bit(addr, size) find_next_zero_bit((addr), (size), 0) - -#endif /*_ASM_GENERIC_BITOPS_FIND_H_ */ diff --git a/tools/testing/radix-tree/linux/bitops/fls.h b/tools/testing/radix-tree/linux/bitops/fls.h deleted file mode 100644 index 850859bc5069..000000000000 --- a/tools/testing/radix-tree/linux/bitops/fls.h +++ /dev/null @@ -1,41 +0,0 @@ -#ifndef _ASM_GENERIC_BITOPS_FLS_H_ -#define _ASM_GENERIC_BITOPS_FLS_H_ - -/** - * fls - find last (most-significant) bit set - * @x: the word to search - * - * This is defined the same way as ffs. - * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32. - */ - -static inline int fls(int x) -{ - int r = 32; - - if (!x) - return 0; - if (!(x & 0xffff0000u)) { - x <<= 16; - r -= 16; - } - if (!(x & 0xff000000u)) { - x <<= 8; - r -= 8; - } - if (!(x & 0xf0000000u)) { - x <<= 4; - r -= 4; - } - if (!(x & 0xc0000000u)) { - x <<= 2; - r -= 2; - } - if (!(x & 0x80000000u)) { - x <<= 1; - r -= 1; - } - return r; -} - -#endif /* _ASM_GENERIC_BITOPS_FLS_H_ */ diff --git a/tools/testing/radix-tree/linux/bitops/fls64.h b/tools/testing/radix-tree/linux/bitops/fls64.h deleted file mode 100644 index 1b6b17ce2428..000000000000 --- a/tools/testing/radix-tree/linux/bitops/fls64.h +++ /dev/null @@ -1,14 +0,0 @@ -#ifndef _ASM_GENERIC_BITOPS_FLS64_H_ -#define _ASM_GENERIC_BITOPS_FLS64_H_ - -#include <asm/types.h> - -static inline int fls64(__u64 x) -{ - __u32 h = x >> 32; - if (h) - return fls(h) + 32; - return fls(x); -} - -#endif /* _ASM_GENERIC_BITOPS_FLS64_H_ */ diff --git a/tools/testing/radix-tree/linux/bitops/hweight.h b/tools/testing/radix-tree/linux/bitops/hweight.h deleted file mode 100644 index fbbc383771da..000000000000 --- a/tools/testing/radix-tree/linux/bitops/hweight.h +++ /dev/null @@ -1,11 +0,0 @@ -#ifndef _ASM_GENERIC_BITOPS_HWEIGHT_H_ -#define _ASM_GENERIC_BITOPS_HWEIGHT_H_ - -#include <asm/types.h> - -extern unsigned int hweight32(unsigned int w); -extern unsigned int hweight16(unsigned int w); -extern unsigned int hweight8(unsigned int w); -extern unsigned long hweight64(__u64 w); - -#endif /* _ASM_GENERIC_BITOPS_HWEIGHT_H_ */ diff --git a/tools/testing/radix-tree/linux/bitops/le.h b/tools/testing/radix-tree/linux/bitops/le.h deleted file mode 100644 index b9c7e5d2d2ad..000000000000 --- a/tools/testing/radix-tree/linux/bitops/le.h +++ /dev/null @@ -1,53 +0,0 @@ -#ifndef _ASM_GENERIC_BITOPS_LE_H_ -#define _ASM_GENERIC_BITOPS_LE_H_ - -#include <asm/types.h> -#include <asm/byteorder.h> - -#define BITOP_WORD(nr) ((nr) / BITS_PER_LONG) -#define BITOP_LE_SWIZZLE ((BITS_PER_LONG-1) & ~0x7) - -#if defined(__LITTLE_ENDIAN) - -#define generic_test_le_bit(nr, addr) test_bit(nr, addr) -#define generic___set_le_bit(nr, addr) __set_bit(nr, addr) -#define generic___clear_le_bit(nr, addr) __clear_bit(nr, addr) - -#define generic_test_and_set_le_bit(nr, addr) test_and_set_bit(nr, addr) -#define generic_test_and_clear_le_bit(nr, addr) test_and_clear_bit(nr, addr) - -#define generic___test_and_set_le_bit(nr, addr) __test_and_set_bit(nr, addr) -#define generic___test_and_clear_le_bit(nr, addr) __test_and_clear_bit(nr, addr) - -#define generic_find_next_zero_le_bit(addr, size, offset) find_next_zero_bit(addr, size, offset) - -#elif defined(__BIG_ENDIAN) - -#define generic_test_le_bit(nr, addr) \ - test_bit((nr) ^ BITOP_LE_SWIZZLE, (addr)) -#define generic___set_le_bit(nr, addr) \ - __set_bit((nr) ^ BITOP_LE_SWIZZLE, (addr)) -#define generic___clear_le_bit(nr, addr) \ - __clear_bit((nr) ^ BITOP_LE_SWIZZLE, (addr)) - -#define generic_test_and_set_le_bit(nr, addr) \ - test_and_set_bit((nr) ^ BITOP_LE_SWIZZLE, (addr)) -#define generic_test_and_clear_le_bit(nr, addr) \ - test_and_clear_bit((nr) ^ BITOP_LE_SWIZZLE, (addr)) - -#define generic___test_and_set_le_bit(nr, addr) \ - __test_and_set_bit((nr) ^ BITOP_LE_SWIZZLE, (addr)) -#define generic___test_and_clear_le_bit(nr, addr) \ - __test_and_clear_bit((nr) ^ BITOP_LE_SWIZZLE, (addr)) - -extern unsigned long generic_find_next_zero_le_bit(const unsigned long *addr, - unsigned long size, unsigned long offset); - -#else -#error "Please fix <asm/byteorder.h>" -#endif - -#define generic_find_first_zero_le_bit(addr, size) \ - generic_find_next_zero_le_bit((addr), (size), 0) - -#endif /* _ASM_GENERIC_BITOPS_LE_H_ */ diff --git a/tools/testing/radix-tree/linux/bitops/non-atomic.h b/tools/testing/radix-tree/linux/bitops/non-atomic.h deleted file mode 100644 index 6a1bcb9d2c4a..000000000000 --- a/tools/testing/radix-tree/linux/bitops/non-atomic.h +++ /dev/null @@ -1,110 +0,0 @@ -#ifndef _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ -#define _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ - -#include <asm/types.h> - -#define BITOP_WORD(nr) ((nr) / BITS_PER_LONG) - -/** - * __set_bit - Set a bit in memory - * @nr: the bit to set - * @addr: the address to start counting from - * - * Unlike set_bit(), this function is non-atomic and may be reordered. - * If it's called on the same region of memory simultaneously, the effect - * may be that only one operation succeeds. - */ -static inline void __set_bit(int nr, volatile unsigned long *addr) -{ - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr); - - *p |= mask; -} - -static inline void __clear_bit(int nr, volatile unsigned long *addr) -{ - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr); - - *p &= ~mask; -} - -/** - * __change_bit - Toggle a bit in memory - * @nr: the bit to change - * @addr: the address to start counting from - * - * Unlike change_bit(), this function is non-atomic and may be reordered. - * If it's called on the same region of memory simultaneously, the effect - * may be that only one operation succeeds. - */ -static inline void __change_bit(int nr, volatile unsigned long *addr) -{ - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr); - - *p ^= mask; -} - -/** - * __test_and_set_bit - Set a bit and return its old value - * @nr: Bit to set - * @addr: Address to count from - * - * This operation is non-atomic and can be reordered. - * If two examples of this operation race, one can appear to succeed - * but actually fail. You must protect multiple accesses with a lock. - */ -static inline int __test_and_set_bit(int nr, volatile unsigned long *addr) -{ - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr); - unsigned long old = *p; - - *p = old | mask; - return (old & mask) != 0; -} - -/** - * __test_and_clear_bit - Clear a bit and return its old value - * @nr: Bit to clear - * @addr: Address to count from - * - * This operation is non-atomic and can be reordered. - * If two examples of this operation race, one can appear to succeed - * but actually fail. You must protect multiple accesses with a lock. - */ -static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr) -{ - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr); - unsigned long old = *p; - - *p = old & ~mask; - return (old & mask) != 0; -} - -/* WARNING: non atomic and it can be reordered! */ -static inline int __test_and_change_bit(int nr, - volatile unsigned long *addr) -{ - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr); - unsigned long old = *p; - - *p = old ^ mask; - return (old & mask) != 0; -} - -/** - * test_bit - Determine whether a bit is set - * @nr: bit number to test - * @addr: Address to start counting from - */ -static inline int test_bit(int nr, const volatile unsigned long *addr) -{ - return 1UL & (addr[BITOP_WORD(nr)] >> (nr & (BITS_PER_LONG-1))); -} - -#endif /* _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ */ diff --git a/tools/testing/radix-tree/linux/export.h b/tools/testing/radix-tree/linux/export.h deleted file mode 100644 index b6afd131998d..000000000000 --- a/tools/testing/radix-tree/linux/export.h +++ /dev/null @@ -1,2 +0,0 @@ - -#define EXPORT_SYMBOL(sym) diff --git a/tools/testing/radix-tree/linux/gfp.h b/tools/testing/radix-tree/linux/gfp.h index 5b09b2ce6c33..39a0dcb9475a 100644 --- a/tools/testing/radix-tree/linux/gfp.h +++ b/tools/testing/radix-tree/linux/gfp.h @@ -1,6 +1,8 @@ #ifndef _GFP_H #define _GFP_H +#include <linux/types.h> + #define __GFP_BITS_SHIFT 26 #define __GFP_BITS_MASK ((gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) @@ -13,10 +15,12 @@ #define __GFP_DIRECT_RECLAIM 0x400000u #define __GFP_KSWAPD_RECLAIM 0x2000000u -#define __GFP_RECLAIM (__GFP_DIRECT_RECLAIM|__GFP_KSWAPD_RECLAIM) +#define __GFP_RECLAIM (__GFP_DIRECT_RECLAIM|__GFP_KSWAPD_RECLAIM) + +#define GFP_ATOMIC (__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM) +#define GFP_KERNEL (__GFP_RECLAIM | __GFP_IO | __GFP_FS) +#define GFP_NOWAIT (__GFP_KSWAPD_RECLAIM) -#define GFP_ATOMIC (__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM) -#define GFP_KERNEL (__GFP_RECLAIM | __GFP_IO | __GFP_FS) static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags) { diff --git a/tools/testing/radix-tree/linux/idr.h b/tools/testing/radix-tree/linux/idr.h new file mode 100644 index 000000000000..4e342f2e37cf --- /dev/null +++ b/tools/testing/radix-tree/linux/idr.h @@ -0,0 +1 @@ +#include "../../../../include/linux/idr.h" diff --git a/tools/testing/radix-tree/linux/init.h b/tools/testing/radix-tree/linux/init.h index 360cabb3c4e7..1bb0afc21309 100644 --- a/tools/testing/radix-tree/linux/init.h +++ b/tools/testing/radix-tree/linux/init.h @@ -1 +1 @@ -/* An empty file stub that allows radix-tree.c to compile. */ +#define __init diff --git a/tools/testing/radix-tree/linux/kernel.h b/tools/testing/radix-tree/linux/kernel.h index 9b43b4975d83..b21a77fddcf7 100644 --- a/tools/testing/radix-tree/linux/kernel.h +++ b/tools/testing/radix-tree/linux/kernel.h @@ -1,64 +1,21 @@ #ifndef _KERNEL_H #define _KERNEL_H -#include <assert.h> +#include "../../include/linux/kernel.h" #include <string.h> #include <stdio.h> -#include <stddef.h> #include <limits.h> -#include "../../include/linux/compiler.h" -#include "../../include/linux/err.h" +#include <linux/compiler.h> +#include <linux/err.h> +#include <linux/bitops.h> +#include <linux/log2.h> #include "../../../include/linux/kconfig.h" -#ifdef BENCHMARK -#define RADIX_TREE_MAP_SHIFT 6 -#else -#define RADIX_TREE_MAP_SHIFT 3 -#endif - -#ifndef NULL -#define NULL 0 -#endif - -#define BUG_ON(expr) assert(!(expr)) -#define WARN_ON(expr) assert(!(expr)) -#define __init -#define __must_check -#define panic(expr) #define printk printf -#define __force -#define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d)) #define pr_debug printk - -#define smp_rmb() barrier() -#define smp_wmb() barrier() -#define cpu_relax() barrier() +#define pr_cont printk #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0])) -#define container_of(ptr, type, member) ({ \ - const typeof( ((type *)0)->member ) *__mptr = (ptr); \ - (type *)( (char *)__mptr - offsetof(type, member) );}) -#define min(a, b) ((a) < (b) ? (a) : (b)) - -#define cond_resched() sched_yield() - -static inline int in_interrupt(void) -{ - return 0; -} - -/* - * This looks more complex than it should be. But we need to - * get the type for the ~ right in round_down (it needs to be - * as wide as the result!), and we want to evaluate the macro - * arguments just once each. - */ -#define __round_mask(x, y) ((__typeof__(x))((y)-1)) -#define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1) -#define round_down(x, y) ((x) & ~__round_mask(x, y)) - -#define xchg(ptr, x) uatomic_xchg(ptr, x) - #endif /* _KERNEL_H */ diff --git a/tools/testing/radix-tree/linux/mempool.h b/tools/testing/radix-tree/linux/mempool.h deleted file mode 100644 index 6a2dc55b41d6..000000000000 --- a/tools/testing/radix-tree/linux/mempool.h +++ /dev/null @@ -1,16 +0,0 @@ - -#include <linux/slab.h> - -typedef void *(mempool_alloc_t)(int gfp_mask, void *pool_data); -typedef void (mempool_free_t)(void *element, void *pool_data); - -typedef struct { - mempool_alloc_t *alloc; - mempool_free_t *free; - void *data; -} mempool_t; - -void *mempool_alloc(mempool_t *pool, int gfp_mask); -void mempool_free(void *element, mempool_t *pool); -mempool_t *mempool_create(int min_nr, mempool_alloc_t *alloc_fn, - mempool_free_t *free_fn, void *pool_data); diff --git a/tools/testing/radix-tree/linux/percpu.h b/tools/testing/radix-tree/linux/percpu.h index 5837f1d56f17..3ea01a1a88c2 100644 --- a/tools/testing/radix-tree/linux/percpu.h +++ b/tools/testing/radix-tree/linux/percpu.h @@ -1,7 +1,10 @@ - +#define DECLARE_PER_CPU(type, val) extern type val #define DEFINE_PER_CPU(type, val) type val #define __get_cpu_var(var) var #define this_cpu_ptr(var) var +#define this_cpu_read(var) var +#define this_cpu_xchg(var, val) uatomic_xchg(&var, val) +#define this_cpu_cmpxchg(var, old, new) uatomic_cmpxchg(&var, old, new) #define per_cpu_ptr(ptr, cpu) ({ (void)(cpu); (ptr); }) #define per_cpu(var, cpu) (*per_cpu_ptr(&(var), cpu)) diff --git a/tools/testing/radix-tree/linux/preempt.h b/tools/testing/radix-tree/linux/preempt.h index 65c04c226965..35c5ac81529f 100644 --- a/tools/testing/radix-tree/linux/preempt.h +++ b/tools/testing/radix-tree/linux/preempt.h @@ -1,4 +1,14 @@ +#ifndef __LINUX_PREEMPT_H +#define __LINUX_PREEMPT_H + extern int preempt_count; #define preempt_disable() uatomic_inc(&preempt_count) #define preempt_enable() uatomic_dec(&preempt_count) + +static inline int in_interrupt(void) +{ + return 0; +} + +#endif /* __LINUX_PREEMPT_H */ diff --git a/tools/testing/radix-tree/linux/radix-tree.h b/tools/testing/radix-tree/linux/radix-tree.h index ce694ddd4aea..bf1bb231f9b5 100644 --- a/tools/testing/radix-tree/linux/radix-tree.h +++ b/tools/testing/radix-tree/linux/radix-tree.h @@ -1 +1,26 @@ +#ifndef _TEST_RADIX_TREE_H +#define _TEST_RADIX_TREE_H + +#include "generated/map-shift.h" #include "../../../../include/linux/radix-tree.h" + +extern int kmalloc_verbose; +extern int test_verbose; + +static inline void trace_call_rcu(struct rcu_head *head, + void (*func)(struct rcu_head *head)) +{ + if (kmalloc_verbose) + printf("Delaying free of %p to slab\n", (char *)head - + offsetof(struct radix_tree_node, rcu_head)); + call_rcu(head, func); +} + +#define printv(verbosity_level, fmt, ...) \ + if(test_verbose >= verbosity_level) \ + printf(fmt, ##__VA_ARGS__) + +#undef call_rcu +#define call_rcu(x, y) trace_call_rcu(x, y) + +#endif /* _TEST_RADIX_TREE_H */ diff --git a/tools/testing/radix-tree/linux/types.h b/tools/testing/radix-tree/linux/types.h deleted file mode 100644 index 8491d89873bb..000000000000 --- a/tools/testing/radix-tree/linux/types.h +++ /dev/null @@ -1,23 +0,0 @@ -#ifndef _TYPES_H -#define _TYPES_H - -#include "../../include/linux/types.h" - -#define __rcu -#define __read_mostly - -static inline void INIT_LIST_HEAD(struct list_head *list) -{ - list->next = list; - list->prev = list; -} - -typedef struct { - unsigned int x; -} spinlock_t; - -#define uninitialized_var(x) x = x - -#include <linux/gfp.h> - -#endif diff --git a/tools/testing/radix-tree/main.c b/tools/testing/radix-tree/main.c index f7e9801a6754..b829127d5670 100644 --- a/tools/testing/radix-tree/main.c +++ b/tools/testing/radix-tree/main.c @@ -3,6 +3,7 @@ #include <unistd.h> #include <time.h> #include <assert.h> +#include <limits.h> #include <linux/slab.h> #include <linux/radix-tree.h> @@ -67,7 +68,7 @@ void big_gang_check(bool long_run) for (i = 0; i < (long_run ? 1000 : 3); i++) { __big_gang_check(); - printf("%d ", i); + printv(2, "%d ", i); fflush(stdout); } } @@ -128,14 +129,19 @@ void check_copied_tags(struct radix_tree_root *tree, unsigned long start, unsign putchar('.'); */ if (idx[i] < start || idx[i] > end) { if (item_tag_get(tree, idx[i], totag)) { - printf("%lu-%lu: %lu, tags %d-%d\n", start, end, idx[i], item_tag_get(tree, idx[i], fromtag), item_tag_get(tree, idx[i], totag)); + printv(2, "%lu-%lu: %lu, tags %d-%d\n", start, + end, idx[i], item_tag_get(tree, idx[i], + fromtag), + item_tag_get(tree, idx[i], totag)); } assert(!item_tag_get(tree, idx[i], totag)); continue; } if (item_tag_get(tree, idx[i], fromtag) ^ item_tag_get(tree, idx[i], totag)) { - printf("%lu-%lu: %lu, tags %d-%d\n", start, end, idx[i], item_tag_get(tree, idx[i], fromtag), item_tag_get(tree, idx[i], totag)); + printv(2, "%lu-%lu: %lu, tags %d-%d\n", start, end, + idx[i], item_tag_get(tree, idx[i], fromtag), + item_tag_get(tree, idx[i], totag)); } assert(!(item_tag_get(tree, idx[i], fromtag) ^ item_tag_get(tree, idx[i], totag))); @@ -237,7 +243,7 @@ static void __locate_check(struct radix_tree_root *tree, unsigned long index, item = item_lookup(tree, index); index2 = find_item(tree, item); if (index != index2) { - printf("index %ld order %d inserted; found %ld\n", + printv(2, "index %ld order %d inserted; found %ld\n", index, order, index2); abort(); } @@ -288,43 +294,48 @@ static void single_thread_tests(bool long_run) { int i; - printf("starting single_thread_tests: %d allocated, preempt %d\n", + printv(1, "starting single_thread_tests: %d allocated, preempt %d\n", nr_allocated, preempt_count); multiorder_checks(); rcu_barrier(); - printf("after multiorder_check: %d allocated, preempt %d\n", + printv(2, "after multiorder_check: %d allocated, preempt %d\n", nr_allocated, preempt_count); locate_check(); rcu_barrier(); - printf("after locate_check: %d allocated, preempt %d\n", + printv(2, "after locate_check: %d allocated, preempt %d\n", nr_allocated, preempt_count); tag_check(); rcu_barrier(); - printf("after tag_check: %d allocated, preempt %d\n", + printv(2, "after tag_check: %d allocated, preempt %d\n", nr_allocated, preempt_count); gang_check(); rcu_barrier(); - printf("after gang_check: %d allocated, preempt %d\n", + printv(2, "after gang_check: %d allocated, preempt %d\n", nr_allocated, preempt_count); add_and_check(); rcu_barrier(); - printf("after add_and_check: %d allocated, preempt %d\n", + printv(2, "after add_and_check: %d allocated, preempt %d\n", nr_allocated, preempt_count); dynamic_height_check(); rcu_barrier(); - printf("after dynamic_height_check: %d allocated, preempt %d\n", + printv(2, "after dynamic_height_check: %d allocated, preempt %d\n", + nr_allocated, preempt_count); + idr_checks(); + ida_checks(); + rcu_barrier(); + printv(2, "after idr_checks: %d allocated, preempt %d\n", nr_allocated, preempt_count); big_gang_check(long_run); rcu_barrier(); - printf("after big_gang_check: %d allocated, preempt %d\n", + printv(2, "after big_gang_check: %d allocated, preempt %d\n", nr_allocated, preempt_count); for (i = 0; i < (long_run ? 2000 : 3); i++) { copy_tag_check(); - printf("%d ", i); + printv(2, "%d ", i); fflush(stdout); } rcu_barrier(); - printf("after copy_tag_check: %d allocated, preempt %d\n", + printv(2, "after copy_tag_check: %d allocated, preempt %d\n", nr_allocated, preempt_count); } @@ -334,24 +345,28 @@ int main(int argc, char **argv) int opt; unsigned int seed = time(NULL); - while ((opt = getopt(argc, argv, "ls:")) != -1) { + while ((opt = getopt(argc, argv, "ls:v")) != -1) { if (opt == 'l') long_run = true; else if (opt == 's') seed = strtoul(optarg, NULL, 0); + else if (opt == 'v') + test_verbose++; } printf("random seed %u\n", seed); srand(seed); + printf("running tests\n"); + rcu_register_thread(); radix_tree_init(); regression1_test(); regression2_test(); regression3_test(); - iteration_test(0, 10); - iteration_test(7, 20); + iteration_test(0, 10 + 90 * long_run); + iteration_test(7, 10 + 90 * long_run); single_thread_tests(long_run); /* Free any remaining preallocated nodes */ @@ -360,9 +375,11 @@ int main(int argc, char **argv) benchmark(); rcu_barrier(); - printf("after rcu_barrier: %d allocated, preempt %d\n", + printv(2, "after rcu_barrier: %d allocated, preempt %d\n", nr_allocated, preempt_count); rcu_unregister_thread(); + printf("tests completed\n"); + exit(0); } diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c index f79812a5e070..06c71178d07d 100644 --- a/tools/testing/radix-tree/multiorder.c +++ b/tools/testing/radix-tree/multiorder.c @@ -30,7 +30,7 @@ static void __multiorder_tag_test(int index, int order) /* our canonical entry */ base = index & ~((1 << order) - 1); - printf("Multiorder tag test with index %d, canonical entry %d\n", + printv(2, "Multiorder tag test with index %d, canonical entry %d\n", index, base); err = item_insert_order(&tree, index, order); @@ -150,7 +150,7 @@ static void multiorder_check(unsigned long index, int order) struct item *item2 = item_create(min, order); RADIX_TREE(tree, GFP_KERNEL); - printf("Multiorder index %ld, order %d\n", index, order); + printv(2, "Multiorder index %ld, order %d\n", index, order); assert(item_insert_order(&tree, index, order) == 0); @@ -188,7 +188,7 @@ static void multiorder_shrink(unsigned long index, int order) RADIX_TREE(tree, GFP_KERNEL); struct radix_tree_node *node; - printf("Multiorder shrink index %ld, order %d\n", index, order); + printv(2, "Multiorder shrink index %ld, order %d\n", index, order); assert(item_insert_order(&tree, 0, order) == 0); @@ -209,7 +209,8 @@ static void multiorder_shrink(unsigned long index, int order) item_check_absent(&tree, i); if (!item_delete(&tree, 0)) { - printf("failed to delete index %ld (order %d)\n", index, order); abort(); + printv(2, "failed to delete index %ld (order %d)\n", index, order); + abort(); } for (i = 0; i < 2*max; i++) @@ -234,7 +235,7 @@ void multiorder_iteration(void) void **slot; int i, j, err; - printf("Multiorder iteration test\n"); + printv(1, "Multiorder iteration test\n"); #define NUM_ENTRIES 11 int index[NUM_ENTRIES] = {0, 2, 4, 8, 16, 32, 34, 36, 64, 72, 128}; @@ -275,7 +276,7 @@ void multiorder_tagged_iteration(void) void **slot; int i, j; - printf("Multiorder tagged iteration test\n"); + printv(1, "Multiorder tagged iteration test\n"); #define MT_NUM_ENTRIES 9 int index[MT_NUM_ENTRIES] = {0, 2, 4, 16, 32, 40, 64, 72, 128}; @@ -355,6 +356,10 @@ void multiorder_tagged_iteration(void) item_kill_tree(&tree); } +/* + * Basic join checks: make sure we can't find an entry in the tree after + * a larger entry has replaced it + */ static void multiorder_join1(unsigned long index, unsigned order1, unsigned order2) { @@ -373,6 +378,10 @@ static void multiorder_join1(unsigned long index, item_kill_tree(&tree); } +/* + * Check that the accounting of exceptional entries is handled correctly + * by joining an exceptional entry to a normal pointer. + */ static void multiorder_join2(unsigned order1, unsigned order2) { RADIX_TREE(tree, GFP_KERNEL); @@ -386,6 +395,9 @@ static void multiorder_join2(unsigned order1, unsigned order2) assert(item2 == (void *)0x12UL); assert(node->exceptional == 1); + item2 = radix_tree_lookup(&tree, 0); + free(item2); + radix_tree_join(&tree, 0, order1, item1); item2 = __radix_tree_lookup(&tree, 1 << order2, &node, NULL); assert(item2 == item1); @@ -453,7 +465,7 @@ static void check_mem(unsigned old_order, unsigned new_order, unsigned alloc) { struct radix_tree_preload *rtp = &radix_tree_preloads; if (rtp->nr != 0) - printf("split(%u %u) remaining %u\n", old_order, new_order, + printv(2, "split(%u %u) remaining %u\n", old_order, new_order, rtp->nr); /* * Can't check for equality here as some nodes may have been @@ -461,7 +473,7 @@ static void check_mem(unsigned old_order, unsigned new_order, unsigned alloc) * nodes allocated since they should have all been preloaded. */ if (nr_allocated > alloc) - printf("split(%u %u) allocated %u %u\n", old_order, new_order, + printv(2, "split(%u %u) allocated %u %u\n", old_order, new_order, alloc, nr_allocated); } @@ -471,6 +483,7 @@ static void __multiorder_split(int old_order, int new_order) void **slot; struct radix_tree_iter iter; unsigned alloc; + struct item *item; radix_tree_preload(GFP_KERNEL); assert(item_insert_order(&tree, 0, old_order) == 0); @@ -479,7 +492,7 @@ static void __multiorder_split(int old_order, int new_order) /* Wipe out the preloaded cache or it'll confuse check_mem() */ radix_tree_cpu_dead(0); - radix_tree_tag_set(&tree, 0, 2); + item = radix_tree_tag_set(&tree, 0, 2); radix_tree_split_preload(old_order, new_order, GFP_KERNEL); alloc = nr_allocated; @@ -492,6 +505,7 @@ static void __multiorder_split(int old_order, int new_order) radix_tree_preload_end(); item_kill_tree(&tree); + free(item); } static void __multiorder_split2(int old_order, int new_order) @@ -633,3 +647,10 @@ void multiorder_checks(void) radix_tree_cpu_dead(0); } + +int __weak main(void) +{ + radix_tree_init(); + multiorder_checks(); + return 0; +} diff --git a/tools/testing/radix-tree/regression1.c b/tools/testing/radix-tree/regression1.c index 0d6813a61b37..bf97742fc18c 100644 --- a/tools/testing/radix-tree/regression1.c +++ b/tools/testing/radix-tree/regression1.c @@ -193,7 +193,7 @@ void regression1_test(void) long arg; /* Regression #1 */ - printf("running regression test 1, should finish in under a minute\n"); + printv(1, "running regression test 1, should finish in under a minute\n"); nr_threads = 2; pthread_barrier_init(&worker_barrier, NULL, nr_threads); @@ -216,5 +216,5 @@ void regression1_test(void) free(threads); - printf("regression test 1, done\n"); + printv(1, "regression test 1, done\n"); } diff --git a/tools/testing/radix-tree/regression2.c b/tools/testing/radix-tree/regression2.c index a41325d7a170..42dd2a33ed24 100644 --- a/tools/testing/radix-tree/regression2.c +++ b/tools/testing/radix-tree/regression2.c @@ -80,7 +80,7 @@ void regression2_test(void) unsigned long int start, end; struct page *pages[1]; - printf("running regression test 2 (should take milliseconds)\n"); + printv(1, "running regression test 2 (should take milliseconds)\n"); /* 0. */ for (i = 0; i <= max_slots - 1; i++) { p = page_alloc(); @@ -103,7 +103,7 @@ void regression2_test(void) /* 4. */ for (i = max_slots - 1; i >= 0; i--) - radix_tree_delete(&mt_tree, i); + free(radix_tree_delete(&mt_tree, i)); /* 5. */ // NOTE: start should not be 0 because radix_tree_gang_lookup_tag_slot @@ -114,7 +114,9 @@ void regression2_test(void) PAGECACHE_TAG_TOWRITE); /* We remove all the remained nodes */ - radix_tree_delete(&mt_tree, max_slots); + free(radix_tree_delete(&mt_tree, max_slots)); - printf("regression test 2, done\n"); + BUG_ON(!radix_tree_empty(&mt_tree)); + + printv(1, "regression test 2, done\n"); } diff --git a/tools/testing/radix-tree/regression3.c b/tools/testing/radix-tree/regression3.c index b594841fae85..670c3d2ae7b1 100644 --- a/tools/testing/radix-tree/regression3.c +++ b/tools/testing/radix-tree/regression3.c @@ -34,21 +34,21 @@ void regression3_test(void) void **slot; bool first; - printf("running regression test 3 (should take milliseconds)\n"); + printv(1, "running regression test 3 (should take milliseconds)\n"); radix_tree_insert(&root, 0, ptr0); radix_tree_tag_set(&root, 0, 0); first = true; radix_tree_for_each_tagged(slot, &root, &iter, 0, 0) { - printf("tagged %ld %p\n", iter.index, *slot); + printv(2, "tagged %ld %p\n", iter.index, *slot); if (first) { radix_tree_insert(&root, 1, ptr); radix_tree_tag_set(&root, 1, 0); first = false; } if (radix_tree_deref_retry(*slot)) { - printf("retry at %ld\n", iter.index); + printv(2, "retry at %ld\n", iter.index); slot = radix_tree_iter_retry(&iter); continue; } @@ -57,13 +57,13 @@ void regression3_test(void) first = true; radix_tree_for_each_slot(slot, &root, &iter, 0) { - printf("slot %ld %p\n", iter.index, *slot); + printv(2, "slot %ld %p\n", iter.index, *slot); if (first) { radix_tree_insert(&root, 1, ptr); first = false; } if (radix_tree_deref_retry(*slot)) { - printk("retry at %ld\n", iter.index); + printv(2, "retry at %ld\n", iter.index); slot = radix_tree_iter_retry(&iter); continue; } @@ -72,30 +72,30 @@ void regression3_test(void) first = true; radix_tree_for_each_contig(slot, &root, &iter, 0) { - printk("contig %ld %p\n", iter.index, *slot); + printv(2, "contig %ld %p\n", iter.index, *slot); if (first) { radix_tree_insert(&root, 1, ptr); first = false; } if (radix_tree_deref_retry(*slot)) { - printk("retry at %ld\n", iter.index); + printv(2, "retry at %ld\n", iter.index); slot = radix_tree_iter_retry(&iter); continue; } } radix_tree_for_each_slot(slot, &root, &iter, 0) { - printf("slot %ld %p\n", iter.index, *slot); + printv(2, "slot %ld %p\n", iter.index, *slot); if (!iter.index) { - printf("next at %ld\n", iter.index); + printv(2, "next at %ld\n", iter.index); slot = radix_tree_iter_resume(slot, &iter); } } radix_tree_for_each_contig(slot, &root, &iter, 0) { - printf("contig %ld %p\n", iter.index, *slot); + printv(2, "contig %ld %p\n", iter.index, *slot); if (!iter.index) { - printf("next at %ld\n", iter.index); + printv(2, "next at %ld\n", iter.index); slot = radix_tree_iter_resume(slot, &iter); } } @@ -103,9 +103,9 @@ void regression3_test(void) radix_tree_tag_set(&root, 0, 0); radix_tree_tag_set(&root, 1, 0); radix_tree_for_each_tagged(slot, &root, &iter, 0, 0) { - printf("tagged %ld %p\n", iter.index, *slot); + printv(2, "tagged %ld %p\n", iter.index, *slot); if (!iter.index) { - printf("next at %ld\n", iter.index); + printv(2, "next at %ld\n", iter.index); slot = radix_tree_iter_resume(slot, &iter); } } @@ -113,5 +113,5 @@ void regression3_test(void) radix_tree_delete(&root, 0); radix_tree_delete(&root, 1); - printf("regression test 3 passed\n"); + printv(1, "regression test 3 passed\n"); } diff --git a/tools/testing/radix-tree/tag_check.c b/tools/testing/radix-tree/tag_check.c index fd98c132207a..d4ff00989245 100644 --- a/tools/testing/radix-tree/tag_check.c +++ b/tools/testing/radix-tree/tag_check.c @@ -49,10 +49,10 @@ void simple_checks(void) } verify_tag_consistency(&tree, 0); verify_tag_consistency(&tree, 1); - printf("before item_kill_tree: %d allocated\n", nr_allocated); + printv(2, "before item_kill_tree: %d allocated\n", nr_allocated); item_kill_tree(&tree); rcu_barrier(); - printf("after item_kill_tree: %d allocated\n", nr_allocated); + printv(2, "after item_kill_tree: %d allocated\n", nr_allocated); } /* @@ -257,7 +257,7 @@ static void do_thrash(struct radix_tree_root *tree, char *thrash_state, int tag) gang_check(tree, thrash_state, tag); - printf("%d(%d) %d(%d) %d(%d) %d(%d) / " + printv(2, "%d(%d) %d(%d) %d(%d) %d(%d) / " "%d(%d) present, %d(%d) tagged\n", insert_chunk, nr_inserted, delete_chunk, nr_deleted, @@ -296,13 +296,13 @@ static void __leak_check(void) { RADIX_TREE(tree, GFP_KERNEL); - printf("%d: nr_allocated=%d\n", __LINE__, nr_allocated); + printv(2, "%d: nr_allocated=%d\n", __LINE__, nr_allocated); item_insert(&tree, 1000000); - printf("%d: nr_allocated=%d\n", __LINE__, nr_allocated); + printv(2, "%d: nr_allocated=%d\n", __LINE__, nr_allocated); item_delete(&tree, 1000000); - printf("%d: nr_allocated=%d\n", __LINE__, nr_allocated); + printv(2, "%d: nr_allocated=%d\n", __LINE__, nr_allocated); item_kill_tree(&tree); - printf("%d: nr_allocated=%d\n", __LINE__, nr_allocated); + printv(2, "%d: nr_allocated=%d\n", __LINE__, nr_allocated); } static void single_check(void) @@ -336,15 +336,15 @@ void tag_check(void) extend_checks(); contract_checks(); rcu_barrier(); - printf("after extend_checks: %d allocated\n", nr_allocated); + printv(2, "after extend_checks: %d allocated\n", nr_allocated); __leak_check(); leak_check(); rcu_barrier(); - printf("after leak_check: %d allocated\n", nr_allocated); + printv(2, "after leak_check: %d allocated\n", nr_allocated); simple_checks(); rcu_barrier(); - printf("after simple_checks: %d allocated\n", nr_allocated); + printv(2, "after simple_checks: %d allocated\n", nr_allocated); thrash_tags(); rcu_barrier(); - printf("after thrash_tags: %d allocated\n", nr_allocated); + printv(2, "after thrash_tags: %d allocated\n", nr_allocated); } diff --git a/tools/testing/radix-tree/test.c b/tools/testing/radix-tree/test.c index e5726e373646..1a257d738a1e 100644 --- a/tools/testing/radix-tree/test.c +++ b/tools/testing/radix-tree/test.c @@ -29,15 +29,28 @@ int __item_insert(struct radix_tree_root *root, struct item *item) return __radix_tree_insert(root, item->index, item->order, item); } -int item_insert(struct radix_tree_root *root, unsigned long index) +struct item *item_create(unsigned long index, unsigned int order) { - return __item_insert(root, item_create(index, 0)); + struct item *ret = malloc(sizeof(*ret)); + + ret->index = index; + ret->order = order; + return ret; } int item_insert_order(struct radix_tree_root *root, unsigned long index, unsigned order) { - return __item_insert(root, item_create(index, order)); + struct item *item = item_create(index, order); + int err = __item_insert(root, item); + if (err) + free(item); + return err; +} + +int item_insert(struct radix_tree_root *root, unsigned long index) +{ + return item_insert_order(root, index, 0); } void item_sanity(struct item *item, unsigned long index) @@ -61,15 +74,6 @@ int item_delete(struct radix_tree_root *root, unsigned long index) return 0; } -struct item *item_create(unsigned long index, unsigned int order) -{ - struct item *ret = malloc(sizeof(*ret)); - - ret->index = index; - ret->order = order; - return ret; -} - void item_check_present(struct radix_tree_root *root, unsigned long index) { struct item *item; diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h index 056a23b56467..b30e11d9d271 100644 --- a/tools/testing/radix-tree/test.h +++ b/tools/testing/radix-tree/test.h @@ -34,6 +34,8 @@ void tag_check(void); void multiorder_checks(void); void iteration_test(unsigned order, unsigned duration); void benchmark(void); +void idr_checks(void); +void ida_checks(void); struct item * item_tag_set(struct radix_tree_root *root, unsigned long index, int tag); |