From 446411e18b2cb17d153e45f634a3c9a79ada3ac2 Mon Sep 17 00:00:00 2001 From: Andreas Larsson Date: Wed, 13 Feb 2013 14:20:25 +0100 Subject: spi: Initialize cs_gpio and cs_gpios with -ENOENT The return value from of_get_named_gpio is -ENOENT when the given index matches a hole in the "cs-gpios" property phandle list. However, the default value of cs_gpio in struct spi_device and entries of cs_gpios in struct spi_master is -EINVAL, which is documented to indicate that a GPIO line should not be used for the given spi_device. This sets the default value of cs_gpio in struct spi_device and entries of cs_gpios in struct spi_master to -ENOENT. Thus, -ENOENT is the only value used to indicate that no GPIO line should be used. Signed-off-by: Andreas Larsson Signed-off-by: Grant Likely --- include/linux/spi/spi.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 38c2b925923d..c395f32b53b3 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -57,7 +57,7 @@ extern struct bus_type spi_bus_type; * @modalias: Name of the driver to use with this device, or an alias * for that name. This appears in the sysfs "modalias" attribute * for driver coldplugging, and in uevents used for hotplugging - * @cs_gpio: gpio number of the chipselect line (optional, -EINVAL when + * @cs_gpio: gpio number of the chipselect line (optional, -ENOENT when * when not using a GPIO line) * * A @spi_device is used to interchange data between an SPI slave @@ -261,7 +261,7 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * queue so the subsystem notifies the driver that it may relax the * hardware by issuing this call * @cs_gpios: Array of GPIOs to use as chip select lines; one per CS - * number. Any individual value may be -EINVAL for CS lines that + * number. Any individual value may be -ENOENT for CS lines that * are not GPIOs (driven by the SPI controller itself). * * Each SPI master controller can communicate with one or more @spi_device -- cgit v1.2.3 From d450f445f9a654080a6be4094376c2192d9a1f36 Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Tue, 19 Feb 2013 02:58:25 +0300 Subject: : fix compilation warnings with DT disabled MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix the following compilation warnings (in Simon Horman's renesas.git repo): In file included from arch/arm/mach-shmobile/setup-r8a7779.c:24:0: include/linux/of_platform.h:107:13: warning: ‘struct of_device_id’ declared inside parameter list [enabled by default] include/linux/of_platform.h:107:13: warning: its scope is only this definition or declaration, which is probably not what you want [enabled by default] include/linux/of_platform.h:107:13: warning: ‘struct device_node’ declared inside parameter list [enabled by default] only #include's headers with definitions of the above mentioned structures if CONFIG_OF_DEVICE=y but uses them even if not. One solution is to move some #include's out of #ifdef CONFIG_OF_DEVICE and use incomplete declarations for the rest of the structures where the #ifdef move doesn't help... Reported-by: Vladimir Barinov Signed-off-by: Sergei Shtylyov Signed-off-by: Rob Herring --- include/linux/of_platform.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h index 3863a4dbdf18..2a93b64a3869 100644 --- a/include/linux/of_platform.h +++ b/include/linux/of_platform.h @@ -11,9 +11,10 @@ * */ -#ifdef CONFIG_OF_DEVICE #include #include + +#ifdef CONFIG_OF_DEVICE #include #include #include @@ -100,7 +101,7 @@ extern int of_platform_populate(struct device_node *root, #if !defined(CONFIG_OF_ADDRESS) struct of_dev_auxdata; -struct device; +struct device_node; static inline int of_platform_populate(struct device_node *root, const struct of_device_id *matches, const struct of_dev_auxdata *lookup, -- cgit v1.2.3 From 7677fc965fba41d1386fa3b76a1f00303f02bb2d Mon Sep 17 00:00:00 2001 From: Rony Efraim Date: Wed, 8 May 2013 22:22:35 +0000 Subject: net/mlx4: Strengthen VLAN tags/priorities enforcement in VST mode Make sure that the following steps are taken: - drop packets sent by the VF with vlan tag - block packets with vlan tag which are steered to the VF - drop/block tagged packets when the policy is priority-tagged - make sure VLAN stripping for received packets is set - make sure force UP bit for the VF QP is set Use enum values for all the above instead of numerical bit offsets. Signed-off-by: Rony Efraim Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_resources.c | 2 +- .../net/ethernet/mellanox/mlx4/resource_tracker.c | 20 ++++++++++++--- include/linux/mlx4/qp.h | 29 ++++++++++++++++++++-- 3 files changed, 45 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx4/en_resources.c b/drivers/net/ethernet/mellanox/mlx4/en_resources.c index 91f2b2c43c12..d3f508697a3d 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_resources.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_resources.c @@ -60,7 +60,7 @@ void mlx4_en_fill_qp_context(struct mlx4_en_priv *priv, int size, int stride, context->pri_path.sched_queue = 0x83 | (priv->port - 1) << 6; if (user_prio >= 0) { context->pri_path.sched_queue |= user_prio << 3; - context->pri_path.feup = 1 << 6; + context->pri_path.feup = MLX4_FEUP_FORCE_ETH_UP; } context->pri_path.counter_index = 0xff; context->cqn_send = cpu_to_be32(cqn); diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index d4a9de666fbd..1157f028a90f 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -372,14 +372,28 @@ static int update_vport_qp_param(struct mlx4_dev *dev, if (MLX4_QP_ST_RC == qp_type) return -EINVAL; + /* force strip vlan by clear vsd */ + qpc->param3 &= ~cpu_to_be32(MLX4_STRIP_VLAN); + if (0 != vp_oper->state.default_vlan) { + qpc->pri_path.vlan_control = + MLX4_VLAN_CTRL_ETH_TX_BLOCK_TAGGED | + MLX4_VLAN_CTRL_ETH_RX_BLOCK_PRIO_TAGGED | + MLX4_VLAN_CTRL_ETH_RX_BLOCK_UNTAGGED; + } else { /* priority tagged */ + qpc->pri_path.vlan_control = + MLX4_VLAN_CTRL_ETH_TX_BLOCK_TAGGED | + MLX4_VLAN_CTRL_ETH_RX_BLOCK_TAGGED; + } + + qpc->pri_path.fvl_rx |= MLX4_FVL_RX_FORCE_ETH_VLAN; qpc->pri_path.vlan_index = vp_oper->vlan_idx; - qpc->pri_path.fl = (1 << 6) | (1 << 2); /* set cv bit and hide_cqe_vlan bit*/ - qpc->pri_path.feup |= 1 << 3; /* set fvl bit */ + qpc->pri_path.fl |= MLX4_FL_CV | MLX4_FL_ETH_HIDE_CQE_VLAN; + qpc->pri_path.feup |= MLX4_FEUP_FORCE_ETH_UP | MLX4_FVL_FORCE_ETH_VLAN; qpc->pri_path.sched_queue &= 0xC7; qpc->pri_path.sched_queue |= (vp_oper->state.default_qos) << 3; } if (vp_oper->state.spoofchk) { - qpc->pri_path.feup |= 1 << 5; /* set fsm bit */; + qpc->pri_path.feup |= MLX4_FSM_FORCE_ETH_SRC_MAC; qpc->pri_path.grh_mylmc = (0x80 & qpc->pri_path.grh_mylmc) + vp_oper->mac_idx; } return 0; diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h index 67f46ad6920a..352eec9df1b8 100644 --- a/include/linux/mlx4/qp.h +++ b/include/linux/mlx4/qp.h @@ -126,7 +126,7 @@ struct mlx4_rss_context { struct mlx4_qp_path { u8 fl; - u8 reserved1[1]; + u8 vlan_control; u8 disable_pkey_check; u8 pkey_index; u8 counter_index; @@ -141,11 +141,32 @@ struct mlx4_qp_path { u8 sched_queue; u8 vlan_index; u8 feup; - u8 reserved3; + u8 fvl_rx; u8 reserved4[2]; u8 dmac[6]; }; +enum { /* fl */ + MLX4_FL_CV = 1 << 6, + MLX4_FL_ETH_HIDE_CQE_VLAN = 1 << 2 +}; +enum { /* vlan_control */ + MLX4_VLAN_CTRL_ETH_TX_BLOCK_TAGGED = 1 << 6, + MLX4_VLAN_CTRL_ETH_RX_BLOCK_TAGGED = 1 << 2, + MLX4_VLAN_CTRL_ETH_RX_BLOCK_PRIO_TAGGED = 1 << 1, /* 802.1p priority tag */ + MLX4_VLAN_CTRL_ETH_RX_BLOCK_UNTAGGED = 1 << 0 +}; + +enum { /* feup */ + MLX4_FEUP_FORCE_ETH_UP = 1 << 6, /* force Eth UP */ + MLX4_FSM_FORCE_ETH_SRC_MAC = 1 << 5, /* force Source MAC */ + MLX4_FVL_FORCE_ETH_VLAN = 1 << 3 /* force Eth vlan */ +}; + +enum { /* fvl_rx */ + MLX4_FVL_RX_FORCE_ETH_VLAN = 1 << 0 /* enforce Eth rx vlan */ +}; + struct mlx4_qp_context { __be32 flags; __be32 pd; @@ -185,6 +206,10 @@ struct mlx4_qp_context { u32 reserved5[10]; }; +enum { /* param3 */ + MLX4_STRIP_VLAN = 1 << 30 +}; + /* Which firmware version adds support for NEC (NoErrorCompletion) bit */ #define MLX4_FW_VER_WQE_CTRL_NEC mlx4_fw_ver(2, 2, 232) -- cgit v1.2.3 From e2555fde4159467fb579e6ae3c0a8fc33015d0f5 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 13 May 2013 09:45:01 -0400 Subject: jbd,jbd2: fix oops in jbd2_journal_put_journal_head() Commit ae4647fb (jbd2: reduce journal_head size) introduced a regression where we occasionally hit panic in jbd2_journal_put_journal_head() because of wrong b_jcount. The bug is caused by gcc making 64-bit access to 32-bit bitfield and thus clobbering b_jcount. At least for now, those 8 bytes saved in struct journal_head are not worth the trouble with gcc bitfield handling so revert that part of the patch. Reported-by: EUNBONG SONG Reported-by: Tony Luck Signed-off-by: Jan Kara Signed-off-by: "Theodore Ts'o" --- include/linux/journal-head.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/journal-head.h b/include/linux/journal-head.h index 13a3da25ff07..98cd41bb39c8 100644 --- a/include/linux/journal-head.h +++ b/include/linux/journal-head.h @@ -30,15 +30,19 @@ struct journal_head { /* * Journalling list for this buffer [jbd_lock_bh_state()] + * NOTE: We *cannot* combine this with b_modified into a bitfield + * as gcc would then (which the C standard allows but which is + * very unuseful) make 64-bit accesses to the bitfield and clobber + * b_jcount if its update races with bitfield modification. */ - unsigned b_jlist:4; + unsigned b_jlist; /* * This flag signals the buffer has been modified by * the currently running transaction * [jbd_lock_bh_state()] */ - unsigned b_modified:1; + unsigned b_modified; /* * Copy of the buffer data frozen for writing to the log. -- cgit v1.2.3 From ee8209fd026b074bb8eb75bece516a338a281b1b Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 8 May 2013 11:55:48 +0300 Subject: dma: acpi-dma: parse CSRT to extract additional resources Since we have CSRT only to get additional DMA controller resources, let's get rid of drivers/acpi/csrt.c and move its logic inside ACPI DMA helpers code. Signed-off-by: Andy Shevchenko Signed-off-by: Mika Westerberg Acked-by: Rafael J. Wysocki Signed-off-by: Vinod Koul --- drivers/acpi/Makefile | 1 - drivers/acpi/csrt.c | 159 ------------------------------------------- drivers/acpi/internal.h | 1 - drivers/acpi/scan.c | 1 - drivers/dma/acpi-dma.c | 172 ++++++++++++++++++++++++++++++++++++++++++++++- include/linux/acpi_dma.h | 4 ++ 6 files changed, 173 insertions(+), 165 deletions(-) delete mode 100644 drivers/acpi/csrt.c (limited to 'include/linux') diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile index ecb743bf05a5..6050c8028dce 100644 --- a/drivers/acpi/Makefile +++ b/drivers/acpi/Makefile @@ -38,7 +38,6 @@ acpi-y += processor_core.o acpi-y += ec.o acpi-$(CONFIG_ACPI_DOCK) += dock.o acpi-y += pci_root.o pci_link.o pci_irq.o -acpi-y += csrt.o acpi-$(CONFIG_X86_INTEL_LPSS) += acpi_lpss.o acpi-y += acpi_platform.o acpi-y += power.o diff --git a/drivers/acpi/csrt.c b/drivers/acpi/csrt.c deleted file mode 100644 index 5c15a91faf0b..000000000000 --- a/drivers/acpi/csrt.c +++ /dev/null @@ -1,159 +0,0 @@ -/* - * Support for Core System Resources Table (CSRT) - * - * Copyright (C) 2013, Intel Corporation - * Authors: Mika Westerberg - * Andy Shevchenko - * - * 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 - * published by the Free Software Foundation. - */ - -#define pr_fmt(fmt) "ACPI: CSRT: " fmt - -#include -#include -#include -#include -#include -#include - -ACPI_MODULE_NAME("CSRT"); - -static int __init acpi_csrt_parse_shared_info(struct platform_device *pdev, - const struct acpi_csrt_group *grp) -{ - const struct acpi_csrt_shared_info *si; - struct resource res[3]; - size_t nres; - int ret; - - memset(res, 0, sizeof(res)); - nres = 0; - - si = (const struct acpi_csrt_shared_info *)&grp[1]; - /* - * The peripherals that are listed on CSRT typically support only - * 32-bit addresses so we only use the low part of MMIO base for - * now. - */ - if (!si->mmio_base_high && si->mmio_base_low) { - /* - * There is no size of the memory resource in shared_info - * so we assume that it is 4k here. - */ - res[nres].start = si->mmio_base_low; - res[nres].end = res[0].start + SZ_4K - 1; - res[nres++].flags = IORESOURCE_MEM; - } - - if (si->gsi_interrupt) { - int irq = acpi_register_gsi(NULL, si->gsi_interrupt, - si->interrupt_mode, - si->interrupt_polarity); - res[nres].start = irq; - res[nres].end = irq; - res[nres++].flags = IORESOURCE_IRQ; - } - - if (si->base_request_line || si->num_handshake_signals) { - /* - * We pass the driver a DMA resource describing the range - * of request lines the device supports. - */ - res[nres].start = si->base_request_line; - res[nres].end = res[nres].start + si->num_handshake_signals - 1; - res[nres++].flags = IORESOURCE_DMA; - } - - ret = platform_device_add_resources(pdev, res, nres); - if (ret) { - if (si->gsi_interrupt) - acpi_unregister_gsi(si->gsi_interrupt); - return ret; - } - - return 0; -} - -static int __init -acpi_csrt_parse_resource_group(const struct acpi_csrt_group *grp) -{ - struct platform_device *pdev; - char vendor[5], name[16]; - int ret, i; - - vendor[0] = grp->vendor_id; - vendor[1] = grp->vendor_id >> 8; - vendor[2] = grp->vendor_id >> 16; - vendor[3] = grp->vendor_id >> 24; - vendor[4] = '\0'; - - if (grp->shared_info_length != sizeof(struct acpi_csrt_shared_info)) - return -ENODEV; - - snprintf(name, sizeof(name), "%s%04X", vendor, grp->device_id); - pdev = platform_device_alloc(name, PLATFORM_DEVID_AUTO); - if (!pdev) - return -ENOMEM; - - /* Add resources based on the shared info */ - ret = acpi_csrt_parse_shared_info(pdev, grp); - if (ret) - goto fail; - - ret = platform_device_add(pdev); - if (ret) - goto fail; - - for (i = 0; i < pdev->num_resources; i++) - dev_dbg(&pdev->dev, "%pR\n", &pdev->resource[i]); - - return 0; - -fail: - platform_device_put(pdev); - return ret; -} - -/* - * CSRT or Core System Resources Table is a proprietary ACPI table - * introduced by Microsoft. This table can contain devices that are not in - * the system DSDT table. In particular DMA controllers might be described - * here. - * - * We present these devices as normal platform devices that don't have ACPI - * IDs or handle. The platform device name will be something like - * ..auto for example: INTL9C06.0.auto. - */ -void __init acpi_csrt_init(void) -{ - struct acpi_csrt_group *grp, *end; - struct acpi_table_csrt *csrt; - acpi_status status; - int ret; - - status = acpi_get_table(ACPI_SIG_CSRT, 0, - (struct acpi_table_header **)&csrt); - if (ACPI_FAILURE(status)) { - if (status != AE_NOT_FOUND) - pr_warn("failed to get the CSRT table\n"); - return; - } - - pr_debug("parsing CSRT table for devices\n"); - - grp = (struct acpi_csrt_group *)(csrt + 1); - end = (struct acpi_csrt_group *)((void *)csrt + csrt->header.length); - - while (grp < end) { - ret = acpi_csrt_parse_resource_group(grp); - if (ret) { - pr_warn("error in parsing resource group: %d\n", ret); - return; - } - - grp = (struct acpi_csrt_group *)((void *)grp + grp->length); - } -} diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h index 6f1afd9118c8..297cbf456f86 100644 --- a/drivers/acpi/internal.h +++ b/drivers/acpi/internal.h @@ -35,7 +35,6 @@ void acpi_pci_link_init(void); void acpi_pci_root_hp_init(void); void acpi_platform_init(void); int acpi_sysfs_init(void); -void acpi_csrt_init(void); #ifdef CONFIG_ACPI_CONTAINER void acpi_container_init(void); #else diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index fe158fd4f1df..aacc08f951aa 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -2042,7 +2042,6 @@ int __init acpi_scan_init(void) acpi_pci_link_init(); acpi_platform_init(); acpi_lpss_init(); - acpi_csrt_init(); acpi_container_init(); acpi_memory_hotplug_init(); diff --git a/drivers/dma/acpi-dma.c b/drivers/dma/acpi-dma.c index ba6fc62e9651..5a18f82f732a 100644 --- a/drivers/dma/acpi-dma.c +++ b/drivers/dma/acpi-dma.c @@ -4,7 +4,8 @@ * Based on of-dma.c * * Copyright (C) 2013, Intel Corporation - * Author: Andy Shevchenko + * Authors: Andy Shevchenko + * Mika Westerberg * * 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 @@ -16,12 +17,124 @@ #include #include #include +#include #include #include static LIST_HEAD(acpi_dma_list); static DEFINE_MUTEX(acpi_dma_lock); +/** + * acpi_dma_parse_resource_group - match device and parse resource group + * @grp: CSRT resource group + * @adev: ACPI device to match with + * @adma: struct acpi_dma of the given DMA controller + * + * Returns 1 on success, 0 when no information is available, or appropriate + * errno value on error. + * + * In order to match a device from DSDT table to the corresponding CSRT device + * we use MMIO address and IRQ. + */ +static int acpi_dma_parse_resource_group(const struct acpi_csrt_group *grp, + struct acpi_device *adev, struct acpi_dma *adma) +{ + const struct acpi_csrt_shared_info *si; + struct list_head resource_list; + struct resource_list_entry *rentry; + resource_size_t mem = 0, irq = 0; + u32 vendor_id; + int ret; + + if (grp->shared_info_length != sizeof(struct acpi_csrt_shared_info)) + return -ENODEV; + + INIT_LIST_HEAD(&resource_list); + ret = acpi_dev_get_resources(adev, &resource_list, NULL, NULL); + if (ret <= 0) + return 0; + + list_for_each_entry(rentry, &resource_list, node) { + if (resource_type(&rentry->res) == IORESOURCE_MEM) + mem = rentry->res.start; + else if (resource_type(&rentry->res) == IORESOURCE_IRQ) + irq = rentry->res.start; + } + + acpi_dev_free_resource_list(&resource_list); + + /* Consider initial zero values as resource not found */ + if (mem == 0 && irq == 0) + return 0; + + si = (const struct acpi_csrt_shared_info *)&grp[1]; + + /* Match device by MMIO and IRQ */ + if (si->mmio_base_low != mem || si->gsi_interrupt != irq) + return 0; + + vendor_id = le32_to_cpu(grp->vendor_id); + dev_dbg(&adev->dev, "matches with %.4s%04X (rev %u)\n", + (char *)&vendor_id, grp->device_id, grp->revision); + + /* Check if the request line range is available */ + if (si->base_request_line == 0 && si->num_handshake_signals == 0) + return 0; + + adma->base_request_line = si->base_request_line; + adma->end_request_line = si->base_request_line + + si->num_handshake_signals - 1; + + dev_dbg(&adev->dev, "request line base: 0x%04x end: 0x%04x\n", + adma->base_request_line, adma->end_request_line); + + return 1; +} + +/** + * acpi_dma_parse_csrt - parse CSRT to exctract additional DMA resources + * @adev: ACPI device to match with + * @adma: struct acpi_dma of the given DMA controller + * + * CSRT or Core System Resources Table is a proprietary ACPI table + * introduced by Microsoft. This table can contain devices that are not in + * the system DSDT table. In particular DMA controllers might be described + * here. + * + * We are using this table to get the request line range of the specific DMA + * controller to be used later. + * + */ +static void acpi_dma_parse_csrt(struct acpi_device *adev, struct acpi_dma *adma) +{ + struct acpi_csrt_group *grp, *end; + struct acpi_table_csrt *csrt; + acpi_status status; + int ret; + + status = acpi_get_table(ACPI_SIG_CSRT, 0, + (struct acpi_table_header **)&csrt); + if (ACPI_FAILURE(status)) { + if (status != AE_NOT_FOUND) + dev_warn(&adev->dev, "failed to get the CSRT table\n"); + return; + } + + grp = (struct acpi_csrt_group *)(csrt + 1); + end = (struct acpi_csrt_group *)((void *)csrt + csrt->header.length); + + while (grp < end) { + ret = acpi_dma_parse_resource_group(grp, adev, adma); + if (ret < 0) { + dev_warn(&adev->dev, + "error in parsing resource group\n"); + return; + } + + grp = (struct acpi_csrt_group *)((void *)grp + grp->length); + } +} + /** * acpi_dma_controller_register - Register a DMA controller to ACPI DMA helpers * @dev: struct device of DMA controller @@ -61,6 +174,8 @@ int acpi_dma_controller_register(struct device *dev, adma->acpi_dma_xlate = acpi_dma_xlate; adma->data = data; + acpi_dma_parse_csrt(adev, adma); + /* Now queue acpi_dma controller structure in list */ mutex_lock(&acpi_dma_lock); list_add_tail(&adma->dma_controllers, &acpi_dma_list); @@ -149,6 +264,45 @@ void devm_acpi_dma_controller_free(struct device *dev) } EXPORT_SYMBOL_GPL(devm_acpi_dma_controller_free); +/** + * acpi_dma_update_dma_spec - prepare dma specifier to pass to translation function + * @adma: struct acpi_dma of DMA controller + * @dma_spec: dma specifier to update + * + * Returns 0, if no information is avaiable, -1 on mismatch, and 1 otherwise. + * + * Accordingly to ACPI 5.0 Specification Table 6-170 "Fixed DMA Resource + * Descriptor": + * DMA Request Line bits is a platform-relative number uniquely + * identifying the request line assigned. Request line-to-Controller + * mapping is done in a controller-specific OS driver. + * That's why we can safely adjust slave_id when the appropriate controller is + * found. + */ +static int acpi_dma_update_dma_spec(struct acpi_dma *adma, + struct acpi_dma_spec *dma_spec) +{ + /* Set link to the DMA controller device */ + dma_spec->dev = adma->dev; + + /* Check if the request line range is available */ + if (adma->base_request_line == 0 && adma->end_request_line == 0) + return 0; + + /* Check if slave_id falls to the range */ + if (dma_spec->slave_id < adma->base_request_line || + dma_spec->slave_id > adma->end_request_line) + return -1; + + /* + * Here we adjust slave_id. It should be a relative number to the base + * request line. + */ + dma_spec->slave_id -= adma->base_request_line; + + return 1; +} + struct acpi_dma_parser_data { struct acpi_dma_spec dma_spec; size_t index; @@ -193,6 +347,7 @@ struct dma_chan *acpi_dma_request_slave_chan_by_index(struct device *dev, struct acpi_device *adev; struct acpi_dma *adma; struct dma_chan *chan = NULL; + int found; /* Check if the device was enumerated by ACPI */ if (!dev || !ACPI_HANDLE(dev)) @@ -219,9 +374,20 @@ struct dma_chan *acpi_dma_request_slave_chan_by_index(struct device *dev, mutex_lock(&acpi_dma_lock); list_for_each_entry(adma, &acpi_dma_list, dma_controllers) { - dma_spec->dev = adma->dev; + /* + * We are not going to call translation function if slave_id + * doesn't fall to the request range. + */ + found = acpi_dma_update_dma_spec(adma, dma_spec); + if (found < 0) + continue; chan = adma->acpi_dma_xlate(dma_spec, adma); - if (chan) + /* + * Try to get a channel only from the DMA controller that + * matches the slave_id. See acpi_dma_update_dma_spec() + * description for the details. + */ + if (found > 0 || chan) break; } diff --git a/include/linux/acpi_dma.h b/include/linux/acpi_dma.h index d09deabc7bf6..fb0298082916 100644 --- a/include/linux/acpi_dma.h +++ b/include/linux/acpi_dma.h @@ -37,6 +37,8 @@ struct acpi_dma_spec { * @dev: struct device of this controller * @acpi_dma_xlate: callback function to find a suitable channel * @data: private data used by a callback function + * @base_request_line: first supported request line (CSRT) + * @end_request_line: last supported request line (CSRT) */ struct acpi_dma { struct list_head dma_controllers; @@ -44,6 +46,8 @@ struct acpi_dma { struct dma_chan *(*acpi_dma_xlate) (struct acpi_dma_spec *, struct acpi_dma *); void *data; + unsigned short base_request_line; + unsigned short end_request_line; }; /* Used with acpi_dma_simple_xlate() */ -- cgit v1.2.3 From b59cc200ac025aca597fb21862c1c9e667f2eff2 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 8 May 2013 11:55:49 +0300 Subject: ACPI / LPSS: register clock device for Lynxpoint DMA properly The DMA controller in Lynxpoint is enumerated as a regular ACPI device now. To work properly it is using the LPSS root clock as a functional clock. That's why we have to register the clock device accordingly to the ACPI ID of the DMA controller. The acpi_lpss.c module is responsible to do the job. This patch also removes hardcoded name of the DMA device in clk-lpt.c and the name of the root clock in acpi_lpss.c. Signed-off-by: Rafael J. Wysocki Signed-off-by: Andy Shevchenko Signed-off-by: Vinod Koul --- drivers/acpi/acpi_lpss.c | 26 ++++++++++++++++++++++---- drivers/clk/x86/clk-lpt.c | 15 +++++++++++---- include/linux/platform_data/clk-lpss.h | 5 +++++ 3 files changed, 38 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c index b1c95422ce74..652fd5ce303c 100644 --- a/drivers/acpi/acpi_lpss.c +++ b/drivers/acpi/acpi_lpss.c @@ -35,11 +35,16 @@ ACPI_MODULE_NAME("acpi_lpss"); struct lpss_device_desc { bool clk_required; - const char *clk_parent; + const char *clkdev_name; bool ltr_required; unsigned int prv_offset; }; +static struct lpss_device_desc lpss_dma_desc = { + .clk_required = true, + .clkdev_name = "hclk", +}; + struct lpss_private_data { void __iomem *mmio_base; resource_size_t mmio_size; @@ -49,7 +54,6 @@ struct lpss_private_data { static struct lpss_device_desc lpt_dev_desc = { .clk_required = true, - .clk_parent = "lpss_clk", .prv_offset = 0x800, .ltr_required = true, }; @@ -60,6 +64,9 @@ static struct lpss_device_desc lpt_sdio_dev_desc = { }; static const struct acpi_device_id acpi_lpss_device_ids[] = { + /* Generic LPSS devices */ + { "INTL9C60", (unsigned long)&lpss_dma_desc }, + /* Lynxpoint LPSS devices */ { "INT33C0", (unsigned long)&lpt_dev_desc }, { "INT33C1", (unsigned long)&lpt_dev_desc }, @@ -91,16 +98,27 @@ static int register_device_clock(struct acpi_device *adev, struct lpss_private_data *pdata) { const struct lpss_device_desc *dev_desc = pdata->dev_desc; + struct lpss_clk_data *clk_data; if (!lpss_clk_dev) lpt_register_clock_device(); - if (!dev_desc->clk_parent || !pdata->mmio_base + clk_data = platform_get_drvdata(lpss_clk_dev); + if (!clk_data) + return -ENODEV; + + if (dev_desc->clkdev_name) { + clk_register_clkdev(clk_data->clk, dev_desc->clkdev_name, + dev_name(&adev->dev)); + return 0; + } + + if (!pdata->mmio_base || pdata->mmio_size < dev_desc->prv_offset + LPSS_CLK_SIZE) return -ENODATA; pdata->clk = clk_register_gate(NULL, dev_name(&adev->dev), - dev_desc->clk_parent, 0, + clk_data->name, 0, pdata->mmio_base + dev_desc->prv_offset, 0, 0, NULL); if (IS_ERR(pdata->clk)) diff --git a/drivers/clk/x86/clk-lpt.c b/drivers/clk/x86/clk-lpt.c index 5cf4f4686406..4f45eee9e33b 100644 --- a/drivers/clk/x86/clk-lpt.c +++ b/drivers/clk/x86/clk-lpt.c @@ -15,22 +15,29 @@ #include #include #include +#include #include #define PRV_CLOCK_PARAMS 0x800 static int lpt_clk_probe(struct platform_device *pdev) { + struct lpss_clk_data *drvdata; struct clk *clk; + drvdata = devm_kzalloc(&pdev->dev, sizeof(*drvdata), GFP_KERNEL); + if (!drvdata) + return -ENOMEM; + /* LPSS free running clock */ - clk = clk_register_fixed_rate(&pdev->dev, "lpss_clk", NULL, CLK_IS_ROOT, - 100000000); + drvdata->name = "lpss_clk"; + clk = clk_register_fixed_rate(&pdev->dev, drvdata->name, NULL, + CLK_IS_ROOT, 100000000); if (IS_ERR(clk)) return PTR_ERR(clk); - /* Shared DMA clock */ - clk_register_clkdev(clk, "hclk", "INTL9C60.0.auto"); + drvdata->clk = clk; + platform_set_drvdata(pdev, drvdata); return 0; } diff --git a/include/linux/platform_data/clk-lpss.h b/include/linux/platform_data/clk-lpss.h index 528e73ce46d2..23901992b9dd 100644 --- a/include/linux/platform_data/clk-lpss.h +++ b/include/linux/platform_data/clk-lpss.h @@ -13,6 +13,11 @@ #ifndef __CLK_LPSS_H #define __CLK_LPSS_H +struct lpss_clk_data { + const char *name; + struct clk *clk; +}; + extern int lpt_clk_init(void); #endif /* __CLK_LPSS_H */ -- cgit v1.2.3 From 63ad9cbff5896dadfee510f631ffcb0176984722 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Tue, 23 Apr 2013 15:28:38 +0200 Subject: pinctrl: generic: Fix typos and clarify comments Drive strength controls both sink and source currents, clarify the description accordingly. Signed-off-by: Laurent Pinchart Signed-off-by: Linus Walleij --- include/linux/pinctrl/pinconf-generic.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pinctrl/pinconf-generic.h b/include/linux/pinctrl/pinconf-generic.h index 72474e18f1e0..6aa238096622 100644 --- a/include/linux/pinctrl/pinconf-generic.h +++ b/include/linux/pinctrl/pinconf-generic.h @@ -37,17 +37,17 @@ * if it is 0, pull-down is disabled. * @PIN_CONFIG_DRIVE_PUSH_PULL: the pin will be driven actively high and * low, this is the most typical case and is typically achieved with two - * active transistors on the output. Sending this config will enabale + * active transistors on the output. Setting this config will enable * push-pull mode, the argument is ignored. * @PIN_CONFIG_DRIVE_OPEN_DRAIN: the pin will be driven with open drain (open * collector) which means it is usually wired with other output ports - * which are then pulled up with an external resistor. Sending this - * config will enabale open drain mode, the argument is ignored. + * which are then pulled up with an external resistor. Setting this + * config will enable open drain mode, the argument is ignored. * @PIN_CONFIG_DRIVE_OPEN_SOURCE: the pin will be driven with open source - * (open emitter). Sending this config will enabale open drain mode, the + * (open emitter). Setting this config will enable open drain mode, the * argument is ignored. - * @PIN_CONFIG_DRIVE_STRENGTH: the pin will output the current passed as - * argument. The argument is in mA. + * @PIN_CONFIG_DRIVE_STRENGTH: the pin will sink or source at most the current + * passed as argument. The argument is in mA. * @PIN_CONFIG_INPUT_SCHMITT_ENABLE: control schmitt-trigger mode on the pin. * If the argument != 0, schmitt-trigger mode is enabled. If it's 0, * schmitt-trigger mode is disabled. -- cgit v1.2.3 From b4f711ee03d28f776fd2324fd0bd999cc428e4d2 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Wed, 24 Apr 2013 11:32:56 -0700 Subject: time: Revert ALWAYS_USE_PERSISTENT_CLOCK compile time optimizaitons Kay Sievers noted that the ALWAYS_USE_PERSISTENT_CLOCK config, which enables some minor compile time optimization to avoid uncessary code in mostly the suspend/resume path could cause problems for userland. In particular, the dependency for RTC_HCTOSYS on !ALWAYS_USE_PERSISTENT_CLOCK, which avoids setting the time twice and simplifies suspend/resume, has the side effect of causing the /sys/class/rtc/rtcN/hctosys flag to always be zero, and this flag is commonly used by udev to setup the /dev/rtc symlink to /dev/rtcN, which can cause pain for older applications. While the udev rules could use some work to be less fragile, breaking userland should strongly be avoided. Additionally the compile time optimizations are fairly minor, and the code being optimized is likely to be reworked in the future, so lets revert this change. Reported-by: Kay Sievers Signed-off-by: John Stultz Cc: stable #3.9 Cc: Feng Tang Cc: Jason Gunthorpe Link: http://lkml.kernel.org/r/1366828376-18124-1-git-send-email-john.stultz@linaro.org Signed-off-by: Thomas Gleixner --- arch/x86/Kconfig | 1 - drivers/rtc/Kconfig | 2 -- include/linux/time.h | 4 ---- kernel/time/Kconfig | 5 ----- 4 files changed, 12 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 5db2117ae288..45c41249321f 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -108,7 +108,6 @@ config X86 select GENERIC_CLOCKEVENTS_BROADCAST if X86_64 || (X86_32 && X86_LOCAL_APIC) select GENERIC_TIME_VSYSCALL if X86_64 select KTIME_SCALAR if X86_32 - select ALWAYS_USE_PERSISTENT_CLOCK select GENERIC_STRNCPY_FROM_USER select GENERIC_STRNLEN_USER select HAVE_CONTEXT_TRACKING if X86_64 diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig index 0c81915b1997..b9838130a7b0 100644 --- a/drivers/rtc/Kconfig +++ b/drivers/rtc/Kconfig @@ -20,7 +20,6 @@ if RTC_CLASS config RTC_HCTOSYS bool "Set system time from RTC on startup and resume" default y - depends on !ALWAYS_USE_PERSISTENT_CLOCK help If you say yes here, the system time (wall clock) will be set using the value read from a specified RTC device. This is useful to avoid @@ -29,7 +28,6 @@ config RTC_HCTOSYS config RTC_SYSTOHC bool "Set the RTC time based on NTP synchronization" default y - depends on !ALWAYS_USE_PERSISTENT_CLOCK help If you say yes here, the system time (wall clock) will be stored in the RTC specified by RTC_HCTOSYS_DEVICE approximately every 11 diff --git a/include/linux/time.h b/include/linux/time.h index 22d81b3c955b..d5d229b2e5af 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -117,14 +117,10 @@ static inline bool timespec_valid_strict(const struct timespec *ts) extern bool persistent_clock_exist; -#ifdef ALWAYS_USE_PERSISTENT_CLOCK -#define has_persistent_clock() true -#else static inline bool has_persistent_clock(void) { return persistent_clock_exist; } -#endif extern void read_persistent_clock(struct timespec *ts); extern void read_boot_clock(struct timespec *ts); diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig index 24510d84efd7..b69692250af4 100644 --- a/kernel/time/Kconfig +++ b/kernel/time/Kconfig @@ -12,11 +12,6 @@ config CLOCKSOURCE_WATCHDOG config ARCH_CLOCKSOURCE_DATA bool -# Platforms has a persistent clock -config ALWAYS_USE_PERSISTENT_CLOCK - bool - default n - # Timekeeping vsyscall support config GENERIC_TIME_VSYSCALL bool -- cgit v1.2.3 From ccf5ae83a6cf3d9cfe9a7038bfe7cd38ab03d5e1 Mon Sep 17 00:00:00 2001 From: Joern Engel Date: Mon, 13 May 2013 16:30:06 -0400 Subject: target: close target_put_sess_cmd() vs. core_tmr_abort_task() race It is possible for one thread to to take se_sess->sess_cmd_lock in core_tmr_abort_task() before taking a reference count on se_cmd->cmd_kref, while another thread in target_put_sess_cmd() drops se_cmd->cmd_kref before taking se_sess->sess_cmd_lock. This introduces kref_put_spinlock_irqsave() and uses it in target_put_sess_cmd() to close the race window. Signed-off-by: Joern Engel Acked-by: Greg Kroah-Hartman Cc: Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_transport.c | 11 +++++------ include/linux/kref.h | 33 +++++++++++++++++++++++++++++++++ 2 files changed, 38 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index c3477fa60942..4a793362309d 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -2211,21 +2211,19 @@ static void target_release_cmd_kref(struct kref *kref) { struct se_cmd *se_cmd = container_of(kref, struct se_cmd, cmd_kref); struct se_session *se_sess = se_cmd->se_sess; - unsigned long flags; - spin_lock_irqsave(&se_sess->sess_cmd_lock, flags); if (list_empty(&se_cmd->se_cmd_list)) { - spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags); + spin_unlock(&se_sess->sess_cmd_lock); se_cmd->se_tfo->release_cmd(se_cmd); return; } if (se_sess->sess_tearing_down && se_cmd->cmd_wait_set) { - spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags); + spin_unlock(&se_sess->sess_cmd_lock); complete(&se_cmd->cmd_wait_comp); return; } list_del(&se_cmd->se_cmd_list); - spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags); + spin_unlock(&se_sess->sess_cmd_lock); se_cmd->se_tfo->release_cmd(se_cmd); } @@ -2236,7 +2234,8 @@ static void target_release_cmd_kref(struct kref *kref) */ int target_put_sess_cmd(struct se_session *se_sess, struct se_cmd *se_cmd) { - return kref_put(&se_cmd->cmd_kref, target_release_cmd_kref); + return kref_put_spinlock_irqsave(&se_cmd->cmd_kref, target_release_cmd_kref, + &se_sess->sess_cmd_lock); } EXPORT_SYMBOL(target_put_sess_cmd); diff --git a/include/linux/kref.h b/include/linux/kref.h index 4972e6e9ca93..7419c02085d7 100644 --- a/include/linux/kref.h +++ b/include/linux/kref.h @@ -19,6 +19,7 @@ #include #include #include +#include struct kref { atomic_t refcount; @@ -95,6 +96,38 @@ static inline int kref_put(struct kref *kref, void (*release)(struct kref *kref) return kref_sub(kref, 1, release); } +/** + * kref_put_spinlock_irqsave - decrement refcount for object. + * @kref: object. + * @release: pointer to the function that will clean up the object when the + * last reference to the object is released. + * This pointer is required, and it is not acceptable to pass kfree + * in as this function. + * @lock: lock to take in release case + * + * Behaves identical to kref_put with one exception. If the reference count + * drops to zero, the lock will be taken atomically wrt dropping the reference + * count. The release function has to call spin_unlock() without _irqrestore. + */ +static inline int kref_put_spinlock_irqsave(struct kref *kref, + void (*release)(struct kref *kref), + spinlock_t *lock) +{ + unsigned long flags; + + WARN_ON(release == NULL); + if (atomic_add_unless(&kref->refcount, -1, 1)) + return 0; + spin_lock_irqsave(lock, flags); + if (atomic_dec_and_test(&kref->refcount)) { + release(kref); + local_irq_restore(flags); + return 1; + } + spin_unlock_irqrestore(lock, flags); + return 0; +} + static inline int kref_put_mutex(struct kref *kref, void (*release)(struct kref *kref), struct mutex *lock) -- cgit v1.2.3 From de97f250394996f5acb07ba9e6dbdfc15ee4316c Mon Sep 17 00:00:00 2001 From: "Robert P. J. Day" Date: Thu, 2 May 2013 09:51:44 -0400 Subject: Correct typo "supperspeed" to "superspeed". Tidy up kernel-doc content for USB GADGET. No functional change. Signed-off-by: Robert P. J. Day Signed-off-by: Felipe Balbi --- include/linux/usb/gadget.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index c454a88abf2e..f1b0dca60f12 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -563,9 +563,8 @@ static inline int gadget_is_dualspeed(struct usb_gadget *g) } /** - * gadget_is_superspeed() - return true if the hardware handles - * supperspeed - * @g: controller that might support supper speed + * gadget_is_superspeed() - return true if the hardware handles superspeed + * @g: controller that might support superspeed */ static inline int gadget_is_superspeed(struct usb_gadget *g) { -- cgit v1.2.3 From 755ccb9d577b95b43537cfeb36da59140412f858 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Wed, 15 May 2013 08:00:25 +0000 Subject: broadcom: add include guards to include/linux/brcmphy.h include/linux/brcmphy.h is currently not protected against double inclusion, add ifdefs guard to fix that. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index b840a4960282..677b4f01b2d0 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -1,3 +1,6 @@ +#ifndef _LINUX_BRCMPHY_H +#define _LINUX_BRCMPHY_H + #define PHY_ID_BCM50610 0x0143bd60 #define PHY_ID_BCM50610M 0x0143bd70 #define PHY_ID_BCM5241 0x0143bc30 @@ -29,3 +32,5 @@ #define PHY_BRCM_CLEAR_RGMII_MODE 0x00004000 #define PHY_BRCM_DIS_TXCRXC_NOENRGY 0x00008000 #define PHY_BCM_FLAGS_VALID 0x80000000 + +#endif /* _LINUX_BRCMPHY_H */ -- cgit v1.2.3 From fc1f7d5606487ae28d6c84e95401952927d7379e Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 25 Apr 2013 20:31:43 +0000 Subject: clocksource: apb_timer: Remove unsused function Signed-off-by: Thomas Gleixner Acked-by: John Stultz Cc: Magnus Damm Acked-by: Jamie Iles Link: http://lkml.kernel.org/r/20130425143435.558006195@linutronix.de Signed-off-by: Thomas Gleixner --- drivers/clocksource/dw_apb_timer.c | 12 ------------ include/linux/dw_apb_timer.h | 1 - 2 files changed, 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/clocksource/dw_apb_timer.c b/drivers/clocksource/dw_apb_timer.c index 8c2a35f26d9b..e54ca1062d8e 100644 --- a/drivers/clocksource/dw_apb_timer.c +++ b/drivers/clocksource/dw_apb_timer.c @@ -387,15 +387,3 @@ cycle_t dw_apb_clocksource_read(struct dw_apb_clocksource *dw_cs) { return (cycle_t)~apbt_readl(&dw_cs->timer, APBTMR_N_CURRENT_VALUE); } - -/** - * dw_apb_clocksource_unregister() - unregister and free a clocksource. - * - * @dw_cs: The clocksource to unregister/free. - */ -void dw_apb_clocksource_unregister(struct dw_apb_clocksource *dw_cs) -{ - clocksource_unregister(&dw_cs->cs); - - kfree(dw_cs); -} diff --git a/include/linux/dw_apb_timer.h b/include/linux/dw_apb_timer.h index dd755ce2a5eb..b1cd9597c241 100644 --- a/include/linux/dw_apb_timer.h +++ b/include/linux/dw_apb_timer.h @@ -51,7 +51,6 @@ dw_apb_clocksource_init(unsigned rating, const char *name, void __iomem *base, void dw_apb_clocksource_register(struct dw_apb_clocksource *dw_cs); void dw_apb_clocksource_start(struct dw_apb_clocksource *dw_cs); cycle_t dw_apb_clocksource_read(struct dw_apb_clocksource *dw_cs); -void dw_apb_clocksource_unregister(struct dw_apb_clocksource *dw_cs); extern void dw_apb_timer_init(void); #endif /* __DW_APB_TIMER_H__ */ -- cgit v1.2.3 From ba919d1caa2e624eb8c6cae1f2ce0a253e697d45 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 25 Apr 2013 20:31:44 +0000 Subject: clocksource: Let timekeeping_notify return success/error timekeeping_notify() can fail due cs->enable() failure. Though the caller does not notice and happily keeps the wrong clocksource as the current one. Let the caller know about failure, so the current clocksource will be shown correctly in sysfs. Signed-off-by: Thomas Gleixner Acked-by: John Stultz Cc: Magnus Damm Link: http://lkml.kernel.org/r/20130425143435.696321912@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/clocksource.h | 2 +- kernel/time/clocksource.c | 6 +++--- kernel/time/timekeeping.c | 5 +++-- 3 files changed, 7 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 7279b94c01da..aa6ba44e75d5 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -321,7 +321,7 @@ static inline void __clocksource_updatefreq_khz(struct clocksource *cs, u32 khz) } -extern void timekeeping_notify(struct clocksource *clock); +extern int timekeeping_notify(struct clocksource *clock); extern cycle_t clocksource_mmio_readl_up(struct clocksource *); extern cycle_t clocksource_mmio_readl_down(struct clocksource *); diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index dda5c7130d93..1923a340bd91 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -611,10 +611,10 @@ static void clocksource_select(void) best = cs; break; } - if (curr_clocksource != best) { - printk(KERN_INFO "Switching to clocksource %s\n", best->name); + + if (curr_clocksource != best && !timekeeping_notify(best)) { + pr_info("Switched to clocksource %s\n", best->name); curr_clocksource = best; - timekeeping_notify(curr_clocksource); } } diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 98cd470bbe49..da6e10c7a378 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -648,14 +648,15 @@ static int change_clocksource(void *data) * This function is called from clocksource.c after a new, better clock * source has been registered. The caller holds the clocksource_mutex. */ -void timekeeping_notify(struct clocksource *clock) +int timekeeping_notify(struct clocksource *clock) { struct timekeeper *tk = &timekeeper; if (tk->clock == clock) - return; + return 0; stop_machine(change_clocksource, clock, NULL); tick_clock_notify(); + return tk->clock == clock ? 0 : -1; } /** -- cgit v1.2.3 From 09ac369c825d9d593404306d59062d854b321e9b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 25 Apr 2013 20:31:44 +0000 Subject: clocksource: Add module refcount Add a module refcount, so the current clocksource cannot be removed unconditionally. Signed-off-by: Thomas Gleixner Cc: John Stultz Cc: Magnus Damm Link: http://lkml.kernel.org/r/20130425143435.762417789@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/clocksource.h | 3 +++ kernel/time/timekeeping.c | 19 ++++++++++++++----- 2 files changed, 17 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index aa6ba44e75d5..32a895b114d8 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -21,6 +21,7 @@ /* clocksource cycle base type */ typedef u64 cycle_t; struct clocksource; +struct module; #ifdef CONFIG_ARCH_CLOCKSOURCE_DATA #include @@ -162,6 +163,7 @@ extern u64 timecounter_cyc2time(struct timecounter *tc, * @suspend: suspend function for the clocksource, if necessary * @resume: resume function for the clocksource, if necessary * @cycle_last: most recent cycle counter value seen by ::read() + * @owner: module reference, must be set by clocksource in modules */ struct clocksource { /* @@ -195,6 +197,7 @@ struct clocksource { cycle_t cs_last; cycle_t wd_last; #endif + struct module *owner; } ____cacheline_aligned; /* diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index da6e10c7a378..933efa4071c3 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -627,11 +627,20 @@ static int change_clocksource(void *data) write_seqcount_begin(&timekeeper_seq); timekeeping_forward_now(tk); - if (!new->enable || new->enable(new) == 0) { - old = tk->clock; - tk_setup_internals(tk, new); - if (old->disable) - old->disable(old); + /* + * If the cs is in module, get a module reference. Succeeds + * for built-in code (owner == NULL) as well. + */ + if (try_module_get(new->owner)) { + if (!new->enable || new->enable(new) == 0) { + old = tk->clock; + tk_setup_internals(tk, new); + if (old->disable) + old->disable(old); + module_put(old->owner); + } else { + module_put(new->owner); + } } timekeeping_update(tk, true, true); -- cgit v1.2.3 From a89c7edbe7d7aa80f507915f3dd801211b116b79 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 25 Apr 2013 20:31:46 +0000 Subject: clocksource: Let clocksource_unregister() return success/error The unregister call can fail, if the clocksource is the current one and there is no replacement clocksource available. It can also fail, if the clocksource is the watchdog clocksource and I'm not going to provide support for this. Signed-off-by: Thomas Gleixner Cc: John Stultz Cc: Magnus Damm Link: http://lkml.kernel.org/r/20130425143436.029915527@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/clocksource.h | 2 +- kernel/time/clocksource.c | 33 ++++++++++++--------------------- 2 files changed, 13 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 32a895b114d8..2f39a4911668 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -282,7 +282,7 @@ static inline s64 clocksource_cyc2ns(cycle_t cycles, u32 mult, u32 shift) extern int clocksource_register(struct clocksource*); -extern void clocksource_unregister(struct clocksource*); +extern int clocksource_unregister(struct clocksource*); extern void clocksource_touch_watchdog(void); extern struct clocksource* clocksource_get_next(void); extern void clocksource_change_rating(struct clocksource *cs, int rating); diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 791d1aeb17ac..31b90332f47b 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -389,28 +389,17 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs) static void clocksource_dequeue_watchdog(struct clocksource *cs) { - struct clocksource *tmp; unsigned long flags; spin_lock_irqsave(&watchdog_lock, flags); - if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) { - /* cs is a watched clocksource. */ - list_del_init(&cs->wd_list); - } else if (cs == watchdog) { - /* Reset watchdog cycles */ - clocksource_reset_watchdog(); - /* Current watchdog is removed. Find an alternative. */ - watchdog = NULL; - list_for_each_entry(tmp, &clocksource_list, list) { - if (tmp == cs || tmp->flags & CLOCK_SOURCE_MUST_VERIFY) - continue; - if (!watchdog || tmp->rating > watchdog->rating) - watchdog = tmp; + if (cs != watchdog) { + if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) { + /* cs is a watched clocksource. */ + list_del_init(&cs->wd_list); + /* Check if the watchdog timer needs to be stopped. */ + clocksource_stop_watchdog(); } } - cs->flags &= ~CLOCK_SOURCE_WATCHDOG; - /* Check if the watchdog timer needs to be stopped. */ - clocksource_stop_watchdog(); spin_unlock_irqrestore(&watchdog_lock, flags); } @@ -841,13 +830,15 @@ static int clocksource_unbind(struct clocksource *cs) * clocksource_unregister - remove a registered clocksource * @cs: clocksource to be unregistered */ -void clocksource_unregister(struct clocksource *cs) +int clocksource_unregister(struct clocksource *cs) { + int ret = 0; + mutex_lock(&clocksource_mutex); - clocksource_dequeue_watchdog(cs); - list_del(&cs->list); - clocksource_select(); + if (!list_empty(&cs->list)) + ret = clocksource_unbind(cs); mutex_unlock(&clocksource_mutex); + return ret; } EXPORT_SYMBOL(clocksource_unregister); -- cgit v1.2.3 From 7172a286ced0c1f4f239a0fa09db54ed37d3ead2 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 25 Apr 2013 20:31:47 +0000 Subject: clockevents: Get rid of the notifier chain 7+ years and still a single user. Kill it. Signed-off-by: Thomas Gleixner Cc: John Stultz Cc: Magnus Damm Link: http://lkml.kernel.org/r/20130425143436.098520211@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/clockchips.h | 1 - kernel/time/clockevents.c | 35 +++-------------------------------- kernel/time/tick-broadcast.c | 5 ++--- kernel/time/tick-common.c | 30 +++++------------------------- kernel/time/tick-internal.h | 7 ++++--- 5 files changed, 14 insertions(+), 64 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index 963d71431388..2f498f66c1bb 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -150,7 +150,6 @@ extern void clockevents_exchange_device(struct clock_event_device *old, struct clock_event_device *new); extern void clockevents_set_mode(struct clock_event_device *dev, enum clock_event_mode mode); -extern int clockevents_register_notifier(struct notifier_block *nb); extern int clockevents_program_event(struct clock_event_device *dev, ktime_t expires, bool force); diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index c6d6400ee137..dd70b4842c62 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -15,7 +15,6 @@ #include #include #include -#include #include #include "tick-internal.h" @@ -23,10 +22,6 @@ /* The registered clock event devices */ static LIST_HEAD(clockevent_devices); static LIST_HEAD(clockevents_released); - -/* Notification for clock events */ -static RAW_NOTIFIER_HEAD(clockevents_chain); - /* Protection for the above */ static DEFINE_RAW_SPINLOCK(clockevents_lock); @@ -232,30 +227,6 @@ int clockevents_program_event(struct clock_event_device *dev, ktime_t expires, return (rc && force) ? clockevents_program_min_delta(dev) : rc; } -/** - * clockevents_register_notifier - register a clock events change listener - */ -int clockevents_register_notifier(struct notifier_block *nb) -{ - unsigned long flags; - int ret; - - raw_spin_lock_irqsave(&clockevents_lock, flags); - ret = raw_notifier_chain_register(&clockevents_chain, nb); - raw_spin_unlock_irqrestore(&clockevents_lock, flags); - - return ret; -} - -/* - * Notify about a clock event change. Called with clockevents_lock - * held. - */ -static void clockevents_do_notify(unsigned long reason, void *dev) -{ - raw_notifier_call_chain(&clockevents_chain, reason, dev); -} - /* * Called after a notify add to make devices available which were * released from the notifier call. @@ -269,7 +240,7 @@ static void clockevents_notify_released(void) struct clock_event_device, list); list_del(&dev->list); list_add(&dev->list, &clockevent_devices); - clockevents_do_notify(CLOCK_EVT_NOTIFY_ADD, dev); + tick_check_new_device(dev); } } @@ -290,7 +261,7 @@ void clockevents_register_device(struct clock_event_device *dev) raw_spin_lock_irqsave(&clockevents_lock, flags); list_add(&dev->list, &clockevent_devices); - clockevents_do_notify(CLOCK_EVT_NOTIFY_ADD, dev); + tick_check_new_device(dev); clockevents_notify_released(); raw_spin_unlock_irqrestore(&clockevents_lock, flags); @@ -433,7 +404,7 @@ void clockevents_notify(unsigned long reason, void *arg) int cpu; raw_spin_lock_irqsave(&clockevents_lock, flags); - clockevents_do_notify(reason, arg); + tick_notify(reason, arg); switch (reason) { case CLOCK_EVT_NOTIFY_CPU_DEAD: diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index 24938d577669..3500caaa0bfd 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -64,7 +64,7 @@ static void tick_broadcast_start_periodic(struct clock_event_device *bc) /* * Check, if the device can be utilized as broadcast device: */ -int tick_check_broadcast_device(struct clock_event_device *dev) +void tick_install_broadcast_device(struct clock_event_device *dev) { struct clock_event_device *cur = tick_broadcast_device.evtdev; @@ -72,7 +72,7 @@ int tick_check_broadcast_device(struct clock_event_device *dev) (tick_broadcast_device.evtdev && tick_broadcast_device.evtdev->rating >= dev->rating) || (dev->features & CLOCK_EVT_FEAT_C3STOP)) - return 0; + return; clockevents_exchange_device(tick_broadcast_device.evtdev, dev); if (cur) @@ -90,7 +90,6 @@ int tick_check_broadcast_device(struct clock_event_device *dev) */ if (dev->features & CLOCK_EVT_FEAT_ONESHOT) tick_clock_notify(); - return 1; } /* diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 5d3fb100bc06..dbf4e18d5101 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -208,11 +208,11 @@ static void tick_setup_device(struct tick_device *td, /* * Check, if the new registered device should be used. */ -static int tick_check_new_device(struct clock_event_device *newdev) +void tick_check_new_device(struct clock_event_device *newdev) { struct clock_event_device *curdev; struct tick_device *td; - int cpu, ret = NOTIFY_OK; + int cpu; unsigned long flags; raw_spin_lock_irqsave(&tick_device_lock, flags); @@ -275,18 +275,14 @@ static int tick_check_new_device(struct clock_event_device *newdev) tick_oneshot_notify(); raw_spin_unlock_irqrestore(&tick_device_lock, flags); - return NOTIFY_STOP; + return; out_bc: /* * Can the new device be used as a broadcast device ? */ - if (tick_check_broadcast_device(newdev)) - ret = NOTIFY_STOP; - + tick_install_broadcast_device(newdev); raw_spin_unlock_irqrestore(&tick_device_lock, flags); - - return ret; } /* @@ -360,17 +356,10 @@ static void tick_resume(void) raw_spin_unlock_irqrestore(&tick_device_lock, flags); } -/* - * Notification about clock event devices - */ -static int tick_notify(struct notifier_block *nb, unsigned long reason, - void *dev) +void tick_notify(unsigned long reason, void *dev) { switch (reason) { - case CLOCK_EVT_NOTIFY_ADD: - return tick_check_new_device(dev); - case CLOCK_EVT_NOTIFY_BROADCAST_ON: case CLOCK_EVT_NOTIFY_BROADCAST_OFF: case CLOCK_EVT_NOTIFY_BROADCAST_FORCE: @@ -404,21 +393,12 @@ static int tick_notify(struct notifier_block *nb, unsigned long reason, default: break; } - - return NOTIFY_OK; } -static struct notifier_block tick_notifier = { - .notifier_call = tick_notify, -}; - /** * tick_init - initialize the tick control - * - * Register the notifier with the clockevents framework */ void __init tick_init(void) { - clockevents_register_notifier(&tick_notifier); tick_broadcast_init(); } diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index f0299eae4602..60742fe6f63d 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -18,6 +18,8 @@ extern int tick_do_timer_cpu __read_mostly; extern void tick_setup_periodic(struct clock_event_device *dev, int broadcast); extern void tick_handle_periodic(struct clock_event_device *dev); +extern void tick_notify(unsigned long reason, void *dev); +extern void tick_check_new_device(struct clock_event_device *dev); extern void clockevents_shutdown(struct clock_event_device *dev); @@ -90,7 +92,7 @@ static inline bool tick_broadcast_oneshot_available(void) { return false; } */ #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST extern int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu); -extern int tick_check_broadcast_device(struct clock_event_device *dev); +extern void tick_install_broadcast_device(struct clock_event_device *dev); extern int tick_is_broadcast_device(struct clock_event_device *dev); extern void tick_broadcast_on_off(unsigned long reason, int *oncpu); extern void tick_shutdown_broadcast(unsigned int *cpup); @@ -102,9 +104,8 @@ tick_set_periodic_handler(struct clock_event_device *dev, int broadcast); #else /* !BROADCAST */ -static inline int tick_check_broadcast_device(struct clock_event_device *dev) +static inline void tick_install_broadcast_device(struct clock_event_device *dev) { - return 0; } static inline int tick_is_broadcast_device(struct clock_event_device *dev) -- cgit v1.2.3 From ccf33d6880f39a35158fff66db13000ae4943fac Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 25 Apr 2013 20:31:49 +0000 Subject: clockevents: Add module refcount We want to be able to remove clockevent modules as well. Add a refcount so we don't remove a module with an active clock event device. Signed-off-by: Thomas Gleixner Cc: John Stultz Cc: Magnus Damm Link: http://lkml.kernel.org/r/20130425143436.307435149@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/clockchips.h | 3 +++ kernel/time/clockevents.c | 1 + kernel/time/tick-broadcast.c | 3 +++ kernel/time/tick-common.c | 4 ++++ 4 files changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index 2f498f66c1bb..ae1193bcf074 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -30,6 +30,7 @@ enum clock_event_nofitiers { #include struct clock_event_device; +struct module; /* Clock event mode commands */ enum clock_event_mode { @@ -83,6 +84,7 @@ enum clock_event_mode { * @irq: IRQ number (only for non CPU local devices) * @cpumask: cpumask to indicate for which CPUs this device works * @list: list head for the management code + * @owner: module reference */ struct clock_event_device { void (*event_handler)(struct clock_event_device *); @@ -112,6 +114,7 @@ struct clock_event_device { int irq; const struct cpumask *cpumask; struct list_head list; + struct module *owner; } ____cacheline_aligned; /* diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 0e3a8448e115..89e394caa769 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -357,6 +357,7 @@ void clockevents_exchange_device(struct clock_event_device *old, * released list and do a notify add later. */ if (old) { + module_put(old->owner); clockevents_set_mode(old, CLOCK_EVT_MODE_UNUSED); list_del(&old->list); list_add(&old->list, &clockevents_released); diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index 3500caaa0bfd..0e374cd2e0ef 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -19,6 +19,7 @@ #include #include #include +#include #include "tick-internal.h" @@ -73,6 +74,8 @@ void tick_install_broadcast_device(struct clock_event_device *dev) tick_broadcast_device.evtdev->rating >= dev->rating) || (dev->features & CLOCK_EVT_FEAT_C3STOP)) return; + if (!try_module_get(dev->owner)) + return; clockevents_exchange_device(tick_broadcast_device.evtdev, dev); if (cur) diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 84c7cfca4d7d..433a1e11d13b 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -18,6 +18,7 @@ #include #include #include +#include #include @@ -257,6 +258,9 @@ void tick_check_new_device(struct clock_event_device *newdev) goto out_bc; } + if (!try_module_get(newdev->owner)) + return; + /* * Replace the eventually existing device by the new * device. If the current device is the broadcast device, do -- cgit v1.2.3 From 03e13cf5ee60584fe0c831682c67212effb7fca4 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 25 Apr 2013 20:31:50 +0000 Subject: clockevents: Implement unbind functionality Provide a sysfs interface to allow unbinding of clockevent devices. The device is unbound if it is unused or if there is a replacement device available. Unbinding of broadcast devices is not supported as we don't want to foster that nonsense. If no replacement device is available the unbind returns -EBUSY. Unbind is available from the kernel and through sysfs, which is necessary to drop the module refcount. Signed-off-by: Thomas Gleixner Cc: John Stultz Cc: Magnus Damm Link: http://lkml.kernel.org/r/20130425143436.499216659@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/clockchips.h | 1 + kernel/time/clockevents.c | 125 ++++++++++++++++++++++++++++++++++++++++++++ kernel/time/clocksource.c | 9 ++-- kernel/time/tick-common.c | 24 +++++++++ kernel/time/tick-internal.h | 7 +++ 5 files changed, 162 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index ae1193bcf074..0857922e8ad0 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -141,6 +141,7 @@ static inline unsigned long div_sc(unsigned long ticks, unsigned long nsec, extern u64 clockevent_delta2ns(unsigned long latch, struct clock_event_device *evt); extern void clockevents_register_device(struct clock_event_device *dev); +extern int clockevents_unbind_device(struct clock_event_device *ced, int cpu); extern void clockevents_config(struct clock_event_device *dev, u32 freq); extern void clockevents_config_and_register(struct clock_event_device *dev, diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 0a23f4f29934..38959c866789 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -25,6 +25,13 @@ static LIST_HEAD(clockevent_devices); static LIST_HEAD(clockevents_released); /* Protection for the above */ static DEFINE_RAW_SPINLOCK(clockevents_lock); +/* Protection for unbind operations */ +static DEFINE_MUTEX(clockevents_mutex); + +struct ce_unbind { + struct clock_event_device *ce; + int res; +}; /** * clockevents_delta2ns - Convert a latch value (device ticks) to nanoseconds @@ -245,6 +252,90 @@ static void clockevents_notify_released(void) } } +/* + * Try to install a replacement clock event device + */ +static int clockevents_replace(struct clock_event_device *ced) +{ + struct clock_event_device *dev, *newdev = NULL; + + list_for_each_entry(dev, &clockevent_devices, list) { + if (dev == ced || dev->mode != CLOCK_EVT_MODE_UNUSED) + continue; + + if (!tick_check_replacement(newdev, dev)) + continue; + + if (!try_module_get(dev->owner)) + continue; + + if (newdev) + module_put(newdev->owner); + newdev = dev; + } + if (newdev) { + tick_install_replacement(newdev); + list_del_init(&ced->list); + } + return newdev ? 0 : -EBUSY; +} + +/* + * Called with clockevents_mutex and clockevents_lock held + */ +static int __clockevents_try_unbind(struct clock_event_device *ced, int cpu) +{ + /* Fast track. Device is unused */ + if (ced->mode == CLOCK_EVT_MODE_UNUSED) { + list_del_init(&ced->list); + return 0; + } + + return ced == per_cpu(tick_cpu_device, cpu).evtdev ? -EAGAIN : -EBUSY; +} + +/* + * SMP function call to unbind a device + */ +static void __clockevents_unbind(void *arg) +{ + struct ce_unbind *cu = arg; + int res; + + raw_spin_lock(&clockevents_lock); + res = __clockevents_try_unbind(cu->ce, smp_processor_id()); + if (res == -EAGAIN) + res = clockevents_replace(cu->ce); + cu->res = res; + raw_spin_unlock(&clockevents_lock); +} + +/* + * Issues smp function call to unbind a per cpu device. Called with + * clockevents_mutex held. + */ +static int clockevents_unbind(struct clock_event_device *ced, int cpu) +{ + struct ce_unbind cu = { .ce = ced, .res = -ENODEV }; + + smp_call_function_single(cpu, __clockevents_unbind, &cu, 1); + return cu.res; +} + +/* + * Unbind a clockevents device. + */ +int clockevents_unbind_device(struct clock_event_device *ced, int cpu) +{ + int ret; + + mutex_lock(&clockevents_mutex); + ret = clockevents_unbind(ced, cpu); + mutex_unlock(&clockevents_mutex); + return ret; +} +EXPORT_SYMBOL_GPL(clockevents_unbind); + /** * clockevents_register_device - register a clock event device * @dev: device to register @@ -487,6 +578,38 @@ static ssize_t sysfs_show_current_tick_dev(struct device *dev, } static DEVICE_ATTR(current_device, 0444, sysfs_show_current_tick_dev, NULL); +/* We don't support the abomination of removable broadcast devices */ +static ssize_t sysfs_unbind_tick_dev(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + char name[CS_NAME_LEN]; + size_t ret = sysfs_get_uname(buf, name, count); + struct clock_event_device *ce; + + if (ret < 0) + return ret; + + ret = -ENODEV; + mutex_lock(&clockevents_mutex); + raw_spin_lock_irq(&clockevents_lock); + list_for_each_entry(ce, &clockevent_devices, list) { + if (!strcmp(ce->name, name)) { + ret = __clockevents_try_unbind(ce, dev->id); + break; + } + } + raw_spin_unlock_irq(&clockevents_lock); + /* + * We hold clockevents_mutex, so ce can't go away + */ + if (ret == -EAGAIN) + ret = clockevents_unbind(ce, dev->id); + mutex_unlock(&clockevents_mutex); + return ret ? ret : count; +} +static DEVICE_ATTR(unbind_device, 0200, NULL, sysfs_unbind_tick_dev); + #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST static struct device tick_bc_dev = { .init_name = "broadcast", @@ -529,6 +652,8 @@ static int __init tick_init_sysfs(void) err = device_register(dev); if (!err) err = device_create_file(dev, &dev_attr_current_device); + if (!err) + err = device_create_file(dev, &dev_attr_unbind_device); if (err) return err; } diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 31b90332f47b..6d05b00410cc 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -31,6 +31,8 @@ #include #include +#include "tick-internal.h" + void timecounter_init(struct timecounter *tc, const struct cyclecounter *cc, u64 start_tstamp) @@ -174,7 +176,6 @@ clocks_calc_mult_shift(u32 *mult, u32 *shift, u32 from, u32 to, u32 maxsec) static struct clocksource *curr_clocksource; static LIST_HEAD(clocksource_list); static DEFINE_MUTEX(clocksource_mutex); -#define CS_NAME_LEN 32 static char override_name[CS_NAME_LEN]; static int finished_booting; @@ -864,7 +865,7 @@ sysfs_show_current_clocksources(struct device *dev, return count; } -static size_t clocksource_get_uname(const char *buf, char *dst, size_t cnt) +size_t sysfs_get_uname(const char *buf, char *dst, size_t cnt) { size_t ret = cnt; @@ -899,7 +900,7 @@ static ssize_t sysfs_override_clocksource(struct device *dev, mutex_lock(&clocksource_mutex); - ret = clocksource_get_uname(buf, override_name, count); + ret = sysfs_get_uname(buf, override_name, count); if (ret >= 0) clocksource_select(); @@ -925,7 +926,7 @@ static ssize_t sysfs_unbind_clocksource(struct device *dev, char name[CS_NAME_LEN]; size_t ret; - ret = clocksource_get_uname(buf, name, count); + ret = sysfs_get_uname(buf, name, count); if (ret < 0) return ret; diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index c34021650348..5edfb4806032 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -205,6 +205,17 @@ static void tick_setup_device(struct tick_device *td, tick_setup_oneshot(newdev, handler, next_event); } +void tick_install_replacement(struct clock_event_device *newdev) +{ + struct tick_device *td = &__get_cpu_var(tick_cpu_device); + int cpu = smp_processor_id(); + + clockevents_exchange_device(td->evtdev, newdev); + tick_setup_device(td, newdev, cpu, cpumask_of(cpu)); + if (newdev->features & CLOCK_EVT_FEAT_ONESHOT) + tick_oneshot_notify(); +} + static bool tick_check_percpu(struct clock_event_device *curdev, struct clock_event_device *newdev, int cpu) { @@ -236,6 +247,19 @@ static bool tick_check_preferred(struct clock_event_device *curdev, return !curdev || newdev->rating > curdev->rating; } +/* + * Check whether the new device is a better fit than curdev. curdev + * can be NULL ! + */ +bool tick_check_replacement(struct clock_event_device *curdev, + struct clock_event_device *newdev) +{ + if (tick_check_percpu(curdev, newdev, smp_processor_id())) + return false; + + return tick_check_preferred(curdev, newdev); +} + /* * Check, if the new registered device should be used. Called with * clockevents_lock held and interrupts disabled. diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index 06bfc8802dfb..be1690eaecff 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -11,6 +11,8 @@ extern seqlock_t jiffies_lock; #define TICK_DO_TIMER_NONE -1 #define TICK_DO_TIMER_BOOT -2 +#define CS_NAME_LEN 32 + DECLARE_PER_CPU(struct tick_device, tick_cpu_device); extern ktime_t tick_next_period; extern ktime_t tick_period; @@ -23,9 +25,14 @@ extern void tick_handover_do_timer(int *cpup); extern void tick_shutdown(unsigned int *cpup); extern void tick_suspend(void); extern void tick_resume(void); +extern bool tick_check_replacement(struct clock_event_device *curdev, + struct clock_event_device *newdev); +extern void tick_install_replacement(struct clock_event_device *dev); extern void clockevents_shutdown(struct clock_event_device *dev); +extern size_t sysfs_get_uname(const char *buf, char *dst, size_t cnt); + /* * NO_HZ / high resolution timer shared code */ -- cgit v1.2.3 From b0ce3508b25ea6fa10ae3ca254de1d695b521702 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 16 May 2013 07:34:53 +0000 Subject: bonding: allow TSO being set on bonding master MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In some situations, we need to disable TSO on bonding slaves. bonding device automatically unset TSO in bond_fix_features(), and performance is not good because : 1) We consume more cpu cycles. 2) GSO segmentation has some bugs leading to out of order TCP packets if this segmentation is done before virtual device. This particular problem will be addressed in a separate patch. This patch allows TSO being set/unset on the bonding master, so that GSO segmentation is done after bonding layer. Signed-off-by: Eric Dumazet Cc: Michał Mirosław Cc: Jay Vosburgh Cc: Andy Gospodarek Cc: Maciej Żenczykowski Cc: Tom Herbert Cc: Neal Cardwell Cc: Yuchung Cheng Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 1 + include/linux/netdevice.h | 11 +++++++++++ 2 files changed, 12 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index d0aade04e49a..449ad9bbe45c 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1362,6 +1362,7 @@ static netdev_features_t bond_fix_features(struct net_device *dev, slave->dev->features, mask); } + features = netdev_add_tso_features(features, mask); out: read_unlock(&bond->lock); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a94a5a0ab122..60584b185a0c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2733,6 +2733,17 @@ static inline netdev_features_t netdev_get_wanted_features( } netdev_features_t netdev_increment_features(netdev_features_t all, netdev_features_t one, netdev_features_t mask); + +/* Allow TSO being used on stacked device : + * Performing the GSO segmentation before last device + * is a performance improvement. + */ +static inline netdev_features_t netdev_add_tso_features(netdev_features_t features, + netdev_features_t mask) +{ + return netdev_increment_features(features, NETIF_F_ALL_TSO, mask); +} + int __netdev_update_features(struct net_device *dev); void netdev_update_features(struct net_device *dev); void netdev_change_features(struct net_device *dev); -- cgit v1.2.3 From 0b8ebdb18888c55588b932f4f564b9c9529de627 Mon Sep 17 00:00:00 2001 From: Fabio Baltieri Date: Thu, 9 May 2013 13:08:08 +0200 Subject: mfd: ab8500-sysctrl: Always enable pm_power_off handler AB8500 sysctrl driver implements a pm_power_off handler, but that is currently not registered until a specific platform data field is enabled. This patch drops the platform data field and always registers ab8500_power_off if no other pm_power_off handler was defined before, and also introduces the necessary cleanup code in the driver's remove function. Acked-by: Linus Walleij Signed-off-by: Fabio Baltieri Signed-off-by: Lee Jones Signed-off-by: Samuel Ortiz --- drivers/mfd/ab8500-sysctrl.c | 6 +++++- include/linux/mfd/abx500/ab8500.h | 2 -- 2 files changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/ab8500-sysctrl.c b/drivers/mfd/ab8500-sysctrl.c index b851692b0755..0c20361eae26 100644 --- a/drivers/mfd/ab8500-sysctrl.c +++ b/drivers/mfd/ab8500-sysctrl.c @@ -193,7 +193,7 @@ static int ab8500_sysctrl_probe(struct platform_device *pdev) sysctrl_dev = &pdev->dev; - if (plat->pm_power_off) + if (!pm_power_off) pm_power_off = ab8500_power_off; pdata = plat->sysctrl; @@ -228,6 +228,10 @@ static int ab8500_sysctrl_probe(struct platform_device *pdev) static int ab8500_sysctrl_remove(struct platform_device *pdev) { sysctrl_dev = NULL; + + if (pm_power_off == ab8500_power_off) + pm_power_off = NULL; + return 0; } diff --git a/include/linux/mfd/abx500/ab8500.h b/include/linux/mfd/abx500/ab8500.h index fb1bf7d6a410..0390d5943ed6 100644 --- a/include/linux/mfd/abx500/ab8500.h +++ b/include/linux/mfd/abx500/ab8500.h @@ -373,13 +373,11 @@ struct ab8500_sysctrl_platform_data; /** * struct ab8500_platform_data - AB8500 platform data * @irq_base: start of AB8500 IRQs, AB8500_NR_IRQS will be used - * @pm_power_off: Should machine pm power off hook be registered or not * @init: board-specific initialization after detection of ab8500 * @regulator: machine-specific constraints for regulators */ struct ab8500_platform_data { int irq_base; - bool pm_power_off; void (*init) (struct ab8500 *); struct ab8500_regulator_platform_data *regulator; struct abx500_gpio_platform_data *gpio; -- cgit v1.2.3 From 0693196fe7bbb5e6cafd255dfce91ff6d10bc18f Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Sun, 5 May 2013 20:32:27 +0200 Subject: USB: serial: add wait_until_sent operation Add wait_until_sent operation which can be used to wait for hardware buffers to drain. Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/usb-serial.c | 17 +++++++++++++++++ include/linux/usb/serial.h | 1 + 2 files changed, 18 insertions(+) (limited to 'include/linux') diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c index cf75beb1251b..31d27686151f 100644 --- a/drivers/usb/serial/usb-serial.c +++ b/drivers/usb/serial/usb-serial.c @@ -375,6 +375,22 @@ static int serial_chars_in_buffer(struct tty_struct *tty) return count; } +static void serial_wait_until_sent(struct tty_struct *tty, int timeout) +{ + struct usb_serial_port *port = tty->driver_data; + struct usb_serial *serial = port->serial; + + dev_dbg(tty->dev, "%s\n", __func__); + + if (!port->serial->type->wait_until_sent) + return; + + mutex_lock(&serial->disc_mutex); + if (!serial->disconnected) + port->serial->type->wait_until_sent(tty, timeout); + mutex_unlock(&serial->disc_mutex); +} + static void serial_throttle(struct tty_struct *tty) { struct usb_serial_port *port = tty->driver_data; @@ -1191,6 +1207,7 @@ static const struct tty_operations serial_ops = { .unthrottle = serial_unthrottle, .break_ctl = serial_break, .chars_in_buffer = serial_chars_in_buffer, + .wait_until_sent = serial_wait_until_sent, .tiocmget = serial_tiocmget, .tiocmset = serial_tiocmset, .get_icount = serial_get_icount, diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index b9b0f7b4e43b..afbb7eeaac5f 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -268,6 +268,7 @@ struct usb_serial_driver { struct usb_serial_port *port, struct ktermios *old); void (*break_ctl)(struct tty_struct *tty, int break_state); int (*chars_in_buffer)(struct tty_struct *tty); + void (*wait_until_sent)(struct tty_struct *tty, long timeout); void (*throttle)(struct tty_struct *tty); void (*unthrottle)(struct tty_struct *tty); int (*tiocmget)(struct tty_struct *tty); -- cgit v1.2.3 From dcf0105039660e951dfea348d317043d17988dfc Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 8 May 2013 17:51:43 +0200 Subject: USB: serial: add generic wait_until_sent implementation Add generic wait_until_sent implementation which polls for empty hardware buffers using the new port-operation tx_empty. The generic implementation will be used for all sub-drivers that implement tx_empty but does not define wait_until_sent. Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/generic.c | 31 +++++++++++++++++++++++++++++++ drivers/usb/serial/usb-serial.c | 2 ++ include/linux/usb/serial.h | 3 +++ 3 files changed, 36 insertions(+) (limited to 'include/linux') diff --git a/drivers/usb/serial/generic.c b/drivers/usb/serial/generic.c index 297665fdd16d..ba45170c78e5 100644 --- a/drivers/usb/serial/generic.c +++ b/drivers/usb/serial/generic.c @@ -253,6 +253,37 @@ int usb_serial_generic_chars_in_buffer(struct tty_struct *tty) } EXPORT_SYMBOL_GPL(usb_serial_generic_chars_in_buffer); +void usb_serial_generic_wait_until_sent(struct tty_struct *tty, long timeout) +{ + struct usb_serial_port *port = tty->driver_data; + unsigned int bps; + unsigned long period; + unsigned long expire; + + bps = tty_get_baud_rate(tty); + if (!bps) + bps = 9600; /* B0 */ + /* + * Use a poll-period of roughly the time it takes to send one + * character or at least one jiffy. + */ + period = max_t(unsigned long, (10 * HZ / bps), 1); + period = min_t(unsigned long, period, timeout); + + dev_dbg(&port->dev, "%s - timeout = %u ms, period = %u ms\n", + __func__, jiffies_to_msecs(timeout), + jiffies_to_msecs(period)); + expire = jiffies + timeout; + while (!port->serial->type->tx_empty(port)) { + schedule_timeout_interruptible(period); + if (signal_pending(current)) + break; + if (time_after(jiffies, expire)) + break; + } +} +EXPORT_SYMBOL_GPL(usb_serial_generic_wait_until_sent); + static int usb_serial_generic_submit_read_urb(struct usb_serial_port *port, int index, gfp_t mem_flags) { diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c index 31d27686151f..60caf9cb99f4 100644 --- a/drivers/usb/serial/usb-serial.c +++ b/drivers/usb/serial/usb-serial.c @@ -1333,6 +1333,8 @@ static void usb_serial_operations_init(struct usb_serial_driver *device) set_to_generic_if_null(device, close); set_to_generic_if_null(device, write_room); set_to_generic_if_null(device, chars_in_buffer); + if (device->tx_empty) + set_to_generic_if_null(device, wait_until_sent); set_to_generic_if_null(device, read_bulk_callback); set_to_generic_if_null(device, write_bulk_callback); set_to_generic_if_null(device, process_read_urb); diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index afbb7eeaac5f..302ddf55d2da 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -269,6 +269,7 @@ struct usb_serial_driver { void (*break_ctl)(struct tty_struct *tty, int break_state); int (*chars_in_buffer)(struct tty_struct *tty); void (*wait_until_sent)(struct tty_struct *tty, long timeout); + bool (*tx_empty)(struct usb_serial_port *port); void (*throttle)(struct tty_struct *tty); void (*unthrottle)(struct tty_struct *tty); int (*tiocmget)(struct tty_struct *tty); @@ -328,6 +329,8 @@ extern void usb_serial_generic_close(struct usb_serial_port *port); extern int usb_serial_generic_resume(struct usb_serial *serial); extern int usb_serial_generic_write_room(struct tty_struct *tty); extern int usb_serial_generic_chars_in_buffer(struct tty_struct *tty); +extern void usb_serial_generic_wait_until_sent(struct tty_struct *tty, + long timeout); extern void usb_serial_generic_read_bulk_callback(struct urb *urb); extern void usb_serial_generic_write_bulk_callback(struct urb *urb); extern void usb_serial_generic_throttle(struct tty_struct *tty); -- cgit v1.2.3 From d4988d4c733ba0b61cb372edd3d1992d26dd10d3 Mon Sep 17 00:00:00 2001 From: Rafał Miłecki Date: Thu, 9 May 2013 21:24:24 +0200 Subject: bcma: add more core IDs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit PCIe and ARM CR4 cores were found on 14e4:43b1 AKA BCM4352. Reported-by: Gabriel Thörnblad Signed-off-by: Rafał Miłecki Signed-off-by: John W. Linville --- drivers/bcma/scan.c | 2 ++ include/linux/bcma/bcma.h | 5 ++++- 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/bcma/scan.c b/drivers/bcma/scan.c index bca9c80056fe..8bffa5c9818c 100644 --- a/drivers/bcma/scan.c +++ b/drivers/bcma/scan.c @@ -84,6 +84,8 @@ static const struct bcma_device_id_name bcma_bcm_device_names[] = { { BCMA_CORE_I2S, "I2S" }, { BCMA_CORE_SDR_DDR1_MEM_CTL, "SDR/DDR1 Memory Controller" }, { BCMA_CORE_SHIM, "SHIM" }, + { BCMA_CORE_PCIE2, "PCIe Gen2" }, + { BCMA_CORE_ARM_CR4, "ARM CR4" }, { BCMA_CORE_DEFAULT, "Default" }, }; diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h index f14a98a79c9d..2e34db82a643 100644 --- a/include/linux/bcma/bcma.h +++ b/include/linux/bcma/bcma.h @@ -134,7 +134,10 @@ struct bcma_host_ops { #define BCMA_CORE_I2S 0x834 #define BCMA_CORE_SDR_DDR1_MEM_CTL 0x835 /* SDR/DDR1 memory controller core */ #define BCMA_CORE_SHIM 0x837 /* SHIM component in ubus/6362 */ -#define BCMA_CORE_ARM_CR4 0x83e +#define BCMA_CORE_PHY_AC 0x83B +#define BCMA_CORE_PCIE2 0x83C /* PCI Express Gen2 */ +#define BCMA_CORE_USB30_DEV 0x83D +#define BCMA_CORE_ARM_CR4 0x83E #define BCMA_CORE_DEFAULT 0xFFF #define BCMA_MAX_NR_CORES 16 -- cgit v1.2.3 From 3f327e39b4b8f760c331bb2836735be6d83fbf53 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Tue, 7 May 2013 11:06:03 -0600 Subject: PCI: acpiphp: Re-enumerate devices when host bridge receives Bus Check When a PCI host bridge device receives a Bus Check notification, we must re-enumerate starting with the bridge to discover changes (devices that have been added or removed). Prior to 668192b678 ("PCI: acpiphp: Move host bridge hotplug to pci_root.c"), this happened in _handle_hotplug_event_bridge(). After that commit, _handle_hotplug_event_bridge() is not installed for host bridges, and the host bridge notify handler, _handle_hotplug_event_root() did not re-enumerate. This patch adds re-enumeration to _handle_hotplug_event_root(). This fixes cases where we don't notice the addition or removal of PCI devices, e.g., the PCI-to-USB ExpressCard in the bugzilla below. [bhelgaas: changelog, references] Reference: https://lkml.kernel.org/r/CAAh6nkmbKR3HTqm5ommevsBwhL_u0N8Rk7Wsms_LfP=nBgKNew@mail.gmail.com Reference: https://bugzilla.kernel.org/show_bug.cgi?id=57961 Reported-by: Gavin Guo Tested-by: Gavin Guo Signed-off-by: Yinghai Lu Signed-off-by: Bjorn Helgaas Reviewed-by: Jiang Liu Acked-by: Rafael J. Wysocki CC: stable@vger.kernel.org # v3.9+ --- drivers/acpi/pci_root.c | 4 +++- drivers/pci/hotplug/acpiphp_glue.c | 14 ++++++++++++++ include/linux/pci-acpi.h | 2 ++ 3 files changed, 19 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c index 1dd6f6c85874..e427dc516c76 100644 --- a/drivers/acpi/pci_root.c +++ b/drivers/acpi/pci_root.c @@ -641,7 +641,9 @@ static void _handle_hotplug_event_root(struct work_struct *work) /* bus enumerate */ printk(KERN_DEBUG "%s: Bus check notify on %s\n", __func__, (char *)buffer.pointer); - if (!root) + if (root) + acpiphp_check_host_bridge(handle); + else handle_root_bridge_insertion(handle); break; diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c index 96fed19c6d90..716aa93fff76 100644 --- a/drivers/pci/hotplug/acpiphp_glue.c +++ b/drivers/pci/hotplug/acpiphp_glue.c @@ -950,6 +950,20 @@ check_sub_bridges(acpi_handle handle, u32 lvl, void *context, void **rv) return AE_OK ; } +void acpiphp_check_host_bridge(acpi_handle handle) +{ + struct acpiphp_bridge *bridge; + + bridge = acpiphp_handle_to_bridge(handle); + if (bridge) { + acpiphp_check_bridge(bridge); + put_bridge(bridge); + } + + acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, + ACPI_UINT32_MAX, check_sub_bridges, NULL, NULL, NULL); +} + static void _handle_hotplug_event_bridge(struct work_struct *work) { struct acpiphp_bridge *bridge; diff --git a/include/linux/pci-acpi.h b/include/linux/pci-acpi.h index 81b31613eb25..170447977278 100644 --- a/include/linux/pci-acpi.h +++ b/include/linux/pci-acpi.h @@ -60,11 +60,13 @@ static inline void acpi_pci_slot_remove(struct pci_bus *bus) { } void acpiphp_init(void); void acpiphp_enumerate_slots(struct pci_bus *bus, acpi_handle handle); void acpiphp_remove_slots(struct pci_bus *bus); +void acpiphp_check_host_bridge(acpi_handle handle); #else static inline void acpiphp_init(void) { } static inline void acpiphp_enumerate_slots(struct pci_bus *bus, acpi_handle handle) { } static inline void acpiphp_remove_slots(struct pci_bus *bus) { } +static inline void acpiphp_check_host_bridge(acpi_handle handle) { } #endif #else /* CONFIG_ACPI */ -- cgit v1.2.3 From 7f18d05a1af75142d4856a91ffd2f1d8eb553c12 Mon Sep 17 00:00:00 2001 From: Santosh Shilimkar Date: Wed, 15 May 2013 20:18:41 +0530 Subject: SERIAL: OMAP: Remove the slave idle handling from the driver UART IP slave idle handling now taken care by runtime pm backend(hwmod layer) so remove the hackery from the driver. As discussed on the list, in future if dma mode needs to be brought back to this driver, UART sysc handling needs to be updated in framework such a way that no-idle/force idle profile can be supported. Given the broken dma mode for OMAP uarts, its very unlikely. Acked-by: Greg Kroah-Hartman Tested-by: Vaibhav Bedia Tested-by: Sourav Poddar Signed-off-by: Rajendra nayak Signed-off-by: Santosh Shilimkar Reviewed-by: Kevin Hilman Tested-by: Kevin Hilman # OMAP4/Panda Signed-off-by: Paul Walmsley --- drivers/tty/serial/omap-serial.c | 23 ----------------------- include/linux/platform_data/serial-omap.h | 2 -- 2 files changed, 25 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c index 30d4f7a783cd..f0b9f6b52b32 100644 --- a/drivers/tty/serial/omap-serial.c +++ b/drivers/tty/serial/omap-serial.c @@ -202,26 +202,6 @@ static int serial_omap_get_context_loss_count(struct uart_omap_port *up) return pdata->get_context_loss_count(up->dev); } -static void serial_omap_set_forceidle(struct uart_omap_port *up) -{ - struct omap_uart_port_info *pdata = up->dev->platform_data; - - if (!pdata || !pdata->set_forceidle) - return; - - pdata->set_forceidle(up->dev); -} - -static void serial_omap_set_noidle(struct uart_omap_port *up) -{ - struct omap_uart_port_info *pdata = up->dev->platform_data; - - if (!pdata || !pdata->set_noidle) - return; - - pdata->set_noidle(up->dev); -} - static void serial_omap_enable_wakeup(struct uart_omap_port *up, bool enable) { struct omap_uart_port_info *pdata = up->dev->platform_data; @@ -298,8 +278,6 @@ static void serial_omap_stop_tx(struct uart_port *port) serial_out(up, UART_IER, up->ier); } - serial_omap_set_forceidle(up); - pm_runtime_mark_last_busy(up->dev); pm_runtime_put_autosuspend(up->dev); } @@ -364,7 +342,6 @@ static void serial_omap_start_tx(struct uart_port *port) pm_runtime_get_sync(up->dev); serial_omap_enable_ier_thri(up); - serial_omap_set_noidle(up); pm_runtime_mark_last_busy(up->dev); pm_runtime_put_autosuspend(up->dev); } diff --git a/include/linux/platform_data/serial-omap.h b/include/linux/platform_data/serial-omap.h index ff9b0aab5281..c860c1b314c0 100644 --- a/include/linux/platform_data/serial-omap.h +++ b/include/linux/platform_data/serial-omap.h @@ -43,8 +43,6 @@ struct omap_uart_port_info { int DTR_present; int (*get_context_loss_count)(struct device *); - void (*set_forceidle)(struct device *); - void (*set_noidle)(struct device *); void (*enable_wakeup)(struct device *, bool); }; -- cgit v1.2.3 From d2f83e9078b8114e3b9d09082856c1aac299aa37 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Fri, 17 May 2013 09:05:21 +0930 Subject: Hoist memcpy_fromiovec/memcpy_toiovec into lib/ ERROR: "memcpy_fromiovec" [drivers/vhost/vhost_scsi.ko] undefined! That function is only present with CONFIG_NET. Turns out that crypto/algif_skcipher.c also uses that outside net, but it actually needs sockets anyway. In addition, commit 6d4f0139d642c45411a47879325891ce2a7c164a added CONFIG_NET dependency to CONFIG_VMCI for memcpy_toiovec, so hoist that function and revert that commit too. socket.h already includes uio.h, so no callers need updating; trying only broke things fo x86_64 randconfig (thanks Fengguang!). Reported-by: Randy Dunlap Acked-by: David S. Miller Acked-by: Michael S. Tsirkin Signed-off-by: Rusty Russell --- drivers/misc/vmw_vmci/Kconfig | 2 +- drivers/misc/vmw_vmci/vmci_queue_pair.c | 2 +- include/linux/socket.h | 2 -- include/linux/uio.h | 3 ++ lib/Makefile | 2 +- lib/iovec.c | 53 +++++++++++++++++++++++++++++++++ net/core/iovec.c | 50 ------------------------------- 7 files changed, 59 insertions(+), 55 deletions(-) create mode 100644 lib/iovec.c (limited to 'include/linux') diff --git a/drivers/misc/vmw_vmci/Kconfig b/drivers/misc/vmw_vmci/Kconfig index ea98f7e9ccd1..39c2ecadb273 100644 --- a/drivers/misc/vmw_vmci/Kconfig +++ b/drivers/misc/vmw_vmci/Kconfig @@ -4,7 +4,7 @@ config VMWARE_VMCI tristate "VMware VMCI Driver" - depends on X86 && PCI && NET + depends on X86 && PCI help This is VMware's Virtual Machine Communication Interface. It enables high-speed communication between host and guest in a virtual diff --git a/drivers/misc/vmw_vmci/vmci_queue_pair.c b/drivers/misc/vmw_vmci/vmci_queue_pair.c index d94245dbd765..8ff2e5ee8fb8 100644 --- a/drivers/misc/vmw_vmci/vmci_queue_pair.c +++ b/drivers/misc/vmw_vmci/vmci_queue_pair.c @@ -23,7 +23,7 @@ #include #include #include -#include +#include #include #include diff --git a/include/linux/socket.h b/include/linux/socket.h index 428c37a1f95c..33bf2dfab19d 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -305,7 +305,6 @@ struct ucred { extern void cred_to_ucred(struct pid *pid, const struct cred *cred, struct ucred *ucred); -extern int memcpy_fromiovec(unsigned char *kdata, struct iovec *iov, int len); extern int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov, int offset, int len); extern int csum_partial_copy_fromiovecend(unsigned char *kdata, @@ -314,7 +313,6 @@ extern int csum_partial_copy_fromiovecend(unsigned char *kdata, unsigned int len, __wsum *csump); extern int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr_storage *address, int mode); -extern int memcpy_toiovec(struct iovec *v, unsigned char *kdata, int len); extern int memcpy_toiovecend(const struct iovec *v, unsigned char *kdata, int offset, int len); extern int move_addr_to_kernel(void __user *uaddr, int ulen, struct sockaddr_storage *kaddr); diff --git a/include/linux/uio.h b/include/linux/uio.h index 629aaf51f30b..c55ce243cc09 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -35,4 +35,7 @@ static inline size_t iov_length(const struct iovec *iov, unsigned long nr_segs) } unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to); + +int memcpy_fromiovec(unsigned char *kdata, struct iovec *iov, int len); +int memcpy_toiovec(struct iovec *iov, unsigned char *kdata, int len); #endif diff --git a/lib/Makefile b/lib/Makefile index e9c52e1b853a..237721165035 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -9,7 +9,7 @@ endif lib-y := ctype.o string.o vsprintf.o cmdline.o \ rbtree.o radix-tree.o dump_stack.o timerqueue.o\ - idr.o int_sqrt.o extable.o \ + idr.o int_sqrt.o extable.o iovec.o \ sha1.o md5.o irq_regs.o reciprocal_div.o argv_split.o \ proportions.o flex_proportions.o prio_heap.o ratelimit.o show_mem.o \ is_single_threaded.o plist.o decompress.o kobject_uevent.o \ diff --git a/lib/iovec.c b/lib/iovec.c new file mode 100644 index 000000000000..454baa88bf27 --- /dev/null +++ b/lib/iovec.c @@ -0,0 +1,53 @@ +#include +#include +#include + +/* + * Copy iovec to kernel. Returns -EFAULT on error. + * + * Note: this modifies the original iovec. + */ + +int memcpy_fromiovec(unsigned char *kdata, struct iovec *iov, int len) +{ + while (len > 0) { + if (iov->iov_len) { + int copy = min_t(unsigned int, len, iov->iov_len); + if (copy_from_user(kdata, iov->iov_base, copy)) + return -EFAULT; + len -= copy; + kdata += copy; + iov->iov_base += copy; + iov->iov_len -= copy; + } + iov++; + } + + return 0; +} +EXPORT_SYMBOL(memcpy_fromiovec); + +/* + * Copy kernel to iovec. Returns -EFAULT on error. + * + * Note: this modifies the original iovec. + */ + +int memcpy_toiovec(struct iovec *iov, unsigned char *kdata, int len) +{ + while (len > 0) { + if (iov->iov_len) { + int copy = min_t(unsigned int, iov->iov_len, len); + if (copy_to_user(iov->iov_base, kdata, copy)) + return -EFAULT; + kdata += copy; + len -= copy; + iov->iov_len -= copy; + iov->iov_base += copy; + } + iov++; + } + + return 0; +} +EXPORT_SYMBOL(memcpy_toiovec); diff --git a/net/core/iovec.c b/net/core/iovec.c index 7e7aeb01de45..de178e462682 100644 --- a/net/core/iovec.c +++ b/net/core/iovec.c @@ -73,31 +73,6 @@ int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr_storage *a return err; } -/* - * Copy kernel to iovec. Returns -EFAULT on error. - * - * Note: this modifies the original iovec. - */ - -int memcpy_toiovec(struct iovec *iov, unsigned char *kdata, int len) -{ - while (len > 0) { - if (iov->iov_len) { - int copy = min_t(unsigned int, iov->iov_len, len); - if (copy_to_user(iov->iov_base, kdata, copy)) - return -EFAULT; - kdata += copy; - len -= copy; - iov->iov_len -= copy; - iov->iov_base += copy; - } - iov++; - } - - return 0; -} -EXPORT_SYMBOL(memcpy_toiovec); - /* * Copy kernel to iovec. Returns -EFAULT on error. */ @@ -124,31 +99,6 @@ int memcpy_toiovecend(const struct iovec *iov, unsigned char *kdata, } EXPORT_SYMBOL(memcpy_toiovecend); -/* - * Copy iovec to kernel. Returns -EFAULT on error. - * - * Note: this modifies the original iovec. - */ - -int memcpy_fromiovec(unsigned char *kdata, struct iovec *iov, int len) -{ - while (len > 0) { - if (iov->iov_len) { - int copy = min_t(unsigned int, len, iov->iov_len); - if (copy_from_user(kdata, iov->iov_base, copy)) - return -EFAULT; - len -= copy; - kdata += copy; - iov->iov_base += copy; - iov->iov_len -= copy; - } - iov++; - } - - return 0; -} -EXPORT_SYMBOL(memcpy_fromiovec); - /* * Copy iovec from kernel. Returns -EFAULT on error. */ -- cgit v1.2.3 From 421b40a6286ee343d77d5e51f5ee6d04d7a2a90f Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Fri, 17 May 2013 12:41:03 -0400 Subject: tty/vt: Fix vc_deallocate() lock order Now that the tty port owns the flip buffers and i/o is allowed from the driver even when no tty is attached, the destruction of the tty port (and the flip buffers) must ensure that no outstanding work is pending. Unfortunately, this creates a lock order problem with the console_lock (see attached lockdep report [1] below). For single console deallocation, drop the console_lock prior to port destruction. When multiple console deallocation, defer port destruction until the consoles have been deallocated. tty_port_destroy() is not required if the port has not been used; remove from vc_allocate() failure path. [1] lockdep report from Dave Jones ====================================================== [ INFO: possible circular locking dependency detected ] 3.9.0+ #16 Not tainted ------------------------------------------------------- (agetty)/26163 is trying to acquire lock: blocked: ((&buf->work)){+.+...}, instance: ffff88011c8b0020, at: [] flush_work+0x5/0x2e0 but task is already holding lock: blocked: (console_lock){+.+.+.}, instance: ffffffff81c2fde0, at: [] vt_ioctl+0xb61/0x1230 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (console_lock){+.+.+.}: [] lock_acquire+0xa4/0x210 [] console_lock+0x77/0x80 [] con_flush_chars+0x2d/0x50 [] n_tty_receive_buf+0x122/0x14d0 [] flush_to_ldisc+0x119/0x170 [] process_one_work+0x211/0x700 [] worker_thread+0x11b/0x3a0 [] kthread+0xed/0x100 [] ret_from_fork+0x7c/0xb0 -> #0 ((&buf->work)){+.+...}: [] __lock_acquire+0x193a/0x1c00 [] lock_acquire+0xa4/0x210 [] flush_work+0x4e/0x2e0 [] __cancel_work_timer+0x95/0x130 [] cancel_work_sync+0x10/0x20 [] tty_port_destroy+0x12/0x20 [] vc_deallocate+0xf8/0x110 [] vt_ioctl+0xb6c/0x1230 [] tty_ioctl+0x285/0xd50 [] do_vfs_ioctl+0x305/0x530 [] sys_ioctl+0x81/0xa0 [] system_call_fastpath+0x16/0x1b other info that might help us debug this: [ 6760.076175] Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(console_lock); lock((&buf->work)); lock(console_lock); lock((&buf->work)); *** DEADLOCK *** 1 lock on stack by (agetty)/26163: #0: blocked: (console_lock){+.+.+.}, instance: ffffffff81c2fde0, at: [] vt_ioctl+0xb61/0x1230 stack backtrace: Pid: 26163, comm: (agetty) Not tainted 3.9.0+ #16 Call Trace: [] print_circular_bug+0x200/0x20e [] __lock_acquire+0x193a/0x1c00 [] ? sched_clock+0x9/0x10 [] ? sched_clock+0x9/0x10 [] ? native_sched_clock+0x20/0x80 [] lock_acquire+0xa4/0x210 [] ? flush_work+0x5/0x2e0 [] flush_work+0x4e/0x2e0 [] ? flush_work+0x5/0x2e0 [] ? mark_held_locks+0xbb/0x140 [] ? __free_pages_ok.part.57+0x93/0xc0 [] ? mark_held_locks+0xbb/0x140 [] ? __cancel_work_timer+0x82/0x130 [] __cancel_work_timer+0x95/0x130 [] cancel_work_sync+0x10/0x20 [] tty_port_destroy+0x12/0x20 [] vc_deallocate+0xf8/0x110 [] vt_ioctl+0xb6c/0x1230 [] ? lock_release_holdtime.part.30+0xa1/0x170 [] tty_ioctl+0x285/0xd50 [] ? inode_has_perm.isra.46.constprop.61+0x56/0x80 [] do_vfs_ioctl+0x305/0x530 [] ? selinux_file_ioctl+0x5b/0x110 [] sys_ioctl+0x81/0xa0 [] system_call_fastpath+0x16/0x1b Cc: Dave Jones Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- drivers/tty/vt/vt.c | 14 +++++----- drivers/tty/vt/vt_ioctl.c | 67 ++++++++++++++++++++++++++++++++++------------- include/linux/vt_kern.h | 2 +- 3 files changed, 56 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index fbd447b390f7..740202d8a5c4 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -779,7 +779,6 @@ int vc_allocate(unsigned int currcons) /* return 0 on success */ con_set_default_unimap(vc); vc->vc_screenbuf = kmalloc(vc->vc_screenbuf_size, GFP_KERNEL); if (!vc->vc_screenbuf) { - tty_port_destroy(&vc->port); kfree(vc); vc_cons[currcons].d = NULL; return -ENOMEM; @@ -986,26 +985,25 @@ static int vt_resize(struct tty_struct *tty, struct winsize *ws) return ret; } -void vc_deallocate(unsigned int currcons) +struct vc_data *vc_deallocate(unsigned int currcons) { + struct vc_data *vc = NULL; + WARN_CONSOLE_UNLOCKED(); if (vc_cons_allocated(currcons)) { - struct vc_data *vc = vc_cons[currcons].d; - struct vt_notifier_param param = { .vc = vc }; + struct vt_notifier_param param; + param.vc = vc = vc_cons[currcons].d; atomic_notifier_call_chain(&vt_notifier_list, VT_DEALLOCATE, ¶m); vcs_remove_sysfs(currcons); vc->vc_sw->con_deinit(vc); put_pid(vc->vt_pid); module_put(vc->vc_sw->owner); kfree(vc->vc_screenbuf); - if (currcons >= MIN_NR_CONSOLES) { - tty_port_destroy(&vc->port); - kfree(vc); - } vc_cons[currcons].d = NULL; } + return vc; } /* diff --git a/drivers/tty/vt/vt_ioctl.c b/drivers/tty/vt/vt_ioctl.c index 98ff1735eafc..fc2c06c66e89 100644 --- a/drivers/tty/vt/vt_ioctl.c +++ b/drivers/tty/vt/vt_ioctl.c @@ -283,6 +283,51 @@ do_unimap_ioctl(int cmd, struct unimapdesc __user *user_ud, int perm, struct vc_ return 0; } +/* deallocate a single console, if possible (leave 0) */ +static int vt_disallocate(unsigned int vc_num) +{ + struct vc_data *vc = NULL; + int ret = 0; + + if (!vc_num) + return 0; + + console_lock(); + if (VT_BUSY(vc_num)) + ret = -EBUSY; + else + vc = vc_deallocate(vc_num); + console_unlock(); + + if (vc && vc_num >= MIN_NR_CONSOLES) { + tty_port_destroy(&vc->port); + kfree(vc); + } + + return ret; +} + +/* deallocate all unused consoles, but leave 0 */ +static void vt_disallocate_all(void) +{ + struct vc_data *vc[MAX_NR_CONSOLES]; + int i; + + console_lock(); + for (i = 1; i < MAX_NR_CONSOLES; i++) + if (!VT_BUSY(i)) + vc[i] = vc_deallocate(i); + else + vc[i] = NULL; + console_unlock(); + + for (i = 1; i < MAX_NR_CONSOLES; i++) { + if (vc[i] && i >= MIN_NR_CONSOLES) { + tty_port_destroy(&vc[i]->port); + kfree(vc[i]); + } + } +} /* @@ -769,24 +814,10 @@ int vt_ioctl(struct tty_struct *tty, ret = -ENXIO; break; } - if (arg == 0) { - /* deallocate all unused consoles, but leave 0 */ - console_lock(); - for (i=1; i Date: Tue, 21 May 2013 10:51:10 +0200 Subject: Add include dependencies to . MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If has not been included before , a build error like the below one will result: CC arch/mips/kernel/idle.o In file included from arch/mips/kernel/idle.c:17:0: include/linux/printk.h:109:1: error: data definition has no type or storage class [-Werror] include/linux/printk.h:109:1: error: type defaults to ‘int’ in declaration of ‘asmlinkage’ [-Werror=implicit-int] include/linux/printk.h:110:1: error: ‘format’ attribute only applies to function types [-Werror=attributes] include/linux/printk.h:110:1: error: expected ‘,’ or ‘;’ before ‘int’ include/linux/printk.h:114:1: error: data definition has no type or storage class [-Werror] include/linux/printk.h:114:1: error: type defaults to ‘int’ in declaration of ‘asmlinkage’ [-Werror=implicit-int] include/linux/printk.h:115:1: error: ‘format’ attribute only applies to function types [-Werror=attributes] include/linux/printk.h:115:1: error: expected ‘,’ or ‘;’ before ‘int’ include/linux/printk.h:117:1: error: data definition has no type or storage class [-Werror] include/linux/printk.h:117:1: error: type defaults to ‘int’ in declaration of ‘asmlinkage’ [-Werror=implicit-int] include/linux/printk.h:118:1: error: ‘format’ attribute only applies to function types [-Werror=attributes] include/linux/printk.h:118:1: error: ‘__cold__’ attribute ignored [-Werror=attributes] include/linux/printk.h:118:1: error: expected ‘,’ or ‘;’ before ‘asmlinkage’ include/linux/printk.h:122:1: error: data definition has no type or storage class [-Werror] include/linux/printk.h:122:1: error: type defaults to ‘int’ in declaration of ‘asmlinkage’ [-Werror=implicit-int] include/linux/printk.h:123:1: error: ‘format’ attribute only applies to function types [-Werror=attributes] include/linux/printk.h:123:1: error: ‘__cold__’ attribute ignored [-Werror=attributes] include/linux/printk.h:123:1: error: expected ‘,’ or ‘;’ before ‘int’ In file included from include/linux/kernel.h:14:0, from include/linux/sched.h:15, from arch/mips/kernel/idle.c:18: include/linux/dynamic_debug.h: In function ‘ddebug_dyndbg_module_param_cb’: include/linux/dynamic_debug.h:124:3: error: implicit declaration of function ‘printk’ [-Werror=implicit-function-declaration] Fixed by including . Signed-off-by: Ralf Baechle --- include/linux/printk.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/printk.h b/include/linux/printk.h index 6af944ab38f0..22c7052e9372 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -4,6 +4,7 @@ #include #include #include +#include extern const char linux_banner[]; extern const char linux_proc_banner[]; -- cgit v1.2.3 From 2a7851bffb008ff4882eee673da74718997b4265 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 17 May 2013 03:56:10 +0000 Subject: netfilter: add nf_ipv6_ops hook to fix xt_addrtype with IPv6 Quoting https://bugzilla.netfilter.org/show_bug.cgi?id=812: [ ip6tables -m addrtype ] When I tried to use in the nat/PREROUTING it messes up the routing cache even if the rule didn't matched at all. [..] If I remove the --limit-iface-in from the non-working scenario, so just use the -m addrtype --dst-type LOCAL it works! This happens when LOCAL type matching is requested with --limit-iface-in, and the default ipv6 route is via the interface the packet we test arrived on. Because xt_addrtype uses ip6_route_output, the ipv6 routing implementation creates an unwanted cached entry, and the packet won't make it to the real/expected destination. Silently ignoring --limit-iface-in makes the routing work but it breaks rule matching (--dst-type LOCAL with limit-iface-in is supposed to only match if the dst address is configured on the incoming interface; without --limit-iface-in it will match if the address is reachable via lo). The test should call ipv6_chk_addr() instead. However, this would add a link-time dependency on ipv6. There are two possible solutions: 1) Revert the commit that moved ipt_addrtype to xt_addrtype, and put ipv6 specific code into ip6t_addrtype. 2) add new "nf_ipv6_ops" struct to register pointers to ipv6 functions. While the former might seem preferable, Pablo pointed out that there are more xt modules with link-time dependeny issues regarding ipv6, so lets go for 2). Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_ipv6.h | 16 ++++++++++++++++ include/net/addrconf.h | 2 +- net/ipv6/addrconf.c | 2 +- net/ipv6/netfilter.c | 7 +++++++ net/netfilter/core.c | 2 ++ net/netfilter/xt_addrtype.c | 27 ++++++++++++++++----------- 6 files changed, 43 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index 98ffb54988b6..2d4df6ce043e 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -17,6 +17,22 @@ extern __sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook, extern int ipv6_netfilter_init(void); extern void ipv6_netfilter_fini(void); + +/* + * Hook functions for ipv6 to allow xt_* modules to be built-in even + * if IPv6 is a module. + */ +struct nf_ipv6_ops { + int (*chk_addr)(struct net *net, const struct in6_addr *addr, + const struct net_device *dev, int strict); +}; + +extern const struct nf_ipv6_ops __rcu *nf_ipv6_ops; +static inline const struct nf_ipv6_ops *nf_get_ipv6_ops(void) +{ + return rcu_dereference(nf_ipv6_ops); +} + #else /* CONFIG_NETFILTER */ static inline int ipv6_netfilter_init(void) { return 0; } static inline void ipv6_netfilter_fini(void) { return; } diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 84a6440f1f19..21f702704f24 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -65,7 +65,7 @@ extern int addrconf_set_dstaddr(struct net *net, extern int ipv6_chk_addr(struct net *net, const struct in6_addr *addr, - struct net_device *dev, + const struct net_device *dev, int strict); #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index d1ab6ab29a55..d1b2d8034b54 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1487,7 +1487,7 @@ static int ipv6_count_addresses(struct inet6_dev *idev) } int ipv6_chk_addr(struct net *net, const struct in6_addr *addr, - struct net_device *dev, int strict) + const struct net_device *dev, int strict) { struct inet6_ifaddr *ifp; unsigned int hash = inet6_addr_hash(addr); diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 72836f40b730..95f3f1da0d7f 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -186,6 +187,10 @@ static __sum16 nf_ip6_checksum_partial(struct sk_buff *skb, unsigned int hook, return csum; }; +static const struct nf_ipv6_ops ipv6ops = { + .chk_addr = ipv6_chk_addr, +}; + static const struct nf_afinfo nf_ip6_afinfo = { .family = AF_INET6, .checksum = nf_ip6_checksum, @@ -198,6 +203,7 @@ static const struct nf_afinfo nf_ip6_afinfo = { int __init ipv6_netfilter_init(void) { + RCU_INIT_POINTER(nf_ipv6_ops, &ipv6ops); return nf_register_afinfo(&nf_ip6_afinfo); } @@ -206,5 +212,6 @@ int __init ipv6_netfilter_init(void) */ void ipv6_netfilter_fini(void) { + RCU_INIT_POINTER(nf_ipv6_ops, NULL); nf_unregister_afinfo(&nf_ip6_afinfo); } diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 07c865a31a3d..857ca9f35177 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -30,6 +30,8 @@ static DEFINE_MUTEX(afinfo_mutex); const struct nf_afinfo __rcu *nf_afinfo[NFPROTO_NUMPROTO] __read_mostly; EXPORT_SYMBOL(nf_afinfo); +const struct nf_ipv6_ops __rcu *nf_ipv6_ops __read_mostly; +EXPORT_SYMBOL_GPL(nf_ipv6_ops); int nf_register_afinfo(const struct nf_afinfo *afinfo) { diff --git a/net/netfilter/xt_addrtype.c b/net/netfilter/xt_addrtype.c index 49c5ff7f6dd6..68ff29f60867 100644 --- a/net/netfilter/xt_addrtype.c +++ b/net/netfilter/xt_addrtype.c @@ -22,6 +22,7 @@ #include #endif +#include #include #include @@ -33,12 +34,12 @@ MODULE_ALIAS("ip6t_addrtype"); #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) static u32 match_lookup_rt6(struct net *net, const struct net_device *dev, - const struct in6_addr *addr) + const struct in6_addr *addr, u16 mask) { const struct nf_afinfo *afinfo; struct flowi6 flow; struct rt6_info *rt; - u32 ret; + u32 ret = 0; int route_err; memset(&flow, 0, sizeof(flow)); @@ -49,12 +50,19 @@ static u32 match_lookup_rt6(struct net *net, const struct net_device *dev, rcu_read_lock(); afinfo = nf_get_afinfo(NFPROTO_IPV6); - if (afinfo != NULL) + if (afinfo != NULL) { + const struct nf_ipv6_ops *v6ops; + + if (dev && (mask & XT_ADDRTYPE_LOCAL)) { + v6ops = nf_get_ipv6_ops(); + if (v6ops && v6ops->chk_addr(net, addr, dev, true)) + ret = XT_ADDRTYPE_LOCAL; + } route_err = afinfo->route(net, (struct dst_entry **)&rt, - flowi6_to_flowi(&flow), !!dev); - else + flowi6_to_flowi(&flow), false); + } else { route_err = 1; - + } rcu_read_unlock(); if (route_err) @@ -62,15 +70,12 @@ static u32 match_lookup_rt6(struct net *net, const struct net_device *dev, if (rt->rt6i_flags & RTF_REJECT) ret = XT_ADDRTYPE_UNREACHABLE; - else - ret = 0; - if (rt->rt6i_flags & RTF_LOCAL) + if (dev == NULL && rt->rt6i_flags & RTF_LOCAL) ret |= XT_ADDRTYPE_LOCAL; if (rt->rt6i_flags & RTF_ANYCAST) ret |= XT_ADDRTYPE_ANYCAST; - dst_release(&rt->dst); return ret; } @@ -90,7 +95,7 @@ static bool match_type6(struct net *net, const struct net_device *dev, if ((XT_ADDRTYPE_LOCAL | XT_ADDRTYPE_ANYCAST | XT_ADDRTYPE_UNREACHABLE) & mask) - return !!(mask & match_lookup_rt6(net, dev, addr)); + return !!(mask & match_lookup_rt6(net, dev, addr, mask)); return true; } -- cgit v1.2.3 From 7805d000db30a3787a4c969bab6ae4d8a5fd8ce6 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 24 May 2013 10:50:24 +0900 Subject: cgroup: fix a subtle bug in descendant pre-order walk When cgroup_next_descendant_pre() initiates a walk, it checks whether the subtree root doesn't have any children and if not returns NULL. Later code assumes that the subtree isn't empty. This is broken because the subtree may become empty inbetween, which can lead to the traversal escaping the subtree by walking to the sibling of the subtree root. There's no reason to have the early exit path. Remove it along with the later assumption that the subtree isn't empty. This simplifies the code a bit and fixes the subtle bug. While at it, fix the comment of cgroup_for_each_descendant_pre() which was incorrectly referring to ->css_offline() instead of ->css_online(). Signed-off-by: Tejun Heo Reviewed-by: Michal Hocko Cc: stable@vger.kernel.org --- include/linux/cgroup.h | 2 +- kernel/cgroup.c | 9 +++------ 2 files changed, 4 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 5047355b9a0f..8bda1294c035 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -707,7 +707,7 @@ struct cgroup *cgroup_rightmost_descendant(struct cgroup *pos); * * If a subsystem synchronizes against the parent in its ->css_online() and * before starting iterating, and synchronizes against @pos on each - * iteration, any descendant cgroup which finished ->css_offline() is + * iteration, any descendant cgroup which finished ->css_online() is * guaranteed to be visible in the future iterations. * * In other words, the following guarantees that a descendant can't escape diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 38b136553044..31e9ef319070 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2954,11 +2954,8 @@ struct cgroup *cgroup_next_descendant_pre(struct cgroup *pos, WARN_ON_ONCE(!rcu_read_lock_held()); /* if first iteration, pretend we just visited @cgroup */ - if (!pos) { - if (list_empty(&cgroup->children)) - return NULL; + if (!pos) pos = cgroup; - } /* visit the first child if exists */ next = list_first_or_null_rcu(&pos->children, struct cgroup, sibling); @@ -2966,14 +2963,14 @@ struct cgroup *cgroup_next_descendant_pre(struct cgroup *pos, return next; /* no child, visit my or the closest ancestor's next sibling */ - do { + while (pos != cgroup) { next = list_entry_rcu(pos->sibling.next, struct cgroup, sibling); if (&next->sibling != &pos->parent->children) return next; pos = pos->parent; - } while (pos != cgroup); + } return NULL; } -- cgit v1.2.3 From a11650e11093ed57dca78bf16e7836517c599098 Mon Sep 17 00:00:00 2001 From: Alexandre Bounine Date: Fri, 24 May 2013 15:55:05 -0700 Subject: rapidio: make enumeration/discovery configurable Systems that use RapidIO fabric may need to implement their own enumeration and discovery methods which are better suitable for needs of a target application. The following set of patches is intended to simplify process of introduction of new RapidIO fabric enumeration/discovery methods. The first patch offers ability to add new RapidIO enumeration/discovery methods using kernel configuration options. This new configuration option mechanism allows to select statically linked or modular enumeration/discovery method(s) from the list of existing methods or use external module(s). This patch also updates the currently existing enumeration/discovery code to be used as a statically linked or modular method. The corresponding configuration option is named "Basic enumeration/discovery" method. This is the only one configuration option available today but new methods are expected to be introduced after adoption of provided patches. The second patch address a long time complaint of RapidIO subsystem users regarding fabric enumeration/discovery start sequence. Existing implementation offers only a boot-time enumeration/discovery start which requires synchronized boot of all endpoints in RapidIO network. While it works for small closed configurations with limited number of endpoints, using this approach in systems with large number of endpoints is quite challenging. To eliminate requirement for synchronized start the second patch introduces RapidIO enumeration/discovery start from user space. For compatibility with the existing RapidIO subsystem implementation, automatic boot time enumeration/discovery start can be configured in by specifying "rio-scan.scan=1" command line parameter if statically linked basic enumeration method is selected. This patch: Rework to implement RapidIO enumeration/discovery method selection combined with ability to use enumeration/discovery as a kernel module. This patch adds ability to introduce new RapidIO enumeration/discovery methods using kernel configuration options. Configuration option mechanism allows to select statically linked or modular enumeration/discovery method from the list of existing methods or use external modules. If a modular enumeration/discovery is selected each RapidIO mport device can have its own method attached to it. The existing enumeration/discovery code was updated to be used as statically linked or modular method. This configuration option is named "Basic enumeration/discovery" method. Several common routines have been moved from rio-scan.c to make them available to other enumeration methods and reduce number of exported symbols. Signed-off-by: Alexandre Bounine Cc: Matt Porter Cc: Li Yang Cc: Kumar Gala Cc: Andre van Herk Cc: Micha Nelissen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/rapidio/Kconfig | 20 ++++ drivers/rapidio/Makefile | 3 +- drivers/rapidio/rio-driver.c | 7 ++ drivers/rapidio/rio-scan.c | 166 ++++++++------------------------ drivers/rapidio/rio.c | 222 +++++++++++++++++++++++++++++++++++++++++-- drivers/rapidio/rio.h | 11 ++- include/linux/rio.h | 13 ++- include/linux/rio_drv.h | 1 + 8 files changed, 304 insertions(+), 139 deletions(-) (limited to 'include/linux') diff --git a/drivers/rapidio/Kconfig b/drivers/rapidio/Kconfig index 6194d35ebb97..5ab056494bbe 100644 --- a/drivers/rapidio/Kconfig +++ b/drivers/rapidio/Kconfig @@ -47,4 +47,24 @@ config RAPIDIO_DEBUG If you are unsure about this, say N here. +choice + prompt "Enumeration method" + depends on RAPIDIO + default RAPIDIO_ENUM_BASIC + help + There are different enumeration and discovery mechanisms offered + for RapidIO subsystem. You may select single built-in method or + or any number of methods to be built as modules. + Selecting a built-in method disables use of loadable methods. + + If unsure, select Basic built-in. + +config RAPIDIO_ENUM_BASIC + tristate "Basic" + help + This option includes basic RapidIO fabric enumeration and discovery + mechanism similar to one described in RapidIO specification Annex 1. + +endchoice + source "drivers/rapidio/switches/Kconfig" diff --git a/drivers/rapidio/Makefile b/drivers/rapidio/Makefile index ec3fb8121004..3036702ffe8b 100644 --- a/drivers/rapidio/Makefile +++ b/drivers/rapidio/Makefile @@ -1,7 +1,8 @@ # # Makefile for RapidIO interconnect services # -obj-y += rio.o rio-access.o rio-driver.o rio-scan.o rio-sysfs.o +obj-y += rio.o rio-access.o rio-driver.o rio-sysfs.o +obj-$(CONFIG_RAPIDIO_ENUM_BASIC) += rio-scan.o obj-$(CONFIG_RAPIDIO) += switches/ obj-$(CONFIG_RAPIDIO) += devices/ diff --git a/drivers/rapidio/rio-driver.c b/drivers/rapidio/rio-driver.c index 0f4a53bdaa3c..55850bb21480 100644 --- a/drivers/rapidio/rio-driver.c +++ b/drivers/rapidio/rio-driver.c @@ -164,6 +164,13 @@ void rio_unregister_driver(struct rio_driver *rdrv) driver_unregister(&rdrv->driver); } +void rio_attach_device(struct rio_dev *rdev) +{ + rdev->dev.bus = &rio_bus_type; + rdev->dev.parent = &rio_bus; +} +EXPORT_SYMBOL_GPL(rio_attach_device); + /** * rio_match_bus - Tell if a RIO device structure has a matching RIO driver device id structure * @dev: the standard device structure to match against diff --git a/drivers/rapidio/rio-scan.c b/drivers/rapidio/rio-scan.c index a965acd3c0e4..7bdc67419cc3 100644 --- a/drivers/rapidio/rio-scan.c +++ b/drivers/rapidio/rio-scan.c @@ -37,12 +37,8 @@ #include "rio.h" -LIST_HEAD(rio_devices); - static void rio_init_em(struct rio_dev *rdev); -DEFINE_SPINLOCK(rio_global_list_lock); - static int next_destid = 0; static int next_comptag = 1; @@ -326,127 +322,6 @@ static int rio_is_switch(struct rio_dev *rdev) return 0; } -/** - * rio_switch_init - Sets switch operations for a particular vendor switch - * @rdev: RIO device - * @do_enum: Enumeration/Discovery mode flag - * - * Searches the RIO switch ops table for known switch types. If the vid - * and did match a switch table entry, then call switch initialization - * routine to setup switch-specific routines. - */ -static void rio_switch_init(struct rio_dev *rdev, int do_enum) -{ - struct rio_switch_ops *cur = __start_rio_switch_ops; - struct rio_switch_ops *end = __end_rio_switch_ops; - - while (cur < end) { - if ((cur->vid == rdev->vid) && (cur->did == rdev->did)) { - pr_debug("RIO: calling init routine for %s\n", - rio_name(rdev)); - cur->init_hook(rdev, do_enum); - break; - } - cur++; - } - - if ((cur >= end) && (rdev->pef & RIO_PEF_STD_RT)) { - pr_debug("RIO: adding STD routing ops for %s\n", - rio_name(rdev)); - rdev->rswitch->add_entry = rio_std_route_add_entry; - rdev->rswitch->get_entry = rio_std_route_get_entry; - rdev->rswitch->clr_table = rio_std_route_clr_table; - } - - if (!rdev->rswitch->add_entry || !rdev->rswitch->get_entry) - printk(KERN_ERR "RIO: missing routing ops for %s\n", - rio_name(rdev)); -} - -/** - * rio_add_device- Adds a RIO device to the device model - * @rdev: RIO device - * - * Adds the RIO device to the global device list and adds the RIO - * device to the RIO device list. Creates the generic sysfs nodes - * for an RIO device. - */ -static int rio_add_device(struct rio_dev *rdev) -{ - int err; - - err = device_add(&rdev->dev); - if (err) - return err; - - spin_lock(&rio_global_list_lock); - list_add_tail(&rdev->global_list, &rio_devices); - spin_unlock(&rio_global_list_lock); - - rio_create_sysfs_dev_files(rdev); - - return 0; -} - -/** - * rio_enable_rx_tx_port - enable input receiver and output transmitter of - * given port - * @port: Master port associated with the RIO network - * @local: local=1 select local port otherwise a far device is reached - * @destid: Destination ID of the device to check host bit - * @hopcount: Number of hops to reach the target - * @port_num: Port (-number on switch) to enable on a far end device - * - * Returns 0 or 1 from on General Control Command and Status Register - * (EXT_PTR+0x3C) - */ -inline int rio_enable_rx_tx_port(struct rio_mport *port, - int local, u16 destid, - u8 hopcount, u8 port_num) { -#ifdef CONFIG_RAPIDIO_ENABLE_RX_TX_PORTS - u32 regval; - u32 ext_ftr_ptr; - - /* - * enable rx input tx output port - */ - pr_debug("rio_enable_rx_tx_port(local = %d, destid = %d, hopcount = " - "%d, port_num = %d)\n", local, destid, hopcount, port_num); - - ext_ftr_ptr = rio_mport_get_physefb(port, local, destid, hopcount); - - if (local) { - rio_local_read_config_32(port, ext_ftr_ptr + - RIO_PORT_N_CTL_CSR(0), - ®val); - } else { - if (rio_mport_read_config_32(port, destid, hopcount, - ext_ftr_ptr + RIO_PORT_N_CTL_CSR(port_num), ®val) < 0) - return -EIO; - } - - if (regval & RIO_PORT_N_CTL_P_TYP_SER) { - /* serial */ - regval = regval | RIO_PORT_N_CTL_EN_RX_SER - | RIO_PORT_N_CTL_EN_TX_SER; - } else { - /* parallel */ - regval = regval | RIO_PORT_N_CTL_EN_RX_PAR - | RIO_PORT_N_CTL_EN_TX_PAR; - } - - if (local) { - rio_local_write_config_32(port, ext_ftr_ptr + - RIO_PORT_N_CTL_CSR(0), regval); - } else { - if (rio_mport_write_config_32(port, destid, hopcount, - ext_ftr_ptr + RIO_PORT_N_CTL_CSR(port_num), regval) < 0) - return -EIO; - } -#endif - return 0; -} - /** * rio_setup_device- Allocates and sets up a RIO device * @net: RIO network @@ -587,8 +462,7 @@ static struct rio_dev *rio_setup_device(struct rio_net *net, rdev->destid); } - rdev->dev.bus = &rio_bus_type; - rdev->dev.parent = &rio_bus; + rio_attach_device(rdev); device_initialize(&rdev->dev); rdev->dev.release = rio_release_dev; @@ -1421,3 +1295,41 @@ enum_done: bail: return -EBUSY; } + +static struct rio_scan rio_scan_ops = { + .enumerate = rio_enum_mport, + .discover = rio_disc_mport, +}; + +static bool scan; +module_param(scan, bool, 0); +MODULE_PARM_DESC(scan, "Start RapidIO network enumeration/discovery " + "(default = 0)"); + +/** + * rio_basic_attach: + * + * When this enumeration/discovery method is loaded as a module this function + * registers its specific enumeration and discover routines for all available + * RapidIO mport devices. The "scan" command line parameter controls ability of + * the module to start RapidIO enumeration/discovery automatically. + * + * Returns 0 for success or -EIO if unable to register itself. + * + * This enumeration/discovery method cannot be unloaded and therefore does not + * provide a matching cleanup_module routine. + */ + +static int __init rio_basic_attach(void) +{ + if (rio_register_scan(RIO_MPORT_ANY, &rio_scan_ops)) + return -EIO; + if (scan) + rio_init_mports(); + return 0; +} + +late_initcall(rio_basic_attach); + +MODULE_DESCRIPTION("Basic RapidIO enumeration/discovery"); +MODULE_LICENSE("GPL"); diff --git a/drivers/rapidio/rio.c b/drivers/rapidio/rio.c index d553b5d13722..6e75dda34799 100644 --- a/drivers/rapidio/rio.c +++ b/drivers/rapidio/rio.c @@ -31,7 +31,11 @@ #include "rio.h" +static LIST_HEAD(rio_devices); +static DEFINE_SPINLOCK(rio_global_list_lock); + static LIST_HEAD(rio_mports); +static DEFINE_MUTEX(rio_mport_list_lock); static unsigned char next_portid; static DEFINE_SPINLOCK(rio_mmap_lock); @@ -52,6 +56,32 @@ u16 rio_local_get_device_id(struct rio_mport *port) return (RIO_GET_DID(port->sys_size, result)); } +/** + * rio_add_device- Adds a RIO device to the device model + * @rdev: RIO device + * + * Adds the RIO device to the global device list and adds the RIO + * device to the RIO device list. Creates the generic sysfs nodes + * for an RIO device. + */ +int rio_add_device(struct rio_dev *rdev) +{ + int err; + + err = device_add(&rdev->dev); + if (err) + return err; + + spin_lock(&rio_global_list_lock); + list_add_tail(&rdev->global_list, &rio_devices); + spin_unlock(&rio_global_list_lock); + + rio_create_sysfs_dev_files(rdev); + + return 0; +} +EXPORT_SYMBOL_GPL(rio_add_device); + /** * rio_request_inb_mbox - request inbound mailbox service * @mport: RIO master port from which to allocate the mailbox resource @@ -489,6 +519,7 @@ rio_mport_get_physefb(struct rio_mport *port, int local, return ext_ftr_ptr; } +EXPORT_SYMBOL_GPL(rio_mport_get_physefb); /** * rio_get_comptag - Begin or continue searching for a RIO device by component tag @@ -521,6 +552,7 @@ exit: spin_unlock(&rio_global_list_lock); return rdev; } +EXPORT_SYMBOL_GPL(rio_get_comptag); /** * rio_set_port_lockout - Sets/clears LOCKOUT bit (RIO EM 1.3) for a switch port. @@ -545,6 +577,107 @@ int rio_set_port_lockout(struct rio_dev *rdev, u32 pnum, int lock) regval); return 0; } +EXPORT_SYMBOL_GPL(rio_set_port_lockout); + +/** + * rio_switch_init - Sets switch operations for a particular vendor switch + * @rdev: RIO device + * @do_enum: Enumeration/Discovery mode flag + * + * Searches the RIO switch ops table for known switch types. If the vid + * and did match a switch table entry, then call switch initialization + * routine to setup switch-specific routines. + */ +void rio_switch_init(struct rio_dev *rdev, int do_enum) +{ + struct rio_switch_ops *cur = __start_rio_switch_ops; + struct rio_switch_ops *end = __end_rio_switch_ops; + + while (cur < end) { + if ((cur->vid == rdev->vid) && (cur->did == rdev->did)) { + pr_debug("RIO: calling init routine for %s\n", + rio_name(rdev)); + cur->init_hook(rdev, do_enum); + break; + } + cur++; + } + + if ((cur >= end) && (rdev->pef & RIO_PEF_STD_RT)) { + pr_debug("RIO: adding STD routing ops for %s\n", + rio_name(rdev)); + rdev->rswitch->add_entry = rio_std_route_add_entry; + rdev->rswitch->get_entry = rio_std_route_get_entry; + rdev->rswitch->clr_table = rio_std_route_clr_table; + } + + if (!rdev->rswitch->add_entry || !rdev->rswitch->get_entry) + printk(KERN_ERR "RIO: missing routing ops for %s\n", + rio_name(rdev)); +} +EXPORT_SYMBOL_GPL(rio_switch_init); + +/** + * rio_enable_rx_tx_port - enable input receiver and output transmitter of + * given port + * @port: Master port associated with the RIO network + * @local: local=1 select local port otherwise a far device is reached + * @destid: Destination ID of the device to check host bit + * @hopcount: Number of hops to reach the target + * @port_num: Port (-number on switch) to enable on a far end device + * + * Returns 0 or 1 from on General Control Command and Status Register + * (EXT_PTR+0x3C) + */ +int rio_enable_rx_tx_port(struct rio_mport *port, + int local, u16 destid, + u8 hopcount, u8 port_num) +{ +#ifdef CONFIG_RAPIDIO_ENABLE_RX_TX_PORTS + u32 regval; + u32 ext_ftr_ptr; + + /* + * enable rx input tx output port + */ + pr_debug("rio_enable_rx_tx_port(local = %d, destid = %d, hopcount = " + "%d, port_num = %d)\n", local, destid, hopcount, port_num); + + ext_ftr_ptr = rio_mport_get_physefb(port, local, destid, hopcount); + + if (local) { + rio_local_read_config_32(port, ext_ftr_ptr + + RIO_PORT_N_CTL_CSR(0), + ®val); + } else { + if (rio_mport_read_config_32(port, destid, hopcount, + ext_ftr_ptr + RIO_PORT_N_CTL_CSR(port_num), ®val) < 0) + return -EIO; + } + + if (regval & RIO_PORT_N_CTL_P_TYP_SER) { + /* serial */ + regval = regval | RIO_PORT_N_CTL_EN_RX_SER + | RIO_PORT_N_CTL_EN_TX_SER; + } else { + /* parallel */ + regval = regval | RIO_PORT_N_CTL_EN_RX_PAR + | RIO_PORT_N_CTL_EN_TX_PAR; + } + + if (local) { + rio_local_write_config_32(port, ext_ftr_ptr + + RIO_PORT_N_CTL_CSR(0), regval); + } else { + if (rio_mport_write_config_32(port, destid, hopcount, + ext_ftr_ptr + RIO_PORT_N_CTL_CSR(port_num), regval) < 0) + return -EIO; + } +#endif + return 0; +} +EXPORT_SYMBOL_GPL(rio_enable_rx_tx_port); + /** * rio_chk_dev_route - Validate route to the specified device. @@ -610,6 +743,7 @@ rio_mport_chk_dev_access(struct rio_mport *mport, u16 destid, u8 hopcount) return 0; } +EXPORT_SYMBOL_GPL(rio_mport_chk_dev_access); /** * rio_chk_dev_access - Validate access to the specified device. @@ -941,6 +1075,7 @@ rio_mport_get_efb(struct rio_mport *port, int local, u16 destid, return RIO_GET_BLOCK_ID(reg_val); } } +EXPORT_SYMBOL_GPL(rio_mport_get_efb); /** * rio_mport_get_feature - query for devices' extended features @@ -997,6 +1132,7 @@ rio_mport_get_feature(struct rio_mport * port, int local, u16 destid, return 0; } +EXPORT_SYMBOL_GPL(rio_mport_get_feature); /** * rio_get_asm - Begin or continue searching for a RIO device by vid/did/asm_vid/asm_did @@ -1246,6 +1382,71 @@ EXPORT_SYMBOL_GPL(rio_dma_prep_slave_sg); #endif /* CONFIG_RAPIDIO_DMA_ENGINE */ +/** + * rio_register_scan - enumeration/discovery method registration interface + * @mport_id: mport device ID for which fabric scan routine has to be set + * (RIO_MPORT_ANY = set for all available mports) + * @scan_ops: enumeration/discovery control structure + * + * Assigns enumeration or discovery method to the specified mport device (or all + * available mports if RIO_MPORT_ANY is specified). + * Returns error if the mport already has an enumerator attached to it. + * In case of RIO_MPORT_ANY ignores ports with valid scan routines and returns + * an error if was unable to find at least one available mport. + */ +int rio_register_scan(int mport_id, struct rio_scan *scan_ops) +{ + struct rio_mport *port; + int rc = -EBUSY; + + mutex_lock(&rio_mport_list_lock); + list_for_each_entry(port, &rio_mports, node) { + if (port->id == mport_id || mport_id == RIO_MPORT_ANY) { + if (port->nscan && mport_id == RIO_MPORT_ANY) + continue; + else if (port->nscan) + break; + + port->nscan = scan_ops; + rc = 0; + + if (mport_id != RIO_MPORT_ANY) + break; + } + } + mutex_unlock(&rio_mport_list_lock); + + return rc; +} +EXPORT_SYMBOL_GPL(rio_register_scan); + +/** + * rio_unregister_scan - removes enumeration/discovery method from mport + * @mport_id: mport device ID for which fabric scan routine has to be + * unregistered (RIO_MPORT_ANY = set for all available mports) + * + * Removes enumeration or discovery method assigned to the specified mport + * device (or all available mports if RIO_MPORT_ANY is specified). + */ +int rio_unregister_scan(int mport_id) +{ + struct rio_mport *port; + + mutex_lock(&rio_mport_list_lock); + list_for_each_entry(port, &rio_mports, node) { + if (port->id == mport_id || mport_id == RIO_MPORT_ANY) { + if (port->nscan) + port->nscan = NULL; + if (mport_id != RIO_MPORT_ANY) + break; + } + } + mutex_unlock(&rio_mport_list_lock); + + return 0; +} +EXPORT_SYMBOL_GPL(rio_unregister_scan); + static void rio_fixup_device(struct rio_dev *dev) { } @@ -1274,7 +1475,7 @@ static void disc_work_handler(struct work_struct *_work) work = container_of(_work, struct rio_disc_work, work); pr_debug("RIO: discovery work for mport %d %s\n", work->mport->id, work->mport->name); - rio_disc_mport(work->mport); + work->mport->nscan->discover(work->mport); } int rio_init_mports(void) @@ -1290,12 +1491,15 @@ int rio_init_mports(void) * First, run enumerations and check if we need to perform discovery * on any of the registered mports. */ + mutex_lock(&rio_mport_list_lock); list_for_each_entry(port, &rio_mports, node) { - if (port->host_deviceid >= 0) - rio_enum_mport(port); - else + if (port->host_deviceid >= 0) { + if (port->nscan) + port->nscan->enumerate(port); + } else n++; } + mutex_unlock(&rio_mport_list_lock); if (!n) goto no_disc; @@ -1322,14 +1526,16 @@ int rio_init_mports(void) } n = 0; + mutex_lock(&rio_mport_list_lock); list_for_each_entry(port, &rio_mports, node) { - if (port->host_deviceid < 0) { + if (port->host_deviceid < 0 && port->nscan) { work[n].mport = port; INIT_WORK(&work[n].work, disc_work_handler); queue_work(rio_wq, &work[n].work); n++; } } + mutex_unlock(&rio_mport_list_lock); flush_workqueue(rio_wq); pr_debug("RIO: destroy discovery workqueue\n"); @@ -1342,8 +1548,6 @@ no_disc: return 0; } -device_initcall_sync(rio_init_mports); - static int hdids[RIO_MAX_MPORTS + 1]; static int rio_get_hdid(int index) @@ -1371,7 +1575,10 @@ int rio_register_mport(struct rio_mport *port) port->id = next_portid++; port->host_deviceid = rio_get_hdid(port->id); + port->nscan = NULL; + mutex_lock(&rio_mport_list_lock); list_add_tail(&port->node, &rio_mports); + mutex_unlock(&rio_mport_list_lock); return 0; } @@ -1386,3 +1593,4 @@ EXPORT_SYMBOL_GPL(rio_request_inb_mbox); EXPORT_SYMBOL_GPL(rio_release_inb_mbox); EXPORT_SYMBOL_GPL(rio_request_outb_mbox); EXPORT_SYMBOL_GPL(rio_release_outb_mbox); +EXPORT_SYMBOL_GPL(rio_init_mports); diff --git a/drivers/rapidio/rio.h b/drivers/rapidio/rio.h index b1af414f15e6..0afdf482517e 100644 --- a/drivers/rapidio/rio.h +++ b/drivers/rapidio/rio.h @@ -15,6 +15,7 @@ #include #define RIO_MAX_CHK_RETRY 3 +#define RIO_MPORT_ANY (-1) /* Functions internal to the RIO core code */ @@ -27,8 +28,6 @@ extern u32 rio_mport_get_efb(struct rio_mport *port, int local, u16 destid, extern int rio_mport_chk_dev_access(struct rio_mport *mport, u16 destid, u8 hopcount); extern int rio_create_sysfs_dev_files(struct rio_dev *rdev); -extern int rio_enum_mport(struct rio_mport *mport); -extern int rio_disc_mport(struct rio_mport *mport); extern int rio_std_route_add_entry(struct rio_mport *mport, u16 destid, u8 hopcount, u16 table, u16 route_destid, u8 route_port); @@ -39,10 +38,16 @@ extern int rio_std_route_clr_table(struct rio_mport *mport, u16 destid, u8 hopcount, u16 table); extern int rio_set_port_lockout(struct rio_dev *rdev, u32 pnum, int lock); extern struct rio_dev *rio_get_comptag(u32 comp_tag, struct rio_dev *from); +extern int rio_add_device(struct rio_dev *rdev); +extern void rio_switch_init(struct rio_dev *rdev, int do_enum); +extern int rio_enable_rx_tx_port(struct rio_mport *port, int local, u16 destid, + u8 hopcount, u8 port_num); +extern int rio_register_scan(int mport_id, struct rio_scan *scan_ops); +extern int rio_unregister_scan(int mport_id); +extern void rio_attach_device(struct rio_dev *rdev); /* Structures internal to the RIO core code */ extern struct device_attribute rio_dev_attrs[]; -extern spinlock_t rio_global_list_lock; extern struct rio_switch_ops __start_rio_switch_ops[]; extern struct rio_switch_ops __end_rio_switch_ops[]; diff --git a/include/linux/rio.h b/include/linux/rio.h index a3e784278667..cd3796ee7410 100644 --- a/include/linux/rio.h +++ b/include/linux/rio.h @@ -83,7 +83,6 @@ extern struct bus_type rio_bus_type; extern struct device rio_bus; -extern struct list_head rio_devices; /* list of all devices */ struct rio_mport; struct rio_dev; @@ -237,6 +236,7 @@ enum rio_phy_type { * @name: Port name string * @priv: Master port private data * @dma: DMA device associated with mport + * @nscan: RapidIO network enumeration/discovery operations */ struct rio_mport { struct list_head dbells; /* list of doorbell events */ @@ -262,6 +262,7 @@ struct rio_mport { #ifdef CONFIG_RAPIDIO_DMA_ENGINE struct dma_device dma; #endif + struct rio_scan *nscan; }; struct rio_id_table { @@ -460,6 +461,16 @@ static inline struct rio_mport *dma_to_mport(struct dma_device *ddev) } #endif /* CONFIG_RAPIDIO_DMA_ENGINE */ +/** + * struct rio_scan - RIO enumeration and discovery operations + * @enumerate: Callback to perform RapidIO fabric enumeration. + * @discover: Callback to perform RapidIO fabric discovery. + */ +struct rio_scan { + int (*enumerate)(struct rio_mport *mport); + int (*discover)(struct rio_mport *mport); +}; + /* Architecture and hardware-specific functions */ extern int rio_register_mport(struct rio_mport *); extern int rio_open_inb_mbox(struct rio_mport *, void *, int, int); diff --git a/include/linux/rio_drv.h b/include/linux/rio_drv.h index b75c05920ab5..5059994fe297 100644 --- a/include/linux/rio_drv.h +++ b/include/linux/rio_drv.h @@ -433,5 +433,6 @@ extern u16 rio_local_get_device_id(struct rio_mport *port); extern struct rio_dev *rio_get_device(u16 vid, u16 did, struct rio_dev *from); extern struct rio_dev *rio_get_asm(u16 vid, u16 did, u16 asm_vid, u16 asm_did, struct rio_dev *from); +extern int rio_init_mports(void); #endif /* LINUX_RIO_DRV_H */ -- cgit v1.2.3 From bc8fcfea18249640f2728c46d70999dcb7e4dc49 Mon Sep 17 00:00:00 2001 From: Alexandre Bounine Date: Fri, 24 May 2013 15:55:06 -0700 Subject: rapidio: add enumeration/discovery start from user space Add RapidIO enumeration/discovery start from user space. User space start allows to defer RapidIO fabric scan until the moment when all participating endpoints are initialized avoiding mandatory synchronized start of all endpoints (which may be challenging in systems with large number of RapidIO endpoints). Signed-off-by: Alexandre Bounine Cc: Matt Porter Cc: Li Yang Cc: Kumar Gala Cc: Andre van Herk Cc: Micha Nelissen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/rapidio/rio-driver.c | 1 + drivers/rapidio/rio-scan.c | 24 ++++++++++++++++++++--- drivers/rapidio/rio-sysfs.c | 45 ++++++++++++++++++++++++++++++++++++++++++++ drivers/rapidio/rio.c | 28 +++++++++++++++++++++++++-- drivers/rapidio/rio.h | 2 ++ include/linux/rio.h | 9 +++++++-- 6 files changed, 102 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/rapidio/rio-driver.c b/drivers/rapidio/rio-driver.c index 55850bb21480..a0c875563d76 100644 --- a/drivers/rapidio/rio-driver.c +++ b/drivers/rapidio/rio-driver.c @@ -207,6 +207,7 @@ struct bus_type rio_bus_type = { .name = "rapidio", .match = rio_match_bus, .dev_attrs = rio_dev_attrs, + .bus_attrs = rio_bus_attrs, .probe = rio_device_probe, .remove = rio_device_remove, }; diff --git a/drivers/rapidio/rio-scan.c b/drivers/rapidio/rio-scan.c index 7bdc67419cc3..4c15dbf81087 100644 --- a/drivers/rapidio/rio-scan.c +++ b/drivers/rapidio/rio-scan.c @@ -1134,19 +1134,30 @@ static void rio_pw_enable(struct rio_mport *port, int enable) /** * rio_enum_mport- Start enumeration through a master port * @mport: Master port to send transactions + * @flags: Enumeration control flags * * Starts the enumeration process. If somebody has enumerated our * master port device, then give up. If not and we have an active * link, then start recursive peer enumeration. Returns %0 if * enumeration succeeds or %-EBUSY if enumeration fails. */ -int rio_enum_mport(struct rio_mport *mport) +int rio_enum_mport(struct rio_mport *mport, u32 flags) { struct rio_net *net = NULL; int rc = 0; printk(KERN_INFO "RIO: enumerate master port %d, %s\n", mport->id, mport->name); + + /* + * To avoid multiple start requests (repeat enumeration is not supported + * by this method) check if enumeration/discovery was performed for this + * mport: if mport was added into the list of mports for a net exit + * with error. + */ + if (mport->nnode.next || mport->nnode.prev) + return -EBUSY; + /* If somebody else enumerated our master port device, bail. */ if (rio_enum_host(mport) < 0) { printk(KERN_INFO @@ -1236,14 +1247,16 @@ static void rio_build_route_tables(struct rio_net *net) /** * rio_disc_mport- Start discovery through a master port * @mport: Master port to send transactions + * @flags: discovery control flags * * Starts the discovery process. If we have an active link, - * then wait for the signal that enumeration is complete. + * then wait for the signal that enumeration is complete (if wait + * is allowed). * When enumeration completion is signaled, start recursive * peer discovery. Returns %0 if discovery succeeds or %-EBUSY * on failure. */ -int rio_disc_mport(struct rio_mport *mport) +int rio_disc_mport(struct rio_mport *mport, u32 flags) { struct rio_net *net = NULL; unsigned long to_end; @@ -1253,6 +1266,11 @@ int rio_disc_mport(struct rio_mport *mport) /* If master port has an active link, allocate net and discover peers */ if (rio_mport_is_active(mport)) { + if (rio_enum_complete(mport)) + goto enum_done; + else if (flags & RIO_SCAN_ENUM_NO_WAIT) + return -EAGAIN; + pr_debug("RIO: wait for enumeration to complete...\n"); to_end = jiffies + CONFIG_RAPIDIO_DISC_TIMEOUT * HZ; diff --git a/drivers/rapidio/rio-sysfs.c b/drivers/rapidio/rio-sysfs.c index 4dbe360989be..66d4acd5e18f 100644 --- a/drivers/rapidio/rio-sysfs.c +++ b/drivers/rapidio/rio-sysfs.c @@ -285,3 +285,48 @@ void rio_remove_sysfs_dev_files(struct rio_dev *rdev) rdev->rswitch->sw_sysfs(rdev, RIO_SW_SYSFS_REMOVE); } } + +static ssize_t bus_scan_store(struct bus_type *bus, const char *buf, + size_t count) +{ + long val; + struct rio_mport *port = NULL; + int rc; + + if (kstrtol(buf, 0, &val) < 0) + return -EINVAL; + + if (val == RIO_MPORT_ANY) { + rc = rio_init_mports(); + goto exit; + } + + if (val < 0 || val >= RIO_MAX_MPORTS) + return -EINVAL; + + port = rio_find_mport((int)val); + + if (!port) { + pr_debug("RIO: %s: mport_%d not available\n", + __func__, (int)val); + return -EINVAL; + } + + if (!port->nscan) + return -EINVAL; + + if (port->host_deviceid >= 0) + rc = port->nscan->enumerate(port, 0); + else + rc = port->nscan->discover(port, RIO_SCAN_ENUM_NO_WAIT); +exit: + if (!rc) + rc = count; + + return rc; +} + +struct bus_attribute rio_bus_attrs[] = { + __ATTR(scan, (S_IWUSR|S_IWGRP), NULL, bus_scan_store), + __ATTR_NULL +}; diff --git a/drivers/rapidio/rio.c b/drivers/rapidio/rio.c index 6e75dda34799..cb1c08996fbb 100644 --- a/drivers/rapidio/rio.c +++ b/drivers/rapidio/rio.c @@ -1382,6 +1382,30 @@ EXPORT_SYMBOL_GPL(rio_dma_prep_slave_sg); #endif /* CONFIG_RAPIDIO_DMA_ENGINE */ +/** + * rio_find_mport - find RIO mport by its ID + * @mport_id: number (ID) of mport device + * + * Given a RIO mport number, the desired mport is located + * in the global list of mports. If the mport is found, a pointer to its + * data structure is returned. If no mport is found, %NULL is returned. + */ +struct rio_mport *rio_find_mport(int mport_id) +{ + struct rio_mport *port; + + mutex_lock(&rio_mport_list_lock); + list_for_each_entry(port, &rio_mports, node) { + if (port->id == mport_id) + goto found; + } + port = NULL; +found: + mutex_unlock(&rio_mport_list_lock); + + return port; +} + /** * rio_register_scan - enumeration/discovery method registration interface * @mport_id: mport device ID for which fabric scan routine has to be set @@ -1475,7 +1499,7 @@ static void disc_work_handler(struct work_struct *_work) work = container_of(_work, struct rio_disc_work, work); pr_debug("RIO: discovery work for mport %d %s\n", work->mport->id, work->mport->name); - work->mport->nscan->discover(work->mport); + work->mport->nscan->discover(work->mport, 0); } int rio_init_mports(void) @@ -1495,7 +1519,7 @@ int rio_init_mports(void) list_for_each_entry(port, &rio_mports, node) { if (port->host_deviceid >= 0) { if (port->nscan) - port->nscan->enumerate(port); + port->nscan->enumerate(port, 0); } else n++; } diff --git a/drivers/rapidio/rio.h b/drivers/rapidio/rio.h index 0afdf482517e..c14f864dea5c 100644 --- a/drivers/rapidio/rio.h +++ b/drivers/rapidio/rio.h @@ -45,9 +45,11 @@ extern int rio_enable_rx_tx_port(struct rio_mport *port, int local, u16 destid, extern int rio_register_scan(int mport_id, struct rio_scan *scan_ops); extern int rio_unregister_scan(int mport_id); extern void rio_attach_device(struct rio_dev *rdev); +extern struct rio_mport *rio_find_mport(int mport_id); /* Structures internal to the RIO core code */ extern struct device_attribute rio_dev_attrs[]; +extern struct bus_attribute rio_bus_attrs[]; extern struct rio_switch_ops __start_rio_switch_ops[]; extern struct rio_switch_ops __end_rio_switch_ops[]; diff --git a/include/linux/rio.h b/include/linux/rio.h index cd3796ee7410..18e099342e6f 100644 --- a/include/linux/rio.h +++ b/include/linux/rio.h @@ -265,6 +265,11 @@ struct rio_mport { struct rio_scan *nscan; }; +/* + * Enumeration/discovery control flags + */ +#define RIO_SCAN_ENUM_NO_WAIT 0x00000001 /* Do not wait for enum completed */ + struct rio_id_table { u16 start; /* logical minimal id */ u32 max; /* max number of IDs in table */ @@ -467,8 +472,8 @@ static inline struct rio_mport *dma_to_mport(struct dma_device *ddev) * @discover: Callback to perform RapidIO fabric discovery. */ struct rio_scan { - int (*enumerate)(struct rio_mport *mport); - int (*discover)(struct rio_mport *mport); + int (*enumerate)(struct rio_mport *mport, u32 flags); + int (*discover)(struct rio_mport *mport, u32 flags); }; /* Architecture and hardware-specific functions */ -- cgit v1.2.3 From 4c663cfc523a88d97a8309b04a089c27dc57fd7e Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Fri, 24 May 2013 15:55:09 -0700 Subject: wait: fix false timeouts when using wait_event_timeout() Many callers of the wait_event_timeout() and wait_event_interruptible_timeout() expect that the return value will be positive if the specified condition becomes true before the timeout elapses. However, at the moment this isn't guaranteed. If the wake-up handler is delayed enough, the time remaining until timeout will be calculated as 0 - and passed back as a return value - even if the condition became true before the timeout has passed. Fix this by returning at least 1 if the condition becomes true. This semantic is in line with what wait_for_condition_timeout() does; see commit bb10ed09 ("sched: fix wait_for_completion_timeout() spurious failure under heavy load"). Daniel said "We have 3 instances of this bug in drm/i915. One case even where we switch between the interruptible and not interruptible wait_event_timeout variants, foolishly presuming they have the same semantics. I very much like this." One such bug is reported at https://bugs.freedesktop.org/show_bug.cgi?id=64133 Signed-off-by: Imre Deak Acked-by: Daniel Vetter Acked-by: David Howells Acked-by: Jens Axboe Cc: "Paul E. McKenney" Cc: Dave Jones Cc: Lukas Czerner Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/wait.h | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/wait.h b/include/linux/wait.h index ac38be2692d8..1133695eb067 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -217,6 +217,8 @@ do { \ if (!ret) \ break; \ } \ + if (!ret && (condition)) \ + ret = 1; \ finish_wait(&wq, &__wait); \ } while (0) @@ -233,8 +235,9 @@ do { \ * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * - * The function returns 0 if the @timeout elapsed, and the remaining - * jiffies if the condition evaluated to true before the timeout elapsed. + * The function returns 0 if the @timeout elapsed, or the remaining + * jiffies (at least 1) if the @condition evaluated to %true before + * the @timeout elapsed. */ #define wait_event_timeout(wq, condition, timeout) \ ({ \ @@ -302,6 +305,8 @@ do { \ ret = -ERESTARTSYS; \ break; \ } \ + if (!ret && (condition)) \ + ret = 1; \ finish_wait(&wq, &__wait); \ } while (0) @@ -318,9 +323,10 @@ do { \ * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * - * The function returns 0 if the @timeout elapsed, -ERESTARTSYS if it - * was interrupted by a signal, and the remaining jiffies otherwise - * if the condition evaluated to true before the timeout elapsed. + * Returns: + * 0 if the @timeout elapsed, -%ERESTARTSYS if it was interrupted by + * a signal, or the remaining jiffies (at least 1) if the @condition + * evaluated to %true before the @timeout elapsed. */ #define wait_event_interruptible_timeout(wq, condition, timeout) \ ({ \ -- cgit v1.2.3 From 7450231fb35492951e78a91b833fd935171f4e66 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 24 May 2013 15:55:20 -0700 Subject: linux/kernel.h: fix kernel-doc warning Fix kernel-doc warning in : Warning(include/linux/kernel.h:590): No description found for parameter 'ip' scripts/kernel-doc cannot handle macros, functions, or function prototypes between the function or macro that is being documented and its definition, so move these prototypes above the function that is being documented. Signed-off-by: Randy Dunlap Cc: Steven Rostedt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index e96329ceb28c..e9ef6d6b51d5 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -562,6 +562,9 @@ int __trace_bprintk(unsigned long ip, const char *fmt, ...); extern __printf(2, 3) int __trace_printk(unsigned long ip, const char *fmt, ...); +extern int __trace_bputs(unsigned long ip, const char *str); +extern int __trace_puts(unsigned long ip, const char *str, int size); + /** * trace_puts - write a string into the ftrace buffer * @str: the string to record @@ -587,8 +590,6 @@ int __trace_printk(unsigned long ip, const char *fmt, ...); * (1 when __trace_bputs is used, strlen(str) when __trace_puts is used) */ -extern int __trace_bputs(unsigned long ip, const char *str); -extern int __trace_puts(unsigned long ip, const char *str, int size); #define trace_puts(str) ({ \ static const char *trace_printk_fmt \ __attribute__((section("__trace_printk_fmt"))) = \ -- cgit v1.2.3 From 26cb63ad11e04047a64309362674bcbbd6a6f246 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 28 May 2013 10:55:48 +0200 Subject: perf: Fix perf mmap bugs Vince reported a problem found by his perf specific trinity fuzzer. Al noticed 2 problems with perf's mmap(): - it has issues against fork() since we use vma->vm_mm for accounting. - it has an rb refcount leak on double mmap(). We fix the issues against fork() by using VM_DONTCOPY; I don't think there's code out there that uses this; we didn't hear about weird accounting problems/crashes. If we do need this to work, the previously proposed VM_PINNED could make this work. Aside from the rb reference leak spotted by Al, Vince's example prog was indeed doing a double mmap() through the use of perf_event_set_output(). This exposes another problem, since we now have 2 events with one buffer, the accounting gets screwy because we account per event. Fix this by making the buffer responsible for its own accounting. Reported-by: Vince Weaver Signed-off-by: Peter Zijlstra Cc: Al Viro Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Link: http://lkml.kernel.org/r/20130528085548.GA12193@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 3 +-- kernel/events/core.c | 37 ++++++++++++++++++++----------------- kernel/events/internal.h | 3 +++ 3 files changed, 24 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index f463a46424e2..c5b6dbf9c2fc 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -389,8 +389,7 @@ struct perf_event { /* mmap bits */ struct mutex mmap_mutex; atomic_t mmap_count; - int mmap_locked; - struct user_struct *mmap_user; + struct ring_buffer *rb; struct list_head rb_entry; diff --git a/kernel/events/core.c b/kernel/events/core.c index 9dc297faf7c0..ae752cd4a086 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2917,7 +2917,7 @@ static void free_event_rcu(struct rcu_head *head) kfree(event); } -static void ring_buffer_put(struct ring_buffer *rb); +static bool ring_buffer_put(struct ring_buffer *rb); static void free_event(struct perf_event *event) { @@ -3582,13 +3582,13 @@ static struct ring_buffer *ring_buffer_get(struct perf_event *event) return rb; } -static void ring_buffer_put(struct ring_buffer *rb) +static bool ring_buffer_put(struct ring_buffer *rb) { struct perf_event *event, *n; unsigned long flags; if (!atomic_dec_and_test(&rb->refcount)) - return; + return false; spin_lock_irqsave(&rb->event_lock, flags); list_for_each_entry_safe(event, n, &rb->event_list, rb_entry) { @@ -3598,6 +3598,7 @@ static void ring_buffer_put(struct ring_buffer *rb) spin_unlock_irqrestore(&rb->event_lock, flags); call_rcu(&rb->rcu_head, rb_free_rcu); + return true; } static void perf_mmap_open(struct vm_area_struct *vma) @@ -3612,18 +3613,20 @@ static void perf_mmap_close(struct vm_area_struct *vma) struct perf_event *event = vma->vm_file->private_data; if (atomic_dec_and_mutex_lock(&event->mmap_count, &event->mmap_mutex)) { - unsigned long size = perf_data_size(event->rb); - struct user_struct *user = event->mmap_user; struct ring_buffer *rb = event->rb; + struct user_struct *mmap_user = rb->mmap_user; + int mmap_locked = rb->mmap_locked; + unsigned long size = perf_data_size(rb); - atomic_long_sub((size >> PAGE_SHIFT) + 1, &user->locked_vm); - vma->vm_mm->pinned_vm -= event->mmap_locked; rcu_assign_pointer(event->rb, NULL); ring_buffer_detach(event, rb); mutex_unlock(&event->mmap_mutex); - ring_buffer_put(rb); - free_uid(user); + if (ring_buffer_put(rb)) { + atomic_long_sub((size >> PAGE_SHIFT) + 1, &mmap_user->locked_vm); + vma->vm_mm->pinned_vm -= mmap_locked; + free_uid(mmap_user); + } } } @@ -3676,9 +3679,7 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) WARN_ON_ONCE(event->ctx->parent_ctx); mutex_lock(&event->mmap_mutex); if (event->rb) { - if (event->rb->nr_pages == nr_pages) - atomic_inc(&event->rb->refcount); - else + if (event->rb->nr_pages != nr_pages) ret = -EINVAL; goto unlock; } @@ -3720,12 +3721,14 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) ret = -ENOMEM; goto unlock; } - rcu_assign_pointer(event->rb, rb); + + rb->mmap_locked = extra; + rb->mmap_user = get_current_user(); atomic_long_add(user_extra, &user->locked_vm); - event->mmap_locked = extra; - event->mmap_user = get_current_user(); - vma->vm_mm->pinned_vm += event->mmap_locked; + vma->vm_mm->pinned_vm += extra; + + rcu_assign_pointer(event->rb, rb); perf_event_update_userpage(event); @@ -3734,7 +3737,7 @@ unlock: atomic_inc(&event->mmap_count); mutex_unlock(&event->mmap_mutex); - vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP; + vma->vm_flags |= VM_DONTCOPY | VM_DONTEXPAND | VM_DONTDUMP; vma->vm_ops = &perf_mmap_vmops; return ret; diff --git a/kernel/events/internal.h b/kernel/events/internal.h index eb675c4d59df..5bc6c8e9b851 100644 --- a/kernel/events/internal.h +++ b/kernel/events/internal.h @@ -31,6 +31,9 @@ struct ring_buffer { spinlock_t event_lock; struct list_head event_list; + int mmap_locked; + struct user_struct *mmap_user; + struct perf_event_mmap_page *user_page; void *data_pages[0]; }; -- cgit v1.2.3 From a44b8bd6072ac82fc49af941de8c1ac85d94852d Mon Sep 17 00:00:00 2001 From: Liu Ying Date: Tue, 7 May 2013 16:38:40 +0800 Subject: ktime: Use macro NSEC_PER_USEC where appropriate We've got the macro NSEC_PER_USEC defined in header file include/linux/time.h. To make the code decent, this patch replaces the immediate number 1000 to convert bewteen a time value in microseconds and one in nanoseconds with the macro NSEC_PER_USEC. Signed-off-by: Liu Ying Cc: David S. Miller Cc: Daniel Borkmann Cc: Thomas Gleixner Cc: John Stultz Signed-off-by: John Stultz --- include/linux/ktime.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ktime.h b/include/linux/ktime.h index bbca12804d12..608728a164a9 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -229,7 +229,8 @@ static inline ktime_t timespec_to_ktime(const struct timespec ts) static inline ktime_t timeval_to_ktime(const struct timeval tv) { return (ktime_t) { .tv = { .sec = (s32)tv.tv_sec, - .nsec = (s32)tv.tv_usec * 1000 } }; + .nsec = (s32)(tv.tv_usec * + NSEC_PER_USEC) } }; } /** @@ -320,12 +321,12 @@ static inline s64 ktime_us_delta(const ktime_t later, const ktime_t earlier) static inline ktime_t ktime_add_us(const ktime_t kt, const u64 usec) { - return ktime_add_ns(kt, usec * 1000); + return ktime_add_ns(kt, usec * NSEC_PER_USEC); } static inline ktime_t ktime_sub_us(const ktime_t kt, const u64 usec) { - return ktime_sub_ns(kt, usec * 1000); + return ktime_sub_ns(kt, usec * NSEC_PER_USEC); } extern ktime_t ktime_add_safe(const ktime_t lhs, const ktime_t rhs); -- cgit v1.2.3 From 35b210855069ae34450eeaafc0f1b5bfa4f71c87 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 16 May 2013 15:47:49 +0200 Subject: ktime: Add __must_check prefix to ktime_to_timespec_cond The function is currently mainly used in the networking code and if others start using it, they must check the result, otherwise it cannot be determined if the timespec conversion suceeded. Currently no user lacks this check, but make future users aware of a possible misusage. Signed-off-by: Daniel Borkmann Signed-off-by: John Stultz --- include/linux/ktime.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ktime.h b/include/linux/ktime.h index 608728a164a9..fc66b301b648 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -339,7 +339,8 @@ extern ktime_t ktime_add_safe(const ktime_t lhs, const ktime_t rhs); * * Returns true if there was a successful conversion, false if kt was 0. */ -static inline bool ktime_to_timespec_cond(const ktime_t kt, struct timespec *ts) +static inline __must_check bool ktime_to_timespec_cond(const ktime_t kt, + struct timespec *ts) { if (kt.tv64) { *ts = ktime_to_timespec(kt); -- cgit v1.2.3 From 55a68c23e0a675b2b8ac2656fd6edbf98b78e4c6 Mon Sep 17 00:00:00 2001 From: Pavel Machek Date: Tue, 7 May 2013 22:11:26 +0200 Subject: dw_apb_timer_of.c: Remove parts that were picoxcell-specific It seems we made a mistake when creating dw_apb_timer_of.c: picoxcell sched_clock had parts that were not related to dw_apb_timer, yet we moved them to dw_apb_timer_of, and tried to use them on socfpga. This results in system where user/system time is not measured properly, as demonstrated by time dd if=/dev/urandom of=/dev/zero bs=100000 count=100 So this patch switches sched_clock to hardware that exists on both platforms, and adds missing of_node_put() in dw_apb_timer_init(). Signed-off-by: Pavel Machek Acked-by: Jamie Iles Signed-off-by: John Stultz --- arch/arm/mach-picoxcell/common.h | 2 -- drivers/clocksource/dw_apb_timer.c | 6 ---- drivers/clocksource/dw_apb_timer_of.c | 52 ++++++++++++++++------------------- include/linux/dw_apb_timer.h | 6 ++++ 4 files changed, 29 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/mach-picoxcell/common.h b/arch/arm/mach-picoxcell/common.h index 481b42a4ef15..237fb3bcbd04 100644 --- a/arch/arm/mach-picoxcell/common.h +++ b/arch/arm/mach-picoxcell/common.h @@ -12,6 +12,4 @@ #include -extern void dw_apb_timer_init(void); - #endif /* __PICOXCELL_COMMON_H__ */ diff --git a/drivers/clocksource/dw_apb_timer.c b/drivers/clocksource/dw_apb_timer.c index e54ca1062d8e..e7042bc5c7d2 100644 --- a/drivers/clocksource/dw_apb_timer.c +++ b/drivers/clocksource/dw_apb_timer.c @@ -21,12 +21,6 @@ #define APBT_MIN_PERIOD 4 #define APBT_MIN_DELTA_USEC 200 -#define APBTMR_N_LOAD_COUNT 0x00 -#define APBTMR_N_CURRENT_VALUE 0x04 -#define APBTMR_N_CONTROL 0x08 -#define APBTMR_N_EOI 0x0c -#define APBTMR_N_INT_STATUS 0x10 - #define APBTMRS_INT_STATUS 0xa0 #define APBTMRS_EOI 0xa4 #define APBTMRS_RAW_INT_STATUS 0xa8 diff --git a/drivers/clocksource/dw_apb_timer_of.c b/drivers/clocksource/dw_apb_timer_of.c index ab09ed3742ee..44a3b9163c46 100644 --- a/drivers/clocksource/dw_apb_timer_of.c +++ b/drivers/clocksource/dw_apb_timer_of.c @@ -57,6 +57,15 @@ static void add_clockevent(struct device_node *event_timer) dw_apb_clockevent_register(ced); } +static void __iomem *sched_io_base; + +/* This is actually same as __apbt_read_clocksource(), but with + different interface */ +static u32 read_sched_clock_sptimer(void) +{ + return ~__raw_readl(sched_io_base + APBTMR_N_CURRENT_VALUE); +} + static void add_clocksource(struct device_node *source_timer) { void __iomem *iobase; @@ -71,41 +80,27 @@ static void add_clocksource(struct device_node *source_timer) dw_apb_clocksource_start(cs); dw_apb_clocksource_register(cs); -} -static void __iomem *sched_io_base; - -static u32 read_sched_clock(void) -{ - return __raw_readl(sched_io_base); + sched_io_base = iobase; + setup_sched_clock(read_sched_clock_sptimer, 32, rate); } -static const struct of_device_id sptimer_ids[] __initconst = { - { .compatible = "picochip,pc3x2-rtc" }, +static const struct of_device_id osctimer_ids[] __initconst = { + { .compatible = "picochip,pc3x2-timer" }, + { .compatible = "snps,dw-apb-timer-osc" }, { .compatible = "snps,dw-apb-timer-sp" }, - { /* Sentinel */ }, + { /* Sentinel */ }, }; -static void init_sched_clock(void) -{ - struct device_node *sched_timer; - u32 rate; - - sched_timer = of_find_matching_node(NULL, sptimer_ids); - if (!sched_timer) - panic("No RTC for sched clock to use"); +/* + You don't have to use dw_apb_timer for scheduler clock, + this should also work fine on arm: - timer_get_base_and_rate(sched_timer, &sched_io_base, &rate); - of_node_put(sched_timer); + twd_local_timer_of_register(); + arch_timer_of_register(); + arch_timer_sched_clock_init(); +*/ - setup_sched_clock(read_sched_clock, 32, rate); -} - -static const struct of_device_id osctimer_ids[] __initconst = { - { .compatible = "picochip,pc3x2-timer" }, - { .compatible = "snps,dw-apb-timer-osc" }, - {}, -}; void __init dw_apb_timer_init(void) { @@ -121,7 +116,6 @@ void __init dw_apb_timer_init(void) panic("No timer for clocksource"); add_clocksource(source_timer); + of_node_put(event_timer); of_node_put(source_timer); - - init_sched_clock(); } diff --git a/include/linux/dw_apb_timer.h b/include/linux/dw_apb_timer.h index b1cd9597c241..de0904e38f33 100644 --- a/include/linux/dw_apb_timer.h +++ b/include/linux/dw_apb_timer.h @@ -17,6 +17,12 @@ #include #include +#define APBTMR_N_LOAD_COUNT 0x00 +#define APBTMR_N_CURRENT_VALUE 0x04 +#define APBTMR_N_CONTROL 0x08 +#define APBTMR_N_EOI 0x0c +#define APBTMR_N_INT_STATUS 0x10 + #define APBTMRS_REG_SIZE 0x14 struct dw_apb_timer { -- cgit v1.2.3 From 3565184ed0c1ea46bea5b792da5f72a83c43e49b Mon Sep 17 00:00:00 2001 From: David Vrabel Date: Mon, 13 May 2013 18:56:06 +0100 Subject: x86: Increase precision of x86_platform.get/set_wallclock() All the virtualized platforms (KVM, lguest and Xen) have persistent wallclocks that have more than one second of precision. read_persistent_wallclock() and update_persistent_wallclock() allow for nanosecond precision but their implementation on x86 with x86_platform.get/set_wallclock() only allows for one second precision. This means guests may see a wallclock time that is off by up to 1 second. Make set_wallclock() and get_wallclock() take a struct timespec parameter (which allows for nanosecond precision) so KVM and Xen guests may start with a more accurate wallclock time and a Xen dom0 can maintain a more accurate wallclock for guests. Signed-off-by: David Vrabel Signed-off-by: John Stultz --- arch/x86/include/asm/mc146818rtc.h | 4 ++-- arch/x86/include/asm/x86_init.h | 6 ++++-- arch/x86/kernel/kvmclock.c | 9 +++------ arch/x86/kernel/rtc.c | 17 +++++++---------- arch/x86/lguest/boot.c | 4 ++-- arch/x86/platform/efi/efi.c | 10 ++++++---- arch/x86/xen/time.c | 19 ++++++------------- include/linux/efi.h | 4 ++-- 8 files changed, 32 insertions(+), 41 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/mc146818rtc.h b/arch/x86/include/asm/mc146818rtc.h index d354fb781c57..a55c7efcc4ed 100644 --- a/arch/x86/include/asm/mc146818rtc.h +++ b/arch/x86/include/asm/mc146818rtc.h @@ -95,8 +95,8 @@ static inline unsigned char current_lock_cmos_reg(void) unsigned char rtc_cmos_read(unsigned char addr); void rtc_cmos_write(unsigned char val, unsigned char addr); -extern int mach_set_rtc_mmss(unsigned long nowtime); -extern unsigned long mach_get_cmos_time(void); +extern int mach_set_rtc_mmss(const struct timespec *now); +extern void mach_get_cmos_time(struct timespec *now); #define RTC_IRQ 8 diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index d8d99222b36a..828a1565ba57 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -142,6 +142,8 @@ struct x86_cpuinit_ops { void (*fixup_cpu_id)(struct cpuinfo_x86 *c, int node); }; +struct timespec; + /** * struct x86_platform_ops - platform specific runtime functions * @calibrate_tsc: calibrate TSC @@ -156,8 +158,8 @@ struct x86_cpuinit_ops { */ struct x86_platform_ops { unsigned long (*calibrate_tsc)(void); - unsigned long (*get_wallclock)(void); - int (*set_wallclock)(unsigned long nowtime); + void (*get_wallclock)(struct timespec *ts); + int (*set_wallclock)(const struct timespec *ts); void (*iommu_shutdown)(void); bool (*is_untracked_pat_range)(u64 start, u64 end); void (*nmi_init)(void); diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index d2c381280e3c..0db81ab511cc 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -48,10 +48,9 @@ static struct pvclock_wall_clock wall_clock; * have elapsed since the hypervisor wrote the data. So we try to account for * that with system time */ -static unsigned long kvm_get_wallclock(void) +static void kvm_get_wallclock(struct timespec *now) { struct pvclock_vcpu_time_info *vcpu_time; - struct timespec ts; int low, high; int cpu; @@ -64,14 +63,12 @@ static unsigned long kvm_get_wallclock(void) cpu = smp_processor_id(); vcpu_time = &hv_clock[cpu].pvti; - pvclock_read_wallclock(&wall_clock, vcpu_time, &ts); + pvclock_read_wallclock(&wall_clock, vcpu_time, now); preempt_enable(); - - return ts.tv_sec; } -static int kvm_set_wallclock(unsigned long now) +static int kvm_set_wallclock(const struct timespec *now) { return -1; } diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index 198eb201ed3b..0aa29394ed6f 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -38,8 +38,9 @@ EXPORT_SYMBOL(rtc_lock); * jump to the next second precisely 500 ms later. Check the Motorola * MC146818A or Dallas DS12887 data sheet for details. */ -int mach_set_rtc_mmss(unsigned long nowtime) +int mach_set_rtc_mmss(const struct timespec *now) { + unsigned long nowtime = now->tv_sec; struct rtc_time tm; int retval = 0; @@ -58,7 +59,7 @@ int mach_set_rtc_mmss(unsigned long nowtime) return retval; } -unsigned long mach_get_cmos_time(void) +void mach_get_cmos_time(struct timespec *now) { unsigned int status, year, mon, day, hour, min, sec, century = 0; unsigned long flags; @@ -107,7 +108,8 @@ unsigned long mach_get_cmos_time(void) } else year += CMOS_YEARS_OFFS; - return mktime(year, mon, day, hour, min, sec); + now->tv_sec = mktime(year, mon, day, hour, min, sec); + now->tv_nsec = 0; } /* Routines for accessing the CMOS RAM/RTC. */ @@ -135,18 +137,13 @@ EXPORT_SYMBOL(rtc_cmos_write); int update_persistent_clock(struct timespec now) { - return x86_platform.set_wallclock(now.tv_sec); + return x86_platform.set_wallclock(&now); } /* not static: needed by APM */ void read_persistent_clock(struct timespec *ts) { - unsigned long retval; - - retval = x86_platform.get_wallclock(); - - ts->tv_sec = retval; - ts->tv_nsec = 0; + x86_platform.get_wallclock(ts); } diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index 7114c63f047d..8424d5adcfa2 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -882,9 +882,9 @@ int lguest_setup_irq(unsigned int irq) * It would be far better for everyone if the Guest had its own clock, but * until then the Host gives us the time on every interrupt. */ -static unsigned long lguest_get_wallclock(void) +static void lguest_get_wallclock(struct timespec *now) { - return lguest_data.time.tv_sec; + *now = lguest_data.time; } /* diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 55856b2310d3..dd3b82530145 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -352,8 +352,9 @@ static efi_status_t __init phys_efi_get_time(efi_time_t *tm, return status; } -int efi_set_rtc_mmss(unsigned long nowtime) +int efi_set_rtc_mmss(const struct timespec *now) { + unsigned long nowtime = now->tv_sec; efi_status_t status; efi_time_t eft; efi_time_cap_t cap; @@ -388,7 +389,7 @@ int efi_set_rtc_mmss(unsigned long nowtime) return 0; } -unsigned long efi_get_time(void) +void efi_get_time(struct timespec *now) { efi_status_t status; efi_time_t eft; @@ -398,8 +399,9 @@ unsigned long efi_get_time(void) if (status != EFI_SUCCESS) pr_err("Oops: efitime: can't read time!\n"); - return mktime(eft.year, eft.month, eft.day, eft.hour, - eft.minute, eft.second); + now->tv_sec = mktime(eft.year, eft.month, eft.day, eft.hour, + eft.minute, eft.second); + now->tv_nsec = 0; } /* diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index 3d88bfdf9e1c..a1947ac2da82 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -191,32 +191,25 @@ static void xen_read_wallclock(struct timespec *ts) put_cpu_var(xen_vcpu); } -static unsigned long xen_get_wallclock(void) +static void xen_get_wallclock(struct timespec *now) { - struct timespec ts; - - xen_read_wallclock(&ts); - return ts.tv_sec; + xen_read_wallclock(now); } -static int xen_set_wallclock(unsigned long now) +static int xen_set_wallclock(const struct timespec *now) { struct xen_platform_op op; - int rc; /* do nothing for domU */ if (!xen_initial_domain()) return -1; op.cmd = XENPF_settime; - op.u.settime.secs = now; - op.u.settime.nsecs = 0; + op.u.settime.secs = now->tv_sec; + op.u.settime.nsecs = now->tv_nsec; op.u.settime.system_time = xen_clocksource_read(); - rc = HYPERVISOR_dom0_op(&op); - WARN(rc != 0, "XENPF_settime failed: now=%ld\n", now); - - return rc; + return HYPERVISOR_dom0_op(&op); } static struct clocksource xen_clocksource __read_mostly = { diff --git a/include/linux/efi.h b/include/linux/efi.h index 2bc0ad78d058..0068bba6f8b6 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -594,8 +594,8 @@ extern u64 efi_mem_attribute (unsigned long phys_addr, unsigned long size); extern int __init efi_uart_console_only (void); extern void efi_initialize_iomem_resources(struct resource *code_resource, struct resource *data_resource, struct resource *bss_resource); -extern unsigned long efi_get_time(void); -extern int efi_set_rtc_mmss(unsigned long nowtime); +extern void efi_get_time(struct timespec *now); +extern int efi_set_rtc_mmss(const struct timespec *now); extern void efi_reserve_boot_services(void); extern struct efi_memory_map memmap; -- cgit v1.2.3 From 12bcbe66d7b3cc9f9f86cd02f925666eaa3c2107 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 28 May 2013 14:38:42 -0400 Subject: rcu: Add _notrace variation of rcu_dereference_raw() and hlist_for_each_entry_rcu() As rcu_dereference_raw() under RCU debug config options can add quite a bit of checks, and that tracing uses rcu_dereference_raw(), these checks happen with the function tracer. The function tracer also happens to trace these debug checks too. This added overhead can livelock the system. Add a new interface to RCU for both rcu_dereference_raw_notrace() as well as hlist_for_each_entry_rcu_notrace() as the hlist iterator uses the rcu_dereference_raw() as well, and is used a bit with the function tracer. Link: http://lkml.kernel.org/r/20130528184209.304356745@goodmis.org Acked-by: Paul E. McKenney Signed-off-by: Steven Rostedt --- include/linux/rculist.h | 20 ++++++++++++++++++++ include/linux/rcupdate.h | 9 +++++++++ 2 files changed, 29 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 8089e35d47ac..f4b1001a4676 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -460,6 +460,26 @@ static inline void hlist_add_after_rcu(struct hlist_node *prev, pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) +/** + * hlist_for_each_entry_rcu_notrace - iterate over rcu list of given type (for tracing) + * @pos: the type * to use as a loop cursor. + * @head: the head for your list. + * @member: the name of the hlist_node within the struct. + * + * This list-traversal primitive may safely run concurrently with + * the _rcu list-mutation primitives such as hlist_add_head_rcu() + * as long as the traversal is guarded by rcu_read_lock(). + * + * This is the same as hlist_for_each_entry_rcu() except that it does + * not do any RCU debugging or tracing. + */ +#define hlist_for_each_entry_rcu_notrace(pos, head, member) \ + for (pos = hlist_entry_safe (rcu_dereference_raw_notrace(hlist_first_rcu(head)),\ + typeof(*(pos)), member); \ + pos; \ + pos = hlist_entry_safe(rcu_dereference_raw_notrace(hlist_next_rcu(\ + &(pos)->member)), typeof(*(pos)), member)) + /** * hlist_for_each_entry_rcu_bh - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 4ccd68e49b00..ddcc7826d907 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -640,6 +640,15 @@ static inline void rcu_preempt_sleep_check(void) #define rcu_dereference_raw(p) rcu_dereference_check(p, 1) /*@@@ needed? @@@*/ +/* + * The tracing infrastructure traces RCU (we want that), but unfortunately + * some of the RCU checks causes tracing to lock up the system. + * + * The tracing version of rcu_dereference_raw() must not call + * rcu_read_lock_held(). + */ +#define rcu_dereference_raw_notrace(p) __rcu_dereference_check((p), 1, __rcu) + /** * rcu_access_index() - fetch RCU index with no dereferencing * @p: The index to read -- cgit v1.2.3 From 6cffe00f7d4e24679eae6b7aae4caaf915288256 Mon Sep 17 00:00:00 2001 From: Todd Poynor Date: Wed, 15 May 2013 14:38:11 -0700 Subject: alarmtimer: Add functions for timerfd support Add functions needed for hooking up alarmtimer to timerfd: * alarm_restart: Similar to hrtimer_restart, restart an alarmtimer after the expires time has already been updated (as with alarm_forward). * alarm_forward_now: Similar to hrtimer_forward_now, move the expires time forward to an interval from the current time of the associated clock. * alarm_start_relative: Start an alarmtimer with an expires time relative to the current time of the associated clock. * alarm_expires_remaining: Similar to hrtimer_expires_remaining, return the amount of time remaining until alarm expiry. Signed-off-by: Todd Poynor Signed-off-by: John Stultz --- include/linux/alarmtimer.h | 4 ++++ kernel/time/alarmtimer.c | 39 ++++++++++++++++++++++++++++++++++++++- 2 files changed, 42 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/alarmtimer.h b/include/linux/alarmtimer.h index 9069694e70eb..a899402a5a0e 100644 --- a/include/linux/alarmtimer.h +++ b/include/linux/alarmtimer.h @@ -44,10 +44,14 @@ struct alarm { void alarm_init(struct alarm *alarm, enum alarmtimer_type type, enum alarmtimer_restart (*function)(struct alarm *, ktime_t)); int alarm_start(struct alarm *alarm, ktime_t start); +int alarm_start_relative(struct alarm *alarm, ktime_t start); +void alarm_restart(struct alarm *alarm); int alarm_try_to_cancel(struct alarm *alarm); int alarm_cancel(struct alarm *alarm); u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval); +u64 alarm_forward_now(struct alarm *alarm, ktime_t interval); +ktime_t alarm_expires_remaining(const struct alarm *alarm); /* Provide way to access the rtc device being used by alarmtimers */ struct rtc_device *alarmtimer_get_rtcdev(void); diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index f11d83b12949..3e5cba274475 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -199,6 +199,12 @@ static enum hrtimer_restart alarmtimer_fired(struct hrtimer *timer) } +ktime_t alarm_expires_remaining(const struct alarm *alarm) +{ + struct alarm_base *base = &alarm_bases[alarm->type]; + return ktime_sub(alarm->node.expires, base->gettime()); +} + #ifdef CONFIG_RTC_CLASS /** * alarmtimer_suspend - Suspend time callback @@ -305,7 +311,7 @@ void alarm_init(struct alarm *alarm, enum alarmtimer_type type, } /** - * alarm_start - Sets an alarm to fire + * alarm_start - Sets an absolute alarm to fire * @alarm: ptr to alarm to set * @start: time to run the alarm */ @@ -324,6 +330,31 @@ int alarm_start(struct alarm *alarm, ktime_t start) return ret; } +/** + * alarm_start_relative - Sets a relative alarm to fire + * @alarm: ptr to alarm to set + * @start: time relative to now to run the alarm + */ +int alarm_start_relative(struct alarm *alarm, ktime_t start) +{ + struct alarm_base *base = &alarm_bases[alarm->type]; + + start = ktime_add(start, base->gettime()); + return alarm_start(alarm, start); +} + +void alarm_restart(struct alarm *alarm) +{ + struct alarm_base *base = &alarm_bases[alarm->type]; + unsigned long flags; + + spin_lock_irqsave(&base->lock, flags); + hrtimer_set_expires(&alarm->timer, alarm->node.expires); + hrtimer_restart(&alarm->timer); + alarmtimer_enqueue(base, alarm); + spin_unlock_irqrestore(&base->lock, flags); +} + /** * alarm_try_to_cancel - Tries to cancel an alarm timer * @alarm: ptr to alarm to be canceled @@ -394,6 +425,12 @@ u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval) return overrun; } +u64 alarm_forward_now(struct alarm *alarm, ktime_t interval) +{ + struct alarm_base *base = &alarm_bases[alarm->type]; + + return alarm_forward(alarm, base->gettime(), interval); +} -- cgit v1.2.3 From ac4e97abce9b80c020e7113325f49e58b7b15e3f Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 30 May 2013 09:19:35 +0200 Subject: scatterlist: sg_set_buf() argument must be in linear mapping Add a check behind CONFIG_DEBUG_SG to verify this. Signed-off-by: Rusty Russell Signed-off-by: Jens Axboe --- include/linux/scatterlist.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h index 5951e3f38878..26806775b11b 100644 --- a/include/linux/scatterlist.h +++ b/include/linux/scatterlist.h @@ -111,6 +111,9 @@ static inline struct page *sg_page(struct scatterlist *sg) static inline void sg_set_buf(struct scatterlist *sg, const void *buf, unsigned int buflen) { +#ifdef CONFIG_DEBUG_SG + BUG_ON(!virt_addr_valid(buf)); +#endif sg_set_page(sg, virt_to_page(buf), buflen, offset_in_page(buf)); } -- cgit v1.2.3 From 37448adfc7ce0d6d5892b87aa8d57edde4126f49 Mon Sep 17 00:00:00 2001 From: Lance Ortiz Date: Thu, 30 May 2013 08:25:12 -0600 Subject: aerdrv: Move cper_print_aer() call out of interrupt context The following warning was seen on 3.9 when a corrected PCIe error was being handled by the AER subsystem. WARNING: at .../drivers/pci/search.c:214 pci_get_dev_by_id+0x8a/0x90() This occurred because a call to pci_get_domain_bus_and_slot() was added to cper_print_pcie() to setup for the call to cper_print_aer(). The warning showed up because cper_print_pcie() is called in an interrupt context and pci_get* functions are not supposed to be called in that context. The solution is to move the cper_print_aer() call out of the interrupt context and into aer_recover_work_func() to avoid any warnings when calling pci_get* functions. Signed-off-by: Lance Ortiz Acked-by: Borislav Petkov Acked-by: Rafael J. Wysocki Signed-off-by: Tony Luck --- drivers/acpi/apei/cper.c | 18 ------------------ drivers/acpi/apei/ghes.c | 4 +++- drivers/pci/pcie/aer/aerdrv_core.c | 5 ++++- drivers/pci/pcie/aer/aerdrv_errprint.c | 4 ++-- include/linux/aer.h | 5 +++-- 5 files changed, 12 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/drivers/acpi/apei/cper.c b/drivers/acpi/apei/cper.c index fefc2ca7cc3e..33dc6a004802 100644 --- a/drivers/acpi/apei/cper.c +++ b/drivers/acpi/apei/cper.c @@ -250,10 +250,6 @@ static const char *cper_pcie_port_type_strs[] = { static void cper_print_pcie(const char *pfx, const struct cper_sec_pcie *pcie, const struct acpi_hest_generic_data *gdata) { -#ifdef CONFIG_ACPI_APEI_PCIEAER - struct pci_dev *dev; -#endif - if (pcie->validation_bits & CPER_PCIE_VALID_PORT_TYPE) printk("%s""port_type: %d, %s\n", pfx, pcie->port_type, pcie->port_type < ARRAY_SIZE(cper_pcie_port_type_strs) ? @@ -285,20 +281,6 @@ static void cper_print_pcie(const char *pfx, const struct cper_sec_pcie *pcie, printk( "%s""bridge: secondary_status: 0x%04x, control: 0x%04x\n", pfx, pcie->bridge.secondary_status, pcie->bridge.control); -#ifdef CONFIG_ACPI_APEI_PCIEAER - dev = pci_get_domain_bus_and_slot(pcie->device_id.segment, - pcie->device_id.bus, pcie->device_id.function); - if (!dev) { - pr_err("PCI AER Cannot get PCI device %04x:%02x:%02x.%d\n", - pcie->device_id.segment, pcie->device_id.bus, - pcie->device_id.slot, pcie->device_id.function); - return; - } - if (pcie->validation_bits & CPER_PCIE_VALID_AER_INFO) - cper_print_aer(pfx, dev, gdata->error_severity, - (struct aer_capability_regs *) pcie->aer_info); - pci_dev_put(dev); -#endif } static const char *apei_estatus_section_flag_strs[] = { diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index d668a8ae602b..403baf4dffc1 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -454,7 +454,9 @@ static void ghes_do_proc(struct ghes *ghes, aer_severity = cper_severity_to_aer(sev); aer_recover_queue(pcie_err->device_id.segment, pcie_err->device_id.bus, - devfn, aer_severity); + devfn, aer_severity, + (struct aer_capability_regs *) + pcie_err->aer_info); } } diff --git a/drivers/pci/pcie/aer/aerdrv_core.c b/drivers/pci/pcie/aer/aerdrv_core.c index 8ec8b4f48560..0f4554e48cc5 100644 --- a/drivers/pci/pcie/aer/aerdrv_core.c +++ b/drivers/pci/pcie/aer/aerdrv_core.c @@ -580,6 +580,7 @@ struct aer_recover_entry u8 devfn; u16 domain; int severity; + struct aer_capability_regs *regs; }; static DEFINE_KFIFO(aer_recover_ring, struct aer_recover_entry, @@ -593,7 +594,7 @@ static DEFINE_SPINLOCK(aer_recover_ring_lock); static DECLARE_WORK(aer_recover_work, aer_recover_work_func); void aer_recover_queue(int domain, unsigned int bus, unsigned int devfn, - int severity) + int severity, struct aer_capability_regs *aer_regs) { unsigned long flags; struct aer_recover_entry entry = { @@ -601,6 +602,7 @@ void aer_recover_queue(int domain, unsigned int bus, unsigned int devfn, .devfn = devfn, .domain = domain, .severity = severity, + .regs = aer_regs, }; spin_lock_irqsave(&aer_recover_ring_lock, flags); @@ -627,6 +629,7 @@ static void aer_recover_work_func(struct work_struct *work) PCI_SLOT(entry.devfn), PCI_FUNC(entry.devfn)); continue; } + cper_print_aer(pdev, entry.severity, entry.regs); do_recovery(pdev, entry.severity); pci_dev_put(pdev); } diff --git a/drivers/pci/pcie/aer/aerdrv_errprint.c b/drivers/pci/pcie/aer/aerdrv_errprint.c index 5ab14251839d..2c7c9f5f592c 100644 --- a/drivers/pci/pcie/aer/aerdrv_errprint.c +++ b/drivers/pci/pcie/aer/aerdrv_errprint.c @@ -220,7 +220,7 @@ int cper_severity_to_aer(int cper_severity) } EXPORT_SYMBOL_GPL(cper_severity_to_aer); -void cper_print_aer(const char *prefix, struct pci_dev *dev, int cper_severity, +void cper_print_aer(struct pci_dev *dev, int cper_severity, struct aer_capability_regs *aer) { int aer_severity, layer, agent, status_strs_size, tlp_header_valid = 0; @@ -244,7 +244,7 @@ void cper_print_aer(const char *prefix, struct pci_dev *dev, int cper_severity, agent = AER_GET_AGENT(aer_severity, status); dev_err(&dev->dev, "aer_status: 0x%08x, aer_mask: 0x%08x\n", status, mask); - cper_print_bits(prefix, status, status_strs, status_strs_size); + cper_print_bits("", status, status_strs, status_strs_size); dev_err(&dev->dev, "aer_layer=%s, aer_agent=%s\n", aer_error_layer[layer], aer_agent_string[agent]); if (aer_severity != AER_CORRECTABLE) diff --git a/include/linux/aer.h b/include/linux/aer.h index ec10e1b24c1c..737f90ab4b62 100644 --- a/include/linux/aer.h +++ b/include/linux/aer.h @@ -49,10 +49,11 @@ static inline int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev) } #endif -extern void cper_print_aer(const char *prefix, struct pci_dev *dev, +extern void cper_print_aer(struct pci_dev *dev, int cper_severity, struct aer_capability_regs *aer); extern int cper_severity_to_aer(int cper_severity); extern void aer_recover_queue(int domain, unsigned int bus, unsigned int devfn, - int severity); + int severity, + struct aer_capability_regs *aer_regs); #endif //_AER_H_ -- cgit v1.2.3 From 45eacc692771bd2b1ea3d384e6345cab3da10861 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 15 May 2013 22:16:32 +0200 Subject: vtime: Use consistent clocks among nohz accounting While computing the cputime delta of dynticks CPUs, we are mixing up clocks of differents natures: * local_clock() which takes care of unstable clock sources and fix these if needed. * sched_clock() which is the weaker version of local_clock(). It doesn't compute any fixup in case of unstable source. If the clock source is stable, those two clocks are the same and we can safely compute the difference against two random points. Otherwise it results in random deltas as sched_clock() can randomly drift away, back or forward, from local_clock(). As a consequence, some strange behaviour with unstable tsc has been observed such as non progressing constant zero cputime. (The 'top' command showing no load). Fix this by only using local_clock(), or its irq safe/remote equivalent, in vtime code. Reported-by: Mike Galbraith Suggested-by: Mike Galbraith Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Signed-off-by: Frederic Weisbecker Signed-off-by: Ingo Molnar --- include/linux/vtime.h | 4 ++-- kernel/sched/core.c | 2 +- kernel/sched/cputime.c | 6 +++--- 3 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vtime.h b/include/linux/vtime.h index 71a5782d8c59..b1dd2db80076 100644 --- a/include/linux/vtime.h +++ b/include/linux/vtime.h @@ -34,7 +34,7 @@ static inline void vtime_user_exit(struct task_struct *tsk) } extern void vtime_guest_enter(struct task_struct *tsk); extern void vtime_guest_exit(struct task_struct *tsk); -extern void vtime_init_idle(struct task_struct *tsk); +extern void vtime_init_idle(struct task_struct *tsk, int cpu); #else static inline void vtime_account_irq_exit(struct task_struct *tsk) { @@ -45,7 +45,7 @@ static inline void vtime_user_enter(struct task_struct *tsk) { } static inline void vtime_user_exit(struct task_struct *tsk) { } static inline void vtime_guest_enter(struct task_struct *tsk) { } static inline void vtime_guest_exit(struct task_struct *tsk) { } -static inline void vtime_init_idle(struct task_struct *tsk) { } +static inline void vtime_init_idle(struct task_struct *tsk, int cpu) { } #endif #ifdef CONFIG_IRQ_TIME_ACCOUNTING diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 58453b8272fd..e1a27f918723 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4745,7 +4745,7 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu) */ idle->sched_class = &idle_sched_class; ftrace_graph_init_idle_task(idle, cpu); - vtime_init_idle(idle); + vtime_init_idle(idle, cpu); #if defined(CONFIG_SMP) sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu); #endif diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index cc2dc3eea8a3..b5ccba22603b 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -747,17 +747,17 @@ void arch_vtime_task_switch(struct task_struct *prev) write_seqlock(¤t->vtime_seqlock); current->vtime_snap_whence = VTIME_SYS; - current->vtime_snap = sched_clock(); + current->vtime_snap = sched_clock_cpu(smp_processor_id()); write_sequnlock(¤t->vtime_seqlock); } -void vtime_init_idle(struct task_struct *t) +void vtime_init_idle(struct task_struct *t, int cpu) { unsigned long flags; write_seqlock_irqsave(&t->vtime_seqlock, flags); t->vtime_snap_whence = VTIME_SYS; - t->vtime_snap = sched_clock(); + t->vtime_snap = sched_clock_cpu(cpu); write_sequnlock_irqrestore(&t->vtime_seqlock, flags); } -- cgit v1.2.3 From 521921bad1192fb1b8f9b6a5aa673635848b8b5f Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 16 May 2013 01:21:38 +0200 Subject: kvm: Move guest entry/exit APIs to context_tracking The kvm_host.h header file doesn't handle well inclusion when archs don't support KVM. This results in build crashes for such archs when they want to implement context tracking because this subsystem includes kvm_host.h in order to implement the guest_enter/exit APIs but it doesn't handle KVM off case. To fix this, move the guest_enter()/guest_exit() declarations and generic implementation to the context tracking headers. These generic APIs actually belong to this subsystem, besides other domains boundary tracking like user_enter() et al. KVM now properly becomes a user of this library, not the other buggy way around. Reported-by: Kevin Hilman Reviewed-by: Kevin Hilman Tested-by: Kevin Hilman Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Kevin Hilman Cc: Marcelo Tosatti Cc: Gleb Natapov Signed-off-by: Ingo Molnar --- include/linux/context_tracking.h | 35 +++++++++++++++++++++++++++++++++++ include/linux/kvm_host.h | 37 +------------------------------------ kernel/context_tracking.c | 1 - 3 files changed, 36 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 365f4a61bf04..fc09d7b0dacf 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -3,6 +3,7 @@ #include #include +#include #include struct context_tracking { @@ -19,6 +20,26 @@ struct context_tracking { } state; }; +static inline void __guest_enter(void) +{ + /* + * This is running in ioctl context so we can avoid + * the call to vtime_account() with its unnecessary idle check. + */ + vtime_account_system(current); + current->flags |= PF_VCPU; +} + +static inline void __guest_exit(void) +{ + /* + * This is running in ioctl context so we can avoid + * the call to vtime_account() with its unnecessary idle check. + */ + vtime_account_system(current); + current->flags &= ~PF_VCPU; +} + #ifdef CONFIG_CONTEXT_TRACKING DECLARE_PER_CPU(struct context_tracking, context_tracking); @@ -35,6 +56,9 @@ static inline bool context_tracking_active(void) extern void user_enter(void); extern void user_exit(void); +extern void guest_enter(void); +extern void guest_exit(void); + static inline enum ctx_state exception_enter(void) { enum ctx_state prev_ctx; @@ -57,6 +81,17 @@ extern void context_tracking_task_switch(struct task_struct *prev, static inline bool context_tracking_in_user(void) { return false; } static inline void user_enter(void) { } static inline void user_exit(void) { } + +static inline void guest_enter(void) +{ + __guest_enter(); +} + +static inline void guest_exit(void) +{ + __guest_exit(); +} + static inline enum ctx_state exception_enter(void) { return 0; } static inline void exception_exit(enum ctx_state prev_ctx) { } static inline void context_tracking_task_switch(struct task_struct *prev, diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index f0eea07d2c2b..8db53cfaccdb 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -23,6 +23,7 @@ #include #include #include +#include #include #include @@ -760,42 +761,6 @@ static inline int kvm_iommu_unmap_guest(struct kvm *kvm) } #endif -static inline void __guest_enter(void) -{ - /* - * This is running in ioctl context so we can avoid - * the call to vtime_account() with its unnecessary idle check. - */ - vtime_account_system(current); - current->flags |= PF_VCPU; -} - -static inline void __guest_exit(void) -{ - /* - * This is running in ioctl context so we can avoid - * the call to vtime_account() with its unnecessary idle check. - */ - vtime_account_system(current); - current->flags &= ~PF_VCPU; -} - -#ifdef CONFIG_CONTEXT_TRACKING -extern void guest_enter(void); -extern void guest_exit(void); - -#else /* !CONFIG_CONTEXT_TRACKING */ -static inline void guest_enter(void) -{ - __guest_enter(); -} - -static inline void guest_exit(void) -{ - __guest_exit(); -} -#endif /* !CONFIG_CONTEXT_TRACKING */ - static inline void kvm_guest_enter(void) { unsigned long flags; diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index 65349f07b878..85bdde1137eb 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -15,7 +15,6 @@ */ #include -#include #include #include #include -- cgit v1.2.3 From 1e2bd517c108816220f262d7954b697af03b5f9c Mon Sep 17 00:00:00 2001 From: Pravin B Shelar Date: Thu, 30 May 2013 06:45:27 +0000 Subject: udp6: Fix udp fragmentation for tunnel traffic. udp6 over GRE tunnel does not work after to GRE tso changes. GRE tso handler passes inner packet but keeps track of outer header start in SKB_GSO_CB(skb)->mac_offset. udp6 fragment need to take care of outer header, which start at the mac_offset, while adding fragment header. This bug is introduced by commit 68c3316311 (GRE: Add TCP segmentation offload for GRE). Reported-by: Dmitry Kravkov Signed-off-by: Pravin B Shelar Tested-by: Dmitry Kravkov Signed-off-by: David S. Miller --- include/linux/skbuff.h | 15 +++++++++++++++ net/ipv6/udp_offload.c | 20 ++++++++++++-------- 2 files changed, 27 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2e0ced1af3b1..9c676eae3968 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2852,6 +2852,21 @@ static inline int skb_tnl_header_len(const struct sk_buff *inner_skb) SKB_GSO_CB(inner_skb)->mac_offset; } +static inline int gso_pskb_expand_head(struct sk_buff *skb, int extra) +{ + int new_headroom, headroom; + int ret; + + headroom = skb_headroom(skb); + ret = pskb_expand_head(skb, extra, 0, GFP_ATOMIC); + if (ret) + return ret; + + new_headroom = skb_headroom(skb); + SKB_GSO_CB(skb)->mac_offset += (new_headroom - headroom); + return 0; +} + static inline bool skb_is_gso(const struct sk_buff *skb) { return skb_shinfo(skb)->gso_size; diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index 3bb3a891a424..d3cfaf9c7a08 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -46,11 +46,12 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, unsigned int mss; unsigned int unfrag_ip6hlen, unfrag_len; struct frag_hdr *fptr; - u8 *mac_start, *prevhdr; + u8 *packet_start, *prevhdr; u8 nexthdr; u8 frag_hdr_sz = sizeof(struct frag_hdr); int offset; __wsum csum; + int tnl_hlen; mss = skb_shinfo(skb)->gso_size; if (unlikely(skb->len <= mss)) @@ -83,9 +84,11 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, skb->ip_summed = CHECKSUM_NONE; /* Check if there is enough headroom to insert fragment header. */ - if ((skb_mac_header(skb) < skb->head + frag_hdr_sz) && - pskb_expand_head(skb, frag_hdr_sz, 0, GFP_ATOMIC)) - goto out; + tnl_hlen = skb_tnl_header_len(skb); + if (skb_headroom(skb) < (tnl_hlen + frag_hdr_sz)) { + if (gso_pskb_expand_head(skb, tnl_hlen + frag_hdr_sz)) + goto out; + } /* Find the unfragmentable header and shift it left by frag_hdr_sz * bytes to insert fragment header. @@ -93,11 +96,12 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr); nexthdr = *prevhdr; *prevhdr = NEXTHDR_FRAGMENT; - unfrag_len = skb_network_header(skb) - skb_mac_header(skb) + - unfrag_ip6hlen; - mac_start = skb_mac_header(skb); - memmove(mac_start-frag_hdr_sz, mac_start, unfrag_len); + unfrag_len = (skb_network_header(skb) - skb_mac_header(skb)) + + unfrag_ip6hlen + tnl_hlen; + packet_start = (u8 *) skb->head + SKB_GSO_CB(skb)->mac_offset; + memmove(packet_start-frag_hdr_sz, packet_start, unfrag_len); + SKB_GSO_CB(skb)->mac_offset -= frag_hdr_sz; skb->mac_header -= frag_hdr_sz; skb->network_header -= frag_hdr_sz; -- cgit v1.2.3 From 6d7581e62f8be462440d7b22c6361f7c9fa4902b Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 29 May 2013 05:02:56 +0000 Subject: list: introduce list_first_entry_or_null non-rcu variant of list_first_or_null_rcu Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/list.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/list.h b/include/linux/list.h index 6a1f8df9144b..b83e5657365a 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -361,6 +361,17 @@ static inline void list_splice_tail_init(struct list_head *list, #define list_first_entry(ptr, type, member) \ list_entry((ptr)->next, type, member) +/** + * list_first_entry_or_null - get the first element from a list + * @ptr: the list head to take the element from. + * @type: the type of the struct this is embedded in. + * @member: the name of the list_struct within the struct. + * + * Note that if the list is empty, it returns NULL. + */ +#define list_first_entry_or_null(ptr, type, member) \ + (!list_empty(ptr) ? list_first_entry(ptr, type, member) : NULL) + /** * list_for_each - iterate over a list * @pos: the &struct list_head to use as a loop cursor. -- cgit v1.2.3 From c87a124a5d5e8cf8e21c4363c3372bcaf53ea190 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 29 May 2013 09:06:27 +0000 Subject: net: force a reload of first item in hlist_nulls_for_each_entry_rcu Roman Gushchin discovered that udp4_lib_lookup2() was not reloading first item in the rcu protected list, in case the loop was restarted. This produced soft lockups as in https://lkml.org/lkml/2013/4/16/37 rcu_dereference(X)/ACCESS_ONCE(X) seem to not work as intended if X is ptr->field : In some cases, gcc caches the value or ptr->field in a register. Use a barrier() to disallow such caching, as documented in Documentation/atomic_ops.txt line 114 Thanks a lot to Roman for providing analysis and numerous patches. Diagnosed-by: Roman Gushchin Signed-off-by: Eric Dumazet Reported-by: Boris Zhmurov Signed-off-by: Roman Gushchin Acked-by: Paul E. McKenney Signed-off-by: David S. Miller --- include/linux/rculist_nulls.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h index 2ae13714828b..1c33dd7da4a7 100644 --- a/include/linux/rculist_nulls.h +++ b/include/linux/rculist_nulls.h @@ -105,9 +105,14 @@ static inline void hlist_nulls_add_head_rcu(struct hlist_nulls_node *n, * @head: the head for your list. * @member: the name of the hlist_nulls_node within the struct. * + * The barrier() is needed to make sure compiler doesn't cache first element [1], + * as this loop can be restarted [2] + * [1] Documentation/atomic_ops.txt around line 114 + * [2] Documentation/RCU/rculist_nulls.txt around line 146 */ #define hlist_nulls_for_each_entry_rcu(tpos, pos, head, member) \ - for (pos = rcu_dereference_raw(hlist_nulls_first_rcu(head)); \ + for (({barrier();}), \ + pos = rcu_dereference_raw(hlist_nulls_first_rcu(head)); \ (!is_a_nulls(pos)) && \ ({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); 1; }); \ pos = rcu_dereference_raw(hlist_nulls_next_rcu(pos))) -- cgit v1.2.3 From a7526eb5d06b0084ef12d7b168d008fcf516caab Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Wed, 5 Jun 2013 19:38:26 +0000 Subject: net: Unbreak compat_sys_{send,recv}msg I broke them in this commit: commit 1be374a0518a288147c6a7398792583200a67261 Author: Andy Lutomirski Date: Wed May 22 14:07:44 2013 -0700 net: Block MSG_CMSG_COMPAT in send(m)msg and recv(m)msg This patch adds __sys_sendmsg and __sys_sendmsg as common helpers that accept MSG_CMSG_COMPAT and blocks MSG_CMSG_COMPAT at the syscall entrypoints. It also reverts some unnecessary checks in sys_socketcall. Apparently I was suffering from underscore blindness the first time around. Signed-off-by: Andy Lutomirski Tested-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/socket.h | 3 +++ net/compat.c | 13 +++++++-- net/socket.c | 72 +++++++++++++++++++++++--------------------------- 3 files changed, 47 insertions(+), 41 deletions(-) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 33bf2dfab19d..b10ce4b341ea 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -320,6 +320,9 @@ extern int put_cmsg(struct msghdr*, int level, int type, int len, void *data); struct timespec; +/* The __sys_...msg variants allow MSG_CMSG_COMPAT */ +extern long __sys_recvmsg(int fd, struct msghdr __user *msg, unsigned flags); +extern long __sys_sendmsg(int fd, struct msghdr __user *msg, unsigned flags); extern int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, unsigned int flags, struct timespec *timeout); extern int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, diff --git a/net/compat.c b/net/compat.c index 79ae88485001..f0a1ba6c8086 100644 --- a/net/compat.c +++ b/net/compat.c @@ -734,19 +734,25 @@ static unsigned char nas[21] = { asmlinkage long compat_sys_sendmsg(int fd, struct compat_msghdr __user *msg, unsigned int flags) { - return sys_sendmsg(fd, (struct msghdr __user *)msg, flags | MSG_CMSG_COMPAT); + if (flags & MSG_CMSG_COMPAT) + return -EINVAL; + return __sys_sendmsg(fd, (struct msghdr __user *)msg, flags | MSG_CMSG_COMPAT); } asmlinkage long compat_sys_sendmmsg(int fd, struct compat_mmsghdr __user *mmsg, unsigned int vlen, unsigned int flags) { + if (flags & MSG_CMSG_COMPAT) + return -EINVAL; return __sys_sendmmsg(fd, (struct mmsghdr __user *)mmsg, vlen, flags | MSG_CMSG_COMPAT); } asmlinkage long compat_sys_recvmsg(int fd, struct compat_msghdr __user *msg, unsigned int flags) { - return sys_recvmsg(fd, (struct msghdr __user *)msg, flags | MSG_CMSG_COMPAT); + if (flags & MSG_CMSG_COMPAT) + return -EINVAL; + return __sys_recvmsg(fd, (struct msghdr __user *)msg, flags | MSG_CMSG_COMPAT); } asmlinkage long compat_sys_recv(int fd, void __user *buf, size_t len, unsigned int flags) @@ -768,6 +774,9 @@ asmlinkage long compat_sys_recvmmsg(int fd, struct compat_mmsghdr __user *mmsg, int datagrams; struct timespec ktspec; + if (flags & MSG_CMSG_COMPAT) + return -EINVAL; + if (COMPAT_USE_64BIT_TIME) return __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen, flags | MSG_CMSG_COMPAT, diff --git a/net/socket.c b/net/socket.c index 9ff6366fee13..4ca1526db756 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1956,7 +1956,7 @@ struct used_address { unsigned int name_len; }; -static int __sys_sendmsg(struct socket *sock, struct msghdr __user *msg, +static int ___sys_sendmsg(struct socket *sock, struct msghdr __user *msg, struct msghdr *msg_sys, unsigned int flags, struct used_address *used_address) { @@ -2071,26 +2071,30 @@ out: * BSD sendmsg interface */ -SYSCALL_DEFINE3(sendmsg, int, fd, struct msghdr __user *, msg, unsigned int, flags) +long __sys_sendmsg(int fd, struct msghdr __user *msg, unsigned flags) { int fput_needed, err; struct msghdr msg_sys; struct socket *sock; - if (flags & MSG_CMSG_COMPAT) - return -EINVAL; - sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; - err = __sys_sendmsg(sock, msg, &msg_sys, flags, NULL); + err = ___sys_sendmsg(sock, msg, &msg_sys, flags, NULL); fput_light(sock->file, fput_needed); out: return err; } +SYSCALL_DEFINE3(sendmsg, int, fd, struct msghdr __user *, msg, unsigned int, flags) +{ + if (flags & MSG_CMSG_COMPAT) + return -EINVAL; + return __sys_sendmsg(fd, msg, flags); +} + /* * Linux sendmmsg interface */ @@ -2121,15 +2125,16 @@ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, while (datagrams < vlen) { if (MSG_CMSG_COMPAT & flags) { - err = __sys_sendmsg(sock, (struct msghdr __user *)compat_entry, - &msg_sys, flags, &used_address); + err = ___sys_sendmsg(sock, (struct msghdr __user *)compat_entry, + &msg_sys, flags, &used_address); if (err < 0) break; err = __put_user(err, &compat_entry->msg_len); ++compat_entry; } else { - err = __sys_sendmsg(sock, (struct msghdr __user *)entry, - &msg_sys, flags, &used_address); + err = ___sys_sendmsg(sock, + (struct msghdr __user *)entry, + &msg_sys, flags, &used_address); if (err < 0) break; err = put_user(err, &entry->msg_len); @@ -2158,7 +2163,7 @@ SYSCALL_DEFINE4(sendmmsg, int, fd, struct mmsghdr __user *, mmsg, return __sys_sendmmsg(fd, mmsg, vlen, flags); } -static int __sys_recvmsg(struct socket *sock, struct msghdr __user *msg, +static int ___sys_recvmsg(struct socket *sock, struct msghdr __user *msg, struct msghdr *msg_sys, unsigned int flags, int nosec) { struct compat_msghdr __user *msg_compat = @@ -2250,27 +2255,31 @@ out: * BSD recvmsg interface */ -SYSCALL_DEFINE3(recvmsg, int, fd, struct msghdr __user *, msg, - unsigned int, flags) +long __sys_recvmsg(int fd, struct msghdr __user *msg, unsigned flags) { int fput_needed, err; struct msghdr msg_sys; struct socket *sock; - if (flags & MSG_CMSG_COMPAT) - return -EINVAL; - sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; - err = __sys_recvmsg(sock, msg, &msg_sys, flags, 0); + err = ___sys_recvmsg(sock, msg, &msg_sys, flags, 0); fput_light(sock->file, fput_needed); out: return err; } +SYSCALL_DEFINE3(recvmsg, int, fd, struct msghdr __user *, msg, + unsigned int, flags) +{ + if (flags & MSG_CMSG_COMPAT) + return -EINVAL; + return __sys_recvmsg(fd, msg, flags); +} + /* * Linux recvmmsg interface */ @@ -2308,17 +2317,18 @@ int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, * No need to ask LSM for more than the first datagram. */ if (MSG_CMSG_COMPAT & flags) { - err = __sys_recvmsg(sock, (struct msghdr __user *)compat_entry, - &msg_sys, flags & ~MSG_WAITFORONE, - datagrams); + err = ___sys_recvmsg(sock, (struct msghdr __user *)compat_entry, + &msg_sys, flags & ~MSG_WAITFORONE, + datagrams); if (err < 0) break; err = __put_user(err, &compat_entry->msg_len); ++compat_entry; } else { - err = __sys_recvmsg(sock, (struct msghdr __user *)entry, - &msg_sys, flags & ~MSG_WAITFORONE, - datagrams); + err = ___sys_recvmsg(sock, + (struct msghdr __user *)entry, + &msg_sys, flags & ~MSG_WAITFORONE, + datagrams); if (err < 0) break; err = put_user(err, &entry->msg_len); @@ -2505,31 +2515,15 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args) (int __user *)a[4]); break; case SYS_SENDMSG: - if (a[2] & MSG_CMSG_COMPAT) { - err = -EINVAL; - break; - } err = sys_sendmsg(a0, (struct msghdr __user *)a1, a[2]); break; case SYS_SENDMMSG: - if (a[3] & MSG_CMSG_COMPAT) { - err = -EINVAL; - break; - } err = sys_sendmmsg(a0, (struct mmsghdr __user *)a1, a[2], a[3]); break; case SYS_RECVMSG: - if (a[2] & MSG_CMSG_COMPAT) { - err = -EINVAL; - break; - } err = sys_recvmsg(a0, (struct msghdr __user *)a1, a[2]); break; case SYS_RECVMMSG: - if (a[3] & MSG_CMSG_COMPAT) { - err = -EINVAL; - break; - } err = sys_recvmmsg(a0, (struct mmsghdr __user *)a1, a[2], a[3], (struct timespec __user *)a[4]); break; -- cgit v1.2.3 From d62840995a99c9766803d54e9d7923f247a1c1db Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 22 May 2013 02:41:36 -0700 Subject: trace: Allow idle-safe tracepoints to be called from irq __DECLARE_TRACE_RCU() currently creates an _rcuidle() tracepoint which may safely be invoked from what RCU considers to be an idle CPU. However, these _rcuidle() tracepoints may -not- be invoked from the handler of an irq taken from idle, because rcu_idle_enter() zeroes RCU's nesting-level counter, so that the rcu_irq_exit() returning to idle will trigger a WARN_ON_ONCE(). This commit therefore substitutes rcu_irq_enter() for rcu_idle_exit() and rcu_irq_exit() for rcu_idle_enter() in order to make the _rcuidle() tracepoints usable from irq handlers as well as from process context. Reported-by: Dave Jones Signed-off-by: Paul E. McKenney Cc: Steven Rostedt --- include/linux/tracepoint.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 2f322c38bd4d..f8e084d0fc77 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -145,8 +145,8 @@ static inline void tracepoint_synchronize_unregister(void) TP_PROTO(data_proto), \ TP_ARGS(data_args), \ TP_CONDITION(cond), \ - rcu_idle_exit(), \ - rcu_idle_enter()); \ + rcu_irq_enter(), \ + rcu_irq_exit()); \ } #else #define __DECLARE_TRACE_RCU(name, proto, args, cond, data_proto, data_args) -- cgit v1.2.3 From ed13998c319b050fc9abdb73915859dfdbe1fb38 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Wed, 5 Jun 2013 15:30:55 +0200 Subject: sock_diag: fix filter code sent to userspace Filters need to be translated to real BPF code for userland, like SO_GETFILTER. Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- include/linux/filter.h | 1 + net/core/filter.c | 2 +- net/core/sock_diag.c | 9 +++++++-- 3 files changed, 9 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index c050dcc322a4..f65f5a69db8f 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -46,6 +46,7 @@ extern int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk); extern int sk_detach_filter(struct sock *sk); extern int sk_chk_filter(struct sock_filter *filter, unsigned int flen); extern int sk_get_filter(struct sock *sk, struct sock_filter __user *filter, unsigned len); +extern void sk_decode_filter(struct sock_filter *filt, struct sock_filter *to); #ifdef CONFIG_BPF_JIT #include diff --git a/net/core/filter.c b/net/core/filter.c index dad2a178f9f8..6438f29ff266 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -778,7 +778,7 @@ int sk_detach_filter(struct sock *sk) } EXPORT_SYMBOL_GPL(sk_detach_filter); -static void sk_decode_filter(struct sock_filter *filt, struct sock_filter *to) +void sk_decode_filter(struct sock_filter *filt, struct sock_filter *to) { static const u16 decodes[] = { [BPF_S_ALU_ADD_K] = BPF_ALU|BPF_ADD|BPF_K, diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index d5bef0b0f639..a0e9cf6379de 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -73,8 +73,13 @@ int sock_diag_put_filterinfo(struct user_namespace *user_ns, struct sock *sk, goto out; } - if (filter) - memcpy(nla_data(attr), filter->insns, len); + if (filter) { + struct sock_filter *fb = (struct sock_filter *)nla_data(attr); + int i; + + for (i = 0; i < filter->len; i++, fb++) + sk_decode_filter(&filter->insns[i], fb); + } out: rcu_read_unlock(); -- cgit v1.2.3 From b79462a8b9f9a452edc20c64a70a89ba3b0a6a88 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Sat, 8 Jun 2013 15:00:55 +0200 Subject: team: fix checks in team_get_first_port_txable_rcu() should be checked if "cur" is txable, not "port". Introduced by commit 6e88e1357c "team: use function team_port_txable() for determing enabled and up port" Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/if_team.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_team.h b/include/linux/if_team.h index 4474557904f6..16fae6436d0e 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -249,12 +249,12 @@ team_get_first_port_txable_rcu(struct team *team, struct team_port *port) return port; cur = port; list_for_each_entry_continue_rcu(cur, &team->port_list, list) - if (team_port_txable(port)) + if (team_port_txable(cur)) return cur; list_for_each_entry_rcu(cur, &team->port_list, list) { if (cur == port) break; - if (team_port_txable(port)) + if (team_port_txable(cur)) return cur; } return NULL; -- cgit v1.2.3 From 38ff87f77af0b5a93fc8581cff1d6e5692ab8970 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Sat, 1 Jun 2013 23:39:40 -0700 Subject: sched_clock: Make ARM's sched_clock generic for all architectures Nothing about the sched_clock implementation in the ARM port is specific to the architecture. Generalize the code so that other architectures can use it by selecting GENERIC_SCHED_CLOCK. Signed-off-by: Stephen Boyd [jstultz: Merge minor collisions with other patches in my tree] Signed-off-by: John Stultz --- arch/arm/Kconfig | 1 + arch/arm/common/timer-sp.c | 2 +- arch/arm/include/asm/sched_clock.h | 16 --- arch/arm/kernel/Makefile | 2 +- arch/arm/kernel/arch_timer.c | 2 +- arch/arm/kernel/sched_clock.c | 216 ------------------------------ arch/arm/kernel/time.c | 4 +- arch/arm/mach-davinci/time.c | 2 +- arch/arm/mach-imx/time.c | 2 +- arch/arm/mach-integrator/integrator_ap.c | 2 +- arch/arm/mach-ixp4xx/common.c | 2 +- arch/arm/mach-mmp/time.c | 2 +- arch/arm/mach-msm/timer.c | 2 +- arch/arm/mach-omap1/time.c | 2 +- arch/arm/mach-omap2/timer.c | 2 +- arch/arm/mach-pxa/time.c | 2 +- arch/arm/mach-sa1100/time.c | 2 +- arch/arm/mach-u300/timer.c | 2 +- arch/arm/plat-iop/time.c | 2 +- arch/arm/plat-omap/counter_32k.c | 2 +- arch/arm/plat-orion/time.c | 2 +- arch/arm/plat-samsung/samsung-time.c | 2 +- arch/arm/plat-versatile/sched-clock.c | 2 +- drivers/clocksource/bcm2835_timer.c | 2 +- drivers/clocksource/clksrc-dbx500-prcmu.c | 3 +- drivers/clocksource/dw_apb_timer_of.c | 3 +- drivers/clocksource/mxs_timer.c | 2 +- drivers/clocksource/nomadik-mtu.c | 2 +- drivers/clocksource/samsung_pwm_timer.c | 2 +- drivers/clocksource/tegra20_timer.c | 2 +- drivers/clocksource/time-armada-370-xp.c | 2 +- drivers/clocksource/timer-marco.c | 2 +- drivers/clocksource/timer-prima2.c | 2 +- include/linux/sched_clock.h | 21 +++ init/Kconfig | 3 + init/main.c | 2 + kernel/time/Makefile | 1 + kernel/time/sched_clock.c | 215 +++++++++++++++++++++++++++++ 38 files changed, 273 insertions(+), 266 deletions(-) delete mode 100644 arch/arm/include/asm/sched_clock.h delete mode 100644 arch/arm/kernel/sched_clock.c create mode 100644 include/linux/sched_clock.h create mode 100644 kernel/time/sched_clock.c (limited to 'include/linux') diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 49d993cee512..53d3a356f61f 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -14,6 +14,7 @@ config ARM select GENERIC_IRQ_PROBE select GENERIC_IRQ_SHOW select GENERIC_PCI_IOMAP + select GENERIC_SCHED_CLOCK select GENERIC_SMP_IDLE_THREAD select GENERIC_IDLE_POLL_SETUP select GENERIC_STRNCPY_FROM_USER diff --git a/arch/arm/common/timer-sp.c b/arch/arm/common/timer-sp.c index ddc740769601..023ee63827a2 100644 --- a/arch/arm/common/timer-sp.c +++ b/arch/arm/common/timer-sp.c @@ -28,8 +28,8 @@ #include #include #include +#include -#include #include #include diff --git a/arch/arm/include/asm/sched_clock.h b/arch/arm/include/asm/sched_clock.h deleted file mode 100644 index 3d520ddca61b..000000000000 --- a/arch/arm/include/asm/sched_clock.h +++ /dev/null @@ -1,16 +0,0 @@ -/* - * sched_clock.h: support for extending counters to full 64-bit ns counter - * - * 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 - * published by the Free Software Foundation. - */ -#ifndef ASM_SCHED_CLOCK -#define ASM_SCHED_CLOCK - -extern void sched_clock_postinit(void); -extern void setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate); - -extern unsigned long long (*sched_clock_func)(void); - -#endif diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index 5f3338eacad2..97cb0576d07c 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -16,7 +16,7 @@ CFLAGS_REMOVE_return_address.o = -pg # Object file lists. obj-y := elf.o entry-armv.o entry-common.o irq.o opcodes.o \ - process.o ptrace.o return_address.o sched_clock.o \ + process.o ptrace.o return_address.o \ setup.o signal.o stacktrace.o sys_arm.o time.o traps.o obj-$(CONFIG_ATAGS) += atags_parse.o diff --git a/arch/arm/kernel/arch_timer.c b/arch/arm/kernel/arch_timer.c index 59dcdced6e30..221f07b11ccb 100644 --- a/arch/arm/kernel/arch_timer.c +++ b/arch/arm/kernel/arch_timer.c @@ -11,9 +11,9 @@ #include #include #include +#include #include -#include #include diff --git a/arch/arm/kernel/sched_clock.c b/arch/arm/kernel/sched_clock.c deleted file mode 100644 index a781c59b93c0..000000000000 --- a/arch/arm/kernel/sched_clock.c +++ /dev/null @@ -1,216 +0,0 @@ -/* - * sched_clock.c: support for extending counters to full 64-bit ns counter - * - * 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 - * published by the Free Software Foundation. - */ -#include -#include -#include -#include -#include -#include -#include -#include - -#include - -struct clock_data { - u64 epoch_ns; - u32 epoch_cyc; - u32 epoch_cyc_copy; - unsigned long rate; - u32 mult; - u32 shift; - bool suspended; -}; - -static void sched_clock_poll(unsigned long wrap_ticks); -static DEFINE_TIMER(sched_clock_timer, sched_clock_poll, 0, 0); -static int irqtime = -1; - -core_param(irqtime, irqtime, int, 0400); - -static struct clock_data cd = { - .mult = NSEC_PER_SEC / HZ, -}; - -static u32 __read_mostly sched_clock_mask = 0xffffffff; - -static u32 notrace jiffy_sched_clock_read(void) -{ - return (u32)(jiffies - INITIAL_JIFFIES); -} - -static u32 __read_mostly (*read_sched_clock)(void) = jiffy_sched_clock_read; - -static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift) -{ - return (cyc * mult) >> shift; -} - -static unsigned long long notrace cyc_to_sched_clock(u32 cyc, u32 mask) -{ - u64 epoch_ns; - u32 epoch_cyc; - - /* - * Load the epoch_cyc and epoch_ns atomically. We do this by - * ensuring that we always write epoch_cyc, epoch_ns and - * epoch_cyc_copy in strict order, and read them in strict order. - * If epoch_cyc and epoch_cyc_copy are not equal, then we're in - * the middle of an update, and we should repeat the load. - */ - do { - epoch_cyc = cd.epoch_cyc; - smp_rmb(); - epoch_ns = cd.epoch_ns; - smp_rmb(); - } while (epoch_cyc != cd.epoch_cyc_copy); - - return epoch_ns + cyc_to_ns((cyc - epoch_cyc) & mask, cd.mult, cd.shift); -} - -/* - * Atomically update the sched_clock epoch. - */ -static void notrace update_sched_clock(void) -{ - unsigned long flags; - u32 cyc; - u64 ns; - - cyc = read_sched_clock(); - ns = cd.epoch_ns + - cyc_to_ns((cyc - cd.epoch_cyc) & sched_clock_mask, - cd.mult, cd.shift); - /* - * Write epoch_cyc and epoch_ns in a way that the update is - * detectable in cyc_to_fixed_sched_clock(). - */ - raw_local_irq_save(flags); - cd.epoch_cyc_copy = cyc; - smp_wmb(); - cd.epoch_ns = ns; - smp_wmb(); - cd.epoch_cyc = cyc; - raw_local_irq_restore(flags); -} - -static void sched_clock_poll(unsigned long wrap_ticks) -{ - mod_timer(&sched_clock_timer, round_jiffies(jiffies + wrap_ticks)); - update_sched_clock(); -} - -void __init setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate) -{ - unsigned long r, w; - u64 res, wrap; - char r_unit; - - if (cd.rate > rate) - return; - - BUG_ON(bits > 32); - WARN_ON(!irqs_disabled()); - read_sched_clock = read; - sched_clock_mask = (1 << bits) - 1; - cd.rate = rate; - - /* calculate the mult/shift to convert counter ticks to ns. */ - clocks_calc_mult_shift(&cd.mult, &cd.shift, rate, NSEC_PER_SEC, 0); - - r = rate; - if (r >= 4000000) { - r /= 1000000; - r_unit = 'M'; - } else if (r >= 1000) { - r /= 1000; - r_unit = 'k'; - } else - r_unit = ' '; - - /* calculate how many ns until we wrap */ - wrap = cyc_to_ns((1ULL << bits) - 1, cd.mult, cd.shift); - do_div(wrap, NSEC_PER_MSEC); - w = wrap; - - /* calculate the ns resolution of this counter */ - res = cyc_to_ns(1ULL, cd.mult, cd.shift); - pr_info("sched_clock: %u bits at %lu%cHz, resolution %lluns, wraps every %lums\n", - bits, r, r_unit, res, w); - - /* - * Start the timer to keep sched_clock() properly updated and - * sets the initial epoch. - */ - sched_clock_timer.data = msecs_to_jiffies(w - (w / 10)); - update_sched_clock(); - - /* - * Ensure that sched_clock() starts off at 0ns - */ - cd.epoch_ns = 0; - - /* Enable IRQ time accounting if we have a fast enough sched_clock */ - if (irqtime > 0 || (irqtime == -1 && rate >= 1000000)) - enable_sched_clock_irqtime(); - - pr_debug("Registered %pF as sched_clock source\n", read); -} - -static unsigned long long notrace sched_clock_32(void) -{ - u32 cyc = read_sched_clock(); - return cyc_to_sched_clock(cyc, sched_clock_mask); -} - -unsigned long long __read_mostly (*sched_clock_func)(void) = sched_clock_32; - -unsigned long long notrace sched_clock(void) -{ - if (cd.suspended) - return cd.epoch_ns; - - return sched_clock_func(); -} - -void __init sched_clock_postinit(void) -{ - /* - * If no sched_clock function has been provided at that point, - * make it the final one one. - */ - if (read_sched_clock == jiffy_sched_clock_read) - setup_sched_clock(jiffy_sched_clock_read, 32, HZ); - - sched_clock_poll(sched_clock_timer.data); -} - -static int sched_clock_suspend(void) -{ - sched_clock_poll(sched_clock_timer.data); - cd.suspended = true; - return 0; -} - -static void sched_clock_resume(void) -{ - cd.epoch_cyc = read_sched_clock(); - cd.epoch_cyc_copy = cd.epoch_cyc; - cd.suspended = false; -} - -static struct syscore_ops sched_clock_ops = { - .suspend = sched_clock_suspend, - .resume = sched_clock_resume, -}; - -static int __init sched_clock_syscore_init(void) -{ - register_syscore_ops(&sched_clock_ops); - return 0; -} -device_initcall(sched_clock_syscore_init); diff --git a/arch/arm/kernel/time.c b/arch/arm/kernel/time.c index abff4e9aaee0..98aee3258398 100644 --- a/arch/arm/kernel/time.c +++ b/arch/arm/kernel/time.c @@ -24,9 +24,9 @@ #include #include #include +#include #include -#include #include #include #include @@ -120,6 +120,4 @@ void __init time_init(void) machine_desc->init_time(); else clocksource_of_init(); - - sched_clock_postinit(); } diff --git a/arch/arm/mach-davinci/time.c b/arch/arm/mach-davinci/time.c index bad361ec1666..7a55b5c95971 100644 --- a/arch/arm/mach-davinci/time.c +++ b/arch/arm/mach-davinci/time.c @@ -18,8 +18,8 @@ #include #include #include +#include -#include #include #include diff --git a/arch/arm/mach-imx/time.c b/arch/arm/mach-imx/time.c index fea91313678b..cd46529e9eaa 100644 --- a/arch/arm/mach-imx/time.c +++ b/arch/arm/mach-imx/time.c @@ -26,8 +26,8 @@ #include #include #include +#include -#include #include #include "common.h" diff --git a/arch/arm/mach-integrator/integrator_ap.c b/arch/arm/mach-integrator/integrator_ap.c index b23c8e4f28e8..aa4346227c41 100644 --- a/arch/arm/mach-integrator/integrator_ap.c +++ b/arch/arm/mach-integrator/integrator_ap.c @@ -41,6 +41,7 @@ #include #include #include +#include #include