From c74f8056621738f5be9f5d3d7e0caa927b21aef6 Mon Sep 17 00:00:00 2001 From: Stanley Chu Date: Mon, 16 Sep 2019 23:56:49 +0800 Subject: scsi: core: allow auto suspend override by low-level driver Rework from previous work by: Sujit Reddy Thumma Until now the scsi mid-layer forbids runtime suspend till userspace enables it. This is mainly to quarantine some disks with broken runtime power management or have high latencies executing suspend resume callbacks. If the userspace doesn't enable the runtime suspend the underlying hardware will be always on even when it is not doing any useful work and thus wasting power. Some low-level drivers for the controllers can efficiently use runtime power management to reduce power consumption and improve battery life. Allow runtime suspend parameters override within the LLD itself instead of waiting for userspace to control the power management. Link: https://lore.kernel.org/r/1568649411-5127-2-git-send-email-stanley.chu@mediatek.com Reviewed-by: Avri Altman Reviewed-by: Bart Van Assche Signed-off-by: Stanley Chu Signed-off-by: Martin K. Petersen --- include/scsi/scsi_device.h | 3 ++- include/scsi/scsi_host.h | 3 +++ 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index 202f4d6a4342..039e289f295e 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -199,7 +199,8 @@ struct scsi_device { unsigned broken_fua:1; /* Don't set FUA bit */ unsigned lun_in_cdb:1; /* Store LUN bits in CDB[1] */ unsigned unmap_limit_for_ws:1; /* Use the UNMAP limit for WRITE SAME */ - + unsigned rpm_autosuspend:1; /* Enable runtime autosuspend at device + * creation time */ atomic_t disk_events_disable_depth; /* disable depth for disk events */ DECLARE_BITMAP(supported_events, SDEV_EVT_MAXBITS); /* supported events */ diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h index 31e0d6ca1eba..2c3f0c58869b 100644 --- a/include/scsi/scsi_host.h +++ b/include/scsi/scsi_host.h @@ -486,6 +486,9 @@ struct scsi_host_template { */ unsigned int cmd_size; struct scsi_host_cmd_pool *cmd_pool; + + /* Delay for runtime autosuspend */ + int rpm_autosuspend_delay; }; /* -- cgit v1.2.3 From d188b0675b21d5a6ca27b3e741381813983f4719 Mon Sep 17 00:00:00 2001 From: Ryan Attard Date: Thu, 26 Sep 2019 11:22:17 -0500 Subject: scsi: core: Add sysfs attributes for VPD pages 0h and 89h Add sysfs attributes for the ATA information page and Supported VPD Pages page. Link: https://lore.kernel.org/r/20190926162216.56591-1-ryanattard@ryanattard.info Signed-off-by: Ryan Attard Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi.c | 4 ++++ drivers/scsi/scsi_sysfs.c | 19 +++++++++++++++++++ include/scsi/scsi_device.h | 2 ++ 3 files changed, 25 insertions(+) (limited to 'include') diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c index 1f5b5c8a7f72..4f76841a7038 100644 --- a/drivers/scsi/scsi.c +++ b/drivers/scsi/scsi.c @@ -465,10 +465,14 @@ void scsi_attach_vpd(struct scsi_device *sdev) return; for (i = 4; i < vpd_buf->len; i++) { + if (vpd_buf->data[i] == 0x0) + scsi_update_vpd_page(sdev, 0x0, &sdev->vpd_pg0); if (vpd_buf->data[i] == 0x80) scsi_update_vpd_page(sdev, 0x80, &sdev->vpd_pg80); if (vpd_buf->data[i] == 0x83) scsi_update_vpd_page(sdev, 0x83, &sdev->vpd_pg83); + if (vpd_buf->data[i] == 0x89) + scsi_update_vpd_page(sdev, 0x89, &sdev->vpd_pg89); } kfree(vpd_buf); } diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index cebb9336c02b..2c76d7a43f67 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -437,6 +437,7 @@ static void scsi_device_dev_release_usercontext(struct work_struct *work) struct device *parent; struct list_head *this, *tmp; struct scsi_vpd *vpd_pg80 = NULL, *vpd_pg83 = NULL; + struct scsi_vpd *vpd_pg0 = NULL, *vpd_pg89 = NULL; unsigned long flags; sdev = container_of(work, struct scsi_device, ew.work); @@ -466,16 +467,24 @@ static void scsi_device_dev_release_usercontext(struct work_struct *work) sdev->request_queue = NULL; mutex_lock(&sdev->inquiry_mutex); + rcu_swap_protected(sdev->vpd_pg0, vpd_pg0, + lockdep_is_held(&sdev->inquiry_mutex)); rcu_swap_protected(sdev->vpd_pg80, vpd_pg80, lockdep_is_held(&sdev->inquiry_mutex)); rcu_swap_protected(sdev->vpd_pg83, vpd_pg83, lockdep_is_held(&sdev->inquiry_mutex)); + rcu_swap_protected(sdev->vpd_pg89, vpd_pg89, + lockdep_is_held(&sdev->inquiry_mutex)); mutex_unlock(&sdev->inquiry_mutex); + if (vpd_pg0) + kfree_rcu(vpd_pg0, rcu); if (vpd_pg83) kfree_rcu(vpd_pg83, rcu); if (vpd_pg80) kfree_rcu(vpd_pg80, rcu); + if (vpd_pg89) + kfree_rcu(vpd_pg89, rcu); kfree(sdev->inquiry); kfree(sdev); @@ -859,6 +868,8 @@ static struct bin_attribute dev_attr_vpd_##_page = { \ sdev_vpd_pg_attr(pg83); sdev_vpd_pg_attr(pg80); +sdev_vpd_pg_attr(pg89); +sdev_vpd_pg_attr(pg0); static ssize_t show_inquiry(struct file *filep, struct kobject *kobj, struct bin_attribute *bin_attr, @@ -1191,12 +1202,18 @@ static umode_t scsi_sdev_bin_attr_is_visible(struct kobject *kobj, struct scsi_device *sdev = to_scsi_device(dev); + if (attr == &dev_attr_vpd_pg0 && !sdev->vpd_pg0) + return 0; + if (attr == &dev_attr_vpd_pg80 && !sdev->vpd_pg80) return 0; if (attr == &dev_attr_vpd_pg83 && !sdev->vpd_pg83) return 0; + if (attr == &dev_attr_vpd_pg89 && !sdev->vpd_pg89) + return 0; + return S_IRUGO; } @@ -1239,8 +1256,10 @@ static struct attribute *scsi_sdev_attrs[] = { }; static struct bin_attribute *scsi_sdev_bin_attrs[] = { + &dev_attr_vpd_pg0, &dev_attr_vpd_pg83, &dev_attr_vpd_pg80, + &dev_attr_vpd_pg89, &dev_attr_inquiry, NULL }; diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index 039e289f295e..3ed836db5306 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -140,8 +140,10 @@ struct scsi_device { const char * rev; /* ... "nullnullnullnull" before scan */ #define SCSI_VPD_PG_LEN 255 + struct scsi_vpd __rcu *vpd_pg0; struct scsi_vpd __rcu *vpd_pg83; struct scsi_vpd __rcu *vpd_pg80; + struct scsi_vpd __rcu *vpd_pg89; unsigned char current_tag; /* current tag */ struct scsi_target *sdev_target; /* used only for single_lun */ -- cgit v1.2.3 From a14b820316e84310b1bad3701a8d4c9159377633 Mon Sep 17 00:00:00 2001 From: Vivek Gautam Date: Thu, 18 Jul 2019 18:32:36 +0530 Subject: soc: qcom: llcc cleanup to get rid of sdm845 specific driver file A single file should suffice the need to program the llcc for various platforms. Get rid of sdm845 specific driver file to make way for a more generic driver. Signed-off-by: Vivek Gautam Signed-off-by: Bjorn Andersson --- drivers/soc/qcom/Kconfig | 14 ++---- drivers/soc/qcom/Makefile | 1 - drivers/soc/qcom/llcc-sdm845.c | 100 ------------------------------------- drivers/soc/qcom/llcc-slice.c | 60 +++++++++++++++++++--- include/linux/soc/qcom/llcc-qcom.h | 57 ++++++++------------- 5 files changed, 77 insertions(+), 155 deletions(-) delete mode 100644 drivers/soc/qcom/llcc-sdm845.c (limited to 'include') diff --git a/drivers/soc/qcom/Kconfig b/drivers/soc/qcom/Kconfig index 661e47acc354..c6df8b43fa6d 100644 --- a/drivers/soc/qcom/Kconfig +++ b/drivers/soc/qcom/Kconfig @@ -58,17 +58,9 @@ config QCOM_LLCC depends on ARCH_QCOM || COMPILE_TEST help Qualcomm Technologies, Inc. platform specific - Last Level Cache Controller(LLCC) driver. This provides interfaces - to clients that use the LLCC. Say yes here to enable LLCC slice - driver. - -config QCOM_SDM845_LLCC - tristate "Qualcomm Technologies, Inc. SDM845 LLCC driver" - depends on QCOM_LLCC - help - Say yes here to enable the LLCC driver for SDM845. This provides - data required to configure LLCC so that clients can start using the - LLCC slices. + Last Level Cache Controller(LLCC) driver for platforms such as, + SDM845. This provides interfaces to clients that use the LLCC. + Say yes here to enable LLCC slice driver. config QCOM_MDT_LOADER tristate diff --git a/drivers/soc/qcom/Makefile b/drivers/soc/qcom/Makefile index 162788701a77..28d45b2e87e8 100644 --- a/drivers/soc/qcom/Makefile +++ b/drivers/soc/qcom/Makefile @@ -22,6 +22,5 @@ obj-$(CONFIG_QCOM_SOCINFO) += socinfo.o obj-$(CONFIG_QCOM_WCNSS_CTRL) += wcnss_ctrl.o obj-$(CONFIG_QCOM_APR) += apr.o obj-$(CONFIG_QCOM_LLCC) += llcc-slice.o -obj-$(CONFIG_QCOM_SDM845_LLCC) += llcc-sdm845.o obj-$(CONFIG_QCOM_RPMHPD) += rpmhpd.o obj-$(CONFIG_QCOM_RPMPD) += rpmpd.o diff --git a/drivers/soc/qcom/llcc-sdm845.c b/drivers/soc/qcom/llcc-sdm845.c deleted file mode 100644 index 86600d97c36d..000000000000 --- a/drivers/soc/qcom/llcc-sdm845.c +++ /dev/null @@ -1,100 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (c) 2017-2018, The Linux Foundation. All rights reserved. - * - */ - -#include -#include -#include -#include -#include - -/* - * SCT(System Cache Table) entry contains of the following members: - * usecase_id: Unique id for the client's use case - * slice_id: llcc slice id for each client - * max_cap: The maximum capacity of the cache slice provided in KB - * priority: Priority of the client used to select victim line for replacement - * fixed_size: Boolean indicating if the slice has a fixed capacity - * bonus_ways: Bonus ways are additional ways to be used for any slice, - * if client ends up using more than reserved cache ways. Bonus - * ways are allocated only if they are not reserved for some - * other client. - * res_ways: Reserved ways for the cache slice, the reserved ways cannot - * be used by any other client than the one its assigned to. - * cache_mode: Each slice operates as a cache, this controls the mode of the - * slice: normal or TCM(Tightly Coupled Memory) - * probe_target_ways: Determines what ways to probe for access hit. When - * configured to 1 only bonus and reserved ways are probed. - * When configured to 0 all ways in llcc are probed. - * dis_cap_alloc: Disable capacity based allocation for a client - * retain_on_pc: If this bit is set and client has maintained active vote - * then the ways assigned to this client are not flushed on power - * collapse. - * activate_on_init: Activate the slice immediately after the SCT is programmed - */ -#define SCT_ENTRY(uid, sid, mc, p, fs, bway, rway, cmod, ptw, dca, rp, a) \ - { \ - .usecase_id = uid, \ - .slice_id = sid, \ - .max_cap = mc, \ - .priority = p, \ - .fixed_size = fs, \ - .bonus_ways = bway, \ - .res_ways = rway, \ - .cache_mode = cmod, \ - .probe_target_ways = ptw, \ - .dis_cap_alloc = dca, \ - .retain_on_pc = rp, \ - .activate_on_init = a, \ - } - -static struct llcc_slice_config sdm845_data[] = { - SCT_ENTRY(LLCC_CPUSS, 1, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 1), - SCT_ENTRY(LLCC_VIDSC0, 2, 512, 2, 1, 0x0, 0x0f0, 0, 0, 1, 1, 0), - SCT_ENTRY(LLCC_VIDSC1, 3, 512, 2, 1, 0x0, 0x0f0, 0, 0, 1, 1, 0), - SCT_ENTRY(LLCC_ROTATOR, 4, 563, 2, 1, 0x0, 0x00e, 2, 0, 1, 1, 0), - SCT_ENTRY(LLCC_VOICE, 5, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 0), - SCT_ENTRY(LLCC_AUDIO, 6, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 0), - SCT_ENTRY(LLCC_MDMHPGRW, 7, 1024, 2, 0, 0xfc, 0xf00, 0, 0, 1, 1, 0), - SCT_ENTRY(LLCC_MDM, 8, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 0), - SCT_ENTRY(LLCC_CMPT, 10, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 0), - SCT_ENTRY(LLCC_GPUHTW, 11, 512, 1, 1, 0xc, 0x0, 0, 0, 1, 1, 0), - SCT_ENTRY(LLCC_GPU, 12, 2304, 1, 0, 0xff0, 0x2, 0, 0, 1, 1, 0), - SCT_ENTRY(LLCC_MMUHWT, 13, 256, 2, 0, 0x0, 0x1, 0, 0, 1, 0, 1), - SCT_ENTRY(LLCC_CMPTDMA, 15, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 0), - SCT_ENTRY(LLCC_DISP, 16, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 0), - SCT_ENTRY(LLCC_VIDFW, 17, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 0), - SCT_ENTRY(LLCC_MDMHPFX, 20, 1024, 2, 1, 0x0, 0xf00, 0, 0, 1, 1, 0), - SCT_ENTRY(LLCC_MDMPNG, 21, 1024, 0, 1, 0x1e, 0x0, 0, 0, 1, 1, 0), - SCT_ENTRY(LLCC_AUDHW, 22, 1024, 1, 1, 0xffc, 0x2, 0, 0, 1, 1, 0), -}; - -static int sdm845_qcom_llcc_remove(struct platform_device *pdev) -{ - return qcom_llcc_remove(pdev); -} - -static int sdm845_qcom_llcc_probe(struct platform_device *pdev) -{ - return qcom_llcc_probe(pdev, sdm845_data, ARRAY_SIZE(sdm845_data)); -} - -static const struct of_device_id sdm845_qcom_llcc_of_match[] = { - { .compatible = "qcom,sdm845-llcc", }, - { } -}; - -static struct platform_driver sdm845_qcom_llcc_driver = { - .driver = { - .name = "sdm845-llcc", - .of_match_table = sdm845_qcom_llcc_of_match, - }, - .probe = sdm845_qcom_llcc_probe, - .remove = sdm845_qcom_llcc_remove, -}; -module_platform_driver(sdm845_qcom_llcc_driver); - -MODULE_DESCRIPTION("QCOM sdm845 LLCC driver"); -MODULE_LICENSE("GPL v2"); diff --git a/drivers/soc/qcom/llcc-slice.c b/drivers/soc/qcom/llcc-slice.c index 9090ea12eaf3..574bb5bf20bc 100644 --- a/drivers/soc/qcom/llcc-slice.c +++ b/drivers/soc/qcom/llcc-slice.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Copyright (c) 2017-2018, The Linux Foundation. All rights reserved. + * Copyright (c) 2017-2019, The Linux Foundation. All rights reserved. * */ @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -46,6 +47,27 @@ #define BANK_OFFSET_STRIDE 0x80000 +static struct llcc_slice_config sdm845_data[] = { + { LLCC_CPUSS, 1, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 1 }, + { LLCC_VIDSC0, 2, 512, 2, 1, 0x0, 0x0f0, 0, 0, 1, 1, 0 }, + { LLCC_VIDSC1, 3, 512, 2, 1, 0x0, 0x0f0, 0, 0, 1, 1, 0 }, + { LLCC_ROTATOR, 4, 563, 2, 1, 0x0, 0x00e, 2, 0, 1, 1, 0 }, + { LLCC_VOICE, 5, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 0 }, + { LLCC_AUDIO, 6, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 0 }, + { LLCC_MDMHPGRW, 7, 1024, 2, 0, 0xfc, 0xf00, 0, 0, 1, 1, 0 }, + { LLCC_MDM, 8, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 0 }, + { LLCC_CMPT, 10, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 0 }, + { LLCC_GPUHTW, 11, 512, 1, 1, 0xc, 0x0, 0, 0, 1, 1, 0 }, + { LLCC_GPU, 12, 2304, 1, 0, 0xff0, 0x2, 0, 0, 1, 1, 0 }, + { LLCC_MMUHWT, 13, 256, 2, 0, 0x0, 0x1, 0, 0, 1, 0, 1 }, + { LLCC_CMPTDMA, 15, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 0 }, + { LLCC_DISP, 16, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 0 }, + { LLCC_VIDFW, 17, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 0 }, + { LLCC_MDMHPFX, 20, 1024, 2, 1, 0x0, 0xf00, 0, 0, 1, 1, 0 }, + { LLCC_MDMPNG, 21, 1024, 0, 1, 0x1e, 0x0, 0, 0, 1, 1, 0 }, + { LLCC_AUDHW, 22, 1024, 1, 1, 0xffc, 0x2, 0, 0, 1, 1, 0 }, +}; + static struct llcc_drv_data *drv_data = (void *) -EPROBE_DEFER; static const struct regmap_config llcc_regmap_config = { @@ -301,13 +323,12 @@ static int qcom_llcc_cfg_program(struct platform_device *pdev) return ret; } -int qcom_llcc_remove(struct platform_device *pdev) +static int qcom_llcc_remove(struct platform_device *pdev) { /* Set the global pointer to a error code to avoid referencing it */ drv_data = ERR_PTR(-ENODEV); return 0; } -EXPORT_SYMBOL_GPL(qcom_llcc_remove); static struct regmap *qcom_llcc_init_mmio(struct platform_device *pdev, const char *name) @@ -326,8 +347,8 @@ static struct regmap *qcom_llcc_init_mmio(struct platform_device *pdev, return devm_regmap_init_mmio(&pdev->dev, base, &llcc_regmap_config); } -int qcom_llcc_probe(struct platform_device *pdev, - const struct llcc_slice_config *llcc_cfg, u32 sz) +static int qcom_llcc_probe(struct platform_device *pdev, + const struct llcc_slice_config *llcc_cfg, u32 sz) { u32 num_banks; struct device *dev = &pdev->dev; @@ -407,6 +428,31 @@ err: drv_data = ERR_PTR(-ENODEV); return ret; } -EXPORT_SYMBOL_GPL(qcom_llcc_probe); + +static int sdm845_qcom_llcc_remove(struct platform_device *pdev) +{ + return qcom_llcc_remove(pdev); +} + +static int sdm845_qcom_llcc_probe(struct platform_device *pdev) +{ + return qcom_llcc_probe(pdev, sdm845_data, ARRAY_SIZE(sdm845_data)); +} + +static const struct of_device_id sdm845_qcom_llcc_of_match[] = { + { .compatible = "qcom,sdm845-llcc", }, + { } +}; + +static struct platform_driver sdm845_qcom_llcc_driver = { + .driver = { + .name = "sdm845-llcc", + .of_match_table = sdm845_qcom_llcc_of_match, + }, + .probe = sdm845_qcom_llcc_probe, + .remove = sdm845_qcom_llcc_remove, +}; +module_platform_driver(sdm845_qcom_llcc_driver); + +MODULE_DESCRIPTION("QCOM sdm845 LLCC driver"); MODULE_LICENSE("GPL v2"); -MODULE_DESCRIPTION("Qualcomm Last Level Cache Controller"); diff --git a/include/linux/soc/qcom/llcc-qcom.h b/include/linux/soc/qcom/llcc-qcom.h index eb71a50b8afc..d5cad6f7953c 100644 --- a/include/linux/soc/qcom/llcc-qcom.h +++ b/include/linux/soc/qcom/llcc-qcom.h @@ -39,18 +39,27 @@ struct llcc_slice_desc { /** * llcc_slice_config - Data associated with the llcc slice - * @usecase_id: usecase id for which the llcc slice is used - * @slice_id: llcc slice id assigned to each slice - * @max_cap: maximum capacity of the llcc slice - * @priority: priority of the llcc slice - * @fixed_size: whether the llcc slice can grow beyond its size - * @bonus_ways: bonus ways associated with llcc slice - * @res_ways: reserved ways associated with llcc slice - * @cache_mode: mode of the llcc slice - * @probe_target_ways: Probe only reserved and bonus ways on a cache miss - * @dis_cap_alloc: Disable capacity based allocation - * @retain_on_pc: Retain through power collapse - * @activate_on_init: activate the slice on init + * @usecase_id: Unique id for the client's use case + * @slice_id: llcc slice id for each client + * @max_cap: The maximum capacity of the cache slice provided in KB + * @priority: Priority of the client used to select victim line for replacement + * @fixed_size: Boolean indicating if the slice has a fixed capacity + * @bonus_ways: Bonus ways are additional ways to be used for any slice, + * if client ends up using more than reserved cache ways. Bonus + * ways are allocated only if they are not reserved for some + * other client. + * @res_ways: Reserved ways for the cache slice, the reserved ways cannot + * be used by any other client than the one its assigned to. + * @cache_mode: Each slice operates as a cache, this controls the mode of the + * slice: normal or TCM(Tightly Coupled Memory) + * @probe_target_ways: Determines what ways to probe for access hit. When + * configured to 1 only bonus and reserved ways are probed. + * When configured to 0 all ways in llcc are probed. + * @dis_cap_alloc: Disable capacity based allocation for a client + * @retain_on_pc: If this bit is set and client has maintained active vote + * then the ways assigned to this client are not flushed on power + * collapse. + * @activate_on_init: Activate the slice immediately after it is programmed */ struct llcc_slice_config { u32 usecase_id; @@ -154,20 +163,6 @@ int llcc_slice_activate(struct llcc_slice_desc *desc); */ int llcc_slice_deactivate(struct llcc_slice_desc *desc); -/** - * qcom_llcc_probe - program the sct table - * @pdev: platform device pointer - * @table: soc sct table - * @sz: Size of the config table - */ -int qcom_llcc_probe(struct platform_device *pdev, - const struct llcc_slice_config *table, u32 sz); - -/** - * qcom_llcc_remove - remove the sct table - * @pdev: Platform device pointer - */ -int qcom_llcc_remove(struct platform_device *pdev); #else static inline struct llcc_slice_desc *llcc_slice_getd(u32 uid) { @@ -197,16 +192,6 @@ static inline int llcc_slice_deactivate(struct llcc_slice_desc *desc) { return -EINVAL; } -static inline int qcom_llcc_probe(struct platform_device *pdev, - const struct llcc_slice_config *table, u32 sz) -{ - return -ENODEV; -} - -static inline int qcom_llcc_remove(struct platform_device *pdev) -{ - return -ENODEV; -} #endif #endif -- cgit v1.2.3 From 99356b03b431f9589bbaec2bc5bacceccb3dd99a Mon Sep 17 00:00:00 2001 From: Vivek Gautam Date: Thu, 18 Jul 2019 18:32:38 +0530 Subject: soc: qcom: Make llcc-qcom a generic driver This makes way for adding future llcc versions. Also pull out the llcc-qcom specific definitions from includes. Includes path now contains the only definitions that are to be exposed to other subsystems. Signed-off-by: Vivek Gautam Signed-off-by: Bjorn Andersson --- drivers/soc/qcom/llcc-qcom.c | 137 +++++++++++++++++++++++++++++++------ include/linux/soc/qcom/llcc-qcom.h | 89 ------------------------ 2 files changed, 116 insertions(+), 110 deletions(-) (limited to 'include') diff --git a/drivers/soc/qcom/llcc-qcom.c b/drivers/soc/qcom/llcc-qcom.c index 574bb5bf20bc..98563ef0ac6b 100644 --- a/drivers/soc/qcom/llcc-qcom.c +++ b/drivers/soc/qcom/llcc-qcom.c @@ -47,6 +47,100 @@ #define BANK_OFFSET_STRIDE 0x80000 +/** + * llcc_slice_config - Data associated with the llcc slice + * @usecase_id: Unique id for the client's use case + * @slice_id: llcc slice id for each client + * @max_cap: The maximum capacity of the cache slice provided in KB + * @priority: Priority of the client used to select victim line for replacement + * @fixed_size: Boolean indicating if the slice has a fixed capacity + * @bonus_ways: Bonus ways are additional ways to be used for any slice, + * if client ends up using more than reserved cache ways. Bonus + * ways are allocated only if they are not reserved for some + * other client. + * @res_ways: Reserved ways for the cache slice, the reserved ways cannot + * be used by any other client than the one its assigned to. + * @cache_mode: Each slice operates as a cache, this controls the mode of the + * slice: normal or TCM(Tightly Coupled Memory) + * @probe_target_ways: Determines what ways to probe for access hit. When + * configured to 1 only bonus and reserved ways are probed. + * When configured to 0 all ways in llcc are probed. + * @dis_cap_alloc: Disable capacity based allocation for a client + * @retain_on_pc: If this bit is set and client has maintained active vote + * then the ways assigned to this client are not flushed on power + * collapse. + * @activate_on_init: Activate the slice immediately after it is programmed + */ +struct llcc_slice_config { + u32 usecase_id; + u32 slice_id; + u32 max_cap; + u32 priority; + bool fixed_size; + u32 bonus_ways; + u32 res_ways; + u32 cache_mode; + u32 probe_target_ways; + bool dis_cap_alloc; + bool retain_on_pc; + bool activate_on_init; +}; + +/** + * llcc_drv_data - Data associated with the llcc driver + * @regmap: regmap associated with the llcc device + * @bcast_regmap: regmap associated with llcc broadcast offset + * @cfg: pointer to the data structure for slice configuration + * @lock: mutex associated with each slice + * @cfg_size: size of the config data table + * @max_slices: max slices as read from device tree + * @num_banks: Number of llcc banks + * @bitmap: Bit map to track the active slice ids + * @offsets: Pointer to the bank offsets array + * @ecc_irq: interrupt for llcc cache error detection and reporting + */ +struct llcc_drv_data { + struct regmap *regmap; + struct regmap *bcast_regmap; + const struct llcc_slice_config *cfg; + struct mutex lock; + u32 cfg_size; + u32 max_slices; + u32 num_banks; + unsigned long *bitmap; + u32 *offsets; + int ecc_irq; +}; + +/** + * llcc_edac_reg_data - llcc edac registers data for each error type + * @name: Name of the error + * @synd_reg: Syndrome register address + * @count_status_reg: Status register address to read the error count + * @ways_status_reg: Status register address to read the error ways + * @reg_cnt: Number of registers + * @count_mask: Mask value to get the error count + * @ways_mask: Mask value to get the error ways + * @count_shift: Shift value to get the error count + * @ways_shift: Shift value to get the error ways + */ +struct llcc_edac_reg_data { + char *name; + u64 synd_reg; + u64 count_status_reg; + u64 ways_status_reg; + u32 reg_cnt; + u32 count_mask; + u32 ways_mask; + u8 count_shift; + u8 ways_shift; +}; + +struct qcom_llcc_config { + const struct llcc_slice_config *sct_data; + int size; +}; + static struct llcc_slice_config sdm845_data[] = { { LLCC_CPUSS, 1, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 1 }, { LLCC_VIDSC0, 2, 512, 2, 1, 0x0, 0x0f0, 0, 0, 1, 1, 0 }, @@ -68,6 +162,11 @@ static struct llcc_slice_config sdm845_data[] = { { LLCC_AUDHW, 22, 1024, 1, 1, 0xffc, 0x2, 0, 0, 1, 1, 0 }, }; +static const struct qcom_llcc_config sdm845_cfg = { + .sct_data = sdm845_data, + .size = ARRAY_SIZE(sdm845_data), +}; + static struct llcc_drv_data *drv_data = (void *) -EPROBE_DEFER; static const struct regmap_config llcc_regmap_config = { @@ -347,13 +446,15 @@ static struct regmap *qcom_llcc_init_mmio(struct platform_device *pdev, return devm_regmap_init_mmio(&pdev->dev, base, &llcc_regmap_config); } -static int qcom_llcc_probe(struct platform_device *pdev, - const struct llcc_slice_config *llcc_cfg, u32 sz) +static int qcom_llcc_probe(struct platform_device *pdev) { u32 num_banks; struct device *dev = &pdev->dev; int ret, i; struct platform_device *llcc_edac; + const struct qcom_llcc_config *cfg; + const struct llcc_slice_config *llcc_cfg; + u32 sz; drv_data = devm_kzalloc(dev, sizeof(*drv_data), GFP_KERNEL); if (!drv_data) { @@ -383,6 +484,10 @@ static int qcom_llcc_probe(struct platform_device *pdev, num_banks >>= LLCC_LB_CNT_SHIFT; drv_data->num_banks = num_banks; + cfg = of_device_get_match_data(&pdev->dev); + llcc_cfg = cfg->sct_data; + sz = cfg->size; + for (i = 0; i < sz; i++) if (llcc_cfg[i].slice_id > drv_data->max_slices) drv_data->max_slices = llcc_cfg[i].slice_id; @@ -429,30 +534,20 @@ err: return ret; } -static int sdm845_qcom_llcc_remove(struct platform_device *pdev) -{ - return qcom_llcc_remove(pdev); -} - -static int sdm845_qcom_llcc_probe(struct platform_device *pdev) -{ - return qcom_llcc_probe(pdev, sdm845_data, ARRAY_SIZE(sdm845_data)); -} - -static const struct of_device_id sdm845_qcom_llcc_of_match[] = { - { .compatible = "qcom,sdm845-llcc", }, +static const struct of_device_id qcom_llcc_of_match[] = { + { .compatible = "qcom,sdm845-llcc", .data = &sdm845_cfg }, { } }; -static struct platform_driver sdm845_qcom_llcc_driver = { +static struct platform_driver qcom_llcc_driver = { .driver = { - .name = "sdm845-llcc", - .of_match_table = sdm845_qcom_llcc_of_match, + .name = "qcom-llcc", + .of_match_table = qcom_llcc_of_match, }, - .probe = sdm845_qcom_llcc_probe, - .remove = sdm845_qcom_llcc_remove, + .probe = qcom_llcc_probe, + .remove = qcom_llcc_remove, }; -module_platform_driver(sdm845_qcom_llcc_driver); +module_platform_driver(qcom_llcc_driver); -MODULE_DESCRIPTION("QCOM sdm845 LLCC driver"); +MODULE_DESCRIPTION("Qualcomm Last Level Cache Controller"); MODULE_LICENSE("GPL v2"); diff --git a/include/linux/soc/qcom/llcc-qcom.h b/include/linux/soc/qcom/llcc-qcom.h index d5cad6f7953c..c0acdb28fde8 100644 --- a/include/linux/soc/qcom/llcc-qcom.h +++ b/include/linux/soc/qcom/llcc-qcom.h @@ -37,95 +37,6 @@ struct llcc_slice_desc { size_t slice_size; }; -/** - * llcc_slice_config - Data associated with the llcc slice - * @usecase_id: Unique id for the client's use case - * @slice_id: llcc slice id for each client - * @max_cap: The maximum capacity of the cache slice provided in KB - * @priority: Priority of the client used to select victim line for replacement - * @fixed_size: Boolean indicating if the slice has a fixed capacity - * @bonus_ways: Bonus ways are additional ways to be used for any slice, - * if client ends up using more than reserved cache ways. Bonus - * ways are allocated only if they are not reserved for some - * other client. - * @res_ways: Reserved ways for the cache slice, the reserved ways cannot - * be used by any other client than the one its assigned to. - * @cache_mode: Each slice operates as a cache, this controls the mode of the - * slice: normal or TCM(Tightly Coupled Memory) - * @probe_target_ways: Determines what ways to probe for access hit. When - * configured to 1 only bonus and reserved ways are probed. - * When configured to 0 all ways in llcc are probed. - * @dis_cap_alloc: Disable capacity based allocation for a client - * @retain_on_pc: If this bit is set and client has maintained active vote - * then the ways assigned to this client are not flushed on power - * collapse. - * @activate_on_init: Activate the slice immediately after it is programmed - */ -struct llcc_slice_config { - u32 usecase_id; - u32 slice_id; - u32 max_cap; - u32 priority; - bool fixed_size; - u32 bonus_ways; - u32 res_ways; - u32 cache_mode; - u32 probe_target_ways; - bool dis_cap_alloc; - bool retain_on_pc; - bool activate_on_init; -}; - -/** - * llcc_drv_data - Data associated with the llcc driver - * @regmap: regmap associated with the llcc device - * @bcast_regmap: regmap associated with llcc broadcast offset - * @cfg: pointer to the data structure for slice configuration - * @lock: mutex associated with each slice - * @cfg_size: size of the config data table - * @max_slices: max slices as read from device tree - * @num_banks: Number of llcc banks - * @bitmap: Bit map to track the active slice ids - * @offsets: Pointer to the bank offsets array - * @ecc_irq: interrupt for llcc cache error detection and reporting - */ -struct llcc_drv_data { - struct regmap *regmap; - struct regmap *bcast_regmap; - const struct llcc_slice_config *cfg; - struct mutex lock; - u32 cfg_size; - u32 max_slices; - u32 num_banks; - unsigned long *bitmap; - u32 *offsets; - int ecc_irq; -}; - -/** - * llcc_edac_reg_data - llcc edac registers data for each error type - * @name: Name of the error - * @synd_reg: Syndrome register address - * @count_status_reg: Status register address to read the error count - * @ways_status_reg: Status register address to read the error ways - * @reg_cnt: Number of registers - * @count_mask: Mask value to get the error count - * @ways_mask: Mask value to get the error ways - * @count_shift: Shift value to get the error count - * @ways_shift: Shift value to get the error ways - */ -struct llcc_edac_reg_data { - char *name; - u64 synd_reg; - u64 count_status_reg; - u64 ways_status_reg; - u32 reg_cnt; - u32 count_mask; - u32 ways_mask; - u8 count_shift; - u8 ways_shift; -}; - #if IS_ENABLED(CONFIG_QCOM_LLCC) /** * llcc_slice_getd - get llcc slice descriptor -- cgit v1.2.3 From 8cde3c2153e8f57be884c0e73f18bc4de150e870 Mon Sep 17 00:00:00 2001 From: Carlo Caione Date: Wed, 31 Jul 2019 09:23:39 +0100 Subject: firmware: meson_sm: Rework driver as a proper platform driver The secure monitor driver is currently a frankenstein driver which is registered as a platform driver but its functionality goes through a global struct accessed by the consumer drivers using exported helper functions. Try to tidy up the driver moving the firmware struct into the driver data and make the consumer drivers referencing the secure-monitor using a new property in the DT. Currently only the nvmem driver is using this API so we can fix it in the same commit. Reviewed-by: Jerome Brunet Signed-off-by: Carlo Caione Signed-off-by: Kevin Hilman --- drivers/firmware/meson/meson_sm.c | 94 ++++++++++++++++++++++----------- drivers/nvmem/meson-efuse.c | 24 +++++++-- include/linux/firmware/meson/meson_sm.h | 15 +++--- 3 files changed, 94 insertions(+), 39 deletions(-) (limited to 'include') diff --git a/drivers/firmware/meson/meson_sm.c b/drivers/firmware/meson/meson_sm.c index 772ca6726e7b..2e36a2aa274c 100644 --- a/drivers/firmware/meson/meson_sm.c +++ b/drivers/firmware/meson/meson_sm.c @@ -54,8 +54,6 @@ struct meson_sm_firmware { void __iomem *sm_shmem_out_base; }; -static struct meson_sm_firmware fw; - static u32 meson_sm_get_cmd(const struct meson_sm_chip *chip, unsigned int cmd_index) { @@ -90,6 +88,7 @@ static void __iomem *meson_sm_map_shmem(u32 cmd_shmem, unsigned int size) /** * meson_sm_call - generic SMC32 call to the secure-monitor * + * @fw: Pointer to secure-monitor firmware * @cmd_index: Index of the SMC32 function ID * @ret: Returned value * @arg0: SMC32 Argument 0 @@ -100,15 +99,15 @@ static void __iomem *meson_sm_map_shmem(u32 cmd_shmem, unsigned int size) * * Return: 0 on success, a negative value on error */ -int meson_sm_call(unsigned int cmd_index, u32 *ret, u32 arg0, - u32 arg1, u32 arg2, u32 arg3, u32 arg4) +int meson_sm_call(struct meson_sm_firmware *fw, unsigned int cmd_index, + u32 *ret, u32 arg0, u32 arg1, u32 arg2, u32 arg3, u32 arg4) { u32 cmd, lret; - if (!fw.chip) + if (!fw->chip) return -ENOENT; - cmd = meson_sm_get_cmd(fw.chip, cmd_index); + cmd = meson_sm_get_cmd(fw->chip, cmd_index); if (!cmd) return -EINVAL; @@ -124,6 +123,7 @@ EXPORT_SYMBOL(meson_sm_call); /** * meson_sm_call_read - retrieve data from secure-monitor * + * @fw: Pointer to secure-monitor firmware * @buffer: Buffer to store the retrieved data * @bsize: Size of the buffer * @cmd_index: Index of the SMC32 function ID @@ -137,22 +137,23 @@ EXPORT_SYMBOL(meson_sm_call); * When 0 is returned there is no guarantee about the amount of * data read and bsize bytes are copied in buffer. */ -int meson_sm_call_read(void *buffer, unsigned int bsize, unsigned int cmd_index, - u32 arg0, u32 arg1, u32 arg2, u32 arg3, u32 arg4) +int meson_sm_call_read(struct meson_sm_firmware *fw, void *buffer, + unsigned int bsize, unsigned int cmd_index, u32 arg0, + u32 arg1, u32 arg2, u32 arg3, u32 arg4) { u32 size; int ret; - if (!fw.chip) + if (!fw->chip) return -ENOENT; - if (!fw.chip->cmd_shmem_out_base) + if (!fw->chip->cmd_shmem_out_base) return -EINVAL; - if (bsize > fw.chip->shmem_size) + if (bsize > fw->chip->shmem_size) return -EINVAL; - if (meson_sm_call(cmd_index, &size, arg0, arg1, arg2, arg3, arg4) < 0) + if (meson_sm_call(fw, cmd_index, &size, arg0, arg1, arg2, arg3, arg4) < 0) return -EINVAL; if (size > bsize) @@ -164,7 +165,7 @@ int meson_sm_call_read(void *buffer, unsigned int bsize, unsigned int cmd_index, size = bsize; if (buffer) - memcpy(buffer, fw.sm_shmem_out_base, size); + memcpy(buffer, fw->sm_shmem_out_base, size); return ret; } @@ -173,6 +174,7 @@ EXPORT_SYMBOL(meson_sm_call_read); /** * meson_sm_call_write - send data to secure-monitor * + * @fw: Pointer to secure-monitor firmware * @buffer: Buffer containing data to send * @size: Size of the data to send * @cmd_index: Index of the SMC32 function ID @@ -184,23 +186,24 @@ EXPORT_SYMBOL(meson_sm_call_read); * * Return: size of sent data on success, a negative value on error */ -int meson_sm_call_write(void *buffer, unsigned int size, unsigned int cmd_index, - u32 arg0, u32 arg1, u32 arg2, u32 arg3, u32 arg4) +int meson_sm_call_write(struct meson_sm_firmware *fw, void *buffer, + unsigned int size, unsigned int cmd_index, u32 arg0, + u32 arg1, u32 arg2, u32 arg3, u32 arg4) { u32 written; - if (!fw.chip) + if (!fw->chip) return -ENOENT; - if (size > fw.chip->shmem_size) + if (size > fw->chip->shmem_size) return -EINVAL; - if (!fw.chip->cmd_shmem_in_base) + if (!fw->chip->cmd_shmem_in_base) return -EINVAL; - memcpy(fw.sm_shmem_in_base, buffer, size); + memcpy(fw->sm_shmem_in_base, buffer, size); - if (meson_sm_call(cmd_index, &written, arg0, arg1, arg2, arg3, arg4) < 0) + if (meson_sm_call(fw, cmd_index, &written, arg0, arg1, arg2, arg3, arg4) < 0) return -EINVAL; if (!written) @@ -210,6 +213,24 @@ int meson_sm_call_write(void *buffer, unsigned int size, unsigned int cmd_index, } EXPORT_SYMBOL(meson_sm_call_write); +/** + * meson_sm_get - get pointer to meson_sm_firmware structure. + * + * @sm_node: Pointer to the secure-monitor Device Tree node. + * + * Return: NULL is the secure-monitor device is not ready. + */ +struct meson_sm_firmware *meson_sm_get(struct device_node *sm_node) +{ + struct platform_device *pdev = of_find_device_by_node(sm_node); + + if (!pdev) + return NULL; + + return platform_get_drvdata(pdev); +} +EXPORT_SYMBOL_GPL(meson_sm_get); + #define SM_CHIP_ID_LENGTH 119 #define SM_CHIP_ID_OFFSET 4 #define SM_CHIP_ID_SIZE 12 @@ -217,14 +238,18 @@ EXPORT_SYMBOL(meson_sm_call_write); static ssize_t serial_show(struct device *dev, struct device_attribute *attr, char *buf) { + struct platform_device *pdev = to_platform_device(dev); + struct meson_sm_firmware *fw; uint8_t *id_buf; int ret; + fw = platform_get_drvdata(pdev); + id_buf = kmalloc(SM_CHIP_ID_LENGTH, GFP_KERNEL); if (!id_buf) return -ENOMEM; - ret = meson_sm_call_read(id_buf, SM_CHIP_ID_LENGTH, SM_GET_CHIP_ID, + ret = meson_sm_call_read(fw, id_buf, SM_CHIP_ID_LENGTH, SM_GET_CHIP_ID, 0, 0, 0, 0, 0); if (ret < 0) { kfree(id_buf); @@ -268,25 +293,34 @@ static const struct of_device_id meson_sm_ids[] = { static int __init meson_sm_probe(struct platform_device *pdev) { + struct device *dev = &pdev->dev; const struct meson_sm_chip *chip; + struct meson_sm_firmware *fw; + + fw = devm_kzalloc(dev, sizeof(*fw), GFP_KERNEL); + if (!fw) + return -ENOMEM; - chip = of_match_device(meson_sm_ids, &pdev->dev)->data; + chip = of_match_device(meson_sm_ids, dev)->data; if (chip->cmd_shmem_in_base) { - fw.sm_shmem_in_base = meson_sm_map_shmem(chip->cmd_shmem_in_base, - chip->shmem_size); - if (WARN_ON(!fw.sm_shmem_in_base)) + fw->sm_shmem_in_base = meson_sm_map_shmem(chip->cmd_shmem_in_base, + chip->shmem_size); + if (WARN_ON(!fw->sm_shmem_in_base)) goto out; } if (chip->cmd_shmem_out_base) { - fw.sm_shmem_out_base = meson_sm_map_shmem(chip->cmd_shmem_out_base, - chip->shmem_size); - if (WARN_ON(!fw.sm_shmem_out_base)) + fw->sm_shmem_out_base = meson_sm_map_shmem(chip->cmd_shmem_out_base, + chip->shmem_size); + if (WARN_ON(!fw->sm_shmem_out_base)) goto out_in_base; } - fw.chip = chip; + fw->chip = chip; + + platform_set_drvdata(pdev, fw); + pr_info("secure-monitor enabled\n"); if (sysfs_create_group(&pdev->dev.kobj, &meson_sm_sysfs_attr_group)) @@ -295,7 +329,7 @@ static int __init meson_sm_probe(struct platform_device *pdev) return 0; out_in_base: - iounmap(fw.sm_shmem_in_base); + iounmap(fw->sm_shmem_in_base); out: return -EINVAL; } diff --git a/drivers/nvmem/meson-efuse.c b/drivers/nvmem/meson-efuse.c index 39bd76306033..d6b533497ce1 100644 --- a/drivers/nvmem/meson-efuse.c +++ b/drivers/nvmem/meson-efuse.c @@ -17,14 +17,18 @@ static int meson_efuse_read(void *context, unsigned int offset, void *val, size_t bytes) { - return meson_sm_call_read((u8 *)val, bytes, SM_EFUSE_READ, offset, + struct meson_sm_firmware *fw = context; + + return meson_sm_call_read(fw, (u8 *)val, bytes, SM_EFUSE_READ, offset, bytes, 0, 0, 0); } static int meson_efuse_write(void *context, unsigned int offset, void *val, size_t bytes) { - return meson_sm_call_write((u8 *)val, bytes, SM_EFUSE_WRITE, offset, + struct meson_sm_firmware *fw = context; + + return meson_sm_call_write(fw, (u8 *)val, bytes, SM_EFUSE_WRITE, offset, bytes, 0, 0, 0); } @@ -37,12 +41,25 @@ MODULE_DEVICE_TABLE(of, meson_efuse_match); static int meson_efuse_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; + struct meson_sm_firmware *fw; + struct device_node *sm_np; struct nvmem_device *nvmem; struct nvmem_config *econfig; struct clk *clk; unsigned int size; int ret; + sm_np = of_parse_phandle(pdev->dev.of_node, "secure-monitor", 0); + if (!sm_np) { + dev_err(&pdev->dev, "no secure-monitor node\n"); + return -ENODEV; + } + + fw = meson_sm_get(sm_np); + of_node_put(sm_np); + if (!fw) + return -EPROBE_DEFER; + clk = devm_clk_get(dev, NULL); if (IS_ERR(clk)) { ret = PTR_ERR(clk); @@ -65,7 +82,7 @@ static int meson_efuse_probe(struct platform_device *pdev) return ret; } - if (meson_sm_call(SM_EFUSE_USER_MAX, &size, 0, 0, 0, 0, 0) < 0) { + if (meson_sm_call(fw, SM_EFUSE_USER_MAX, &size, 0, 0, 0, 0, 0) < 0) { dev_err(dev, "failed to get max user"); return -EINVAL; } @@ -81,6 +98,7 @@ static int meson_efuse_probe(struct platform_device *pdev) econfig->reg_read = meson_efuse_read; econfig->reg_write = meson_efuse_write; econfig->size = size; + econfig->priv = fw; nvmem = devm_nvmem_register(&pdev->dev, econfig); diff --git a/include/linux/firmware/meson/meson_sm.h b/include/linux/firmware/meson/meson_sm.h index 7613bf7c9442..6669e2a1d5fd 100644 --- a/include/linux/firmware/meson/meson_sm.h +++ b/include/linux/firmware/meson/meson_sm.h @@ -16,11 +16,14 @@ enum { struct meson_sm_firmware; -int meson_sm_call(unsigned int cmd_index, u32 *ret, u32 arg0, u32 arg1, - u32 arg2, u32 arg3, u32 arg4); -int meson_sm_call_write(void *buffer, unsigned int b_size, unsigned int cmd_index, - u32 arg0, u32 arg1, u32 arg2, u32 arg3, u32 arg4); -int meson_sm_call_read(void *buffer, unsigned int bsize, unsigned int cmd_index, - u32 arg0, u32 arg1, u32 arg2, u32 arg3, u32 arg4); +int meson_sm_call(struct meson_sm_firmware *fw, unsigned int cmd_index, + u32 *ret, u32 arg0, u32 arg1, u32 arg2, u32 arg3, u32 arg4); +int meson_sm_call_write(struct meson_sm_firmware *fw, void *buffer, + unsigned int b_size, unsigned int cmd_index, u32 arg0, + u32 arg1, u32 arg2, u32 arg3, u32 arg4); +int meson_sm_call_read(struct meson_sm_firmware *fw, void *buffer, + unsigned int bsize, unsigned int cmd_index, u32 arg0, + u32 arg1, u32 arg2, u32 arg3, u32 arg4); +struct meson_sm_firmware *meson_sm_get(struct device_node *firmware_node); #endif /* _MESON_SM_FW_H_ */ -- cgit v1.2.3 From c2016cc612db7b88483073d6ff51edd200bc6ddc Mon Sep 17 00:00:00 2001 From: Jerome Brunet Date: Thu, 5 Sep 2019 15:50:39 +0200 Subject: reset: dt-bindings: meson: update arb bindings for sm1 SM1 SoC family adds two new audio FIFOs with the related arb reset lines Reviewed-by: Rob Herring Signed-off-by: Jerome Brunet Signed-off-by: Philipp Zabel --- .../devicetree/bindings/reset/amlogic,meson-axg-audio-arb.txt | 3 ++- include/dt-bindings/reset/amlogic,meson-axg-audio-arb.h | 2 ++ 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/Documentation/devicetree/bindings/reset/amlogic,meson-axg-audio-arb.txt b/Documentation/devicetree/bindings/reset/amlogic,meson-axg-audio-arb.txt index 26e542eb96df..43e580ef64ba 100644 --- a/Documentation/devicetree/bindings/reset/amlogic,meson-axg-audio-arb.txt +++ b/Documentation/devicetree/bindings/reset/amlogic,meson-axg-audio-arb.txt @@ -4,7 +4,8 @@ The Amlogic Audio ARB is a simple device which enables or disables the access of Audio FIFOs to DDR on AXG based SoC. Required properties: -- compatible: 'amlogic,meson-axg-audio-arb' +- compatible: 'amlogic,meson-axg-audio-arb' or + 'amlogic,meson-sm1-audio-arb' - reg: physical base address of the controller and length of memory mapped region. - clocks: phandle to the fifo peripheral clock provided by the audio diff --git a/include/dt-bindings/reset/amlogic,meson-axg-audio-arb.h b/include/dt-bindings/reset/amlogic,meson-axg-audio-arb.h index 05c36367875c..1ef807856cb8 100644 --- a/include/dt-bindings/reset/amlogic,meson-axg-audio-arb.h +++ b/include/dt-bindings/reset/amlogic,meson-axg-audio-arb.h @@ -13,5 +13,7 @@ #define AXG_ARB_FRDDR_A 3 #define AXG_ARB_FRDDR_B 4 #define AXG_ARB_FRDDR_C 5 +#define AXG_ARB_TODDR_D 6 +#define AXG_ARB_FRDDR_D 7 #endif /* _DT_BINDINGS_AMLOGIC_MESON_AXG_AUDIO_ARB_H */ -- cgit v1.2.3 From 27f722ccbe1563629275bb7ee30c0e307f5837a2 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Mon, 30 Sep 2019 16:22:24 -0700 Subject: scsi: target: Remove tpg_list and se_portal_group.se_tpg_node Maintaining tpg_list without ever iterating over it is not useful. Hence remove tpg_list. This patch does not change the behavior of the SCSI target code. Cc: Mike Christie Cc: Christoph Hellwig Cc: Hannes Reinecke Cc: Nicholas Bellinger Link: https://lore.kernel.org/r/20190930232224.58980-1-bvanassche@acm.org Signed-off-by: Bart Van Assche Reviewed-by: Mike Christie Signed-off-by: Martin K. Petersen --- drivers/target/target_core_tpg.c | 12 ------------ drivers/target/target_core_xcopy.c | 1 - include/target/target_core_base.h | 1 - 3 files changed, 14 deletions(-) (limited to 'include') diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c index e5a71addbb06..d24e0a3ba3ff 100644 --- a/drivers/target/target_core_tpg.c +++ b/drivers/target/target_core_tpg.c @@ -32,9 +32,6 @@ extern struct se_device *g_lun0_dev; -static DEFINE_SPINLOCK(tpg_lock); -static LIST_HEAD(tpg_list); - /* __core_tpg_get_initiator_node_acl(): * * mutex_lock(&tpg->acl_node_mutex); must be held when calling @@ -475,7 +472,6 @@ int core_tpg_register( se_tpg->se_tpg_wwn = se_wwn; atomic_set(&se_tpg->tpg_pr_ref_count, 0); INIT_LIST_HEAD(&se_tpg->acl_node_list); - INIT_LIST_HEAD(&se_tpg->se_tpg_node); INIT_LIST_HEAD(&se_tpg->tpg_sess_list); spin_lock_init(&se_tpg->session_lock); mutex_init(&se_tpg->tpg_lun_mutex); @@ -494,10 +490,6 @@ int core_tpg_register( } } - spin_lock_bh(&tpg_lock); - list_add_tail(&se_tpg->se_tpg_node, &tpg_list); - spin_unlock_bh(&tpg_lock); - pr_debug("TARGET_CORE[%s]: Allocated portal_group for endpoint: %s, " "Proto: %d, Portal Tag: %u\n", se_tpg->se_tpg_tfo->fabric_name, se_tpg->se_tpg_tfo->tpg_get_wwn(se_tpg) ? @@ -519,10 +511,6 @@ int core_tpg_deregister(struct se_portal_group *se_tpg) tfo->tpg_get_wwn(se_tpg) ? tfo->tpg_get_wwn(se_tpg) : NULL, se_tpg->proto_id, tfo->tpg_get_tag(se_tpg)); - spin_lock_bh(&tpg_lock); - list_del(&se_tpg->se_tpg_node); - spin_unlock_bh(&tpg_lock); - while (atomic_read(&se_tpg->tpg_pr_ref_count) != 0) cpu_relax(); diff --git a/drivers/target/target_core_xcopy.c b/drivers/target/target_core_xcopy.c index b9b1e92c6f8d..425c1070de08 100644 --- a/drivers/target/target_core_xcopy.c +++ b/drivers/target/target_core_xcopy.c @@ -467,7 +467,6 @@ int target_xcopy_setup_pt(void) } memset(&xcopy_pt_tpg, 0, sizeof(struct se_portal_group)); - INIT_LIST_HEAD(&xcopy_pt_tpg.se_tpg_node); INIT_LIST_HEAD(&xcopy_pt_tpg.acl_node_list); INIT_LIST_HEAD(&xcopy_pt_tpg.tpg_sess_list); diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index 7c9716fe731e..1728e883b7b2 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -876,7 +876,6 @@ struct se_portal_group { /* Spinlock for adding/removing sessions */ spinlock_t session_lock; struct mutex tpg_lun_mutex; - struct list_head se_tpg_node; /* linked list for initiator ACL list */ struct list_head acl_node_list; struct hlist_head tpg_lun_hlist; -- cgit v1.2.3 From 4bc6aadbcc0e2a852e584bf5410fe90ea5a5f86a Mon Sep 17 00:00:00 2001 From: "Angelo G. Del Regno" Date: Sat, 21 Sep 2019 12:12:06 +0200 Subject: dt-bindings: power: Add missing rpmpd smd performance level The RPM_SMD_LEVEL_TURBO_HIGH is used by MSM8956/8976 and APQ variants: add the definition. Signed-off-by: Angelo G. Del Regno Signed-off-by: Bjorn Andersson --- include/dt-bindings/power/qcom-rpmpd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/dt-bindings/power/qcom-rpmpd.h b/include/dt-bindings/power/qcom-rpmpd.h index 93e36d011527..30a0aee0df57 100644 --- a/include/dt-bindings/power/qcom-rpmpd.h +++ b/include/dt-bindings/power/qcom-rpmpd.h @@ -68,6 +68,7 @@ #define RPM_SMD_LEVEL_NOM_PLUS 320 #define RPM_SMD_LEVEL_TURBO 384 #define RPM_SMD_LEVEL_TURBO_NO_CPR 416 +#define RPM_SMD_LEVEL_TURBO_HIGH 448 #define RPM_SMD_LEVEL_BINNING 512 #endif -- cgit v1.2.3 From b1d522443b4b000974e48f27d4ee77dbfc67962d Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Sat, 5 Oct 2019 13:07:58 +0200 Subject: soc: qcom: rpmpd: Add rpm power domains for msm8976 The MSM8956/76 SoCs have two main voltage-level power domains, VDD_CX and VDD_MX, which also have their own voltage-floor-level (VFL) corner. Signed-off-by: AngeloGioacchino Del Regno Signed-off-by: Bjorn Andersson --- .../devicetree/bindings/power/qcom,rpmpd.txt | 1 + drivers/soc/qcom/rpmpd.c | 23 ++++++++++++++++++++++ include/dt-bindings/power/qcom-rpmpd.h | 8 ++++++++ 3 files changed, 32 insertions(+) (limited to 'include') diff --git a/Documentation/devicetree/bindings/power/qcom,rpmpd.txt b/Documentation/devicetree/bindings/power/qcom,rpmpd.txt index eb35b22f9e23..bc75bf49cdae 100644 --- a/Documentation/devicetree/bindings/power/qcom,rpmpd.txt +++ b/Documentation/devicetree/bindings/power/qcom,rpmpd.txt @@ -5,6 +5,7 @@ which then translates it into a corresponding voltage on a rail Required Properties: - compatible: Should be one of the following + * qcom,msm8976-rpmpd: RPM Power domain for the msm8976 family of SoC * qcom,msm8996-rpmpd: RPM Power domain for the msm8996 family of SoC * qcom,msm8998-rpmpd: RPM Power domain for the msm8998 family of SoC * qcom,qcs404-rpmpd: RPM Power domain for the qcs404 family of SoC diff --git a/drivers/soc/qcom/rpmpd.c b/drivers/soc/qcom/rpmpd.c index 3c1a55cf25d6..2b1834c5609a 100644 --- a/drivers/soc/qcom/rpmpd.c +++ b/drivers/soc/qcom/rpmpd.c @@ -115,6 +115,28 @@ struct rpmpd_desc { static DEFINE_MUTEX(rpmpd_lock); +/* msm8976 RPM Power Domains */ +DEFINE_RPMPD_PAIR(msm8976, vddcx, vddcx_ao, SMPA, LEVEL, 2); +DEFINE_RPMPD_PAIR(msm8976, vddmx, vddmx_ao, SMPA, LEVEL, 6); + +DEFINE_RPMPD_VFL(msm8976, vddcx_vfl, RWSC, 2); +DEFINE_RPMPD_VFL(msm8976, vddmx_vfl, RWSM, 6); + +static struct rpmpd *msm8976_rpmpds[] = { + [MSM8976_VDDCX] = &msm8976_vddcx, + [MSM8976_VDDCX_AO] = &msm8976_vddcx_ao, + [MSM8976_VDDCX_VFL] = &msm8976_vddcx_vfl, + [MSM8976_VDDMX] = &msm8976_vddmx, + [MSM8976_VDDMX_AO] = &msm8976_vddmx_ao, + [MSM8976_VDDMX_VFL] = &msm8976_vddmx_vfl, +}; + +static const struct rpmpd_desc msm8976_desc = { + .rpmpds = msm8976_rpmpds, + .num_pds = ARRAY_SIZE(msm8976_rpmpds), + .max_state = RPM_SMD_LEVEL_TURBO_HIGH, +}; + /* msm8996 RPM Power domains */ DEFINE_RPMPD_PAIR(msm8996, vddcx, vddcx_ao, SMPA, CORNER, 1); DEFINE_RPMPD_PAIR(msm8996, vddmx, vddmx_ao, SMPA, CORNER, 2); @@ -198,6 +220,7 @@ static const struct rpmpd_desc qcs404_desc = { }; static const struct of_device_id rpmpd_match_table[] = { + { .compatible = "qcom,msm8976-rpmpd", .data = &msm8976_desc }, { .compatible = "qcom,msm8996-rpmpd", .data = &msm8996_desc }, { .compatible = "qcom,msm8998-rpmpd", .data = &msm8998_desc }, { .compatible = "qcom,qcs404-rpmpd", .data = &qcs404_desc }, diff --git a/include/dt-bindings/power/qcom-rpmpd.h b/include/dt-bindings/power/qcom-rpmpd.h index 30a0aee0df57..f05f8b1808ec 100644 --- a/include/dt-bindings/power/qcom-rpmpd.h +++ b/include/dt-bindings/power/qcom-rpmpd.h @@ -27,6 +27,14 @@ #define RPMH_REGULATOR_LEVEL_TURBO 384 #define RPMH_REGULATOR_LEVEL_TURBO_L1 416 +/* MSM8976 Power Domain Indexes */ +#define MSM8976_VDDCX 0 +#define MSM8976_VDDCX_AO 1 +#define MSM8976_VDDCX_VFL 2 +#define MSM8976_VDDMX 3 +#define MSM8976_VDDMX_AO 4 +#define MSM8976_VDDMX_VFL 5 + /* MSM8996 Power Domain Indexes */ #define MSM8996_VDDCX 0 #define MSM8996_VDDCX_AO 1 -- cgit v1.2.3 From f00eaa38eb0c7185ffff51c5288d00af9032e354 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Mon, 7 Oct 2019 15:47:15 +0200 Subject: rtc: add a timestamp for year 0 A few RTCs handle dates from year 0 to year 9999. Add a timestamp even if years before 1970 will probably never be used. Link: https://lore.kernel.org/r/20191007134724.15505-1-alexandre.belloni@bootlin.com Signed-off-by: Alexandre Belloni --- include/linux/rtc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/rtc.h b/include/linux/rtc.h index df666cf29ef1..2680f9b2b119 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -160,6 +160,7 @@ struct rtc_device { #define to_rtc_device(d) container_of(d, struct rtc_device, dev) /* useful timestamps */ +#define RTC_TIMESTAMP_BEGIN_0000 -62167219200ULL /* 0000-01-01 00:00:00 */ #define RTC_TIMESTAMP_BEGIN_1900 -2208988800LL /* 1900-01-01 00:00:00 */ #define RTC_TIMESTAMP_BEGIN_2000 946684800LL /* 2000-01-01 00:00:00 */ #define RTC_TIMESTAMP_END_2063 2966371199LL /* 2063-12-31 23:59:59 */ -- cgit v1.2.3 From b0a1614fb1f58520938968ebe1f4f11bcf34839e Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Fri, 23 Aug 2019 05:16:33 -0700 Subject: firmware: qcom: scm: add OCMEM lock/unlock interface Add support for the OCMEM lock/unlock interface that is needed by the On Chip MEMory (OCMEM) that is present on some Snapdragon devices. Signed-off-by: Rob Clark [masneyb@onstation.org: ported to latest kernel; minor reformatting.] Signed-off-by: Brian Masney Reviewed-by: Bjorn Andersson Tested-by: Gabriel Francisco Signed-off-by: Rob Clark --- drivers/firmware/qcom_scm-32.c | 35 +++++++++++++++++++++++++++++++++++ drivers/firmware/qcom_scm-64.c | 12 ++++++++++++ drivers/firmware/qcom_scm.c | 40 ++++++++++++++++++++++++++++++++++++++++ drivers/firmware/qcom_scm.h | 9 +++++++++ include/linux/qcom_scm.h | 15 +++++++++++++++ 5 files changed, 111 insertions(+) (limited to 'include') diff --git a/drivers/firmware/qcom_scm-32.c b/drivers/firmware/qcom_scm-32.c index 215061c581e1..4c2514e5e249 100644 --- a/drivers/firmware/qcom_scm-32.c +++ b/drivers/firmware/qcom_scm-32.c @@ -442,6 +442,41 @@ int __qcom_scm_hdcp_req(struct device *dev, struct qcom_scm_hdcp_req *req, req, req_cnt * sizeof(*req), resp, sizeof(*resp)); } +int __qcom_scm_ocmem_lock(struct device *dev, u32 id, u32 offset, u32 size, + u32 mode) +{ + struct ocmem_tz_lock { + __le32 id; + __le32 offset; + __le32 size; + __le32 mode; + } request; + + request.id = cpu_to_le32(id); + request.offset = cpu_to_le32(offset); + request.size = cpu_to_le32(size); + request.mode = cpu_to_le32(mode); + + return qcom_scm_call(dev, QCOM_SCM_OCMEM_SVC, QCOM_SCM_OCMEM_LOCK_CMD, + &request, sizeof(request), NULL, 0); +} + +int __qcom_scm_ocmem_unlock(struct device *dev, u32 id, u32 offset, u32 size) +{ + struct ocmem_tz_unlock { + __le32 id; + __le32 offset; + __le32 size; + } request; + + request.id = cpu_to_le32(id); + request.offset = cpu_to_le32(offset); + request.size = cpu_to_le32(size); + + return qcom_scm_call(dev, QCOM_SCM_OCMEM_SVC, QCOM_SCM_OCMEM_UNLOCK_CMD, + &request, sizeof(request), NULL, 0); +} + void __qcom_scm_init(void) { } diff --git a/drivers/firmware/qcom_scm-64.c b/drivers/firmware/qcom_scm-64.c index 91d5ad7cf58b..c3a3d9874def 100644 --- a/drivers/firmware/qcom_scm-64.c +++ b/drivers/firmware/qcom_scm-64.c @@ -241,6 +241,18 @@ int __qcom_scm_hdcp_req(struct device *dev, struct qcom_scm_hdcp_req *req, return ret; } +int __qcom_scm_ocmem_lock(struct device *dev, uint32_t id, uint32_t offset, + uint32_t size, uint32_t mode) +{ + return -ENOTSUPP; +} + +int __qcom_scm_ocmem_unlock(struct device *dev, uint32_t id, uint32_t offset, + uint32_t size) +{ + return -ENOTSUPP; +} + void __qcom_scm_init(void) { u64 cmd; diff --git a/drivers/firmware/qcom_scm.c b/drivers/firmware/qcom_scm.c index 4802ab170fe5..7e285ff3961d 100644 --- a/drivers/firmware/qcom_scm.c +++ b/drivers/firmware/qcom_scm.c @@ -191,6 +191,46 @@ bool qcom_scm_pas_supported(u32 peripheral) } EXPORT_SYMBOL(qcom_scm_pas_supported); +/** + * qcom_scm_ocmem_lock_available() - is OCMEM lock/unlock interface available + */ +bool qcom_scm_ocmem_lock_available(void) +{ + return __qcom_scm_is_call_available(__scm->dev, QCOM_SCM_OCMEM_SVC, + QCOM_SCM_OCMEM_LOCK_CMD); +} +EXPORT_SYMBOL(qcom_scm_ocmem_lock_available); + +/** + * qcom_scm_ocmem_lock() - call OCMEM lock interface to assign an OCMEM + * region to the specified initiator + * + * @id: tz initiator id + * @offset: OCMEM offset + * @size: OCMEM size + * @mode: access mode (WIDE/NARROW) + */ +int qcom_scm_ocmem_lock(enum qcom_scm_ocmem_client id, u32 offset, u32 size, + u32 mode) +{ + return __qcom_scm_ocmem_lock(__scm->dev, id, offset, size, mode); +} +EXPORT_SYMBOL(qcom_scm_ocmem_lock); + +/** + * qcom_scm_ocmem_unlock() - call OCMEM unlock interface to release an OCMEM + * region from the specified initiator + * + * @id: tz initiator id + * @offset: OCMEM offset + * @size: OCMEM size + */ +int qcom_scm_ocmem_unlock(enum qcom_scm_ocmem_client id, u32 offset, u32 size) +{ + return __qcom_scm_ocmem_unlock(__scm->dev, id, offset, size); +} +EXPORT_SYMBOL(qcom_scm_ocmem_unlock); + /** * qcom_scm_pas_init_image() - Initialize peripheral authentication service * state machine for a given peripheral, using the diff --git a/drivers/firmware/qcom_scm.h b/drivers/firmware/qcom_scm.h index 99506bd873c0..ef293ee67ec1 100644 --- a/drivers/firmware/qcom_scm.h +++ b/drivers/firmware/qcom_scm.h @@ -42,6 +42,15 @@ extern int __qcom_scm_hdcp_req(struct device *dev, extern void __qcom_scm_init(void); +#define QCOM_SCM_OCMEM_SVC 0xf +#define QCOM_SCM_OCMEM_LOCK_CMD 0x1 +#define QCOM_SCM_OCMEM_UNLOCK_CMD 0x2 + +extern int __qcom_scm_ocmem_lock(struct device *dev, u32 id, u32 offset, + u32 size, u32 mode); +extern int __qcom_scm_ocmem_unlock(struct device *dev, u32 id, u32 offset, + u32 size); + #define QCOM_SCM_SVC_PIL 0x2 #define QCOM_SCM_PAS_INIT_IMAGE_CMD 0x1 #define QCOM_SCM_PAS_MEM_SETUP_CMD 0x2 diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h index 2d5eff506e13..b49b734d662c 100644 --- a/include/linux/qcom_scm.h +++ b/include/linux/qcom_scm.h @@ -24,6 +24,16 @@ struct qcom_scm_vmperm { int perm; }; +enum qcom_scm_ocmem_client { + QCOM_SCM_OCMEM_UNUSED_ID = 0x0, + QCOM_SCM_OCMEM_GRAPHICS_ID, + QCOM_SCM_OCMEM_VIDEO_ID, + QCOM_SCM_OCMEM_LP_AUDIO_ID, + QCOM_SCM_OCMEM_SENSORS_ID, + QCOM_SCM_OCMEM_OTHER_OS_ID, + QCOM_SCM_OCMEM_DEBUG_ID, +}; + #define QCOM_SCM_VMID_HLOS 0x3 #define QCOM_SCM_VMID_MSS_MSA 0xF #define QCOM_SCM_VMID_WLAN 0x18 @@ -41,6 +51,11 @@ extern bool qcom_scm_is_available(void); extern bool qcom_scm_hdcp_available(void); extern int qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt, u32 *resp); +extern bool qcom_scm_ocmem_lock_available(void); +extern int qcom_scm_ocmem_lock(enum qcom_scm_ocmem_client id, u32 offset, + u32 size, u32 mode); +extern int qcom_scm_ocmem_unlock(enum qcom_scm_ocmem_client id, u32 offset, + u32 size); extern bool qcom_scm_pas_supported(u32 peripheral); extern int qcom_scm_pas_init_image(u32 peripheral, const void *metadata, size_t size); -- cgit v1.2.3 From 0434a4061471a9afc2b2061add496e58ba4bb92d Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Fri, 23 Aug 2019 05:16:34 -0700 Subject: firmware: qcom: scm: add support to restore secure config to qcm_scm-32 Add support to restore the secure configuration for qcm_scm-32.c. This is needed by the On Chip MEMory (OCMEM) that is present on some Snapdragon devices. Signed-off-by: Rob Clark [masneyb@onstation.org: ported to latest kernel; set ctx_bank_num to spare parameter.] Signed-off-by: Brian Masney Reviewed-by: Bjorn Andersson Tested-by: Gabriel Francisco Signed-off-by: Rob Clark --- drivers/firmware/qcom_scm-32.c | 17 ++++++++++++++++- drivers/firmware/qcom_scm.c | 13 +++++++++++++ include/linux/qcom_scm.h | 11 +++++++++++ 3 files changed, 40 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/firmware/qcom_scm-32.c b/drivers/firmware/qcom_scm-32.c index 4c2514e5e249..5d90b7f5ab5a 100644 --- a/drivers/firmware/qcom_scm-32.c +++ b/drivers/firmware/qcom_scm-32.c @@ -617,7 +617,22 @@ int __qcom_scm_assign_mem(struct device *dev, phys_addr_t mem_region, int __qcom_scm_restore_sec_cfg(struct device *dev, u32 device_id, u32 spare) { - return -ENODEV; + struct msm_scm_sec_cfg { + __le32 id; + __le32 ctx_bank_num; + } cfg; + int ret, scm_ret = 0; + + cfg.id = cpu_to_le32(device_id); + cfg.ctx_bank_num = cpu_to_le32(spare); + + ret = qcom_scm_call(dev, QCOM_SCM_SVC_MP, QCOM_SCM_RESTORE_SEC_CFG, + &cfg, sizeof(cfg), &scm_ret, sizeof(scm_ret)); + + if (ret || scm_ret) + return ret ? ret : -EINVAL; + + return 0; } int __qcom_scm_iommu_secure_ptbl_size(struct device *dev, u32 spare, diff --git a/drivers/firmware/qcom_scm.c b/drivers/firmware/qcom_scm.c index 7e285ff3961d..27c1d98a34e6 100644 --- a/drivers/firmware/qcom_scm.c +++ b/drivers/firmware/qcom_scm.c @@ -367,6 +367,19 @@ static const struct reset_control_ops qcom_scm_pas_reset_ops = { .deassert = qcom_scm_pas_reset_deassert, }; +/** + * qcom_scm_restore_sec_cfg_available() - Check if secure environment + * supports restore security config interface. + * + * Return true if restore-cfg interface is supported, false if not. + */ +bool qcom_scm_restore_sec_cfg_available(void) +{ + return __qcom_scm_is_call_available(__scm->dev, QCOM_SCM_SVC_MP, + QCOM_SCM_RESTORE_SEC_CFG); +} +EXPORT_SYMBOL(qcom_scm_restore_sec_cfg_available); + int qcom_scm_restore_sec_cfg(u32 device_id, u32 spare) { return __qcom_scm_restore_sec_cfg(__scm->dev, device_id, spare); diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h index b49b734d662c..04382e1798e4 100644 --- a/include/linux/qcom_scm.h +++ b/include/linux/qcom_scm.h @@ -34,6 +34,16 @@ enum qcom_scm_ocmem_client { QCOM_SCM_OCMEM_DEBUG_ID, }; +enum qcom_scm_sec_dev_id { + QCOM_SCM_MDSS_DEV_ID = 1, + QCOM_SCM_OCMEM_DEV_ID = 5, + QCOM_SCM_PCIE0_DEV_ID = 11, + QCOM_SCM_PCIE1_DEV_ID = 12, + QCOM_SCM_GFX_DEV_ID = 18, + QCOM_SCM_UFS_DEV_ID = 19, + QCOM_SCM_ICE_DEV_ID = 20, +}; + #define QCOM_SCM_VMID_HLOS 0x3 #define QCOM_SCM_VMID_MSS_MSA 0xF #define QCOM_SCM_VMID_WLAN 0x18 @@ -70,6 +80,7 @@ extern int qcom_scm_assign_mem(phys_addr_t mem_addr, size_t mem_sz, extern void qcom_scm_cpu_power_down(u32 flags); extern u32 qcom_scm_get_version(void); extern int qcom_scm_set_remote_state(u32 state, u32 id); +extern bool qcom_scm_restore_sec_cfg_available(void); extern int qcom_scm_restore_sec_cfg(u32 device_id, u32 spare); extern int qcom_scm_iommu_secure_ptbl_size(u32 spare, size_t *size); extern int qcom_scm_iommu_secure_ptbl_init(u64 addr, u32 size, u32 spare); -- cgit v1.2.3 From 88c1e9404f1deee02e52d13aae3d9ee2cabd66f5 Mon Sep 17 00:00:00 2001 From: Brian Masney Date: Fri, 23 Aug 2019 05:16:35 -0700 Subject: soc: qcom: add OCMEM driver The OCMEM driver handles allocation and configuration of the On Chip MEMory that is present on some Snapdragon SoCs. Devices which have OCMEM do not have GMEM inside the GPU core, so the GPU must instead use OCMEM to be functional. Since the GPU is currently the only OCMEM user with an upstream driver, this is just a minimal implementation sufficient for statically allocating to the GPU it's chunk of OCMEM. This driver currently does not read the gmu-sram node that is described in the device tree bindings. The starting memory address of the GPU's reserved memory region is hardcoded to zero to match what the hardware expects. The driver can be updated to read the reserved memory regions from device tree once other users of OCMEM are added upstream. Signed-off-by: Brian Masney Co-developed-by: Rob Clark Signed-off-by: Rob Clark Reviewed-by: Bjorn Andersson Tested-by: Gabriel Francisco Signed-off-by: Rob Clark --- drivers/soc/qcom/Kconfig | 10 ++ drivers/soc/qcom/Makefile | 1 + drivers/soc/qcom/ocmem.c | 433 ++++++++++++++++++++++++++++++++++++++++++++++ include/soc/qcom/ocmem.h | 62 +++++++ 4 files changed, 506 insertions(+) create mode 100644 drivers/soc/qcom/ocmem.c create mode 100644 include/soc/qcom/ocmem.h (limited to 'include') diff --git a/drivers/soc/qcom/Kconfig b/drivers/soc/qcom/Kconfig index 661e47acc354..adbf3bfae805 100644 --- a/drivers/soc/qcom/Kconfig +++ b/drivers/soc/qcom/Kconfig @@ -74,6 +74,16 @@ config QCOM_MDT_LOADER tristate select QCOM_SCM +config QCOM_OCMEM + tristate "Qualcomm On Chip Memory (OCMEM) driver" + depends on ARCH_QCOM + select QCOM_SCM + help + The On Chip Memory (OCMEM) allocator allows various clients to + allocate memory from OCMEM based on performance, latency and power + requirements. This is typically used by the GPU, camera/video, and + audio components on some Snapdragon SoCs. + config QCOM_PM bool "Qualcomm Power Management" depends on ARCH_QCOM && !ARM64 diff --git a/drivers/soc/qcom/Makefile b/drivers/soc/qcom/Makefile index 162788701a77..aab333720bfd 100644 --- a/drivers/soc/qcom/Makefile +++ b/drivers/soc/qcom/Makefile @@ -6,6 +6,7 @@ obj-$(CONFIG_QCOM_COMMAND_DB) += cmd-db.o obj-$(CONFIG_QCOM_GLINK_SSR) += glink_ssr.o obj-$(CONFIG_QCOM_GSBI) += qcom_gsbi.o obj-$(CONFIG_QCOM_MDT_LOADER) += mdt_loader.o +obj-$(CONFIG_QCOM_OCMEM) += ocmem.o obj-$(CONFIG_QCOM_PM) += spm.o obj-$(CONFIG_QCOM_QMI_HELPERS) += qmi_helpers.o qmi_helpers-y += qmi_encdec.o qmi_interface.o diff --git a/drivers/soc/qcom/ocmem.c b/drivers/soc/qcom/ocmem.c new file mode 100644 index 000000000000..7f9e9944d1ea --- /dev/null +++ b/drivers/soc/qcom/ocmem.c @@ -0,0 +1,433 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * The On Chip Memory (OCMEM) allocator allows various clients to allocate + * memory from OCMEM based on performance, latency and power requirements. + * This is typically used by the GPU, camera/video, and audio components on + * some Snapdragon SoCs. + * + * Copyright (C) 2019 Brian Masney + * Copyright (C) 2015 Red Hat. Author: Rob Clark + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +enum region_mode { + WIDE_MODE = 0x0, + THIN_MODE, + MODE_DEFAULT = WIDE_MODE, +}; + +enum ocmem_macro_state { + PASSTHROUGH = 0, + PERI_ON = 1, + CORE_ON = 2, + CLK_OFF = 4, +}; + +struct ocmem_region { + bool interleaved; + enum region_mode mode; + unsigned int num_macros; + enum ocmem_macro_state macro_state[4]; + unsigned long macro_size; + unsigned long region_size; +}; + +struct ocmem_config { + uint8_t num_regions; + unsigned long macro_size; +}; + +struct ocmem { + struct device *dev; + const struct ocmem_config *config; + struct resource *memory; + void __iomem *mmio; + unsigned int num_ports; + unsigned int num_macros; + bool interleaved; + struct ocmem_region *regions; + unsigned long active_allocations; +}; + +#define OCMEM_MIN_ALIGN SZ_64K +#define OCMEM_MIN_ALLOC SZ_64K + +#define OCMEM_REG_HW_VERSION 0x00000000 +#define OCMEM_REG_HW_PROFILE 0x00000004 + +#define OCMEM_REG_REGION_MODE_CTL 0x00001000 +#define OCMEM_REGION_MODE_CTL_REG0_THIN 0x00000001 +#define OCMEM_REGION_MODE_CTL_REG1_THIN 0x00000002 +#define OCMEM_REGION_MODE_CTL_REG2_THIN 0x00000004 +#define OCMEM_REGION_MODE_CTL_REG3_THIN 0x00000008 + +#define OCMEM_REG_GFX_MPU_START 0x00001004 +#define OCMEM_REG_GFX_MPU_END 0x00001008 + +#define OCMEM_HW_PROFILE_NUM_PORTS(val) FIELD_PREP(0x0000000f, (val)) +#define OCMEM_HW_PROFILE_NUM_MACROS(val) FIELD_PREP(0x00003f00, (val)) + +#define OCMEM_HW_PROFILE_LAST_REGN_HALFSIZE 0x00010000 +#define OCMEM_HW_PROFILE_INTERLEAVING 0x00020000 +#define OCMEM_REG_GEN_STATUS 0x0000000c + +#define OCMEM_REG_PSGSC_STATUS 0x00000038 +#define OCMEM_REG_PSGSC_CTL(i0) (0x0000003c + 0x1*(i0)) + +#define OCMEM_PSGSC_CTL_MACRO0_MODE(val) FIELD_PREP(0x00000007, (val)) +#define OCMEM_PSGSC_CTL_MACRO1_MODE(val) FIELD_PREP(0x00000070, (val)) +#define OCMEM_PSGSC_CTL_MACRO2_MODE(val) FIELD_PREP(0x00000700, (val)) +#define OCMEM_PSGSC_CTL_MACRO3_MODE(val) FIELD_PREP(0x00007000, (val)) + +#define OCMEM_CLK_CORE_IDX 0 +static struct clk_bulk_data ocmem_clks[] = { + { + .id = "core", + }, + { + .id = "iface", + }, +}; + +static inline void ocmem_write(struct ocmem *ocmem, u32 reg, u32 data) +{ + writel(data, ocmem->mmio + reg); +} + +static inline u32 ocmem_read(struct ocmem *ocmem, u32 reg) +{ + return readl(ocmem->mmio + reg); +} + +static void update_ocmem(struct ocmem *ocmem) +{ + uint32_t region_mode_ctrl = 0x0; + int i; + + if (!qcom_scm_ocmem_lock_available()) { + for (i = 0; i < ocmem->config->num_regions; i++) { + struct ocmem_region *region = &ocmem->regions[i]; + + if (region->mode == THIN_MODE) + region_mode_ctrl |= BIT(i); + } + + dev_dbg(ocmem->dev, "ocmem_region_mode_control %x\n", + region_mode_ctrl); + ocmem_write(ocmem, OCMEM_REG_REGION_MODE_CTL, region_mode_ctrl); + } + + for (i = 0; i < ocmem->config->num_regions; i++) { + struct ocmem_region *region = &ocmem->regions[i]; + u32 data; + + data = OCMEM_PSGSC_CTL_MACRO0_MODE(region->macro_state[0]) | + OCMEM_PSGSC_CTL_MACRO1_MODE(region->macro_state[1]) | + OCMEM_PSGSC_CTL_MACRO2_MODE(region->macro_state[2]) | + OCMEM_PSGSC_CTL_MACRO3_MODE(region->macro_state[3]); + + ocmem_write(ocmem, OCMEM_REG_PSGSC_CTL(i), data); + } +} + +static unsigned long phys_to_offset(struct ocmem *ocmem, + unsigned long addr) +{ + if (addr < ocmem->memory->start || addr >= ocmem->memory->end) + return 0; + + return addr - ocmem->memory->start; +} + +static unsigned long device_address(struct ocmem *ocmem, + enum ocmem_client client, + unsigned long addr) +{ + WARN_ON(client != OCMEM_GRAPHICS); + + /* TODO: gpu uses phys_to_offset, but others do not.. */ + return phys_to_offset(ocmem, addr); +} + +static void update_range(struct ocmem *ocmem, struct ocmem_buf *buf, + enum ocmem_macro_state mstate, enum region_mode rmode) +{ + unsigned long offset = 0; + int i, j; + + for (i = 0; i < ocmem->config->num_regions; i++) { + struct ocmem_region *region = &ocmem->regions[i]; + + if (buf->offset <= offset && offset < buf->offset + buf->len) + region->mode = rmode; + + for (j = 0; j < region->num_macros; j++) { + if (buf->offset <= offset && + offset < buf->offset + buf->len) + region->macro_state[j] = mstate; + + offset += region->macro_size; + } + } + + update_ocmem(ocmem); +} + +struct ocmem *of_get_ocmem(struct device *dev) +{ + struct platform_device *pdev; + struct device_node *devnode; + + devnode = of_parse_phandle(dev->of_node, "sram", 0); + if (!devnode || !devnode->parent) { + dev_err(dev, "Cannot look up sram phandle\n"); + return ERR_PTR(-ENODEV); + } + + pdev = of_find_device_by_node(devnode->parent); + if (!pdev) { + dev_err(dev, "Cannot find device node %s\n", devnode->name); + return ERR_PTR(-EPROBE_DEFER); + } + + return platform_get_drvdata(pdev); +} +EXPORT_SYMBOL(of_get_ocmem); + +struct ocmem_buf *ocmem_allocate(struct ocmem *ocmem, enum ocmem_client client, + unsigned long size) +{ + struct ocmem_buf *buf; + int ret; + + /* TODO: add support for other clients... */ + if (WARN_ON(client != OCMEM_GRAPHICS)) + return ERR_PTR(-ENODEV); + + if (size < OCMEM_MIN_ALLOC || !IS_ALIGNED(size, OCMEM_MIN_ALIGN)) + return ERR_PTR(-EINVAL); + + if (test_and_set_bit_lock(BIT(client), &ocmem->active_allocations)) + return ERR_PTR(-EBUSY); + + buf = kzalloc(sizeof(*buf), GFP_KERNEL); + if (!buf) { + ret = -ENOMEM; + goto err_unlock; + } + + buf->offset = 0; + buf->addr = device_address(ocmem, client, buf->offset); + buf->len = size; + + update_range(ocmem, buf, CORE_ON, WIDE_MODE); + + if (qcom_scm_ocmem_lock_available()) { + ret = qcom_scm_ocmem_lock(QCOM_SCM_OCMEM_GRAPHICS_ID, + buf->offset, buf->len, WIDE_MODE); + if (ret) { + dev_err(ocmem->dev, "could not lock: %d\n", ret); + ret = -EINVAL; + goto err_kfree; + } + } else { + ocmem_write(ocmem, OCMEM_REG_GFX_MPU_START, buf->offset); + ocmem_write(ocmem, OCMEM_REG_GFX_MPU_END, + buf->offset + buf->len); + } + + dev_dbg(ocmem->dev, "using %ldK of OCMEM at 0x%08lx for client %d\n", + size / 1024, buf->addr, client); + + return buf; + +err_kfree: + kfree(buf); +err_unlock: + clear_bit_unlock(BIT(client), &ocmem->active_allocations); + + return ERR_PTR(ret); +} +EXPORT_SYMBOL(ocmem_allocate); + +void ocmem_free(struct ocmem *ocmem, enum ocmem_client client, + struct ocmem_buf *buf) +{ + /* TODO: add support for other clients... */ + if (WARN_ON(client != OCMEM_GRAPHICS)) + return; + + update_range(ocmem, buf, CLK_OFF, MODE_DEFAULT); + + if (qcom_scm_ocmem_lock_available()) { + int ret; + + ret = qcom_scm_ocmem_unlock(QCOM_SCM_OCMEM_GRAPHICS_ID, + buf->offset, buf->len); + if (ret) + dev_err(ocmem->dev, "could not unlock: %d\n", ret); + } else { + ocmem_write(ocmem, OCMEM_REG_GFX_MPU_START, 0x0); + ocmem_write(ocmem, OCMEM_REG_GFX_MPU_END, 0x0); + } + + kfree(buf); + + clear_bit_unlock(BIT(client), &ocmem->active_allocations); +} +EXPORT_SYMBOL(ocmem_free); + +static int ocmem_dev_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + unsigned long reg, region_size; + int i, j, ret, num_banks; + struct resource *res; + struct ocmem *ocmem; + + if (!qcom_scm_is_available()) + return -EPROBE_DEFER; + + ocmem = devm_kzalloc(dev, sizeof(*ocmem), GFP_KERNEL); + if (!ocmem) + return -ENOMEM; + + ocmem->dev = dev; + ocmem->config = device_get_match_data(dev); + + ret = devm_clk_bulk_get(dev, ARRAY_SIZE(ocmem_clks), ocmem_clks); + if (ret) { + if (ret != -EPROBE_DEFER) + dev_err(dev, "Unable to get clocks\n"); + + return ret; + } + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "ctrl"); + ocmem->mmio = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(ocmem->mmio)) { + dev_err(&pdev->dev, "Failed to ioremap ocmem_ctrl resource\n"); + return PTR_ERR(ocmem->mmio); + } + + ocmem->memory = platform_get_resource_byname(pdev, IORESOURCE_MEM, + "mem"); + if (!ocmem->memory) { + dev_err(dev, "Could not get mem region\n"); + return -ENXIO; + } + + /* The core clock is synchronous with graphics */ + WARN_ON(clk_set_rate(ocmem_clks[OCMEM_CLK_CORE_IDX].clk, 1000) < 0); + + ret = clk_bulk_prepare_enable(ARRAY_SIZE(ocmem_clks), ocmem_clks); + if (ret) { + dev_info(ocmem->dev, "Failed to enable clocks\n"); + return ret; + } + + if (qcom_scm_restore_sec_cfg_available()) { + dev_dbg(dev, "configuring scm\n"); + ret = qcom_scm_restore_sec_cfg(QCOM_SCM_OCMEM_DEV_ID, 0); + if (ret) { + dev_err(dev, "Could not enable secure configuration\n"); + goto err_clk_disable; + } + } + + reg = ocmem_read(ocmem, OCMEM_REG_HW_PROFILE); + ocmem->num_ports = OCMEM_HW_PROFILE_NUM_PORTS(reg); + ocmem->num_macros = OCMEM_HW_PROFILE_NUM_MACROS(reg); + ocmem->interleaved = !!(reg & OCMEM_HW_PROFILE_INTERLEAVING); + + num_banks = ocmem->num_ports / 2; + region_size = ocmem->config->macro_size * num_banks; + + dev_info(dev, "%u ports, %u regions, %u macros, %sinterleaved\n", + ocmem->num_ports, ocmem->config->num_regions, + ocmem->num_macros, ocmem->interleaved ? "" : "not "); + + ocmem->regions = devm_kcalloc(dev, ocmem->config->num_regions, + sizeof(struct ocmem_region), GFP_KERNEL); + if (!ocmem->regions) { + ret = -ENOMEM; + goto err_clk_disable; + } + + for (i = 0; i < ocmem->config->num_regions; i++) { + struct ocmem_region *region = &ocmem->regions[i]; + + if (WARN_ON(num_banks > ARRAY_SIZE(region->macro_state))) { + ret = -EINVAL; + goto err_clk_disable; + } + + region->mode = MODE_DEFAULT; + region->num_macros = num_banks; + + if (i == (ocmem->config->num_regions - 1) && + reg & OCMEM_HW_PROFILE_LAST_REGN_HALFSIZE) { + region->macro_size = ocmem->config->macro_size / 2; + region->region_size = region_size / 2; + } else { + region->macro_size = ocmem->config->macro_size; + region->region_size = region_size; + } + + for (j = 0; j < ARRAY_SIZE(region->macro_state); j++) + region->macro_state[j] = CLK_OFF; + } + + platform_set_drvdata(pdev, ocmem); + + return 0; + +err_clk_disable: + clk_bulk_disable_unprepare(ARRAY_SIZE(ocmem_clks), ocmem_clks); + return ret; +} + +static int ocmem_dev_remove(struct platform_device *pdev) +{ + clk_bulk_disable_unprepare(ARRAY_SIZE(ocmem_clks), ocmem_clks); + + return 0; +} + +static const struct ocmem_config ocmem_8974_config = { + .num_regions = 3, + .macro_size = SZ_128K, +}; + +static const struct of_device_id ocmem_of_match[] = { + { .compatible = "qcom,msm8974-ocmem", .data = &ocmem_8974_config }, + { } +}; + +MODULE_DEVICE_TABLE(of, ocmem_of_match); + +static struct platform_driver ocmem_driver = { + .probe = ocmem_dev_probe, + .remove = ocmem_dev_remove, + .driver = { + .name = "ocmem", + .of_match_table = ocmem_of_match, + }, +}; + +module_platform_driver(ocmem_driver); + +MODULE_DESCRIPTION("On Chip Memory (OCMEM) allocator for some Snapdragon SoCs"); +MODULE_LICENSE("GPL v2"); diff --git a/include/soc/qcom/ocmem.h b/include/soc/qcom/ocmem.h new file mode 100644 index 000000000000..a0ae336ba78b --- /dev/null +++ b/include/soc/qcom/ocmem.h @@ -0,0 +1,62 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * The On Chip Memory (OCMEM) allocator allows various clients to allocate + * memory from OCMEM based on performance, latency and power requirements. + * This is typically used by the GPU, camera/video, and audio components on + * some Snapdragon SoCs. + * + * Copyright (C) 2019 Brian Masney + * Copyright (C) 2015 Red Hat. Author: Rob Clark + */ + +#ifndef __OCMEM_H__ +#define __OCMEM_H__ + +enum ocmem_client { + /* GMEM clients */ + OCMEM_GRAPHICS = 0x0, + /* + * TODO add more once ocmem_allocate() is clever enough to + * deal with multiple clients. + */ + OCMEM_CLIENT_MAX, +}; + +struct ocmem; + +struct ocmem_buf { + unsigned long offset; + unsigned long addr; + unsigned long len; +}; + +#if IS_ENABLED(CONFIG_QCOM_OCMEM) + +struct ocmem *of_get_ocmem(struct device *dev); +struct ocmem_buf *ocmem_allocate(struct ocmem *ocmem, enum ocmem_client client, + unsigned long size); +void ocmem_free(struct ocmem *ocmem, enum ocmem_client client, + struct ocmem_buf *buf); + +#else /* IS_ENABLED(CONFIG_QCOM_OCMEM) */ + +static inline struct ocmem *of_get_ocmem(struct device *dev) +{ + return ERR_PTR(-ENODEV); +} + +static inline struct ocmem_buf *ocmem_allocate(struct ocmem *ocmem, + enum ocmem_client client, + unsigned long size) +{ + return ERR_PTR(-ENODEV); +} + +static inline void ocmem_free(struct ocmem *ocmem, enum ocmem_client client, + struct ocmem_buf *buf) +{ +} + +#endif /* IS_ENABLED(CONFIG_QCOM_OCMEM) */ + +#endif /* __OCMEM_H__ */ -- cgit v1.2.3 From bfcb7e1555ecc157cea23e35057002e3055e90a6 Mon Sep 17 00:00:00 2001 From: Brian Masney Date: Sun, 1 Sep 2019 17:30:37 -0400 Subject: soc: qcom: ocmem: add missing includes The kbuild bot reported the following compiler errors when compiling on MIPS with CONFIG_QCOM_OCMEM disabled: In file included from :0:0: >> include/soc/qcom/ocmem.h:43:49: warning: 'struct device' declared inside parameter list will not be visible outside of this definition or declaration static inline struct ocmem *of_get_ocmem(struct device *dev) ^~~~~~ include/soc/qcom/ocmem.h: In function 'of_get_ocmem': >> include/soc/qcom/ocmem.h:45:9: error: implicit declaration of function 'ERR_PTR' [-Werror=implicit-function-declaration] return ERR_PTR(-ENODEV); ^~~~~~~ >> include/soc/qcom/ocmem.h:45:18: error: 'ENODEV' undeclared (first use in this function) return ERR_PTR(-ENODEV); Add the proper includes to fix the compiler errors. Signed-off-by: Brian Masney Reported-by: kbuild test robot Tested-by: Gabriel Francisco Signed-off-by: Rob Clark --- include/soc/qcom/ocmem.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/soc/qcom/ocmem.h b/include/soc/qcom/ocmem.h index a0ae336ba78b..02a8bc2677b1 100644 --- a/include/soc/qcom/ocmem.h +++ b/include/soc/qcom/ocmem.h @@ -9,6 +9,9 @@ * Copyright (C) 2015 Red Hat. Author: Rob Clark */ +#include +#include + #ifndef __OCMEM_H__ #define __OCMEM_H__ -- cgit v1.2.3 From 5d9730b9eb05a349c278a9f6f058ebefa9063def Mon Sep 17 00:00:00 2001 From: Xingyu Chen Date: Sun, 29 Sep 2019 14:24:14 +0800 Subject: dt-bindings: reset: add bindings for the Meson-A1 SoC Reset Controller Add DT bindings for the Meson-A1 SoC Reset Controller include file, and also slightly update documentation. Signed-off-by: Xingyu Chen Reviewed-by: Rob Herring Signed-off-by: Philipp Zabel --- .../bindings/reset/amlogic,meson-reset.yaml | 1 + include/dt-bindings/reset/amlogic,meson-a1-reset.h | 74 ++++++++++++++++++++++ 2 files changed, 75 insertions(+) create mode 100644 include/dt-bindings/reset/amlogic,meson-a1-reset.h (limited to 'include') diff --git a/Documentation/devicetree/bindings/reset/amlogic,meson-reset.yaml b/Documentation/devicetree/bindings/reset/amlogic,meson-reset.yaml index 00917d868d58..b3f57d81f007 100644 --- a/Documentation/devicetree/bindings/reset/amlogic,meson-reset.yaml +++ b/Documentation/devicetree/bindings/reset/amlogic,meson-reset.yaml @@ -16,6 +16,7 @@ properties: - amlogic,meson8b-reset # Reset Controller on Meson8b and compatible SoCs - amlogic,meson-gxbb-reset # Reset Controller on GXBB and compatible SoCs - amlogic,meson-axg-reset # Reset Controller on AXG and compatible SoCs + - amlogic,meson-a1-reset # Reset Controller on A1 and compatible SoCs reg: maxItems: 1 diff --git a/include/dt-bindings/reset/amlogic,meson-a1-reset.h b/include/dt-bindings/reset/amlogic,meson-a1-reset.h new file mode 100644 index 000000000000..f1a3a797540d --- /dev/null +++ b/include/dt-bindings/reset/amlogic,meson-a1-reset.h @@ -0,0 +1,74 @@ +/* SPDX-License-Identifier: (GPL-2.0+ OR MIT) + * + * Copyright (c) 2019 Amlogic, Inc. All rights reserved. + * Author: Xingyu Chen + * + */ + +#ifndef _DT_BINDINGS_AMLOGIC_MESON_A1_RESET_H +#define _DT_BINDINGS_AMLOGIC_MESON_A1_RESET_H + +/* RESET0 */ +/* 0 */ +#define RESET_AM2AXI_VAD 1 +/* 2-3 */ +#define RESET_PSRAM 4 +#define RESET_PAD_CTRL 5 +/* 6 */ +#define RESET_TEMP_SENSOR 7 +#define RESET_AM2AXI_DEV 8 +/* 9 */ +#define RESET_SPICC_A 10 +#define RESET_MSR_CLK 11 +#define RESET_AUDIO 12 +#define RESET_ANALOG_CTRL 13 +#define RESET_SAR_ADC 14 +#define RESET_AUDIO_VAD 15 +#define RESET_CEC 16 +#define RESET_PWM_EF 17 +#define RESET_PWM_CD 18 +#define RESET_PWM_AB 19 +/* 20 */ +#define RESET_IR_CTRL 21 +#define RESET_I2C_S_A 22 +/* 23 */ +#define RESET_I2C_M_D 24 +#define RESET_I2C_M_C 25 +#define RESET_I2C_M_B 26 +#define RESET_I2C_M_A 27 +#define RESET_I2C_PROD_AHB 28 +#define RESET_I2C_PROD 29 +/* 30-31 */ + +/* RESET1 */ +#define RESET_ACODEC 32 +#define RESET_DMA 33 +#define RESET_SD_EMMC_A 34 +/* 35 */ +#define RESET_USBCTRL 36 +/* 37 */ +#define RESET_USBPHY 38 +/* 39-41 */ +#define RESET_RSA 42 +#define RESET_DMC 43 +/* 44 */ +#define RESET_IRQ_CTRL 45 +/* 46 */ +#define RESET_NIC_VAD 47 +#define RESET_NIC_AXI 48 +#define RESET_RAMA 49 +#define RESET_RAMB 50 +/* 51-52 */ +#define RESET_ROM 53 +#define RESET_SPIFC 54 +#define RESET_GIC 55 +#define RESET_UART_C 56 +#define RESET_UART_B 57 +#define RESET_UART_A 58 +#define RESET_OSC_RING 59 +/* 60-63 */ + +/* RESET2 */ +/* 64-95 */ + +#endif -- cgit v1.2.3 From 3a9ac959ba2825a3a6235bc909d369cc30386e9e Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Thu, 5 Sep 2019 11:44:24 +0100 Subject: of: Remove unused of_find_matching_node_by_address() of_find_matching_node_by_address() is unused, so remove it. Cc: Robin Murphy Reviewed-by: Geert Uytterhoeven Reviewed-by: Christoph Hellwig Tested-by: Nicolas Saenz Julienne Reviewed-by: Nicolas Saenz Julienne Signed-off-by: Rob Herring --- drivers/of/address.c | 19 ------------------- include/linux/of_address.h | 12 ------------ 2 files changed, 31 deletions(-) (limited to 'include') diff --git a/drivers/of/address.c b/drivers/of/address.c index 978427a9d5e6..0c3cf515c510 100644 --- a/drivers/of/address.c +++ b/drivers/of/address.c @@ -826,25 +826,6 @@ int of_address_to_resource(struct device_node *dev, int index, } EXPORT_SYMBOL_GPL(of_address_to_resource); -struct device_node *of_find_matching_node_by_address(struct device_node *from, - const struct of_device_id *matches, - u64 base_address) -{ - struct device_node *dn = of_find_matching_node(from, matches); - struct resource res; - - while (dn) { - if (!of_address_to_resource(dn, 0, &res) && - res.start == base_address) - return dn; - - dn = of_find_matching_node(dn, matches); - } - - return NULL; -} - - /** * of_iomap - Maps the memory mapped IO for a given device_node * @device: the device whose io range will be mapped diff --git a/include/linux/of_address.h b/include/linux/of_address.h index 30e40fb6936b..e317f375374a 100644 --- a/include/linux/of_address.h +++ b/include/linux/of_address.h @@ -33,10 +33,6 @@ extern u64 of_translate_dma_address(struct device_node *dev, extern u64 of_translate_address(struct device_node *np, const __be32 *addr); extern int of_address_to_resource(struct device_node *dev, int index, struct resource *r); -extern struct device_node *of_find_matching_node_by_address( - struct device_node *from, - const struct of_device_id *matches, - u64 base_address); extern void __iomem *of_iomap(struct device_node *device, int index); void __iomem *of_io_request_and_map(struct device_node *device, int index, const char *name); @@ -71,14 +67,6 @@ static inline u64 of_translate_address(struct device_node *np, return OF_BAD_ADDR; } -static inline struct device_node *of_find_matching_node_by_address( - struct device_node *from, - const struct of_device_id *matches, - u64 base_address) -{ - return NULL; -} - static inline const __be32 *of_get_address(struct device_node *dev, int index, u64 *size, unsigned int *flags) { -- cgit v1.2.3 From 6e6faf63744333373db8bc64aea52dab86cbf0bc Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Thu, 5 Sep 2019 11:53:27 +0100 Subject: of: Make of_dma_get_range() private of_dma_get_range() is only used within the DT core code, so remove the export and move the header declaration to the private header. Cc: Robin Murphy Reviewed-by: Geert Uytterhoeven Tested-by: Nicolas Saenz Julienne Reviewed-by: Nicolas Saenz Julienne Reviewed-by: Christoph Hellwig Signed-off-by: Rob Herring --- drivers/of/address.c | 1 - drivers/of/of_private.h | 11 +++++++++++ include/linux/of_address.h | 8 -------- 3 files changed, 11 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/drivers/of/address.c b/drivers/of/address.c index 0c3cf515c510..8e354d12fb04 100644 --- a/drivers/of/address.c +++ b/drivers/of/address.c @@ -972,7 +972,6 @@ out: return ret; } -EXPORT_SYMBOL_GPL(of_dma_get_range); /** * of_dma_is_coherent - Check if device is coherent diff --git a/drivers/of/of_private.h b/drivers/of/of_private.h index 24786818e32e..f8c58615c393 100644 --- a/drivers/of/of_private.h +++ b/drivers/of/of_private.h @@ -158,4 +158,15 @@ extern void __of_sysfs_remove_bin_file(struct device_node *np, #define for_each_transaction_entry_reverse(_oft, _te) \ list_for_each_entry_reverse(_te, &(_oft)->te_list, node) +#ifdef CONFIG_OF_ADDRESS +extern int of_dma_get_range(struct device_node *np, u64 *dma_addr, + u64 *paddr, u64 *size); +#else +static inline int of_dma_get_range(struct device_node *np, u64 *dma_addr, + u64 *paddr, u64 *size) +{ + return -ENODEV; +} +#endif + #endif /* _LINUX_OF_PRIVATE_H */ diff --git a/include/linux/of_address.h b/include/linux/of_address.h index e317f375374a..ddda3936039c 100644 --- a/include/linux/of_address.h +++ b/include/linux/of_address.h @@ -51,8 +51,6 @@ extern int of_pci_dma_range_parser_init(struct of_pci_range_parser *parser, extern struct of_pci_range *of_pci_range_parser_one( struct of_pci_range_parser *parser, struct of_pci_range *range); -extern int of_dma_get_range(struct device_node *np, u64 *dma_addr, - u64 *paddr, u64 *size); extern bool of_dma_is_coherent(struct device_node *np); #else /* CONFIG_OF_ADDRESS */ static inline void __iomem *of_io_request_and_map(struct device_node *device, @@ -92,12 +90,6 @@ static inline struct of_pci_range *of_pci_range_parser_one( return NULL; } -static inline int of_dma_get_range(struct device_node *np, u64 *dma_addr, - u64 *paddr, u64 *size) -{ - return -ENODEV; -} - static inline bool of_dma_is_coherent(struct device_node *np) { return false; -- cgit v1.2.3 From 645c138636de3d6d6ed7d92edec39298fd6873d7 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Thu, 5 Sep 2019 10:47:26 +0100 Subject: of/address: Fix of_pci_range_parser_one translation of DMA addresses of_pci_range_parser_one() has a bug when parsing dma-ranges. When it translates the parent address (aka cpu address in the code), 'ranges' is always being used. This happens to work because most users are just 1:1 translation. Cc: Robin Murphy Tested-by: Nicolas Saenz Julienne Reviewed-by: Nicolas Saenz Julienne Signed-off-by: Rob Herring --- drivers/of/address.c | 15 ++++++++++++--- include/linux/of_address.h | 1 + 2 files changed, 13 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/of/address.c b/drivers/of/address.c index 1c291bd6bce2..5ce69d026584 100644 --- a/drivers/of/address.c +++ b/drivers/of/address.c @@ -243,6 +243,7 @@ static int parser_init(struct of_pci_range_parser *parser, parser->node = node; parser->pna = of_n_addr_cells(node); parser->np = parser->pna + na + ns; + parser->dma = !strcmp(name, "dma-ranges"); parser->range = of_get_property(node, name, &rlen); if (parser->range == NULL) @@ -281,7 +282,11 @@ struct of_pci_range *of_pci_range_parser_one(struct of_pci_range_parser *parser, range->pci_space = be32_to_cpup(parser->range); range->flags = of_bus_pci_get_flags(parser->range); range->pci_addr = of_read_number(parser->range + 1, ns); - range->cpu_addr = of_translate_address(parser->node, + if (parser->dma) + range->cpu_addr = of_translate_dma_address(parser->node, + parser->range + na); + else + range->cpu_addr = of_translate_address(parser->node, parser->range + na); range->size = of_read_number(parser->range + parser->pna + na, ns); @@ -294,8 +299,12 @@ struct of_pci_range *of_pci_range_parser_one(struct of_pci_range_parser *parser, flags = of_bus_pci_get_flags(parser->range); pci_addr = of_read_number(parser->range + 1, ns); - cpu_addr = of_translate_address(parser->node, - parser->range + na); + if (parser->dma) + cpu_addr = of_translate_dma_address(parser->node, + parser->range + na); + else + cpu_addr = of_translate_address(parser->node, + parser->range + na); size = of_read_number(parser->range + parser->pna + na, ns); if (flags != range->flags) diff --git a/include/linux/of_address.h b/include/linux/of_address.h index ddda3936039c..eac7ab109df4 100644 --- a/include/linux/of_address.h +++ b/include/linux/of_address.h @@ -12,6 +12,7 @@ struct of_pci_range_parser { const __be32 *end; int np; int pna; + bool dma; }; struct of_pci_range { -- cgit v1.2.3 From 832b2cb955437dcfe9b8f08e5f37303c9097fc87 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 4 Oct 2019 09:58:20 -0400 Subject: svcrdma: Improve DMA mapping trace points Capture the total size of Sends, the size of DMA map and the matching DMA unmap to ensure operation is correct. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/trace/events/rpcrdma.h | 30 +++++++++++++++++++++++------- net/sunrpc/xprtrdma/svc_rdma_sendto.c | 8 ++++++-- 2 files changed, 29 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index a13830616107..9dd76806a5c9 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -1498,31 +1498,47 @@ DEFINE_ERROR_EVENT(chunk); ** Server-side RDMA API events **/ -TRACE_EVENT(svcrdma_dma_map_page, +DECLARE_EVENT_CLASS(svcrdma_dma_map_class, TP_PROTO( const struct svcxprt_rdma *rdma, - const void *page + u64 dma_addr, + u32 length ), - TP_ARGS(rdma, page), + TP_ARGS(rdma, dma_addr, length), TP_STRUCT__entry( - __field(const void *, page); + __field(u64, dma_addr) + __field(u32, length) __string(device, rdma->sc_cm_id->device->name) __string(addr, rdma->sc_xprt.xpt_remotebuf) ), TP_fast_assign( - __entry->page = page; + __entry->dma_addr = dma_addr; + __entry->length = length; __assign_str(device, rdma->sc_cm_id->device->name); __assign_str(addr, rdma->sc_xprt.xpt_remotebuf); ), - TP_printk("addr=%s device=%s page=%p", - __get_str(addr), __get_str(device), __entry->page + TP_printk("addr=%s device=%s dma_addr=%llu length=%u", + __get_str(addr), __get_str(device), + __entry->dma_addr, __entry->length ) ); +#define DEFINE_SVC_DMA_EVENT(name) \ + DEFINE_EVENT(svcrdma_dma_map_class, svcrdma_##name, \ + TP_PROTO( \ + const struct svcxprt_rdma *rdma,\ + u64 dma_addr, \ + u32 length \ + ), \ + TP_ARGS(rdma, dma_addr, length)) + +DEFINE_SVC_DMA_EVENT(dma_map_page); +DEFINE_SVC_DMA_EVENT(dma_unmap_page); + TRACE_EVENT(svcrdma_dma_map_rwctx, TP_PROTO( const struct svcxprt_rdma *rdma, diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index 6fdba72f89f4..f3f108090aa4 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -233,11 +233,15 @@ void svc_rdma_send_ctxt_put(struct svcxprt_rdma *rdma, /* The first SGE contains the transport header, which * remains mapped until @ctxt is destroyed. */ - for (i = 1; i < ctxt->sc_send_wr.num_sge; i++) + for (i = 1; i < ctxt->sc_send_wr.num_sge; i++) { ib_dma_unmap_page(device, ctxt->sc_sges[i].addr, ctxt->sc_sges[i].length, DMA_TO_DEVICE); + trace_svcrdma_dma_unmap_page(rdma, + ctxt->sc_sges[i].addr, + ctxt->sc_sges[i].length); + } for (i = 0; i < ctxt->sc_page_count; ++i) put_page(ctxt->sc_pages[i]); @@ -490,6 +494,7 @@ static int svc_rdma_dma_map_page(struct svcxprt_rdma *rdma, dma_addr_t dma_addr; dma_addr = ib_dma_map_page(dev, page, offset, len, DMA_TO_DEVICE); + trace_svcrdma_dma_map_page(rdma, dma_addr, len); if (ib_dma_mapping_error(dev, dma_addr)) goto out_maperr; @@ -499,7 +504,6 @@ static int svc_rdma_dma_map_page(struct svcxprt_rdma *rdma, return 0; out_maperr: - trace_svcrdma_dma_map_page(rdma, page); return -EIO; } -- cgit v1.2.3 From 89da2ba947b1080199f4a6413686569a75fc2e7d Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Tue, 8 Oct 2019 15:16:14 +0800 Subject: soc: qcom: Fix llcc-qcom definitions to include commit 99356b03b431 ("soc: qcom: Make llcc-qcom a generic driver") move these out of llcc-qcom.h, make the building fails: drivers/edac/qcom_edac.c:86:40: error: array type has incomplete element type struct llcc_edac_reg_data static const struct llcc_edac_reg_data edac_reg_data[] = { ^~~~~~~~~~~~~ drivers/edac/qcom_edac.c:87:3: error: array index in non-array initializer [LLCC_DRAM_CE] = { ^~~~~~~~~~~~ drivers/edac/qcom_edac.c:87:3: note: (near initialization for edac_reg_data) drivers/edac/qcom_edac.c:88:3: error: field name not in record or union initializer .name = "DRAM Single-bit", ... drivers/edac/qcom_edac.c:169:51: warning: struct llcc_drv_data declared inside parameter list will not be visible outside of this definition or declaration qcom_llcc_clear_error_status(int err_type, struct llcc_drv_data *drv) ^~~~~~~~~~~~~ This patch move the needed definitions back to include. Reported-by: Hulk Robot Fixes: 99356b03b431 ("soc: qcom: Make llcc-qcom a generic driver") Signed-off-by: YueHaibing Signed-off-by: Bjorn Andersson --- drivers/soc/qcom/llcc-qcom.c | 50 -------------------------------------- include/linux/soc/qcom/llcc-qcom.h | 50 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 50 insertions(+), 50 deletions(-) (limited to 'include') diff --git a/drivers/soc/qcom/llcc-qcom.c b/drivers/soc/qcom/llcc-qcom.c index 98563ef0ac6b..436067367db4 100644 --- a/drivers/soc/qcom/llcc-qcom.c +++ b/drivers/soc/qcom/llcc-qcom.c @@ -86,56 +86,6 @@ struct llcc_slice_config { bool activate_on_init; }; -/** - * llcc_drv_data - Data associated with the llcc driver - * @regmap: regmap associated with the llcc device - * @bcast_regmap: regmap associated with llcc broadcast offset - * @cfg: pointer to the data structure for slice configuration - * @lock: mutex associated with each slice - * @cfg_size: size of the config data table - * @max_slices: max slices as read from device tree - * @num_banks: Number of llcc banks - * @bitmap: Bit map to track the active slice ids - * @offsets: Pointer to the bank offsets array - * @ecc_irq: interrupt for llcc cache error detection and reporting - */ -struct llcc_drv_data { - struct regmap *regmap; - struct regmap *bcast_regmap; - const struct llcc_slice_config *cfg; - struct mutex lock; - u32 cfg_size; - u32 max_slices; - u32 num_banks; - unsigned long *bitmap; - u32 *offsets; - int ecc_irq; -}; - -/** - * llcc_edac_reg_data - llcc edac registers data for each error type - * @name: Name of the error - * @synd_reg: Syndrome register address - * @count_status_reg: Status register address to read the error count - * @ways_status_reg: Status register address to read the error ways - * @reg_cnt: Number of registers - * @count_mask: Mask value to get the error count - * @ways_mask: Mask value to get the error ways - * @count_shift: Shift value to get the error count - * @ways_shift: Shift value to get the error ways - */ -struct llcc_edac_reg_data { - char *name; - u64 synd_reg; - u64 count_status_reg; - u64 ways_status_reg; - u32 reg_cnt; - u32 count_mask; - u32 ways_mask; - u8 count_shift; - u8 ways_shift; -}; - struct qcom_llcc_config { const struct llcc_slice_config *sct_data; int size; diff --git a/include/linux/soc/qcom/llcc-qcom.h b/include/linux/soc/qcom/llcc-qcom.h index c0acdb28fde8..90b864655822 100644 --- a/include/linux/soc/qcom/llcc-qcom.h +++ b/include/linux/soc/qcom/llcc-qcom.h @@ -37,6 +37,56 @@ struct llcc_slice_desc { size_t slice_size; }; +/** + * llcc_edac_reg_data - llcc edac registers data for each error type + * @name: Name of the error + * @synd_reg: Syndrome register address + * @count_status_reg: Status register address to read the error count + * @ways_status_reg: Status register address to read the error ways + * @reg_cnt: Number of registers + * @count_mask: Mask value to get the error count + * @ways_mask: Mask value to get the error ways + * @count_shift: Shift value to get the error count + * @ways_shift: Shift value to get the error ways + */ +struct llcc_edac_reg_data { + char *name; + u64 synd_reg; + u64 count_status_reg; + u64 ways_status_reg; + u32 reg_cnt; + u32 count_mask; + u32 ways_mask; + u8 count_shift; + u8 ways_shift; +}; + +/** + * llcc_drv_data - Data associated with the llcc driver + * @regmap: regmap associated with the llcc device + * @bcast_regmap: regmap associated with llcc broadcast offset + * @cfg: pointer to the data structure for slice configuration + * @lock: mutex associated with each slice + * @cfg_size: size of the config data table + * @max_slices: max slices as read from device tree + * @num_banks: Number of llcc banks + * @bitmap: Bit map to track the active slice ids + * @offsets: Pointer to the bank offsets array + * @ecc_irq: interrupt for llcc cache error detection and reporting + */ +struct llcc_drv_data { + struct regmap *regmap; + struct regmap *bcast_regmap; + const struct llcc_slice_config *cfg; + struct mutex lock; + u32 cfg_size; + u32 max_slices; + u32 num_banks; + unsigned long *bitmap; + u32 *offsets; + int ecc_irq; +}; + #if IS_ENABLED(CONFIG_QCOM_LLCC) /** * llcc_slice_getd - get llcc slice descriptor -- cgit v1.2.3 From d30cd83f68535ca21412b1abe8684438690c1c2b Mon Sep 17 00:00:00 2001 From: Tero Kristo Date: Wed, 9 Oct 2019 08:55:38 -0700 Subject: soc: ti: omap-prm: add support for denying idle for reset clockdomain TI SoCs hardware reset signals require the parent clockdomain to be in force wakeup mode while de-asserting the reset, otherwise it may never complete. To support this, add pdata hooks to control the clockdomain directly. Signed-off-by: Tero Kristo Reviewed-by: Tony Lindgren Signed-off-by: Santosh Shilimkar --- drivers/soc/ti/omap_prm.c | 36 ++++++++++++++++++++++++++++++++++-- include/linux/platform_data/ti-prm.h | 21 +++++++++++++++++++++ 2 files changed, 55 insertions(+), 2 deletions(-) create mode 100644 include/linux/platform_data/ti-prm.h (limited to 'include') diff --git a/drivers/soc/ti/omap_prm.c b/drivers/soc/ti/omap_prm.c index a3ffb19e402f..09985da8f6d0 100644 --- a/drivers/soc/ti/omap_prm.c +++ b/drivers/soc/ti/omap_prm.c @@ -16,6 +16,8 @@ #include #include +#include + struct omap_rst_map { s8 rst; s8 st; @@ -24,6 +26,7 @@ struct omap_rst_map { struct omap_prm_data { u32 base; const char *name; + const char *clkdm_name; u16 rstctrl; u16 rstst; const struct omap_rst_map *rstmap; @@ -40,6 +43,8 @@ struct omap_reset_data { struct omap_prm *prm; u32 mask; spinlock_t lock; + struct clockdomain *clkdm; + struct device *dev; }; #define to_omap_reset_data(p) container_of((p), struct omap_reset_data, rcdev) @@ -49,6 +54,7 @@ struct omap_reset_data { #define OMAP_PRM_HAS_RSTCTRL BIT(0) #define OMAP_PRM_HAS_RSTST BIT(1) +#define OMAP_PRM_HAS_NO_CLKDM BIT(2) #define OMAP_PRM_HAS_RESETS (OMAP_PRM_HAS_RSTCTRL | OMAP_PRM_HAS_RSTST) @@ -133,6 +139,8 @@ static int omap_reset_deassert(struct reset_controller_dev *rcdev, int st_bit; bool has_rstst; unsigned long flags; + struct ti_prm_platform_data *pdata = dev_get_platdata(reset->dev); + int ret = 0; has_rstst = reset->prm->data->rstst || (reset->prm->data->flags & OMAP_PRM_HAS_RSTST); @@ -145,6 +153,9 @@ static int omap_reset_deassert(struct reset_controller_dev *rcdev, writel_relaxed(v, reset->prm->base + reset->prm->data->rstst); } + if (reset->clkdm) + pdata->clkdm_deny_idle(reset->clkdm); + /* de-assert the reset control line */ spin_lock_irqsave(&reset->lock, flags); v = readl_relaxed(reset->prm->base + reset->prm->data->rstctrl); @@ -153,7 +164,7 @@ static int omap_reset_deassert(struct reset_controller_dev *rcdev, spin_unlock_irqrestore(&reset->lock, flags); if (!has_rstst) - return 0; + goto exit; /* wait for the status to be set */ ret = readl_relaxed_poll_timeout(reset->prm->base + @@ -164,7 +175,11 @@ static int omap_reset_deassert(struct reset_controller_dev *rcdev, pr_err("%s: timedout waiting for %s:%lu\n", __func__, reset->prm->data->name, id); - return 0; +exit: + if (reset->clkdm) + pdata->clkdm_allow_idle(reset->clkdm); + + return ret; } static const struct reset_control_ops omap_reset_ops = { @@ -189,6 +204,8 @@ static int omap_prm_reset_init(struct platform_device *pdev, { struct omap_reset_data *reset; const struct omap_rst_map *map; + struct ti_prm_platform_data *pdata = dev_get_platdata(&pdev->dev); + char buf[32]; /* * Check if we have controllable resets. If either rstctrl is non-zero @@ -198,6 +215,11 @@ static int omap_prm_reset_init(struct platform_device *pdev, if (!prm->data->rstctrl && !(prm->data->flags & OMAP_PRM_HAS_RSTCTRL)) return 0; + /* Check if we have the pdata callbacks in place */ + if (!pdata || !pdata->clkdm_lookup || !pdata->clkdm_deny_idle || + !pdata->clkdm_allow_idle) + return -EINVAL; + map = prm->data->rstmap; if (!map) return -EINVAL; @@ -212,10 +234,20 @@ static int omap_prm_reset_init(struct platform_device *pdev, reset->rcdev.nr_resets = OMAP_MAX_RESETS; reset->rcdev.of_xlate = omap_prm_reset_xlate; reset->rcdev.of_reset_n_cells = 1; + reset->dev = &pdev->dev; spin_lock_init(&reset->lock); reset->prm = prm; + sprintf(buf, "%s_clkdm", prm->data->clkdm_name ? prm->data->clkdm_name : + prm->data->name); + + if (!(prm->data->flags & OMAP_PRM_HAS_NO_CLKDM)) { + reset->clkdm = pdata->clkdm_lookup(buf); + if (!reset->clkdm) + return -EINVAL; + } + while (map->rst >= 0) { reset->mask |= BIT(map->rst); map++; diff --git a/include/linux/platform_data/ti-prm.h b/include/linux/platform_data/ti-prm.h new file mode 100644 index 000000000000..28154c3226c2 --- /dev/null +++ b/include/linux/platform_data/ti-prm.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * TI PRM (Power & Reset Manager) platform data + * + * Copyright (C) 2019 Texas Instruments, Inc. + * + * Tero Kristo + */ + +#ifndef _LINUX_PLATFORM_DATA_TI_PRM_H +#define _LINUX_PLATFORM_DATA_TI_PRM_H + +struct clockdomain; + +struct ti_prm_platform_data { + void (*clkdm_deny_idle)(struct clockdomain *clkdm); + void (*clkdm_allow_idle)(struct clockdomain *clkdm); + struct clockdomain * (*clkdm_lookup)(const char *name); +}; + +#endif /* _LINUX_PLATFORM_DATA_TI_PRM_H */ -- cgit v1.2.3 From f9bdad8ca8a40270576dd8751ac225febaa87f93 Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Mon, 29 Oct 2018 13:23:40 -0400 Subject: NFS NFSD: defining nl4_servers structure needed by both These structures are needed by COPY_NOTIFY on the client and needed by the nfsd as well Reviewed-by: Jeff Layton Signed-off-by: Olga Kornievskaia --- include/linux/nfs4.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index fd59904a282c..5810e248c1bd 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -16,6 +16,7 @@ #include #include #include +#include enum nfs4_acl_whotype { NFS4_ACL_WHO_NAMED = 0, @@ -674,4 +675,27 @@ struct nfs4_op_map { } u; }; +struct nfs42_netaddr { + char netid[RPCBIND_MAXNETIDLEN]; + char addr[RPCBIND_MAXUADDRLEN + 1]; + u32 netid_len; + u32 addr_len; +}; + +enum netloc_type4 { + NL4_NAME = 1, + NL4_URL = 2, + NL4_NETADDR = 3, +}; + +struct nl4_server { + enum netloc_type4 nl4_type; + union { + struct { /* NL4_NAME, NL4_URL */ + int nl4_str_sz; + char nl4_str[NFS4_OPAQUE_LIMIT + 1]; + }; + struct nfs42_netaddr nl4_addr; /* NL4_NETADDR */ + } u; +}; #endif -- cgit v1.2.3 From 0491567b51efeca807da1125a1a0d5193875e286 Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Tue, 4 Jun 2019 16:14:30 -0400 Subject: NFS: add COPY_NOTIFY operation Try using the delegation stateid, then the open stateid. Only NL4_NETATTR, No support for NL4_NAME and NL4_URL. Allow only one source server address to be returned for now. To distinguish between same server copy offload ("intra") and a copy between different server ("inter"), do a check of server owner identity and also make sure server is capable of doing a copy offload. Signed-off-by: Andy Adamson Signed-off-by: Olga Kornievskaia --- fs/nfs/nfs42.h | 12 ++++ fs/nfs/nfs42proc.c | 91 ++++++++++++++++++++++++ fs/nfs/nfs42xdr.c | 178 ++++++++++++++++++++++++++++++++++++++++++++++ fs/nfs/nfs4_fs.h | 2 + fs/nfs/nfs4client.c | 2 +- fs/nfs/nfs4file.c | 20 +++++- fs/nfs/nfs4proc.c | 1 + fs/nfs/nfs4xdr.c | 1 + include/linux/nfs4.h | 1 + include/linux/nfs_fs_sb.h | 1 + include/linux/nfs_xdr.h | 16 +++++ 11 files changed, 323 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h index 901cca7542f9..4995731a6714 100644 --- a/fs/nfs/nfs42.h +++ b/fs/nfs/nfs42.h @@ -13,6 +13,7 @@ #define PNFS_LAYOUTSTATS_MAXDEV (4) /* nfs4.2proc.c */ +#ifdef CONFIG_NFS_V4_2 int nfs42_proc_allocate(struct file *, loff_t, loff_t); ssize_t nfs42_proc_copy(struct file *, loff_t, struct file *, loff_t, size_t); int nfs42_proc_deallocate(struct file *, loff_t, loff_t); @@ -23,5 +24,16 @@ int nfs42_proc_clone(struct file *, struct file *, loff_t, loff_t, loff_t); int nfs42_proc_layouterror(struct pnfs_layout_segment *lseg, const struct nfs42_layout_error *errors, size_t n); +int nfs42_proc_copy_notify(struct file *, struct file *, + struct nfs42_copy_notify_res *); +static inline bool nfs42_files_from_same_server(struct file *in, + struct file *out) +{ + struct nfs_client *c_in = (NFS_SERVER(file_inode(in)))->nfs_client; + struct nfs_client *c_out = (NFS_SERVER(file_inode(out)))->nfs_client; + return nfs4_check_serverowner_major_id(c_in->cl_serverowner, + c_out->cl_serverowner); +} +#endif /* CONFIG_NFS_V4_2 */ #endif /* __LINUX_FS_NFS_NFS4_2_H */ diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 5196bfa7894d..6317dd89cf43 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -3,6 +3,7 @@ * Copyright (c) 2014 Anna Schumaker */ #include +#include #include #include #include @@ -15,10 +16,30 @@ #include "pnfs.h" #include "nfs4session.h" #include "internal.h" +#include "delegation.h" #define NFSDBG_FACILITY NFSDBG_PROC static int nfs42_do_offload_cancel_async(struct file *dst, nfs4_stateid *std); +static void nfs42_set_netaddr(struct file *filep, struct nfs42_netaddr *naddr) +{ + struct nfs_client *clp = (NFS_SERVER(file_inode(filep)))->nfs_client; + unsigned short port = 2049; + + rcu_read_lock(); + naddr->netid_len = scnprintf(naddr->netid, + sizeof(naddr->netid), "%s", + rpc_peeraddr2str(clp->cl_rpcclient, + RPC_DISPLAY_NETID)); + naddr->addr_len = scnprintf(naddr->addr, + sizeof(naddr->addr), + "%s.%u.%u", + rpc_peeraddr2str(clp->cl_rpcclient, + RPC_DISPLAY_ADDR), + port >> 8, port & 255); + rcu_read_unlock(); +} + static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, struct nfs_lock_context *lock, loff_t offset, loff_t len) { @@ -459,6 +480,76 @@ static int nfs42_do_offload_cancel_async(struct file *dst, return status; } +int _nfs42_proc_copy_notify(struct file *src, struct file *dst, + struct nfs42_copy_notify_args *args, + struct nfs42_copy_notify_res *res) +{ + struct nfs_server *src_server = NFS_SERVER(file_inode(src)); + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_COPY_NOTIFY], + .rpc_argp = args, + .rpc_resp = res, + }; + int status; + struct nfs_open_context *ctx; + struct nfs_lock_context *l_ctx; + + ctx = get_nfs_open_context(nfs_file_open_context(src)); + l_ctx = nfs_get_lock_context(ctx); + if (IS_ERR(l_ctx)) + return PTR_ERR(l_ctx); + + status = nfs4_set_rw_stateid(&args->cna_src_stateid, ctx, l_ctx, + FMODE_READ); + nfs_put_lock_context(l_ctx); + if (status) + return status; + + status = nfs4_call_sync(src_server->client, src_server, &msg, + &args->cna_seq_args, &res->cnr_seq_res, 0); + if (status == -ENOTSUPP) + src_server->caps &= ~NFS_CAP_COPY_NOTIFY; + + put_nfs_open_context(nfs_file_open_context(src)); + return status; +} + +int nfs42_proc_copy_notify(struct file *src, struct file *dst, + struct nfs42_copy_notify_res *res) +{ + struct nfs_server *src_server = NFS_SERVER(file_inode(src)); + struct nfs42_copy_notify_args *args; + struct nfs4_exception exception = { + .inode = file_inode(src), + }; + int status; + + if (!(src_server->caps & NFS_CAP_COPY_NOTIFY)) + return -EOPNOTSUPP; + + args = kzalloc(sizeof(struct nfs42_copy_notify_args), GFP_NOFS); + if (args == NULL) + return -ENOMEM; + + args->cna_src_fh = NFS_FH(file_inode(src)), + args->cna_dst.nl4_type = NL4_NETADDR; + nfs42_set_netaddr(dst, &args->cna_dst.u.nl4_addr); + exception.stateid = &args->cna_src_stateid; + + do { + status = _nfs42_proc_copy_notify(src, dst, args, res); + if (status == -ENOTSUPP) { + status = -EOPNOTSUPP; + goto out; + } + status = nfs4_handle_exception(src_server, status, &exception); + } while (exception.retry); + +out: + kfree(args); + return status; +} + static loff_t _nfs42_proc_llseek(struct file *filep, struct nfs_lock_context *lock, loff_t offset, int whence) { diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c index aed865a84629..ccabc0cd93dd 100644 --- a/fs/nfs/nfs42xdr.c +++ b/fs/nfs/nfs42xdr.c @@ -29,6 +29,16 @@ #define encode_offload_cancel_maxsz (op_encode_hdr_maxsz + \ XDR_QUADLEN(NFS4_STATEID_SIZE)) #define decode_offload_cancel_maxsz (op_decode_hdr_maxsz) +#define encode_copy_notify_maxsz (op_encode_hdr_maxsz + \ + XDR_QUADLEN(NFS4_STATEID_SIZE) + \ + 1 + /* nl4_type */ \ + 1 + XDR_QUADLEN(NFS4_OPAQUE_LIMIT)) +#define decode_copy_notify_maxsz (op_decode_hdr_maxsz + \ + 3 + /* cnr_lease_time */\ + XDR_QUADLEN(NFS4_STATEID_SIZE) + \ + 1 + /* Support 1 cnr_source_server */\ + 1 + /* nl4_type */ \ + 1 + XDR_QUADLEN(NFS4_OPAQUE_LIMIT)) #define encode_deallocate_maxsz (op_encode_hdr_maxsz + \ encode_fallocate_maxsz) #define decode_deallocate_maxsz (op_decode_hdr_maxsz) @@ -99,6 +109,12 @@ decode_sequence_maxsz + \ decode_putfh_maxsz + \ decode_offload_cancel_maxsz) +#define NFS4_enc_copy_notify_sz (compound_encode_hdr_maxsz + \ + encode_putfh_maxsz + \ + encode_copy_notify_maxsz) +#define NFS4_dec_copy_notify_sz (compound_decode_hdr_maxsz + \ + decode_putfh_maxsz + \ + decode_copy_notify_maxsz) #define NFS4_enc_deallocate_sz (compound_encode_hdr_maxsz + \ encode_sequence_maxsz + \ encode_putfh_maxsz + \ @@ -166,6 +182,26 @@ static void encode_allocate(struct xdr_stream *xdr, encode_fallocate(xdr, args); } +static void encode_nl4_server(struct xdr_stream *xdr, + const struct nl4_server *ns) +{ + encode_uint32(xdr, ns->nl4_type); + switch (ns->nl4_type) { + case NL4_NAME: + case NL4_URL: + encode_string(xdr, ns->u.nl4_str_sz, ns->u.nl4_str); + break; + case NL4_NETADDR: + encode_string(xdr, ns->u.nl4_addr.netid_len, + ns->u.nl4_addr.netid); + encode_string(xdr, ns->u.nl4_addr.addr_len, + ns->u.nl4_addr.addr); + break; + default: + WARN_ON_ONCE(1); + } +} + static void encode_copy(struct xdr_stream *xdr, const struct nfs42_copy_args *args, struct compound_hdr *hdr) @@ -191,6 +227,15 @@ static void encode_offload_cancel(struct xdr_stream *xdr, encode_nfs4_stateid(xdr, &args->osa_stateid); } +static void encode_copy_notify(struct xdr_stream *xdr, + const struct nfs42_copy_notify_args *args, + struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_COPY_NOTIFY, decode_copy_notify_maxsz, hdr); + encode_nfs4_stateid(xdr, &args->cna_src_stateid); + encode_nl4_server(xdr, &args->cna_dst); +} + static void encode_deallocate(struct xdr_stream *xdr, const struct nfs42_falloc_args *args, struct compound_hdr *hdr) @@ -354,6 +399,25 @@ static void nfs4_xdr_enc_offload_cancel(struct rpc_rqst *req, encode_nops(&hdr); } +/* + * Encode COPY_NOTIFY request + */ +static void nfs4_xdr_enc_copy_notify(struct rpc_rqst *req, + struct xdr_stream *xdr, + const void *data) +{ + const struct nfs42_copy_notify_args *args = data; + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->cna_seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->cna_seq_args, &hdr); + encode_putfh(xdr, args->cna_src_fh, &hdr); + encode_copy_notify(xdr, args, &hdr); + encode_nops(&hdr); +} + /* * Encode DEALLOCATE request */ @@ -490,6 +554,58 @@ static int decode_write_response(struct xdr_stream *xdr, return decode_verifier(xdr, &res->verifier.verifier); } +static int decode_nl4_server(struct xdr_stream *xdr, struct nl4_server *ns) +{ + struct nfs42_netaddr *naddr; + uint32_t dummy; + char *dummy_str; + __be32 *p; + int status; + + /* nl_type */ + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + return -EIO; + ns->nl4_type = be32_to_cpup(p); + switch (ns->nl4_type) { + case NL4_NAME: + case NL4_URL: + status = decode_opaque_inline(xdr, &dummy, &dummy_str); + if (unlikely(status)) + return status; + if (unlikely(dummy > NFS4_OPAQUE_LIMIT)) + return -EIO; + memcpy(&ns->u.nl4_str, dummy_str, dummy); + ns->u.nl4_str_sz = dummy; + break; + case NL4_NETADDR: + naddr = &ns->u.nl4_addr; + + /* netid string */ + status = decode_opaque_inline(xdr, &dummy, &dummy_str); + if (unlikely(status)) + return status; + if (unlikely(dummy > RPCBIND_MAXNETIDLEN)) + return -EIO; + naddr->netid_len = dummy; + memcpy(naddr->netid, dummy_str, naddr->netid_len); + + /* uaddr string */ + status = decode_opaque_inline(xdr, &dummy, &dummy_str); + if (unlikely(status)) + return status; + if (unlikely(dummy > RPCBIND_MAXUADDRLEN)) + return -EIO; + naddr->addr_len = dummy; + memcpy(naddr->addr, dummy_str, naddr->addr_len); + break; + default: + WARN_ON_ONCE(1); + return -EIO; + } + return 0; +} + static int decode_copy_requirements(struct xdr_stream *xdr, struct nfs42_copy_res *res) { __be32 *p; @@ -529,6 +645,42 @@ static int decode_offload_cancel(struct xdr_stream *xdr, return decode_op_hdr(xdr, OP_OFFLOAD_CANCEL); } +static int decode_copy_notify(struct xdr_stream *xdr, + struct nfs42_copy_notify_res *res) +{ + __be32 *p; + int status, count; + + status = decode_op_hdr(xdr, OP_COPY_NOTIFY); + if (status) + return status; + /* cnr_lease_time */ + p = xdr_inline_decode(xdr, 12); + if (unlikely(!p)) + return -EIO; + p = xdr_decode_hyper(p, &res->cnr_lease_time.seconds); + res->cnr_lease_time.nseconds = be32_to_cpup(p); + + status = decode_opaque_fixed(xdr, &res->cnr_stateid, NFS4_STATEID_SIZE); + if (unlikely(status)) + return -EIO; + + /* number of source addresses */ + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + return -EIO; + + count = be32_to_cpup(p); + if (count > 1) + pr_warn("NFS: %s: nsvr %d > Supported. Use first servers\n", + __func__, count); + + status = decode_nl4_server(xdr, &res->cnr_src); + if (unlikely(status)) + return -EIO; + return 0; +} + static int decode_deallocate(struct xdr_stream *xdr, struct nfs42_falloc_res *res) { return decode_op_hdr(xdr, OP_DEALLOCATE); @@ -656,6 +808,32 @@ out: return status; } +/* + * Decode COPY_NOTIFY response + */ +static int nfs4_xdr_dec_copy_notify(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + void *data) +{ + struct nfs42_copy_notify_res *res = data; + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->cnr_seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_copy_notify(xdr, res); + +out: + return status; +} + /* * Decode DEALLOCATE request */ diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 16b2e5cc3e94..8e590b424d75 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -457,6 +457,8 @@ int nfs41_discover_server_trunking(struct nfs_client *clp, struct nfs_client **, const struct cred *); extern void nfs4_schedule_session_recovery(struct nfs4_session *, int); extern void nfs41_notify_server(struct nfs_client *); +bool nfs4_check_serverowner_major_id(struct nfs41_server_owner *o1, + struct nfs41_server_owner *o2); #else static inline void nfs4_schedule_session_recovery(struct nfs4_session *session, int err) { diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index da6204025a2d..54aaf553d009 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -629,7 +629,7 @@ out: /* * Returns true if the server major ids match */ -static bool +bool nfs4_check_serverowner_major_id(struct nfs41_server_owner *o1, struct nfs41_server_owner *o2) { diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 339663d04bf8..686a6c4071e3 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -133,6 +133,9 @@ static ssize_t __nfs4_copy_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, size_t count, unsigned int flags) { + struct nfs42_copy_notify_res *cn_resp = NULL; + ssize_t ret; + /* Only offload copy if superblock is the same */ if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb) return -EXDEV; @@ -140,7 +143,22 @@ static ssize_t __nfs4_copy_file_range(struct file *file_in, loff_t pos_in, return -EOPNOTSUPP; if (file_inode(file_in) == file_inode(file_out)) return -EOPNOTSUPP; - return nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count); + if (!nfs42_files_from_same_server(file_in, file_out)) { + cn_resp = kzalloc(sizeof(struct nfs42_copy_notify_res), + GFP_NOFS); + if (unlikely(cn_resp == NULL)) + return -ENOMEM; + + ret = nfs42_proc_copy_notify(file_in, file_out, cn_resp); + if (ret) { + ret = -EOPNOTSUPP; + goto out; + } + } + ret = nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count); +out: + kfree(cn_resp); + return ret; } static ssize_t nfs4_copy_file_range(struct file *file_in, loff_t pos_in, diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 11eafcfc490b..505045b47670 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -9899,6 +9899,7 @@ static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = { | NFS_CAP_ALLOCATE | NFS_CAP_COPY | NFS_CAP_OFFLOAD_CANCEL + | NFS_CAP_COPY_NOTIFY | NFS_CAP_DEALLOCATE | NFS_CAP_SEEK | NFS_CAP_LAYOUTSTATS diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index ab07db0f07cd..2f9315de3d7d 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -7581,6 +7581,7 @@ const struct rpc_procinfo nfs4_procedures[] = { PROC42(CLONE, enc_clone, dec_clone), PROC42(COPY, enc_copy, dec_copy), PROC42(OFFLOAD_CANCEL, enc_offload_cancel, dec_offload_cancel), + PROC42(COPY_NOTIFY, enc_copy_notify, dec_copy_notify), PROC(LOOKUPP, enc_lookupp, dec_lookupp), PROC42(LAYOUTERROR, enc_layouterror, dec_layouterror), }; diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 5810e248c1bd..5e7a5261af4e 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -537,6 +537,7 @@ enum { NFSPROC4_CLNT_CLONE, NFSPROC4_CLNT_COPY, NFSPROC4_CLNT_OFFLOAD_CANCEL, + NFSPROC4_CLNT_COPY_NOTIFY, NFSPROC4_CLNT_LOOKUPP, NFSPROC4_CLNT_LAYOUTERROR, diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index a87fe854f008..e1c8748e1e82 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -276,5 +276,6 @@ struct nfs_server { #define NFS_CAP_COPY (1U << 24) #define NFS_CAP_OFFLOAD_CANCEL (1U << 25) #define NFS_CAP_LAYOUTERROR (1U << 26) +#define NFS_CAP_COPY_NOTIFY (1U << 27) #endif diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 9b8324ec08f3..0a7af40026d7 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1463,6 +1463,22 @@ struct nfs42_offload_status_res { int osr_status; }; +struct nfs42_copy_notify_args { + struct nfs4_sequence_args cna_seq_args; + + struct nfs_fh *cna_src_fh; + nfs4_stateid cna_src_stateid; + struct nl4_server cna_dst; +}; + +struct nfs42_copy_notify_res { + struct nfs4_sequence_res cnr_seq_res; + + struct nfstime4 cnr_lease_time; + nfs4_stateid cnr_stateid; + struct nl4_server cnr_src; +}; + struct nfs42_seek_args { struct nfs4_sequence_args seq_args; -- cgit v1.2.3 From 1d38f3f0d70008671f4dc055697ff3c3bb44a284 Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Tue, 4 Jun 2019 11:54:18 -0400 Subject: NFS: add ca_source_server<> to COPY Support only one source server address: the same address that the client and source server use. Signed-off-by: Andy Adamson Signed-off-by: Olga Kornievskaia --- fs/nfs/nfs42.h | 3 ++- fs/nfs/nfs42proc.c | 26 +++++++++++++++++--------- fs/nfs/nfs42xdr.c | 12 ++++++++++-- fs/nfs/nfs4file.c | 7 ++++++- include/linux/nfs_xdr.h | 1 + 5 files changed, 36 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h index 4995731a6714..02e3810cd889 100644 --- a/fs/nfs/nfs42.h +++ b/fs/nfs/nfs42.h @@ -15,7 +15,8 @@ /* nfs4.2proc.c */ #ifdef CONFIG_NFS_V4_2 int nfs42_proc_allocate(struct file *, loff_t, loff_t); -ssize_t nfs42_proc_copy(struct file *, loff_t, struct file *, loff_t, size_t); +ssize_t nfs42_proc_copy(struct file *, loff_t, struct file *, loff_t, size_t, + struct nl4_server *, nfs4_stateid *); int nfs42_proc_deallocate(struct file *, loff_t, loff_t); loff_t nfs42_proc_llseek(struct file *, loff_t, int); int nfs42_proc_layoutstats_generic(struct nfs_server *, diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 6317dd89cf43..e34ade844737 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -243,7 +243,9 @@ static ssize_t _nfs42_proc_copy(struct file *src, struct file *dst, struct nfs_lock_context *dst_lock, struct nfs42_copy_args *args, - struct nfs42_copy_res *res) + struct nfs42_copy_res *res, + struct nl4_server *nss, + nfs4_stateid *cnr_stateid) { struct rpc_message msg = { .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_COPY], @@ -257,11 +259,15 @@ static ssize_t _nfs42_proc_copy(struct file *src, size_t count = args->count; ssize_t status; - status = nfs4_set_rw_stateid(&args->src_stateid, src_lock->open_context, - src_lock, FMODE_READ); - if (status) - return status; - + if (nss) { + args->cp_src = nss; + nfs4_stateid_copy(&args->src_stateid, cnr_stateid); + } else { + status = nfs4_set_rw_stateid(&args->src_stateid, + src_lock->open_context, src_lock, FMODE_READ); + if (status) + return status; + } status = nfs_filemap_write_and_wait_range(file_inode(src)->i_mapping, pos_src, pos_src + (loff_t)count - 1); if (status) @@ -325,8 +331,9 @@ out: } ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src, - struct file *dst, loff_t pos_dst, - size_t count) + struct file *dst, loff_t pos_dst, size_t count, + struct nl4_server *nss, + nfs4_stateid *cnr_stateid) { struct nfs_server *server = NFS_SERVER(file_inode(dst)); struct nfs_lock_context *src_lock; @@ -368,7 +375,8 @@ ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src, inode_lock(file_inode(dst)); err = _nfs42_proc_copy(src, src_lock, dst, dst_lock, - &args, &res); + &args, &res, + nss, cnr_stateid); inode_unlock(file_inode(dst)); if (err >= 0) diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c index ccabc0cd93dd..c03f3246d6c5 100644 --- a/fs/nfs/nfs42xdr.c +++ b/fs/nfs/nfs42xdr.c @@ -21,7 +21,10 @@ #define encode_copy_maxsz (op_encode_hdr_maxsz + \ XDR_QUADLEN(NFS4_STATEID_SIZE) + \ XDR_QUADLEN(NFS4_STATEID_SIZE) + \ - 2 + 2 + 2 + 1 + 1 + 1) + 2 + 2 + 2 + 1 + 1 + 1 +\ + 1 + /* One cnr_source_server */\ + 1 + /* nl4_type */ \ + 1 + XDR_QUADLEN(NFS4_OPAQUE_LIMIT)) #define decode_copy_maxsz (op_decode_hdr_maxsz + \ NFS42_WRITE_RES_SIZE + \ 1 /* cr_consecutive */ + \ @@ -216,7 +219,12 @@ static void encode_copy(struct xdr_stream *xdr, encode_uint32(xdr, 1); /* consecutive = true */ encode_uint32(xdr, args->sync); - encode_uint32(xdr, 0); /* src server list */ + if (args->cp_src == NULL) { /* intra-ssc */ + encode_uint32(xdr, 0); /* no src server list */ + return; + } + encode_uint32(xdr, 1); /* supporting 1 server */ + encode_nl4_server(xdr, args->cp_src); } static void encode_offload_cancel(struct xdr_stream *xdr, diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 686a6c4071e3..b68b41be6d9f 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -134,6 +134,8 @@ static ssize_t __nfs4_copy_file_range(struct file *file_in, loff_t pos_in, size_t count, unsigned int flags) { struct nfs42_copy_notify_res *cn_resp = NULL; + struct nl4_server *nss = NULL; + nfs4_stateid *cnrs = NULL; ssize_t ret; /* Only offload copy if superblock is the same */ @@ -154,8 +156,11 @@ static ssize_t __nfs4_copy_file_range(struct file *file_in, loff_t pos_in, ret = -EOPNOTSUPP; goto out; } + nss = &cn_resp->cnr_src; + cnrs = &cn_resp->cnr_stateid; } - ret = nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count); + ret = nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count, + nss, cnrs); out: kfree(cn_resp); return ret; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 0a7af40026d7..008facac8a30 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1435,6 +1435,7 @@ struct nfs42_copy_args { u64 count; bool sync; + struct nl4_server *cp_src; }; struct nfs42_write_res { -- cgit v1.2.3 From 0e65a32c8a569db363048e17a708b1a0913adbef Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Fri, 14 Jun 2019 14:38:40 -0400 Subject: NFS: handle source server reboot When the source server reboots after a server-to-server copy was issued, we need to retry the copy from COPY_NOTIFY. We need to detect that the source server rebooted and there is a copy waiting on a destination server and wake it up. Signed-off-by: Olga Kornievskaia --- fs/nfs/nfs42proc.c | 68 ++++++++++++++++++++++++++++++++++---------------- fs/nfs/nfs4_fs.h | 1 + fs/nfs/nfs4file.c | 3 +++ fs/nfs/nfs4state.c | 26 +++++++++++++++---- include/linux/nfs_fs.h | 4 ++- 5 files changed, 75 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 5d833f5748e9..9c7feacb0358 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -153,22 +153,26 @@ out_unlock: } static int handle_async_copy(struct nfs42_copy_res *res, - struct nfs_server *server, + struct nfs_server *dst_server, + struct nfs_server *src_server, struct file *src, struct file *dst, - nfs4_stateid *src_stateid) + nfs4_stateid *src_stateid, + bool *restart) { struct nfs4_copy_state *copy, *tmp_copy; int status = NFS4_OK; bool found_pending = false; - struct nfs_open_context *ctx = nfs_file_open_context(dst); + struct nfs_open_context *dst_ctx = nfs_file_open_context(dst); + struct nfs_open_context *src_ctx = nfs_file_open_context(src); copy = kzalloc(sizeof(struct nfs4_copy_state), GFP_NOFS); if (!copy) return -ENOMEM; - spin_lock(&server->nfs_client->cl_lock); - list_for_each_entry(tmp_copy, &server->nfs_client->pending_cb_stateids, + spin_lock(&dst_server->nfs_client->cl_lock); + list_for_each_entry(tmp_copy, + &dst_server->nfs_client->pending_cb_stateids, copies) { if (memcmp(&res->write_res.stateid, &tmp_copy->stateid, NFS4_STATEID_SIZE)) @@ -178,7 +182,7 @@ static int handle_async_copy(struct nfs42_copy_res *res, break; } if (found_pending) { - spin_unlock(&server->nfs_client->cl_lock); + spin_unlock(&dst_server->nfs_client->cl_lock); kfree(copy); copy = tmp_copy; goto out; @@ -186,19 +190,32 @@ static int handle_async_copy(struct nfs42_copy_res *res, memcpy(©->stateid, &res->write_res.stateid, NFS4_STATEID_SIZE); init_completion(©->completion); - copy->parent_state = ctx->state; + copy->parent_dst_state = dst_ctx->state; + copy->parent_src_state = src_ctx->state; + + list_add_tail(©->copies, &dst_server->ss_copies); + spin_unlock(&dst_server->nfs_client->cl_lock); - list_add_tail(©->copies, &server->ss_copies); - spin_unlock(&server->nfs_client->cl_lock); + if (dst_server != src_server) { + spin_lock(&src_server->nfs_client->cl_lock); + list_add_tail(©->src_copies, &src_server->ss_copies); + spin_unlock(&src_server->nfs_client->cl_lock); + } status = wait_for_completion_interruptible(©->completion); - spin_lock(&server->nfs_client->cl_lock); + spin_lock(&dst_server->nfs_client->cl_lock); list_del_init(©->copies); - spin_unlock(&server->nfs_client->cl_lock); + spin_unlock(&dst_server->nfs_client->cl_lock); + if (dst_server != src_server) { + spin_lock(&src_server->nfs_client->cl_lock); + list_del_init(©->src_copies); + spin_unlock(&src_server->nfs_client->cl_lock); + } if (status == -ERESTARTSYS) { goto out_cancel; - } else if (copy->flags) { + } else if (copy->flags || copy->error == NFS4ERR_PARTNER_NO_AUTH) { status = -EAGAIN; + *restart = true; goto out_cancel; } out: @@ -247,7 +264,8 @@ static ssize_t _nfs42_proc_copy(struct file *src, struct nfs42_copy_args *args, struct nfs42_copy_res *res, struct nl4_server *nss, - nfs4_stateid *cnr_stateid) + nfs4_stateid *cnr_stateid, + bool *restart) { struct rpc_message msg = { .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_COPY], @@ -255,7 +273,9 @@ static ssize_t _nfs42_proc_copy(struct file *src, .rpc_resp = res, }; struct inode *dst_inode = file_inode(dst); - struct nfs_server *server = NFS_SERVER(dst_inode); + struct inode *src_inode = file_inode(src); + struct nfs_server *dst_server = NFS_SERVER(dst_inode); + struct nfs_server *src_server = NFS_SERVER(src_inode); loff_t pos_src = args->src_pos; loff_t pos_dst = args->dst_pos; size_t count = args->count; @@ -291,13 +311,15 @@ static ssize_t _nfs42_proc_copy(struct file *src, if (!res->commit_res.verf) return -ENOMEM; } + set_bit(NFS_CLNT_SRC_SSC_COPY_STATE, + &src_lock->open_context->state->flags); set_bit(NFS_CLNT_DST_SSC_COPY_STATE, &dst_lock->open_context->state->flags); - status = nfs4_call_sync(server->client, server, &msg, + status = nfs4_call_sync(dst_server->client, dst_server, &msg, &args->seq_args, &res->seq_res, 0); if (status == -ENOTSUPP) - server->caps &= ~NFS_CAP_COPY; + dst_server->caps &= ~NFS_CAP_COPY; if (status) goto out; @@ -309,8 +331,8 @@ static ssize_t _nfs42_proc_copy(struct file *src, } if (!res->synchronous) { - status = handle_async_copy(res, server, src, dst, - &args->src_stateid); + status = handle_async_copy(res, dst_server, src_server, src, + dst, &args->src_stateid, restart); if (status) return status; } @@ -358,6 +380,7 @@ ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src, .stateid = &args.dst_stateid, }; ssize_t err, err2; + bool restart = false; src_lock = nfs_get_lock_context(nfs_file_open_context(src)); if (IS_ERR(src_lock)) @@ -378,7 +401,7 @@ ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src, err = _nfs42_proc_copy(src, src_lock, dst, dst_lock, &args, &res, - nss, cnr_stateid); + nss, cnr_stateid, &restart); inode_unlock(file_inode(dst)); if (err >= 0) @@ -388,8 +411,11 @@ ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src, err = -EOPNOTSUPP; break; } else if (err == -EAGAIN) { - dst_exception.retry = 1; - continue; + if (!restart) { + dst_exception.retry = 1; + continue; + } + break; } else if (err == -NFS4ERR_OFFLOAD_NO_REQS && !args.sync) { args.sync = true; dst_exception.retry = 1; diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 814674f073a1..2122748f6f7c 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -168,6 +168,7 @@ enum { NFS_STATE_CHANGE_WAIT, /* A state changing operation is outstanding */ #ifdef CONFIG_NFS_V4_2 NFS_CLNT_DST_SSC_COPY_STATE, /* dst server open state on client*/ + NFS_CLNT_SRC_SSC_COPY_STATE, /* src server open state on client*/ NFS_SRV_SSC_COPY_STATE, /* ssc state on the dst server */ #endif /* CONFIG_NFS_V4_2 */ }; diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index a932fc9ca9c4..2af30b7f5bfd 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -146,6 +146,7 @@ static ssize_t __nfs4_copy_file_range(struct file *file_in, loff_t pos_in, return -EOPNOTSUPP; if (file_inode(file_in) == file_inode(file_out)) return -EOPNOTSUPP; +retry: if (!nfs42_files_from_same_server(file_in, file_out)) { cn_resp = kzalloc(sizeof(struct nfs42_copy_notify_res), GFP_NOFS); @@ -164,6 +165,8 @@ static ssize_t __nfs4_copy_file_range(struct file *file_in, loff_t pos_in, nss, cnrs); out: kfree(cn_resp); + if (ret == -EAGAIN) + goto retry; return ret; } diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index c45b3007e2af..e799fbe9ac58 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1556,16 +1556,32 @@ static void nfs42_complete_copies(struct nfs4_state_owner *sp, struct nfs4_state { struct nfs4_copy_state *copy; - if (!test_bit(NFS_CLNT_DST_SSC_COPY_STATE, &state->flags)) + if (!test_bit(NFS_CLNT_DST_SSC_COPY_STATE, &state->flags) && + !test_bit(NFS_CLNT_SRC_SSC_COPY_STATE, &state->flags)) return; spin_lock(&sp->so_server->nfs_client->cl_lock); list_for_each_entry(copy, &sp->so_server->ss_copies, copies) { - if (!nfs4_stateid_match_other(&state->stateid, ©->parent_state->stateid)) - continue; + if ((test_bit(NFS_CLNT_DST_SSC_COPY_STATE, &state->flags) && + !nfs4_stateid_match_other(&state->stateid, + ©->parent_dst_state->stateid))) + continue; copy->flags = 1; - complete(©->completion); - break; + if (test_and_clear_bit(NFS_CLNT_DST_SSC_COPY_STATE, + &state->flags)) { + clear_bit(NFS_CLNT_SRC_SSC_COPY_STATE, &state->flags); + complete(©->completion); + } + } + list_for_each_entry(copy, &sp->so_server->ss_copies, src_copies) { + if ((test_bit(NFS_CLNT_SRC_SSC_COPY_STATE, &state->flags) && + !nfs4_stateid_match_other(&state->stateid, + ©->parent_src_state->stateid))) + continue; + copy->flags = 1; + if (test_and_clear_bit(NFS_CLNT_DST_SSC_COPY_STATE, + &state->flags)) + complete(©->completion); } spin_unlock(&sp->so_server->nfs_client->cl_lock); } diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 570a60c2f4f4..c06b1fd130f3 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -189,13 +189,15 @@ struct nfs_inode { struct nfs4_copy_state { struct list_head copies; + struct list_head src_copies; nfs4_stateid stateid; struct completion completion; uint64_t count; struct nfs_writeverf verf; int error; int flags; - struct nfs4_state *parent_state; + struct nfs4_state *parent_src_state; + struct nfs4_state *parent_dst_state; }; /* -- cgit v1.2.3 From c51c4841f1571673d9075b8cf5efa6995ea91d0e Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 29 Jul 2019 01:46:43 +0900 Subject: scsi: ch: add include guard to chio.h Add a header include guard just in case. Link: https://lore.kernel.org/r/20190728164643.16335-1-yamada.masahiro@socionext.com Signed-off-by: Masahiro Yamada Signed-off-by: Martin K. Petersen --- include/uapi/linux/chio.h | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/chio.h b/include/uapi/linux/chio.h index 689fc93fafda..e1cad4c319ee 100644 --- a/include/uapi/linux/chio.h +++ b/include/uapi/linux/chio.h @@ -3,6 +3,9 @@ * ioctl interface for the scsi media changer driver */ +#ifndef _UAPI_LINUX_CHIO_H +#define _UAPI_LINUX_CHIO_H + /* changer element types */ #define CHET_MT 0 /* media transport element (robot) */ #define CHET_ST 1 /* storage element (media slots) */ @@ -160,10 +163,4 @@ struct changer_set_voltag { #define CHIOSVOLTAG _IOW('c',18,struct changer_set_voltag) #define CHIOGVPARAMS _IOR('c',19,struct changer_vendor_params) -/* ---------------------------------------------------------------------- */ - -/* - * Local variables: - * c-basic-offset: 8 - * End: - */ +#endif /* _UAPI_LINUX_CHIO_H */ -- cgit v1.2.3 From 1f1a65d495df99925a497b2c602200c7532723e5 Mon Sep 17 00:00:00 2001 From: Maciej Falkowski Date: Thu, 26 Sep 2019 13:02:19 +0200 Subject: ASoC: samsung: i2s: Document clocks macros Document clocks macros with their description from 'Documentation/devicetree/bindings/sound/samsung-i2s.txt' Signed-off-by: Maciej Falkowski Signed-off-by: Marek Szyprowski Reviewed-by: Krzysztof Kozlowski Signed-off-by: Rob Herring --- include/dt-bindings/sound/samsung-i2s.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/dt-bindings/sound/samsung-i2s.h b/include/dt-bindings/sound/samsung-i2s.h index 77545f14c379..250de0d6c734 100644 --- a/include/dt-bindings/sound/samsung-i2s.h +++ b/include/dt-bindings/sound/samsung-i2s.h @@ -2,8 +2,14 @@ #ifndef _DT_BINDINGS_SAMSUNG_I2S_H #define _DT_BINDINGS_SAMSUNG_I2S_H -#define CLK_I2S_CDCLK 0 -#define CLK_I2S_RCLK_SRC 1 -#define CLK_I2S_RCLK_PSR 2 +#define CLK_I2S_CDCLK 0 /* the CDCLK (CODECLKO) gate clock */ + +#define CLK_I2S_RCLK_SRC 1 /* the RCLKSRC mux clock (corresponding to + * RCLKSRC bit in IISMOD register) + */ + +#define CLK_I2S_RCLK_PSR 2 /* the RCLK prescaler divider clock + * (corresponding to the IISPSR register) + */ #endif /* _DT_BINDINGS_SAMSUNG_I2S_H */ -- cgit v1.2.3 From c9c13ba428ef90a9b408a6cdf874e14ab5754516 Mon Sep 17 00:00:00 2001 From: Denis Efremov Date: Sat, 28 Sep 2019 02:43:08 +0300 Subject: PCI: Add PCI_STD_NUM_BARS for the number of standard BARs Code that iterates over all standard PCI BARs typically uses PCI_STD_RESOURCE_END. However, that requires the unusual test "i <= PCI_STD_RESOURCE_END" rather than something the typical "i < PCI_STD_NUM_BARS". Add a definition for PCI_STD_NUM_BARS and change loops to use the more idiomatic C style to help avoid fencepost errors. Link: https://lore.kernel.org/r/20190927234026.23342-1-efremov@linux.com Link: https://lore.kernel.org/r/20190927234308.23935-1-efremov@linux.com Link: https://lore.kernel.org/r/20190916204158.6889-3-efremov@linux.com Signed-off-by: Denis Efremov Signed-off-by: Bjorn Helgaas Acked-by: Sebastian Ott # arch/s390/ Acked-by: Bartlomiej Zolnierkiewicz # video/fbdev/ Acked-by: Gustavo Pimentel # pci/controller/dwc/ Acked-by: Jack Wang # scsi/pm8001/ Acked-by: Martin K. Petersen # scsi/pm8001/ Acked-by: Ulf Hansson # memstick/ --- arch/alpha/kernel/pci-sysfs.c | 8 +++--- arch/s390/include/asm/pci.h | 5 +--- arch/s390/include/asm/pci_clp.h | 6 ++--- arch/s390/pci/pci.c | 16 ++++++------ arch/s390/pci/pci_clp.c | 6 ++--- arch/x86/pci/common.c | 2 +- arch/x86/pci/intel_mid_pci.c | 2 +- drivers/ata/pata_atp867x.c | 2 +- drivers/ata/sata_nv.c | 2 +- drivers/memstick/host/jmb38x_ms.c | 2 +- drivers/misc/pci_endpoint_test.c | 8 +++--- drivers/net/ethernet/intel/e1000/e1000.h | 1 - drivers/net/ethernet/intel/e1000/e1000_main.c | 2 +- drivers/net/ethernet/intel/ixgb/ixgb.h | 1 - drivers/net/ethernet/intel/ixgb/ixgb_main.c | 2 +- drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c | 4 +-- drivers/net/ethernet/synopsys/dwc-xlgmac-pci.c | 2 +- drivers/pci/controller/dwc/pci-dra7xx.c | 2 +- drivers/pci/controller/dwc/pci-layerscape-ep.c | 2 +- drivers/pci/controller/dwc/pcie-artpec6.c | 2 +- drivers/pci/controller/dwc/pcie-designware-plat.c | 2 +- drivers/pci/controller/dwc/pcie-designware.h | 2 +- drivers/pci/controller/pci-hyperv.c | 10 +++---- drivers/pci/endpoint/functions/pci-epf-test.c | 10 +++---- drivers/pci/pci-sysfs.c | 4 +-- drivers/pci/pci.c | 13 ++++----- drivers/pci/proc.c | 4 +-- drivers/pci/quirks.c | 4 +-- drivers/rapidio/devices/tsi721.c | 2 +- drivers/scsi/pm8001/pm8001_hwi.c | 2 +- drivers/scsi/pm8001/pm8001_init.c | 2 +- drivers/staging/gasket/gasket_constants.h | 3 --- drivers/staging/gasket/gasket_core.c | 12 ++++----- drivers/staging/gasket/gasket_core.h | 4 +-- drivers/tty/serial/8250/8250_pci.c | 8 +++--- drivers/usb/core/hcd-pci.c | 2 +- drivers/usb/host/pci-quirks.c | 2 +- drivers/vfio/pci/vfio_pci.c | 11 +++++--- drivers/vfio/pci/vfio_pci_config.c | 32 ++++++++++++----------- drivers/vfio/pci/vfio_pci_private.h | 4 +-- drivers/video/fbdev/core/fbmem.c | 4 +-- drivers/video/fbdev/efifb.c | 2 +- include/linux/pci-epc.h | 2 +- include/linux/pci.h | 2 +- include/uapi/linux/pci_regs.h | 1 + lib/devres.c | 2 +- 46 files changed, 110 insertions(+), 113 deletions(-) (limited to 'include') diff --git a/arch/alpha/kernel/pci-sysfs.c b/arch/alpha/kernel/pci-sysfs.c index f94c732fedeb..0021580d79ad 100644 --- a/arch/alpha/kernel/pci-sysfs.c +++ b/arch/alpha/kernel/pci-sysfs.c @@ -71,10 +71,10 @@ static int pci_mmap_resource(struct kobject *kobj, struct pci_bus_region bar; int i; - for (i = 0; i < PCI_ROM_RESOURCE; i++) + for (i = 0; i < PCI_STD_NUM_BARS; i++) if (res == &pdev->resource[i]) break; - if (i >= PCI_ROM_RESOURCE) + if (i >= PCI_STD_NUM_BARS) return -ENODEV; if (res->flags & IORESOURCE_MEM && iomem_is_exclusive(res->start)) @@ -115,7 +115,7 @@ void pci_remove_resource_files(struct pci_dev *pdev) { int i; - for (i = 0; i < PCI_ROM_RESOURCE; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { struct bin_attribute *res_attr; res_attr = pdev->res_attr[i]; @@ -232,7 +232,7 @@ int pci_create_resource_files(struct pci_dev *pdev) int retval; /* Expose the PCI resources from this device as files */ - for (i = 0; i < PCI_ROM_RESOURCE; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { /* skip empty resources */ if (!pci_resource_len(pdev, i)) diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h index a2399eff84ca..3a06c264ea53 100644 --- a/arch/s390/include/asm/pci.h +++ b/arch/s390/include/asm/pci.h @@ -2,9 +2,6 @@ #ifndef __ASM_S390_PCI_H #define __ASM_S390_PCI_H -/* must be set before including pci_clp.h */ -#define PCI_BAR_COUNT 6 - #include #include #include @@ -138,7 +135,7 @@ struct zpci_dev { char res_name[16]; bool mio_capable; - struct zpci_bar_struct bars[PCI_BAR_COUNT]; + struct zpci_bar_struct bars[PCI_STD_NUM_BARS]; u64 start_dma; /* Start of available DMA addresses */ u64 end_dma; /* End of available DMA addresses */ diff --git a/arch/s390/include/asm/pci_clp.h b/arch/s390/include/asm/pci_clp.h index 50359172cc48..bd2cb4ea7d93 100644 --- a/arch/s390/include/asm/pci_clp.h +++ b/arch/s390/include/asm/pci_clp.h @@ -77,7 +77,7 @@ struct mio_info { struct { u64 wb; u64 wt; - } addr[PCI_BAR_COUNT]; + } addr[PCI_STD_NUM_BARS]; u32 reserved[6]; } __packed; @@ -98,9 +98,9 @@ struct clp_rsp_query_pci { u16 util_str_avail : 1; /* utility string available? */ u16 pfgid : 8; /* pci function group id */ u32 fid; /* pci function id */ - u8 bar_size[PCI_BAR_COUNT]; + u8 bar_size[PCI_STD_NUM_BARS]; u16 pchid; - __le32 bar[PCI_BAR_COUNT]; + __le32 bar[PCI_STD_NUM_BARS]; u8 pfip[CLP_PFIP_NR_SEGMENTS]; /* pci function internal path */ u32 : 16; u8 fmb_len; diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index c7fea9bea8cb..7b4c2acf05a8 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -43,7 +43,7 @@ static DECLARE_BITMAP(zpci_domain, ZPCI_NR_DEVICES); static DEFINE_SPINLOCK(zpci_domain_lock); #define ZPCI_IOMAP_ENTRIES \ - min(((unsigned long) ZPCI_NR_DEVICES * PCI_BAR_COUNT / 2), \ + min(((unsigned long) ZPCI_NR_DEVICES * PCI_STD_NUM_BARS / 2), \ ZPCI_IOMAP_MAX_ENTRIES) static DEFINE_SPINLOCK(zpci_iomap_lock); @@ -294,7 +294,7 @@ static void __iomem *pci_iomap_range_mio(struct pci_dev *pdev, int bar, void __iomem *pci_iomap_range(struct pci_dev *pdev, int bar, unsigned long offset, unsigned long max) { - if (!pci_resource_len(pdev, bar) || bar >= PCI_BAR_COUNT) + if (bar >= PCI_STD_NUM_BARS || !pci_resource_len(pdev, bar)) return NULL; if (static_branch_likely(&have_mio)) @@ -324,7 +324,7 @@ static void __iomem *pci_iomap_wc_range_mio(struct pci_dev *pdev, int bar, void __iomem *pci_iomap_wc_range(struct pci_dev *pdev, int bar, unsigned long offset, unsigned long max) { - if (!pci_resource_len(pdev, bar) || bar >= PCI_BAR_COUNT) + if (bar >= PCI_STD_NUM_BARS || !pci_resource_len(pdev, bar)) return NULL; if (static_branch_likely(&have_mio)) @@ -416,7 +416,7 @@ static void zpci_map_resources(struct pci_dev *pdev) resource_size_t len; int i; - for (i = 0; i < PCI_BAR_COUNT; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { len = pci_resource_len(pdev, i); if (!len) continue; @@ -451,7 +451,7 @@ static void zpci_unmap_resources(struct pci_dev *pdev) if (zpci_use_mio(zdev)) return; - for (i = 0; i < PCI_BAR_COUNT; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { len = pci_resource_len(pdev, i); if (!len) continue; @@ -514,7 +514,7 @@ static int zpci_setup_bus_resources(struct zpci_dev *zdev, snprintf(zdev->res_name, sizeof(zdev->res_name), "PCI Bus %04x:%02x", zdev->domain, ZPCI_BUS_NR); - for (i = 0; i < PCI_BAR_COUNT; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { if (!zdev->bars[i].size) continue; entry = zpci_alloc_iomap(zdev); @@ -551,7 +551,7 @@ static void zpci_cleanup_bus_resources(struct zpci_dev *zdev) { int i; - for (i = 0; i < PCI_BAR_COUNT; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { if (!zdev->bars[i].size || !zdev->bars[i].res) continue; @@ -573,7 +573,7 @@ int pcibios_add_device(struct pci_dev *pdev) pdev->dev.dma_ops = &s390_pci_dma_ops; zpci_map_resources(pdev); - for (i = 0; i < PCI_BAR_COUNT; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { res = &pdev->resource[i]; if (res->parent || !res->flags) continue; diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c index 9bdff4defef1..8b729b5f2972 100644 --- a/arch/s390/pci/pci_clp.c +++ b/arch/s390/pci/pci_clp.c @@ -145,7 +145,7 @@ static int clp_store_query_pci_fn(struct zpci_dev *zdev, { int i; - for (i = 0; i < PCI_BAR_COUNT; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { zdev->bars[i].val = le32_to_cpu(response->bar[i]); zdev->bars[i].size = response->bar_size[i]; } @@ -164,8 +164,8 @@ static int clp_store_query_pci_fn(struct zpci_dev *zdev, sizeof(zdev->util_str)); } zdev->mio_capable = response->mio_addr_avail; - for (i = 0; i < PCI_BAR_COUNT; i++) { - if (!(response->mio.valid & (1 << (PCI_BAR_COUNT - i - 1)))) + for (i = 0; i < PCI_STD_NUM_BARS; i++) { + if (!(response->mio.valid & (1 << (PCI_STD_NUM_BARS - i - 1)))) continue; zdev->bars[i].mio_wb = (void __iomem *) response->mio.addr[i].wb; diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 9acab6ac28f5..1e59df041456 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -135,7 +135,7 @@ static void pcibios_fixup_device_resources(struct pci_dev *dev) * resource so the kernel doesn't attempt to assign * it later on in pci_assign_unassigned_resources */ - for (bar = 0; bar <= PCI_STD_RESOURCE_END; bar++) { + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) { bar_r = &dev->resource[bar]; if (bar_r->start == 0 && bar_r->end != 0) { bar_r->flags = 0; diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c index 43867bc85368..00c62115f39c 100644 --- a/arch/x86/pci/intel_mid_pci.c +++ b/arch/x86/pci/intel_mid_pci.c @@ -382,7 +382,7 @@ static void pci_fixed_bar_fixup(struct pci_dev *dev) PCI_DEVFN(2, 2) == dev->devfn) return; - for (i = 0; i < PCI_ROM_RESOURCE; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { pci_read_config_dword(dev, offset + 8 + (i * 4), &size); dev->resource[i].end = dev->resource[i].start + size - 1; dev->resource[i].flags |= IORESOURCE_PCI_FIXED; diff --git a/drivers/ata/pata_atp867x.c b/drivers/ata/pata_atp867x.c index cfd0cf2cbca6..e01a3a6e4d46 100644 --- a/drivers/ata/pata_atp867x.c +++ b/drivers/ata/pata_atp867x.c @@ -422,7 +422,7 @@ static int atp867x_ata_pci_sff_init_host(struct ata_host *host) #ifdef ATP867X_DEBUG atp867x_check_res(pdev); - for (i = 0; i < PCI_ROM_RESOURCE; i++) + for (i = 0; i < PCI_STD_NUM_BARS; i++) printk(KERN_DEBUG "ATP867X: iomap[%d]=0x%llx\n", i, (unsigned long long)(host->iomap[i])); #endif diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c index 56946012d113..6f261fbae8c2 100644 --- a/drivers/ata/sata_nv.c +++ b/drivers/ata/sata_nv.c @@ -2325,7 +2325,7 @@ static int nv_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) // Make sure this is a SATA controller by counting the number of bars // (NVIDIA SATA controllers will always have six bars). Otherwise, // it's an IDE controller and we ignore it. - for (bar = 0; bar < 6; bar++) + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) if (pci_resource_start(pdev, bar) == 0) return -ENODEV; diff --git a/drivers/memstick/host/jmb38x_ms.c b/drivers/memstick/host/jmb38x_ms.c index 32747425297d..fd281c1d39b1 100644 --- a/drivers/memstick/host/jmb38x_ms.c +++ b/drivers/memstick/host/jmb38x_ms.c @@ -848,7 +848,7 @@ static int jmb38x_ms_count_slots(struct pci_dev *pdev) { int cnt, rc = 0; - for (cnt = 0; cnt < PCI_ROM_RESOURCE; ++cnt) { + for (cnt = 0; cnt < PCI_STD_NUM_BARS; ++cnt) { if (!(IORESOURCE_MEM & pci_resource_flags(pdev, cnt))) break; diff --git a/drivers/misc/pci_endpoint_test.c b/drivers/misc/pci_endpoint_test.c index 6e208a060a58..a5e317073d95 100644 --- a/drivers/misc/pci_endpoint_test.c +++ b/drivers/misc/pci_endpoint_test.c @@ -94,7 +94,7 @@ enum pci_barno { struct pci_endpoint_test { struct pci_dev *pdev; void __iomem *base; - void __iomem *bar[6]; + void __iomem *bar[PCI_STD_NUM_BARS]; struct completion irq_raised; int last_irq; int num_irqs; @@ -687,7 +687,7 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev, if (!pci_endpoint_test_request_irq(test)) goto err_disable_irq; - for (bar = BAR_0; bar <= BAR_5; bar++) { + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) { if (pci_resource_flags(pdev, bar) & IORESOURCE_MEM) { base = pci_ioremap_bar(pdev, bar); if (!base) { @@ -740,7 +740,7 @@ err_ida_remove: ida_simple_remove(&pci_endpoint_test_ida, id); err_iounmap: - for (bar = BAR_0; bar <= BAR_5; bar++) { + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) { if (test->bar[bar]) pci_iounmap(pdev, test->bar[bar]); } @@ -771,7 +771,7 @@ static void pci_endpoint_test_remove(struct pci_dev *pdev) misc_deregister(&test->miscdev); kfree(misc_device->name); ida_simple_remove(&pci_endpoint_test_ida, id); - for (bar = BAR_0; bar <= BAR_5; bar++) { + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) { if (test->bar[bar]) pci_iounmap(pdev, test->bar[bar]); } diff --git a/drivers/net/ethernet/intel/e1000/e1000.h b/drivers/net/ethernet/intel/e1000/e1000.h index c40729b2c184..7fad2f24dcad 100644 --- a/drivers/net/ethernet/intel/e1000/e1000.h +++ b/drivers/net/ethernet/intel/e1000/e1000.h @@ -45,7 +45,6 @@ #define BAR_0 0 #define BAR_1 1 -#define BAR_5 5 #define INTEL_E1000_ETHERNET_DEVICE(device_id) {\ PCI_DEVICE(PCI_VENDOR_ID_INTEL, device_id)} diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index 86493fea56e4..78db33694494 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -977,7 +977,7 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_ioremap; if (adapter->need_ioport) { - for (i = BAR_1; i <= BAR_5; i++) { + for (i = BAR_1; i < PCI_STD_NUM_BARS; i++) { if (pci_resource_len(pdev, i) == 0) continue; if (pci_resource_flags(pdev, i) & IORESOURCE_IO) { diff --git a/drivers/net/ethernet/intel/ixgb/ixgb.h b/drivers/net/ethernet/intel/ixgb/ixgb.h index e85271b68410..681d44cc9784 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb.h +++ b/drivers/net/ethernet/intel/ixgb/ixgb.h @@ -42,7 +42,6 @@ #define BAR_0 0 #define BAR_1 1 -#define BAR_5 5 struct ixgb_adapter; #include "ixgb_hw.h" diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c index 0940a0da16f2..3d8c051dd327 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_main.c +++ b/drivers/net/ethernet/intel/ixgb/ixgb_main.c @@ -412,7 +412,7 @@ ixgb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_ioremap; } - for (i = BAR_1; i <= BAR_5; i++) { + for (i = BAR_1; i < PCI_STD_NUM_BARS; i++) { if (pci_resource_len(pdev, i) == 0) continue; if (pci_resource_flags(pdev, i) & IORESOURCE_IO) { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c index 292045f4581f..8237dbc3e991 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c @@ -489,7 +489,7 @@ static int stmmac_pci_probe(struct pci_dev *pdev, } /* Get the base address of device */ - for (i = 0; i <= PCI_STD_RESOURCE_END; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { if (pci_resource_len(pdev, i) == 0) continue; ret = pcim_iomap_regions(pdev, BIT(i), pci_name(pdev)); @@ -532,7 +532,7 @@ static void stmmac_pci_remove(struct pci_dev *pdev) if (priv->plat->stmmac_clk) clk_unregister_fixed_rate(priv->plat->stmmac_clk); - for (i = 0; i <= PCI_STD_RESOURCE_END; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { if (pci_resource_len(pdev, i) == 0) continue; pcim_iounmap_regions(pdev, BIT(i)); diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-pci.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-pci.c index 386bafe74c3f..fa8604d7b797 100644 --- a/drivers/net/ethernet/synopsys/dwc-xlgmac-pci.c +++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-pci.c @@ -34,7 +34,7 @@ static int xlgmac_probe(struct pci_dev *pcidev, const struct pci_device_id *id) return ret; } - for (i = 0; i <= PCI_STD_RESOURCE_END; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { if (pci_resource_len(pcidev, i) == 0) continue; ret = pcim_iomap_regions(pcidev, BIT(i), XLGMAC_DRV_NAME); diff --git a/drivers/pci/controller/dwc/pci-dra7xx.c b/drivers/pci/controller/dwc/pci-dra7xx.c index 4234ddb4722f..b20651cea09f 100644 --- a/drivers/pci/controller/dwc/pci-dra7xx.c +++ b/drivers/pci/controller/dwc/pci-dra7xx.c @@ -353,7 +353,7 @@ static void dra7xx_pcie_ep_init(struct dw_pcie_ep *ep) struct dra7xx_pcie *dra7xx = to_dra7xx_pcie(pci); enum pci_barno bar; - for (bar = BAR_0; bar <= BAR_5; bar++) + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) dw_pcie_ep_reset_bar(pci, bar); dra7xx_pcie_enable_wrapper_interrupts(dra7xx); diff --git a/drivers/pci/controller/dwc/pci-layerscape-ep.c b/drivers/pci/controller/dwc/pci-layerscape-ep.c index ca9aa4501e7e..0d151cead1b7 100644 --- a/drivers/pci/controller/dwc/pci-layerscape-ep.c +++ b/drivers/pci/controller/dwc/pci-layerscape-ep.c @@ -58,7 +58,7 @@ static void ls_pcie_ep_init(struct dw_pcie_ep *ep) struct dw_pcie *pci = to_dw_pcie_from_ep(ep); enum pci_barno bar; - for (bar = BAR_0; bar <= BAR_5; bar++) + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) dw_pcie_ep_reset_bar(pci, bar); } diff --git a/drivers/pci/controller/dwc/pcie-artpec6.c b/drivers/pci/controller/dwc/pcie-artpec6.c index d00252bd8fae..9e2482bd7b6d 100644 --- a/drivers/pci/controller/dwc/pcie-artpec6.c +++ b/drivers/pci/controller/dwc/pcie-artpec6.c @@ -422,7 +422,7 @@ static void artpec6_pcie_ep_init(struct dw_pcie_ep *ep) artpec6_pcie_wait_for_phy(artpec6_pcie); artpec6_pcie_set_nfts(artpec6_pcie); - for (bar = BAR_0; bar <= BAR_5; bar++) + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) dw_pcie_ep_reset_bar(pci, bar); } diff --git a/drivers/pci/controller/dwc/pcie-designware-plat.c b/drivers/pci/controller/dwc/pcie-designware-plat.c index b58fdcbc664b..73646b677aff 100644 --- a/drivers/pci/controller/dwc/pcie-designware-plat.c +++ b/drivers/pci/controller/dwc/pcie-designware-plat.c @@ -70,7 +70,7 @@ static void dw_plat_pcie_ep_init(struct dw_pcie_ep *ep) struct dw_pcie *pci = to_dw_pcie_from_ep(ep); enum pci_barno bar; - for (bar = BAR_0; bar <= BAR_5; bar++) + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) dw_pcie_ep_reset_bar(pci, bar); } diff --git a/drivers/pci/controller/dwc/pcie-designware.h b/drivers/pci/controller/dwc/pcie-designware.h index 5a18e94e52c8..5accdd6bc388 100644 --- a/drivers/pci/controller/dwc/pcie-designware.h +++ b/drivers/pci/controller/dwc/pcie-designware.h @@ -214,7 +214,7 @@ struct dw_pcie_ep { phys_addr_t phys_base; size_t addr_size; size_t page_size; - u8 bar_to_atu[6]; + u8 bar_to_atu[PCI_STD_NUM_BARS]; phys_addr_t *outbound_addr; unsigned long *ib_window_map; unsigned long *ob_window_map; diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index f1f300218fab..ad40e848d564 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -307,7 +307,7 @@ struct pci_bus_relations { struct pci_q_res_req_response { struct vmpacket_descriptor hdr; s32 status; /* negative values are failures */ - u32 probed_bar[6]; + u32 probed_bar[PCI_STD_NUM_BARS]; } __packed; struct pci_set_power { @@ -539,7 +539,7 @@ struct hv_pci_dev { * What would be observed if one wrote 0xFFFFFFFF to a BAR and then * read it back, for each of the BAR offsets within config space. */ - u32 probed_bar[6]; + u32 probed_bar[PCI_STD_NUM_BARS]; }; struct hv_pci_compl { @@ -1610,7 +1610,7 @@ static void survey_child_resources(struct hv_pcibus_device *hbus) * so it's sufficient to just add them up without tracking alignment. */ list_for_each_entry(hpdev, &hbus->children, list_entry) { - for (i = 0; i < 6; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { if (hpdev->probed_bar[i] & PCI_BASE_ADDRESS_SPACE_IO) dev_err(&hbus->hdev->device, "There's an I/O BAR in this list!\n"); @@ -1684,7 +1684,7 @@ static void prepopulate_bars(struct hv_pcibus_device *hbus) /* Pick addresses for the BARs. */ do { list_for_each_entry(hpdev, &hbus->children, list_entry) { - for (i = 0; i < 6; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { bar_val = hpdev->probed_bar[i]; if (bar_val == 0) continue; @@ -1841,7 +1841,7 @@ static void q_resource_requirements(void *context, struct pci_response *resp, "query resource requirements failed: %x\n", resp->status); } else { - for (i = 0; i < 6; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { completion->hpdev->probed_bar[i] = q_res_req->probed_bar[i]; } diff --git a/drivers/pci/endpoint/functions/pci-epf-test.c b/drivers/pci/endpoint/functions/pci-epf-test.c index 1cfe3687a211..5d74f81ddfe4 100644 --- a/drivers/pci/endpoint/functions/pci-epf-test.c +++ b/drivers/pci/endpoint/functions/pci-epf-test.c @@ -44,7 +44,7 @@ static struct workqueue_struct *kpcitest_workqueue; struct pci_epf_test { - void *reg[6]; + void *reg[PCI_STD_NUM_BARS]; struct pci_epf *epf; enum pci_barno test_reg_bar; struct delayed_work cmd_handler; @@ -377,7 +377,7 @@ static void pci_epf_test_unbind(struct pci_epf *epf) cancel_delayed_work(&epf_test->cmd_handler); pci_epc_stop(epc); - for (bar = BAR_0; bar <= BAR_5; bar++) { + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) { epf_bar = &epf->bar[bar]; if (epf_test->reg[bar]) { @@ -400,7 +400,7 @@ static int pci_epf_test_set_bar(struct pci_epf *epf) epc_features = epf_test->epc_features; - for (bar = BAR_0; bar <= BAR_5; bar += add) { + for (bar = 0; bar < PCI_STD_NUM_BARS; bar += add) { epf_bar = &epf->bar[bar]; /* * pci_epc_set_bar() sets PCI_BASE_ADDRESS_MEM_TYPE_64 @@ -450,7 +450,7 @@ static int pci_epf_test_alloc_space(struct pci_epf *epf) } epf_test->reg[test_reg_bar] = base; - for (bar = BAR_0; bar <= BAR_5; bar += add) { + for (bar = 0; bar < PCI_STD_NUM_BARS; bar += add) { epf_bar = &epf->bar[bar]; add = (epf_bar->flags & PCI_BASE_ADDRESS_MEM_TYPE_64) ? 2 : 1; @@ -478,7 +478,7 @@ static void pci_epf_configure_bar(struct pci_epf *epf, bool bar_fixed_64bit; int i; - for (i = BAR_0; i <= BAR_5; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { epf_bar = &epf->bar[i]; bar_fixed_64bit = !!(epc_features->bar_fixed_64bit & (1 << i)); if (bar_fixed_64bit) diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index 793412954529..07bd84c50238 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -1122,7 +1122,7 @@ static void pci_remove_resource_files(struct pci_dev *pdev) { int i; - for (i = 0; i < PCI_ROM_RESOURCE; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { struct bin_attribute *res_attr; res_attr = pdev->res_attr[i]; @@ -1193,7 +1193,7 @@ static int pci_create_resource_files(struct pci_dev *pdev) int retval; /* Expose the PCI resources from this device as files */ - for (i = 0; i < PCI_ROM_RESOURCE; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { /* skip empty resources */ if (!pci_resource_len(pdev, i)) diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index e7982af9a5d8..184765f12848 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -674,7 +674,7 @@ struct resource *pci_find_resource(struct pci_dev *dev, struct resource *res) { int i; - for (i = 0; i < PCI_ROM_RESOURCE; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { struct resource *r = &dev->resource[i]; if (r->start && resource_contains(r, res)) @@ -3768,7 +3768,7 @@ void pci_release_selected_regions(struct pci_dev *pdev, int bars) { int i; - for (i = 0; i < 6; i++) + for (i = 0; i < PCI_STD_NUM_BARS; i++) if (bars & (1 << i)) pci_release_region(pdev, i); } @@ -3779,7 +3779,7 @@ static int __pci_request_selected_regions(struct pci_dev *pdev, int bars, { int i; - for (i = 0; i < 6; i++) + for (i = 0; i < PCI_STD_NUM_BARS; i++) if (bars & (1 << i)) if (__pci_request_region(pdev, i, res_name, excl)) goto err_out; @@ -3827,7 +3827,7 @@ EXPORT_SYMBOL(pci_request_selected_regions_exclusive); void pci_release_regions(struct pci_dev *pdev) { - pci_release_selected_regions(pdev, (1 << 6) - 1); + pci_release_selected_regions(pdev, (1 << PCI_STD_NUM_BARS) - 1); } EXPORT_SYMBOL(pci_release_regions); @@ -3846,7 +3846,8 @@ EXPORT_SYMBOL(pci_release_regions); */ int pci_request_regions(struct pci_dev *pdev, const char *res_name) { - return pci_request_selected_regions(pdev, ((1 << 6) - 1), res_name); + return pci_request_selected_regions(pdev, + ((1 << PCI_STD_NUM_BARS) - 1), res_name); } EXPORT_SYMBOL(pci_request_regions); @@ -3868,7 +3869,7 @@ EXPORT_SYMBOL(pci_request_regions); int pci_request_regions_exclusive(struct pci_dev *pdev, const char *res_name) { return pci_request_selected_regions_exclusive(pdev, - ((1 << 6) - 1), res_name); + ((1 << PCI_STD_NUM_BARS) - 1), res_name); } EXPORT_SYMBOL(pci_request_regions_exclusive); diff --git a/drivers/pci/proc.c b/drivers/pci/proc.c index 5495537c60c2..6ef74bf5013f 100644 --- a/drivers/pci/proc.c +++ b/drivers/pci/proc.c @@ -258,13 +258,13 @@ static int proc_bus_pci_mmap(struct file *file, struct vm_area_struct *vma) } /* Make sure the caller is mapping a real resource for this device */ - for (i = 0; i < PCI_ROM_RESOURCE; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { if (dev->resource[i].flags & res_bit && pci_mmap_fits(dev, i, vma, PCI_MMAP_PROCFS)) break; } - if (i >= PCI_ROM_RESOURCE) + if (i >= PCI_STD_NUM_BARS) return -ENODEV; if (fpriv->mmap_state == pci_mmap_mem && diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 320255e5e8f8..5d5e6f2f7837 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -474,7 +474,7 @@ static void quirk_extend_bar_to_page(struct pci_dev *dev) { int i; - for (i = 0; i <= PCI_STD_RESOURCE_END; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { struct resource *r = &dev->resource[i]; if (r->flags & IORESOURCE_MEM && resource_size(r) < PAGE_SIZE) { @@ -1809,7 +1809,7 @@ static void quirk_alder_ioapic(struct pci_dev *pdev) * The next five BARs all seem to be rubbish, so just clean * them out. */ - for (i = 1; i < 6; i++) + for (i = 1; i < PCI_STD_NUM_BARS; i++) memset(&pdev->resource[i], 0, sizeof(pdev->resource[i])); } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_EESSC, quirk_alder_ioapic); diff --git a/drivers/rapidio/devices/tsi721.c b/drivers/rapidio/devices/tsi721.c index 125a173bed45..4dd31dd9feea 100644 --- a/drivers/rapidio/devices/tsi721.c +++ b/drivers/rapidio/devices/tsi721.c @@ -2755,7 +2755,7 @@ static int tsi721_probe(struct pci_dev *pdev, { int i; - for (i = 0; i <= PCI_STD_RESOURCE_END; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { tsi_debug(INIT, &pdev->dev, "res%d %pR", i, &pdev->resource[i]); } diff --git a/drivers/scsi/pm8001/pm8001_hwi.c b/drivers/scsi/pm8001/pm8001_hwi.c index 68a8217032d0..1a3661d6be06 100644 --- a/drivers/scsi/pm8001/pm8001_hwi.c +++ b/drivers/scsi/pm8001/pm8001_hwi.c @@ -1186,7 +1186,7 @@ static void pm8001_hw_chip_rst(struct pm8001_hba_info *pm8001_ha) void pm8001_chip_iounmap(struct pm8001_hba_info *pm8001_ha) { s8 bar, logical = 0; - for (bar = 0; bar < 6; bar++) { + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) { /* ** logical BARs for SPC: ** bar 0 and 1 - logical BAR0 diff --git a/drivers/scsi/pm8001/pm8001_init.c b/drivers/scsi/pm8001/pm8001_init.c index 3374f553c617..aca913490eb5 100644 --- a/drivers/scsi/pm8001/pm8001_init.c +++ b/drivers/scsi/pm8001/pm8001_init.c @@ -401,7 +401,7 @@ static int pm8001_ioremap(struct pm8001_hba_info *pm8001_ha) pdev = pm8001_ha->pdev; /* map pci mem (PMC pci base 0-3)*/ - for (bar = 0; bar < 6; bar++) { + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) { /* ** logical BARs for SPC: ** bar 0 and 1 - logical BAR0 diff --git a/drivers/staging/gasket/gasket_constants.h b/drivers/staging/gasket/gasket_constants.h index 50d87c7b178c..9ea9c8833f27 100644 --- a/drivers/staging/gasket/gasket_constants.h +++ b/drivers/staging/gasket/gasket_constants.h @@ -13,9 +13,6 @@ /* The maximum devices per each type. */ #define GASKET_DEV_MAX 256 -/* The number of supported (and possible) PCI BARs. */ -#define GASKET_NUM_BARS 6 - /* The number of supported Gasket page tables per device. */ #define GASKET_MAX_NUM_PAGE_TABLES 1 diff --git a/drivers/staging/gasket/gasket_core.c b/drivers/staging/gasket/gasket_core.c index 13179f063a61..cd8be80d2076 100644 --- a/drivers/staging/gasket/gasket_core.c +++ b/drivers/staging/gasket/gasket_core.c @@ -371,7 +371,7 @@ static int gasket_setup_pci(struct pci_dev *pci_dev, { int i, mapped_bars, ret; - for (i = 0; i < GASKET_NUM_BARS; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { ret = gasket_map_pci_bar(gasket_dev, i); if (ret) { mapped_bars = i; @@ -393,7 +393,7 @@ static void gasket_cleanup_pci(struct gasket_dev *gasket_dev) { int i; - for (i = 0; i < GASKET_NUM_BARS; i++) + for (i = 0; i < PCI_STD_NUM_BARS; i++) gasket_unmap_pci_bar(gasket_dev, i); } @@ -493,7 +493,7 @@ static ssize_t gasket_sysfs_data_show(struct device *device, (enum gasket_sysfs_attribute_type)gasket_attr->data.attr_type; switch (sysfs_type) { case ATTR_BAR_OFFSETS: - for (i = 0; i < GASKET_NUM_BARS; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { bar_desc = &driver_desc->bar_descriptions[i]; if (bar_desc->size == 0) continue; @@ -505,7 +505,7 @@ static ssize_t gasket_sysfs_data_show(struct device *device, } break; case ATTR_BAR_SIZES: - for (i = 0; i < GASKET_NUM_BARS; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { bar_desc = &driver_desc->bar_descriptions[i]; if (bar_desc->size == 0) continue; @@ -556,7 +556,7 @@ static ssize_t gasket_sysfs_data_show(struct device *device, ret = snprintf(buf, PAGE_SIZE, "%d\n", gasket_dev->reset_count); break; case ATTR_USER_MEM_RANGES: - for (i = 0; i < GASKET_NUM_BARS; ++i) { + for (i = 0; i < PCI_STD_NUM_BARS; ++i) { current_written = gasket_write_mappable_regions(buf, driver_desc, i); @@ -736,7 +736,7 @@ static int gasket_get_bar_index(const struct gasket_dev *gasket_dev, const struct gasket_driver_desc *driver_desc; driver_desc = gasket_dev->internal_desc->driver_desc; - for (i = 0; i < GASKET_NUM_BARS; ++i) { + for (i = 0; i < PCI_STD_NUM_BARS; ++i) { struct gasket_bar_desc bar_desc = driver_desc->bar_descriptions[i]; diff --git a/drivers/staging/gasket/gasket_core.h b/drivers/staging/gasket/gasket_core.h index be44ac1e3118..c417acadb0d5 100644 --- a/drivers/staging/gasket/gasket_core.h +++ b/drivers/staging/gasket/gasket_core.h @@ -268,7 +268,7 @@ struct gasket_dev { char kobj_name[GASKET_NAME_MAX]; /* Virtual address of mapped BAR memory range. */ - struct gasket_bar_data bar_data[GASKET_NUM_BARS]; + struct gasket_bar_data bar_data[PCI_STD_NUM_BARS]; /* Coherent buffer. */ struct gasket_coherent_buffer coherent_buffer; @@ -369,7 +369,7 @@ struct gasket_driver_desc { /* Set of 6 bar descriptions that describe all PCIe bars. * Note that BUS/AXI devices (i.e. non PCI devices) use those. */ - struct gasket_bar_desc bar_descriptions[GASKET_NUM_BARS]; + struct gasket_bar_desc bar_descriptions[PCI_STD_NUM_BARS]; /* * Coherent buffer description. diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index 6adbadd6a56a..0b8784cd6d71 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -48,8 +48,6 @@ struct f815xxa_data { int idx; }; -#define PCI_NUM_BAR_RESOURCES 6 - struct serial_private { struct pci_dev *dev; unsigned int nr; @@ -89,7 +87,7 @@ setup_port(struct serial_private *priv, struct uart_8250_port *port, { struct pci_dev *dev = priv->dev; - if (bar >= PCI_NUM_BAR_RESOURCES) + if (bar >= PCI_STD_NUM_BARS) return -EINVAL; if (pci_resource_flags(dev, bar) & IORESOURCE_MEM) { @@ -4060,7 +4058,7 @@ serial_pci_guess_board(struct pci_dev *dev, struct pciserial_board *board) return -ENODEV; num_iomem = num_port = 0; - for (i = 0; i < PCI_NUM_BAR_RESOURCES; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { if (pci_resource_flags(dev, i) & IORESOURCE_IO) { num_port++; if (first_port == -1) @@ -4088,7 +4086,7 @@ serial_pci_guess_board(struct pci_dev *dev, struct pciserial_board *board) */ first_port = -1; num_port = 0; - for (i = 0; i < PCI_NUM_BAR_RESOURCES; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { if (pci_resource_flags(dev, i) & IORESOURCE_IO && pci_resource_len(dev, i) == 8 && (first_port == -1 || (first_port + num_port) == i)) { diff --git a/drivers/usb/core/hcd-pci.c b/drivers/usb/core/hcd-pci.c index 9e26b0143a59..9ae2a7a93df2 100644 --- a/drivers/usb/core/hcd-pci.c +++ b/drivers/usb/core/hcd-pci.c @@ -234,7 +234,7 @@ int usb_hcd_pci_probe(struct pci_dev *dev, const struct pci_device_id *id) /* UHCI */ int region; - for (region = 0; region < PCI_ROM_RESOURCE; region++) { + for (region = 0; region < PCI_STD_NUM_BARS; region++) { if (!(pci_resource_flags(dev, region) & IORESOURCE_IO)) continue; diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c index f6d04491df60..6c7f0a876b96 100644 --- a/drivers/usb/host/pci-quirks.c +++ b/drivers/usb/host/pci-quirks.c @@ -728,7 +728,7 @@ static void quirk_usb_handoff_uhci(struct pci_dev *pdev) if (!pio_enabled(pdev)) return; - for (i = 0; i < PCI_ROM_RESOURCE; i++) + for (i = 0; i < PCI_STD_NUM_BARS; i++) if ((pci_resource_flags(pdev, i) & IORESOURCE_IO)) { base = pci_resource_start(pdev, i); break; diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 02206162eaa9..379a02c36e37 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -110,13 +110,15 @@ static inline bool vfio_pci_is_vga(struct pci_dev *pdev) static void vfio_pci_probe_mmaps(struct vfio_pci_device *vdev) { struct resource *res; - int bar; + int i; struct vfio_pci_dummy_resource *dummy_res; INIT_LIST_HEAD(&vdev->dummy_resources_list); - for (bar = PCI_STD_RESOURCES; bar <= PCI_STD_RESOURCE_END; bar++) { - res = vdev->pdev->resource + bar; + for (i = 0; i < PCI_STD_NUM_BARS; i++) { + int bar = i + PCI_STD_RESOURCES; + + res = &vdev->pdev->resource[bar]; if (!IS_ENABLED(CONFIG_VFIO_PCI_MMAP)) goto no_mmap; @@ -399,7 +401,8 @@ static void vfio_pci_disable(struct vfio_pci_device *vdev) vfio_config_free(vdev); - for (bar = PCI_STD_RESOURCES; bar <= PCI_STD_RESOURCE_END; bar++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { + bar = i + PCI_STD_RESOURCES; if (!vdev->barmap[bar]) continue; pci_iounmap(pdev, vdev->barmap[bar]); diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c index f0891bd8444c..90c0b80f8acf 100644 --- a/drivers/vfio/pci/vfio_pci_config.c +++ b/drivers/vfio/pci/vfio_pci_config.c @@ -450,30 +450,32 @@ static void vfio_bar_fixup(struct vfio_pci_device *vdev) { struct pci_dev *pdev = vdev->pdev; int i; - __le32 *bar; + __le32 *vbar; u64 mask; - bar = (__le32 *)&vdev->vconfig[PCI_BASE_ADDRESS_0]; + vbar = (__le32 *)&vdev->vconfig[PCI_BASE_ADDRESS_0]; - for (i = PCI_STD_RESOURCES; i <= PCI_STD_RESOURCE_END; i++, bar++) { - if (!pci_resource_start(pdev, i)) { - *bar = 0; /* Unmapped by host = unimplemented to user */ + for (i = 0; i < PCI_STD_NUM_BARS; i++, vbar++) { + int bar = i + PCI_STD_RESOURCES; + + if (!pci_resource_start(pdev, bar)) { + *vbar = 0; /* Unmapped by host = unimplemented to user */ continue; } - mask = ~(pci_resource_len(pdev, i) - 1); + mask = ~(pci_resource_len(pdev, bar) - 1); - *bar &= cpu_to_le32((u32)mask); - *bar |= vfio_generate_bar_flags(pdev, i); + *vbar &= cpu_to_le32((u32)mask); + *vbar |= vfio_generate_bar_flags(pdev, bar); - if (*bar & cpu_to_le32(PCI_BASE_ADDRESS_MEM_TYPE_64)) { - bar++; - *bar &= cpu_to_le32((u32)(mask >> 32)); + if (*vbar & cpu_to_le32(PCI_BASE_ADDRESS_MEM_TYPE_64)) { + vbar++; + *vbar &= cpu_to_le32((u32)(mask >> 32)); i++; } } - bar = (__le32 *)&vdev->vconfig[PCI_ROM_ADDRESS]; + vbar = (__le32 *)&vdev->vconfig[PCI_ROM_ADDRESS]; /* * NB. REGION_INFO will have reported zero size if we weren't able @@ -483,14 +485,14 @@ static void vfio_bar_fixup(struct vfio_pci_device *vdev) if (pci_resource_start(pdev, PCI_ROM_RESOURCE)) { mask = ~(pci_resource_len(pdev, PCI_ROM_RESOURCE) - 1); mask |= PCI_ROM_ADDRESS_ENABLE; - *bar &= cpu_to_le32((u32)mask); + *vbar &= cpu_to_le32((u32)mask); } else if (pdev->resource[PCI_ROM_RESOURCE].flags & IORESOURCE_ROM_SHADOW) { mask = ~(0x20000 - 1); mask |= PCI_ROM_ADDRESS_ENABLE; - *bar &= cpu_to_le32((u32)mask); + *vbar &= cpu_to_le32((u32)mask); } else - *bar = 0; + *vbar = 0; vdev->bardirty = false; } diff --git a/drivers/vfio/pci/vfio_pci_private.h b/drivers/vfio/pci/vfio_pci_private.h index ee6ee91718a4..8a2c7607d513 100644 --- a/drivers/vfio/pci/vfio_pci_private.h +++ b/drivers/vfio/pci/vfio_pci_private.h @@ -86,8 +86,8 @@ struct vfio_pci_reflck { struct vfio_pci_device { struct pci_dev *pdev; - void __iomem *barmap[PCI_STD_RESOURCE_END + 1]; - bool bar_mmap_supported[PCI_STD_RESOURCE_END + 1]; + void __iomem *barmap[PCI_STD_NUM_BARS]; + bool bar_mmap_supported[PCI_STD_NUM_BARS]; u8 *pci_config_map; u8 *vconfig; struct perm_bits *msi_perm; diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c index e6a1c805064f..19af5626a317 100644 --- a/drivers/video/fbdev/core/fbmem.c +++ b/drivers/video/fbdev/core/fbmem.c @@ -1774,7 +1774,7 @@ int remove_conflicting_pci_framebuffers(struct pci_dev *pdev, int res_id, const int err, idx, bar; bool res_id_found = false; - for (idx = 0, bar = 0; bar < PCI_ROM_RESOURCE; bar++) { + for (idx = 0, bar = 0; bar < PCI_STD_NUM_BARS; bar++) { if (!(pci_resource_flags(pdev, bar) & IORESOURCE_MEM)) continue; idx++; @@ -1784,7 +1784,7 @@ int remove_conflicting_pci_framebuffers(struct pci_dev *pdev, int res_id, const if (!ap) return -ENOMEM; - for (idx = 0, bar = 0; bar < PCI_ROM_RESOURCE; bar++) { + for (idx = 0, bar = 0; bar < PCI_STD_NUM_BARS; bar++) { if (!(pci_resource_flags(pdev, bar) & IORESOURCE_MEM)) continue; ap->ranges[idx].base = pci_resource_start(pdev, bar); diff --git a/drivers/video/fbdev/efifb.c b/drivers/video/fbdev/efifb.c index 51d97ec4f58f..1caa3726cb45 100644 --- a/drivers/video/fbdev/efifb.c +++ b/drivers/video/fbdev/efifb.c @@ -653,7 +653,7 @@ static void efifb_fixup_resources(struct pci_dev *dev) if (!base) return; - for (i = 0; i <= PCI_STD_RESOURCE_END; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { struct resource *res = &dev->resource[i]; if (!(res->flags & IORESOURCE_MEM)) diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h index f641badc2c61..56f1846b9d39 100644 --- a/include/linux/pci-epc.h +++ b/include/linux/pci-epc.h @@ -117,7 +117,7 @@ struct pci_epc_features { unsigned int msix_capable : 1; u8 reserved_bar; u8 bar_fixed_64bit; - u64 bar_fixed_size[BAR_5 + 1]; + u64 bar_fixed_size[PCI_STD_NUM_BARS]; size_t align; }; diff --git a/include/linux/pci.h b/include/linux/pci.h index f9088c89a534..4cc739616148 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -82,7 +82,7 @@ enum pci_mmap_state { enum { /* #0-5: standard PCI resources */ PCI_STD_RESOURCES, - PCI_STD_RESOURCE_END = 5, + PCI_STD_RESOURCE_END = PCI_STD_RESOURCES + PCI_STD_NUM_BARS - 1, /* #6: expansion ROM resource */ PCI_ROM_RESOURCE, diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index 29d6e93fd15e..43cf74eba29d 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -34,6 +34,7 @@ * of which the first 64 bytes are standardized as follows: */ #define PCI_STD_HEADER_SIZEOF 64 +#define PCI_STD_NUM_BARS 6 /* Number of standard BARs */ #define PCI_VENDOR_ID 0x00 /* 16 bits */ #define PCI_DEVICE_ID 0x02 /* 16 bits */ #define PCI_COMMAND 0x04 /* 16 bits */ diff --git a/lib/devres.c b/lib/devres.c index 6a0e9bd6524a..ab75d73122b8 100644 --- a/lib/devres.c +++ b/lib/devres.c @@ -262,7 +262,7 @@ EXPORT_SYMBOL(devm_ioport_unmap); /* * PCI iomap devres */ -#define PCIM_IOMAP_MAX PCI_ROM_RESOURCE +#define PCIM_IOMAP_MAX PCI_STD_NUM_BARS struct pcim_iomap_devres { void __iomem *table[PCIM_IOMAP_MAX]; -- cgit v1.2.3 From 9e420d7f125f51ab1eda37497b08c4fad9efe4a8 Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Fri, 11 Oct 2019 17:05:43 +0200 Subject: rts: ds1685: remove not needed fields from private struct A few of the fields in struct ds1685_priv aren't needed at all, so we can remove it. Signed-off-by: Thomas Bogendoerfer Acked-by: Joshua Kinard Link: https://lore.kernel.org/r/20191011150546.9186-1-tbogendoerfer@suse.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-ds1685.c | 3 --- include/linux/rtc/ds1685.h | 3 --- 2 files changed, 6 deletions(-) (limited to 'include') diff --git a/drivers/rtc/rtc-ds1685.c b/drivers/rtc/rtc-ds1685.c index 184e4a3e2bef..51f568473de8 100644 --- a/drivers/rtc/rtc-ds1685.c +++ b/drivers/rtc/rtc-ds1685.c @@ -1086,12 +1086,10 @@ ds1685_rtc_probe(struct platform_device *pdev) * Set the base address for the rtc, and ioremap its * registers. */ - rtc->baseaddr = res->start; rtc->regs = devm_ioremap(&pdev->dev, res->start, rtc->size); if (!rtc->regs) return -ENOMEM; } - rtc->alloc_io_resources = pdata->alloc_io_resources; /* Get the register step size. */ if (pdata->regstep > 0) @@ -1271,7 +1269,6 @@ ds1685_rtc_probe(struct platform_device *pdev) /* See if the platform doesn't support UIE. */ if (pdata->uie_unsupported) rtc_dev->uie_unsupported = 1; - rtc->uie_unsupported = pdata->uie_unsupported; rtc->dev = rtc_dev; diff --git a/include/linux/rtc/ds1685.h b/include/linux/rtc/ds1685.h index 43aec568ba7c..b9671d00d964 100644 --- a/include/linux/rtc/ds1685.h +++ b/include/linux/rtc/ds1685.h @@ -43,13 +43,10 @@ struct ds1685_priv { struct rtc_device *dev; void __iomem *regs; u32 regstep; - resource_size_t baseaddr; size_t size; int irq_num; bool bcd_mode; bool no_irq; - bool uie_unsupported; - bool alloc_io_resources; u8 (*read)(struct ds1685_priv *, int); void (*write)(struct ds1685_priv *, int, u8); void (*prepare_poweroff)(void); -- cgit v1.2.3 From af818031f4637b0e8d106fcc9023f1c22c44e13a Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Fri, 11 Oct 2019 17:05:44 +0200 Subject: rtc: ds1685: use devm_platform_ioremap_resource helper Simplify ioremapping of registers by using devm_platform_ioremap_resource. Signed-off-by: Thomas Bogendoerfer Acked-by: Joshua Kinard Link: https://lore.kernel.org/r/20191011150546.9186-2-tbogendoerfer@suse.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-ds1685.c | 23 +++-------------------- include/linux/rtc/ds1685.h | 1 - 2 files changed, 3 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/drivers/rtc/rtc-ds1685.c b/drivers/rtc/rtc-ds1685.c index 51f568473de8..349a8d1caca1 100644 --- a/drivers/rtc/rtc-ds1685.c +++ b/drivers/rtc/rtc-ds1685.c @@ -1040,7 +1040,6 @@ static int ds1685_rtc_probe(struct platform_device *pdev) { struct rtc_device *rtc_dev; - struct resource *res; struct ds1685_priv *rtc; struct ds1685_rtc_platform_data *pdata; u8 ctrla, ctrlb, hours; @@ -1070,25 +1069,9 @@ ds1685_rtc_probe(struct platform_device *pdev) * that sits behind the IOC3 PCI metadevice. */ if (pdata->alloc_io_resources) { - /* Get the platform resources. */ - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!res) - return -ENXIO; - rtc->size = resource_size(res); - - /* Request a memory region. */ - /* XXX: mmio-only for now. */ - if (!devm_request_mem_region(&pdev->dev, res->start, rtc->size, - pdev->name)) - return -EBUSY; - - /* - * Set the base address for the rtc, and ioremap its - * registers. - */ - rtc->regs = devm_ioremap(&pdev->dev, res->start, rtc->size); - if (!rtc->regs) - return -ENOMEM; + rtc->regs = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(rtc->regs)) + return PTR_ERR(rtc->regs); } /* Get the register step size. */ diff --git a/include/linux/rtc/ds1685.h b/include/linux/rtc/ds1685.h index b9671d00d964..101c7adc05a2 100644 --- a/include/linux/rtc/ds1685.h +++ b/include/linux/rtc/ds1685.h @@ -43,7 +43,6 @@ struct ds1685_priv { struct rtc_device *dev; void __iomem *regs; u32 regstep; - size_t size; int irq_num; bool bcd_mode; bool no_irq; -- cgit v1.2.3 From 781ca2de89bae1b1d2c96df9ef33e9a324415995 Mon Sep 17 00:00:00 2001 From: Tom Murphy Date: Sun, 8 Sep 2019 09:56:38 -0700 Subject: iommu: Add gfp parameter to iommu_ops::map Add a gfp_t parameter to the iommu_ops::map function. Remove the needless locking in the AMD iommu driver. The iommu_ops::map function (or the iommu_map function which calls it) was always supposed to be sleepable (according to Joerg's comment in this thread: https://lore.kernel.org/patchwork/patch/977520/ ) and so should probably have had a "might_sleep()" since it was written. However currently the dma-iommu api can call iommu_map in an atomic context, which it shouldn't do. This doesn't cause any problems because any iommu driver which uses the dma-iommu api uses gfp_atomic in it's iommu_ops::map function. But doing this wastes the memory allocators atomic pools. Signed-off-by: Tom Murphy Reviewed-by: Robin Murphy Reviewed-by: Christoph Hellwig Signed-off-by: Joerg Roedel --- drivers/iommu/amd_iommu.c | 3 ++- drivers/iommu/arm-smmu-v3.c | 2 +- drivers/iommu/arm-smmu.c | 2 +- drivers/iommu/dma-iommu.c | 6 +++--- drivers/iommu/exynos-iommu.c | 2 +- drivers/iommu/intel-iommu.c | 2 +- drivers/iommu/iommu.c | 43 ++++++++++++++++++++++++++++++++++++------ drivers/iommu/ipmmu-vmsa.c | 2 +- drivers/iommu/msm_iommu.c | 2 +- drivers/iommu/mtk_iommu.c | 2 +- drivers/iommu/mtk_iommu_v1.c | 2 +- drivers/iommu/omap-iommu.c | 2 +- drivers/iommu/qcom_iommu.c | 2 +- drivers/iommu/rockchip-iommu.c | 2 +- drivers/iommu/s390-iommu.c | 2 +- drivers/iommu/tegra-gart.c | 2 +- drivers/iommu/tegra-smmu.c | 2 +- drivers/iommu/virtio-iommu.c | 2 +- include/linux/iommu.h | 21 ++++++++++++++++++++- 19 files changed, 77 insertions(+), 26 deletions(-) (limited to 'include') diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 97ca4ed4ce0c..1444757f0ff9 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -3106,7 +3106,8 @@ static int amd_iommu_attach_device(struct iommu_domain *dom, } static int amd_iommu_map(struct iommu_domain *dom, unsigned long iova, - phys_addr_t paddr, size_t page_size, int iommu_prot) + phys_addr_t paddr, size_t page_size, int iommu_prot, + gfp_t gfp) { struct protection_domain *domain = to_pdomain(dom); int prot = 0; diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index 8da93e730d6f..f1bdaaa8c5de 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -2448,7 +2448,7 @@ out_unlock: } static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { struct io_pgtable_ops *ops = to_smmu_domain(domain)->pgtbl_ops; diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index b18aac4c105e..e85bc0e8d564 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -1159,7 +1159,7 @@ rpm_put: } static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { struct io_pgtable_ops *ops = to_smmu_domain(domain)->pgtbl_ops; struct arm_smmu_device *smmu = to_smmu_domain(domain)->smmu; diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index f321279baf9e..cc3bf5cf0a90 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -476,7 +476,7 @@ static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys, if (!iova) return DMA_MAPPING_ERROR; - if (iommu_map(domain, iova, phys - iova_off, size, prot)) { + if (iommu_map_atomic(domain, iova, phys - iova_off, size, prot)) { iommu_dma_free_iova(cookie, iova, size); return DMA_MAPPING_ERROR; } @@ -611,7 +611,7 @@ static void *iommu_dma_alloc_remap(struct device *dev, size_t size, arch_dma_prep_coherent(sg_page(sg), sg->length); } - if (iommu_map_sg(domain, iova, sgt.sgl, sgt.orig_nents, ioprot) + if (iommu_map_sg_atomic(domain, iova, sgt.sgl, sgt.orig_nents, ioprot) < size) goto out_free_sg; @@ -871,7 +871,7 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg, * We'll leave any physical concatenation to the IOMMU driver's * implementation - it knows better than we do. */ - if (iommu_map_sg(domain, iova, sg, nents, prot) < iova_len) + if (iommu_map_sg_atomic(domain, iova, sg, nents, prot) < iova_len) goto out_free_iova; return __finalise_sg(dev, sg, nents, iova); diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c index 9c94e16fb127..186ff5cc975c 100644 --- a/drivers/iommu/exynos-iommu.c +++ b/drivers/iommu/exynos-iommu.c @@ -1073,7 +1073,7 @@ static int lv2set_page(sysmmu_pte_t *pent, phys_addr_t paddr, size_t size, */ static int exynos_iommu_map(struct iommu_domain *iommu_domain, unsigned long l_iova, phys_addr_t paddr, size_t size, - int prot) + int prot, gfp_t gfp) { struct exynos_iommu_domain *domain = to_exynos_domain(iommu_domain); sysmmu_pte_t *entry; diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 3f974919d3bd..615495aa613e 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -5432,7 +5432,7 @@ static void intel_iommu_aux_detach_device(struct iommu_domain *domain, static int intel_iommu_map(struct iommu_domain *domain, unsigned long iova, phys_addr_t hpa, - size_t size, int iommu_prot) + size_t size, int iommu_prot, gfp_t gfp) { struct dmar_domain *dmar_domain = to_dmar_domain(domain); u64 max_addr; diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index d658c7c6a2ab..f8853dbf1c4e 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -1854,8 +1854,8 @@ static size_t iommu_pgsize(struct iommu_domain *domain, return pgsize; } -int iommu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) +int __iommu_map(struct iommu_domain *domain, unsigned long iova, + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { const struct iommu_ops *ops = domain->ops; unsigned long orig_iova = iova; @@ -1892,8 +1892,8 @@ int iommu_map(struct iommu_domain *domain, unsigned long iova, pr_debug("mapping: iova 0x%lx pa %pa pgsize 0x%zx\n", iova, &paddr, pgsize); + ret = ops->map(domain, iova, paddr, pgsize, prot, gfp); - ret = ops->map(domain, iova, paddr, pgsize, prot); if (ret) break; @@ -1913,8 +1913,22 @@ int iommu_map(struct iommu_domain *domain, unsigned long iova, return ret; } + +int iommu_map(struct iommu_domain *domain, unsigned long iova, + phys_addr_t paddr, size_t size, int prot) +{ + might_sleep(); + return __iommu_map(domain, iova, paddr, size, prot, GFP_KERNEL); +} EXPORT_SYMBOL_GPL(iommu_map); +int iommu_map_atomic(struct iommu_domain *domain, unsigned long iova, + phys_addr_t paddr, size_t size, int prot) +{ + return __iommu_map(domain, iova, paddr, size, prot, GFP_ATOMIC); +} +EXPORT_SYMBOL_GPL(iommu_map_atomic); + static size_t __iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size, struct iommu_iotlb_gather *iotlb_gather) @@ -1991,8 +2005,9 @@ size_t iommu_unmap_fast(struct iommu_domain *domain, } EXPORT_SYMBOL_GPL(iommu_unmap_fast); -size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova, - struct scatterlist *sg, unsigned int nents, int prot) +size_t __iommu_map_sg(struct iommu_domain *domain, unsigned long iova, + struct scatterlist *sg, unsigned int nents, int prot, + gfp_t gfp) { size_t len = 0, mapped = 0; phys_addr_t start; @@ -2003,7 +2018,9 @@ size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova, phys_addr_t s_phys = sg_phys(sg); if (len && s_phys != start + len) { - ret = iommu_map(domain, iova + mapped, start, len, prot); + ret = __iommu_map(domain, iova + mapped, start, + len, prot, gfp); + if (ret) goto out_err; @@ -2031,8 +2048,22 @@ out_err: return 0; } + +size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova, + struct scatterlist *sg, unsigned int nents, int prot) +{ + might_sleep(); + return __iommu_map_sg(domain, iova, sg, nents, prot, GFP_KERNEL); +} EXPORT_SYMBOL_GPL(iommu_map_sg); +size_t iommu_map_sg_atomic(struct iommu_domain *domain, unsigned long iova, + struct scatterlist *sg, unsigned int nents, int prot) +{ + return __iommu_map_sg(domain, iova, sg, nents, prot, GFP_ATOMIC); +} +EXPORT_SYMBOL_GPL(iommu_map_sg_atomic); + int iommu_domain_window_enable(struct iommu_domain *domain, u32 wnd_nr, phys_addr_t paddr, u64 size, int prot) { diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c index 9da8309f7170..35f3edaba0e2 100644 --- a/drivers/iommu/ipmmu-vmsa.c +++ b/drivers/iommu/ipmmu-vmsa.c @@ -724,7 +724,7 @@ static void ipmmu_detach_device(struct iommu_domain *io_domain, } static int ipmmu_map(struct iommu_domain *io_domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain); diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c index be99d408cf35..93f14bca26ee 100644 --- a/drivers/iommu/msm_iommu.c +++ b/drivers/iommu/msm_iommu.c @@ -504,7 +504,7 @@ fail: } static int msm_iommu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t pa, size_t len, int prot) + phys_addr_t pa, size_t len, int prot, gfp_t gfp) { struct msm_priv *priv = to_msm_priv(domain); unsigned long flags; diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index 67a483c1a935..556beaa110b3 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -412,7 +412,7 @@ static void mtk_iommu_detach_device(struct iommu_domain *domain, } static int mtk_iommu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { struct mtk_iommu_domain *dom = to_mtk_domain(domain); struct mtk_iommu_data *data = mtk_iommu_get_m4u_data(); diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c index b5efd6dac953..e93b94ecac45 100644 --- a/drivers/iommu/mtk_iommu_v1.c +++ b/drivers/iommu/mtk_iommu_v1.c @@ -295,7 +295,7 @@ static void mtk_iommu_detach_device(struct iommu_domain *domain, } static int mtk_iommu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { struct mtk_iommu_domain *dom = to_mtk_domain(domain); unsigned int page_num = size >> MT2701_IOMMU_PAGE_SHIFT; diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c index 09c6e1c680db..be551cc34be4 100644 --- a/drivers/iommu/omap-iommu.c +++ b/drivers/iommu/omap-iommu.c @@ -1339,7 +1339,7 @@ static u32 iotlb_init_entry(struct iotlb_entry *e, u32 da, u32 pa, int pgsz) } static int omap_iommu_map(struct iommu_domain *domain, unsigned long da, - phys_addr_t pa, size_t bytes, int prot) + phys_addr_t pa, size_t bytes, int prot, gfp_t gfp) { struct omap_iommu_domain *omap_domain = to_omap_domain(domain); struct device *dev = omap_domain->dev; diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c index c31e7bc4ccbe..6ad5f934f00f 100644 --- a/drivers/iommu/qcom_iommu.c +++ b/drivers/iommu/qcom_iommu.c @@ -423,7 +423,7 @@ static void qcom_iommu_detach_dev(struct iommu_domain *domain, struct device *de } static int qcom_iommu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { int ret; unsigned long flags; diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c index 26290f310f90..a4f6425fd12d 100644 --- a/drivers/iommu/rockchip-iommu.c +++ b/drivers/iommu/rockchip-iommu.c @@ -757,7 +757,7 @@ unwind: } static int rk_iommu_map(struct iommu_domain *domain, unsigned long _iova, - phys_addr_t paddr, size_t size, int prot) + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { struct rk_iommu_domain *rk_domain = to_rk_domain(domain); unsigned long flags; diff --git a/drivers/iommu/s390-iommu.c b/drivers/iommu/s390-iommu.c index 3b0b18e23187..1137f3ddcb85 100644 --- a/drivers/iommu/s390-iommu.c +++ b/drivers/iommu/s390-iommu.c @@ -265,7 +265,7 @@ undo_cpu_trans: } static int s390_iommu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { struct s390_domain *s390_domain = to_s390_domain(domain); int flags = ZPCI_PTE_VALID, rc = 0; diff --git a/drivers/iommu/tegra-gart.c b/drivers/iommu/tegra-gart.c index 3924f7c05544..3fb7ba72507d 100644 --- a/drivers/iommu/tegra-gart.c +++ b/drivers/iommu/tegra-gart.c @@ -178,7 +178,7 @@ static inline int __gart_iommu_map(struct gart_device *gart, unsigned long iova, } static int gart_iommu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t pa, size_t bytes, int prot) + phys_addr_t pa, size_t bytes, int prot, gfp_t gfp) { struct gart_device *gart = gart_handle; int ret; diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c index 7293fc3f796d..99f85fb5a704 100644 --- a/drivers/iommu/tegra-smmu.c +++ b/drivers/iommu/tegra-smmu.c @@ -650,7 +650,7 @@ static void tegra_smmu_set_pte(struct tegra_smmu_as *as, unsigned long iova, } static int tegra_smmu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { struct tegra_smmu_as *as = to_smmu_as(domain); dma_addr_t pte_dma; diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c index 3ea9d7682999..2ebcf4bae0c6 100644 --- a/drivers/iommu/virtio-iommu.c +++ b/drivers/iommu/virtio-iommu.c @@ -713,7 +713,7 @@ static int viommu_attach_dev(struct iommu_domain *domain, struct device *dev) } static int viommu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { int ret; u32 flags; diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 29bac5345563..6ca3fb2873d7 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -256,7 +256,7 @@ struct iommu_ops { int (*attach_dev)(struct iommu_domain *domain, struct device *dev); void (*detach_dev)(struct iommu_domain *domain, struct device *dev); int (*map)(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot); + phys_addr_t paddr, size_t size, int prot, gfp_t gfp); size_t (*unmap)(struct iommu_domain *domain, unsigned long iova, size_t size, struct iommu_iotlb_gather *iotlb_gather); void (*flush_iotlb_all)(struct iommu_domain *domain); @@ -421,6 +421,8 @@ extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev); extern struct iommu_domain *iommu_get_dma_domain(struct device *dev); extern int iommu_map(struct iommu_domain *domain, unsigned long iova, phys_addr_t paddr, size_t size, int prot); +extern int iommu_map_atomic(struct iommu_domain *domain, unsigned long iova, + phys_addr_t paddr, size_t size, int prot); extern size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size); extern size_t iommu_unmap_fast(struct iommu_domain *domain, @@ -428,6 +430,9 @@ extern size_t iommu_unmap_fast(struct iommu_domain *domain, struct iommu_iotlb_gather *iotlb_gather); extern size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova, struct scatterlist *sg,unsigned int nents, int prot); +extern size_t iommu_map_sg_atomic(struct iommu_domain *domain, + unsigned long iova, struct scatterlist *sg, + unsigned int nents, int prot); extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova); extern void iommu_set_fault_handler(struct iommu_domain *domain, iommu_fault_handler_t handler, void *token); @@ -662,6 +667,13 @@ static inline int iommu_map(struct iommu_domain *domain, unsigned long iova, return -ENODEV; } +static inline int iommu_map_atomic(struct iommu_domain *domain, + unsigned long iova, phys_addr_t paddr, + size_t size, int prot) +{ + return -ENODEV; +} + static inline size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size) { @@ -682,6 +694,13 @@ static inline size_t iommu_map_sg(struct iommu_domain *domain, return 0; } +static inline size_t iommu_map_sg_atomic(struct iommu_domain *domain, + unsigned long iova, struct scatterlist *sg, + unsigned int nents, int prot) +{ + return 0; +} + static inline void iommu_flush_tlb_all(struct iommu_domain *domain) { } -- cgit v1.2.3 From 4c7c171f85b261f91270d405b7c7390aa6ddfb60 Mon Sep 17 00:00:00 2001 From: Yi L Liu Date: Wed, 2 Oct 2019 12:42:40 -0700 Subject: iommu: Introduce cache_invalidate API In any virtualization use case, when the first translation stage is "owned" by the guest OS, the host IOMMU driver has no knowledge of caching structure updates unless the guest invalidation activities are trapped by the virtualizer and passed down to the host. Since the invalidation data can be obtained from user space and will be written into physical IOMMU, we must allow security check at various layers. Therefore, generic invalidation data format are proposed here, model specific IOMMU drivers need to convert them into their own format. Signed-off-by: Yi L Liu Signed-off-by: Jacob Pan Signed-off-by: Ashok Raj Signed-off-by: Eric Auger Signed-off-by: Jean-Philippe Brucker Reviewed-by: Jean-Philippe Brucker Reviewed-by: Eric Auger Signed-off-by: Joerg Roedel --- drivers/iommu/iommu.c | 10 +++++ include/linux/iommu.h | 14 ++++++ include/uapi/linux/iommu.h | 110 +++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 134 insertions(+) (limited to 'include') diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index d658c7c6a2ab..6ca9d28c08bb 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -1665,6 +1665,16 @@ out_unlock: } EXPORT_SYMBOL_GPL(iommu_attach_device); +int iommu_cache_invalidate(struct iommu_domain *domain, struct device *dev, + struct iommu_cache_invalidate_info *inv_info) +{ + if (unlikely(!domain->ops->cache_invalidate)) + return -ENODEV; + + return domain->ops->cache_invalidate(domain, dev, inv_info); +} +EXPORT_SYMBOL_GPL(iommu_cache_invalidate); + static void __iommu_detach_device(struct iommu_domain *domain, struct device *dev) { diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 29bac5345563..9b22055e6f85 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -244,6 +244,7 @@ struct iommu_iotlb_gather { * @sva_unbind: Unbind process address space from device * @sva_get_pasid: Get PASID associated to a SVA handle * @page_response: handle page request response + * @cache_invalidate: invalidate translation caches * @pgsize_bitmap: bitmap of all possible supported page sizes */ struct iommu_ops { @@ -306,6 +307,8 @@ struct iommu_ops { int (*page_response)(struct device *dev, struct iommu_fault_event *evt, struct iommu_page_response *msg); + int (*cache_invalidate)(struct iommu_domain *domain, struct device *dev, + struct iommu_cache_invalidate_info *inv_info); unsigned long pgsize_bitmap; }; @@ -417,6 +420,9 @@ extern int iommu_attach_device(struct iommu_domain *domain, struct device *dev); extern void iommu_detach_device(struct iommu_domain *domain, struct device *dev); +extern int iommu_cache_invalidate(struct iommu_domain *domain, + struct device *dev, + struct iommu_cache_invalidate_info *inv_info); extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev); extern struct iommu_domain *iommu_get_dma_domain(struct device *dev); extern int iommu_map(struct iommu_domain *domain, unsigned long iova, @@ -1005,6 +1011,14 @@ static inline int iommu_sva_get_pasid(struct iommu_sva *handle) return IOMMU_PASID_INVALID; } +static inline int +iommu_cache_invalidate(struct iommu_domain *domain, + struct device *dev, + struct iommu_cache_invalidate_info *inv_info) +{ + return -ENODEV; +} + #endif /* CONFIG_IOMMU_API */ #ifdef CONFIG_IOMMU_DEBUGFS diff --git a/include/uapi/linux/iommu.h b/include/uapi/linux/iommu.h index fc00c5d4741b..f3e96214df8e 100644 --- a/include/uapi/linux/iommu.h +++ b/include/uapi/linux/iommu.h @@ -152,4 +152,114 @@ struct iommu_page_response { __u32 code; }; +/* defines the granularity of the invalidation */ +enum iommu_inv_granularity { + IOMMU_INV_GRANU_DOMAIN, /* domain-selective invalidation */ + IOMMU_INV_GRANU_PASID, /* PASID-selective invalidation */ + IOMMU_INV_GRANU_ADDR, /* page-selective invalidation */ + IOMMU_INV_GRANU_NR, /* number of invalidation granularities */ +}; + +/** + * struct iommu_inv_addr_info - Address Selective Invalidation Structure + * + * @flags: indicates the granularity of the address-selective invalidation + * - If the PASID bit is set, the @pasid field is populated and the invalidation + * relates to cache entries tagged with this PASID and matching the address + * range. + * - If ARCHID bit is set, @archid is populated and the invalidation relates + * to cache entries tagged with this architecture specific ID and matching + * the address range. + * - Both PASID and ARCHID can be set as they may tag different caches. + * - If neither PASID or ARCHID is set, global addr invalidation applies. + * - The LEAF flag indicates whether only the leaf PTE caching needs to be + * invalidated and other paging structure caches can be preserved. + * @pasid: process address space ID + * @archid: architecture-specific ID + * @addr: first stage/level input address + * @granule_size: page/block size of the mapping in bytes + * @nb_granules: number of contiguous granules to be invalidated + */ +struct iommu_inv_addr_info { +#define IOMMU_INV_ADDR_FLAGS_PASID (1 << 0) +#define IOMMU_INV_ADDR_FLAGS_ARCHID (1 << 1) +#define IOMMU_INV_ADDR_FLAGS_LEAF (1 << 2) + __u32 flags; + __u32 archid; + __u64 pasid; + __u64 addr; + __u64 granule_size; + __u64 nb_granules; +}; + +/** + * struct iommu_inv_pasid_info - PASID Selective Invalidation Structure + * + * @flags: indicates the granularity of the PASID-selective invalidation + * - If the PASID bit is set, the @pasid field is populated and the invalidation + * relates to cache entries tagged with this PASID and matching the address + * range. + * - If the ARCHID bit is set, the @archid is populated and the invalidation + * relates to cache entries tagged with this architecture specific ID and + * matching the address range. + * - Both PASID and ARCHID can be set as they may tag different caches. + * - At least one of PASID or ARCHID must be set. + * @pasid: process address space ID + * @archid: architecture-specific ID + */ +struct iommu_inv_pasid_info { +#define IOMMU_INV_PASID_FLAGS_PASID (1 << 0) +#define IOMMU_INV_PASID_FLAGS_ARCHID (1 << 1) + __u32 flags; + __u32 archid; + __u64 pasid; +}; + +/** + * struct iommu_cache_invalidate_info - First level/stage invalidation + * information + * @version: API version of this structure + * @cache: bitfield that allows to select which caches to invalidate + * @granularity: defines the lowest granularity used for the invalidation: + * domain > PASID > addr + * @padding: reserved for future use (should be zero) + * @pasid_info: invalidation data when @granularity is %IOMMU_INV_GRANU_PASID + * @addr_info: invalidation data when @granularity is %IOMMU_INV_GRANU_ADDR + * + * Not all the combinations of cache/granularity are valid: + * + * +--------------+---------------+---------------+---------------+ + * | type / | DEV_IOTLB | IOTLB | PASID | + * | granularity | | | cache | + * +==============+===============+===============+===============+ + * | DOMAIN | N/A | Y | Y | + * +--------------+---------------+---------------+---------------+ + * | PASID | Y | Y | Y | + * +--------------+---------------+---------------+---------------+ + * | ADDR | Y | Y | N/A | + * +--------------+---------------+---------------+---------------+ + * + * Invalidations by %IOMMU_INV_GRANU_DOMAIN don't take any argument other than + * @version and @cache. + * + * If multiple cache types are invalidated simultaneously, they all + * must support the used granularity. + */ +struct iommu_cache_invalidate_info { +#define IOMMU_CACHE_INVALIDATE_INFO_VERSION_1 1 + __u32 version; +/* IOMMU paging structure cache */ +#define IOMMU_CACHE_INV_TYPE_IOTLB (1 << 0) /* IOMMU IOTLB */ +#define IOMMU_CACHE_INV_TYPE_DEV_IOTLB (1 << 1) /* Device IOTLB */ +#define IOMMU_CACHE_INV_TYPE_PASID (1 << 2) /* PASID cache */ +#define IOMMU_CACHE_INV_TYPE_NR (3) + __u8 cache; + __u8 granularity; + __u8 padding[2]; + union { + struct iommu_inv_pasid_info pasid_info; + struct iommu_inv_addr_info addr_info; + }; +}; + #endif /* _UAPI_IOMMU_H */ -- cgit v1.2.3 From fa83433c92e340822a056a610a4fa2063a3db304 Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Wed, 2 Oct 2019 12:42:41 -0700 Subject: iommu: Add I/O ASID allocator Some devices might support multiple DMA address spaces, in particular those that have the PCI PASID feature. PASID (Process Address Space ID) allows to share process address spaces with devices (SVA), partition a device into VM-assignable entities (VFIO mdev) or simply provide multiple DMA address space to kernel drivers. Add a global PASID allocator usable by different drivers at the same time. Name it I/O ASID to avoid confusion with ASIDs allocated by arch code, which are usually a separate ID space. The IOASID space is global. Each device can have its own PASID space, but by convention the IOMMU ended up having a global PASID space, so that with SVA, each mm_struct is associated to a single PASID. The allocator is primarily used by IOMMU subsystem but in rare occasions drivers would like to allocate PASIDs for devices that aren't managed by an IOMMU, using the same ID space as IOMMU. Signed-off-by: Jean-Philippe Brucker Signed-off-by: Jacob Pan Reviewed-by: Jean-Philippe Brucker Reviewed-by: Eric Auger Signed-off-by: Joerg Roedel --- drivers/iommu/Kconfig | 4 ++ drivers/iommu/Makefile | 1 + drivers/iommu/ioasid.c | 151 +++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/ioasid.h | 48 ++++++++++++++++ 4 files changed, 204 insertions(+) create mode 100644 drivers/iommu/ioasid.c create mode 100644 include/linux/ioasid.h (limited to 'include') diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index e3842eabcfdd..fd50ddffffbf 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -3,6 +3,10 @@ config IOMMU_IOVA tristate +# The IOASID library may also be used by non-IOMMU_API users +config IOASID + tristate + # IOMMU_API always gets selected by whoever wants it. config IOMMU_API bool diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile index 4f405f926e73..35d17094fe3b 100644 --- a/drivers/iommu/Makefile +++ b/drivers/iommu/Makefile @@ -7,6 +7,7 @@ obj-$(CONFIG_IOMMU_DMA) += dma-iommu.o obj-$(CONFIG_IOMMU_IO_PGTABLE) += io-pgtable.o obj-$(CONFIG_IOMMU_IO_PGTABLE_ARMV7S) += io-pgtable-arm-v7s.o obj-$(CONFIG_IOMMU_IO_PGTABLE_LPAE) += io-pgtable-arm.o +obj-$(CONFIG_IOASID) += ioasid.o obj-$(CONFIG_IOMMU_IOVA) += iova.o obj-$(CONFIG_OF_IOMMU) += of_iommu.o obj-$(CONFIG_MSM_IOMMU) += msm_iommu.o diff --git a/drivers/iommu/ioasid.c b/drivers/iommu/ioasid.c new file mode 100644 index 000000000000..aadf500c281c --- /dev/null +++ b/drivers/iommu/ioasid.c @@ -0,0 +1,151 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * I/O Address Space ID allocator. There is one global IOASID space, split into + * subsets. Users create a subset with DECLARE_IOASID_SET, then allocate and + * free IOASIDs with ioasid_alloc and ioasid_free. + */ +#include +#include +#include +#include +#include + +struct ioasid_data { + ioasid_t id; + struct ioasid_set *set; + void *private; + struct rcu_head rcu; +}; + +static DEFINE_XARRAY_ALLOC(ioasid_xa); + +/** + * ioasid_set_data - Set private data for an allocated ioasid + * @ioasid: the ID to set data + * @data: the private data + * + * For IOASID that is already allocated, private data can be set + * via this API. Future lookup can be done via ioasid_find. + */ +int ioasid_set_data(ioasid_t ioasid, void *data) +{ + struct ioasid_data *ioasid_data; + int ret = 0; + + xa_lock(&ioasid_xa); + ioasid_data = xa_load(&ioasid_xa, ioasid); + if (ioasid_data) + rcu_assign_pointer(ioasid_data->private, data); + else + ret = -ENOENT; + xa_unlock(&ioasid_xa); + + /* + * Wait for readers to stop accessing the old private data, so the + * caller can free it. + */ + if (!ret) + synchronize_rcu(); + + return ret; +} +EXPORT_SYMBOL_GPL(ioasid_set_data); + +/** + * ioasid_alloc - Allocate an IOASID + * @set: the IOASID set + * @min: the minimum ID (inclusive) + * @max: the maximum ID (inclusive) + * @private: data private to the caller + * + * Allocate an ID between @min and @max. The @private pointer is stored + * internally and can be retrieved with ioasid_find(). + * + * Return: the allocated ID on success, or %INVALID_IOASID on failure. + */ +ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, ioasid_t max, + void *private) +{ + struct ioasid_data *data; + ioasid_t id; + + data = kzalloc(sizeof(*data), GFP_ATOMIC); + if (!data) + return INVALID_IOASID; + + data->set = set; + data->private = private; + + if (xa_alloc(&ioasid_xa, &id, data, XA_LIMIT(min, max), GFP_KERNEL)) { + pr_err("Failed to alloc ioasid from %d to %d\n", min, max); + goto exit_free; + } + data->id = id; + + return id; +exit_free: + kfree(data); + return INVALID_IOASID; +} +EXPORT_SYMBOL_GPL(ioasid_alloc); + +/** + * ioasid_free - Free an IOASID + * @ioasid: the ID to remove + */ +void ioasid_free(ioasid_t ioasid) +{ + struct ioasid_data *ioasid_data; + + ioasid_data = xa_erase(&ioasid_xa, ioasid); + + kfree_rcu(ioasid_data, rcu); +} +EXPORT_SYMBOL_GPL(ioasid_free); + +/** + * ioasid_find - Find IOASID data + * @set: the IOASID set + * @ioasid: the IOASID to find + * @getter: function to call on the found object + * + * The optional getter function allows to take a reference to the found object + * under the rcu lock. The function can also check if the object is still valid: + * if @getter returns false, then the object is invalid and NULL is returned. + * + * If the IOASID exists, return the private pointer passed to ioasid_alloc. + * Private data can be NULL if not set. Return an error if the IOASID is not + * found, or if @set is not NULL and the IOASID does not belong to the set. + */ +void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid, + bool (*getter)(void *)) +{ + void *priv; + struct ioasid_data *ioasid_data; + + rcu_read_lock(); + ioasid_data = xa_load(&ioasid_xa, ioasid); + if (!ioasid_data) { + priv = ERR_PTR(-ENOENT); + goto unlock; + } + if (set && ioasid_data->set != set) { + /* data found but does not belong to the set */ + priv = ERR_PTR(-EACCES); + goto unlock; + } + /* Now IOASID and its set is verified, we can return the private data */ + priv = rcu_dereference(ioasid_data->private); + if (getter && !getter(priv)) + priv = NULL; +unlock: + rcu_read_unlock(); + + return priv; +} +EXPORT_SYMBOL_GPL(ioasid_find); + +MODULE_AUTHOR("Jean-Philippe Brucker "); +MODULE_AUTHOR("Jacob Pan "); +MODULE_DESCRIPTION("IO Address Space ID (IOASID) allocator"); +MODULE_LICENSE("GPL"); diff --git a/include/linux/ioasid.h b/include/linux/ioasid.h new file mode 100644 index 000000000000..17337a13f06e --- /dev/null +++ b/include/linux/ioasid.h @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_IOASID_H +#define __LINUX_IOASID_H + +#include +#include + +#define INVALID_IOASID ((ioasid_t)-1) +typedef unsigned int ioasid_t; + +struct ioasid_set { + int dummy; +}; + +#define DECLARE_IOASID_SET(name) struct ioasid_set name = { 0 } + +#if IS_ENABLED(CONFIG_IOASID) +ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, ioasid_t max, + void *private); +void ioasid_free(ioasid_t ioasid); +void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid, + bool (*getter)(void *)); +int ioasid_set_data(ioasid_t ioasid, void *data); + +#else /* !CONFIG_IOASID */ +static inline ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, + ioasid_t max, void *private) +{ + return INVALID_IOASID; +} + +static inline void ioasid_free(ioasid_t ioasid) +{ +} + +static inline void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid, + bool (*getter)(void *)) +{ + return NULL; +} + +static inline int ioasid_set_data(ioasid_t ioasid, void *data) +{ + return -ENOTSUPP; +} + +#endif /* CONFIG_IOASID */ +#endif /* __LINUX_IOASID_H */ -- cgit v1.2.3 From e5c0bd7f2206cd288029edb6afbfde93c73b4048 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Wed, 2 Oct 2019 12:42:42 -0700 Subject: iommu/ioasid: Add custom allocators IOASID allocation may rely on platform specific methods. One use case is that when running in the guest, in order to obtain system wide global IOASIDs, emulated allocation interface is needed to communicate with the host. Here we call these platform specific allocators custom allocators. Custom IOASID allocators can be registered at runtime and take precedence over the default XArray allocator. They have these attributes: - provides platform specific alloc()/free() functions with private data. - allocation results lookup are not provided by the allocator, lookup request must be done by the IOASID framework by its own XArray. - allocators can be unregistered at runtime, either fallback to the next custom allocator or to the default allocator. - custom allocators can share the same set of alloc()/free() helpers, in this case they also share the same IOASID space, thus the same XArray. - switching between allocators requires all outstanding IOASIDs to be freed unless the two allocators share the same alloc()/free() helpers. Signed-off-by: Jean-Philippe Brucker Signed-off-by: Jacob Pan Link: https://lkml.org/lkml/2019/4/26/462 Reviewed-by: Jean-Philippe Brucker Reviewed-by: Eric Auger Signed-off-by: Joerg Roedel --- drivers/iommu/ioasid.c | 289 +++++++++++++++++++++++++++++++++++++++++++++++-- include/linux/ioasid.h | 28 +++++ 2 files changed, 308 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/drivers/iommu/ioasid.c b/drivers/iommu/ioasid.c index aadf500c281c..0f8dd377aada 100644 --- a/drivers/iommu/ioasid.c +++ b/drivers/iommu/ioasid.c @@ -17,7 +17,245 @@ struct ioasid_data { struct rcu_head rcu; }; -static DEFINE_XARRAY_ALLOC(ioasid_xa); +/* + * struct ioasid_allocator_data - Internal data structure to hold information + * about an allocator. There are two types of allocators: + * + * - Default allocator always has its own XArray to track the IOASIDs allocated. + * - Custom allocators may share allocation helpers with different private data. + * Custom allocators that share the same helper functions also share the same + * XArray. + * Rules: + * 1. Default allocator is always available, not dynamically registered. This is + * to prevent race conditions with early boot code that want to register + * custom allocators or allocate IOASIDs. + * 2. Custom allocators take precedence over the default allocator. + * 3. When all custom allocators sharing the same helper functions are + * unregistered (e.g. due to hotplug), all outstanding IOASIDs must be + * freed. Otherwise, outstanding IOASIDs will be lost and orphaned. + * 4. When switching between custom allocators sharing the same helper + * functions, outstanding IOASIDs are preserved. + * 5. When switching between custom allocator and default allocator, all IOASIDs + * must be freed to ensure unadulterated space for the new allocator. + * + * @ops: allocator helper functions and its data + * @list: registered custom allocators + * @slist: allocators share the same ops but different data + * @flags: attributes of the allocator + * @xa: xarray holds the IOASID space + * @rcu: used for kfree_rcu when unregistering allocator + */ +struct ioasid_allocator_data { + struct ioasid_allocator_ops *ops; + struct list_head list; + struct list_head slist; +#define IOASID_ALLOCATOR_CUSTOM BIT(0) /* Needs framework to track results */ + unsigned long flags; + struct xarray xa; + struct rcu_head rcu; +}; + +static DEFINE_SPINLOCK(ioasid_allocator_lock); +static LIST_HEAD(allocators_list); + +static ioasid_t default_alloc(ioasid_t min, ioasid_t max, void *opaque); +static void default_free(ioasid_t ioasid, void *opaque); + +static struct ioasid_allocator_ops default_ops = { + .alloc = default_alloc, + .free = default_free, +}; + +static struct ioasid_allocator_data default_allocator = { + .ops = &default_ops, + .flags = 0, + .xa = XARRAY_INIT(ioasid_xa, XA_FLAGS_ALLOC), +}; + +static struct ioasid_allocator_data *active_allocator = &default_allocator; + +static ioasid_t default_alloc(ioasid_t min, ioasid_t max, void *opaque) +{ + ioasid_t id; + + if (xa_alloc(&default_allocator.xa, &id, opaque, XA_LIMIT(min, max), GFP_ATOMIC)) { + pr_err("Failed to alloc ioasid from %d to %d\n", min, max); + return INVALID_IOASID; + } + + return id; +} + +static void default_free(ioasid_t ioasid, void *opaque) +{ + struct ioasid_data *ioasid_data; + + ioasid_data = xa_erase(&default_allocator.xa, ioasid); + kfree_rcu(ioasid_data, rcu); +} + +/* Allocate and initialize a new custom allocator with its helper functions */ +static struct ioasid_allocator_data *ioasid_alloc_allocator(struct ioasid_allocator_ops *ops) +{ + struct ioasid_allocator_data *ia_data; + + ia_data = kzalloc(sizeof(*ia_data), GFP_ATOMIC); + if (!ia_data) + return NULL; + + xa_init_flags(&ia_data->xa, XA_FLAGS_ALLOC); + INIT_LIST_HEAD(&ia_data->slist); + ia_data->flags |= IOASID_ALLOCATOR_CUSTOM; + ia_data->ops = ops; + + /* For tracking custom allocators that share the same ops */ + list_add_tail(&ops->list, &ia_data->slist); + + return ia_data; +} + +static bool use_same_ops(struct ioasid_allocator_ops *a, struct ioasid_allocator_ops *b) +{ + return (a->free == b->free) && (a->alloc == b->alloc); +} + +/** + * ioasid_register_allocator - register a custom allocator + * @ops: the custom allocator ops to be registered + * + * Custom allocators take precedence over the default xarray based allocator. + * Private data associated with the IOASID allocated by the custom allocators + * are managed by IOASID framework similar to data stored in xa by default + * allocator. + * + * There can be multiple allocators registered but only one is active. In case + * of runtime removal of a custom allocator, the next one is activated based + * on the registration ordering. + * + * Multiple allocators can share the same alloc() function, in this case the + * IOASID space is shared. + */ +int ioasid_register_allocator(struct ioasid_allocator_ops *ops) +{ + struct ioasid_allocator_data *ia_data; + struct ioasid_allocator_data *pallocator; + int ret = 0; + + spin_lock(&ioasid_allocator_lock); + + ia_data = ioasid_alloc_allocator(ops); + if (!ia_data) { + ret = -ENOMEM; + goto out_unlock; + } + + /* + * No particular preference, we activate the first one and keep + * the later registered allocators in a list in case the first one gets + * removed due to hotplug. + */ + if (list_empty(&allocators_list)) { + WARN_ON(active_allocator != &default_allocator); + /* Use this new allocator if default is not active */ + if (xa_empty(&active_allocator->xa)) { + rcu_assign_pointer(active_allocator, ia_data); + list_add_tail(&ia_data->list, &allocators_list); + goto out_unlock; + } + pr_warn("Default allocator active with outstanding IOASID\n"); + ret = -EAGAIN; + goto out_free; + } + + /* Check if the allocator is already registered */ + list_for_each_entry(pallocator, &allocators_list, list) { + if (pallocator->ops == ops) { + pr_err("IOASID allocator already registered\n"); + ret = -EEXIST; + goto out_free; + } else if (use_same_ops(pallocator->ops, ops)) { + /* + * If the new allocator shares the same ops, + * then they will share the same IOASID space. + * We should put them under the same xarray. + */ + list_add_tail(&ops->list, &pallocator->slist); + goto out_free; + } + } + list_add_tail(&ia_data->list, &allocators_list); + + spin_unlock(&ioasid_allocator_lock); + return 0; +out_free: + kfree(ia_data); +out_unlock: + spin_unlock(&ioasid_allocator_lock); + return ret; +} +EXPORT_SYMBOL_GPL(ioasid_register_allocator); + +/** + * ioasid_unregister_allocator - Remove a custom IOASID allocator ops + * @ops: the custom allocator to be removed + * + * Remove an allocator from the list, activate the next allocator in + * the order it was registered. Or revert to default allocator if all + * custom allocators are unregistered without outstanding IOASIDs. + */ +void ioasid_unregister_allocator(struct ioasid_allocator_ops *ops) +{ + struct ioasid_allocator_data *pallocator; + struct ioasid_allocator_ops *sops; + + spin_lock(&ioasid_allocator_lock); + if (list_empty(&allocators_list)) { + pr_warn("No custom IOASID allocators active!\n"); + goto exit_unlock; + } + + list_for_each_entry(pallocator, &allocators_list, list) { + if (!use_same_ops(pallocator->ops, ops)) + continue; + + if (list_is_singular(&pallocator->slist)) { + /* No shared helper functions */ + list_del(&pallocator->list); + /* + * All IOASIDs should have been freed before + * the last allocator that shares the same ops + * is unregistered. + */ + WARN_ON(!xa_empty(&pallocator->xa)); + if (list_empty(&allocators_list)) { + pr_info("No custom IOASID allocators, switch to default.\n"); + rcu_assign_pointer(active_allocator, &default_allocator); + } else if (pallocator == active_allocator) { + rcu_assign_pointer(active_allocator, + list_first_entry(&allocators_list, + struct ioasid_allocator_data, list)); + pr_info("IOASID allocator changed"); + } + kfree_rcu(pallocator, rcu); + break; + } + /* + * Find the matching shared ops to delete, + * but keep outstanding IOASIDs + */ + list_for_each_entry(sops, &pallocator->slist, list) { + if (sops == ops) { + list_del(&ops->list); + break; + } + } + break; + } + +exit_unlock: + spin_unlock(&ioasid_allocator_lock); +} +EXPORT_SYMBOL_GPL(ioasid_unregister_allocator); /** * ioasid_set_data - Set private data for an allocated ioasid @@ -32,13 +270,13 @@ int ioasid_set_data(ioasid_t ioasid, void *data) struct ioasid_data *ioasid_data; int ret = 0; - xa_lock(&ioasid_xa); - ioasid_data = xa_load(&ioasid_xa, ioasid); + spin_lock(&ioasid_allocator_lock); + ioasid_data = xa_load(&active_allocator->xa, ioasid); if (ioasid_data) rcu_assign_pointer(ioasid_data->private, data); else ret = -ENOENT; - xa_unlock(&ioasid_xa); + spin_unlock(&ioasid_allocator_lock); /* * Wait for readers to stop accessing the old private data, so the @@ -67,6 +305,7 @@ ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, ioasid_t max, void *private) { struct ioasid_data *data; + void *adata; ioasid_t id; data = kzalloc(sizeof(*data), GFP_ATOMIC); @@ -76,14 +315,31 @@ ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, ioasid_t max, data->set = set; data->private = private; - if (xa_alloc(&ioasid_xa, &id, data, XA_LIMIT(min, max), GFP_KERNEL)) { - pr_err("Failed to alloc ioasid from %d to %d\n", min, max); + /* + * Custom allocator needs allocator data to perform platform specific + * operations. + */ + spin_lock(&ioasid_allocator_lock); + adata = active_allocator->flags & IOASID_ALLOCATOR_CUSTOM ? active_allocator->ops->pdata : data; + id = active_allocator->ops->alloc(min, max, adata); + if (id == INVALID_IOASID) { + pr_err("Failed ASID allocation %lu\n", active_allocator->flags); + goto exit_free; + } + + if ((active_allocator->flags & IOASID_ALLOCATOR_CUSTOM) && + xa_alloc(&active_allocator->xa, &id, data, XA_LIMIT(id, id), GFP_ATOMIC)) { + /* Custom allocator needs framework to store and track allocation results */ + pr_err("Failed to alloc ioasid from %d\n", id); + active_allocator->ops->free(id, active_allocator->ops->pdata); goto exit_free; } data->id = id; + spin_unlock(&ioasid_allocator_lock); return id; exit_free: + spin_unlock(&ioasid_allocator_lock); kfree(data); return INVALID_IOASID; } @@ -97,9 +353,22 @@ void ioasid_free(ioasid_t ioasid) { struct ioasid_data *ioasid_data; - ioasid_data = xa_erase(&ioasid_xa, ioasid); + spin_lock(&ioasid_allocator_lock); + ioasid_data = xa_load(&active_allocator->xa, ioasid); + if (!ioasid_data) { + pr_err("Trying to free unknown IOASID %u\n", ioasid); + goto exit_unlock; + } - kfree_rcu(ioasid_data, rcu); + active_allocator->ops->free(ioasid, active_allocator->ops->pdata); + /* Custom allocator needs additional steps to free the xa element */ + if (active_allocator->flags & IOASID_ALLOCATOR_CUSTOM) { + ioasid_data = xa_erase(&active_allocator->xa, ioasid); + kfree_rcu(ioasid_data, rcu); + } + +exit_unlock: + spin_unlock(&ioasid_allocator_lock); } EXPORT_SYMBOL_GPL(ioasid_free); @@ -122,9 +391,11 @@ void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid, { void *priv; struct ioasid_data *ioasid_data; + struct ioasid_allocator_data *idata; rcu_read_lock(); - ioasid_data = xa_load(&ioasid_xa, ioasid); + idata = rcu_dereference(active_allocator); + ioasid_data = xa_load(&idata->xa, ioasid); if (!ioasid_data) { priv = ERR_PTR(-ENOENT); goto unlock; diff --git a/include/linux/ioasid.h b/include/linux/ioasid.h index 17337a13f06e..6f000d7a0ddc 100644 --- a/include/linux/ioasid.h +++ b/include/linux/ioasid.h @@ -7,11 +7,28 @@ #define INVALID_IOASID ((ioasid_t)-1) typedef unsigned int ioasid_t; +typedef ioasid_t (*ioasid_alloc_fn_t)(ioasid_t min, ioasid_t max, void *data); +typedef void (*ioasid_free_fn_t)(ioasid_t ioasid, void *data); struct ioasid_set { int dummy; }; +/** + * struct ioasid_allocator_ops - IOASID allocator helper functions and data + * + * @alloc: helper function to allocate IOASID + * @free: helper function to free IOASID + * @list: for tracking ops that share helper functions but not data + * @pdata: data belong to the allocator, provided when calling alloc() + */ +struct ioasid_allocator_ops { + ioasid_alloc_fn_t alloc; + ioasid_free_fn_t free; + struct list_head list; + void *pdata; +}; + #define DECLARE_IOASID_SET(name) struct ioasid_set name = { 0 } #if IS_ENABLED(CONFIG_IOASID) @@ -20,6 +37,8 @@ ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, ioasid_t max, void ioasid_free(ioasid_t ioasid); void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid, bool (*getter)(void *)); +int ioasid_register_allocator(struct ioasid_allocator_ops *allocator); +void ioasid_unregister_allocator(struct ioasid_allocator_ops *allocator); int ioasid_set_data(ioasid_t ioasid, void *data); #else /* !CONFIG_IOASID */ @@ -39,6 +58,15 @@ static inline void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid, return NULL; } +static inline int ioasid_register_allocator(struct ioasid_allocator_ops *allocator) +{ + return -ENOTSUPP; +} + +static inline void ioasid_unregister_allocator(struct ioasid_allocator_ops *allocator) +{ +} + static inline int ioasid_set_data(ioasid_t ioasid, void *data) { return -ENOTSUPP; -- cgit v1.2.3 From 808be0aae53a3675337fad9cde616e086bdc8287 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Wed, 2 Oct 2019 12:42:43 -0700 Subject: iommu: Introduce guest PASID bind function Guest shared virtual address (SVA) may require host to shadow guest PASID tables. Guest PASID can also be allocated from the host via enlightened interfaces. In this case, guest needs to bind the guest mm, i.e. cr3 in guest physical address to the actual PASID table in the host IOMMU. Nesting will be turned on such that guest virtual address can go through a two level translation: - 1st level translates GVA to GPA - 2nd level translates GPA to HPA This patch introduces APIs to bind guest PASID data to the assigned device entry in the physical IOMMU. See the diagram below for usage explanation. .-------------. .---------------------------. | vIOMMU | | Guest process mm, FL only | | | '---------------------------' .----------------/ | PASID Entry |--- PASID cache flush - '-------------' | | | V | | GP '-------------' Guest ------| Shadow |----------------------- GP->HP* --------- v v | Host v .-------------. .----------------------. | pIOMMU | | Bind FL for GVA-GPA | | | '----------------------' .----------------/ | | PASID Entry | V (Nested xlate) '----------------\.---------------------. | | |Set SL to GPA-HPA | | | '---------------------' '-------------' Where: - FL = First level/stage one page tables - SL = Second level/stage two page tables - GP = Guest PASID - HP = Host PASID * Conversion needed if non-identity GP-HP mapping option is chosen. Signed-off-by: Jacob Pan Signed-off-by: Liu Yi L Reviewed-by: Jean-Philippe Brucker Reviewed-by: Jean-Philippe Brucker Reviewed-by: Eric Auger Signed-off-by: Joerg Roedel --- drivers/iommu/iommu.c | 20 ++++++++++++++++ include/linux/iommu.h | 22 +++++++++++++++++ include/uapi/linux/iommu.h | 59 ++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 101 insertions(+) (limited to 'include') diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 6ca9d28c08bb..4486c4e6830a 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -1675,6 +1675,26 @@ int iommu_cache_invalidate(struct iommu_domain *domain, struct device *dev, } EXPORT_SYMBOL_GPL(iommu_cache_invalidate); +int iommu_sva_bind_gpasid(struct iommu_domain *domain, + struct device *dev, struct iommu_gpasid_bind_data *data) +{ + if (unlikely(!domain->ops->sva_bind_gpasid)) + return -ENODEV; + + return domain->ops->sva_bind_gpasid(domain, dev, data); +} +EXPORT_SYMBOL_GPL(iommu_sva_bind_gpasid); + +int iommu_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev, + ioasid_t pasid) +{ + if (unlikely(!domain->ops->sva_unbind_gpasid)) + return -ENODEV; + + return domain->ops->sva_unbind_gpasid(dev, pasid); +} +EXPORT_SYMBOL_GPL(iommu_sva_unbind_gpasid); + static void __iommu_detach_device(struct iommu_domain *domain, struct device *dev) { diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 9b22055e6f85..f8959f759e41 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -13,6 +13,7 @@ #include #include #include +#include #include #define IOMMU_READ (1 << 0) @@ -246,6 +247,8 @@ struct iommu_iotlb_gather { * @page_response: handle page request response * @cache_invalidate: invalidate translation caches * @pgsize_bitmap: bitmap of all possible supported page sizes + * @sva_bind_gpasid: bind guest pasid and mm + * @sva_unbind_gpasid: unbind guest pasid and mm */ struct iommu_ops { bool (*capable)(enum iommu_cap); @@ -309,6 +312,10 @@ struct iommu_ops { struct iommu_page_response *msg); int (*cache_invalidate)(struct iommu_domain *domain, struct device *dev, struct iommu_cache_invalidate_info *inv_info); + int (*sva_bind_gpasid)(struct iommu_domain *domain, + struct device *dev, struct iommu_gpasid_bind_data *data); + + int (*sva_unbind_gpasid)(struct device *dev, int pasid); unsigned long pgsize_bitmap; }; @@ -423,6 +430,10 @@ extern void iommu_detach_device(struct iommu_domain *domain, extern int iommu_cache_invalidate(struct iommu_domain *domain, struct device *dev, struct iommu_cache_invalidate_info *inv_info); +extern int iommu_sva_bind_gpasid(struct iommu_domain *domain, + struct device *dev, struct iommu_gpasid_bind_data *data); +extern int iommu_sva_unbind_gpasid(struct iommu_domain *domain, + struct device *dev, ioasid_t pasid); extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev); extern struct iommu_domain *iommu_get_dma_domain(struct device *dev); extern int iommu_map(struct iommu_domain *domain, unsigned long iova, @@ -1018,6 +1029,17 @@ iommu_cache_invalidate(struct iommu_domain *domain, { return -ENODEV; } +static inline int iommu_sva_bind_gpasid(struct iommu_domain *domain, + struct device *dev, struct iommu_gpasid_bind_data *data) +{ + return -ENODEV; +} + +static inline int iommu_sva_unbind_gpasid(struct iommu_domain *domain, + struct device *dev, int pasid) +{ + return -ENODEV; +} #endif /* CONFIG_IOMMU_API */ diff --git a/include/uapi/linux/iommu.h b/include/uapi/linux/iommu.h index f3e96214df8e..4ad3496e5c43 100644 --- a/include/uapi/linux/iommu.h +++ b/include/uapi/linux/iommu.h @@ -262,4 +262,63 @@ struct iommu_cache_invalidate_info { }; }; +/** + * struct iommu_gpasid_bind_data_vtd - Intel VT-d specific data on device and guest + * SVA binding. + * + * @flags: VT-d PASID table entry attributes + * @pat: Page attribute table data to compute effective memory type + * @emt: Extended memory type + * + * Only guest vIOMMU selectable and effective options are passed down to + * the host IOMMU. + */ +struct iommu_gpasid_bind_data_vtd { +#define IOMMU_SVA_VTD_GPASID_SRE (1 << 0) /* supervisor request */ +#define IOMMU_SVA_VTD_GPASID_EAFE (1 << 1) /* extended access enable */ +#define IOMMU_SVA_VTD_GPASID_PCD (1 << 2) /* page-level cache disable */ +#define IOMMU_SVA_VTD_GPASID_PWT (1 << 3) /* page-level write through */ +#define IOMMU_SVA_VTD_GPASID_EMTE (1 << 4) /* extended mem type enable */ +#define IOMMU_SVA_VTD_GPASID_CD (1 << 5) /* PASID-level cache disable */ + __u64 flags; + __u32 pat; + __u32 emt; +}; + +/** + * struct iommu_gpasid_bind_data - Information about device and guest PASID binding + * @version: Version of this data structure + * @format: PASID table entry format + * @flags: Additional information on guest bind request + * @gpgd: Guest page directory base of the guest mm to bind + * @hpasid: Process address space ID used for the guest mm in host IOMMU + * @gpasid: Process address space ID used for the guest mm in guest IOMMU + * @addr_width: Guest virtual address width + * @padding: Reserved for future use (should be zero) + * @vtd: Intel VT-d specific data + * + * Guest to host PASID mapping can be an identity or non-identity, where guest + * has its own PASID space. For non-identify mapping, guest to host PASID lookup + * is needed when VM programs guest PASID into an assigned device. VMM may + * trap such PASID programming then request host IOMMU driver to convert guest + * PASID to host PASID based on this bind data. + */ +struct iommu_gpasid_bind_data { +#define IOMMU_GPASID_BIND_VERSION_1 1 + __u32 version; +#define IOMMU_PASID_FORMAT_INTEL_VTD 1 + __u32 format; +#define IOMMU_SVA_GPASID_VAL (1 << 0) /* guest PASID valid */ + __u64 flags; + __u64 gpgd; + __u64 hpasid; + __u64 gpasid; + __u32 addr_width; + __u8 padding[12]; + /* Vendor specific data */ + union { + struct iommu_gpasid_bind_data_vtd vtd; + }; +}; + #endif /* _UAPI_IOMMU_H */ -- cgit v1.2.3 From aff5d0552da4055da3faa27ee4252e48bb1f5821 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sat, 5 Oct 2019 14:04:36 +0200 Subject: PCI/ASPM: Add L1 PM substate support to pci_disable_link_state() Add support for disabling states L1.1 and L1.2 to pci_disable_link_state(). Allow separate control of ASPM and PCI PM L1 substates. Link: https://lore.kernel.org/r/d81f8036-c236-6463-48e7-ebcdcda85bba@gmail.com Signed-off-by: Heiner Kallweit Signed-off-by: Bjorn Helgaas --- drivers/pci/pcie/aspm.c | 11 ++++++++++- include/linux/pci.h | 10 +++++++--- 2 files changed, 17 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index f5c7138a34aa..f8572a523a15 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -1094,7 +1094,16 @@ static int __pci_disable_link_state(struct pci_dev *pdev, int state, bool sem) if (state & PCIE_LINK_STATE_L0S) link->aspm_disable |= ASPM_STATE_L0S; if (state & PCIE_LINK_STATE_L1) - link->aspm_disable |= ASPM_STATE_L1; + /* L1 PM substates require L1 */ + link->aspm_disable |= ASPM_STATE_L1 | ASPM_STATE_L1SS; + if (state & PCIE_LINK_STATE_L1_1) + link->aspm_disable |= ASPM_STATE_L1_1; + if (state & PCIE_LINK_STATE_L1_2) + link->aspm_disable |= ASPM_STATE_L1_2; + if (state & PCIE_LINK_STATE_L1_1_PCIPM) + link->aspm_disable |= ASPM_STATE_L1_1_PCIPM; + if (state & PCIE_LINK_STATE_L1_2_PCIPM) + link->aspm_disable |= ASPM_STATE_L1_2_PCIPM; pcie_config_aspm_link(link, policy_to_aspm_state(link)); if (state & PCIE_LINK_STATE_CLKPM) { diff --git a/include/linux/pci.h b/include/linux/pci.h index f9088c89a534..9dc5bee14ae9 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1544,9 +1544,13 @@ extern bool pcie_ports_native; #define pcie_ports_native false #endif -#define PCIE_LINK_STATE_L0S 1 -#define PCIE_LINK_STATE_L1 2 -#define PCIE_LINK_STATE_CLKPM 4 +#define PCIE_LINK_STATE_L0S BIT(0) +#define PCIE_LINK_STATE_L1 BIT(1) +#define PCIE_LINK_STATE_CLKPM BIT(2) +#define PCIE_LINK_STATE_L1_1 BIT(3) +#define PCIE_LINK_STATE_L1_2 BIT(4) +#define PCIE_LINK_STATE_L1_1_PCIPM BIT(5) +#define PCIE_LINK_STATE_L1_2_PCIPM BIT(6) #ifdef CONFIG_PCIEASPM int pci_disable_link_state(struct pci_dev *pdev, int state); -- cgit v1.2.3 From 8cbb8a9374a271099bacdc890fb16d374261332b Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Wed, 9 Oct 2019 14:54:01 -0500 Subject: PCI/ATS: Move pci_prg_resp_pasid_required() to CONFIG_PCI_PRI pci_prg_resp_pasid_required() returns the value of the "PRG Response PASID Required" bit from the PRI capability, but the interface was previously defined under #ifdef CONFIG_PCI_PASID. Move it from CONFIG_PCI_PASID to CONFIG_PCI_PRI so it's with the other PRI-related things. Signed-off-by: Bjorn Helgaas Reviewed-by: Kuppuswamy Sathyanarayanan Reviewed-by: Joerg Roedel --- drivers/pci/ats.c | 55 ++++++++++++++++++++++--------------------------- include/linux/pci-ats.h | 11 +++++----- 2 files changed, 30 insertions(+), 36 deletions(-) (limited to 'include') diff --git a/drivers/pci/ats.c b/drivers/pci/ats.c index e18499243f84..0d06177252c7 100644 --- a/drivers/pci/ats.c +++ b/drivers/pci/ats.c @@ -280,6 +280,31 @@ int pci_reset_pri(struct pci_dev *pdev) return 0; } EXPORT_SYMBOL_GPL(pci_reset_pri); + +/** + * pci_prg_resp_pasid_required - Return PRG Response PASID Required bit + * status. + * @pdev: PCI device structure + * + * Returns 1 if PASID is required in PRG Response Message, 0 otherwise. + */ +int pci_prg_resp_pasid_required(struct pci_dev *pdev) +{ + u16 status; + int pos; + + pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PRI); + if (!pos) + return 0; + + pci_read_config_word(pdev, pos + PCI_PRI_STATUS, &status); + + if (status & PCI_PRI_STATUS_PASID) + return 1; + + return 0; +} +EXPORT_SYMBOL_GPL(pci_prg_resp_pasid_required); #endif /* CONFIG_PCI_PRI */ #ifdef CONFIG_PCI_PASID @@ -395,36 +420,6 @@ int pci_pasid_features(struct pci_dev *pdev) } EXPORT_SYMBOL_GPL(pci_pasid_features); -/** - * pci_prg_resp_pasid_required - Return PRG Response PASID Required bit - * status. - * @pdev: PCI device structure - * - * Returns 1 if PASID is required in PRG Response Message, 0 otherwise. - * - * Even though the PRG response PASID status is read from PRI Status - * Register, since this API will mainly be used by PASID users, this - * function is defined within #ifdef CONFIG_PCI_PASID instead of - * CONFIG_PCI_PRI. - */ -int pci_prg_resp_pasid_required(struct pci_dev *pdev) -{ - u16 status; - int pos; - - pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PRI); - if (!pos) - return 0; - - pci_read_config_word(pdev, pos + PCI_PRI_STATUS, &status); - - if (status & PCI_PRI_STATUS_PASID) - return 1; - - return 0; -} -EXPORT_SYMBOL_GPL(pci_prg_resp_pasid_required); - #define PASID_NUMBER_SHIFT 8 #define PASID_NUMBER_MASK (0x1f << PASID_NUMBER_SHIFT) /** diff --git a/include/linux/pci-ats.h b/include/linux/pci-ats.h index 1ebb88e7c184..a7a2b3d94fcc 100644 --- a/include/linux/pci-ats.h +++ b/include/linux/pci-ats.h @@ -10,6 +10,7 @@ int pci_enable_pri(struct pci_dev *pdev, u32 reqs); void pci_disable_pri(struct pci_dev *pdev); void pci_restore_pri_state(struct pci_dev *pdev); int pci_reset_pri(struct pci_dev *pdev); +int pci_prg_resp_pasid_required(struct pci_dev *pdev); #else /* CONFIG_PCI_PRI */ @@ -31,6 +32,10 @@ static inline int pci_reset_pri(struct pci_dev *pdev) return -ENODEV; } +static inline int pci_prg_resp_pasid_required(struct pci_dev *pdev) +{ + return 0; +} #endif /* CONFIG_PCI_PRI */ #ifdef CONFIG_PCI_PASID @@ -40,7 +45,6 @@ void pci_disable_pasid(struct pci_dev *pdev); void pci_restore_pasid_state(struct pci_dev *pdev); int pci_pasid_features(struct pci_dev *pdev); int pci_max_pasids(struct pci_dev *pdev); -int pci_prg_resp_pasid_required(struct pci_dev *pdev); #else /* CONFIG_PCI_PASID */ @@ -66,11 +70,6 @@ static inline int pci_max_pasids(struct pci_dev *pdev) { return -EINVAL; } - -static inline int pci_prg_resp_pasid_required(struct pci_dev *pdev) -{ - return 0; -} #endif /* CONFIG_PCI_PASID */ -- cgit v1.2.3 From 3ad62192097443e8c3a8e244475bacaecb894d4e Mon Sep 17 00:00:00 2001 From: Kuppuswamy Sathyanarayanan Date: Thu, 5 Sep 2019 14:31:44 -0500 Subject: PCI/ATS: Disable PF/VF ATS service independently Previously we didn't disable the PF ATS until all associated VFs had disabled it. But per PCIe spec r5.0, sec 9.3.7.8, the ATS Capability in VFs and associated PFs may be enabled independently. Leaving ATS enabled in the PF unnecessarily may have power and performance impacts. Remove this dependency logic in the ATS enable/disable code. [bhelgaas: commit log] Suggested-by: Ashok Raj Link: https://lore.kernel.org/r/8163ab8fa66afd2cba514ae95d29ab12104781aa.1567029860.git.sathyanarayanan.kuppuswamy@linux.intel.com Link: https://lore.kernel.org/r/20190905193146.90250-4-helgaas@kernel.org Signed-off-by: Kuppuswamy Sathyanarayanan Signed-off-by: Bjorn Helgaas Cc: Ashok Raj Cc: Keith Busch --- drivers/pci/ats.c | 11 ----------- include/linux/pci.h | 1 - 2 files changed, 12 deletions(-) (limited to 'include') diff --git a/drivers/pci/ats.c b/drivers/pci/ats.c index fb5cfd27dd3c..a708ed4146ca 100644 --- a/drivers/pci/ats.c +++ b/drivers/pci/ats.c @@ -60,8 +60,6 @@ int pci_enable_ats(struct pci_dev *dev, int ps) pdev = pci_physfn(dev); if (pdev->ats_stu != ps) return -EINVAL; - - atomic_inc(&pdev->ats_ref_cnt); /* count enabled VFs */ } else { dev->ats_stu = ps; ctrl |= PCI_ATS_CTRL_STU(dev->ats_stu - PCI_ATS_MIN_STU); @@ -79,20 +77,11 @@ EXPORT_SYMBOL_GPL(pci_enable_ats); */ void pci_disable_ats(struct pci_dev *dev) { - struct pci_dev *pdev; u16 ctrl; if (WARN_ON(!dev->ats_enabled)) return; - if (atomic_read(&dev->ats_ref_cnt)) - return; /* VFs still enabled */ - - if (dev->is_virtfn) { - pdev = pci_physfn(dev); - atomic_dec(&pdev->ats_ref_cnt); - } - pci_read_config_word(dev, dev->ats_cap + PCI_ATS_CTRL, &ctrl); ctrl &= ~PCI_ATS_CTRL_ENABLE; pci_write_config_word(dev, dev->ats_cap + PCI_ATS_CTRL, ctrl); diff --git a/include/linux/pci.h b/include/linux/pci.h index f9088c89a534..c028883c8460 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -452,7 +452,6 @@ struct pci_dev { }; u16 ats_cap; /* ATS Capability offset */ u8 ats_stu; /* ATS Smallest Translation Unit */ - atomic_t ats_ref_cnt; /* Number of VFs with ATS enabled */ #endif #ifdef CONFIG_PCI_PRI u32 pri_reqs_alloc; /* Number of PRI requests allocated */ -- cgit v1.2.3 From c065190bbcd4fb54ce9c5fd34fcad71acf2a0ea4 Mon Sep 17 00:00:00 2001 From: Kuppuswamy Sathyanarayanan Date: Thu, 5 Sep 2019 14:31:45 -0500 Subject: PCI/ATS: Cache PRI Capability offset Previously each PRI interface searched for the PRI Capability. Cache the capability offset the first time we use it instead of searching each time. [bhelgaas: commit log, reorder patch to later, call pci_pri_init() from pci_init_capabilities()] Link: https://lore.kernel.org/r/0c5495d376faf6dbb8eb2165204c474438aaae65.156 7029860.git.sathyanarayanan.kuppuswamy@linux.intel.com Link: https://lore.kernel.org/r/20190905193146.90250-5-helgaas@kernel.org Signed-off-by: Kuppuswamy Sathyanarayanan Signed-off-by: Bjorn Helgaas --- drivers/pci/ats.c | 51 ++++++++++++++++++++++++++------------------------- drivers/pci/pci.h | 6 ++++++ drivers/pci/probe.c | 3 +++ include/linux/pci.h | 1 + 4 files changed, 36 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/drivers/pci/ats.c b/drivers/pci/ats.c index a708ed4146ca..c97e862b538a 100644 --- a/drivers/pci/ats.c +++ b/drivers/pci/ats.c @@ -159,6 +159,11 @@ int pci_ats_page_aligned(struct pci_dev *pdev) EXPORT_SYMBOL_GPL(pci_ats_page_aligned); #ifdef CONFIG_PCI_PRI +void pci_pri_init(struct pci_dev *pdev) +{ + pdev->pri_cap = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PRI); +} + /** * pci_enable_pri - Enable PRI capability * @ pdev: PCI device structure @@ -169,7 +174,7 @@ int pci_enable_pri(struct pci_dev *pdev, u32 reqs) { u16 control, status; u32 max_requests; - int pos; + int pri = pdev->pri_cap; /* * VFs must not implement the PRI Capability. If their PF @@ -185,21 +190,20 @@ int pci_enable_pri(struct pci_dev *pdev, u32 reqs) if (WARN_ON(pdev->pri_enabled)) return -EBUSY; - pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PRI); - if (!pos) + if (!pri) return -EINVAL; - pci_read_config_word(pdev, pos + PCI_PRI_STATUS, &status); + pci_read_config_word(pdev, pri + PCI_PRI_STATUS, &status); if (!(status & PCI_PRI_STATUS_STOPPED)) return -EBUSY; - pci_read_config_dword(pdev, pos + PCI_PRI_MAX_REQ, &max_requests); + pci_read_config_dword(pdev, pri + PCI_PRI_MAX_REQ, &max_requests); reqs = min(max_requests, reqs); pdev->pri_reqs_alloc = reqs; - pci_write_config_dword(pdev, pos + PCI_PRI_ALLOC_REQ, reqs); + pci_write_config_dword(pdev, pri + PCI_PRI_ALLOC_REQ, reqs); control = PCI_PRI_CTRL_ENABLE; - pci_write_config_word(pdev, pos + PCI_PRI_CTRL, control); + pci_write_config_word(pdev, pri + PCI_PRI_CTRL, control); pdev->pri_enabled = 1; @@ -216,7 +220,7 @@ EXPORT_SYMBOL_GPL(pci_enable_pri); void pci_disable_pri(struct pci_dev *pdev) { u16 control; - int pos; + int pri = pdev->pri_cap; /* VFs share the PF PRI */ if (pdev->is_virtfn) @@ -225,13 +229,12 @@ void pci_disable_pri(struct pci_dev *pdev) if (WARN_ON(!pdev->pri_enabled)) return; - pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PRI); - if (!pos) + if (!pri) return; - pci_read_config_word(pdev, pos + PCI_PRI_CTRL, &control); + pci_read_config_word(pdev, pri + PCI_PRI_CTRL, &control); control &= ~PCI_PRI_CTRL_ENABLE; - pci_write_config_word(pdev, pos + PCI_PRI_CTRL, control); + pci_write_config_word(pdev, pri + PCI_PRI_CTRL, control); pdev->pri_enabled = 0; } @@ -245,7 +248,7 @@ void pci_restore_pri_state(struct pci_dev *pdev) { u16 control = PCI_PRI_CTRL_ENABLE; u32 reqs = pdev->pri_reqs_alloc; - int pos; + int pri = pdev->pri_cap; if (pdev->is_virtfn) return; @@ -253,12 +256,11 @@ void pci_restore_pri_state(struct pci_dev *pdev) if (!pdev->pri_enabled) return; - pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PRI); - if (!pos) + if (!pri) return; - pci_write_config_dword(pdev, pos + PCI_PRI_ALLOC_REQ, reqs); - pci_write_config_word(pdev, pos + PCI_PRI_CTRL, control); + pci_write_config_dword(pdev, pri + PCI_PRI_ALLOC_REQ, reqs); + pci_write_config_word(pdev, pri + PCI_PRI_CTRL, control); } EXPORT_SYMBOL_GPL(pci_restore_pri_state); @@ -272,7 +274,7 @@ EXPORT_SYMBOL_GPL(pci_restore_pri_state); int pci_reset_pri(struct pci_dev *pdev) { u16 control; - int pos; + int pri = pdev->pri_cap; if (pdev->is_virtfn) return 0; @@ -280,12 +282,11 @@ int pci_reset_pri(struct pci_dev *pdev) if (WARN_ON(pdev->pri_enabled)) return -EBUSY; - pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PRI); - if (!pos) + if (!pri) return -EINVAL; control = PCI_PRI_CTRL_RESET; - pci_write_config_word(pdev, pos + PCI_PRI_CTRL, control); + pci_write_config_word(pdev, pri + PCI_PRI_CTRL, control); return 0; } @@ -301,16 +302,16 @@ EXPORT_SYMBOL_GPL(pci_reset_pri); int pci_prg_resp_pasid_required(struct pci_dev *pdev) { u16 status; - int pos; + int pri; if (pdev->is_virtfn) pdev = pci_physfn(pdev); - pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PRI); - if (!pos) + pri = pdev->pri_cap; + if (!pri) return 0; - pci_read_config_word(pdev, pos + PCI_PRI_STATUS, &status); + pci_read_config_word(pdev, pri + PCI_PRI_STATUS, &status); if (status & PCI_PRI_STATUS_PASID) return 1; diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 3f6947ee3324..aa08cd35bf87 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -456,6 +456,12 @@ static inline void pci_ats_init(struct pci_dev *d) { } static inline void pci_restore_ats_state(struct pci_dev *dev) { } #endif /* CONFIG_PCI_ATS */ +#ifdef CONFIG_PCI_PRI +void pci_pri_init(struct pci_dev *dev); +#else +static inline void pci_pri_init(struct pci_dev *dev) { } +#endif + #ifdef CONFIG_PCI_IOV int pci_iov_init(struct pci_dev *dev); void pci_iov_release(struct pci_dev *dev); diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 3d5271a7a849..d145165c799c 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2324,6 +2324,9 @@ static void pci_init_capabilities(struct pci_dev *dev) /* Address Translation Services */ pci_ats_init(dev); + /* Page Request Interface */ + pci_pri_init(dev); + /* Enable ACS P2P upstream forwarding */ pci_enable_acs(dev); diff --git a/include/linux/pci.h b/include/linux/pci.h index c028883c8460..e7770d990c46 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -454,6 +454,7 @@ struct pci_dev { u8 ats_stu; /* ATS Smallest Translation Unit */ #endif #ifdef CONFIG_PCI_PRI + u16 pri_cap; /* PRI Capability offset */ u32 pri_reqs_alloc; /* Number of PRI requests allocated */ #endif #ifdef CONFIG_PCI_PASID -- cgit v1.2.3 From 751035b8dc061ae434c3311bac9cd6d0e5e00f94 Mon Sep 17 00:00:00 2001 From: Kuppuswamy Sathyanarayanan Date: Thu, 5 Sep 2019 14:31:46 -0500 Subject: PCI/ATS: Cache PASID Capability offset Previously each PASID interface searched for the PASID Capability. Cache the capability offset the first time we use it instead of searching each time. [bhelgaas: commit log, reorder patch to later, call pci_pasid_init() from pci_init_capabilities()] Link: https://lore.kernel.org/r/4957778959fa34eab3e8b3065d1951989c61cb0f.1567029860.git.sathyanarayanan.kuppuswamy@linux.intel.com Link: https://lore.kernel.org/r/20190905193146.90250-6-helgaas@kernel.org Signed-off-by: Kuppuswamy Sathyanarayanan Signed-off-by: Bjorn Helgaas --- drivers/pci/ats.c | 42 +++++++++++++++++++++--------------------- drivers/pci/pci.h | 6 ++++++ drivers/pci/probe.c | 3 +++ include/linux/pci.h | 1 + 4 files changed, 31 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/drivers/pci/ats.c b/drivers/pci/ats.c index c97e862b538a..d5ac808cae21 100644 --- a/drivers/pci/ats.c +++ b/drivers/pci/ats.c @@ -322,6 +322,11 @@ EXPORT_SYMBOL_GPL(pci_prg_resp_pasid_required); #endif /* CONFIG_PCI_PRI */ #ifdef CONFIG_PCI_PASID +void pci_pasid_init(struct pci_dev *pdev) +{ + pdev->pasid_cap = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PASID); +} + /** * pci_enable_pasid - Enable the PASID capability * @pdev: PCI device structure @@ -334,7 +339,7 @@ EXPORT_SYMBOL_GPL(pci_prg_resp_pasid_required); int pci_enable_pasid(struct pci_dev *pdev, int features) { u16 control, supported; - int pos; + int pasid = pdev->pasid_cap; /* * VFs must not implement the PASID Capability, but if a PF @@ -352,11 +357,10 @@ int pci_enable_pasid(struct pci_dev *pdev, int features) if (!pdev->eetlp_prefix_path) return -EINVAL; - pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PASID); - if (!pos) + if (!pasid) return -EINVAL; - pci_read_config_word(pdev, pos + PCI_PASID_CAP, &supported); + pci_read_config_word(pdev, pasid + PCI_PASID_CAP, &supported); supported &= PCI_PASID_CAP_EXEC | PCI_PASID_CAP_PRIV; /* User wants to enable anything unsupported? */ @@ -366,7 +370,7 @@ int pci_enable_pasid(struct pci_dev *pdev, int features) control = PCI_PASID_CTRL_ENABLE | features; pdev->pasid_features = features; - pci_write_config_word(pdev, pos + PCI_PASID_CTRL, control); + pci_write_config_word(pdev, pasid + PCI_PASID_CTRL, control); pdev->pasid_enabled = 1; @@ -381,7 +385,7 @@ EXPORT_SYMBOL_GPL(pci_enable_pasid); void pci_disable_pasid(struct pci_dev *pdev) { u16 control = 0; - int pos; + int pasid = pdev->pasid_cap; /* VFs share the PF PASID configuration */ if (pdev->is_virtfn) @@ -390,11 +394,10 @@ void pci_disable_pasid(struct pci_dev *pdev) if (WARN_ON(!pdev->pasid_enabled)) return; - pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PASID); - if (!pos) + if (!pasid) return; - pci_write_config_word(pdev, pos + PCI_PASID_CTRL, control); + pci_write_config_word(pdev, pasid + PCI_PASID_CTRL, control); pdev->pasid_enabled = 0; } @@ -407,7 +410,7 @@ EXPORT_SYMBOL_GPL(pci_disable_pasid); void pci_restore_pasid_state(struct pci_dev *pdev) { u16 control; - int pos; + int pasid = pdev->pasid_cap; if (pdev->is_virtfn) return; @@ -415,12 +418,11 @@ void pci_restore_pasid_state(struct pci_dev *pdev) if (!pdev->pasid_enabled) return; - pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PASID); - if (!pos) + if (!pasid) return; control = PCI_PASID_CTRL_ENABLE | pdev->pasid_features; - pci_write_config_word(pdev, pos + PCI_PASID_CTRL, control); + pci_write_config_word(pdev, pasid + PCI_PASID_CTRL, control); } EXPORT_SYMBOL_GPL(pci_restore_pasid_state); @@ -437,16 +439,15 @@ EXPORT_SYMBOL_GPL(pci_restore_pasid_state); int pci_pasid_features(struct pci_dev *pdev) { u16 supported; - int pos; + int pasid = pdev->pasid_cap; if (pdev->is_virtfn) pdev = pci_physfn(pdev); - pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PASID); - if (!pos) + if (!pasid) return -EINVAL; - pci_read_config_word(pdev, pos + PCI_PASID_CAP, &supported); + pci_read_config_word(pdev, pasid + PCI_PASID_CAP, &supported); supported &= PCI_PASID_CAP_EXEC | PCI_PASID_CAP_PRIV; @@ -466,16 +467,15 @@ EXPORT_SYMBOL_GPL(pci_pasid_features); int pci_max_pasids(struct pci_dev *pdev) { u16 supported; - int pos; + int pasid = pdev->pasid_cap; if (pdev->is_virtfn) pdev = pci_physfn(pdev); - pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PASID); - if (!pos) + if (!pasid) return -EINVAL; - pci_read_config_word(pdev, pos + PCI_PASID_CAP, &supported); + pci_read_config_word(pdev, pasid + PCI_PASID_CAP, &supported); supported = (supported & PASID_NUMBER_MASK) >> PASID_NUMBER_SHIFT; diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index aa08cd35bf87..ae84d28ba03a 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -462,6 +462,12 @@ void pci_pri_init(struct pci_dev *dev); static inline void pci_pri_init(struct pci_dev *dev) { } #endif +#ifdef CONFIG_PCI_PASID +void pci_pasid_init(struct pci_dev *dev); +#else +static inline void pci_pasid_init(struct pci_dev *dev) { } +#endif + #ifdef CONFIG_PCI_IOV int pci_iov_init(struct pci_dev *dev); void pci_iov_release(struct pci_dev *dev); diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index d145165c799c..df2b77866f3b 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2327,6 +2327,9 @@ static void pci_init_capabilities(struct pci_dev *dev) /* Page Request Interface */ pci_pri_init(dev); + /* Process Address Space ID */ + pci_pasid_init(dev); + /* Enable ACS P2P upstream forwarding */ pci_enable_acs(dev); diff --git a/include/linux/pci.h b/include/linux/pci.h index e7770d990c46..6542100bd2dd 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -458,6 +458,7 @@ struct pci_dev { u32 pri_reqs_alloc; /* Number of PRI requests allocated */ #endif #ifdef CONFIG_PCI_PASID + u16 pasid_cap; /* PASID Capability offset */ u16 pasid_features; #endif #ifdef CONFIG_PCI_P2PDMA -- cgit v1.2.3 From e5adf79a1d8086aefa56f48eeb08f8fe4e054a3d Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Wed, 9 Oct 2019 16:07:51 -0500 Subject: PCI/ATS: Cache PRI PRG Response PASID Required bit The PRG Response PASID Required bit in the PRI Capability is read-only. Read it once when we enumerate the device and cache the value so we don't need to read it again. Based-on-patch-by: Kuppuswamy Sathyanarayanan Signed-off-by: Bjorn Helgaas --- drivers/pci/ats.c | 23 ++++++++++------------- include/linux/pci.h | 1 + 2 files changed, 11 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/drivers/pci/ats.c b/drivers/pci/ats.c index d5ac808cae21..76ae518d55f4 100644 --- a/drivers/pci/ats.c +++ b/drivers/pci/ats.c @@ -161,7 +161,16 @@ EXPORT_SYMBOL_GPL(pci_ats_page_aligned); #ifdef CONFIG_PCI_PRI void pci_pri_init(struct pci_dev *pdev) { + u16 status; + pdev->pri_cap = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PRI); + + if (!pdev->pri_cap) + return; + + pci_read_config_word(pdev, pdev->pri_cap + PCI_PRI_STATUS, &status); + if (status & PCI_PRI_STATUS_PASID) + pdev->pasid_required = 1; } /** @@ -301,22 +310,10 @@ EXPORT_SYMBOL_GPL(pci_reset_pri); */ int pci_prg_resp_pasid_required(struct pci_dev *pdev) { - u16 status; - int pri; - if (pdev->is_virtfn) pdev = pci_physfn(pdev); - pri = pdev->pri_cap; - if (!pri) - return 0; - - pci_read_config_word(pdev, pri + PCI_PRI_STATUS, &status); - - if (status & PCI_PRI_STATUS_PASID) - return 1; - - return 0; + return pdev->pasid_required; } EXPORT_SYMBOL_GPL(pci_prg_resp_pasid_required); #endif /* CONFIG_PCI_PRI */ diff --git a/include/linux/pci.h b/include/linux/pci.h index 6542100bd2dd..64d35e730fab 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -456,6 +456,7 @@ struct pci_dev { #ifdef CONFIG_PCI_PRI u16 pri_cap; /* PRI Capability offset */ u32 pri_reqs_alloc; /* Number of PRI requests allocated */ + unsigned int pasid_required:1; /* PRG Response PASID Required */ #endif #ifdef CONFIG_PCI_PASID u16 pasid_cap; /* PASID Capability offset */ -- cgit v1.2.3 From b24d5c2098596a41cf187af41287777a2e0dd753 Mon Sep 17 00:00:00 2001 From: Krzysztof Wilczynski Date: Sat, 14 Sep 2019 23:30:32 +0200 Subject: PCI/ATS: Consolidate ATS declarations in linux/pci-ats.h Move ATS function prototypes from include/linux/pci.h to include/linux/pci-ats.h as the ATS, PRI, and PASID interfaces are related and are used only by the IOMMU drivers. This effectively reverts ff9bee895c4d ("PCI: Move ATS declarations to linux/pci.h so they're all together"). Also, remove surplus forward declaration of struct pci_ats from include/linux/pci.h, as it is no longer needed, since struct pci_ats was embedded directly into struct pci_dev by d544d75ac96a ("PCI: Embed ATS info directly into struct pci_dev"). No functional changes intended. Link: https://lore.kernel.org/r/20190914213032.22314-1-kw@linux.com Signed-off-by: Krzysztof Wilczynski Signed-off-by: Bjorn Helgaas --- include/linux/pci-ats.h | 75 ++++++++++++++++++------------------------------- include/linux/pci.h | 14 --------- 2 files changed, 28 insertions(+), 61 deletions(-) (limited to 'include') diff --git a/include/linux/pci-ats.h b/include/linux/pci-ats.h index a7a2b3d94fcc..67de3a9499bb 100644 --- a/include/linux/pci-ats.h +++ b/include/linux/pci-ats.h @@ -4,73 +4,54 @@ #include -#ifdef CONFIG_PCI_PRI +#ifdef CONFIG_PCI_ATS +/* Address Translation Service */ +int pci_enable_ats(struct pci_dev *dev, int ps); +void pci_disable_ats(struct pci_dev *dev); +int pci_ats_queue_depth(struct pci_dev *dev); +int pci_ats_page_aligned(struct pci_dev *dev); +#else /* CONFIG_PCI_ATS */ +static inline int pci_enable_ats(struct pci_dev *d, int ps) +{ return -ENODEV; } +static inline void pci_disable_ats(struct pci_dev *d) { } +static inline int pci_ats_queue_depth(struct pci_dev *d) +{ return -ENODEV; } +static inline int pci_ats_page_aligned(struct pci_dev *dev) +{ return 0; } +#endif /* CONFIG_PCI_ATS */ +#ifdef CONFIG_PCI_PRI int pci_enable_pri(struct pci_dev *pdev, u32 reqs); void pci_disable_pri(struct pci_dev *pdev); void pci_restore_pri_state(struct pci_dev *pdev); int pci_reset_pri(struct pci_dev *pdev); int pci_prg_resp_pasid_required(struct pci_dev *pdev); - #else /* CONFIG_PCI_PRI */ - static inline int pci_enable_pri(struct pci_dev *pdev, u32 reqs) -{ - return -ENODEV; -} - -static inline void pci_disable_pri(struct pci_dev *pdev) -{ -} - -static inline void pci_restore_pri_state(struct pci_dev *pdev) -{ -} - +{ return -ENODEV; } +static inline void pci_disable_pri(struct pci_dev *pdev) { } +static inline void pci_restore_pri_state(struct pci_dev *pdev) { } static inline int pci_reset_pri(struct pci_dev *pdev) -{ - return -ENODEV; -} - +{ return -ENODEV; } static inline int pci_prg_resp_pasid_required(struct pci_dev *pdev) -{ - return 0; -} +{ return 0; } #endif /* CONFIG_PCI_PRI */ #ifdef CONFIG_PCI_PASID - int pci_enable_pasid(struct pci_dev *pdev, int features); void pci_disable_pasid(struct pci_dev *pdev); void pci_restore_pasid_state(struct pci_dev *pdev); int pci_pasid_features(struct pci_dev *pdev); int pci_max_pasids(struct pci_dev *pdev); - -#else /* CONFIG_PCI_PASID */ - +#else /* CONFIG_PCI_PASID */ static inline int pci_enable_pasid(struct pci_dev *pdev, int features) -{ - return -EINVAL; -} - -static inline void pci_disable_pasid(struct pci_dev *pdev) -{ -} - -static inline void pci_restore_pasid_state(struct pci_dev *pdev) -{ -} - +{ return -EINVAL; } +static inline void pci_disable_pasid(struct pci_dev *pdev) { } +static inline void pci_restore_pasid_state(struct pci_dev *pdev) { } static inline int pci_pasid_features(struct pci_dev *pdev) -{ - return -EINVAL; -} - +{ return -EINVAL; } static inline int pci_max_pasids(struct pci_dev *pdev) -{ - return -EINVAL; -} +{ return -EINVAL; } #endif /* CONFIG_PCI_PASID */ - -#endif /* LINUX_PCI_ATS_H*/ +#endif /* LINUX_PCI_ATS_H */ diff --git a/include/linux/pci.h b/include/linux/pci.h index 64d35e730fab..9fc22f48055e 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -284,7 +284,6 @@ struct irq_affinity; struct pcie_link_state; struct pci_vpd; struct pci_sriov; -struct pci_ats; struct pci_p2pdma; /* The pci_dev structure describes PCI devices */ @@ -1778,19 +1777,6 @@ pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs, NULL); } -#ifdef CONFIG_PCI_ATS -/* Address Translation Service */ -int pci_enable_ats(struct pci_dev *dev, int ps); -void pci_disable_ats(struct pci_dev *dev); -int pci_ats_queue_depth(struct pci_dev *dev); -int pci_ats_page_aligned(struct pci_dev *dev); -#else -static inline int pci_enable_ats(struct pci_dev *d, int ps) { return -ENODEV; } -static inline void pci_disable_ats(struct pci_dev *d) { } -static inline int pci_ats_queue_depth(struct pci_dev *d) { return -ENODEV; } -static inline int pci_ats_page_aligned(struct pci_dev *dev) { return 0; } -#endif - /* Include architecture-dependent settings and functions */ #include -- cgit v1.2.3 From c6e9aefbf9db818d60818aa5540d78c1da289aae Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Wed, 9 Oct 2019 16:27:30 -0500 Subject: PCI/ATS: Remove unused PRI and PASID stubs The following functions are only used by amd_iommu.c and intel-iommu.c (when CONFIG_INTEL_IOMMU_SVM is enabled). CONFIG_PCI_PRI and CONFIG_PCI_PASID are always defined in those cases, so there's no need for the stubs. pci_enable_pri() pci_disable_pri() pci_reset_pri() pci_prg_resp_pasid_required() pci_enable_pasid() pci_disable_pasid() Remove the unused stubs. Signed-off-by: Bjorn Helgaas Reviewed-by: Kuppuswamy Sathyanarayanan Reviewed-by: Joerg Roedel --- include/linux/pci-ats.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include') diff --git a/include/linux/pci-ats.h b/include/linux/pci-ats.h index 67de3a9499bb..963c11f7c56b 100644 --- a/include/linux/pci-ats.h +++ b/include/linux/pci-ats.h @@ -27,14 +27,7 @@ void pci_restore_pri_state(struct pci_dev *pdev); int pci_reset_pri(struct pci_dev *pdev); int pci_prg_resp_pasid_required(struct pci_dev *pdev); #else /* CONFIG_PCI_PRI */ -static inline int pci_enable_pri(struct pci_dev *pdev, u32 reqs) -{ return -ENODEV; } -static inline void pci_disable_pri(struct pci_dev *pdev) { } static inline void pci_restore_pri_state(struct pci_dev *pdev) { } -static inline int pci_reset_pri(struct pci_dev *pdev) -{ return -ENODEV; } -static inline int pci_prg_resp_pasid_required(struct pci_dev *pdev) -{ return 0; } #endif /* CONFIG_PCI_PRI */ #ifdef CONFIG_PCI_PASID @@ -44,9 +37,6 @@ void pci_restore_pasid_state(struct pci_dev *pdev); int pci_pasid_features(struct pci_dev *pdev); int pci_max_pasids(struct pci_dev *pdev); #else /* CONFIG_PCI_PASID */ -static inline int pci_enable_pasid(struct pci_dev *pdev, int features) -{ return -EINVAL; } -static inline void pci_disable_pasid(struct pci_dev *pdev) { } static inline void pci_restore_pasid_state(struct pci_dev *pdev) { } static inline int pci_pasid_features(struct pci_dev *pdev) { return -EINVAL; } -- cgit v1.2.3 From fef2dd8b3966517172514ea5a89104ba7745678b Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Wed, 9 Oct 2019 16:47:15 -0500 Subject: PCI/ATS: Make pci_restore_pri_state(), pci_restore_pasid_state() private These interfaces: void pci_restore_pri_state(struct pci_dev *pdev); void pci_restore_pasid_state(struct pci_dev *pdev); are only used in drivers/pci and do not need to be seen by the rest of the kernel. Most them to drivers/pci/pci.h so they're private to the PCI subsystem. Signed-off-by: Bjorn Helgaas Reviewed-by: Joerg Roedel --- drivers/pci/pci.h | 4 ++++ include/linux/pci-ats.h | 5 ----- 2 files changed, 4 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index ae84d28ba03a..e6b46d2b9846 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -458,14 +458,18 @@ static inline void pci_restore_ats_state(struct pci_dev *dev) { } #ifdef CONFIG_PCI_PRI void pci_pri_init(struct pci_dev *dev); +void pci_restore_pri_state(struct pci_dev *pdev); #else static inline void pci_pri_init(struct pci_dev *dev) { } +static inline void pci_restore_pri_state(struct pci_dev *pdev) { } #endif #ifdef CONFIG_PCI_PASID void pci_pasid_init(struct pci_dev *dev); +void pci_restore_pasid_state(struct pci_dev *pdev); #else static inline void pci_pasid_init(struct pci_dev *dev) { } +static inline void pci_restore_pasid_state(struct pci_dev *pdev) { } #endif #ifdef CONFIG_PCI_IOV diff --git a/include/linux/pci-ats.h b/include/linux/pci-ats.h index 963c11f7c56b..5d62e78946a3 100644 --- a/include/linux/pci-ats.h +++ b/include/linux/pci-ats.h @@ -23,21 +23,16 @@ static inline int pci_ats_page_aligned(struct pci_dev *dev) #ifdef CONFIG_PCI_PRI int pci_enable_pri(struct pci_dev *pdev, u32 reqs); void pci_disable_pri(struct pci_dev *pdev); -void pci_restore_pri_state(struct pci_dev *pdev); int pci_reset_pri(struct pci_dev *pdev); int pci_prg_resp_pasid_required(struct pci_dev *pdev); -#else /* CONFIG_PCI_PRI */ -static inline void pci_restore_pri_state(struct pci_dev *pdev) { } #endif /* CONFIG_PCI_PRI */ #ifdef CONFIG_PCI_PASID int pci_enable_pasid(struct pci_dev *pdev, int features); void pci_disable_pasid(struct pci_dev *pdev); -void pci_restore_pasid_state(struct pci_dev *pdev); int pci_pasid_features(struct pci_dev *pdev); int pci_max_pasids(struct pci_dev *pdev); #else /* CONFIG_PCI_PASID */ -static inline void pci_restore_pasid_state(struct pci_dev *pdev) { } static inline int pci_pasid_features(struct pci_dev *pdev) { return -EINVAL; } static inline int pci_max_pasids(struct pci_dev *pdev) -- cgit v1.2.3 From 299b610117a4145dfe15963f0ea037ab319ce531 Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Mon, 14 Oct 2019 23:46:21 +0200 Subject: rtc: ds1685: add indirect access method and remove plat_read/plat_write SGI Octane (IP30) doesn't have RTC register directly mapped into CPU address space, but accesses RTC registers with an address and data register. This is now supported by additional access functions, which are selected by a new field in platform data. Removed plat_read/plat_write since there is no user and their usage could introduce lifetime issue, when functions are placed in different modules. Signed-off-by: Thomas Bogendoerfer Acked-by: Joshua Kinard Reviewed-by: Joshua Kinard Link: https://lore.kernel.org/r/20191014214621.25257-1-tbogendoerfer@suse.de Signed-off-by: Alexandre Belloni --- arch/mips/sgi-ip32/ip32-platform.c | 2 +- drivers/rtc/rtc-ds1685.c | 78 +++++++++++++++++++++++++------------- include/linux/rtc/ds1685.h | 8 ++-- 3 files changed, 58 insertions(+), 30 deletions(-) (limited to 'include') diff --git a/arch/mips/sgi-ip32/ip32-platform.c b/arch/mips/sgi-ip32/ip32-platform.c index 5a2a82148d8d..c3909bd8dd1a 100644 --- a/arch/mips/sgi-ip32/ip32-platform.c +++ b/arch/mips/sgi-ip32/ip32-platform.c @@ -115,7 +115,7 @@ ip32_rtc_platform_data[] = { .bcd_mode = true, .no_irq = false, .uie_unsupported = false, - .alloc_io_resources = true, + .access_type = ds1685_reg_direct, .plat_prepare_poweroff = ip32_prepare_poweroff, }, }; diff --git a/drivers/rtc/rtc-ds1685.c b/drivers/rtc/rtc-ds1685.c index 349a8d1caca1..98d06b3ee913 100644 --- a/drivers/rtc/rtc-ds1685.c +++ b/drivers/rtc/rtc-ds1685.c @@ -31,7 +31,10 @@ /* ----------------------------------------------------------------------- */ -/* Standard read/write functions if platform does not provide overrides */ +/* + * Standard read/write + * all registers are mapped in CPU address space + */ /** * ds1685_read - read a value from an rtc register. @@ -59,6 +62,35 @@ ds1685_write(struct ds1685_priv *rtc, int reg, u8 value) } /* ----------------------------------------------------------------------- */ +/* + * Indirect read/write functions + * access happens via address and data register mapped in CPU address space + */ + +/** + * ds1685_indirect_read - read a value from an rtc register. + * @rtc: pointer to the ds1685 rtc structure. + * @reg: the register address to read. + */ +static u8 +ds1685_indirect_read(struct ds1685_priv *rtc, int reg) +{ + writeb(reg, rtc->regs); + return readb(rtc->data); +} + +/** + * ds1685_indirect_write - write a value to an rtc register. + * @rtc: pointer to the ds1685 rtc structure. + * @reg: the register address to write. + * @value: value to write to the register. + */ +static void +ds1685_indirect_write(struct ds1685_priv *rtc, int reg, u8 value) +{ + writeb(reg, rtc->regs); + writeb(value, rtc->data); +} /* ----------------------------------------------------------------------- */ /* Inlined functions */ @@ -1062,42 +1094,36 @@ ds1685_rtc_probe(struct platform_device *pdev) if (!rtc) return -ENOMEM; - /* - * Allocate/setup any IORESOURCE_MEM resources, if required. Not all - * platforms put the RTC in an easy-access place. Like the SGI Octane, - * which attaches the RTC to a "ByteBus", hooked to a SuperIO chip - * that sits behind the IOC3 PCI metadevice. - */ - if (pdata->alloc_io_resources) { + /* Setup resources and access functions */ + switch (pdata->access_type) { + case ds1685_reg_direct: + rtc->regs = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(rtc->regs)) + return PTR_ERR(rtc->regs); + rtc->read = ds1685_read; + rtc->write = ds1685_write; + break; + case ds1685_reg_indirect: rtc->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(rtc->regs)) return PTR_ERR(rtc->regs); + rtc->data = devm_platform_ioremap_resource(pdev, 1); + if (IS_ERR(rtc->data)) + return PTR_ERR(rtc->data); + rtc->read = ds1685_indirect_read; + rtc->write = ds1685_indirect_write; + break; } + if (!rtc->read || !rtc->write) + return -ENXIO; + /* Get the register step size. */ if (pdata->regstep > 0) rtc->regstep = pdata->regstep; else rtc->regstep = 1; - /* Platform read function, else default if mmio setup */ - if (pdata->plat_read) - rtc->read = pdata->plat_read; - else - if (pdata->alloc_io_resources) - rtc->read = ds1685_read; - else - return -ENXIO; - - /* Platform write function, else default if mmio setup */ - if (pdata->plat_write) - rtc->write = pdata->plat_write; - else - if (pdata->alloc_io_resources) - rtc->write = ds1685_write; - else - return -ENXIO; - /* Platform pre-shutdown function, if defined. */ if (pdata->plat_prepare_poweroff) rtc->prepare_poweroff = pdata->plat_prepare_poweroff; diff --git a/include/linux/rtc/ds1685.h b/include/linux/rtc/ds1685.h index 101c7adc05a2..67ee9d20cc5a 100644 --- a/include/linux/rtc/ds1685.h +++ b/include/linux/rtc/ds1685.h @@ -42,6 +42,7 @@ struct ds1685_priv { struct rtc_device *dev; void __iomem *regs; + void __iomem *data; u32 regstep; int irq_num; bool bcd_mode; @@ -70,12 +71,13 @@ struct ds1685_rtc_platform_data { const bool bcd_mode; const bool no_irq; const bool uie_unsupported; - const bool alloc_io_resources; - u8 (*plat_read)(struct ds1685_priv *, int); - void (*plat_write)(struct ds1685_priv *, int, u8); void (*plat_prepare_poweroff)(void); void (*plat_wake_alarm)(void); void (*plat_post_ram_clear)(void); + enum { + ds1685_reg_direct, + ds1685_reg_indirect + } access_type; }; -- cgit v1.2.3 From e502ff8606b32df4f9f2435ab00278312db125b3 Mon Sep 17 00:00:00 2001 From: Tejas Patel Date: Mon, 26 Aug 2019 13:30:44 -0700 Subject: soc: xilinx: Set CAP_UNUSABLE requirement for versal while powering down domain For "0" requirement which is used to inform firmware that device is not required currently by master, Versal PLM (Platform Loader and Manager) which runs on Platform Management Controller and is responsible platform management of devices that disables clock, power it down and reset the device. genpd_power_off() is being called during runtime suspend also. So, if any device goes to runtime suspend state during resumes it needs to be re-initialized again. It is possible that drivers do not reinitialize device upon resume from runtime suspend every time ans so dont want it to be powered down or get reset during runtime suspend. In Versal PLM new PM_CAP_UNUSABLE capability is added, which disables clock only and avoids power down and reset during runtime suspend. Power and reset will be gated with core suspend.So, this patch sets CAPABILITY_UNUSABLE requirement during gpd_power_off() if platform is other than zynqmp. Signed-off-by: Tejas Patel Signed-off-by: Jolly Shah Signed-off-by: Michal Simek --- drivers/soc/xilinx/zynqmp_pm_domains.c | 10 ++++++++-- include/linux/firmware/xlnx-zynqmp.h | 3 ++- 2 files changed, 10 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/soc/xilinx/zynqmp_pm_domains.c b/drivers/soc/xilinx/zynqmp_pm_domains.c index 600f57cf0c2e..23d90cb12ba9 100644 --- a/drivers/soc/xilinx/zynqmp_pm_domains.c +++ b/drivers/soc/xilinx/zynqmp_pm_domains.c @@ -2,7 +2,7 @@ /* * ZynqMP Generic PM domain support * - * Copyright (C) 2015-2018 Xilinx, Inc. + * Copyright (C) 2015-2019 Xilinx, Inc. * * Davorin Mista * Jolly Shah @@ -25,6 +25,8 @@ static const struct zynqmp_eemi_ops *eemi_ops; +static int min_capability; + /** * struct zynqmp_pm_domain - Wrapper around struct generic_pm_domain * @gpd: Generic power domain @@ -106,7 +108,7 @@ static int zynqmp_gpd_power_off(struct generic_pm_domain *domain) int ret; struct pm_domain_data *pdd, *tmp; struct zynqmp_pm_domain *pd; - u32 capabilities = 0; + u32 capabilities = min_capability; bool may_wakeup; if (!eemi_ops->set_requirement) @@ -283,6 +285,10 @@ static int zynqmp_gpd_probe(struct platform_device *pdev) if (!domains) return -ENOMEM; + if (!of_device_is_compatible(dev->parent->of_node, + "xlnx,zynqmp-firmware")) + min_capability = ZYNQMP_PM_CAPABILITY_UNUSABLE; + for (i = 0; i < ZYNQMP_NUM_DOMAINS; i++, pd++) { pd->node_id = 0; pd->gpd.name = kasprintf(GFP_KERNEL, "domain%d", i); diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 778abbbc7d94..adb14bcedca2 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -2,7 +2,7 @@ /* * Xilinx Zynq MPSoC Firmware layer * - * Copyright (C) 2014-2018 Xilinx + * Copyright (C) 2014-2019 Xilinx * * Michal Simek * Davorin Mista @@ -46,6 +46,7 @@ #define ZYNQMP_PM_CAPABILITY_ACCESS 0x1U #define ZYNQMP_PM_CAPABILITY_CONTEXT 0x2U #define ZYNQMP_PM_CAPABILITY_WAKEUP 0x4U +#define ZYNQMP_PM_CAPABILITY_UNUSABLE 0x8U /* * Firmware FPGA Manager flags -- cgit v1.2.3 From 9905f32aefbe3d9cb2d24c3bd9c882397eaf3842 Mon Sep 17 00:00:00 2001 From: Stefan-Gabriel Mirea Date: Wed, 16 Oct 2019 15:48:25 +0300 Subject: serial: fsl_linflexuart: Be consistent with the name For consistency reasons, spell the controller name as "LINFlexD" in comments and documentation. Signed-off-by: Stefan-Gabriel Mirea Link: https://lore.kernel.org/r/1571230107-8493-4-git-send-email-stefan-gabriel.mirea@nxp.com Signed-off-by: Greg Kroah-Hartman --- Documentation/admin-guide/kernel-parameters.txt | 2 +- drivers/tty/serial/Kconfig | 8 ++++---- drivers/tty/serial/fsl_linflexuart.c | 4 ++-- include/uapi/linux/serial_core.h | 2 +- 4 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index a84a83f8881e..6dbd871493af 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1101,7 +1101,7 @@ mapped with the correct attributes. linflex, - Use early console provided by Freescale LinFlex UART + Use early console provided by Freescale LINFlexD UART serial driver for NXP S32V234 SoCs. A valid base address must be provided, and the serial port must already be setup and configured. diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig index 67a9eb3f94ce..c07c2667a2e4 100644 --- a/drivers/tty/serial/Kconfig +++ b/drivers/tty/serial/Kconfig @@ -1392,19 +1392,19 @@ config SERIAL_FSL_LPUART_CONSOLE you can make it the console by answering Y to this option. config SERIAL_FSL_LINFLEXUART - tristate "Freescale linflexuart serial port support" + tristate "Freescale LINFlexD UART serial port support" depends on PRINTK select SERIAL_CORE help - Support for the on-chip linflexuart on some Freescale SOCs. + Support for the on-chip LINFlexD UART on some Freescale SOCs. config SERIAL_FSL_LINFLEXUART_CONSOLE - bool "Console on Freescale linflexuart serial port" + bool "Console on Freescale LINFlexD UART serial port" depends on SERIAL_FSL_LINFLEXUART=y select SERIAL_CORE_CONSOLE select SERIAL_EARLYCON help - If you have enabled the linflexuart serial port on the Freescale + If you have enabled the LINFlexD UART serial port on the Freescale SoCs, you can make it the console by answering Y to this option. config SERIAL_CONEXANT_DIGICOLOR diff --git a/drivers/tty/serial/fsl_linflexuart.c b/drivers/tty/serial/fsl_linflexuart.c index a32f0d2afd59..205c31a61684 100644 --- a/drivers/tty/serial/fsl_linflexuart.c +++ b/drivers/tty/serial/fsl_linflexuart.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Freescale linflexuart serial port driver + * Freescale LINFlexD UART serial port driver * * Copyright 2012-2016 Freescale Semiconductor, Inc. * Copyright 2017-2019 NXP @@ -940,5 +940,5 @@ static void __exit linflex_serial_exit(void) module_init(linflex_serial_init); module_exit(linflex_serial_exit); -MODULE_DESCRIPTION("Freescale linflex serial port driver"); +MODULE_DESCRIPTION("Freescale LINFlexD serial port driver"); MODULE_LICENSE("GPL v2"); diff --git a/include/uapi/linux/serial_core.h b/include/uapi/linux/serial_core.h index e7fe550b6038..8ec3dd742ea4 100644 --- a/include/uapi/linux/serial_core.h +++ b/include/uapi/linux/serial_core.h @@ -290,7 +290,7 @@ /* Sunix UART */ #define PORT_SUNIX 121 -/* Freescale Linflex UART */ +/* Freescale LINFlexD UART */ #define PORT_LINFLEXUART 122 #endif /* _UAPILINUX_SERIAL_CORE_H */ -- cgit v1.2.3 From d083ce427947bbf10358e4c12bf20f288ee6b3df Mon Sep 17 00:00:00 2001 From: Johan Jonker Date: Tue, 15 Oct 2019 22:58:52 +0200 Subject: include: dt-bindings: rockchip: mark RK_FUNC defines as deprecated The defines RK_FUNC_1, RK_FUNC_2, RK_FUNC_3 and RK_FUNC_4 are no longer used. Mark them as "deprecated" to prevent that someone start using them again. Signed-off-by: Johan Jonker Link: https://lore.kernel.org/r/20191015205852.4200-2-jbx6244@gmail.com Signed-off-by: Heiko Stuebner --- include/dt-bindings/pinctrl/rockchip.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/dt-bindings/pinctrl/rockchip.h b/include/dt-bindings/pinctrl/rockchip.h index dc5c1c73d030..6d6bac1c26d7 100644 --- a/include/dt-bindings/pinctrl/rockchip.h +++ b/include/dt-bindings/pinctrl/rockchip.h @@ -50,9 +50,9 @@ #define RK_PD7 31 #define RK_FUNC_GPIO 0 -#define RK_FUNC_1 1 -#define RK_FUNC_2 2 -#define RK_FUNC_3 3 -#define RK_FUNC_4 4 +#define RK_FUNC_1 1 /* deprecated */ +#define RK_FUNC_2 2 /* deprecated */ +#define RK_FUNC_3 3 /* deprecated */ +#define RK_FUNC_4 4 /* deprecated */ #endif -- cgit v1.2.3 From 32adcaa010fa85e09296a6a606ad07348ef349ed Mon Sep 17 00:00:00 2001 From: Lubomir Rintel Date: Thu, 8 Aug 2019 15:47:24 +0200 Subject: ARM: mmp: move cputype.h to include/linux/soc/ Let's move cputype.h away from mach-mmp/ so that the drivers outside that directory are able to tell the precise silicon revision. The MMP3 USB OTG PHY driver needs this. Signed-off-by: Lubomir Rintel --- MAINTAINERS | 1 + arch/arm/mach-mmp/common.c | 2 +- arch/arm/mach-mmp/cputype.h | 85 ----------------------------------------- arch/arm/mach-mmp/devices.c | 2 +- arch/arm/mach-mmp/mmp2.c | 2 +- arch/arm/mach-mmp/pm-mmp2.c | 2 +- arch/arm/mach-mmp/pm-pxa910.c | 2 +- arch/arm/mach-mmp/pxa168.c | 2 +- arch/arm/mach-mmp/pxa910.c | 2 +- arch/arm/mach-mmp/time.c | 2 +- include/Kbuild | 1 + include/linux/soc/mmp/cputype.h | 85 +++++++++++++++++++++++++++++++++++++++++ 12 files changed, 95 insertions(+), 93 deletions(-) delete mode 100644 arch/arm/mach-mmp/cputype.h create mode 100644 include/linux/soc/mmp/cputype.h (limited to 'include') diff --git a/MAINTAINERS b/MAINTAINERS index 296de2b51c83..85f64ade294d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10908,6 +10908,7 @@ L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Odd Fixes F: arch/arm/boot/dts/mmp* F: arch/arm/mach-mmp/ +F: linux/soc/mmp/ MMU GATHER AND TLB INVALIDATION M: Will Deacon diff --git a/arch/arm/mach-mmp/common.c b/arch/arm/mach-mmp/common.c index 24c689a01ecb..e94349d4726c 100644 --- a/arch/arm/mach-mmp/common.c +++ b/arch/arm/mach-mmp/common.c @@ -13,7 +13,7 @@ #include #include #include "addr-map.h" -#include "cputype.h" +#include #include "common.h" diff --git a/arch/arm/mach-mmp/cputype.h b/arch/arm/mach-mmp/cputype.h deleted file mode 100644 index c3ec88983e94..000000000000 --- a/arch/arm/mach-mmp/cputype.h +++ /dev/null @@ -1,85 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __ASM_MACH_CPUTYPE_H -#define __ASM_MACH_CPUTYPE_H - -#include - -/* - * CPU Stepping CPU_ID CHIP_ID - * - * PXA168 S0 0x56158400 0x0000C910 - * PXA168 A0 0x56158400 0x00A0A168 - * PXA910 Y1 0x56158400 0x00F2C920 - * PXA910 A0 0x56158400 0x00F2C910 - * PXA910 A1 0x56158400 0x00A0C910 - * PXA920 Y0 0x56158400 0x00F2C920 - * PXA920 A0 0x56158400 0x00A0C920 - * PXA920 A1 0x56158400 0x00A1C920 - * MMP2 Z0 0x560f5811 0x00F00410 - * MMP2 Z1 0x560f5811 0x00E00410 - * MMP2 A0 0x560f5811 0x00A0A610 - * MMP3 A0 0x562f5842 0x00A02128 - * MMP3 B0 0x562f5842 0x00B02128 - */ - -extern unsigned int mmp_chip_id; - -#ifdef CONFIG_CPU_PXA168 -static inline int cpu_is_pxa168(void) -{ - return (((read_cpuid_id() >> 8) & 0xff) == 0x84) && - ((mmp_chip_id & 0xfff) == 0x168); -} -#else -#define cpu_is_pxa168() (0) -#endif - -/* cpu_is_pxa910() is shared on both pxa910 and pxa920 */ -#ifdef CONFIG_CPU_PXA910 -static inline int cpu_is_pxa910(void) -{ - return (((read_cpuid_id() >> 8) & 0xff) == 0x84) && - (((mmp_chip_id & 0xfff) == 0x910) || - ((mmp_chip_id & 0xfff) == 0x920)); -} -#else -#define cpu_is_pxa910() (0) -#endif - -#if defined(CONFIG_CPU_MMP2) || defined(CONFIG_MACH_MMP2_DT) -static inline int cpu_is_mmp2(void) -{ - return (((read_cpuid_id() >> 8) & 0xff) == 0x58) && - (((mmp_chip_id & 0xfff) == 0x410) || - ((mmp_chip_id & 0xfff) == 0x610)); -} -#else -#define cpu_is_mmp2() (0) -#endif - -#ifdef CONFIG_MACH_MMP3_DT -static inline int cpu_is_mmp3(void) -{ - return (((read_cpuid_id() >> 8) & 0xff) == 0x58) && - ((mmp_chip_id & 0xffff) == 0x2128); -} - -static inline int cpu_is_mmp3_a0(void) -{ - return (cpu_is_mmp3() && - ((mmp_chip_id & 0x00ff0000) == 0x00a00000)); -} - -static inline int cpu_is_mmp3_b0(void) -{ - return (cpu_is_mmp3() && - ((mmp_chip_id & 0x00ff0000) == 0x00b00000)); -} - -#else -#define cpu_is_mmp3() (0) -#define cpu_is_mmp3_a0() (0) -#define cpu_is_mmp3_b0() (0) -#endif - -#endif /* __ASM_MACH_CPUTYPE_H */ diff --git a/arch/arm/mach-mmp/devices.c b/arch/arm/mach-mmp/devices.c index 130c1a603ba2..18bee66a671f 100644 --- a/arch/arm/mach-mmp/devices.c +++ b/arch/arm/mach-mmp/devices.c @@ -11,7 +11,7 @@ #include #include "irqs.h" #include "devices.h" -#include "cputype.h" +#include #include "regs-usb.h" int __init pxa_register_device(struct pxa_device_desc *desc, diff --git a/arch/arm/mach-mmp/mmp2.c b/arch/arm/mach-mmp/mmp2.c index 18ea3e1a26e6..bbc4c2274de3 100644 --- a/arch/arm/mach-mmp/mmp2.c +++ b/arch/arm/mach-mmp/mmp2.c @@ -20,7 +20,7 @@ #include #include "addr-map.h" #include "regs-apbc.h" -#include "cputype.h" +#include #include "irqs.h" #include "mfp.h" #include "devices.h" diff --git a/arch/arm/mach-mmp/pm-mmp2.c b/arch/arm/mach-mmp/pm-mmp2.c index 2923dd5732a6..2d86381e152d 100644 --- a/arch/arm/mach-mmp/pm-mmp2.c +++ b/arch/arm/mach-mmp/pm-mmp2.c @@ -17,7 +17,7 @@ #include #include -#include "cputype.h" +#include #include "addr-map.h" #include "pm-mmp2.h" #include "regs-icu.h" diff --git a/arch/arm/mach-mmp/pm-pxa910.c b/arch/arm/mach-mmp/pm-pxa910.c index 58535ce206dc..69ebe18ff209 100644 --- a/arch/arm/mach-mmp/pm-pxa910.c +++ b/arch/arm/mach-mmp/pm-pxa910.c @@ -18,7 +18,7 @@ #include #include -#include "cputype.h" +#include #include "addr-map.h" #include "pm-pxa910.h" #include "regs-icu.h" diff --git a/arch/arm/mach-mmp/pxa168.c b/arch/arm/mach-mmp/pxa168.c index 6e0277488967..b642e900727a 100644 --- a/arch/arm/mach-mmp/pxa168.c +++ b/arch/arm/mach-mmp/pxa168.c @@ -21,7 +21,7 @@ #include "addr-map.h" #include "clock.h" #include "common.h" -#include "cputype.h" +#include #include "devices.h" #include "irqs.h" #include "mfp.h" diff --git a/arch/arm/mach-mmp/pxa910.c b/arch/arm/mach-mmp/pxa910.c index cba31c758dea..b19a069d9fab 100644 --- a/arch/arm/mach-mmp/pxa910.c +++ b/arch/arm/mach-mmp/pxa910.c @@ -18,7 +18,7 @@ #include #include "addr-map.h" #include "regs-apbc.h" -#include "cputype.h" +#include #include "irqs.h" #include "mfp.h" #include "devices.h" diff --git a/arch/arm/mach-mmp/time.c b/arch/arm/mach-mmp/time.c index 8f4cacbf640e..110dcb3314d1 100644 --- a/arch/arm/mach-mmp/time.c +++ b/arch/arm/mach-mmp/time.c @@ -33,7 +33,7 @@ #include "regs-timers.h" #include "regs-apbc.h" #include "irqs.h" -#include "cputype.h" +#include #include "clock.h" #define TIMERS_VIRT_BASE TIMERS1_VIRT_BASE diff --git a/include/Kbuild b/include/Kbuild index ffba79483cc5..5a01ab62f61e 100644 --- a/include/Kbuild +++ b/include/Kbuild @@ -633,6 +633,7 @@ header-test- += linux/soc/amlogic/meson-canvas.h header-test- += linux/soc/brcmstb/brcmstb.h header-test- += linux/soc/ixp4xx/npe.h header-test- += linux/soc/mediatek/infracfg.h +header-test- += linux/soc/mmp/cputype.h header-test- += linux/soc/qcom/smd-rpm.h header-test- += linux/soc/qcom/smem.h header-test- += linux/soc/qcom/smem_state.h diff --git a/include/linux/soc/mmp/cputype.h b/include/linux/soc/mmp/cputype.h new file mode 100644 index 000000000000..c3ec88983e94 --- /dev/null +++ b/include/linux/soc/mmp/cputype.h @@ -0,0 +1,85 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_MACH_CPUTYPE_H +#define __ASM_MACH_CPUTYPE_H + +#include + +/* + * CPU Stepping CPU_ID CHIP_ID + * + * PXA168 S0 0x56158400 0x0000C910 + * PXA168 A0 0x56158400 0x00A0A168 + * PXA910 Y1 0x56158400 0x00F2C920 + * PXA910 A0 0x56158400 0x00F2C910 + * PXA910 A1 0x56158400 0x00A0C910 + * PXA920 Y0 0x56158400 0x00F2C920 + * PXA920 A0 0x56158400 0x00A0C920 + * PXA920 A1 0x56158400 0x00A1C920 + * MMP2 Z0 0x560f5811 0x00F00410 + * MMP2 Z1 0x560f5811 0x00E00410 + * MMP2 A0 0x560f5811 0x00A0A610 + * MMP3 A0 0x562f5842 0x00A02128 + * MMP3 B0 0x562f5842 0x00B02128 + */ + +extern unsigned int mmp_chip_id; + +#ifdef CONFIG_CPU_PXA168 +static inline int cpu_is_pxa168(void) +{ + return (((read_cpuid_id() >> 8) & 0xff) == 0x84) && + ((mmp_chip_id & 0xfff) == 0x168); +} +#else +#define cpu_is_pxa168() (0) +#endif + +/* cpu_is_pxa910() is shared on both pxa910 and pxa920 */ +#ifdef CONFIG_CPU_PXA910 +static inline int cpu_is_pxa910(void) +{ + return (((read_cpuid_id() >> 8) & 0xff) == 0x84) && + (((mmp_chip_id & 0xfff) == 0x910) || + ((mmp_chip_id & 0xfff) == 0x920)); +} +#else +#define cpu_is_pxa910() (0) +#endif + +#if defined(CONFIG_CPU_MMP2) || defined(CONFIG_MACH_MMP2_DT) +static inline int cpu_is_mmp2(void) +{ + return (((read_cpuid_id() >> 8) & 0xff) == 0x58) && + (((mmp_chip_id & 0xfff) == 0x410) || + ((mmp_chip_id & 0xfff) == 0x610)); +} +#else +#define cpu_is_mmp2() (0) +#endif + +#ifdef CONFIG_MACH_MMP3_DT +static inline int cpu_is_mmp3(void) +{ + return (((read_cpuid_id() >> 8) & 0xff) == 0x58) && + ((mmp_chip_id & 0xffff) == 0x2128); +} + +static inline int cpu_is_mmp3_a0(void) +{ + return (cpu_is_mmp3() && + ((mmp_chip_id & 0x00ff0000) == 0x00a00000)); +} + +static inline int cpu_is_mmp3_b0(void) +{ + return (cpu_is_mmp3() && + ((mmp_chip_id & 0x00ff0000) == 0x00b00000)); +} + +#else +#define cpu_is_mmp3() (0) +#define cpu_is_mmp3_a0() (0) +#define cpu_is_mmp3_b0() (0) +#endif + +#endif /* __ASM_MACH_CPUTYPE_H */ -- cgit v1.2.3 From 825dbc6ff7a3a063ea91be7d94af940080b0c991 Mon Sep 17 00:00:00 2001 From: Ben Dooks Date: Tue, 15 Oct 2019 11:26:15 +0100 Subject: percpu: add __percpu to SHIFT_PERCPU_PTR The SHIFT_PERCPU_PTR() returns a pointer used by a number of functions that expect the pointer to be __percpu annotated (sparse address space 3). Adding __percpu to this makes the following sparse warnings go away. Note, this then creates the problem the __percup is marked as noderef, which may need removing for some of the internal functions, or to remove other warnings. mm/vmstat.c:385:13: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:385:13: expected signed char [noderef] [usertype] *__p mm/vmstat.c:385:13: got signed char * mm/vmstat.c:385:13: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:385:13: expected signed char [noderef] [usertype] *__p mm/vmstat.c:385:13: got signed char * mm/vmstat.c:385:13: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:385:13: expected signed char [noderef] [usertype] *__p mm/vmstat.c:385:13: got signed char * mm/vmstat.c:385:13: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:385:13: expected signed char [noderef] [usertype] *__p mm/vmstat.c:385:13: got signed char * mm/vmstat.c:401:13: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:401:13: expected signed char [noderef] [usertype] *__p mm/vmstat.c:401:13: got signed char * mm/vmstat.c:401:13: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:401:13: expected signed char [noderef] [usertype] *__p mm/vmstat.c:401:13: got signed char * mm/vmstat.c:401:13: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:401:13: expected signed char [noderef] [usertype] *__p mm/vmstat.c:401:13: got signed char * mm/vmstat.c:401:13: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:401:13: expected signed char [noderef] [usertype] *__p mm/vmstat.c:401:13: got signed char * mm/vmstat.c:429:13: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:429:13: expected signed char [noderef] [usertype] *__p mm/vmstat.c:429:13: got signed char * mm/vmstat.c:429:13: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:429:13: expected signed char [noderef] [usertype] *__p mm/vmstat.c:429:13: got signed char * mm/vmstat.c:429:13: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:429:13: expected signed char [noderef] [usertype] *__p mm/vmstat.c:429:13: got signed char * mm/vmstat.c:429:13: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:429:13: expected signed char [noderef] [usertype] *__p mm/vmstat.c:429:13: got signed char * mm/vmstat.c:445:13: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:445:13: expected signed char [noderef] [usertype] *__p mm/vmstat.c:445:13: got signed char * mm/vmstat.c:445:13: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:445:13: expected signed char [noderef] [usertype] *__p mm/vmstat.c:445:13: got signed char * mm/vmstat.c:445:13: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:445:13: expected signed char [noderef] [usertype] *__p mm/vmstat.c:445:13: got signed char * mm/vmstat.c:445:13: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:445:13: expected signed char [noderef] [usertype] *__p mm/vmstat.c:445:13: got signed char * mm/vmstat.c:763:29: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:763:29: expected signed char [noderef] *__p mm/vmstat.c:763:29: got signed char * mm/vmstat.c:763:29: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:763:29: expected signed char [noderef] *__p mm/vmstat.c:763:29: got signed char * mm/vmstat.c:763:29: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:763:29: expected signed char [noderef] *__p mm/vmstat.c:763:29: got signed char * mm/vmstat.c:763:29: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:763:29: expected signed char [noderef] *__p mm/vmstat.c:763:29: got signed char * mm/vmstat.c:825:29: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:825:29: expected signed char [noderef] *__p mm/vmstat.c:825:29: got signed char * mm/vmstat.c:825:29: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:825:29: expected signed char [noderef] *__p mm/vmstat.c:825:29: got signed char * mm/vmstat.c:825:29: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:825:29: expected signed char [noderef] *__p mm/vmstat.c:825:29: got signed char * mm/vmstat.c:825:29: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:825:29: expected signed char [noderef] *__p mm/vmstat.c:825:29: got signed char * Signed-off-by: Ben Dooks Signed-off-by: Dennis Zhou --- include/linux/percpu-defs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index a6fabd865211..a49b6c702598 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -229,7 +229,7 @@ do { \ * pointer value. The weird cast keeps both GCC and sparse happy. */ #define SHIFT_PERCPU_PTR(__p, __offset) \ - RELOC_HIDE((typeof(*(__p)) __kernel __force *)(__p), (__offset)) + RELOC_HIDE((typeof(*(__p)) __kernel __percpu __force *)(__p), (__offset)) #define per_cpu_ptr(ptr, cpu) \ ({ \ -- cgit v1.2.3 From af65d1ad416bc6e069ccb9e649faeda224248f96 Mon Sep 17 00:00:00 2001 From: "Patel, Mayurkumar" Date: Fri, 18 Oct 2019 16:52:21 +0000 Subject: PCI/AER: Save AER Capability for suspend/resume Previously we did not save and restore the AER configuration on suspend/resume, so the configuration may be lost after resume. Save the AER configuration during suspend and restore it during resume. [bhelgaas: commit log] Link: https://lore.kernel.org/r/92EBB4272BF81E4089A7126EC1E7B28492C3B007@IRSMSX101.ger.corp.intel.com Signed-off-by: Mayurkumar Patel Signed-off-by: Kuppuswamy Sathyanarayanan Signed-off-by: Bjorn Helgaas Reviewed-by: Andy Shevchenko --- drivers/pci/access.c | 2 +- drivers/pci/pci.c | 2 ++ drivers/pci/pci.h | 1 + drivers/pci/pcie/aer.c | 62 ++++++++++++++++++++++++++++++++++++++++++++++++-- include/linux/aer.h | 4 ++++ 5 files changed, 68 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/pci/access.c b/drivers/pci/access.c index 2fccb5762c76..79c4a2ef269a 100644 --- a/drivers/pci/access.c +++ b/drivers/pci/access.c @@ -355,7 +355,7 @@ static inline bool pcie_cap_has_sltctl(const struct pci_dev *dev) pcie_caps_reg(dev) & PCI_EXP_FLAGS_SLOT; } -static inline bool pcie_cap_has_rtctl(const struct pci_dev *dev) +bool pcie_cap_has_rtctl(const struct pci_dev *dev) { int type = pci_pcie_type(dev); diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index e7982af9a5d8..d02636540ca1 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1361,6 +1361,7 @@ int pci_save_state(struct pci_dev *dev) pci_save_ltr_state(dev); pci_save_dpc_state(dev); + pci_save_aer_state(dev); return pci_save_vc_state(dev); } EXPORT_SYMBOL(pci_save_state); @@ -1474,6 +1475,7 @@ void pci_restore_state(struct pci_dev *dev) pci_restore_dpc_state(dev); pci_cleanup_aer_error_status_regs(dev); + pci_restore_aer_state(dev); pci_restore_config_space(dev); diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 3f6947ee3324..b96988f90315 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -12,6 +12,7 @@ extern const unsigned char pcie_link_speed[]; extern bool pci_early_dump; bool pcie_cap_has_lnkctl(const struct pci_dev *dev); +bool pcie_cap_has_rtctl(const struct pci_dev *dev); /* Functions internal to the PCI core code */ diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c index b45bc47d04fe..443512882be4 100644 --- a/drivers/pci/pcie/aer.c +++ b/drivers/pci/pcie/aer.c @@ -448,12 +448,70 @@ int pci_cleanup_aer_error_status_regs(struct pci_dev *dev) return 0; } +void pci_save_aer_state(struct pci_dev *dev) +{ + struct pci_cap_saved_state *save_state; + u32 *cap; + int pos; + + pos = dev->aer_cap; + if (!pos) + return; + + save_state = pci_find_saved_ext_cap(dev, PCI_EXT_CAP_ID_ERR); + if (!save_state) + return; + + cap = &save_state->cap.data[0]; + pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_MASK, cap++); + pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, cap++); + pci_read_config_dword(dev, pos + PCI_ERR_COR_MASK, cap++); + pci_read_config_dword(dev, pos + PCI_ERR_CAP, cap++); + if (pcie_cap_has_rtctl(dev)) + pci_read_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, cap++); +} + +void pci_restore_aer_state(struct pci_dev *dev) +{ + struct pci_cap_saved_state *save_state; + u32 *cap; + int pos; + + pos = dev->aer_cap; + if (!pos) + return; + + save_state = pci_find_saved_ext_cap(dev, PCI_EXT_CAP_ID_ERR); + if (!save_state) + return; + + cap = &save_state->cap.data[0]; + pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_MASK, *cap++); + pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, *cap++); + pci_write_config_dword(dev, pos + PCI_ERR_COR_MASK, *cap++); + pci_write_config_dword(dev, pos + PCI_ERR_CAP, *cap++); + if (pcie_cap_has_rtctl(dev)) + pci_write_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, *cap++); +} + void pci_aer_init(struct pci_dev *dev) { + int n; + dev->aer_cap = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR); + if (!dev->aer_cap) + return; - if (dev->aer_cap) - dev->aer_stats = kzalloc(sizeof(struct aer_stats), GFP_KERNEL); + dev->aer_stats = kzalloc(sizeof(struct aer_stats), GFP_KERNEL); + + /* + * We save/restore PCI_ERR_UNCOR_MASK, PCI_ERR_UNCOR_SEVER, + * PCI_ERR_COR_MASK, and PCI_ERR_CAP. Root and Root Complex Event + * Collectors also implement PCI_ERR_ROOT_COMMAND (PCIe r5.0, sec + * 7.8.4). + */ + n = pcie_cap_has_rtctl(dev) ? 5 : 4; + pci_add_ext_cap_save_buffer(dev, PCI_EXT_CAP_ID_ERR, sizeof(u32) * n); pci_cleanup_aer_error_status_regs(dev); } diff --git a/include/linux/aer.h b/include/linux/aer.h index 514bffa11dbb..fa19e01f418a 100644 --- a/include/linux/aer.h +++ b/include/linux/aer.h @@ -46,6 +46,8 @@ int pci_enable_pcie_error_reporting(struct pci_dev *dev); int pci_disable_pcie_error_reporting(struct pci_dev *dev); int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev); int pci_cleanup_aer_error_status_regs(struct pci_dev *dev); +void pci_save_aer_state(struct pci_dev *dev); +void pci_restore_aer_state(struct pci_dev *dev); #else static inline int pci_enable_pcie_error_reporting(struct pci_dev *dev) { @@ -63,6 +65,8 @@ static inline int pci_cleanup_aer_error_status_regs(struct pci_dev *dev) { return -EINVAL; } +static inline void pci_save_aer_state(struct pci_dev *dev) {} +static inline void pci_restore_aer_state(struct pci_dev *dev) {} #endif void cper_print_aer(struct pci_dev *dev, int aer_severity, -- cgit v1.2.3 From 8d6ac1cec7251a74c2d2f21e72b842c000206811 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Wed, 16 Oct 2019 22:16:22 +0200 Subject: rtc: add timestamp for end of 2199 Some RTCs handle date up to 2199. Link: https://lore.kernel.org/r/20191016201626.31309-1-alexandre.belloni@bootlin.com Signed-off-by: Alexandre Belloni --- include/linux/rtc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 2680f9b2b119..e86a9f307b82 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -165,6 +165,7 @@ struct rtc_device { #define RTC_TIMESTAMP_BEGIN_2000 946684800LL /* 2000-01-01 00:00:00 */ #define RTC_TIMESTAMP_END_2063 2966371199LL /* 2063-12-31 23:59:59 */ #define RTC_TIMESTAMP_END_2099 4102444799LL /* 2099-12-31 23:59:59 */ +#define RTC_TIMESTAMP_END_2199 7258118399LL /* 2199-12-31 23:59:59 */ #define RTC_TIMESTAMP_END_9999 253402300799LL /* 9999-12-31 23:59:59 */ extern struct rtc_device *devm_rtc_device_register(struct device *dev, -- cgit v1.2.3 From ae4866884338259318be94fa8f88015cced07000 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Sat, 19 Oct 2019 22:50:34 +0200 Subject: rtc: introduce lock helpers Introduce rtc_lock and rtc_unlock to shorten the code when locking and unlocking ops_lock from drivers. Link: https://lore.kernel.org/r/20191019205034.6382-1-alexandre.belloni@bootlin.com Signed-off-by: Alexandre Belloni --- include/linux/rtc.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/rtc.h b/include/linux/rtc.h index e86a9f307b82..4e9d3c71addb 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -159,6 +159,9 @@ struct rtc_device { }; #define to_rtc_device(d) container_of(d, struct rtc_device, dev) +#define rtc_lock(d) mutex_lock(&d->ops_lock) +#define rtc_unlock(d) mutex_unlock(&d->ops_lock) + /* useful timestamps */ #define RTC_TIMESTAMP_BEGIN_0000 -62167219200ULL /* 0000-01-01 00:00:00 */ #define RTC_TIMESTAMP_BEGIN_1900 -2208988800LL /* 1900-01-01 00:00:00 */ -- cgit v1.2.3 From 27938fd8ba78b4c7f9a2385b7b52cca19ab891b8 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Fri, 4 Oct 2019 15:32:07 +0200 Subject: pwm: Update comment on struct pwm_ops::apply MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 71523d1812ac (pwm: Ensure pwm_apply_state() doesn't modify the state argument) updated the kernel-doc for pwm_apply_state(), but not for the ->apply callback in the pwm_ops struct. Signed-off-by: Rasmus Villemoes Reviewed-by: Uwe Kleine-König Reviewed-by: Bjorn Andersson Signed-off-by: Thierry Reding --- include/linux/pwm.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/pwm.h b/include/linux/pwm.h index b2c9c460947d..0ef808d925bb 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -243,10 +243,7 @@ pwm_set_relative_duty_cycle(struct pwm_state *state, unsigned int duty_cycle, * @request: optional hook for requesting a PWM * @free: optional hook for freeing a PWM * @capture: capture and report PWM signal - * @apply: atomically apply a new PWM config. The state argument - * should be adjusted with the real hardware config (if the - * approximate the period or duty_cycle value, state should - * reflect it) + * @apply: atomically apply a new PWM config * @get_state: get the current PWM state. This function is only * called once per PWM device when the PWM chip is * registered. -- cgit v1.2.3 From 8e53622594f5530b5a86094464937dda47fc6e3b Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Wed, 16 Oct 2019 12:42:40 +0200 Subject: pwm: stm32: Remove clutter from ternary operator Remove usage of the ternary operator to assign values for register fields. Instead, parameterize the register and field offset macros and pass the index to them. This removes clutter and improves readability. Signed-off-by: Thierry Reding --- drivers/pwm/pwm-stm32.c | 21 +++++++++------------ include/linux/mfd/stm32-timers.h | 12 ++++-------- 2 files changed, 13 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/drivers/pwm/pwm-stm32.c b/drivers/pwm/pwm-stm32.c index c5f51a33ee1b..7a2be0453824 100644 --- a/drivers/pwm/pwm-stm32.c +++ b/drivers/pwm/pwm-stm32.c @@ -493,20 +493,17 @@ static const struct pwm_ops stm32pwm_ops = { static int stm32_pwm_set_breakinput(struct stm32_pwm *priv, int index, int level, int filter) { - u32 bke = (index == 0) ? TIM_BDTR_BKE : TIM_BDTR_BK2E; - int shift = (index == 0) ? TIM_BDTR_BKF_SHIFT : TIM_BDTR_BK2F_SHIFT; - u32 mask = (index == 0) ? TIM_BDTR_BKE | TIM_BDTR_BKP | TIM_BDTR_BKF - : TIM_BDTR_BK2E | TIM_BDTR_BK2P | TIM_BDTR_BK2F; - u32 bdtr = bke; + u32 shift = TIM_BDTR_BKF_SHIFT(index); + u32 bke = TIM_BDTR_BKE(index); + u32 bkp = TIM_BDTR_BKP(index); + u32 bkf = TIM_BDTR_BKF(index); + u32 mask = bkf | bkp | bke; + u32 bdtr; - /* - * The both bits could be set since only one will be wrote - * due to mask value. - */ - if (level) - bdtr |= TIM_BDTR_BKP | TIM_BDTR_BK2P; + bdtr = (filter & TIM_BDTR_BKF_MASK) << shift | bke; - bdtr |= (filter & TIM_BDTR_BKF_MASK) << shift; + if (level) + bdtr |= bkp; regmap_update_bits(priv->regmap, TIM_BDTR, mask, bdtr); diff --git a/include/linux/mfd/stm32-timers.h b/include/linux/mfd/stm32-timers.h index 067d14655c28..f8db83aedb2b 100644 --- a/include/linux/mfd/stm32-timers.h +++ b/include/linux/mfd/stm32-timers.h @@ -70,14 +70,11 @@ #define TIM_CCER_CC4E BIT(12) /* Capt/Comp 4 out Ena */ #define TIM_CCER_CC4P BIT(13) /* Capt/Comp 4 Polarity */ #define TIM_CCER_CCXE (BIT(0) | BIT(4) | BIT(8) | BIT(12)) -#define TIM_BDTR_BKE BIT(12) /* Break input enable */ -#define TIM_BDTR_BKP BIT(13) /* Break input polarity */ +#define TIM_BDTR_BKE(x) BIT(12 + (x) * 12) /* Break input enable */ +#define TIM_BDTR_BKP(x) BIT(13 + (x) * 12) /* Break input polarity */ #define TIM_BDTR_AOE BIT(14) /* Automatic Output Enable */ #define TIM_BDTR_MOE BIT(15) /* Main Output Enable */ -#define TIM_BDTR_BKF (BIT(16) | BIT(17) | BIT(18) | BIT(19)) -#define TIM_BDTR_BK2F (BIT(20) | BIT(21) | BIT(22) | BIT(23)) -#define TIM_BDTR_BK2E BIT(24) /* Break 2 input enable */ -#define TIM_BDTR_BK2P BIT(25) /* Break 2 input polarity */ +#define TIM_BDTR_BKF(x) (0xf << (16 + (x) * 4)) #define TIM_DCR_DBA GENMASK(4, 0) /* DMA base addr */ #define TIM_DCR_DBL GENMASK(12, 8) /* DMA burst len */ @@ -87,8 +84,7 @@ #define TIM_CR2_MMS2_SHIFT 20 #define TIM_SMCR_TS_SHIFT 4 #define TIM_BDTR_BKF_MASK 0xF -#define TIM_BDTR_BKF_SHIFT 16 -#define TIM_BDTR_BK2F_SHIFT 20 +#define TIM_BDTR_BKF_SHIFT(x) (16 + (x) * 4) enum stm32_timers_dmas { STM32_TIMERS_DMA_CH1, -- cgit v1.2.3 From a362687404edc5d73a4fc281af3b2b1542ef194e Mon Sep 17 00:00:00 2001 From: Olof Johansson Date: Mon, 21 Oct 2019 18:52:24 -0700 Subject: soc: mmp: guard include of asm/cputype.h with CONFIG_ARM{,64} Since this driver is enabled for COMPILE_TEST, it avoids build error on x86 allmodconfig: In file included from /build/drivers/phy/marvell/phy-mmp3-usb.c:12: /build/include/linux/soc/mmp/cputype.h:5:10: fatal error: asm/cputype.h: No such file or directory Link: https://lore.kernel.org/r/20191022015658.14624-1-olof@lixom.net Signed-off-by: Olof Johansson --- include/linux/soc/mmp/cputype.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/soc/mmp/cputype.h b/include/linux/soc/mmp/cputype.h index c3ec88983e94..221790761e8e 100644 --- a/include/linux/soc/mmp/cputype.h +++ b/include/linux/soc/mmp/cputype.h @@ -2,7 +2,9 @@ #ifndef __ASM_MACH_CPUTYPE_H #define __ASM_MACH_CPUTYPE_H +#if defined(CONFIG_ARM) || defined(CONFIG_ARM64) #include +#endif /* * CPU Stepping CPU_ID CHIP_ID -- cgit v1.2.3 From 771fdcf8d3d04e77ae0f0dc1018144206a61d216 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Wed, 16 Oct 2019 16:57:53 +0200 Subject: PM / OPP: Support adjusting OPP voltages at runtime On some SoCs the Adaptive Voltage Scaling (AVS) technique is employed to optimize the operating voltage of a device. At a given frequency, the hardware monitors dynamic factors and either makes a suggestion for how much to adjust a voltage for the current frequency, or it automatically adjusts the voltage without software intervention. Add an API to the OPP library for the former case, so that AVS type devices can update the voltages for an OPP when the hardware determines the voltage should change. The assumption is that drivers like CPUfreq or devfreq will register for the OPP notifiers and adjust the voltage according to suggestions that AVS makes. This patch is derived from [1] submitted by Stephen. [1] https://lore.kernel.org/patchwork/patch/599279/ Signed-off-by: Stephen Boyd Signed-off-by: Roger Lu [s.nawrocki@samsung.com: added handling of OPP min/max voltage] Signed-off-by: Sylwester Nawrocki Signed-off-by: Viresh Kumar --- drivers/opp/core.c | 69 ++++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/pm_opp.h | 13 ++++++++++ 2 files changed, 82 insertions(+) (limited to 'include') diff --git a/drivers/opp/core.c b/drivers/opp/core.c index 3b7ffd0234e9..f38b3be85072 100644 --- a/drivers/opp/core.c +++ b/drivers/opp/core.c @@ -2112,6 +2112,75 @@ put_table: return r; } +/** + * dev_pm_opp_adjust_voltage() - helper to change the voltage of an OPP + * @dev: device for which we do this operation + * @freq: OPP frequency to adjust voltage of + * @u_volt: new OPP target voltage + * @u_volt_min: new OPP min voltage + * @u_volt_max: new OPP max voltage + * + * Return: -EINVAL for bad pointers, -ENOMEM if no memory available for the + * copy operation, returns 0 if no modifcation was done OR modification was + * successful. + */ +int dev_pm_opp_adjust_voltage(struct device *dev, unsigned long freq, + unsigned long u_volt, unsigned long u_volt_min, + unsigned long u_volt_max) + +{ + struct opp_table *opp_table; + struct dev_pm_opp *tmp_opp, *opp = ERR_PTR(-ENODEV); + int r = 0; + + /* Find the opp_table */ + opp_table = _find_opp_table(dev); + if (IS_ERR(opp_table)) { + r = PTR_ERR(opp_table); + dev_warn(dev, "%s: Device OPP not found (%d)\n", __func__, r); + return r; + } + + mutex_lock(&opp_table->lock); + + /* Do we have the frequency? */ + list_for_each_entry(tmp_opp, &opp_table->opp_list, node) { + if (tmp_opp->rate == freq) { + opp = tmp_opp; + break; + } + } + + if (IS_ERR(opp)) { + r = PTR_ERR(opp); + goto adjust_unlock; + } + + /* Is update really needed? */ + if (opp->supplies->u_volt == u_volt) + goto adjust_unlock; + + opp->supplies->u_volt = u_volt; + opp->supplies->u_volt_min = u_volt_min; + opp->supplies->u_volt_max = u_volt_max; + + dev_pm_opp_get(opp); + mutex_unlock(&opp_table->lock); + + /* Notify the voltage change of the OPP */ + blocking_notifier_call_chain(&opp_table->head, OPP_EVENT_ADJUST_VOLTAGE, + opp); + + dev_pm_opp_put(opp); + goto adjust_put_table; + +adjust_unlock: + mutex_unlock(&opp_table->lock); +adjust_put_table: + dev_pm_opp_put_opp_table(opp_table); + return r; +} + /** * dev_pm_opp_enable() - Enable a specific OPP * @dev: device for which we do this operation diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index b8197ab014f2..747861816f4f 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -22,6 +22,7 @@ struct opp_table; enum dev_pm_opp_event { OPP_EVENT_ADD, OPP_EVENT_REMOVE, OPP_EVENT_ENABLE, OPP_EVENT_DISABLE, + OPP_EVENT_ADJUST_VOLTAGE, }; /** @@ -113,6 +114,10 @@ int dev_pm_opp_add(struct device *dev, unsigned long freq, void dev_pm_opp_remove(struct device *dev, unsigned long freq); void dev_pm_opp_remove_all_dynamic(struct device *dev); +int dev_pm_opp_adjust_voltage(struct device *dev, unsigned long freq, + unsigned long u_volt, unsigned long u_volt_min, + unsigned long u_volt_max); + int dev_pm_opp_enable(struct device *dev, unsigned long freq); int dev_pm_opp_disable(struct device *dev, unsigned long freq); @@ -242,6 +247,14 @@ static inline void dev_pm_opp_remove_all_dynamic(struct device *dev) { } +static inline int +dev_pm_opp_adjust_voltage(struct device *dev, unsigned long freq, + unsigned long u_volt, unsigned long u_volt_min, + unsigned long u_volt_max) +{ + return 0; +} + static inline int dev_pm_opp_enable(struct device *dev, unsigned long freq) { return 0; -- cgit v1.2.3 From a48108c0c20f02485b8cc3ca83652a55a0f5e47f Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Tue, 22 Oct 2019 16:51:37 +0200 Subject: reset: improve of_xlate documentation Mention of_reset_simple_xlate as the default if of_xlate is not set. Signed-off-by: Philipp Zabel --- drivers/reset/core.c | 6 ++++-- include/linux/reset-controller.h | 3 ++- 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/reset/core.c b/drivers/reset/core.c index 2badff33a0db..329c78599a02 100644 --- a/drivers/reset/core.c +++ b/drivers/reset/core.c @@ -78,8 +78,10 @@ static const char *rcdev_name(struct reset_controller_dev *rcdev) * @reset_spec: reset line specifier as found in the device tree * @flags: a flags pointer to fill in (optional) * - * This simple translation function should be used for reset controllers - * with 1:1 mapping, where reset lines can be indexed by number without gaps. + * This static translation function is used by default if of_xlate in + * :c:type:`reset_controller_dev` is not set. It is useful for all reset + * controllers with 1:1 mapping, where reset lines can be indexed by number + * without gaps. */ static int of_reset_simple_xlate(struct reset_controller_dev *rcdev, const struct of_phandle_args *reset_spec) diff --git a/include/linux/reset-controller.h b/include/linux/reset-controller.h index 9326d671b6e6..8d35753d419e 100644 --- a/include/linux/reset-controller.h +++ b/include/linux/reset-controller.h @@ -62,7 +62,8 @@ struct reset_control_lookup { * @of_node: corresponding device tree node as phandle target * @of_reset_n_cells: number of cells in reset line specifiers * @of_xlate: translation function to translate from specifier as found in the - * device tree to id as given to the reset control ops + * device tree to id as given to the reset control ops, defaults + * to :c:func:`of_reset_simple_xlate`. * @nr_resets: number of reset controls in this reset controller device */ struct reset_controller_dev { -- cgit v1.2.3 From c2ffa00ad6152ad54940f942fc316b9c83d5e6f9 Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Tue, 22 Oct 2019 16:53:25 +0200 Subject: reset: document (devm_)reset_control_get_optional variants Add kerneldoc comments for the optional reset_control_get variants. Signed-off-by: Philipp Zabel --- include/linux/reset.h | 46 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 46 insertions(+) (limited to 'include') diff --git a/include/linux/reset.h b/include/linux/reset.h index e7793fc0fa93..bf7c7f188406 100644 --- a/include/linux/reset.h +++ b/include/linux/reset.h @@ -203,12 +203,34 @@ static inline struct reset_control *reset_control_get_shared( return __reset_control_get(dev, id, 0, true, false, false); } +/** + * reset_control_get_optional_exclusive - optional reset_control_get_exclusive() + * @dev: device to be reset by the controller + * @id: reset line name + * + * Optional variant of reset_control_get_exclusive(). If the requested reset + * is not specified in the device tree, this function returns NULL instead of + * an error. + * + * See reset_control_get_exclusive() for more information. + */ static inline struct reset_control *reset_control_get_optional_exclusive( struct device *dev, const char *id) { return __reset_control_get(dev, id, 0, false, true, true); } +/** + * reset_control_get_optional_shared - optional reset_control_get_shared() + * @dev: device to be reset by the controller + * @id: reset line name + * + * Optional variant of reset_control_get_shared(). If the requested reset + * is not specified in the device tree, this function returns NULL instead of + * an error. + * + * See reset_control_get_shared() for more information. + */ static inline struct reset_control *reset_control_get_optional_shared( struct device *dev, const char *id) { @@ -354,12 +376,36 @@ static inline struct reset_control *devm_reset_control_get_shared( return __devm_reset_control_get(dev, id, 0, true, false, false); } +/** + * devm_reset_control_get_optional_exclusive - resource managed + * reset_control_get_optional_exclusive() + * @dev: device to be reset by the controller + * @id: reset line name + * + * Managed reset_control_get_optional_exclusive(). For reset controllers + * returned from this function, reset_control_put() is called automatically on + * driver detach. + * + * See reset_control_get_optional_exclusive() for more information. + */ static inline struct reset_control *devm_reset_control_get_optional_exclusive( struct device *dev, const char *id) { return __devm_reset_control_get(dev, id, 0, false, true, true); } +/** + * devm_reset_control_get_optional_shared - resource managed + * reset_control_get_optional_shared() + * @dev: device to be reset by the controller + * @id: reset line name + * + * Managed reset_control_get_optional_shared(). For reset controllers returned + * from this function, reset_control_put() is called automatically on driver + * detach. + * + * See reset_control_get_optional_shared() for more information. + */ static inline struct reset_control *devm_reset_control_get_optional_shared( struct device *dev, const char *id) { -- cgit v1.2.3 From bf7ca707ae60045342e145c88a83bbe00f66775f Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 9 Oct 2019 12:58:14 -0400 Subject: SUNRPC: Add trace points to observe transport congestion control To help debug problems with RPC/RDMA credit management, replace dprintk() call sites in the transport send lock paths with trace events. Similar trace points are defined for the non-congestion paths. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/trace/events/sunrpc.h | 93 +++++++++++++++++++++++++++++++++++++++++++ net/sunrpc/xprt.c | 22 +++++----- 2 files changed, 106 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index ffa3c51dbb1a..378233fe5ac7 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -777,6 +777,99 @@ TRACE_EVENT(xprt_ping, __get_str(addr), __get_str(port), __entry->status) ); +DECLARE_EVENT_CLASS(xprt_writelock_event, + TP_PROTO( + const struct rpc_xprt *xprt, const struct rpc_task *task + ), + + TP_ARGS(xprt, task), + + TP_STRUCT__entry( + __field(unsigned int, task_id) + __field(unsigned int, client_id) + __field(unsigned int, snd_task_id) + ), + + TP_fast_assign( + if (task) { + __entry->task_id = task->tk_pid; + __entry->client_id = task->tk_client ? + task->tk_client->cl_clid : -1; + } else { + __entry->task_id = -1; + __entry->client_id = -1; + } + __entry->snd_task_id = xprt->snd_task ? + xprt->snd_task->tk_pid : -1; + ), + + TP_printk("task:%u@%u snd_task:%u", + __entry->task_id, __entry->client_id, + __entry->snd_task_id) +); + +#define DEFINE_WRITELOCK_EVENT(name) \ + DEFINE_EVENT(xprt_writelock_event, xprt_##name, \ + TP_PROTO( \ + const struct rpc_xprt *xprt, \ + const struct rpc_task *task \ + ), \ + TP_ARGS(xprt, task)) + +DEFINE_WRITELOCK_EVENT(reserve_xprt); +DEFINE_WRITELOCK_EVENT(release_xprt); + +DECLARE_EVENT_CLASS(xprt_cong_event, + TP_PROTO( + const struct rpc_xprt *xprt, const struct rpc_task *task + ), + + TP_ARGS(xprt, task), + + TP_STRUCT__entry( + __field(unsigned int, task_id) + __field(unsigned int, client_id) + __field(unsigned int, snd_task_id) + __field(unsigned long, cong) + __field(unsigned long, cwnd) + __field(bool, wait) + ), + + TP_fast_assign( + if (task) { + __entry->task_id = task->tk_pid; + __entry->client_id = task->tk_client ? + task->tk_client->cl_clid : -1; + } else { + __entry->task_id = -1; + __entry->client_id = -1; + } + __entry->snd_task_id = xprt->snd_task ? + xprt->snd_task->tk_pid : -1; + __entry->cong = xprt->cong; + __entry->cwnd = xprt->cwnd; + __entry->wait = test_bit(XPRT_CWND_WAIT, &xprt->state); + ), + + TP_printk("task:%u@%u snd_task:%u cong=%lu cwnd=%lu%s", + __entry->task_id, __entry->client_id, + __entry->snd_task_id, __entry->cong, __entry->cwnd, + __entry->wait ? " (wait)" : "") +); + +#define DEFINE_CONG_EVENT(name) \ + DEFINE_EVENT(xprt_cong_event, xprt_##name, \ + TP_PROTO( \ + const struct rpc_xprt *xprt, \ + const struct rpc_task *task \ + ), \ + TP_ARGS(xprt, task)) + +DEFINE_CONG_EVENT(reserve_cong); +DEFINE_CONG_EVENT(release_cong); +DEFINE_CONG_EVENT(get_cong); +DEFINE_CONG_EVENT(put_cong); + TRACE_EVENT(xs_stream_read_data, TP_PROTO(struct rpc_xprt *xprt, ssize_t err, size_t total), diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 8a45b3ccc313..fcbeb56c82cd 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -205,20 +205,20 @@ int xprt_reserve_xprt(struct rpc_xprt *xprt, struct rpc_task *task) if (test_and_set_bit(XPRT_LOCKED, &xprt->state)) { if (task == xprt->snd_task) - return 1; + goto out_locked; goto out_sleep; } if (test_bit(XPRT_WRITE_SPACE, &xprt->state)) goto out_unlock; xprt->snd_task = task; +out_locked: + trace_xprt_reserve_xprt(xprt, task); return 1; out_unlock: xprt_clear_locked(xprt); out_sleep: - dprintk("RPC: %5u failed to lock transport %p\n", - task->tk_pid, xprt); task->tk_status = -EAGAIN; if (RPC_IS_SOFT(task)) rpc_sleep_on_timeout(&xprt->sending, task, NULL, @@ -269,23 +269,22 @@ int xprt_reserve_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task) if (test_and_set_bit(XPRT_LOCKED, &xprt->state)) { if (task == xprt->snd_task) - return 1; + goto out_locked; goto out_sleep; } if (req == NULL) { xprt->snd_task = task; - return 1; + goto out_locked; } if (test_bit(XPRT_WRITE_SPACE, &xprt->state)) goto out_unlock; if (!xprt_need_congestion_window_wait(xprt)) { xprt->snd_task = task; - return 1; + goto out_locked; } out_unlock: xprt_clear_locked(xprt); out_sleep: - dprintk("RPC: %5u failed to lock transport %p\n", task->tk_pid, xprt); task->tk_status = -EAGAIN; if (RPC_IS_SOFT(task)) rpc_sleep_on_timeout(&xprt->sending, task, NULL, @@ -293,6 +292,9 @@ out_sleep: else rpc_sleep_on(&xprt->sending, task, NULL); return 0; +out_locked: + trace_xprt_reserve_cong(xprt, task); + return 1; } EXPORT_SYMBOL_GPL(xprt_reserve_xprt_cong); @@ -357,6 +359,7 @@ void xprt_release_xprt(struct rpc_xprt *xprt, struct rpc_task *task) xprt_clear_locked(xprt); __xprt_lock_write_next(xprt); } + trace_xprt_release_xprt(xprt, task); } EXPORT_SYMBOL_GPL(xprt_release_xprt); @@ -374,6 +377,7 @@ void xprt_release_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task) xprt_clear_locked(xprt); __xprt_lock_write_next_cong(xprt); } + trace_xprt_release_cong(xprt, task); } EXPORT_SYMBOL_GPL(xprt_release_xprt_cong); @@ -395,8 +399,7 @@ __xprt_get_cong(struct rpc_xprt *xprt, struct rpc_rqst *req) { if (req->rq_cong) return 1; - dprintk("RPC: %5u xprt_cwnd_limited cong = %lu cwnd = %lu\n", - req->rq_task->tk_pid, xprt->cong, xprt->cwnd); + trace_xprt_get_cong(xprt, req->rq_task); if (RPCXPRT_CONGESTED(xprt)) { xprt_set_congestion_window_wait(xprt); return 0; @@ -418,6 +421,7 @@ __xprt_put_cong(struct rpc_xprt *xprt, struct rpc_rqst *req) req->rq_cong = 0; xprt->cong -= RPC_CWNDSCALE; xprt_test_and_clear_congestion_window_wait(xprt); + trace_xprt_put_cong(xprt, req->rq_task); __xprt_lock_write_next_cong(xprt); } -- cgit v1.2.3 From 4b93dab36f28e673725e5e6123ebfccf7697f96a Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 9 Oct 2019 13:07:21 -0400 Subject: xprtrdma: Add unique trace points for posting Local Invalidate WRs When adding frwr_unmap_async way back when, I re-used the existing trace_xprtrdma_post_send() trace point to record the return code of ib_post_send. Unfortunately there are some cases where re-using that trace point causes a crash. Instead, construct a trace point specific to posting Local Invalidate WRs that will always be safe to use in that context, and will act as a trace log eye-catcher for Local Invalidation. Fixes: 847568942f93 ("xprtrdma: Remove fr_state") Fixes: d8099feda483 ("xprtrdma: Reduce context switching due ... ") Signed-off-by: Chuck Lever Tested-by: Bill Baker Signed-off-by: Anna Schumaker --- include/trace/events/rpcrdma.h | 25 +++++++++++++++++++++++++ net/sunrpc/xprtrdma/frwr_ops.c | 4 ++-- 2 files changed, 27 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index a13830616107..7fd11ec1c9a4 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -735,6 +735,31 @@ TRACE_EVENT(xprtrdma_post_recvs, ) ); +TRACE_EVENT(xprtrdma_post_linv, + TP_PROTO( + const struct rpcrdma_req *req, + int status + ), + + TP_ARGS(req, status), + + TP_STRUCT__entry( + __field(const void *, req) + __field(int, status) + __field(u32, xid) + ), + + TP_fast_assign( + __entry->req = req; + __entry->status = status; + __entry->xid = be32_to_cpu(req->rl_slot.rq_xid); + ), + + TP_printk("req=%p xid=0x%08x status=%d", + __entry->req, __entry->xid, __entry->status + ) +); + /** ** Completion events **/ diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index 30065a28628c..9901a811f598 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -570,7 +570,6 @@ void frwr_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) */ bad_wr = NULL; rc = ib_post_send(r_xprt->rx_ia.ri_id->qp, first, &bad_wr); - trace_xprtrdma_post_send(req, rc); /* The final LOCAL_INV WR in the chain is supposed to * do the wake. If it was never posted, the wake will @@ -583,6 +582,7 @@ void frwr_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) /* Recycle MRs in the LOCAL_INV chain that did not get posted. */ + trace_xprtrdma_post_linv(req, rc); while (bad_wr) { frwr = container_of(bad_wr, struct rpcrdma_frwr, fr_invwr); @@ -673,12 +673,12 @@ void frwr_unmap_async(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) */ bad_wr = NULL; rc = ib_post_send(r_xprt->rx_ia.ri_id->qp, first, &bad_wr); - trace_xprtrdma_post_send(req, rc); if (!rc) return; /* Recycle MRs in the LOCAL_INV chain that did not get posted. */ + trace_xprtrdma_post_linv(req, rc); while (bad_wr) { frwr = container_of(bad_wr, struct rpcrdma_frwr, fr_invwr); mr = container_of(frwr, struct rpcrdma_mr, frwr); -- cgit v1.2.3 From dc15c3d5f16808f7c171b55da6a82a5c0f279647 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 17 Oct 2019 14:31:35 -0400 Subject: xprtrdma: Move the rpcrdma_sendctx::sc_wr field Clean up: This field is not needed in the Send completion handler, so it can be moved to struct rpcrdma_req to reduce the size of struct rpcrdma_sendctx, and to reduce the amount of memory that is sloshed between the sending process and the Send completion process. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/trace/events/rpcrdma.h | 5 ++--- net/sunrpc/xprtrdma/frwr_ops.c | 2 +- net/sunrpc/xprtrdma/rpc_rdma.c | 9 ++++++--- net/sunrpc/xprtrdma/verbs.c | 5 +---- net/sunrpc/xprtrdma/xprt_rdma.h | 2 +- 5 files changed, 11 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index 7fd11ec1c9a4..f8edab91e09c 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -667,9 +667,8 @@ TRACE_EVENT(xprtrdma_post_send, __entry->client_id = rqst->rq_task->tk_client ? rqst->rq_task->tk_client->cl_clid : -1; __entry->req = req; - __entry->num_sge = req->rl_sendctx->sc_wr.num_sge; - __entry->signaled = req->rl_sendctx->sc_wr.send_flags & - IB_SEND_SIGNALED; + __entry->num_sge = req->rl_wr.num_sge; + __entry->signaled = req->rl_wr.send_flags & IB_SEND_SIGNALED; __entry->status = status; ), diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index 5cd871568c67..523722be6a16 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -396,7 +396,7 @@ int frwr_send(struct rpcrdma_ia *ia, struct rpcrdma_req *req) struct ib_send_wr *post_wr; struct rpcrdma_mr *mr; - post_wr = &req->rl_sendctx->sc_wr; + post_wr = &req->rl_wr; list_for_each_entry(mr, &req->rl_registered, mr_list) { struct rpcrdma_frwr *frwr; diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 1941b2261ca5..53cd2e3cf003 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -599,7 +599,7 @@ static bool rpcrdma_prepare_hdr_sge(struct rpcrdma_xprt *r_xprt, ib_dma_sync_single_for_device(rdmab_device(rb), sge->addr, sge->length, DMA_TO_DEVICE); - sc->sc_wr.num_sge++; + req->rl_wr.num_sge++; return true; out_regbuf: @@ -711,7 +711,7 @@ map_tail: } out: - sc->sc_wr.num_sge += sge_no; + req->rl_wr.num_sge += sge_no; if (sc->sc_unmap_count) kref_get(&req->rl_kref); return true; @@ -752,10 +752,13 @@ rpcrdma_prepare_send_sges(struct rpcrdma_xprt *r_xprt, req->rl_sendctx = rpcrdma_sendctx_get_locked(r_xprt); if (!req->rl_sendctx) goto err; - req->rl_sendctx->sc_wr.num_sge = 0; req->rl_sendctx->sc_unmap_count = 0; req->rl_sendctx->sc_req = req; kref_init(&req->rl_kref); + req->rl_wr.wr_cqe = &req->rl_sendctx->sc_cqe; + req->rl_wr.sg_list = req->rl_sendctx->sc_sges; + req->rl_wr.num_sge = 0; + req->rl_wr.opcode = IB_WR_SEND; ret = -EIO; if (!rpcrdma_prepare_hdr_sge(r_xprt, req, hdrlen)) diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 3ab086aa69bb..2f4658255343 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -811,9 +811,6 @@ static struct rpcrdma_sendctx *rpcrdma_sendctx_create(struct rpcrdma_ia *ia) if (!sc) return NULL; - sc->sc_wr.wr_cqe = &sc->sc_cqe; - sc->sc_wr.sg_list = sc->sc_sges; - sc->sc_wr.opcode = IB_WR_SEND; sc->sc_cqe.done = rpcrdma_wc_send; return sc; } @@ -1469,7 +1466,7 @@ rpcrdma_ep_post(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep, struct rpcrdma_req *req) { - struct ib_send_wr *send_wr = &req->rl_sendctx->sc_wr; + struct ib_send_wr *send_wr = &req->rl_wr; int rc; if (!ep->rep_send_count || kref_read(&req->rl_kref) > 1) { diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 0e5b7f373077..cdd6a3d43e0f 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -219,7 +219,6 @@ enum { */ struct rpcrdma_req; struct rpcrdma_sendctx { - struct ib_send_wr sc_wr; struct ib_cqe sc_cqe; struct rpcrdma_req *sc_req; unsigned int sc_unmap_count; @@ -314,6 +313,7 @@ struct rpcrdma_req { struct rpcrdma_rep *rl_reply; struct xdr_stream rl_stream; struct xdr_buf rl_hdrbuf; + struct ib_send_wr rl_wr; struct rpcrdma_sendctx *rl_sendctx; struct rpcrdma_regbuf *rl_rdmabuf; /* xprt header */ struct rpcrdma_regbuf *rl_sendbuf; /* rq_snd_buf */ -- cgit v1.2.3 From 614f3c96d7e5efd1c4dc699524857130a52c6a7f Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 17 Oct 2019 14:31:53 -0400 Subject: xprtrdma: Pull up sometimes On some platforms, DMA mapping part of a page is more costly than copying bytes. Restore the pull-up code and use that when we think it's going to be faster. The heuristic for now is to pull-up when the size of the RPC message body fits in the buffer underlying the head iovec. Indeed, not involving the I/O MMU can help the RPC/RDMA transport scale better for tiny I/Os across more RDMA devices. This is because interaction with the I/O MMU is eliminated, as is handling a Send completion, for each of these small I/Os. Without the explicit unmapping, the NIC no longer needs to do a costly internal TLB shoot down for buffers that are just a handful of bytes. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/trace/events/rpcrdma.h | 4 ++ net/sunrpc/xprtrdma/backchannel.c | 2 +- net/sunrpc/xprtrdma/rpc_rdma.c | 82 ++++++++++++++++++++++++++++++++++++--- net/sunrpc/xprtrdma/verbs.c | 2 +- net/sunrpc/xprtrdma/xprt_rdma.h | 2 + 5 files changed, 85 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index f8edab91e09c..213c72585a5f 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -532,6 +532,8 @@ DEFINE_WRCH_EVENT(write); DEFINE_WRCH_EVENT(reply); TRACE_DEFINE_ENUM(rpcrdma_noch); +TRACE_DEFINE_ENUM(rpcrdma_noch_pullup); +TRACE_DEFINE_ENUM(rpcrdma_noch_mapped); TRACE_DEFINE_ENUM(rpcrdma_readch); TRACE_DEFINE_ENUM(rpcrdma_areadch); TRACE_DEFINE_ENUM(rpcrdma_writech); @@ -540,6 +542,8 @@ TRACE_DEFINE_ENUM(rpcrdma_replych); #define xprtrdma_show_chunktype(x) \ __print_symbolic(x, \ { rpcrdma_noch, "inline" }, \ + { rpcrdma_noch_pullup, "pullup" }, \ + { rpcrdma_noch_mapped, "mapped" }, \ { rpcrdma_readch, "read list" }, \ { rpcrdma_areadch, "*read list" }, \ { rpcrdma_writech, "write list" }, \ diff --git a/net/sunrpc/xprtrdma/backchannel.c b/net/sunrpc/xprtrdma/backchannel.c index 50e075fcdd8f..11685245546a 100644 --- a/net/sunrpc/xprtrdma/backchannel.c +++ b/net/sunrpc/xprtrdma/backchannel.c @@ -79,7 +79,7 @@ static int rpcrdma_bc_marshal_reply(struct rpc_rqst *rqst) *p = xdr_zero; if (rpcrdma_prepare_send_sges(r_xprt, req, RPCRDMA_HDRLEN_MIN, - &rqst->rq_snd_buf, rpcrdma_noch)) + &rqst->rq_snd_buf, rpcrdma_noch_pullup)) return -EIO; trace_xprtrdma_cb_reply(rqst); diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index a441dbf9f198..4ad88893e964 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -392,7 +392,7 @@ static int rpcrdma_encode_read_list(struct rpcrdma_xprt *r_xprt, unsigned int pos; int nsegs; - if (rtype == rpcrdma_noch) + if (rtype == rpcrdma_noch_pullup || rtype == rpcrdma_noch_mapped) goto done; pos = rqst->rq_snd_buf.head[0].iov_len; @@ -691,6 +691,72 @@ out_mapping_err: return false; } +/* Copy the tail to the end of the head buffer. + */ +static void rpcrdma_pullup_tail_iov(struct rpcrdma_xprt *r_xprt, + struct rpcrdma_req *req, + struct xdr_buf *xdr) +{ + unsigned char *dst; + + dst = (unsigned char *)xdr->head[0].iov_base; + dst += xdr->head[0].iov_len + xdr->page_len; + memmove(dst, xdr->tail[0].iov_base, xdr->tail[0].iov_len); + r_xprt->rx_stats.pullup_copy_count += xdr->tail[0].iov_len; +} + +/* Copy pagelist content into the head buffer. + */ +static void rpcrdma_pullup_pagelist(struct rpcrdma_xprt *r_xprt, + struct rpcrdma_req *req, + struct xdr_buf *xdr) +{ + unsigned int len, page_base, remaining; + struct page **ppages; + unsigned char *src, *dst; + + dst = (unsigned char *)xdr->head[0].iov_base; + dst += xdr->head[0].iov_len; + ppages = xdr->pages + (xdr->page_base >> PAGE_SHIFT); + page_base = offset_in_page(xdr->page_base); + remaining = xdr->page_len; + while (remaining) { + src = page_address(*ppages); + src += page_base; + len = min_t(unsigned int, PAGE_SIZE - page_base, remaining); + memcpy(dst, src, len); + r_xprt->rx_stats.pullup_copy_count += len; + + ppages++; + dst += len; + remaining -= len; + page_base = 0; + } +} + +/* Copy the contents of @xdr into @rl_sendbuf and DMA sync it. + * When the head, pagelist, and tail are small, a pull-up copy + * is considerably less costly than DMA mapping the components + * of @xdr. + * + * Assumptions: + * - the caller has already verified that the total length + * of the RPC Call body will fit into @rl_sendbuf. + */ +static bool rpcrdma_prepare_noch_pullup(struct rpcrdma_xprt *r_xprt, + struct rpcrdma_req *req, + struct xdr_buf *xdr) +{ + if (unlikely(xdr->tail[0].iov_len)) + rpcrdma_pullup_tail_iov(r_xprt, req, xdr); + + if (unlikely(xdr->page_len)) + rpcrdma_pullup_pagelist(r_xprt, req, xdr); + + /* The whole RPC message resides in the head iovec now */ + return rpcrdma_prepare_head_iov(r_xprt, req, xdr->len); +} + static bool rpcrdma_prepare_noch_mapped(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, struct xdr_buf *xdr) @@ -779,7 +845,11 @@ inline int rpcrdma_prepare_send_sges(struct rpcrdma_xprt *r_xprt, goto out_unmap; switch (rtype) { - case rpcrdma_noch: + case rpcrdma_noch_pullup: + if (!rpcrdma_prepare_noch_pullup(r_xprt, req, xdr)) + goto out_unmap; + break; + case rpcrdma_noch_mapped: if (!rpcrdma_prepare_noch_mapped(r_xprt, req, xdr)) goto out_unmap; break; @@ -827,6 +897,7 @@ rpcrdma_marshal_req(struct rpcrdma_xprt *r_xprt, struct rpc_rqst *rqst) struct rpcrdma_req *req = rpcr_to_rdmar(rqst); struct xdr_stream *xdr = &req->rl_stream; enum rpcrdma_chunktype rtype, wtype; + struct xdr_buf *buf = &rqst->rq_snd_buf; bool ddp_allowed; __be32 *p; int ret; @@ -884,8 +955,9 @@ rpcrdma_marshal_req(struct rpcrdma_xprt *r_xprt, struct rpc_rqst *rqst) */ if (rpcrdma_args_inline(r_xprt, rqst)) { *p++ = rdma_msg; - rtype = rpcrdma_noch; - } else if (ddp_allowed && rqst->rq_snd_buf.flags & XDRBUF_WRITE) { + rtype = buf->len < rdmab_length(req->rl_sendbuf) ? + rpcrdma_noch_pullup : rpcrdma_noch_mapped; + } else if (ddp_allowed && buf->flags & XDRBUF_WRITE) { *p++ = rdma_msg; rtype = rpcrdma_readch; } else { @@ -927,7 +999,7 @@ rpcrdma_marshal_req(struct rpcrdma_xprt *r_xprt, struct rpc_rqst *rqst) goto out_err; ret = rpcrdma_prepare_send_sges(r_xprt, req, req->rl_hdrbuf.len, - &rqst->rq_snd_buf, rtype); + buf, rtype); if (ret) goto out_err; diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 2f4658255343..a514e2c89ac3 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -1165,7 +1165,7 @@ int rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt) for (i = 0; i < buf->rb_max_requests; i++) { struct rpcrdma_req *req; - req = rpcrdma_req_create(r_xprt, RPCRDMA_V1_DEF_INLINE_SIZE, + req = rpcrdma_req_create(r_xprt, RPCRDMA_V1_DEF_INLINE_SIZE * 2, GFP_KERNEL); if (!req) goto out; diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index cdd6a3d43e0f..5d15140a0266 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -554,6 +554,8 @@ void frwr_unmap_async(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req); enum rpcrdma_chunktype { rpcrdma_noch = 0, + rpcrdma_noch_pullup, + rpcrdma_noch_mapped, rpcrdma_readch, rpcrdma_areadch, rpcrdma_writech, -- cgit v1.2.3 From 7b020f17bbd34c219419b634d9efb9e93a3af4c2 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 23 Oct 2019 10:01:58 -0400 Subject: xprtrdma: Report the computed connect delay For debugging, the op_connect trace point should report the computed connect delay. We can then ensure that the delay is computed at the proper times, for example. As a further clean-up, remove a few low-value "heartbeat" trace points in the connect path. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/trace/events/rpcrdma.h | 77 ++++++++++++++++++++++++++++++----------- net/sunrpc/xprtrdma/transport.c | 3 +- net/sunrpc/xprtrdma/verbs.c | 13 ++----- 3 files changed, 60 insertions(+), 33 deletions(-) (limited to 'include') diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index 213c72585a5f..99e3c61609b2 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -85,6 +85,44 @@ DECLARE_EVENT_CLASS(xprtrdma_rxprt, ), \ TP_ARGS(r_xprt)) +DECLARE_EVENT_CLASS(xprtrdma_connect_class, + TP_PROTO( + const struct rpcrdma_xprt *r_xprt, + int rc + ), + + TP_ARGS(r_xprt, rc), + + TP_STRUCT__entry( + __field(const void *, r_xprt) + __field(int, rc) + __field(int, connect_status) + __string(addr, rpcrdma_addrstr(r_xprt)) + __string(port, rpcrdma_portstr(r_xprt)) + ), + + TP_fast_assign( + __entry->r_xprt = r_xprt; + __entry->rc = rc; + __entry->connect_status = r_xprt->rx_ep.rep_connected; + __assign_str(addr, rpcrdma_addrstr(r_xprt)); + __assign_str(port, rpcrdma_portstr(r_xprt)); + ), + + TP_printk("peer=[%s]:%s r_xprt=%p: rc=%d connect status=%d", + __get_str(addr), __get_str(port), __entry->r_xprt, + __entry->rc, __entry->connect_status + ) +); + +#define DEFINE_CONN_EVENT(name) \ + DEFINE_EVENT(xprtrdma_connect_class, xprtrdma_##name, \ + TP_PROTO( \ + const struct rpcrdma_xprt *r_xprt, \ + int rc \ + ), \ + TP_ARGS(r_xprt, rc)) + DECLARE_EVENT_CLASS(xprtrdma_rdch_event, TP_PROTO( const struct rpc_task *task, @@ -333,47 +371,44 @@ TRACE_EVENT(xprtrdma_cm_event, ) ); -TRACE_EVENT(xprtrdma_disconnect, +DEFINE_CONN_EVENT(connect); +DEFINE_CONN_EVENT(disconnect); + +DEFINE_RXPRT_EVENT(xprtrdma_create); +DEFINE_RXPRT_EVENT(xprtrdma_op_destroy); +DEFINE_RXPRT_EVENT(xprtrdma_remove); +DEFINE_RXPRT_EVENT(xprtrdma_reinsert); +DEFINE_RXPRT_EVENT(xprtrdma_op_inject_dsc); +DEFINE_RXPRT_EVENT(xprtrdma_op_close); + +TRACE_EVENT(xprtrdma_op_connect, TP_PROTO( const struct rpcrdma_xprt *r_xprt, - int status + unsigned long delay ), - TP_ARGS(r_xprt, status), + TP_ARGS(r_xprt, delay), TP_STRUCT__entry( __field(const void *, r_xprt) - __field(int, status) - __field(int, connected) + __field(unsigned long, delay) __string(addr, rpcrdma_addrstr(r_xprt)) __string(port, rpcrdma_portstr(r_xprt)) ), TP_fast_assign( __entry->r_xprt = r_xprt; - __entry->status = status; - __entry->connected = r_xprt->rx_ep.rep_connected; + __entry->delay = delay; __assign_str(addr, rpcrdma_addrstr(r_xprt)); __assign_str(port, rpcrdma_portstr(r_xprt)); ), - TP_printk("peer=[%s]:%s r_xprt=%p: status=%d %sconnected", - __get_str(addr), __get_str(port), - __entry->r_xprt, __entry->status, - __entry->connected == 1 ? "still " : "dis" + TP_printk("peer=[%s]:%s r_xprt=%p delay=%lu", + __get_str(addr), __get_str(port), __entry->r_xprt, + __entry->delay ) ); -DEFINE_RXPRT_EVENT(xprtrdma_conn_start); -DEFINE_RXPRT_EVENT(xprtrdma_conn_tout); -DEFINE_RXPRT_EVENT(xprtrdma_create); -DEFINE_RXPRT_EVENT(xprtrdma_op_destroy); -DEFINE_RXPRT_EVENT(xprtrdma_remove); -DEFINE_RXPRT_EVENT(xprtrdma_reinsert); -DEFINE_RXPRT_EVENT(xprtrdma_reconnect); -DEFINE_RXPRT_EVENT(xprtrdma_op_inject_dsc); -DEFINE_RXPRT_EVENT(xprtrdma_op_close); -DEFINE_RXPRT_EVENT(xprtrdma_op_connect); TRACE_EVENT(xprtrdma_op_set_cto, TP_PROTO( diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 361e59146807..ce263e6f779c 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -527,13 +527,12 @@ xprt_rdma_connect(struct rpc_xprt *xprt, struct rpc_task *task) struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt); unsigned long delay; - trace_xprtrdma_op_connect(r_xprt); - delay = 0; if (r_xprt->rx_ep.rep_connected != 0) { delay = xprt_reconnect_delay(xprt); xprt_reconnect_backoff(xprt, RPCRDMA_INIT_REEST_TO); } + trace_xprtrdma_op_connect(r_xprt, delay); queue_delayed_work(xprtiod_workqueue, &r_xprt->rx_connect_worker, delay); } diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index a514e2c89ac3..92bdf053716a 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -297,8 +297,6 @@ rpcrdma_create_id(struct rpcrdma_xprt *xprt, struct rpcrdma_ia *ia) struct rdma_cm_id *id; int rc; - trace_xprtrdma_conn_start(xprt); - init_completion(&ia->ri_done); init_completion(&ia->ri_remove_done); @@ -314,10 +312,8 @@ rpcrdma_create_id(struct rpcrdma_xprt *xprt, struct rpcrdma_ia *ia) if (rc) goto out; rc = wait_for_completion_interruptible_timeout(&ia->ri_done, wtimeout); - if (rc < 0) { - trace_xprtrdma_conn_tout(xprt); + if (rc < 0) goto out; - } rc = ia->ri_async_rc; if (rc) @@ -328,10 +324,8 @@ rpcrdma_create_id(struct rpcrdma_xprt *xprt, struct rpcrdma_ia *ia) if (rc) goto out; rc = wait_for_completion_interruptible_timeout(&ia->ri_done, wtimeout); - if (rc < 0) { - trace_xprtrdma_conn_tout(xprt); + if (rc < 0) goto out; - } rc = ia->ri_async_rc; if (rc) goto out; @@ -644,8 +638,6 @@ static int rpcrdma_ep_reconnect(struct rpcrdma_xprt *r_xprt, struct rdma_cm_id *id, *old; int err, rc; - trace_xprtrdma_reconnect(r_xprt); - rpcrdma_ep_disconnect(&r_xprt->rx_ep, ia); rc = -EHOSTUNREACH; @@ -744,6 +736,7 @@ out: ep->rep_connected = rc; out_noupdate: + trace_xprtrdma_connect(r_xprt, rc); return rc; } -- cgit v1.2.3 From d4957f01d29b2a01200117fc04b9faaa52aca4bf Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 23 Oct 2019 10:02:03 -0400 Subject: xprtrdma: Refine trace_xprtrdma_fixup Slightly reduce overhead and display more useful information. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/trace/events/rpcrdma.h | 60 +++++++++--------------------------------- net/sunrpc/xprtrdma/rpc_rdma.c | 5 ++-- 2 files changed, 15 insertions(+), 50 deletions(-) (limited to 'include') diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index 99e3c61609b2..542177c5896f 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -1084,66 +1084,32 @@ DEFINE_REPLY_EVENT(xprtrdma_reply_hdr); TRACE_EVENT(xprtrdma_fixup, TP_PROTO( const struct rpc_rqst *rqst, - int len, - int hdrlen + unsigned long fixup ), - TP_ARGS(rqst, len, hdrlen), + TP_ARGS(rqst, fixup), TP_STRUCT__entry( __field(unsigned int, task_id) __field(unsigned int, client_id) - __field(const void *, base) - __field(int, len) - __field(int, hdrlen) - ), - - TP_fast_assign( - __entry->task_id = rqst->rq_task->tk_pid; - __entry->client_id = rqst->rq_task->tk_client->cl_clid; - __entry->base = rqst->rq_rcv_buf.head[0].iov_base; - __entry->len = len; - __entry->hdrlen = hdrlen; - ), - - TP_printk("task:%u@%u base=%p len=%d hdrlen=%d", - __entry->task_id, __entry->client_id, - __entry->base, __entry->len, __entry->hdrlen - ) -); - -TRACE_EVENT(xprtrdma_fixup_pg, - TP_PROTO( - const struct rpc_rqst *rqst, - int pageno, - const void *pos, - int len, - int curlen - ), - - TP_ARGS(rqst, pageno, pos, len, curlen), - - TP_STRUCT__entry( - __field(unsigned int, task_id) - __field(unsigned int, client_id) - __field(const void *, pos) - __field(int, pageno) - __field(int, len) - __field(int, curlen) + __field(unsigned long, fixup) + __field(size_t, headlen) + __field(unsigned int, pagelen) + __field(size_t, taillen) ), TP_fast_assign( __entry->task_id = rqst->rq_task->tk_pid; __entry->client_id = rqst->rq_task->tk_client->cl_clid; - __entry->pos = pos; - __entry->pageno = pageno; - __entry->len = len; - __entry->curlen = curlen; + __entry->fixup = fixup; + __entry->headlen = rqst->rq_rcv_buf.head[0].iov_len; + __entry->pagelen = rqst->rq_rcv_buf.page_len; + __entry->taillen = rqst->rq_rcv_buf.tail[0].iov_len; ), - TP_printk("task:%u@%u pageno=%d pos=%p len=%d curlen=%d", - __entry->task_id, __entry->client_id, - __entry->pageno, __entry->pos, __entry->len, __entry->curlen + TP_printk("task:%u@%u fixup=%lu xdr=%zu/%u/%zu", + __entry->task_id, __entry->client_id, __entry->fixup, + __entry->headlen, __entry->pagelen, __entry->taillen ) ); diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 4ad88893e964..26d334c83b38 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -1086,7 +1086,6 @@ rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len, int pad) curlen = rqst->rq_rcv_buf.head[0].iov_len; if (curlen > copy_len) curlen = copy_len; - trace_xprtrdma_fixup(rqst, copy_len, curlen); srcp += curlen; copy_len -= curlen; @@ -1106,8 +1105,6 @@ rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len, int pad) if (curlen > pagelist_len) curlen = pagelist_len; - trace_xprtrdma_fixup_pg(rqst, i, srcp, - copy_len, curlen); destp = kmap_atomic(ppages[i]); memcpy(destp + page_base, srcp, curlen); flush_dcache_page(ppages[i]); @@ -1139,6 +1136,8 @@ rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len, int pad) rqst->rq_private_buf.tail[0].iov_base = srcp; } + if (fixup_copy_count) + trace_xprtrdma_fixup(rqst, fixup_copy_count); return fixup_copy_count; } -- cgit v1.2.3 From f54c870d326aa02b73b68d2e0a503ec81dd3a4e4 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 23 Oct 2019 10:02:09 -0400 Subject: xprtrdma: Replace dprintk() in rpcrdma_update_connect_private() Clean up: Use a single trace point to record each connection's negotiated inline thresholds and the computed maximum byte size of transport headers. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/trace/events/rpcrdma.h | 36 ++++++++++++++++++++++++++++++++++++ net/sunrpc/xprtrdma/rpc_rdma.c | 4 ---- net/sunrpc/xprtrdma/verbs.c | 21 ++++++++++----------- 3 files changed, 46 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index 542177c5896f..0ca118bcc5ce 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -371,6 +371,42 @@ TRACE_EVENT(xprtrdma_cm_event, ) ); +TRACE_EVENT(xprtrdma_inline_thresh, + TP_PROTO( + const struct rpcrdma_xprt *r_xprt + ), + + TP_ARGS(r_xprt), + + TP_STRUCT__entry( + __field(const void *, r_xprt) + __field(unsigned int, inline_send) + __field(unsigned int, inline_recv) + __field(unsigned int, max_send) + __field(unsigned int, max_recv) + __string(addr, rpcrdma_addrstr(r_xprt)) + __string(port, rpcrdma_portstr(r_xprt)) + ), + + TP_fast_assign( + const struct rpcrdma_ep *ep = &r_xprt->rx_ep; + + __entry->r_xprt = r_xprt; + __entry->inline_send = ep->rep_inline_send; + __entry->inline_recv = ep->rep_inline_recv; + __entry->max_send = ep->rep_max_inline_send; + __entry->max_recv = ep->rep_max_inline_recv; + __assign_str(addr, rpcrdma_addrstr(r_xprt)); + __assign_str(port, rpcrdma_portstr(r_xprt)); + ), + + TP_printk("peer=[%s]:%s r_xprt=%p neg send/recv=%u/%u, calc send/recv=%u/%u", + __get_str(addr), __get_str(port), __entry->r_xprt, + __entry->inline_send, __entry->inline_recv, + __entry->max_send, __entry->max_recv + ) +); + DEFINE_CONN_EVENT(connect); DEFINE_CONN_EVENT(disconnect); diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 26d334c83b38..aec3beb93b25 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -78,8 +78,6 @@ static unsigned int rpcrdma_max_call_header_size(unsigned int maxsegs) size += rpcrdma_segment_maxsz * sizeof(__be32); size += sizeof(__be32); /* list discriminator */ - dprintk("RPC: %s: max call header size = %u\n", - __func__, size); return size; } @@ -100,8 +98,6 @@ static unsigned int rpcrdma_max_reply_header_size(unsigned int maxsegs) size += maxsegs * rpcrdma_segment_maxsz * sizeof(__be32); size += sizeof(__be32); /* list discriminator */ - dprintk("RPC: %s: max reply header size = %u\n", - __func__, size); return size; } diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 92bdf053716a..77c7dd7f05e8 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -177,11 +177,11 @@ out_flushed: rpcrdma_recv_buffer_put(rep); } -static void -rpcrdma_update_connect_private(struct rpcrdma_xprt *r_xprt, - struct rdma_conn_param *param) +static void rpcrdma_update_cm_private(struct rpcrdma_xprt *r_xprt, + struct rdma_conn_param *param) { const struct rpcrdma_connect_private *pmsg = param->private_data; + struct rpcrdma_ep *ep = &r_xprt->rx_ep; unsigned int rsize, wsize; /* Default settings for RPC-over-RDMA Version One */ @@ -197,13 +197,11 @@ rpcrdma_update_connect_private(struct rpcrdma_xprt *r_xprt, wsize = rpcrdma_decode_buffer_size(pmsg->cp_recv_size); } - if (rsize < r_xprt->rx_ep.rep_inline_recv) - r_xprt->rx_ep.rep_inline_recv = rsize; - if (wsize < r_xprt->rx_ep.rep_inline_send) - r_xprt->rx_ep.rep_inline_send = wsize; - dprintk("RPC: %s: max send %u, max recv %u\n", __func__, - r_xprt->rx_ep.rep_inline_send, - r_xprt->rx_ep.rep_inline_recv); + if (rsize < ep->rep_inline_recv) + ep->rep_inline_recv = rsize; + if (wsize < ep->rep_inline_send) + ep->rep_inline_send = wsize; + rpcrdma_set_max_header_sizes(r_xprt); } @@ -257,7 +255,8 @@ rpcrdma_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event) case RDMA_CM_EVENT_ESTABLISHED: ++xprt->connect_cookie; ep->rep_connected = 1; - rpcrdma_update_connect_private(r_xprt, &event->param.conn); + rpcrdma_update_cm_private(r_xprt, &event->param.conn); + trace_xprtrdma_inline_thresh(r_xprt); wake_up_all(&ep->rep_connect_wait); break; case RDMA_CM_EVENT_CONNECT_ERROR: -- cgit v1.2.3 From a52c23b8b207d676d6cdf531af482a79fa622b9d Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 23 Oct 2019 10:02:14 -0400 Subject: xprtrdma: Replace dprintk in xprt_rdma_set_port Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/trace/events/rpcrdma.h | 1 + net/sunrpc/xprtrdma/transport.c | 9 +++------ 2 files changed, 4 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index 0ca118bcc5ce..69a8278e5cef 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -416,6 +416,7 @@ DEFINE_RXPRT_EVENT(xprtrdma_remove); DEFINE_RXPRT_EVENT(xprtrdma_reinsert); DEFINE_RXPRT_EVENT(xprtrdma_op_inject_dsc); DEFINE_RXPRT_EVENT(xprtrdma_op_close); +DEFINE_RXPRT_EVENT(xprtrdma_op_setport); TRACE_EVENT(xprtrdma_op_connect, TP_PROTO( diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index ce263e6f779c..7395eb2cfdeb 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -441,12 +441,6 @@ xprt_rdma_set_port(struct rpc_xprt *xprt, u16 port) struct sockaddr *sap = (struct sockaddr *)&xprt->addr; char buf[8]; - dprintk("RPC: %s: setting port for xprt %p (%s:%s) to %u\n", - __func__, xprt, - xprt->address_strings[RPC_DISPLAY_ADDR], - xprt->address_strings[RPC_DISPLAY_PORT], - port); - rpc_set_port(sap, port); kfree(xprt->address_strings[RPC_DISPLAY_PORT]); @@ -456,6 +450,9 @@ xprt_rdma_set_port(struct rpc_xprt *xprt, u16 port) kfree(xprt->address_strings[RPC_DISPLAY_HEX_PORT]); snprintf(buf, sizeof(buf), "%4hx", port); xprt->address_strings[RPC_DISPLAY_HEX_PORT] = kstrdup(buf, GFP_KERNEL); + + trace_xprtrdma_op_setport(container_of(xprt, struct rpcrdma_xprt, + rx_xprt)); } /** -- cgit v1.2.3 From 26ed19adbab16410460bd8b90ccc7430229a0b4a Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 18 Jun 2019 01:21:23 +0900 Subject: libfdt: reduce the number of headers included from libfdt_env.h Currently, libfdt_env.h includes just for INT_MAX. pulls in a lots of broat. Thanks to commit 54d50897d544 ("linux/kernel.h: split *_MAX and *_MIN macros into "), can be replaced with . This saves including dozens of headers. Signed-off-by: Masahiro Yamada Signed-off-by: Rob Herring --- include/linux/libfdt_env.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/libfdt_env.h b/include/linux/libfdt_env.h index edb0f0c30904..2231eb855e8f 100644 --- a/include/linux/libfdt_env.h +++ b/include/linux/libfdt_env.h @@ -2,7 +2,7 @@ #ifndef LIBFDT_ENV_H #define LIBFDT_ENV_H -#include /* For INT_MAX */ +#include /* For INT_MAX */ #include #include -- cgit v1.2.3 From 837a6e7f5cdb5e411c6187729e12962c2705160d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Oct 2019 22:26:02 -0700 Subject: fs: add generic UNRESVSP and ZERO_RANGE ioctl handlers These use the same scheme as the pre-existing mapping of the XFS RESVP ioctls to ->falloc, so just extend it and remove the XFS implementation. Signed-off-by: Christoph Hellwig [darrick: fix compile error on s390] Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/compat_ioctl.c | 31 ++++++++++++++++++---- fs/ioctl.c | 12 ++++++--- fs/xfs/xfs_ioctl.c | 72 +++++++++----------------------------------------- fs/xfs/xfs_ioctl.h | 1 - fs/xfs/xfs_ioctl32.c | 7 ++--- include/linux/falloc.h | 3 +++ include/linux/fs.h | 2 +- 7 files changed, 53 insertions(+), 75 deletions(-) (limited to 'include') diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index a7ec2d3dff92..62e530814cef 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -480,11 +480,14 @@ struct space_resv_32 { __s32 l_pad[4]; /* reserve area */ }; -#define FS_IOC_RESVSP_32 _IOW ('X', 40, struct space_resv_32) +#define FS_IOC_RESVSP_32 _IOW ('X', 40, struct space_resv_32) +#define FS_IOC_UNRESVSP_32 _IOW ('X', 41, struct space_resv_32) #define FS_IOC_RESVSP64_32 _IOW ('X', 42, struct space_resv_32) +#define FS_IOC_UNRESVSP64_32 _IOW ('X', 43, struct space_resv_32) +#define FS_IOC_ZERO_RANGE_32 _IOW ('X', 57, struct space_resv_32) /* just account for different alignment */ -static int compat_ioctl_preallocate(struct file *file, +static int compat_ioctl_preallocate(struct file *file, int mode, struct space_resv_32 __user *p32) { struct space_resv __user *p = compat_alloc_user_space(sizeof(*p)); @@ -498,7 +501,7 @@ static int compat_ioctl_preallocate(struct file *file, copy_in_user(&p->l_pad, &p32->l_pad, 4*sizeof(u32))) return -EFAULT; - return ioctl_preallocate(file, p); + return ioctl_preallocate(file, mode, p); } #endif @@ -1022,12 +1025,30 @@ COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, #if defined(CONFIG_IA64) || defined(CONFIG_X86_64) case FS_IOC_RESVSP_32: case FS_IOC_RESVSP64_32: - error = compat_ioctl_preallocate(f.file, compat_ptr(arg)); + error = compat_ioctl_preallocate(f.file, 0, compat_ptr(arg)); + goto out_fput; + case FS_IOC_UNRESVSP_32: + case FS_IOC_UNRESVSP64_32: + error = compat_ioctl_preallocate(f.file, FALLOC_FL_PUNCH_HOLE, + compat_ptr(arg)); + goto out_fput; + case FS_IOC_ZERO_RANGE_32: + error = compat_ioctl_preallocate(f.file, FALLOC_FL_ZERO_RANGE, + compat_ptr(arg)); goto out_fput; #else case FS_IOC_RESVSP: case FS_IOC_RESVSP64: - error = ioctl_preallocate(f.file, compat_ptr(arg)); + error = ioctl_preallocate(f.file, 0, compat_ptr(arg)); + goto out_fput; + case FS_IOC_UNRESVSP: + case FS_IOC_UNRESVSP64: + error = ioctl_preallocate(f.file, FALLOC_FL_PUNCH_HOLE, + compat_ptr(arg)); + goto out_fput; + case FS_IOC_ZERO_RANGE: + error = ioctl_preallocate(f.file, FALLOC_FL_ZERO_RANGE, + compat_ptr(arg)); goto out_fput; #endif diff --git a/fs/ioctl.c b/fs/ioctl.c index fef3a6bf7c78..55c7cfb0e599 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -466,7 +466,7 @@ EXPORT_SYMBOL(generic_block_fiemap); * Only the l_start, l_len and l_whence fields of the 'struct space_resv' * are used here, rest are ignored. */ -int ioctl_preallocate(struct file *filp, void __user *argp) +int ioctl_preallocate(struct file *filp, int mode, void __user *argp) { struct inode *inode = file_inode(filp); struct space_resv sr; @@ -487,7 +487,8 @@ int ioctl_preallocate(struct file *filp, void __user *argp) return -EINVAL; } - return vfs_fallocate(filp, FALLOC_FL_KEEP_SIZE, sr.l_start, sr.l_len); + return vfs_fallocate(filp, mode | FALLOC_FL_KEEP_SIZE, sr.l_start, + sr.l_len); } static int file_ioctl(struct file *filp, unsigned int cmd, @@ -503,7 +504,12 @@ static int file_ioctl(struct file *filp, unsigned int cmd, return put_user(i_size_read(inode) - filp->f_pos, p); case FS_IOC_RESVSP: case FS_IOC_RESVSP64: - return ioctl_preallocate(filp, p); + return ioctl_preallocate(filp, 0, p); + case FS_IOC_UNRESVSP: + case FS_IOC_UNRESVSP64: + return ioctl_preallocate(filp, FALLOC_FL_PUNCH_HOLE, p); + case FS_IOC_ZERO_RANGE: + return ioctl_preallocate(filp, FALLOC_FL_ZERO_RANGE, p); } return vfs_ioctl(filp, cmd, arg); diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 2f26417405a5..e897d5363d01 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -588,13 +588,12 @@ xfs_attrmulti_by_handle( int xfs_ioc_space( struct file *filp, - unsigned int cmd, xfs_flock64_t *bf) { struct inode *inode = file_inode(filp); struct xfs_inode *ip = XFS_I(inode); struct iattr iattr; - enum xfs_prealloc_flags flags = 0; + enum xfs_prealloc_flags flags = XFS_PREALLOC_CLEAR; uint iolock = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL; int error; @@ -635,65 +634,21 @@ xfs_ioc_space( goto out_unlock; } - /* - * length of <= 0 for resv/unresv/zero is invalid. length for - * alloc/free is ignored completely and we have no idea what userspace - * might have set it to, so set it to zero to allow range - * checks to pass. - */ - switch (cmd) { - case XFS_IOC_ZERO_RANGE: - case XFS_IOC_UNRESVSP: - case XFS_IOC_UNRESVSP64: - if (bf->l_len <= 0) { - error = -EINVAL; - goto out_unlock; - } - break; - default: - bf->l_len = 0; - break; - } - - if (bf->l_start < 0 || - bf->l_start > inode->i_sb->s_maxbytes || - bf->l_start + bf->l_len < 0 || - bf->l_start + bf->l_len >= inode->i_sb->s_maxbytes) { + if (bf->l_start < 0 || bf->l_start > inode->i_sb->s_maxbytes) { error = -EINVAL; goto out_unlock; } - switch (cmd) { - case XFS_IOC_ZERO_RANGE: - flags |= XFS_PREALLOC_SET; - error = xfs_zero_file_space(ip, bf->l_start, bf->l_len); - break; - case XFS_IOC_UNRESVSP: - case XFS_IOC_UNRESVSP64: - error = xfs_free_file_space(ip, bf->l_start, bf->l_len); - break; - case XFS_IOC_ALLOCSP: - case XFS_IOC_ALLOCSP64: - case XFS_IOC_FREESP: - case XFS_IOC_FREESP64: - flags |= XFS_PREALLOC_CLEAR; - if (bf->l_start > XFS_ISIZE(ip)) { - error = xfs_alloc_file_space(ip, XFS_ISIZE(ip), - bf->l_start - XFS_ISIZE(ip), 0); - if (error) - goto out_unlock; - } - - iattr.ia_valid = ATTR_SIZE; - iattr.ia_size = bf->l_start; - - error = xfs_vn_setattr_size(file_dentry(filp), &iattr); - break; - default: - ASSERT(0); - error = -EINVAL; + if (bf->l_start > XFS_ISIZE(ip)) { + error = xfs_alloc_file_space(ip, XFS_ISIZE(ip), + bf->l_start - XFS_ISIZE(ip), 0); + if (error) + goto out_unlock; } + iattr.ia_valid = ATTR_SIZE; + iattr.ia_size = bf->l_start; + error = xfs_vn_setattr_size(file_dentry(filp), &iattr); if (error) goto out_unlock; @@ -2113,16 +2068,13 @@ xfs_file_ioctl( return xfs_ioc_setlabel(filp, mp, arg); case XFS_IOC_ALLOCSP: case XFS_IOC_FREESP: - case XFS_IOC_UNRESVSP: case XFS_IOC_ALLOCSP64: - case XFS_IOC_FREESP64: - case XFS_IOC_UNRESVSP64: - case XFS_IOC_ZERO_RANGE: { + case XFS_IOC_FREESP64: { xfs_flock64_t bf; if (copy_from_user(&bf, arg, sizeof(bf))) return -EFAULT; - return xfs_ioc_space(filp, cmd, &bf); + return xfs_ioc_space(filp, &bf); } case XFS_IOC_DIOINFO: { struct xfs_buftarg *target = xfs_inode_buftarg(ip); diff --git a/fs/xfs/xfs_ioctl.h b/fs/xfs/xfs_ioctl.h index 654c0bb1bcf8..25ef178cbb74 100644 --- a/fs/xfs/xfs_ioctl.h +++ b/fs/xfs/xfs_ioctl.h @@ -9,7 +9,6 @@ extern int xfs_ioc_space( struct file *filp, - unsigned int cmd, xfs_flock64_t *bf); int diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c index 257b7caf7fed..3c0d518e1039 100644 --- a/fs/xfs/xfs_ioctl32.c +++ b/fs/xfs/xfs_ioctl32.c @@ -557,16 +557,13 @@ xfs_file_compat_ioctl( case XFS_IOC_ALLOCSP_32: case XFS_IOC_FREESP_32: case XFS_IOC_ALLOCSP64_32: - case XFS_IOC_FREESP64_32: - case XFS_IOC_RESVSP64_32: - case XFS_IOC_UNRESVSP64_32: - case XFS_IOC_ZERO_RANGE_32: { + case XFS_IOC_FREESP64_32: { struct xfs_flock64 bf; if (xfs_compat_flock64_copyin(&bf, arg)) return -EFAULT; cmd = _NATIVE_IOC(cmd, struct xfs_flock64); - return xfs_ioc_space(filp, cmd, &bf); + return xfs_ioc_space(filp, &bf); } case XFS_IOC_FSGEOMETRY_V1_32: return xfs_compat_ioc_fsgeometry_v1(mp, arg); diff --git a/include/linux/falloc.h b/include/linux/falloc.h index 674d59f4d6ce..f5c73f0ec22d 100644 --- a/include/linux/falloc.h +++ b/include/linux/falloc.h @@ -20,7 +20,10 @@ struct space_resv { }; #define FS_IOC_RESVSP _IOW('X', 40, struct space_resv) +#define FS_IOC_UNRESVSP _IOW('X', 41, struct space_resv) #define FS_IOC_RESVSP64 _IOW('X', 42, struct space_resv) +#define FS_IOC_UNRESVSP64 _IOW('X', 43, struct space_resv) +#define FS_IOC_ZERO_RANGE _IOW('X', 57, struct space_resv) #define FALLOC_FL_SUPPORTED_MASK (FALLOC_FL_KEEP_SIZE | \ FALLOC_FL_PUNCH_HOLE | \ diff --git a/include/linux/fs.h b/include/linux/fs.h index e0d909d35763..2b5692207c1d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2547,7 +2547,7 @@ extern int finish_no_open(struct file *file, struct dentry *dentry); /* fs/ioctl.c */ -extern int ioctl_preallocate(struct file *filp, void __user *argp); +extern int ioctl_preallocate(struct file *filp, int mode, void __user *argp); /* fs/dcache.c */ extern void __init vfs_caches_init_early(void); -- cgit v1.2.3 From c3a6cf19e695c8b0a9bf8b5933f863e12d878b7c Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Fri, 18 Oct 2019 10:31:43 +0100 Subject: export: avoid code duplication in include/linux/export.h include/linux/export.h has lots of code duplication between EXPORT_SYMBOL and EXPORT_SYMBOL_NS. To improve the maintainability and readability, unify the implementation. When the symbol has no namespace, pass the empty string "" to the 'ns' parameter. The drawback of this change is, it grows the code size. When the symbol has no namespace, sym->namespace was previously NULL, but it is now an empty string "". So, it increases 1 byte for every no namespace EXPORT_SYMBOL. A typical kernel configuration has 10K exported symbols, so it increases 10KB in rough estimation. I did not come up with a good idea to refactor it without increasing the code size. I am not sure how big a deal it is, but at least include/linux/export.h looks nicer. Reviewed-by: Greg Kroah-Hartman Signed-off-by: Masahiro Yamada [maennich: rebase on top of 3 fixes for the namespace feature] Signed-off-by: Matthias Maennich Signed-off-by: Jessica Yu --- include/linux/export.h | 91 ++++++++++++++++---------------------------------- kernel/module.c | 2 +- 2 files changed, 29 insertions(+), 64 deletions(-) (limited to 'include') diff --git a/include/linux/export.h b/include/linux/export.h index 941d075f03d6..201262793369 100644 --- a/include/linux/export.h +++ b/include/linux/export.h @@ -46,7 +46,7 @@ extern struct module __this_module; * absolute relocations that require runtime processing on relocatable * kernels. */ -#define __KSYMTAB_ENTRY_NS(sym, sec) \ +#define __KSYMTAB_ENTRY(sym, sec) \ __ADDRESSABLE(sym) \ asm(" .section \"___ksymtab" sec "+" #sym "\", \"a\" \n" \ " .balign 4 \n" \ @@ -56,33 +56,17 @@ extern struct module __this_module; " .long __kstrtabns_" #sym "- . \n" \ " .previous \n") -#define __KSYMTAB_ENTRY(sym, sec) \ - __ADDRESSABLE(sym) \ - asm(" .section \"___ksymtab" sec "+" #sym "\", \"a\" \n" \ - " .balign 4 \n" \ - "__ksymtab_" #sym ": \n" \ - " .long " #sym "- . \n" \ - " .long __kstrtab_" #sym "- . \n" \ - " .long 0 \n" \ - " .previous \n") - struct kernel_symbol { int value_offset; int name_offset; int namespace_offset; }; #else -#define __KSYMTAB_ENTRY_NS(sym, sec) \ - static const struct kernel_symbol __ksymtab_##sym \ - __attribute__((section("___ksymtab" sec "+" #sym), used)) \ - __aligned(sizeof(void *)) \ - = { (unsigned long)&sym, __kstrtab_##sym, __kstrtabns_##sym } - #define __KSYMTAB_ENTRY(sym, sec) \ static const struct kernel_symbol __ksymtab_##sym \ __attribute__((section("___ksymtab" sec "+" #sym), used)) \ __aligned(sizeof(void *)) \ - = { (unsigned long)&sym, __kstrtab_##sym, NULL } + = { (unsigned long)&sym, __kstrtab_##sym, __kstrtabns_##sym } struct kernel_symbol { unsigned long value; @@ -93,28 +77,20 @@ struct kernel_symbol { #ifdef __GENKSYMS__ -#define ___EXPORT_SYMBOL(sym,sec) __GENKSYMS_EXPORT_SYMBOL(sym) -#define ___EXPORT_SYMBOL_NS(sym,sec,ns) __GENKSYMS_EXPORT_SYMBOL(sym) +#define ___EXPORT_SYMBOL(sym, sec, ns) __GENKSYMS_EXPORT_SYMBOL(sym) #else -#define ___export_symbol_common(sym, sec) \ +/* For every exported symbol, place a struct in the __ksymtab section */ +#define ___EXPORT_SYMBOL(sym, sec, ns) \ extern typeof(sym) sym; \ __CRC_SYMBOL(sym, sec); \ static const char __kstrtab_##sym[] \ __attribute__((section("__ksymtab_strings"), used, aligned(1))) \ - = #sym \ - -/* For every exported symbol, place a struct in the __ksymtab section */ -#define ___EXPORT_SYMBOL_NS(sym, sec, ns) \ - ___export_symbol_common(sym, sec); \ + = #sym; \ static const char __kstrtabns_##sym[] \ __attribute__((section("__ksymtab_strings"), used, aligned(1))) \ - = #ns; \ - __KSYMTAB_ENTRY_NS(sym, sec) - -#define ___EXPORT_SYMBOL(sym, sec) \ - ___export_symbol_common(sym, sec); \ + = ns; \ __KSYMTAB_ENTRY(sym, sec) #endif @@ -126,8 +102,7 @@ struct kernel_symbol { * be reused in other execution contexts such as the UEFI stub or the * decompressor. */ -#define __EXPORT_SYMBOL_NS(sym, sec, ns) -#define __EXPORT_SYMBOL(sym, sec) +#define __EXPORT_SYMBOL(sym, sec, ns) #elif defined(CONFIG_TRIM_UNUSED_KSYMS) @@ -143,48 +118,38 @@ struct kernel_symbol { #define __ksym_marker(sym) \ static int __ksym_marker_##sym[0] __section(".discard.ksym") __used -#define __EXPORT_SYMBOL(sym, sec) \ - __ksym_marker(sym); \ - __cond_export_sym(sym, sec, __is_defined(__KSYM_##sym)) -#define __cond_export_sym(sym, sec, conf) \ - ___cond_export_sym(sym, sec, conf) -#define ___cond_export_sym(sym, sec, enabled) \ - __cond_export_sym_##enabled(sym, sec) -#define __cond_export_sym_1(sym, sec) ___EXPORT_SYMBOL(sym, sec) -#define __cond_export_sym_0(sym, sec) /* nothing */ - -#define __EXPORT_SYMBOL_NS(sym, sec, ns) \ +#define __EXPORT_SYMBOL(sym, sec, ns) \ __ksym_marker(sym); \ - __cond_export_ns_sym(sym, sec, ns, __is_defined(__KSYM_##sym)) -#define __cond_export_ns_sym(sym, sec, ns, conf) \ - ___cond_export_ns_sym(sym, sec, ns, conf) -#define ___cond_export_ns_sym(sym, sec, ns, enabled) \ - __cond_export_ns_sym_##enabled(sym, sec, ns) -#define __cond_export_ns_sym_1(sym, sec, ns) ___EXPORT_SYMBOL_NS(sym, sec, ns) -#define __cond_export_ns_sym_0(sym, sec, ns) /* nothing */ + __cond_export_sym(sym, sec, ns, __is_defined(__KSYM_##sym)) +#define __cond_export_sym(sym, sec, ns, conf) \ + ___cond_export_sym(sym, sec, ns, conf) +#define ___cond_export_sym(sym, sec, ns, enabled) \ + __cond_export_sym_##enabled(sym, sec, ns) +#define __cond_export_sym_1(sym, sec, ns) ___EXPORT_SYMBOL(sym, sec, ns) +#define __cond_export_sym_0(sym, sec, ns) /* nothing */ #else -#define __EXPORT_SYMBOL_NS(sym,sec,ns) ___EXPORT_SYMBOL_NS(sym,sec,ns) -#define __EXPORT_SYMBOL(sym,sec) ___EXPORT_SYMBOL(sym,sec) +#define __EXPORT_SYMBOL(sym, sec, ns) ___EXPORT_SYMBOL(sym, sec, ns) #endif /* CONFIG_MODULES */ #ifdef DEFAULT_SYMBOL_NAMESPACE -#undef __EXPORT_SYMBOL -#define __EXPORT_SYMBOL(sym, sec) \ - __EXPORT_SYMBOL_NS(sym, sec, DEFAULT_SYMBOL_NAMESPACE) +#include +#define _EXPORT_SYMBOL(sym, sec) __EXPORT_SYMBOL(sym, sec, __stringify(DEFAULT_SYMBOL_NAMESPACE)) +#else +#define _EXPORT_SYMBOL(sym, sec) __EXPORT_SYMBOL(sym, sec, "") #endif -#define EXPORT_SYMBOL(sym) __EXPORT_SYMBOL(sym, "") -#define EXPORT_SYMBOL_GPL(sym) __EXPORT_SYMBOL(sym, "_gpl") -#define EXPORT_SYMBOL_GPL_FUTURE(sym) __EXPORT_SYMBOL(sym, "_gpl_future") -#define EXPORT_SYMBOL_NS(sym, ns) __EXPORT_SYMBOL_NS(sym, "", ns) -#define EXPORT_SYMBOL_NS_GPL(sym, ns) __EXPORT_SYMBOL_NS(sym, "_gpl", ns) +#define EXPORT_SYMBOL(sym) _EXPORT_SYMBOL(sym, "") +#define EXPORT_SYMBOL_GPL(sym) _EXPORT_SYMBOL(sym, "_gpl") +#define EXPORT_SYMBOL_GPL_FUTURE(sym) _EXPORT_SYMBOL(sym, "_gpl_future") +#define EXPORT_SYMBOL_NS(sym, ns) __EXPORT_SYMBOL(sym, "", #ns) +#define EXPORT_SYMBOL_NS_GPL(sym, ns) __EXPORT_SYMBOL(sym, "_gpl", #ns) #ifdef CONFIG_UNUSED_SYMBOLS -#define EXPORT_UNUSED_SYMBOL(sym) __EXPORT_SYMBOL(sym, "_unused") -#define EXPORT_UNUSED_SYMBOL_GPL(sym) __EXPORT_SYMBOL(sym, "_unused_gpl") +#define EXPORT_UNUSED_SYMBOL(sym) _EXPORT_SYMBOL(sym, "_unused") +#define EXPORT_UNUSED_SYMBOL_GPL(sym) _EXPORT_SYMBOL(sym, "_unused_gpl") #else #define EXPORT_UNUSED_SYMBOL(sym) #define EXPORT_UNUSED_SYMBOL_GPL(sym) diff --git a/kernel/module.c b/kernel/module.c index ff2d7359a418..26c13173da3d 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1400,7 +1400,7 @@ static int verify_namespace_is_imported(const struct load_info *info, char *imported_namespace; namespace = kernel_symbol_namespace(sym); - if (namespace) { + if (namespace && namespace[0]) { imported_namespace = get_modinfo(info, "import_ns"); while (imported_namespace) { if (strcmp(namespace, imported_namespace) == 0) -- cgit v1.2.3 From 4df56a1eb130b8a5ff59ac0a1a025a0f8c3bcf59 Mon Sep 17 00:00:00 2001 From: Andreas Färber Date: Tue, 15 Aug 2017 23:50:56 +0200 Subject: dt-bindings: reset: Add Realtek RTD1295 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a header with symbolic reset indices for Realtek RTD1295 SoC. Naming was derived from reset-names in an OEM's Device Tree. Acked-by: Rob Herring [AF: Dropped RTD1295 specific binding definition, updated SPDX] Acked-by: Philipp Zabel Signed-off-by: Andreas Färber --- include/dt-bindings/reset/realtek,rtd1295.h | 111 ++++++++++++++++++++++++++++ 1 file changed, 111 insertions(+) create mode 100644 include/dt-bindings/reset/realtek,rtd1295.h (limited to 'include') diff --git a/include/dt-bindings/reset/realtek,rtd1295.h b/include/dt-bindings/reset/realtek,rtd1295.h new file mode 100644 index 000000000000..2c0cb6afe816 --- /dev/null +++ b/include/dt-bindings/reset/realtek,rtd1295.h @@ -0,0 +1,111 @@ +/* SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-2-Clause) */ +/* + * Realtek RTD1295 reset controllers + * + * Copyright (c) 2017 Andreas Färber + */ +#ifndef DT_BINDINGS_RESET_RTD1295_H +#define DT_BINDINGS_RESET_RTD1295_H + +/* soft reset 1 */ +#define RTD1295_RSTN_MISC 0 +#define RTD1295_RSTN_NAT 1 +#define RTD1295_RSTN_USB3_PHY0_POW 2 +#define RTD1295_RSTN_GSPI 3 +#define RTD1295_RSTN_USB3_P0_MDIO 4 +#define RTD1295_RSTN_SATA_0 5 +#define RTD1295_RSTN_USB 6 +#define RTD1295_RSTN_SATA_PHY_0 7 +#define RTD1295_RSTN_USB_PHY0 8 +#define RTD1295_RSTN_USB_PHY1 9 +#define RTD1295_RSTN_SATA_PHY_POW_0 10 +#define RTD1295_RSTN_SATA_FUNC_EXIST_0 11 +#define RTD1295_RSTN_HDMI 12 +#define RTD1295_RSTN_VE1 13 +#define RTD1295_RSTN_VE2 14 +#define RTD1295_RSTN_VE3 15 +#define RTD1295_RSTN_ETN 16 +#define RTD1295_RSTN_AIO 17 +#define RTD1295_RSTN_GPU 18 +#define RTD1295_RSTN_TVE 19 +#define RTD1295_RSTN_VO 20 +#define RTD1295_RSTN_LVDS 21 +#define RTD1295_RSTN_SE 22 +#define RTD1295_RSTN_DCU 23 +#define RTD1295_RSTN_DC_PHY 24 +#define RTD1295_RSTN_CP 25 +#define RTD1295_RSTN_MD 26 +#define RTD1295_RSTN_TP 27 +#define RTD1295_RSTN_AE 28 +#define RTD1295_RSTN_NF 29 +#define RTD1295_RSTN_MIPI 30 +#define RTD1295_RSTN_RSA 31 + +/* soft reset 2 */ +#define RTD1295_RSTN_ACPU 0 +#define RTD1295_RSTN_JPEG 1 +#define RTD1295_RSTN_USB_PHY3 2 +#define RTD1295_RSTN_USB_PHY2 3 +#define RTD1295_RSTN_USB3_PHY1_POW 4 +#define RTD1295_RSTN_USB3_P1_MDIO 5 +#define RTD1295_RSTN_PCIE0_STITCH 6 +#define RTD1295_RSTN_PCIE0_PHY 7 +#define RTD1295_RSTN_PCIE0 8 +#define RTD1295_RSTN_PCR_CNT 9 +#define RTD1295_RSTN_CR 10 +#define RTD1295_RSTN_EMMC 11 +#define RTD1295_RSTN_SDIO 12 +#define RTD1295_RSTN_PCIE0_CORE 13 +#define RTD1295_RSTN_PCIE0_POWER 14 +#define RTD1295_RSTN_PCIE0_NONSTICH 15 +#define RTD1295_RSTN_PCIE1_PHY 16 +#define RTD1295_RSTN_PCIE1 17 +#define RTD1295_RSTN_I2C_5 18 +#define RTD1295_RSTN_PCIE1_STITCH 19 +#define RTD1295_RSTN_PCIE1_CORE 20 +#define RTD1295_RSTN_PCIE1_POWER 21 +#define RTD1295_RSTN_PCIE1_NONSTICH 22 +#define RTD1295_RSTN_I2C_4 23 +#define RTD1295_RSTN_I2C_3 24 +#define RTD1295_RSTN_I2C_2 25 +#define RTD1295_RSTN_I2C_1 26 +#define RTD1295_RSTN_UR2 27 +#define RTD1295_RSTN_UR1 28 +#define RTD1295_RSTN_MISC_SC 29 +#define RTD1295_RSTN_CBUS_TX 30 +#define RTD1295_RSTN_SDS_PHY 31 + +/* soft reset 4 */ +#define RTD1295_RSTN_DCPHY_CRT 0 +#define RTD1295_RSTN_DCPHY_ALERT_RX 1 +#define RTD1295_RSTN_DCPHY_PTR 2 +#define RTD1295_RSTN_DCPHY_LDO 3 +#define RTD1295_RSTN_DCPHY_SSC_DIG 4 +#define RTD1295_RSTN_HDMIRX 5 +#define RTD1295_RSTN_CBUSRX 6 +#define RTD1295_RSTN_SATA_PHY_POW_1 7 +#define RTD1295_RSTN_SATA_FUNC_EXIST_1 8 +#define RTD1295_RSTN_SATA_PHY_1 9 +#define RTD1295_RSTN_SATA_1 10 +#define RTD1295_RSTN_FAN 11 +#define RTD1295_RSTN_HDMIRX_WRAP 12 +#define RTD1295_RSTN_PCIE0_PHY_MDIO 13 +#define RTD1295_RSTN_PCIE1_PHY_MDIO 14 +#define RTD1295_RSTN_DISP 15 + +/* iso reset */ +#define RTD1295_ISO_RSTN_IR 1 +#define RTD1295_ISO_RSTN_CEC0 2 +#define RTD1295_ISO_RSTN_CEC1 3 +#define RTD1295_ISO_RSTN_DP 4 +#define RTD1295_ISO_RSTN_CBUSTX 5 +#define RTD1295_ISO_RSTN_CBUSRX 6 +#define RTD1295_ISO_RSTN_EFUSE 7 +#define RTD1295_ISO_RSTN_UR0 8 +#define RTD1295_ISO_RSTN_GMAC 9 +#define RTD1295_ISO_RSTN_GPHY 10 +#define RTD1295_ISO_RSTN_I2C_0 11 +#define RTD1295_ISO_RSTN_I2C_1 12 +#define RTD1295_ISO_RSTN_CBUS 13 + +#endif -- cgit v1.2.3 From 494f8b10d832456a96be4ee7317425f6936cabc8 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Mon, 28 Oct 2019 11:32:32 -0500 Subject: resource: Add a resource_list_first_type helper A common pattern is looping over a resource_list just to get a matching entry with a specific type. Add resource_list_first_type() helper which implements this. Signed-off-by: Rob Herring Signed-off-by: Lorenzo Pieralisi --- include/linux/resource_ext.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/resource_ext.h b/include/linux/resource_ext.h index 06da59b23b79..ff0339df56af 100644 --- a/include/linux/resource_ext.h +++ b/include/linux/resource_ext.h @@ -66,4 +66,16 @@ resource_list_destroy_entry(struct resource_entry *entry) #define resource_list_for_each_entry_safe(entry, tmp, list) \ list_for_each_entry_safe((entry), (tmp), (list), node) +static inline struct resource_entry * +resource_list_first_type(struct list_head *list, unsigned long type) +{ + struct resource_entry *entry; + + resource_list_for_each_entry(entry, list) { + if (resource_type(entry->res) == type) + return entry; + } + return NULL; +} + #endif /* _LINUX_RESOURCE_EXT_H */ -- cgit v1.2.3 From b4941adb24c0676f77ddc25e6d7836b8245c47fc Mon Sep 17 00:00:00 2001 From: Ran Wang Date: Thu, 24 Oct 2019 17:26:42 +0800 Subject: PM: wakeup: Add routine to help fetch wakeup source object. Some user might want to go through all registered wakeup sources and doing things accordingly. For example, SoC PM driver might need to do HW programming to prevent powering down specific IP which wakeup source depending on. So add this API to help walk through all registered wakeup source objects on that list and return them one by one. Signed-off-by: Ran Wang Tested-by: Leonard Crestez Reviewed-by: Rafael J. Wysocki Signed-off-by: Li Yang --- drivers/base/power/wakeup.c | 54 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/pm_wakeup.h | 9 ++++++++ 2 files changed, 63 insertions(+) (limited to 'include') diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c index 5817b51d2b15..70a9edb5f525 100644 --- a/drivers/base/power/wakeup.c +++ b/drivers/base/power/wakeup.c @@ -247,6 +247,60 @@ void wakeup_source_unregister(struct wakeup_source *ws) } EXPORT_SYMBOL_GPL(wakeup_source_unregister); +/** + * wakeup_sources_read_lock - Lock wakeup source list for read. + * + * Returns an index of srcu lock for struct wakeup_srcu. + * This index must be passed to the matching wakeup_sources_read_unlock(). + */ +int wakeup_sources_read_lock(void) +{ + return srcu_read_lock(&wakeup_srcu); +} +EXPORT_SYMBOL_GPL(wakeup_sources_read_lock); + +/** + * wakeup_sources_read_unlock - Unlock wakeup source list. + * @idx: return value from corresponding wakeup_sources_read_lock() + */ +void wakeup_sources_read_unlock(int idx) +{ + srcu_read_unlock(&wakeup_srcu, idx); +} +EXPORT_SYMBOL_GPL(wakeup_sources_read_unlock); + +/** + * wakeup_sources_walk_start - Begin a walk on wakeup source list + * + * Returns first object of the list of wakeup sources. + * + * Note that to be safe, wakeup sources list needs to be locked by calling + * wakeup_source_read_lock() for this. + */ +struct wakeup_source *wakeup_sources_walk_start(void) +{ + struct list_head *ws_head = &wakeup_sources; + + return list_entry_rcu(ws_head->next, struct wakeup_source, entry); +} +EXPORT_SYMBOL_GPL(wakeup_sources_walk_start); + +/** + * wakeup_sources_walk_next - Get next wakeup source from the list + * @ws: Previous wakeup source object + * + * Note that to be safe, wakeup sources list needs to be locked by calling + * wakeup_source_read_lock() for this. + */ +struct wakeup_source *wakeup_sources_walk_next(struct wakeup_source *ws) +{ + struct list_head *ws_head = &wakeup_sources; + + return list_next_or_null_rcu(ws_head, &ws->entry, + struct wakeup_source, entry); +} +EXPORT_SYMBOL_GPL(wakeup_sources_walk_next); + /** * device_wakeup_attach - Attach a wakeup source object to a device object. * @dev: Device to handle. diff --git a/include/linux/pm_wakeup.h b/include/linux/pm_wakeup.h index 661efa029c96..aa3da6611533 100644 --- a/include/linux/pm_wakeup.h +++ b/include/linux/pm_wakeup.h @@ -63,6 +63,11 @@ struct wakeup_source { bool autosleep_enabled:1; }; +#define for_each_wakeup_source(ws) \ + for ((ws) = wakeup_sources_walk_start(); \ + (ws); \ + (ws) = wakeup_sources_walk_next((ws))) + #ifdef CONFIG_PM_SLEEP /* @@ -92,6 +97,10 @@ extern void wakeup_source_remove(struct wakeup_source *ws); extern struct wakeup_source *wakeup_source_register(struct device *dev, const char *name); extern void wakeup_source_unregister(struct wakeup_source *ws); +extern int wakeup_sources_read_lock(void); +extern void wakeup_sources_read_unlock(int idx); +extern struct wakeup_source *wakeup_sources_walk_start(void); +extern struct wakeup_source *wakeup_sources_walk_next(struct wakeup_source *ws); extern int device_wakeup_enable(struct device *dev); extern int device_wakeup_disable(struct device *dev); extern void device_set_wakeup_capable(struct device *dev, bool capable); -- cgit v1.2.3 From ff27e9f748303e8567bfceb6d7ff264cbcaca2ef Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 24 Oct 2019 09:34:10 -0400 Subject: SUNRPC: Trace gssproxy upcall results Record results of a GSS proxy ACCEPT_SEC_CONTEXT upcall and the svc_authenticate() function to make field debugging of NFS server Kerberos issues easier. Signed-off-by: Chuck Lever Reviewed-by: Bill Baker Signed-off-by: J. Bruce Fields --- include/trace/events/rpcgss.h | 45 ++++++++++++++++++++++++++++ include/trace/events/sunrpc.h | 55 +++++++++++++++++++++++++++++++++++ net/sunrpc/auth_gss/gss_mech_switch.c | 4 ++- net/sunrpc/auth_gss/svcauth_gss.c | 8 +++-- net/sunrpc/svc.c | 2 ++ net/sunrpc/svcauth.c | 2 ++ 6 files changed, 112 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/trace/events/rpcgss.h b/include/trace/events/rpcgss.h index d1f7fe1b6fe4..9827f535f032 100644 --- a/include/trace/events/rpcgss.h +++ b/include/trace/events/rpcgss.h @@ -126,6 +126,34 @@ DEFINE_GSSAPI_EVENT(verify_mic); DEFINE_GSSAPI_EVENT(wrap); DEFINE_GSSAPI_EVENT(unwrap); +TRACE_EVENT(rpcgss_accept_upcall, + TP_PROTO( + __be32 xid, + u32 major_status, + u32 minor_status + ), + + TP_ARGS(xid, major_status, minor_status), + + TP_STRUCT__entry( + __field(u32, xid) + __field(u32, minor_status) + __field(unsigned long, major_status) + ), + + TP_fast_assign( + __entry->xid = be32_to_cpu(xid); + __entry->minor_status = minor_status; + __entry->major_status = major_status; + ), + + TP_printk("xid=0x%08x major_status=%s (0x%08lx) minor_status=%u", + __entry->xid, __entry->major_status == 0 ? "GSS_S_COMPLETE" : + show_gss_status(__entry->major_status), + __entry->major_status, __entry->minor_status + ) +); + /** ** GSS auth unwrap failures @@ -355,6 +383,23 @@ TRACE_EVENT(rpcgss_createauth, show_pseudoflavor(__entry->flavor), __entry->error) ); +TRACE_EVENT(rpcgss_oid_to_mech, + TP_PROTO( + const char *oid + ), + + TP_ARGS(oid), + + TP_STRUCT__entry( + __string(oid, oid) + ), + + TP_fast_assign( + __assign_str(oid, oid); + ), + + TP_printk("mech for oid %s was not found", __get_str(oid)) +); #endif /* _TRACE_RPCGSS_H */ diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index ffa3c51dbb1a..c358a0af683b 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -14,6 +14,26 @@ #include #include +TRACE_DEFINE_ENUM(RPC_AUTH_OK); +TRACE_DEFINE_ENUM(RPC_AUTH_BADCRED); +TRACE_DEFINE_ENUM(RPC_AUTH_REJECTEDCRED); +TRACE_DEFINE_ENUM(RPC_AUTH_BADVERF); +TRACE_DEFINE_ENUM(RPC_AUTH_REJECTEDVERF); +TRACE_DEFINE_ENUM(RPC_AUTH_TOOWEAK); +TRACE_DEFINE_ENUM(RPCSEC_GSS_CREDPROBLEM); +TRACE_DEFINE_ENUM(RPCSEC_GSS_CTXPROBLEM); + +#define rpc_show_auth_stat(status) \ + __print_symbolic(status, \ + { RPC_AUTH_OK, "AUTH_OK" }, \ + { RPC_AUTH_BADCRED, "BADCRED" }, \ + { RPC_AUTH_REJECTEDCRED, "REJECTEDCRED" }, \ + { RPC_AUTH_BADVERF, "BADVERF" }, \ + { RPC_AUTH_REJECTEDVERF, "REJECTEDVERF" }, \ + { RPC_AUTH_TOOWEAK, "TOOWEAK" }, \ + { RPCSEC_GSS_CREDPROBLEM, "GSS_CREDPROBLEM" }, \ + { RPCSEC_GSS_CTXPROBLEM, "GSS_CTXPROBLEM" }) \ + DECLARE_EVENT_CLASS(rpc_task_status, TP_PROTO(const struct rpc_task *task), @@ -866,6 +886,41 @@ TRACE_EVENT(svc_recv, show_rqstp_flags(__entry->flags)) ); +#define svc_show_status(status) \ + __print_symbolic(status, \ + { SVC_GARBAGE, "SVC_GARBAGE" }, \ + { SVC_SYSERR, "SVC_SYSERR" }, \ + { SVC_VALID, "SVC_VALID" }, \ + { SVC_NEGATIVE, "SVC_NEGATIVE" }, \ + { SVC_OK, "SVC_OK" }, \ + { SVC_DROP, "SVC_DROP" }, \ + { SVC_CLOSE, "SVC_CLOSE" }, \ + { SVC_DENIED, "SVC_DENIED" }, \ + { SVC_PENDING, "SVC_PENDING" }, \ + { SVC_COMPLETE, "SVC_COMPLETE" }) + +TRACE_EVENT(svc_authenticate, + TP_PROTO(const struct svc_rqst *rqst, int auth_res, __be32 auth_stat), + + TP_ARGS(rqst, auth_res, auth_stat), + + TP_STRUCT__entry( + __field(u32, xid) + __field(unsigned long, svc_status) + __field(unsigned long, auth_stat) + ), + + TP_fast_assign( + __entry->xid = be32_to_cpu(rqst->rq_xid); + __entry->svc_status = auth_res; + __entry->auth_stat = be32_to_cpu(auth_stat); + ), + + TP_printk("xid=0x%08x auth_res=%s auth_stat=%s", + __entry->xid, svc_show_status(__entry->svc_status), + rpc_show_auth_stat(__entry->auth_stat)) +); + TRACE_EVENT(svc_process, TP_PROTO(const struct svc_rqst *rqst, const char *name), diff --git a/net/sunrpc/auth_gss/gss_mech_switch.c b/net/sunrpc/auth_gss/gss_mech_switch.c index 82060099a429..30b7de6f3d76 100644 --- a/net/sunrpc/auth_gss/gss_mech_switch.c +++ b/net/sunrpc/auth_gss/gss_mech_switch.c @@ -20,6 +20,7 @@ #include #include #include +#include #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH @@ -158,7 +159,6 @@ struct gss_api_mech *gss_mech_get_by_OID(struct rpcsec_gss_oid *obj) if (sprint_oid(obj->data, obj->len, buf, sizeof(buf)) < 0) return NULL; - dprintk("RPC: %s(%s)\n", __func__, buf); request_module("rpc-auth-gss-%s", buf); rcu_read_lock(); @@ -172,6 +172,8 @@ struct gss_api_mech *gss_mech_get_by_OID(struct rpcsec_gss_oid *obj) } } rcu_read_unlock(); + if (!gm) + trace_rpcgss_oid_to_mech(buf); return gm; } diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 8be2f209982b..f1309905aed3 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -49,6 +49,9 @@ #include #include #include + +#include + #include "gss_rpc_upcall.h" @@ -1270,9 +1273,8 @@ static int svcauth_gss_proxy_init(struct svc_rqst *rqstp, if (status) goto out; - dprintk("RPC: svcauth_gss: gss major status = %d " - "minor status = %d\n", - ud.major_status, ud.minor_status); + trace_rpcgss_accept_upcall(rqstp->rq_xid, ud.major_status, + ud.minor_status); switch (ud.major_status) { case GSS_S_CONTINUE_NEEDED: diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index d11b70552c33..187dd4e73d64 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1337,6 +1337,8 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) auth_stat = rpc_autherr_badcred; auth_res = progp->pg_authenticate(rqstp); } + if (auth_res != SVC_OK) + trace_svc_authenticate(rqstp, auth_res, auth_stat); switch (auth_res) { case SVC_OK: break; diff --git a/net/sunrpc/svcauth.c b/net/sunrpc/svcauth.c index 550b214cb001..552617e3467b 100644 --- a/net/sunrpc/svcauth.c +++ b/net/sunrpc/svcauth.c @@ -19,6 +19,8 @@ #include #include +#include + #define RPCDBG_FACILITY RPCDBG_AUTH -- cgit v1.2.3 From 6eb045e092efefafc6687409a6fa6d1dabf0fb69 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 25 Oct 2019 14:58:55 +0800 Subject: scsi: core: avoid host-wide host_busy counter for scsi_mq It isn't necessary to check the host depth in scsi_queue_rq() any more since it has been respected by blk-mq before calling scsi_queue_rq() via getting driver tag. Lots of LUNs may attach to same host and per-host IOPS may reach millions, so we should avoid expensive atomic operations on the host-wide counter in the IO path. This patch implements scsi_host_busy() via blk_mq_tagset_busy_iter() with one scsi command state for reading the count of busy IOs for scsi_mq. It is observed that IOPS is increased by 15% in IO test on scsi_debug (32 LUNs, 32 submit queues, 1024 can_queue, libaio/dio) in a dual-socket system. Cc: Jens Axboe Cc: Ewan D. Milne Cc: Omar Sandoval , Cc: "Martin K. Petersen" , Cc: James Bottomley , Cc: Christoph Hellwig , Cc: Kashyap Desai Cc: Hannes Reinecke Cc: Laurence Oberman Cc: Bart Van Assche Link: https://lore.kernel.org/r/20191025065855.6309-1-ming.lei@redhat.com Signed-off-by: Ming Lei Reviewed-by: Jens Axboe Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- drivers/scsi/hosts.c | 19 ++++++++++++++++++- drivers/scsi/scsi.c | 2 +- drivers/scsi/scsi_lib.c | 45 ++++++++++++++++++++++----------------------- drivers/scsi/scsi_priv.h | 2 +- include/scsi/scsi_cmnd.h | 1 + include/scsi/scsi_host.h | 3 +-- 6 files changed, 44 insertions(+), 28 deletions(-) (limited to 'include') diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c index 55522b7162d3..1d669e47b692 100644 --- a/drivers/scsi/hosts.c +++ b/drivers/scsi/hosts.c @@ -38,6 +38,7 @@ #include #include #include +#include #include "scsi_priv.h" #include "scsi_logging.h" @@ -554,13 +555,29 @@ struct Scsi_Host *scsi_host_get(struct Scsi_Host *shost) } EXPORT_SYMBOL(scsi_host_get); +static bool scsi_host_check_in_flight(struct request *rq, void *data, + bool reserved) +{ + int *count = data; + struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq); + + if (test_bit(SCMD_STATE_INFLIGHT, &cmd->state)) + (*count)++; + + return true; +} + /** * scsi_host_busy - Return the host busy counter * @shost: Pointer to Scsi_Host to inc. **/ int scsi_host_busy(struct Scsi_Host *shost) { - return atomic_read(&shost->host_busy); + int cnt = 0; + + blk_mq_tagset_busy_iter(&shost->tag_set, + scsi_host_check_in_flight, &cnt); + return cnt; } EXPORT_SYMBOL(scsi_host_busy); diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c index 4f76841a7038..adfe8b3693d5 100644 --- a/drivers/scsi/scsi.c +++ b/drivers/scsi/scsi.c @@ -186,7 +186,7 @@ void scsi_finish_command(struct scsi_cmnd *cmd) struct scsi_driver *drv; unsigned int good_bytes; - scsi_device_unbusy(sdev); + scsi_device_unbusy(sdev, cmd); /* * Clear the flags that say that the device/target/host is no longer diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index dc210b9d4896..2563b061f56b 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -189,7 +189,7 @@ static void __scsi_queue_insert(struct scsi_cmnd *cmd, int reason, bool unbusy) * active on the host/device. */ if (unbusy) - scsi_device_unbusy(device); + scsi_device_unbusy(device, cmd); /* * Requeue this command. It will go before all other commands @@ -321,20 +321,20 @@ static void scsi_init_cmd_errh(struct scsi_cmnd *cmd) } /* - * Decrement the host_busy counter and wake up the error handler if necessary. - * Avoid as follows that the error handler is not woken up if shost->host_busy - * == shost->host_failed: use call_rcu() in scsi_eh_scmd_add() in combination - * with an RCU read lock in this function to ensure that this function in its - * entirety either finishes before scsi_eh_scmd_add() increases the + * Wake up the error handler if necessary. Avoid as follows that the error + * handler is not woken up if host in-flight requests number == + * shost->host_failed: use call_rcu() in scsi_eh_scmd_add() in combination + * with an RCU read lock in this function to ensure that this function in + * its entirety either finishes before scsi_eh_scmd_add() increases the * host_failed counter or that it notices the shost state change made by * scsi_eh_scmd_add(). */ -static void scsi_dec_host_busy(struct Scsi_Host *shost) +static void scsi_dec_host_busy(struct Scsi_Host *shost, struct scsi_cmnd *cmd) { unsigned long flags; rcu_read_lock(); - atomic_dec(&shost->host_busy); + __clear_bit(SCMD_STATE_INFLIGHT, &cmd->state); if (unlikely(scsi_host_in_recovery(shost))) { spin_lock_irqsave(shost->host_lock, flags); if (shost->host_failed || shost->host_eh_scheduled) @@ -344,12 +344,12 @@ static void scsi_dec_host_busy(struct Scsi_Host *shost) rcu_read_unlock(); } -void scsi_device_unbusy(struct scsi_device *sdev) +void scsi_device_unbusy(struct scsi_device *sdev, struct scsi_cmnd *cmd) { struct Scsi_Host *shost = sdev->host; struct scsi_target *starget = scsi_target(sdev); - scsi_dec_host_busy(shost); + scsi_dec_host_busy(shost, cmd); if (starget->can_queue > 0) atomic_dec(&starget->target_busy); @@ -430,9 +430,6 @@ static inline bool scsi_target_is_busy(struct scsi_target *starget) static inline bool scsi_host_is_busy(struct Scsi_Host *shost) { - if (shost->can_queue > 0 && - atomic_read(&shost->host_busy) >= shost->can_queue) - return true; if (atomic_read(&shost->host_blocked) > 0) return true; if (shost->host_self_blocked) @@ -1139,6 +1136,7 @@ void scsi_init_command(struct scsi_device *dev, struct scsi_cmnd *cmd) unsigned int flags = cmd->flags & SCMD_PRESERVED_FLAGS; unsigned long jiffies_at_alloc; int retries; + bool in_flight; if (!blk_rq_is_scsi(rq) && !(flags & SCMD_INITIALIZED)) { flags |= SCMD_INITIALIZED; @@ -1147,6 +1145,7 @@ void scsi_init_command(struct scsi_device *dev, struct scsi_cmnd *cmd) jiffies_at_alloc = cmd->jiffies_at_alloc; retries = cmd->retries; + in_flight = test_bit(SCMD_STATE_INFLIGHT, &cmd->state); /* zero out the cmd, except for the embedded scsi_request */ memset((char *)cmd + sizeof(cmd->req), 0, sizeof(*cmd) - sizeof(cmd->req) + dev->host->hostt->cmd_size); @@ -1158,6 +1157,8 @@ void scsi_init_command(struct scsi_device *dev, struct scsi_cmnd *cmd) INIT_DELAYED_WORK(&cmd->abort_work, scmd_eh_abort_handler); cmd->jiffies_at_alloc = jiffies_at_alloc; cmd->retries = retries; + if (in_flight) + __set_bit(SCMD_STATE_INFLIGHT, &cmd->state); scsi_add_cmd_to_list(cmd); } @@ -1367,16 +1368,14 @@ out_dec: */ static inline int scsi_host_queue_ready(struct request_queue *q, struct Scsi_Host *shost, - struct scsi_device *sdev) + struct scsi_device *sdev, + struct scsi_cmnd *cmd) { - unsigned int busy; - if (scsi_host_in_recovery(shost)) return 0; - busy = atomic_inc_return(&shost->host_busy) - 1; if (atomic_read(&shost->host_blocked) > 0) { - if (busy) + if (scsi_host_busy(shost) > 0) goto starved; /* @@ -1390,8 +1389,6 @@ static inline int scsi_host_queue_ready(struct request_queue *q, "unblocking host at zero depth\n")); } - if (shost->can_queue > 0 && busy >= shost->can_queue) - goto starved; if (shost->host_self_blocked) goto starved; @@ -1403,6 +1400,8 @@ static inline int scsi_host_queue_ready(struct request_queue *q, spin_unlock_irq(shost->host_lock); } + __set_bit(SCMD_STATE_INFLIGHT, &cmd->state); + return 1; starved: @@ -1411,7 +1410,7 @@ starved: list_add_tail(&sdev->starved_entry, &shost->starved_list); spin_unlock_irq(shost->host_lock); out_dec: - scsi_dec_host_busy(shost); + scsi_dec_host_busy(shost, cmd); return 0; } @@ -1665,7 +1664,7 @@ static blk_status_t scsi_queue_rq(struct blk_mq_hw_ctx *hctx, ret = BLK_STS_RESOURCE; if (!scsi_target_queue_ready(shost, sdev)) goto out_put_budget; - if (!scsi_host_queue_ready(q, shost, sdev)) + if (!scsi_host_queue_ready(q, shost, sdev, cmd)) goto out_dec_target_busy; if (!(req->rq_flags & RQF_DONTPREP)) { @@ -1697,7 +1696,7 @@ static blk_status_t scsi_queue_rq(struct blk_mq_hw_ctx *hctx, return BLK_STS_OK; out_dec_host_busy: - scsi_dec_host_busy(shost); + scsi_dec_host_busy(shost, cmd); out_dec_target_busy: if (scsi_target(sdev)->can_queue > 0) atomic_dec(&scsi_target(sdev)->target_busy); diff --git a/drivers/scsi/scsi_priv.h b/drivers/scsi/scsi_priv.h index cc2859d76d81..3bff9f7aa684 100644 --- a/drivers/scsi/scsi_priv.h +++ b/drivers/scsi/scsi_priv.h @@ -87,7 +87,7 @@ int scsi_noretry_cmd(struct scsi_cmnd *scmd); extern void scsi_add_cmd_to_list(struct scsi_cmnd *cmd); extern void scsi_del_cmd_from_list(struct scsi_cmnd *cmd); extern int scsi_maybe_unblock_host(struct scsi_device *sdev); -extern void scsi_device_unbusy(struct scsi_device *sdev); +extern void scsi_device_unbusy(struct scsi_device *sdev, struct scsi_cmnd *cmd); extern void scsi_queue_insert(struct scsi_cmnd *cmd, int reason); extern void scsi_io_completion(struct scsi_cmnd *, unsigned int); extern void scsi_run_host_queues(struct Scsi_Host *shost); diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h index 91bd749a02f7..9c22e85902ec 100644 --- a/include/scsi/scsi_cmnd.h +++ b/include/scsi/scsi_cmnd.h @@ -63,6 +63,7 @@ struct scsi_pointer { /* for scmd->state */ #define SCMD_STATE_COMPLETE 0 +#define SCMD_STATE_INFLIGHT 1 struct scsi_cmnd { struct scsi_request req; diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h index 2c3f0c58869b..fccdf84ec7e2 100644 --- a/include/scsi/scsi_host.h +++ b/include/scsi/scsi_host.h @@ -345,7 +345,7 @@ struct scsi_host_template { /* * This determines if we will use a non-interrupt driven * or an interrupt driven scheme. It is set to the maximum number - * of simultaneous commands a given host adapter will accept. + * of simultaneous commands a single hw queue in HBA will accept. */ int can_queue; @@ -554,7 +554,6 @@ struct Scsi_Host { /* Area to keep a shared tag map */ struct blk_mq_tag_set tag_set; - atomic_t host_busy; /* commands actually active on low-level */ atomic_t host_blocked; unsigned int host_failed; /* commands that failed. -- cgit v1.2.3 From e86d5a02874c1364c50e1b532481835b54173ed2 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 4 Oct 2019 16:38:56 -0400 Subject: NFS: Convert struct nfs_fattr to use struct timespec64 NFSv4 supports 64-bit times, so we should switch to using struct timespec64 when decoding attributes. Signed-off-by: Trond Myklebust --- fs/nfs/inode.c | 54 +++++++++++++++++++++++------------------------ fs/nfs/internal.h | 2 +- fs/nfs/nfs2xdr.c | 2 +- fs/nfs/nfs3xdr.c | 2 +- fs/nfs/nfs4xdr.c | 14 ++++++------ include/linux/nfs_fs_sb.h | 2 +- include/linux/nfs_xdr.h | 12 +++++------ 7 files changed, 44 insertions(+), 44 deletions(-) (limited to 'include') diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 2a03bfeec10a..b0b4b9f303fd 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -504,15 +504,15 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st nfsi->read_cache_jiffies = fattr->time_start; nfsi->attr_gencount = fattr->gencount; if (fattr->valid & NFS_ATTR_FATTR_ATIME) - inode->i_atime = timespec_to_timespec64(fattr->atime); + inode->i_atime = fattr->atime; else if (nfs_server_capable(inode, NFS_CAP_ATIME)) nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATIME); if (fattr->valid & NFS_ATTR_FATTR_MTIME) - inode->i_mtime = timespec_to_timespec64(fattr->mtime); + inode->i_mtime = fattr->mtime; else if (nfs_server_capable(inode, NFS_CAP_MTIME)) nfs_set_cache_invalid(inode, NFS_INO_INVALID_MTIME); if (fattr->valid & NFS_ATTR_FATTR_CTIME) - inode->i_ctime = timespec_to_timespec64(fattr->ctime); + inode->i_ctime = fattr->ctime; else if (nfs_server_capable(inode, NFS_CAP_CTIME)) nfs_set_cache_invalid(inode, NFS_INO_INVALID_CTIME); if (fattr->valid & NFS_ATTR_FATTR_CHANGE) @@ -698,7 +698,7 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, if ((attr->ia_valid & ATTR_GID) != 0) inode->i_gid = attr->ia_gid; if (fattr->valid & NFS_ATTR_FATTR_CTIME) - inode->i_ctime = timespec_to_timespec64(fattr->ctime); + inode->i_ctime = fattr->ctime; else nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME); @@ -709,14 +709,14 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, NFS_I(inode)->cache_validity &= ~(NFS_INO_INVALID_ATIME | NFS_INO_INVALID_CTIME); if (fattr->valid & NFS_ATTR_FATTR_ATIME) - inode->i_atime = timespec_to_timespec64(fattr->atime); + inode->i_atime = fattr->atime; else if (attr->ia_valid & ATTR_ATIME_SET) inode->i_atime = attr->ia_atime; else nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATIME); if (fattr->valid & NFS_ATTR_FATTR_CTIME) - inode->i_ctime = timespec_to_timespec64(fattr->ctime); + inode->i_ctime = fattr->ctime; else nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME); @@ -725,14 +725,14 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, NFS_I(inode)->cache_validity &= ~(NFS_INO_INVALID_MTIME | NFS_INO_INVALID_CTIME); if (fattr->valid & NFS_ATTR_FATTR_MTIME) - inode->i_mtime = timespec_to_timespec64(fattr->mtime); + inode->i_mtime = fattr->mtime; else if (attr->ia_valid & ATTR_MTIME_SET) inode->i_mtime = attr->ia_mtime; else nfs_set_cache_invalid(inode, NFS_INO_INVALID_MTIME); if (fattr->valid & NFS_ATTR_FATTR_CTIME) - inode->i_ctime = timespec_to_timespec64(fattr->ctime); + inode->i_ctime = fattr->ctime; else nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME); @@ -1351,7 +1351,7 @@ static bool nfs_file_has_buffered_writers(struct nfs_inode *nfsi) static void nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr) { - struct timespec ts; + struct timespec64 ts; if ((fattr->valid & NFS_ATTR_FATTR_PRECHANGE) && (fattr->valid & NFS_ATTR_FATTR_CHANGE) @@ -1361,18 +1361,18 @@ static void nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr) nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA); } /* If we have atomic WCC data, we may update some attributes */ - ts = timespec64_to_timespec(inode->i_ctime); + ts = inode->i_ctime; if ((fattr->valid & NFS_ATTR_FATTR_PRECTIME) && (fattr->valid & NFS_ATTR_FATTR_CTIME) - && timespec_equal(&ts, &fattr->pre_ctime)) { - inode->i_ctime = timespec_to_timespec64(fattr->ctime); + && timespec64_equal(&ts, &fattr->pre_ctime)) { + inode->i_ctime = fattr->ctime; } - ts = timespec64_to_timespec(inode->i_mtime); + ts = inode->i_mtime; if ((fattr->valid & NFS_ATTR_FATTR_PREMTIME) && (fattr->valid & NFS_ATTR_FATTR_MTIME) - && timespec_equal(&ts, &fattr->pre_mtime)) { - inode->i_mtime = timespec_to_timespec64(fattr->mtime); + && timespec64_equal(&ts, &fattr->pre_mtime)) { + inode->i_mtime = fattr->mtime; if (S_ISDIR(inode->i_mode)) nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA); } @@ -1398,7 +1398,7 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat struct nfs_inode *nfsi = NFS_I(inode); loff_t cur_size, new_isize; unsigned long invalid = 0; - struct timespec ts; + struct timespec64 ts; if (NFS_PROTO(inode)->have_delegation(inode, FMODE_READ)) return 0; @@ -1425,12 +1425,12 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat invalid |= NFS_INO_INVALID_CHANGE | NFS_INO_REVAL_PAGECACHE; - ts = timespec64_to_timespec(inode->i_mtime); - if ((fattr->valid & NFS_ATTR_FATTR_MTIME) && !timespec_equal(&ts, &fattr->mtime)) + ts = inode->i_mtime; + if ((fattr->valid & NFS_ATTR_FATTR_MTIME) && !timespec64_equal(&ts, &fattr->mtime)) invalid |= NFS_INO_INVALID_MTIME; - ts = timespec64_to_timespec(inode->i_ctime); - if ((fattr->valid & NFS_ATTR_FATTR_CTIME) && !timespec_equal(&ts, &fattr->ctime)) + ts = inode->i_ctime; + if ((fattr->valid & NFS_ATTR_FATTR_CTIME) && !timespec64_equal(&ts, &fattr->ctime)) invalid |= NFS_INO_INVALID_CTIME; if (fattr->valid & NFS_ATTR_FATTR_SIZE) { @@ -1460,8 +1460,8 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat if ((fattr->valid & NFS_ATTR_FATTR_NLINK) && inode->i_nlink != fattr->nlink) invalid |= NFS_INO_INVALID_OTHER; - ts = timespec64_to_timespec(inode->i_atime); - if ((fattr->valid & NFS_ATTR_FATTR_ATIME) && !timespec_equal(&ts, &fattr->atime)) + ts = inode->i_atime; + if ((fattr->valid & NFS_ATTR_FATTR_ATIME) && !timespec64_equal(&ts, &fattr->atime)) invalid |= NFS_INO_INVALID_ATIME; if (invalid != 0) @@ -1733,12 +1733,12 @@ int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fa } if ((fattr->valid & NFS_ATTR_FATTR_CTIME) != 0 && (fattr->valid & NFS_ATTR_FATTR_PRECTIME) == 0) { - fattr->pre_ctime = timespec64_to_timespec(inode->i_ctime); + fattr->pre_ctime = inode->i_ctime; fattr->valid |= NFS_ATTR_FATTR_PRECTIME; } if ((fattr->valid & NFS_ATTR_FATTR_MTIME) != 0 && (fattr->valid & NFS_ATTR_FATTR_PREMTIME) == 0) { - fattr->pre_mtime = timespec64_to_timespec(inode->i_mtime); + fattr->pre_mtime = inode->i_mtime; fattr->valid |= NFS_ATTR_FATTR_PREMTIME; } if ((fattr->valid & NFS_ATTR_FATTR_SIZE) != 0 && @@ -1899,7 +1899,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) } if (fattr->valid & NFS_ATTR_FATTR_MTIME) { - inode->i_mtime = timespec_to_timespec64(fattr->mtime); + inode->i_mtime = fattr->mtime; } else if (server->caps & NFS_CAP_MTIME) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_MTIME @@ -1908,7 +1908,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) } if (fattr->valid & NFS_ATTR_FATTR_CTIME) { - inode->i_ctime = timespec_to_timespec64(fattr->ctime); + inode->i_ctime = fattr->ctime; } else if (server->caps & NFS_CAP_CTIME) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_CTIME @@ -1946,7 +1946,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) if (fattr->valid & NFS_ATTR_FATTR_ATIME) - inode->i_atime = timespec_to_timespec64(fattr->atime); + inode->i_atime = fattr->atime; else if (server->caps & NFS_CAP_ATIME) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATIME diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 447a3c17fa8e..24a65da58aa9 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -713,7 +713,7 @@ unsigned int nfs_page_array_len(unsigned int base, size_t len) * 1024*1024*1024. */ static inline -u64 nfs_timespec_to_change_attr(const struct timespec *ts) +u64 nfs_timespec_to_change_attr(const struct timespec64 *ts) { return ((u64)ts->tv_sec << 30) + ts->tv_nsec; } diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c index cbc17a203248..d4e144712034 100644 --- a/fs/nfs/nfs2xdr.c +++ b/fs/nfs/nfs2xdr.c @@ -234,7 +234,7 @@ static __be32 *xdr_encode_current_server_time(__be32 *p, return p; } -static __be32 *xdr_decode_time(__be32 *p, struct timespec *timep) +static __be32 *xdr_decode_time(__be32 *p, struct timespec64 *timep) { timep->tv_sec = be32_to_cpup(p++); timep->tv_nsec = be32_to_cpup(p++) * NSEC_PER_USEC; diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index 602767850b36..2a16bbda3937 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -463,7 +463,7 @@ static __be32 *xdr_encode_nfstime3(__be32 *p, const struct timespec *timep) return p; } -static __be32 *xdr_decode_nfstime3(__be32 *p, struct timespec *timep) +static __be32 *xdr_decode_nfstime3(__be32 *p, struct timespec64 *timep) { timep->tv_sec = be32_to_cpup(p++); timep->tv_nsec = be32_to_cpup(p++); diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index ab07db0f07cd..2af962810ed8 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -4065,17 +4065,17 @@ static int decode_attr_space_used(struct xdr_stream *xdr, uint32_t *bitmap, uint } static __be32 * -xdr_decode_nfstime4(__be32 *p, struct timespec *t) +xdr_decode_nfstime4(__be32 *p, struct timespec64 *t) { __u64 sec; p = xdr_decode_hyper(p, &sec); - t-> tv_sec = (time_t)sec; + t-> tv_sec = sec; t->tv_nsec = be32_to_cpup(p++); return p; } -static int decode_attr_time(struct xdr_stream *xdr, struct timespec *time) +static int decode_attr_time(struct xdr_stream *xdr, struct timespec64 *time) { __be32 *p; @@ -4086,7 +4086,7 @@ static int decode_attr_time(struct xdr_stream *xdr, struct timespec *time) return 0; } -static int decode_attr_time_access(struct xdr_stream *xdr, uint32_t *bitmap, struct timespec *time) +static int decode_attr_time_access(struct xdr_stream *xdr, uint32_t *bitmap, struct timespec64 *time) { int status = 0; @@ -4104,7 +4104,7 @@ static int decode_attr_time_access(struct xdr_stream *xdr, uint32_t *bitmap, str return status; } -static int decode_attr_time_metadata(struct xdr_stream *xdr, uint32_t *bitmap, struct timespec *time) +static int decode_attr_time_metadata(struct xdr_stream *xdr, uint32_t *bitmap, struct timespec64 *time) { int status = 0; @@ -4123,7 +4123,7 @@ static int decode_attr_time_metadata(struct xdr_stream *xdr, uint32_t *bitmap, s } static int decode_attr_time_delta(struct xdr_stream *xdr, uint32_t *bitmap, - struct timespec *time) + struct timespec64 *time) { int status = 0; @@ -4186,7 +4186,7 @@ static int decode_attr_security_label(struct xdr_stream *xdr, uint32_t *bitmap, return status; } -static int decode_attr_time_modify(struct xdr_stream *xdr, uint32_t *bitmap, struct timespec *time) +static int decode_attr_time_modify(struct xdr_stream *xdr, uint32_t *bitmap, struct timespec64 *time) { int status = 0; diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index a87fe854f008..47266870a235 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -171,7 +171,7 @@ struct nfs_server { struct nfs_fsid fsid; __u64 maxfilesize; /* maximum file size */ - struct timespec time_delta; /* smallest time granularity */ + struct timespec64 time_delta; /* smallest time granularity */ unsigned long mount_time; /* when this fs was mounted */ struct super_block *super; /* VFS super block */ dev_t s_dev; /* superblock dev numbers */ diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 9b8324ec08f3..db5c01001937 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -62,14 +62,14 @@ struct nfs_fattr { struct nfs_fsid fsid; __u64 fileid; __u64 mounted_on_fileid; - struct timespec atime; - struct timespec mtime; - struct timespec ctime; + struct timespec64 atime; + struct timespec64 mtime; + struct timespec64 ctime; __u64 change_attr; /* NFSv4 change attribute */ __u64 pre_change_attr;/* pre-op NFSv4 change attribute */ __u64 pre_size; /* pre_op_attr.size */ - struct timespec pre_mtime; /* pre_op_attr.mtime */ - struct timespec pre_ctime; /* pre_op_attr.ctime */ + struct timespec64 pre_mtime; /* pre_op_attr.mtime */ + struct timespec64 pre_ctime; /* pre_op_attr.ctime */ unsigned long time_start; unsigned long gencount; struct nfs4_string *owner_name; @@ -143,7 +143,7 @@ struct nfs_fsinfo { __u32 wtmult; /* writes should be multiple of this */ __u32 dtpref; /* pref. readdir transfer size */ __u64 maxfilesize; - struct timespec time_delta; /* server time granularity */ + struct timespec64 time_delta; /* server time granularity */ __u32 lease_time; /* in seconds */ __u32 nlayouttypes; /* number of layouttypes */ __u32 layouttype[NFS_MAX_LAYOUT_TYPES]; /* supported pnfs layout driver */ -- cgit v1.2.3 From 6430b323ae09f146dfc26e6d17c432bfc3d11452 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 4 Oct 2019 17:00:02 -0400 Subject: NFSv3: Clean up timespec encode Simplify the struct iattr timestamp encoding by skipping the step of an intermediate struct timespec. Signed-off-by: Trond Myklebust --- fs/nfs/nfs3xdr.c | 12 ++++-------- include/linux/nfs_xdr.h | 2 +- 2 files changed, 5 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index 2a16bbda3937..927eb680f161 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -456,9 +456,9 @@ static void zero_nfs_fh3(struct nfs_fh *fh) * uint32 nseconds; * }; */ -static __be32 *xdr_encode_nfstime3(__be32 *p, const struct timespec *timep) +static __be32 *xdr_encode_nfstime3(__be32 *p, const struct timespec64 *timep) { - *p++ = cpu_to_be32(timep->tv_sec); + *p++ = cpu_to_be32((u32)timep->tv_sec); *p++ = cpu_to_be32(timep->tv_nsec); return p; } @@ -533,7 +533,6 @@ static __be32 *xdr_decode_nfstime3(__be32 *p, struct timespec64 *timep) static void encode_sattr3(struct xdr_stream *xdr, const struct iattr *attr, struct user_namespace *userns) { - struct timespec ts; u32 nbytes; __be32 *p; @@ -583,10 +582,8 @@ static void encode_sattr3(struct xdr_stream *xdr, const struct iattr *attr, *p++ = xdr_zero; if (attr->ia_valid & ATTR_ATIME_SET) { - struct timespec ts; *p++ = xdr_two; - ts = timespec64_to_timespec(attr->ia_atime); - p = xdr_encode_nfstime3(p, &ts); + p = xdr_encode_nfstime3(p, &attr->ia_atime); } else if (attr->ia_valid & ATTR_ATIME) { *p++ = xdr_one; } else @@ -594,8 +591,7 @@ static void encode_sattr3(struct xdr_stream *xdr, const struct iattr *attr, if (attr->ia_valid & ATTR_MTIME_SET) { *p++ = xdr_two; - ts = timespec64_to_timespec(attr->ia_mtime); - xdr_encode_nfstime3(p, &ts); + xdr_encode_nfstime3(p, &attr->ia_mtime); } else if (attr->ia_valid & ATTR_MTIME) { *p = xdr_one; } else diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index db5c01001937..22bc6613474e 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -869,7 +869,7 @@ struct nfs3_sattrargs { struct nfs_fh * fh; struct iattr * sattr; unsigned int guard; - struct timespec guardtime; + struct timespec64 guardtime; }; struct nfs3_diropargs { -- cgit v1.2.3 From 4b1b69cedf9de8c203101ea74510c07d428538f7 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 3 Oct 2019 14:08:43 -0400 Subject: NFS: Add a flag to tell nfs_client to set RPC_CLNT_CREATE_NOPING Add a flag to tell the nfs_client it should set RPC_CLNT_CREATE_NOPING when creating the rpc client. Signed-off-by: Trond Myklebust --- fs/nfs/client.c | 2 ++ include/linux/nfs_fs_sb.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include') diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 30838304a0bf..fa7d92328c72 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -515,6 +515,8 @@ int nfs_create_rpc_client(struct nfs_client *clp, args.flags |= RPC_CLNT_CREATE_NONPRIVPORT; if (test_bit(NFS_CS_INFINITE_SLOTS, &clp->cl_flags)) args.flags |= RPC_CLNT_CREATE_INFINITE_SLOTS; + if (test_bit(NFS_CS_NOPING, &clp->cl_flags)) + args.flags |= RPC_CLNT_CREATE_NOPING; if (!IS_ERR(clp->cl_rpcclient)) return 0; diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 47266870a235..a50dd432475b 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -45,6 +45,7 @@ struct nfs_client { #define NFS_CS_INFINITE_SLOTS 3 /* - don't limit TCP slots */ #define NFS_CS_NO_RETRANS_TIMEOUT 4 /* - Disable retransmit timeouts */ #define NFS_CS_TSM_POSSIBLE 5 /* - Maybe state migration */ +#define NFS_CS_NOPING 6 /* - don't ping on connect */ struct sockaddr_storage cl_addr; /* server identifier */ size_t cl_addrlen; char * cl_hostname; /* hostname of server */ -- cgit v1.2.3 From 52f98f1a2ddd2bb561f2c7e3b19a81d816a63118 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 17 Oct 2019 09:49:45 -0400 Subject: NFS/pnfs: Separate NFSv3 DS and MDS traffic If a NFSv3 server is being used as both a DS and as a regular NFSv3 server, we may want to keep the IO traffic on a separate TCP connection, since it will typically have very different timeout characteristics. This patch therefore sets up a flag to separate the two modes of operation for the nfs_client. Signed-off-by: Trond Myklebust --- fs/nfs/client.c | 6 ++++++ fs/nfs/nfs3client.c | 1 + include/linux/nfs_fs_sb.h | 1 + 3 files changed, 8 insertions(+) (limited to 'include') diff --git a/fs/nfs/client.c b/fs/nfs/client.c index fa7d92328c72..bd6575ee3b8e 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -312,6 +312,12 @@ again: /* Match nfsv4 minorversion */ if (clp->cl_minorversion != data->minorversion) continue; + + /* Match request for a dedicated DS */ + if (test_bit(NFS_CS_DS, &data->init_flags) != + test_bit(NFS_CS_DS, &clp->cl_flags)) + continue; + /* Match the full socket address */ if (!rpc_cmp_addr_port(sap, clap)) /* Match all xprt_switch full socket addresses */ diff --git a/fs/nfs/nfs3client.c b/fs/nfs/nfs3client.c index 793fa4273edb..223904bc40a7 100644 --- a/fs/nfs/nfs3client.c +++ b/fs/nfs/nfs3client.c @@ -109,6 +109,7 @@ struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv, __set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags); __set_bit(NFS_CS_NOPING, &cl_init.init_flags); + __set_bit(NFS_CS_DS, &cl_init.init_flags); /* Use the MDS nfs_client cl_ipaddr. */ nfs_init_timeout_values(&ds_timeout, ds_proto, ds_timeo, ds_retrans); diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index a50dd432475b..69e80cef5a81 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -46,6 +46,7 @@ struct nfs_client { #define NFS_CS_NO_RETRANS_TIMEOUT 4 /* - Disable retransmit timeouts */ #define NFS_CS_TSM_POSSIBLE 5 /* - Maybe state migration */ #define NFS_CS_NOPING 6 /* - don't ping on connect */ +#define NFS_CS_DS 7 /* - Server is a DS */ struct sockaddr_storage cl_addr; /* server identifier */ size_t cl_addrlen; char * cl_hostname; /* hostname of server */ -- cgit v1.2.3 From e6237b6feb37582fbd6bd7a8336d1256a6b4b4f9 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 17 Oct 2019 11:13:54 -0400 Subject: NFSv4.1: Don't rebind to the same source port when reconnecting to the server NFSv2, v3 and NFSv4 servers often have duplicate replay caches that look at the source port when deciding whether or not an RPC call is a replay of a previous call. This requires clients to perform strange TCP gymnastics in order to ensure that when they reconnect to the server, they bind to the same source port. NFSv4.1 and NFSv4.2 have sessions that provide proper replay semantics, that do not look at the source port of the connection. This patch therefore ensures they can ignore the rebind requirement. Signed-off-by: Trond Myklebust --- fs/lockd/host.c | 3 ++- fs/nfs/client.c | 3 +++ fs/nfs/nfs4client.c | 5 ++++- include/linux/nfs_fs_sb.h | 1 + include/linux/sunrpc/clnt.h | 1 + include/linux/sunrpc/xprt.h | 3 ++- net/sunrpc/clnt.c | 7 ++++++- net/sunrpc/xprtsock.c | 2 +- 8 files changed, 20 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/fs/lockd/host.c b/fs/lockd/host.c index 7d46fafdbbe5..0afb6d59bad0 100644 --- a/fs/lockd/host.c +++ b/fs/lockd/host.c @@ -464,7 +464,8 @@ nlm_bind_host(struct nlm_host *host) .version = host->h_version, .authflavor = RPC_AUTH_UNIX, .flags = (RPC_CLNT_CREATE_NOPING | - RPC_CLNT_CREATE_AUTOBIND), + RPC_CLNT_CREATE_AUTOBIND | + RPC_CLNT_CREATE_REUSEPORT), .cred = host->h_cred, }; diff --git a/fs/nfs/client.c b/fs/nfs/client.c index bd6575ee3b8e..02110a30a49e 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -523,6 +523,8 @@ int nfs_create_rpc_client(struct nfs_client *clp, args.flags |= RPC_CLNT_CREATE_INFINITE_SLOTS; if (test_bit(NFS_CS_NOPING, &clp->cl_flags)) args.flags |= RPC_CLNT_CREATE_NOPING; + if (test_bit(NFS_CS_REUSEPORT, &clp->cl_flags)) + args.flags |= RPC_CLNT_CREATE_REUSEPORT; if (!IS_ERR(clp->cl_rpcclient)) return 0; @@ -670,6 +672,7 @@ static int nfs_init_server(struct nfs_server *server, .timeparms = &timeparms, .cred = server->cred, .nconnect = data->nfs_server.nconnect, + .init_flags = (1UL << NFS_CS_REUSEPORT), }; struct nfs_client *clp; int error; diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index ebc960dd89ff..abd5af77fe94 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -879,8 +879,11 @@ static int nfs4_set_client(struct nfs_server *server, }; struct nfs_client *clp; - if (minorversion > 0 && proto == XPRT_TRANSPORT_TCP) + if (minorversion == 0) + __set_bit(NFS_CS_REUSEPORT, &cl_init.init_flags); + else if (proto == XPRT_TRANSPORT_TCP) cl_init.nconnect = nconnect; + if (server->flags & NFS_MOUNT_NORESVPORT) __set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags); if (server->options & NFS_OPTION_MIGRATION) diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 69e80cef5a81..df61ff8981e8 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -47,6 +47,7 @@ struct nfs_client { #define NFS_CS_TSM_POSSIBLE 5 /* - Maybe state migration */ #define NFS_CS_NOPING 6 /* - don't ping on connect */ #define NFS_CS_DS 7 /* - Server is a DS */ +#define NFS_CS_REUSEPORT 8 /* - reuse src port on reconnect */ struct sockaddr_storage cl_addr; /* server identifier */ size_t cl_addrlen; char * cl_hostname; /* hostname of server */ diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index abc63bd1be2b..ec52e78d432b 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -149,6 +149,7 @@ struct rpc_add_xprt_test { #define RPC_CLNT_CREATE_NO_IDLE_TIMEOUT (1UL << 8) #define RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT (1UL << 9) #define RPC_CLNT_CREATE_SOFTERR (1UL << 10) +#define RPC_CLNT_CREATE_REUSEPORT (1UL << 11) struct rpc_clnt *rpc_create(struct rpc_create_args *args); struct rpc_clnt *rpc_bind_new_program(struct rpc_clnt *, diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index d783e15ba898..ccd35cf4fc41 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -207,7 +207,8 @@ struct rpc_xprt { unsigned int min_reqs; /* min number of slots */ unsigned int num_reqs; /* total slots */ unsigned long state; /* transport state */ - unsigned char resvport : 1; /* use a reserved port */ + unsigned char resvport : 1, /* use a reserved port */ + reuseport : 1; /* reuse port on reconnect */ atomic_t swapper; /* we're swapping over this transport */ unsigned int bind_index; /* bind function index */ diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index f7f78566be46..5baf9b9be2e8 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -591,6 +591,9 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args) xprt->resvport = 1; if (args->flags & RPC_CLNT_CREATE_NONPRIVPORT) xprt->resvport = 0; + xprt->reuseport = 0; + if (args->flags & RPC_CLNT_CREATE_REUSEPORT) + xprt->reuseport = 1; clnt = rpc_create_xprt(args, xprt); if (IS_ERR(clnt) || args->nconnect <= 1) @@ -2906,7 +2909,7 @@ int rpc_clnt_add_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt; unsigned long connect_timeout; unsigned long reconnect_timeout; - unsigned char resvport; + unsigned char resvport, reuseport; int ret = 0; rcu_read_lock(); @@ -2918,6 +2921,7 @@ int rpc_clnt_add_xprt(struct rpc_clnt *clnt, return -EAGAIN; } resvport = xprt->resvport; + reuseport = xprt->reuseport; connect_timeout = xprt->connect_timeout; reconnect_timeout = xprt->max_reconnect_timeout; rcu_read_unlock(); @@ -2928,6 +2932,7 @@ int rpc_clnt_add_xprt(struct rpc_clnt *clnt, goto out_put_switch; } xprt->resvport = resvport; + xprt->reuseport = reuseport; if (xprt->ops->set_connect_timeout != NULL) xprt->ops->set_connect_timeout(xprt, connect_timeout, diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 70e52f567b2a..98e2d40b2d6a 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1752,7 +1752,7 @@ static void xs_set_port(struct rpc_xprt *xprt, unsigned short port) static void xs_set_srcport(struct sock_xprt *transport, struct socket *sock) { - if (transport->srcport == 0) + if (transport->srcport == 0 && transport->xprt.reuseport) transport->srcport = xs_sock_getport(sock); } -- cgit v1.2.3 From 5eb0e0e4f90addc6b79ebf1cb4b06b56b09f09de Mon Sep 17 00:00:00 2001 From: Vivek Gautam Date: Fri, 20 Sep 2019 13:34:28 +0530 Subject: firmware/qcom_scm: Add scm call to handle smmu errata Qcom's smmu-500 needs to toggle wait-for-safe sequence to handle TLB invalidation sync's. Few firmwares allow doing that through SCM interface. Add API to toggle wait for safe from firmware through a SCM call. Signed-off-by: Vivek Gautam Reviewed-by: Bjorn Andersson Reviewed-by: Stephen Boyd Acked-by: Andy Gross Signed-off-by: Sai Prakash Ranjan Signed-off-by: Will Deacon --- drivers/firmware/qcom_scm-32.c | 5 +++++ drivers/firmware/qcom_scm-64.c | 13 +++++++++++++ drivers/firmware/qcom_scm.c | 6 ++++++ drivers/firmware/qcom_scm.h | 5 +++++ include/linux/qcom_scm.h | 2 ++ 5 files changed, 31 insertions(+) (limited to 'include') diff --git a/drivers/firmware/qcom_scm-32.c b/drivers/firmware/qcom_scm-32.c index 215061c581e1..bee8729525ec 100644 --- a/drivers/firmware/qcom_scm-32.c +++ b/drivers/firmware/qcom_scm-32.c @@ -614,3 +614,8 @@ int __qcom_scm_io_writel(struct device *dev, phys_addr_t addr, unsigned int val) return qcom_scm_call_atomic2(QCOM_SCM_SVC_IO, QCOM_SCM_IO_WRITE, addr, val); } + +int __qcom_scm_qsmmu500_wait_safe_toggle(struct device *dev, bool enable) +{ + return -ENODEV; +} diff --git a/drivers/firmware/qcom_scm-64.c b/drivers/firmware/qcom_scm-64.c index 872155c67b2d..e1cd933ea9ae 100644 --- a/drivers/firmware/qcom_scm-64.c +++ b/drivers/firmware/qcom_scm-64.c @@ -552,3 +552,16 @@ int __qcom_scm_io_writel(struct device *dev, phys_addr_t addr, unsigned int val) return qcom_scm_call(dev, QCOM_SCM_SVC_IO, QCOM_SCM_IO_WRITE, &desc, &res); } + +int __qcom_scm_qsmmu500_wait_safe_toggle(struct device *dev, bool en) +{ + struct qcom_scm_desc desc = {0}; + struct arm_smccc_res res; + + desc.args[0] = QCOM_SCM_CONFIG_ERRATA1_CLIENT_ALL; + desc.args[1] = en; + desc.arginfo = QCOM_SCM_ARGS(2); + + return qcom_scm_call_atomic(dev, QCOM_SCM_SVC_SMMU_PROGRAM, + QCOM_SCM_CONFIG_ERRATA1, &desc, &res); +} diff --git a/drivers/firmware/qcom_scm.c b/drivers/firmware/qcom_scm.c index 4802ab170fe5..a729e05c21b8 100644 --- a/drivers/firmware/qcom_scm.c +++ b/drivers/firmware/qcom_scm.c @@ -345,6 +345,12 @@ int qcom_scm_iommu_secure_ptbl_init(u64 addr, u32 size, u32 spare) } EXPORT_SYMBOL(qcom_scm_iommu_secure_ptbl_init); +int qcom_scm_qsmmu500_wait_safe_toggle(bool en) +{ + return __qcom_scm_qsmmu500_wait_safe_toggle(__scm->dev, en); +} +EXPORT_SYMBOL(qcom_scm_qsmmu500_wait_safe_toggle); + int qcom_scm_io_readl(phys_addr_t addr, unsigned int *val) { return __qcom_scm_io_readl(__scm->dev, addr, val); diff --git a/drivers/firmware/qcom_scm.h b/drivers/firmware/qcom_scm.h index 99506bd873c0..baee744dbcfe 100644 --- a/drivers/firmware/qcom_scm.h +++ b/drivers/firmware/qcom_scm.h @@ -91,10 +91,15 @@ extern int __qcom_scm_restore_sec_cfg(struct device *dev, u32 device_id, u32 spare); #define QCOM_SCM_IOMMU_SECURE_PTBL_SIZE 3 #define QCOM_SCM_IOMMU_SECURE_PTBL_INIT 4 +#define QCOM_SCM_SVC_SMMU_PROGRAM 0x15 +#define QCOM_SCM_CONFIG_ERRATA1 0x3 +#define QCOM_SCM_CONFIG_ERRATA1_CLIENT_ALL 0x2 extern int __qcom_scm_iommu_secure_ptbl_size(struct device *dev, u32 spare, size_t *size); extern int __qcom_scm_iommu_secure_ptbl_init(struct device *dev, u64 addr, u32 size, u32 spare); +extern int __qcom_scm_qsmmu500_wait_safe_toggle(struct device *dev, + bool enable); #define QCOM_MEM_PROT_ASSIGN_ID 0x16 extern int __qcom_scm_assign_mem(struct device *dev, phys_addr_t mem_region, size_t mem_sz, diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h index 2d5eff506e13..ffd72b3b14ee 100644 --- a/include/linux/qcom_scm.h +++ b/include/linux/qcom_scm.h @@ -58,6 +58,7 @@ extern int qcom_scm_set_remote_state(u32 state, u32 id); extern int qcom_scm_restore_sec_cfg(u32 device_id, u32 spare); extern int qcom_scm_iommu_secure_ptbl_size(u32 spare, size_t *size); extern int qcom_scm_iommu_secure_ptbl_init(u64 addr, u32 size, u32 spare); +extern int qcom_scm_qsmmu500_wait_safe_toggle(bool en); extern int qcom_scm_io_readl(phys_addr_t addr, unsigned int *val); extern int qcom_scm_io_writel(phys_addr_t addr, unsigned int val); #else @@ -97,6 +98,7 @@ qcom_scm_set_remote_state(u32 state,u32 id) { return -ENODEV; } static inline int qcom_scm_restore_sec_cfg(u32 device_id, u32 spare) { return -ENODEV; } static inline int qcom_scm_iommu_secure_ptbl_size(u32 spare, size_t *size) { return -ENODEV; } static inline int qcom_scm_iommu_secure_ptbl_init(u64 addr, u32 size, u32 spare) { return -ENODEV; } +static inline int qcom_scm_qsmmu500_wait_safe_toggle(bool en) { return -ENODEV; } static inline int qcom_scm_io_readl(phys_addr_t addr, unsigned int *val) { return -ENODEV; } static inline int qcom_scm_io_writel(phys_addr_t addr, unsigned int val) { return -ENODEV; } #endif -- cgit v1.2.3 From 205577ab6f7ade6185f764ed78fb6875dca40205 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Fri, 25 Oct 2019 19:08:36 +0100 Subject: iommu/io-pgtable-arm: Rationalise MAIR handling Between VMSAv8-64 and the various 32-bit formats, there is either one 64-bit MAIR or a pair of 32-bit MAIR0/MAIR1 or NMRR/PMRR registers. As such, keeping two 64-bit values in io_pgtable_cfg has always been overkill. Signed-off-by: Robin Murphy Signed-off-by: Will Deacon --- drivers/iommu/arm-smmu-v3.c | 2 +- drivers/iommu/arm-smmu.c | 4 ++-- drivers/iommu/io-pgtable-arm.c | 3 +-- drivers/iommu/ipmmu-vmsa.c | 2 +- drivers/iommu/qcom_iommu.c | 4 ++-- include/linux/io-pgtable.h | 2 +- 6 files changed, 8 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index 8da93e730d6f..3f20e548f1ec 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -2172,7 +2172,7 @@ static int arm_smmu_domain_finalise_s1(struct arm_smmu_domain *smmu_domain, cfg->cd.asid = (u16)asid; cfg->cd.ttbr = pgtbl_cfg->arm_lpae_s1_cfg.ttbr[0]; cfg->cd.tcr = pgtbl_cfg->arm_lpae_s1_cfg.tcr; - cfg->cd.mair = pgtbl_cfg->arm_lpae_s1_cfg.mair[0]; + cfg->cd.mair = pgtbl_cfg->arm_lpae_s1_cfg.mair; return 0; out_free_asid: diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index a180665ea002..424ebf38cd09 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -552,8 +552,8 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain, cb->mair[0] = pgtbl_cfg->arm_v7s_cfg.prrr; cb->mair[1] = pgtbl_cfg->arm_v7s_cfg.nmrr; } else { - cb->mair[0] = pgtbl_cfg->arm_lpae_s1_cfg.mair[0]; - cb->mair[1] = pgtbl_cfg->arm_lpae_s1_cfg.mair[1]; + cb->mair[0] = pgtbl_cfg->arm_lpae_s1_cfg.mair; + cb->mair[1] = pgtbl_cfg->arm_lpae_s1_cfg.mair >> 32; } } } diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index fcb302704053..cd96442af44b 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -861,8 +861,7 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie) (ARM_LPAE_MAIR_ATTR_INC_OWBRWA << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_INC_OCACHE)); - cfg->arm_lpae_s1_cfg.mair[0] = reg; - cfg->arm_lpae_s1_cfg.mair[1] = 0; + cfg->arm_lpae_s1_cfg.mair = reg; /* Looking good; allocate a pgd */ data->pgd = __arm_lpae_alloc_pages(ARM_LPAE_PGD_SIZE(data), diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c index 9da8309f7170..e4da6efbda49 100644 --- a/drivers/iommu/ipmmu-vmsa.c +++ b/drivers/iommu/ipmmu-vmsa.c @@ -438,7 +438,7 @@ static void ipmmu_domain_setup_context(struct ipmmu_vmsa_domain *domain) /* MAIR0 */ ipmmu_ctx_write_root(domain, IMMAIR0, - domain->cfg.arm_lpae_s1_cfg.mair[0]); + domain->cfg.arm_lpae_s1_cfg.mair); /* IMBUSCR */ if (domain->mmu->features->setup_imbuscr) diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c index c31e7bc4ccbe..66e9b40e9275 100644 --- a/drivers/iommu/qcom_iommu.c +++ b/drivers/iommu/qcom_iommu.c @@ -284,9 +284,9 @@ static int qcom_iommu_init_domain(struct iommu_domain *domain, /* MAIRs (stage-1 only) */ iommu_writel(ctx, ARM_SMMU_CB_S1_MAIR0, - pgtbl_cfg.arm_lpae_s1_cfg.mair[0]); + pgtbl_cfg.arm_lpae_s1_cfg.mair); iommu_writel(ctx, ARM_SMMU_CB_S1_MAIR1, - pgtbl_cfg.arm_lpae_s1_cfg.mair[1]); + pgtbl_cfg.arm_lpae_s1_cfg.mair >> 32); /* SCTLR */ reg = SCTLR_CFIE | SCTLR_CFRE | SCTLR_AFE | SCTLR_TRE | diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index ec7a13405f10..ee21eedafe98 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -102,7 +102,7 @@ struct io_pgtable_cfg { struct { u64 ttbr[2]; u64 tcr; - u64 mair[2]; + u64 mair; } arm_lpae_s1_cfg; struct { -- cgit v1.2.3 From b8104fda1fff0882e43b7e98832a76d7e98eb3e9 Mon Sep 17 00:00:00 2001 From: John Garry Date: Tue, 5 Nov 2019 01:22:16 +0800 Subject: logic_pio: Define PIO_INDIRECT_SIZE for !CONFIG_INDIRECT_PIO With the goal of expanding the test coverage of the HiSi LPC driver to !ARM64, define a dummy PIO_INDIRECT_SIZE for !CONFIG_INDIRECT_PIO, which is required by the named driver. Signed-off-by: John Garry Signed-off-by: Wei Xu --- include/linux/logic_pio.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/logic_pio.h b/include/linux/logic_pio.h index 88e1e6304a71..54945aa824b4 100644 --- a/include/linux/logic_pio.h +++ b/include/linux/logic_pio.h @@ -108,10 +108,10 @@ void logic_outsl(unsigned long addr, const void *buffer, unsigned int count); * area by redefining the macro below. */ #define PIO_INDIRECT_SIZE 0x4000 -#define MMIO_UPPER_LIMIT (IO_SPACE_LIMIT - PIO_INDIRECT_SIZE) #else -#define MMIO_UPPER_LIMIT IO_SPACE_LIMIT +#define PIO_INDIRECT_SIZE 0 #endif /* CONFIG_INDIRECT_PIO */ +#define MMIO_UPPER_LIMIT (IO_SPACE_LIMIT - PIO_INDIRECT_SIZE) struct logic_pio_hwaddr *find_io_range_by_fwnode(struct fwnode_handle *fwnode); unsigned long logic_pio_trans_hwaddr(struct fwnode_handle *fwnode, -- cgit v1.2.3 From 634d811c619b0dbe16dc890a53d2c978e9d055d5 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 5 Nov 2019 14:59:02 -0500 Subject: nfsv4: Move NFSPROC4_CLNT_COPY_NOTIFY to end of list We shouldn't insert things into the NFSPROC4_CLNT enums, since that causes the nfsstat array to be reordered. Signed-off-by: Trond Myklebust --- include/linux/nfs4.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 5e7a5261af4e..82d8fb422092 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -537,10 +537,11 @@ enum { NFSPROC4_CLNT_CLONE, NFSPROC4_CLNT_COPY, NFSPROC4_CLNT_OFFLOAD_CANCEL, - NFSPROC4_CLNT_COPY_NOTIFY, NFSPROC4_CLNT_LOOKUPP, NFSPROC4_CLNT_LAYOUTERROR, + + NFSPROC4_CLNT_COPY_NOTIFY, }; /* nfs41 types */ -- cgit v1.2.3 From be80507d45bea0358b54d1918db144d90a2ecd78 Mon Sep 17 00:00:00 2001 From: Zhou Yanjie Date: Fri, 25 Oct 2019 01:21:09 +0800 Subject: dt-bindings: dmaengine: Add X1000 bindings. Add the dmaengine bindings for the X1000 Soc from Ingenic. Signed-off-by: Zhou Yanjie Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/1571937670-30828-2-git-send-email-zhouyanjie@zoho.com Signed-off-by: Vinod Koul --- .../devicetree/bindings/dma/jz4780-dma.txt | 3 +- include/dt-bindings/dma/x1000-dma.h | 40 ++++++++++++++++++++++ 2 files changed, 42 insertions(+), 1 deletion(-) create mode 100644 include/dt-bindings/dma/x1000-dma.h (limited to 'include') diff --git a/Documentation/devicetree/bindings/dma/jz4780-dma.txt b/Documentation/devicetree/bindings/dma/jz4780-dma.txt index 636fcb26b164..ec89782d9498 100644 --- a/Documentation/devicetree/bindings/dma/jz4780-dma.txt +++ b/Documentation/devicetree/bindings/dma/jz4780-dma.txt @@ -7,10 +7,11 @@ Required properties: * ingenic,jz4725b-dma * ingenic,jz4770-dma * ingenic,jz4780-dma + * ingenic,x1000-dma - reg: Should contain the DMA channel registers location and length, followed by the DMA controller registers location and length. - interrupts: Should contain the interrupt specifier of the DMA controller. -- clocks: Should contain a clock specifier for the JZ4780 PDMA clock. +- clocks: Should contain a clock specifier for the JZ4780/X1000 PDMA clock. - #dma-cells: Must be <2>. Number of integer cells in the dmas property of DMA clients (see below). diff --git a/include/dt-bindings/dma/x1000-dma.h b/include/dt-bindings/dma/x1000-dma.h new file mode 100644 index 000000000000..401e1656e696 --- /dev/null +++ b/include/dt-bindings/dma/x1000-dma.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * This header provides macros for X1000 DMA bindings. + * + * Copyright (c) 2019 Zhou Yanjie + */ + +#ifndef __DT_BINDINGS_DMA_X1000_DMA_H__ +#define __DT_BINDINGS_DMA_X1000_DMA_H__ + +/* + * Request type numbers for the X1000 DMA controller (written to the DRTn + * register for the channel). + */ +#define X1000_DMA_DMIC_RX 0x5 +#define X1000_DMA_I2S0_TX 0x6 +#define X1000_DMA_I2S0_RX 0x7 +#define X1000_DMA_AUTO 0x8 +#define X1000_DMA_UART2_TX 0x10 +#define X1000_DMA_UART2_RX 0x11 +#define X1000_DMA_UART1_TX 0x12 +#define X1000_DMA_UART1_RX 0x13 +#define X1000_DMA_UART0_TX 0x14 +#define X1000_DMA_UART0_RX 0x15 +#define X1000_DMA_SSI0_TX 0x16 +#define X1000_DMA_SSI0_RX 0x17 +#define X1000_DMA_MSC0_TX 0x1a +#define X1000_DMA_MSC0_RX 0x1b +#define X1000_DMA_MSC1_TX 0x1c +#define X1000_DMA_MSC1_RX 0x1d +#define X1000_DMA_PCM0_TX 0x20 +#define X1000_DMA_PCM0_RX 0x21 +#define X1000_DMA_SMB0_TX 0x24 +#define X1000_DMA_SMB0_RX 0x25 +#define X1000_DMA_SMB1_TX 0x26 +#define X1000_DMA_SMB1_RX 0x27 +#define X1000_DMA_SMB2_TX 0x28 +#define X1000_DMA_SMB2_RX 0x29 + +#endif /* __DT_BINDINGS_DMA_X1000_DMA_H__ */ -- cgit v1.2.3 From 56144737e67329c9aaed15f942d46a6302e2e3d8 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 6 Nov 2019 09:48:04 -0800 Subject: hrtimer: Annotate lockless access to timer->state syzbot reported various data-race caused by hrtimer_is_queued() reading timer->state. A READ_ONCE() is required there to silence the warning. Also add the corresponding WRITE_ONCE() when timer->state is set. In remove_hrtimer() the hrtimer_is_queued() helper is open coded to avoid loading timer->state twice. KCSAN reported these cases: BUG: KCSAN: data-race in __remove_hrtimer / tcp_pacing_check write to 0xffff8880b2a7d388 of 1 bytes by interrupt on cpu 0: __remove_hrtimer+0x52/0x130 kernel/time/hrtimer.c:991 __run_hrtimer kernel/time/hrtimer.c:1496 [inline] __hrtimer_run_queues+0x250/0x600 kernel/time/hrtimer.c:1576 hrtimer_run_softirq+0x10e/0x150 kernel/time/hrtimer.c:1593 __do_softirq+0x115/0x33f kernel/softirq.c:292 run_ksoftirqd+0x46/0x60 kernel/softirq.c:603 smpboot_thread_fn+0x37d/0x4a0 kernel/smpboot.c:165 kthread+0x1d4/0x200 drivers/block/aoe/aoecmd.c:1253 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:352 read to 0xffff8880b2a7d388 of 1 bytes by task 24652 on cpu 1: tcp_pacing_check net/ipv4/tcp_output.c:2235 [inline] tcp_pacing_check+0xba/0x130 net/ipv4/tcp_output.c:2225 tcp_xmit_retransmit_queue+0x32c/0x5a0 net/ipv4/tcp_output.c:3044 tcp_xmit_recovery+0x7c/0x120 net/ipv4/tcp_input.c:3558 tcp_ack+0x17b6/0x3170 net/ipv4/tcp_input.c:3717 tcp_rcv_established+0x37e/0xf50 net/ipv4/tcp_input.c:5696 tcp_v4_do_rcv+0x381/0x4e0 net/ipv4/tcp_ipv4.c:1561 sk_backlog_rcv include/net/sock.h:945 [inline] __release_sock+0x135/0x1e0 net/core/sock.c:2435 release_sock+0x61/0x160 net/core/sock.c:2951 sk_stream_wait_memory+0x3d7/0x7c0 net/core/stream.c:145 tcp_sendmsg_locked+0xb47/0x1f30 net/ipv4/tcp.c:1393 tcp_sendmsg+0x39/0x60 net/ipv4/tcp.c:1434 inet_sendmsg+0x6d/0x90 net/ipv4/af_inet.c:807 sock_sendmsg_nosec net/socket.c:637 [inline] sock_sendmsg+0x9f/0xc0 net/socket.c:657 BUG: KCSAN: data-race in __remove_hrtimer / __tcp_ack_snd_check write to 0xffff8880a3a65588 of 1 bytes by interrupt on cpu 0: __remove_hrtimer+0x52/0x130 kernel/time/hrtimer.c:991 __run_hrtimer kernel/time/hrtimer.c:1496 [inline] __hrtimer_run_queues+0x250/0x600 kernel/time/hrtimer.c:1576 hrtimer_run_softirq+0x10e/0x150 kernel/time/hrtimer.c:1593 __do_softirq+0x115/0x33f kernel/softirq.c:292 invoke_softirq kernel/softirq.c:373 [inline] irq_exit+0xbb/0xe0 kernel/softirq.c:413 exiting_irq arch/x86/include/asm/apic.h:536 [inline] smp_apic_timer_interrupt+0xe6/0x280 arch/x86/kernel/apic/apic.c:1137 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:830 read to 0xffff8880a3a65588 of 1 bytes by task 22891 on cpu 1: __tcp_ack_snd_check+0x415/0x4f0 net/ipv4/tcp_input.c:5265 tcp_ack_snd_check net/ipv4/tcp_input.c:5287 [inline] tcp_rcv_established+0x750/0xf50 net/ipv4/tcp_input.c:5708 tcp_v4_do_rcv+0x381/0x4e0 net/ipv4/tcp_ipv4.c:1561 sk_backlog_rcv include/net/sock.h:945 [inline] __release_sock+0x135/0x1e0 net/core/sock.c:2435 release_sock+0x61/0x160 net/core/sock.c:2951 sk_stream_wait_memory+0x3d7/0x7c0 net/core/stream.c:145 tcp_sendmsg_locked+0xb47/0x1f30 net/ipv4/tcp.c:1393 tcp_sendmsg+0x39/0x60 net/ipv4/tcp.c:1434 inet_sendmsg+0x6d/0x90 net/ipv4/af_inet.c:807 sock_sendmsg_nosec net/socket.c:637 [inline] sock_sendmsg+0x9f/0xc0 net/socket.c:657 __sys_sendto+0x21f/0x320 net/socket.c:1952 __do_sys_sendto net/socket.c:1964 [inline] __se_sys_sendto net/socket.c:1960 [inline] __x64_sys_sendto+0x89/0xb0 net/socket.c:1960 do_syscall_64+0xcc/0x370 arch/x86/entry/common.c:290 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 24652 Comm: syz-executor.3 Not tainted 5.4.0-rc3+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 [ tglx: Added comments ] Reported-by: syzbot Signed-off-by: Eric Dumazet Signed-off-by: Thomas Gleixner Link: https://lkml.kernel.org/r/20191106174804.74723-1-edumazet@google.com --- include/linux/hrtimer.h | 14 ++++++++++---- kernel/time/hrtimer.c | 11 +++++++---- 2 files changed, 17 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 1b9a51a1bccb..1f98b52118f0 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -456,12 +456,18 @@ extern u64 hrtimer_next_event_without(const struct hrtimer *exclude); extern bool hrtimer_active(const struct hrtimer *timer); -/* - * Helper function to check, whether the timer is on one of the queues +/** + * hrtimer_is_queued = check, whether the timer is on one of the queues + * @timer: Timer to check + * + * Returns: True if the timer is queued, false otherwise + * + * The function can be used lockless, but it gives only a current snapshot. */ -static inline int hrtimer_is_queued(struct hrtimer *timer) +static inline bool hrtimer_is_queued(struct hrtimer *timer) { - return timer->state & HRTIMER_STATE_ENQUEUED; + /* The READ_ONCE pairs with the update functions of timer->state */ + return !!(READ_ONCE(timer->state) & HRTIMER_STATE_ENQUEUED); } /* diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 65605530ee34..7f31932216a1 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -966,7 +966,8 @@ static int enqueue_hrtimer(struct hrtimer *timer, base->cpu_base->active_bases |= 1 << base->index; - timer->state = HRTIMER_STATE_ENQUEUED; + /* Pairs with the lockless read in hrtimer_is_queued() */ + WRITE_ONCE(timer->state, HRTIMER_STATE_ENQUEUED); return timerqueue_add(&base->active, &timer->node); } @@ -988,7 +989,8 @@ static void __remove_hrtimer(struct hrtimer *timer, struct hrtimer_cpu_base *cpu_base = base->cpu_base; u8 state = timer->state; - timer->state = newstate; + /* Pairs with the lockless read in hrtimer_is_queued() */ + WRITE_ONCE(timer->state, newstate); if (!(state & HRTIMER_STATE_ENQUEUED)) return; @@ -1013,8 +1015,9 @@ static void __remove_hrtimer(struct hrtimer *timer, static inline int remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, bool restart) { - if (hrtimer_is_queued(timer)) { - u8 state = timer->state; + u8 state = timer->state; + + if (state & HRTIMER_STATE_ENQUEUED) { int reprogram; /* -- cgit v1.2.3 From 81d2c6f81996e01fbcd2b5aeefbb519e21c806e9 Mon Sep 17 00:00:00 2001 From: Daniel Axtens Date: Tue, 20 Aug 2019 12:49:40 +1000 Subject: kasan: support instrumented bitops combined with generic bitops Currently bitops-instrumented.h assumes that the architecture provides atomic, non-atomic and locking bitops (e.g. both set_bit and __set_bit). This is true on x86 and s390, but is not always true: there is a generic bitops/non-atomic.h header that provides generic non-atomic operations, and also a generic bitops/lock.h for locking operations. powerpc uses the generic non-atomic version, so it does not have it's own e.g. __set_bit that could be renamed arch___set_bit. Split up bitops-instrumented.h to mirror the atomic/non-atomic/lock split. This allows arches to only include the headers where they have arch-specific versions to rename. Update x86 and s390. (The generic operations are automatically instrumented because they're written in C, not asm.) Suggested-by: Christophe Leroy Reviewed-by: Christophe Leroy Signed-off-by: Daniel Axtens Acked-by: Marco Elver Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20190820024941.12640-1-dja@axtens.net --- Documentation/core-api/kernel-api.rst | 17 +- arch/s390/include/asm/bitops.h | 4 +- arch/x86/include/asm/bitops.h | 4 +- include/asm-generic/bitops-instrumented.h | 263 --------------------- include/asm-generic/bitops/instrumented-atomic.h | 100 ++++++++ include/asm-generic/bitops/instrumented-lock.h | 81 +++++++ .../asm-generic/bitops/instrumented-non-atomic.h | 114 +++++++++ 7 files changed, 317 insertions(+), 266 deletions(-) delete mode 100644 include/asm-generic/bitops-instrumented.h create mode 100644 include/asm-generic/bitops/instrumented-atomic.h create mode 100644 include/asm-generic/bitops/instrumented-lock.h create mode 100644 include/asm-generic/bitops/instrumented-non-atomic.h (limited to 'include') diff --git a/Documentation/core-api/kernel-api.rst b/Documentation/core-api/kernel-api.rst index f77de49b1d51..2caaeb55e8dd 100644 --- a/Documentation/core-api/kernel-api.rst +++ b/Documentation/core-api/kernel-api.rst @@ -57,7 +57,22 @@ The Linux kernel provides more basic utility functions. Bit Operations -------------- -.. kernel-doc:: include/asm-generic/bitops-instrumented.h +Atomic Operations +~~~~~~~~~~~~~~~~~ + +.. kernel-doc:: include/asm-generic/bitops/instrumented-atomic.h + :internal: + +Non-atomic Operations +~~~~~~~~~~~~~~~~~~~~~ + +.. kernel-doc:: include/asm-generic/bitops/instrumented-non-atomic.h + :internal: + +Locking Operations +~~~~~~~~~~~~~~~~~~ + +.. kernel-doc:: include/asm-generic/bitops/instrumented-lock.h :internal: Bitmap Operations diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h index eb7eed43e780..431e208a5ea4 100644 --- a/arch/s390/include/asm/bitops.h +++ b/arch/s390/include/asm/bitops.h @@ -241,7 +241,9 @@ static inline void arch___clear_bit_unlock(unsigned long nr, arch___clear_bit(nr, ptr); } -#include +#include +#include +#include /* * Functions which use MSB0 bit numbering. diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 7d1f6a49bfae..062cdecb2f24 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -388,7 +388,9 @@ static __always_inline int fls64(__u64 x) #include -#include +#include +#include +#include #include diff --git a/include/asm-generic/bitops-instrumented.h b/include/asm-generic/bitops-instrumented.h deleted file mode 100644 index ddd1c6d9d8db..000000000000 --- a/include/asm-generic/bitops-instrumented.h +++ /dev/null @@ -1,263 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ - -/* - * This file provides wrappers with sanitizer instrumentation for bit - * operations. - * - * To use this functionality, an arch's bitops.h file needs to define each of - * the below bit operations with an arch_ prefix (e.g. arch_set_bit(), - * arch___set_bit(), etc.). - */ -#ifndef _ASM_GENERIC_BITOPS_INSTRUMENTED_H -#define _ASM_GENERIC_BITOPS_INSTRUMENTED_H - -#include - -/** - * set_bit - Atomically set a bit in memory - * @nr: the bit to set - * @addr: the address to start counting from - * - * This is a relaxed atomic operation (no implied memory barriers). - * - * Note that @nr may be almost arbitrarily large; this function is not - * restricted to acting on a single-word quantity. - */ -static inline void set_bit(long nr, volatile unsigned long *addr) -{ - kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); - arch_set_bit(nr, addr); -} - -/** - * __set_bit - Set a bit in memory - * @nr: the bit to set - * @addr: the address to start counting from - * - * Unlike set_bit(), this function is non-atomic. If it is called on the same - * region of memory concurrently, the effect may be that only one operation - * succeeds. - */ -static inline void __set_bit(long nr, volatile unsigned long *addr) -{ - kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); - arch___set_bit(nr, addr); -} - -/** - * clear_bit - Clears a bit in memory - * @nr: Bit to clear - * @addr: Address to start counting from - * - * This is a relaxed atomic operation (no implied memory barriers). - */ -static inline void clear_bit(long nr, volatile unsigned long *addr) -{ - kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); - arch_clear_bit(nr, addr); -} - -/** - * __clear_bit - Clears a bit in memory - * @nr: the bit to clear - * @addr: the address to start counting from - * - * Unlike clear_bit(), this function is non-atomic. If it is called on the same - * region of memory concurrently, the effect may be that only one operation - * succeeds. - */ -static inline void __clear_bit(long nr, volatile unsigned long *addr) -{ - kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); - arch___clear_bit(nr, addr); -} - -/** - * clear_bit_unlock - Clear a bit in memory, for unlock - * @nr: the bit to set - * @addr: the address to start counting from - * - * This operation is atomic and provides release barrier semantics. - */ -static inline void clear_bit_unlock(long nr, volatile unsigned long *addr) -{ - kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); - arch_clear_bit_unlock(nr, addr); -} - -/** - * __clear_bit_unlock - Clears a bit in memory - * @nr: Bit to clear - * @addr: Address to start counting from - * - * This is a non-atomic operation but implies a release barrier before the - * memory operation. It can be used for an unlock if no other CPUs can - * concurrently modify other bits in the word. - */ -static inline void __clear_bit_unlock(long nr, volatile unsigned long *addr) -{ - kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); - arch___clear_bit_unlock(nr, addr); -} - -/** - * change_bit - Toggle a bit in memory - * @nr: Bit to change - * @addr: Address to start counting from - * - * This is a relaxed atomic operation (no implied memory barriers). - * - * Note that @nr may be almost arbitrarily large; this function is not - * restricted to acting on a single-word quantity. - */ -static inline void change_bit(long nr, volatile unsigned long *addr) -{ - kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); - arch_change_bit(nr, addr); -} - -/** - * __change_bit - Toggle a bit in memory - * @nr: the bit to change - * @addr: the address to start counting from - * - * Unlike change_bit(), this function is non-atomic. If it is called on the same - * region of memory concurrently, the effect may be that only one operation - * succeeds. - */ -static inline void __change_bit(long nr, volatile unsigned long *addr) -{ - kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); - arch___change_bit(nr, addr); -} - -/** - * test_and_set_bit - Set a bit and return its old value - * @nr: Bit to set - * @addr: Address to count from - * - * This is an atomic fully-ordered operation (implied full memory barrier). - */ -static inline bool test_and_set_bit(long nr, volatile unsigned long *addr) -{ - kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); - return arch_test_and_set_bit(nr, addr); -} - -/** - * __test_and_set_bit - Set a bit and return its old value - * @nr: Bit to set - * @addr: Address to count from - * - * This operation is non-atomic. If two instances of this operation race, one - * can appear to succeed but actually fail. - */ -static inline bool __test_and_set_bit(long nr, volatile unsigned long *addr) -{ - kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); - return arch___test_and_set_bit(nr, addr); -} - -/** - * test_and_set_bit_lock - Set a bit and return its old value, for lock - * @nr: Bit to set - * @addr: Address to count from - * - * This operation is atomic and provides acquire barrier semantics if - * the returned value is 0. - * It can be used to implement bit locks. - */ -static inline bool test_and_set_bit_lock(long nr, volatile unsigned long *addr) -{ - kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); - return arch_test_and_set_bit_lock(nr, addr); -} - -/** - * test_and_clear_bit - Clear a bit and return its old value - * @nr: Bit to clear - * @addr: Address to count from - * - * This is an atomic fully-ordered operation (implied full memory barrier). - */ -static inline bool test_and_clear_bit(long nr, volatile unsigned long *addr) -{ - kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); - return arch_test_and_clear_bit(nr, addr); -} - -/** - * __test_and_clear_bit - Clear a bit and return its old value - * @nr: Bit to clear - * @addr: Address to count from - * - * This operation is non-atomic. If two instances of this operation race, one - * can appear to succeed but actually fail. - */ -static inline bool __test_and_clear_bit(long nr, volatile unsigned long *addr) -{ - kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); - return arch___test_and_clear_bit(nr, addr); -} - -/** - * test_and_change_bit - Change a bit and return its old value - * @nr: Bit to change - * @addr: Address to count from - * - * This is an atomic fully-ordered operation (implied full memory barrier). - */ -static inline bool test_and_change_bit(long nr, volatile unsigned long *addr) -{ - kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); - return arch_test_and_change_bit(nr, addr); -} - -/** - * __test_and_change_bit - Change a bit and return its old value - * @nr: Bit to change - * @addr: Address to count from - * - * This operation is non-atomic. If two instances of this operation race, one - * can appear to succeed but actually fail. - */ -static inline bool __test_and_change_bit(long nr, volatile unsigned long *addr) -{ - kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); - return arch___test_and_change_bit(nr, addr); -} - -/** - * test_bit - Determine whether a bit is set - * @nr: bit number to test - * @addr: Address to start counting from - */ -static inline bool test_bit(long nr, const volatile unsigned long *addr) -{ - kasan_check_read(addr + BIT_WORD(nr), sizeof(long)); - return arch_test_bit(nr, addr); -} - -#if defined(arch_clear_bit_unlock_is_negative_byte) -/** - * clear_bit_unlock_is_negative_byte - Clear a bit in memory and test if bottom - * byte is negative, for unlock. - * @nr: the bit to clear - * @addr: the address to start counting from - * - * This operation is atomic and provides release barrier semantics. - * - * This is a bit of a one-trick-pony for the filemap code, which clears - * PG_locked and tests PG_waiters, - */ -static inline bool -clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr) -{ - kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); - return arch_clear_bit_unlock_is_negative_byte(nr, addr); -} -/* Let everybody know we have it. */ -#define clear_bit_unlock_is_negative_byte clear_bit_unlock_is_negative_byte -#endif - -#endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_H */ diff --git a/include/asm-generic/bitops/instrumented-atomic.h b/include/asm-generic/bitops/instrumented-atomic.h new file mode 100644 index 000000000000..18ce3c9e8eec --- /dev/null +++ b/include/asm-generic/bitops/instrumented-atomic.h @@ -0,0 +1,100 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * This file provides wrappers with sanitizer instrumentation for atomic bit + * operations. + * + * To use this functionality, an arch's bitops.h file needs to define each of + * the below bit operations with an arch_ prefix (e.g. arch_set_bit(), + * arch___set_bit(), etc.). + */ +#ifndef _ASM_GENERIC_BITOPS_INSTRUMENTED_ATOMIC_H +#define _ASM_GENERIC_BITOPS_INSTRUMENTED_ATOMIC_H + +#include + +/** + * set_bit - Atomically set a bit in memory + * @nr: the bit to set + * @addr: the address to start counting from + * + * This is a relaxed atomic operation (no implied memory barriers). + * + * Note that @nr may be almost arbitrarily large; this function is not + * restricted to acting on a single-word quantity. + */ +static inline void set_bit(long nr, volatile unsigned long *addr) +{ + kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); + arch_set_bit(nr, addr); +} + +/** + * clear_bit - Clears a bit in memory + * @nr: Bit to clear + * @addr: Address to start counting from + * + * This is a relaxed atomic operation (no implied memory barriers). + */ +static inline void clear_bit(long nr, volatile unsigned long *addr) +{ + kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); + arch_clear_bit(nr, addr); +} + +/** + * change_bit - Toggle a bit in memory + * @nr: Bit to change + * @addr: Address to start counting from + * + * This is a relaxed atomic operation (no implied memory barriers). + * + * Note that @nr may be almost arbitrarily large; this function is not + * restricted to acting on a single-word quantity. + */ +static inline void change_bit(long nr, volatile unsigned long *addr) +{ + kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); + arch_change_bit(nr, addr); +} + +/** + * test_and_set_bit - Set a bit and return its old value + * @nr: Bit to set + * @addr: Address to count from + * + * This is an atomic fully-ordered operation (implied full memory barrier). + */ +static inline bool test_and_set_bit(long nr, volatile unsigned long *addr) +{ + kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); + return arch_test_and_set_bit(nr, addr); +} + +/** + * test_and_clear_bit - Clear a bit and return its old value + * @nr: Bit to clear + * @addr: Address to count from + * + * This is an atomic fully-ordered operation (implied full memory barrier). + */ +static inline bool test_and_clear_bit(long nr, volatile unsigned long *addr) +{ + kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); + return arch_test_and_clear_bit(nr, addr); +} + +/** + * test_and_change_bit - Change a bit and return its old value + * @nr: Bit to change + * @addr: Address to count from + * + * This is an atomic fully-ordered operation (implied full memory barrier). + */ +static inline bool test_and_change_bit(long nr, volatile unsigned long *addr) +{ + kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); + return arch_test_and_change_bit(nr, addr); +} + +#endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H */ diff --git a/include/asm-generic/bitops/instrumented-lock.h b/include/asm-generic/bitops/instrumented-lock.h new file mode 100644 index 000000000000..ec53fdeea9ec --- /dev/null +++ b/include/asm-generic/bitops/instrumented-lock.h @@ -0,0 +1,81 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * This file provides wrappers with sanitizer instrumentation for bit + * locking operations. + * + * To use this functionality, an arch's bitops.h file needs to define each of + * the below bit operations with an arch_ prefix (e.g. arch_set_bit(), + * arch___set_bit(), etc.). + */ +#ifndef _ASM_GENERIC_BITOPS_INSTRUMENTED_LOCK_H +#define _ASM_GENERIC_BITOPS_INSTRUMENTED_LOCK_H + +#include + +/** + * clear_bit_unlock - Clear a bit in memory, for unlock + * @nr: the bit to set + * @addr: the address to start counting from + * + * This operation is atomic and provides release barrier semantics. + */ +static inline void clear_bit_unlock(long nr, volatile unsigned long *addr) +{ + kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); + arch_clear_bit_unlock(nr, addr); +} + +/** + * __clear_bit_unlock - Clears a bit in memory + * @nr: Bit to clear + * @addr: Address to start counting from + * + * This is a non-atomic operation but implies a release barrier before the + * memory operation. It can be used for an unlock if no other CPUs can + * concurrently modify other bits in the word. + */ +static inline void __clear_bit_unlock(long nr, volatile unsigned long *addr) +{ + kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); + arch___clear_bit_unlock(nr, addr); +} + +/** + * test_and_set_bit_lock - Set a bit and return its old value, for lock + * @nr: Bit to set + * @addr: Address to count from + * + * This operation is atomic and provides acquire barrier semantics if + * the returned value is 0. + * It can be used to implement bit locks. + */ +static inline bool test_and_set_bit_lock(long nr, volatile unsigned long *addr) +{ + kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); + return arch_test_and_set_bit_lock(nr, addr); +} + +#if defined(arch_clear_bit_unlock_is_negative_byte) +/** + * clear_bit_unlock_is_negative_byte - Clear a bit in memory and test if bottom + * byte is negative, for unlock. + * @nr: the bit to clear + * @addr: the address to start counting from + * + * This operation is atomic and provides release barrier semantics. + * + * This is a bit of a one-trick-pony for the filemap code, which clears + * PG_locked and tests PG_waiters, + */ +static inline bool +clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr) +{ + kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); + return arch_clear_bit_unlock_is_negative_byte(nr, addr); +} +/* Let everybody know we have it. */ +#define clear_bit_unlock_is_negative_byte clear_bit_unlock_is_negative_byte +#endif + +#endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_LOCK_H */ diff --git a/include/asm-generic/bitops/instrumented-non-atomic.h b/include/asm-generic/bitops/instrumented-non-atomic.h new file mode 100644 index 000000000000..95ff28d128a1 --- /dev/null +++ b/include/asm-generic/bitops/instrumented-non-atomic.h @@ -0,0 +1,114 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * This file provides wrappers with sanitizer instrumentation for non-atomic + * bit operations. + * + * To use this functionality, an arch's bitops.h file needs to define each of + * the below bit operations with an arch_ prefix (e.g. arch_set_bit(), + * arch___set_bit(), etc.). + */ +#ifndef _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H +#define _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H + +#include + +/** + * __set_bit - Set a bit in memory + * @nr: the bit to set + * @addr: the address to start counting from + * + * Unlike set_bit(), this function is non-atomic. If it is called on the same + * region of memory concurrently, the effect may be that only one operation + * succeeds. + */ +static inline void __set_bit(long nr, volatile unsigned long *addr) +{ + kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); + arch___set_bit(nr, addr); +} + +/** + * __clear_bit - Clears a bit in memory + * @nr: the bit to clear + * @addr: the address to start counting from + * + * Unlike clear_bit(), this function is non-atomic. If it is called on the same + * region of memory concurrently, the effect may be that only one operation + * succeeds. + */ +static inline void __clear_bit(long nr, volatile unsigned long *addr) +{ + kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); + arch___clear_bit(nr, addr); +} + +/** + * __change_bit - Toggle a bit in memory + * @nr: the bit to change + * @addr: the address to start counting from + * + * Unlike change_bit(), this function is non-atomic. If it is called on the same + * region of memory concurrently, the effect may be that only one operation + * succeeds. + */ +static inline void __change_bit(long nr, volatile unsigned long *addr) +{ + kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); + arch___change_bit(nr, addr); +} + +/** + * __test_and_set_bit - Set a bit and return its old value + * @nr: Bit to set + * @addr: Address to count from + * + * This operation is non-atomic. If two instances of this operation race, one + * can appear to succeed but actually fail. + */ +static inline bool __test_and_set_bit(long nr, volatile unsigned long *addr) +{ + kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); + return arch___test_and_set_bit(nr, addr); +} + +/** + * __test_and_clear_bit - Clear a bit and return its old value + * @nr: Bit to clear + * @addr: Address to count from + * + * This operation is non-atomic. If two instances of this operation race, one + * can appear to succeed but actually fail. + */ +static inline bool __test_and_clear_bit(long nr, volatile unsigned long *addr) +{ + kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); + return arch___test_and_clear_bit(nr, addr); +} + +/** + * __test_and_change_bit - Change a bit and return its old value + * @nr: Bit to change + * @addr: Address to count from + * + * This operation is non-atomic. If two instances of this operation race, one + * can appear to succeed but actually fail. + */ +static inline bool __test_and_change_bit(long nr, volatile unsigned long *addr) +{ + kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); + return arch___test_and_change_bit(nr, addr); +} + +/** + * test_bit - Determine whether a bit is set + * @nr: bit number to test + * @addr: Address to start counting from + */ +static inline bool test_bit(long nr, const volatile unsigned long *addr) +{ + kasan_check_read(addr + BIT_WORD(nr), sizeof(long)); + return arch_test_bit(nr, addr); +} + +#endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H */ -- cgit v1.2.3 From f96c8e50152814d05a4002b8c03a80366a27afa3 Mon Sep 17 00:00:00 2001 From: Amit Kucheria Date: Mon, 21 Oct 2019 17:45:10 +0530 Subject: thermal: Remove netlink support There are no users of netlink messages for thermal inside the kernel. Remove the code and adjust the documentation. Signed-off-by: Amit Kucheria Acked-by: Viresh Kumar Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/8ff02cf62186c7a54fff325fad40a2e9ca3affa6.1571656014.git.amit.kucheria@linaro.org --- Documentation/driver-api/thermal/sysfs-api.rst | 26 ++----- drivers/thermal/thermal_core.c | 101 +------------------------ include/linux/thermal.h | 11 --- 3 files changed, 7 insertions(+), 131 deletions(-) (limited to 'include') diff --git a/Documentation/driver-api/thermal/sysfs-api.rst b/Documentation/driver-api/thermal/sysfs-api.rst index fab2c9b36d08..b40b1f839148 100644 --- a/Documentation/driver-api/thermal/sysfs-api.rst +++ b/Documentation/driver-api/thermal/sysfs-api.rst @@ -725,24 +725,10 @@ method, the sys I/F structure will be built like this:: |---temp1_input: 37000 |---temp1_crit: 100000 -4. Event Notification +4. Export Symbol APIs ===================== -The framework includes a simple notification mechanism, in the form of a -netlink event. Netlink socket initialization is done during the _init_ -of the framework. Drivers which intend to use the notification mechanism -just need to call thermal_generate_netlink_event() with two arguments viz -(originator, event). The originator is a pointer to struct thermal_zone_device -from where the event has been originated. An integer which represents the -thermal zone device will be used in the message to identify the zone. The -event will be one of:{THERMAL_AUX0, THERMAL_AUX1, THERMAL_CRITICAL, -THERMAL_DEV_FAULT}. Notification can be sent when the current temperature -crosses any of the configured thresholds. - -5. Export Symbol APIs -===================== - -5.1. get_tz_trend +4.1. get_tz_trend ----------------- This function returns the trend of a thermal zone, i.e the rate of change @@ -751,14 +737,14 @@ are supposed to implement the callback. If they don't, the thermal framework calculated the trend by comparing the previous and the current temperature values. -5.2. get_thermal_instance +4.2. get_thermal_instance ------------------------- This function returns the thermal_instance corresponding to a given {thermal_zone, cooling_device, trip_point} combination. Returns NULL if such an instance does not exist. -5.3. thermal_notify_framework +4.3. thermal_notify_framework ----------------------------- This function handles the trip events from sensor drivers. It starts @@ -768,14 +754,14 @@ and does actual throttling for other trip points i.e ACTIVE and PASSIVE. The throttling policy is based on the configured platform data; if no platform data is provided, this uses the step_wise throttling policy. -5.4. thermal_cdev_update +4.4. thermal_cdev_update ------------------------ This function serves as an arbitrator to set the state of a cooling device. It sets the cooling device to the deepest cooling state if possible. -6. thermal_emergency_poweroff +5. thermal_emergency_poweroff ============================= On an event of critical trip temperature crossing. Thermal framework diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index d4481cc8958f..cced0638b686 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -19,8 +19,6 @@ #include #include #include -#include -#include #include #define CREATE_TRACE_POINTS @@ -1464,97 +1462,6 @@ exit: } EXPORT_SYMBOL_GPL(thermal_zone_get_zone_by_name); -#ifdef CONFIG_NET -static const struct genl_multicast_group thermal_event_mcgrps[] = { - { .name = THERMAL_GENL_MCAST_GROUP_NAME, }, -}; - -static struct genl_family thermal_event_genl_family __ro_after_init = { - .module = THIS_MODULE, - .name = THERMAL_GENL_FAMILY_NAME, - .version = THERMAL_GENL_VERSION, - .maxattr = THERMAL_GENL_ATTR_MAX, - .mcgrps = thermal_event_mcgrps, - .n_mcgrps = ARRAY_SIZE(thermal_event_mcgrps), -}; - -int thermal_generate_netlink_event(struct thermal_zone_device *tz, - enum events event) -{ - struct sk_buff *skb; - struct nlattr *attr; - struct thermal_genl_event *thermal_event; - void *msg_header; - int size; - int result; - static unsigned int thermal_event_seqnum; - - if (!tz) - return -EINVAL; - - /* allocate memory */ - size = nla_total_size(sizeof(struct thermal_genl_event)) + - nla_total_size(0); - - skb = genlmsg_new(size, GFP_ATOMIC); - if (!skb) - return -ENOMEM; - - /* add the genetlink message header */ - msg_header = genlmsg_put(skb, 0, thermal_event_seqnum++, - &thermal_event_genl_family, 0, - THERMAL_GENL_CMD_EVENT); - if (!msg_header) { - nlmsg_free(skb); - return -ENOMEM; - } - - /* fill the data */ - attr = nla_reserve(skb, THERMAL_GENL_ATTR_EVENT, - sizeof(struct thermal_genl_event)); - - if (!attr) { - nlmsg_free(skb); - return -EINVAL; - } - - thermal_event = nla_data(attr); - if (!thermal_event) { - nlmsg_free(skb); - return -EINVAL; - } - - memset(thermal_event, 0, sizeof(struct thermal_genl_event)); - - thermal_event->orig = tz->id; - thermal_event->event = event; - - /* send multicast genetlink message */ - genlmsg_end(skb, msg_header); - - result = genlmsg_multicast(&thermal_event_genl_family, skb, 0, - 0, GFP_ATOMIC); - if (result) - dev_err(&tz->device, "Failed to send netlink event:%d", result); - - return result; -} -EXPORT_SYMBOL_GPL(thermal_generate_netlink_event); - -static int __init genetlink_init(void) -{ - return genl_register_family(&thermal_event_genl_family); -} - -static void genetlink_exit(void) -{ - genl_unregister_family(&thermal_event_genl_family); -} -#else /* !CONFIG_NET */ -static inline int genetlink_init(void) { return 0; } -static inline void genetlink_exit(void) {} -#endif /* !CONFIG_NET */ - static int thermal_pm_notify(struct notifier_block *nb, unsigned long mode, void *_unused) { @@ -1607,13 +1514,9 @@ static int __init thermal_init(void) if (result) goto unregister_governors; - result = genetlink_init(); - if (result) - goto unregister_class; - result = of_parse_thermal_zones(); if (result) - goto exit_netlink; + goto unregister_class; result = register_pm_notifier(&thermal_pm_nb); if (result) @@ -1622,8 +1525,6 @@ static int __init thermal_init(void) return 0; -exit_netlink: - genetlink_exit(); unregister_class: class_unregister(&thermal_class); unregister_governors: diff --git a/include/linux/thermal.h b/include/linux/thermal.h index e45659c75920..d9111aebb97d 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -544,15 +544,4 @@ static inline void thermal_notify_framework(struct thermal_zone_device *tz, { } #endif /* CONFIG_THERMAL */ -#if defined(CONFIG_NET) && IS_ENABLED(CONFIG_THERMAL) -extern int thermal_generate_netlink_event(struct thermal_zone_device *tz, - enum events event); -#else -static inline int thermal_generate_netlink_event(struct thermal_zone_device *tz, - enum events event) -{ - return 0; -} -#endif - #endif /* __THERMAL_H__ */ -- cgit v1.2.3 From f5bf3c06730c1bd85a3c064357de433736facc5a Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Wed, 30 Oct 2019 10:10:36 +0100 Subject: thermal: cpu_cooling: Remove pointless dependency on CONFIG_OF The option CONFIG_CPU_THERMAL depends on CONFIG_OF in the Kconfig. It it pointless to check if CONFIG_OF is set in the header file as this is always true if CONFIG_CPU_THERMAL is true. Remove it. Signed-off-by: Daniel Lezcano Acked-by: Viresh Kumar Reviewed-by: Amit Kucheria Link: https://lore.kernel.org/r/20191030091038.678-1-daniel.lezcano@linaro.org --- include/linux/cpu_cooling.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/cpu_cooling.h b/include/linux/cpu_cooling.h index bae54bb7c048..72d1c9c5e538 100644 --- a/include/linux/cpu_cooling.h +++ b/include/linux/cpu_cooling.h @@ -47,7 +47,7 @@ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev) } #endif /* CONFIG_CPU_THERMAL */ -#if defined(CONFIG_THERMAL_OF) && defined(CONFIG_CPU_THERMAL) +#ifdef CONFIG_CPU_THERMAL /** * of_cpufreq_cooling_register - create cpufreq cooling device based on DT. * @policy: cpufreq policy. @@ -60,6 +60,6 @@ of_cpufreq_cooling_register(struct cpufreq_policy *policy) { return NULL; } -#endif /* defined(CONFIG_THERMAL_OF) && defined(CONFIG_CPU_THERMAL) */ +#endif /* CONFIG_CPU_THERMAL */ #endif /* __CPU_COOLING_H__ */ -- cgit v1.2.3 From 0cac7559f1b67aa29879ead6b6b6a856d963905f Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Wed, 30 Oct 2019 10:10:37 +0100 Subject: thermal: cpu_cooling: Reorder the header file As the conditions are simplified and unified, it is useless to have different blocks of definitions under the same compiler condition, let's merge the blocks. There is no functional change. Signed-off-by: Daniel Lezcano Acked-by: Viresh Kumar Reviewed-by: Amit Kucheria Link: https://lore.kernel.org/r/20191030091038.678-2-daniel.lezcano@linaro.org --- include/linux/cpu_cooling.h | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/cpu_cooling.h b/include/linux/cpu_cooling.h index 72d1c9c5e538..b74732535e4b 100644 --- a/include/linux/cpu_cooling.h +++ b/include/linux/cpu_cooling.h @@ -33,6 +33,13 @@ cpufreq_cooling_register(struct cpufreq_policy *policy); */ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev); +/** + * of_cpufreq_cooling_register - create cpufreq cooling device based on DT. + * @policy: cpufreq policy. + */ +struct thermal_cooling_device * +of_cpufreq_cooling_register(struct cpufreq_policy *policy); + #else /* !CONFIG_CPU_THERMAL */ static inline struct thermal_cooling_device * cpufreq_cooling_register(struct cpufreq_policy *policy) @@ -45,16 +52,7 @@ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev) { return; } -#endif /* CONFIG_CPU_THERMAL */ -#ifdef CONFIG_CPU_THERMAL -/** - * of_cpufreq_cooling_register - create cpufreq cooling device based on DT. - * @policy: cpufreq policy. - */ -struct thermal_cooling_device * -of_cpufreq_cooling_register(struct cpufreq_policy *policy); -#else static inline struct thermal_cooling_device * of_cpufreq_cooling_register(struct cpufreq_policy *policy) { -- cgit v1.2.3 From 27a47e422ef3cb09f6a428e2b05eb79079506875 Mon Sep 17 00:00:00 2001 From: Quentin Perret Date: Wed, 30 Oct 2019 15:14:49 +0000 Subject: PM / EM: Declare EM data types unconditionally The structs representing capacity states and performance domains of an Energy Model are currently only defined for CONFIG_ENERGY_MODEL=y. That makes it hard for code outside PM_EM to manipulate those structures without a lot of ifdefery or stubbed accessors. So, move the declaration of the two structs outside of the CONFIG_ENERGY_MODEL ifdef. The client code (e.g. EAS or thermal) always checks the return of em_cpu_get() before using it, so the exising code is still safe to use as-is. Reported-by: kbuild test robot Signed-off-by: Quentin Perret Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20191030151451.7961-3-qperret@google.com --- include/linux/energy_model.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 73f8c3cb9588..d249b88a4d5a 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -9,7 +9,6 @@ #include #include -#ifdef CONFIG_ENERGY_MODEL /** * em_cap_state - Capacity state of a performance domain * @frequency: The CPU frequency in KHz, for consistency with CPUFreq @@ -40,6 +39,7 @@ struct em_perf_domain { unsigned long cpus[0]; }; +#ifdef CONFIG_ENERGY_MODEL #define EM_CPU_MAX_POWER 0xFFFF struct em_data_callback { @@ -160,7 +160,6 @@ static inline int em_pd_nr_cap_states(struct em_perf_domain *pd) } #else -struct em_perf_domain {}; struct em_data_callback {}; #define EM_DATA_CB(_active_power_cb) { } -- cgit v1.2.3 From dd5ddd3c7a8c7ac382a82d15757f0ca3ab2b2dbc Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 24 Oct 2019 16:57:39 +0100 Subject: iommu/io-pgtable-arm: Rename IOMMU_QCOM_SYS_CACHE and improve doc The 'IOMMU_QCOM_SYS_CACHE' IOMMU protection flag is exposed to all users of the IOMMU API. Despite its name, the idea behind it isn't especially tied to Qualcomm implementations and could conceivably be used by other systems. Rename it to 'IOMMU_SYS_CACHE_ONLY' and update the comment to describe a bit better the idea behind it. Cc: Robin Murphy Cc: "Isaac J. Manjarres" Signed-off-by: Will Deacon --- drivers/iommu/io-pgtable-arm.c | 2 +- include/linux/iommu.h | 8 ++++---- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index cd96442af44b..bdf47f745268 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -455,7 +455,7 @@ static arm_lpae_iopte arm_lpae_prot_to_pte(struct arm_lpae_io_pgtable *data, else if (prot & IOMMU_CACHE) pte |= (ARM_LPAE_MAIR_ATTR_IDX_CACHE << ARM_LPAE_PTE_ATTRINDX_SHIFT); - else if (prot & IOMMU_QCOM_SYS_CACHE) + else if (prot & IOMMU_SYS_CACHE_ONLY) pte |= (ARM_LPAE_MAIR_ATTR_IDX_INC_OCACHE << ARM_LPAE_PTE_ATTRINDX_SHIFT); } diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 29bac5345563..a86bd21d08a9 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -31,11 +31,11 @@ */ #define IOMMU_PRIV (1 << 5) /* - * Non-coherent masters on few Qualcomm SoCs can use this page protection flag - * to set correct cacheability attributes to use an outer level of cache - - * last level cache, aka system cache. + * Non-coherent masters can use this page protection flag to set cacheable + * memory attributes for only a transparent outer level of cache, also known as + * the last-level or system cache. */ -#define IOMMU_QCOM_SYS_CACHE (1 << 6) +#define IOMMU_SYS_CACHE_ONLY (1 << 6) struct iommu_ops; struct iommu_group; -- cgit v1.2.3 From e2854a1054ab171a2c5cad6e9b7f0c580bab409d Mon Sep 17 00:00:00 2001 From: Zhenzhong Duan Date: Mon, 4 Nov 2019 17:09:37 +0800 Subject: moduleparam: fix parameter description mismatch The first parameter of module_param is @name, but @value is used in description. Fix it. Fixes: 546970bc6afc ("param: add kerneldoc to moduleparam.h") Signed-off-by: Zhenzhong Duan Signed-off-by: Jessica Yu --- include/linux/moduleparam.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h index 5ba250d9172a..e5c3e23919b8 100644 --- a/include/linux/moduleparam.h +++ b/include/linux/moduleparam.h @@ -100,11 +100,11 @@ struct kparam_array /** * module_param - typesafe helper for a module/cmdline parameter - * @value: the variable to alter, and exposed parameter name. + * @name: the variable to alter, and exposed parameter name. * @type: the type of the parameter * @perm: visibility in sysfs. * - * @value becomes the module parameter, or (prefixed by KBUILD_MODNAME and a + * @name becomes the module parameter, or (prefixed by KBUILD_MODNAME and a * ".") the kernel commandline parameter. Note that - is changed to _, so * the user can use "foo-bar=1" even for variable "foo_bar". * -- cgit v1.2.3 From dbbf98392af6e2cf3673908c1388ca1ae915c8bb Mon Sep 17 00:00:00 2001 From: Tudor Ambarus Date: Fri, 6 Sep 2019 15:06:41 +0000 Subject: memory: atmel-ebi: move NUM_CS definition inside EBI driver The total number of EBI CS lines is described by the EBI controller and not by the Matrix. Move the definition for the number of CS inside EBI driver. Signed-off-by: Tudor Ambarus Link: https://lore.kernel.org/r/20190906150632.19039-1-tudor.ambarus@microchip.com Signed-off-by: Alexandre Belloni --- drivers/memory/atmel-ebi.c | 6 ++++-- include/linux/mfd/syscon/atmel-matrix.h | 1 - 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/memory/atmel-ebi.c b/drivers/memory/atmel-ebi.c index 0322df9dc249..8515196c2b03 100644 --- a/drivers/memory/atmel-ebi.c +++ b/drivers/memory/atmel-ebi.c @@ -19,6 +19,8 @@ #include #include +#define AT91_EBI_NUM_CS 8 + struct atmel_ebi_dev_config { int cs; struct atmel_smc_cs_conf smcconf; @@ -314,7 +316,7 @@ static int atmel_ebi_dev_setup(struct atmel_ebi *ebi, struct device_node *np, if (ret) return ret; - if (cs >= AT91_MATRIX_EBI_NUM_CS || + if (cs >= AT91_EBI_NUM_CS || !(ebi->caps->available_cs & BIT(cs))) { dev_err(dev, "invalid reg property in %pOF\n", np); return -EINVAL; @@ -344,7 +346,7 @@ static int atmel_ebi_dev_setup(struct atmel_ebi *ebi, struct device_node *np, apply = true; i = 0; - for_each_set_bit(cs, &cslines, AT91_MATRIX_EBI_NUM_CS) { + for_each_set_bit(cs, &cslines, AT91_EBI_NUM_CS) { ebid->configs[i].cs = cs; if (apply) { diff --git a/include/linux/mfd/syscon/atmel-matrix.h b/include/linux/mfd/syscon/atmel-matrix.h index f61cd127a852..20c25665216a 100644 --- a/include/linux/mfd/syscon/atmel-matrix.h +++ b/include/linux/mfd/syscon/atmel-matrix.h @@ -106,7 +106,6 @@ #define AT91_MATRIX_DDR_IOSR BIT(18) #define AT91_MATRIX_NFD0_SELECT BIT(24) #define AT91_MATRIX_DDR_MP_EN BIT(25) -#define AT91_MATRIX_EBI_NUM_CS 8 #define AT91_MATRIX_USBPUCR_PUON BIT(30) -- cgit v1.2.3 From 9237f04e12cc385334043cd7cf84b74dcbda0256 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Wed, 30 Oct 2019 18:08:47 +0900 Subject: scsi: core: Fix scsi_get/set_resid() interface struct scsi_cmnd cmd->req.resid_len which is returned and set respectively by the helper functions scsi_get_resid() and scsi_set_resid() is an unsigned int. Reflect this fact in the interface of these helper functions. Also fix compilation errors due to min() and max() type mismatch introduced by this change in scsi debug code, usb transport code and in the USB ENE card reader driver. Link: https://lore.kernel.org/r/20191030090847.25650-1-damien.lemoal@wdc.com Signed-off-by: Damien Le Moal Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_debug.c | 4 ++-- drivers/usb/storage/ene_ub6250.c | 2 +- drivers/usb/storage/transport.c | 3 +-- include/scsi/scsi_cmnd.h | 4 ++-- 4 files changed, 6 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index d323523f5f9d..4daf2637c011 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -1025,7 +1025,7 @@ static int fill_from_dev_buffer(struct scsi_cmnd *scp, unsigned char *arr, static int p_fill_from_dev_buffer(struct scsi_cmnd *scp, const void *arr, int arr_len, unsigned int off_dst) { - int act_len, n; + unsigned int act_len, n; struct scsi_data_buffer *sdb = &scp->sdb; off_t skip = off_dst; @@ -1039,7 +1039,7 @@ static int p_fill_from_dev_buffer(struct scsi_cmnd *scp, const void *arr, pr_debug("%s: off_dst=%u, scsi_bufflen=%u, act_len=%u, resid=%d\n", __func__, off_dst, scsi_bufflen(scp), act_len, scsi_get_resid(scp)); - n = (int)scsi_bufflen(scp) - ((int)off_dst + act_len); + n = scsi_bufflen(scp) - (off_dst + act_len); scsi_set_resid(scp, min(scsi_get_resid(scp), n)); return 0; } diff --git a/drivers/usb/storage/ene_ub6250.c b/drivers/usb/storage/ene_ub6250.c index 8b1b73065421..98c1aa594e6c 100644 --- a/drivers/usb/storage/ene_ub6250.c +++ b/drivers/usb/storage/ene_ub6250.c @@ -561,7 +561,7 @@ static int ene_send_scsi_cmd(struct us_data *us, u8 fDir, void *buf, int use_sg) residue = min(residue, transfer_length); if (us->srb != NULL) scsi_set_resid(us->srb, max(scsi_get_resid(us->srb), - (int)residue)); + residue)); } if (bcs->Status != US_BULK_STAT_OK) diff --git a/drivers/usb/storage/transport.c b/drivers/usb/storage/transport.c index 96cb0409dd89..238a8088e17f 100644 --- a/drivers/usb/storage/transport.c +++ b/drivers/usb/storage/transport.c @@ -1284,8 +1284,7 @@ int usb_stor_Bulk_transport(struct scsi_cmnd *srb, struct us_data *us) } else { residue = min(residue, transfer_length); - scsi_set_resid(srb, max(scsi_get_resid(srb), - (int) residue)); + scsi_set_resid(srb, max(scsi_get_resid(srb), residue)); } } diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h index 9c22e85902ec..a2849bb9cd19 100644 --- a/include/scsi/scsi_cmnd.h +++ b/include/scsi/scsi_cmnd.h @@ -191,12 +191,12 @@ static inline unsigned scsi_bufflen(struct scsi_cmnd *cmd) return cmd->sdb.length; } -static inline void scsi_set_resid(struct scsi_cmnd *cmd, int resid) +static inline void scsi_set_resid(struct scsi_cmnd *cmd, unsigned int resid) { cmd->req.resid_len = resid; } -static inline int scsi_get_resid(struct scsi_cmnd *cmd) +static inline unsigned int scsi_get_resid(struct scsi_cmnd *cmd) { return cmd->req.resid_len; } -- cgit v1.2.3 From ffedbf0cba153c91a0da5d1280a5e639664c5ab3 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 8 Nov 2019 16:57:59 +0000 Subject: irqchip/gic-v3-its: Kill its->ite_size and use TYPER copy instead Now that we have a copy of TYPER in the ITS structure, rely on this to provide the same service as its->ite_size, which gets axed. Errata workarounds are now updating the cached fields instead of requiring a separate field in the ITS structure. Signed-off-by: Marc Zyngier Reviewed-by: Zenghui Yu Link: https://lore.kernel.org/r/20191027144234.8395-6-maz@kernel.org Link: https://lore.kernel.org/r/20191108165805.3071-6-maz@kernel.org --- drivers/irqchip/irq-gic-v3-its.c | 8 ++++---- include/linux/irqchip/arm-gic-v3.h | 2 +- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 5bb3eacbbde4..c3a1e47e7836 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -6,6 +6,7 @@ #include #include +#include #include #include #include @@ -108,7 +109,6 @@ struct its_node { struct list_head its_device_list; u64 flags; unsigned long list_nr; - u32 ite_size; u32 device_ids; int numa_node; unsigned int msi_domain_flags; @@ -2453,7 +2453,7 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id, * sized as a power of two (and you need at least one bit...). */ nr_ites = max(2, nvecs); - sz = nr_ites * its->ite_size; + sz = nr_ites * (FIELD_GET(GITS_TYPER_ITT_ENTRY_SIZE, its->typer) + 1); sz = max(sz, ITS_ITT_ALIGN) + ITS_ITT_ALIGN - 1; itt = kzalloc_node(sz, GFP_KERNEL, its->numa_node); if (alloc_lpis) { @@ -3268,7 +3268,8 @@ static bool __maybe_unused its_enable_quirk_qdf2400_e0065(void *data) struct its_node *its = data; /* On QDF2400, the size of the ITE is 16Bytes */ - its->ite_size = 16; + its->typer &= ~GITS_TYPER_ITT_ENTRY_SIZE; + its->typer |= FIELD_PREP(GITS_TYPER_ITT_ENTRY_SIZE, 16 - 1); return true; } @@ -3637,7 +3638,6 @@ static int __init its_probe_one(struct resource *res, its->typer = typer; its->base = its_base; its->phys_base = res->start; - its->ite_size = GITS_TYPER_ITT_ENTRY_SIZE(typer); its->device_ids = GITS_TYPER_DEVBITS(typer); if (is_v4(its)) { if (!(typer & GITS_TYPER_VMOVP)) { diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 5cc10cf7cb3e..4bce7a904075 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -334,7 +334,7 @@ #define GITS_TYPER_PLPIS (1UL << 0) #define GITS_TYPER_VLPIS (1UL << 1) #define GITS_TYPER_ITT_ENTRY_SIZE_SHIFT 4 -#define GITS_TYPER_ITT_ENTRY_SIZE(r) ((((r) >> GITS_TYPER_ITT_ENTRY_SIZE_SHIFT) & 0xf) + 1) +#define GITS_TYPER_ITT_ENTRY_SIZE GENMASK_ULL(7, 4) #define GITS_TYPER_IDBITS_SHIFT 8 #define GITS_TYPER_DEVBITS_SHIFT 13 #define GITS_TYPER_DEVBITS(r) ((((r) >> GITS_TYPER_DEVBITS_SHIFT) & 0x1f) + 1) -- cgit v1.2.3 From 576a83429757999f220f36f206044af2b9026672 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 8 Nov 2019 16:58:00 +0000 Subject: irqchip/gic-v3-its: Kill its->device_ids and use TYPER copy instead Now that we have a copy of TYPER in the ITS structure, rely on this to provide the same service as its->device_ids, which gets axed. Errata workarounds are now updating the cached fields instead of requiring a separate field in the ITS structure. Signed-off-by: Marc Zyngier Reviewed-by: Zenghui Yu Link: https://lore.kernel.org/r/20191027144234.8395-7-maz@kernel.org Link: https://lore.kernel.org/r/20191108165805.3071-7-maz@kernel.org --- drivers/irqchip/irq-gic-v3-its.c | 24 +++++++++++++----------- include/linux/irqchip/arm-gic-v3.h | 2 +- 2 files changed, 14 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index c3a1e47e7836..e8aeb07e1cb0 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -109,7 +109,6 @@ struct its_node { struct list_head its_device_list; u64 flags; unsigned long list_nr; - u32 device_ids; int numa_node; unsigned int msi_domain_flags; u32 pre_its_base; /* for Socionext Synquacer */ @@ -117,6 +116,7 @@ struct its_node { }; #define is_v4(its) (!!((its)->typer & GITS_TYPER_VLPIS)) +#define device_ids(its) (FIELD_GET(GITS_TYPER_DEVBITS, (its)->typer) + 1) #define ITS_ITT_ALIGN SZ_256 @@ -1956,9 +1956,9 @@ static bool its_parse_indirect_baser(struct its_node *its, if (new_order >= MAX_ORDER) { new_order = MAX_ORDER - 1; ids = ilog2(PAGE_ORDER_TO_SIZE(new_order) / (int)esz); - pr_warn("ITS@%pa: %s Table too large, reduce ids %u->%u\n", + pr_warn("ITS@%pa: %s Table too large, reduce ids %llu->%u\n", &its->phys_base, its_base_type_string[type], - its->device_ids, ids); + device_ids(its), ids); } *order = new_order; @@ -2004,7 +2004,7 @@ static int its_alloc_tables(struct its_node *its) case GITS_BASER_TYPE_DEVICE: indirect = its_parse_indirect_baser(its, baser, psz, &order, - its->device_ids); + device_ids(its)); break; case GITS_BASER_TYPE_VCPU: @@ -2395,7 +2395,7 @@ static bool its_alloc_device_table(struct its_node *its, u32 dev_id) /* Don't allow device id that exceeds ITS hardware limit */ if (!baser) - return (ilog2(dev_id) < its->device_ids); + return (ilog2(dev_id) < device_ids(its)); return its_alloc_table_entry(its, baser, dev_id); } @@ -3247,8 +3247,9 @@ static bool __maybe_unused its_enable_quirk_cavium_22375(void *data) { struct its_node *its = data; - /* erratum 22375: only alloc 8MB table size */ - its->device_ids = 0x14; /* 20 bits, 8MB */ + /* erratum 22375: only alloc 8MB table size (20 bits) */ + its->typer &= ~GITS_TYPER_DEVBITS; + its->typer |= FIELD_PREP(GITS_TYPER_DEVBITS, 20 - 1); its->flags |= ITS_FLAGS_WORKAROUND_CAVIUM_22375; return true; @@ -3303,8 +3304,10 @@ static bool __maybe_unused its_enable_quirk_socionext_synquacer(void *data) its->get_msi_base = its_irq_get_msi_base_pre_its; ids = ilog2(pre_its_window[1]) - 2; - if (its->device_ids > ids) - its->device_ids = ids; + if (device_ids(its) > ids) { + its->typer &= ~GITS_TYPER_DEVBITS; + its->typer |= FIELD_PREP(GITS_TYPER_DEVBITS, ids - 1); + } /* the pre-ITS breaks isolation, so disable MSI remapping */ its->msi_domain_flags &= ~IRQ_DOMAIN_FLAG_MSI_REMAP; @@ -3537,7 +3540,7 @@ static int its_init_vpe_domain(void) } /* Use the last possible DevID */ - devid = GENMASK(its->device_ids - 1, 0); + devid = GENMASK(device_ids(its) - 1, 0); vpe_proxy.dev = its_create_device(its, devid, entries, false); if (!vpe_proxy.dev) { kfree(vpe_proxy.vpes); @@ -3638,7 +3641,6 @@ static int __init its_probe_one(struct resource *res, its->typer = typer; its->base = its_base; its->phys_base = res->start; - its->device_ids = GITS_TYPER_DEVBITS(typer); if (is_v4(its)) { if (!(typer & GITS_TYPER_VMOVP)) { err = its_compute_its_list_map(res, its_base); diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 4bce7a904075..b6514e8893bf 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -337,7 +337,7 @@ #define GITS_TYPER_ITT_ENTRY_SIZE GENMASK_ULL(7, 4) #define GITS_TYPER_IDBITS_SHIFT 8 #define GITS_TYPER_DEVBITS_SHIFT 13 -#define GITS_TYPER_DEVBITS(r) ((((r) >> GITS_TYPER_DEVBITS_SHIFT) & 0x1f) + 1) +#define GITS_TYPER_DEVBITS GENMASK_ULL(17, 13) #define GITS_TYPER_PTA (1UL << 19) #define GITS_TYPER_HCC_SHIFT 24 #define GITS_TYPER_HCC(r) (((r) >> GITS_TYPER_HCC_SHIFT) & 0xff) -- cgit v1.2.3 From 20b44b4de61f2887694981e8cae74fe1bf58f950 Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Wed, 2 Oct 2019 19:25:21 +0800 Subject: irqchip: ingenic: Drop redundant irq_suspend / irq_resume functions The same behaviour can be obtained by using the IRQCHIP_MASK_ON_SUSPEND flag on the IRQ chip. Signed-off-by: Paul Cercueil Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/1570015525-27018-2-git-send-email-zhouyanjie@zoho.com --- drivers/irqchip/irq-ingenic.c | 24 +----------------------- include/linux/irqchip/ingenic.h | 14 -------------- 2 files changed, 1 insertion(+), 37 deletions(-) delete mode 100644 include/linux/irqchip/ingenic.h (limited to 'include') diff --git a/drivers/irqchip/irq-ingenic.c b/drivers/irqchip/irq-ingenic.c index f126255b3260..06fa810e89bb 100644 --- a/drivers/irqchip/irq-ingenic.c +++ b/drivers/irqchip/irq-ingenic.c @@ -10,7 +10,6 @@ #include #include #include -#include #include #include #include @@ -50,26 +49,6 @@ static irqreturn_t intc_cascade(int irq, void *data) return IRQ_HANDLED; } -static void intc_irq_set_mask(struct irq_chip_generic *gc, uint32_t mask) -{ - struct irq_chip_regs *regs = &gc->chip_types->regs; - - writel(mask, gc->reg_base + regs->enable); - writel(~mask, gc->reg_base + regs->disable); -} - -void ingenic_intc_irq_suspend(struct irq_data *data) -{ - struct irq_chip_generic *gc = irq_data_get_irq_chip_data(data); - intc_irq_set_mask(gc, gc->wake_active); -} - -void ingenic_intc_irq_resume(struct irq_data *data) -{ - struct irq_chip_generic *gc = irq_data_get_irq_chip_data(data); - intc_irq_set_mask(gc, gc->mask_cache); -} - static struct irqaction intc_cascade_action = { .handler = intc_cascade, .name = "SoC intc cascade interrupt", @@ -127,8 +106,7 @@ static int __init ingenic_intc_of_init(struct device_node *node, ct->chip.irq_mask = irq_gc_mask_disable_reg; ct->chip.irq_mask_ack = irq_gc_mask_disable_reg; ct->chip.irq_set_wake = irq_gc_set_wake; - ct->chip.irq_suspend = ingenic_intc_irq_suspend; - ct->chip.irq_resume = ingenic_intc_irq_resume; + ct->chip.flags = IRQCHIP_MASK_ON_SUSPEND; irq_setup_generic_chip(gc, IRQ_MSK(32), 0, 0, IRQ_NOPROBE | IRQ_LEVEL); diff --git a/include/linux/irqchip/ingenic.h b/include/linux/irqchip/ingenic.h deleted file mode 100644 index 146558853ad4..000000000000 --- a/include/linux/irqchip/ingenic.h +++ /dev/null @@ -1,14 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Copyright (C) 2010, Lars-Peter Clausen - */ - -#ifndef __LINUX_IRQCHIP_INGENIC_H__ -#define __LINUX_IRQCHIP_INGENIC_H__ - -#include - -extern void ingenic_intc_irq_suspend(struct irq_data *data); -extern void ingenic_intc_irq_resume(struct irq_data *data); - -#endif -- cgit v1.2.3 From 153bedbac2ebd475e1c7c2d2fa0c042f5525927d Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 8 Nov 2019 17:08:55 +0100 Subject: irq_work: Convert flags to atomic_t We need to convert flags to atomic_t in order to later fix an ordering issue on atomic_cmpxchg() failure. This will allow us to use atomic_fetch_or(). Also clarify the nature of those flags. [ mingo: Converted two more usage site the original patch missed. ] Signed-off-by: Frederic Weisbecker Cc: Linus Torvalds Cc: Paul E . McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Link: https://lkml.kernel.org/r/20191108160858.31665-2-frederic@kernel.org Signed-off-by: Ingo Molnar --- include/linux/irq_work.h | 10 +++++++--- kernel/bpf/stackmap.c | 2 +- kernel/irq_work.c | 18 +++++++++--------- kernel/printk/printk.c | 2 +- kernel/trace/bpf_trace.c | 2 +- 5 files changed, 19 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h index b11fcdfd0770..02da997ad12c 100644 --- a/include/linux/irq_work.h +++ b/include/linux/irq_work.h @@ -22,7 +22,7 @@ #define IRQ_WORK_CLAIMED (IRQ_WORK_PENDING | IRQ_WORK_BUSY) struct irq_work { - unsigned long flags; + atomic_t flags; struct llist_node llnode; void (*func)(struct irq_work *); }; @@ -30,11 +30,15 @@ struct irq_work { static inline void init_irq_work(struct irq_work *work, void (*func)(struct irq_work *)) { - work->flags = 0; + atomic_set(&work->flags, 0); work->func = func; } -#define DEFINE_IRQ_WORK(name, _f) struct irq_work name = { .func = (_f), } +#define DEFINE_IRQ_WORK(name, _f) struct irq_work name = { \ + .flags = ATOMIC_INIT(0), \ + .func = (_f) \ +} + bool irq_work_queue(struct irq_work *work); bool irq_work_queue_on(struct irq_work *work, int cpu); diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 052580c33d26..4d31284095e2 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -289,7 +289,7 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, if (in_nmi()) { work = this_cpu_ptr(&up_read_work); - if (work->irq_work.flags & IRQ_WORK_BUSY) + if (atomic_read(&work->irq_work.flags) & IRQ_WORK_BUSY) /* cannot queue more up_read, fallback */ irq_work_busy = true; } diff --git a/kernel/irq_work.c b/kernel/irq_work.c index d42acaf81886..df0dbf4d859b 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -29,16 +29,16 @@ static DEFINE_PER_CPU(struct llist_head, lazy_list); */ static bool irq_work_claim(struct irq_work *work) { - unsigned long flags, oflags, nflags; + int flags, oflags, nflags; /* * Start with our best wish as a premise but only trust any * flag value after cmpxchg() result. */ - flags = work->flags & ~IRQ_WORK_PENDING; + flags = atomic_read(&work->flags) & ~IRQ_WORK_PENDING; for (;;) { nflags = flags | IRQ_WORK_CLAIMED; - oflags = cmpxchg(&work->flags, flags, nflags); + oflags = atomic_cmpxchg(&work->flags, flags, nflags); if (oflags == flags) break; if (oflags & IRQ_WORK_PENDING) @@ -61,7 +61,7 @@ void __weak arch_irq_work_raise(void) static void __irq_work_queue_local(struct irq_work *work) { /* If the work is "lazy", handle it from next tick if any */ - if (work->flags & IRQ_WORK_LAZY) { + if (atomic_read(&work->flags) & IRQ_WORK_LAZY) { if (llist_add(&work->llnode, this_cpu_ptr(&lazy_list)) && tick_nohz_tick_stopped()) arch_irq_work_raise(); @@ -143,7 +143,7 @@ static void irq_work_run_list(struct llist_head *list) { struct irq_work *work, *tmp; struct llist_node *llnode; - unsigned long flags; + int flags; BUG_ON(!irqs_disabled()); @@ -159,15 +159,15 @@ static void irq_work_run_list(struct llist_head *list) * to claim that work don't rely on us to handle their data * while we are in the middle of the func. */ - flags = work->flags & ~IRQ_WORK_PENDING; - xchg(&work->flags, flags); + flags = atomic_read(&work->flags) & ~IRQ_WORK_PENDING; + atomic_xchg(&work->flags, flags); work->func(work); /* * Clear the BUSY bit and return to the free state if * no-one else claimed it meanwhile. */ - (void)cmpxchg(&work->flags, flags, flags & ~IRQ_WORK_BUSY); + (void)atomic_cmpxchg(&work->flags, flags, flags & ~IRQ_WORK_BUSY); } } @@ -199,7 +199,7 @@ void irq_work_sync(struct irq_work *work) { lockdep_assert_irqs_enabled(); - while (work->flags & IRQ_WORK_BUSY) + while (atomic_read(&work->flags) & IRQ_WORK_BUSY) cpu_relax(); } EXPORT_SYMBOL_GPL(irq_work_sync); diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index ca65327a6de8..865727373a3b 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -2961,7 +2961,7 @@ static void wake_up_klogd_work_func(struct irq_work *irq_work) static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) = { .func = wake_up_klogd_work_func, - .flags = IRQ_WORK_LAZY, + .flags = ATOMIC_INIT(IRQ_WORK_LAZY), }; void wake_up_klogd(void) diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 44bd08f2443b..ff467a4e2639 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -660,7 +660,7 @@ BPF_CALL_1(bpf_send_signal, u32, sig) return -EINVAL; work = this_cpu_ptr(&send_signal_work); - if (work->irq_work.flags & IRQ_WORK_BUSY) + if (atomic_read(&work->irq_work.flags) & IRQ_WORK_BUSY) return -EBUSY; /* Add the current task, which is the target of sending signal, -- cgit v1.2.3 From a31ec048ef01a76ff893e0fa482e569d04d0c4b4 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Fri, 18 Oct 2019 13:31:47 +0900 Subject: asm-generic/export.h: make __ksymtab_* local symbols For EXPORT_SYMBOL from C files, defines __ksymtab_* as local symbols. For EXPORT_SYMBOL from assembly, in contrast, produces globally-visible __ksymtab_* symbols due to this .globl directive. I do not know why this must be global. It still works without this. Signed-off-by: Masahiro Yamada --- include/asm-generic/export.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/asm-generic/export.h b/include/asm-generic/export.h index fa577978fbbd..80ef2dc0c8be 100644 --- a/include/asm-generic/export.h +++ b/include/asm-generic/export.h @@ -31,7 +31,6 @@ */ .macro ___EXPORT_SYMBOL name,val,sec #ifdef CONFIG_MODULES - .globl __ksymtab_\name .section ___ksymtab\sec+\name,"a" .balign KSYM_ALIGN __ksymtab_\name: -- cgit v1.2.3 From 03034dbdaed8b47282d647c1100dbb0f522798f3 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Fri, 18 Oct 2019 13:31:48 +0900 Subject: asm-generic/export.h: remove unneeded __kcrctab_* symbols EXPORT_SYMBOL from assembly code produces an unused symbol __kcrctab_*. kcrctab is used as a section name (prefixed with three underscores), but never used as a symbol. Signed-off-by: Masahiro Yamada --- include/asm-generic/export.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/asm-generic/export.h b/include/asm-generic/export.h index 80ef2dc0c8be..a3983e2ce0fd 100644 --- a/include/asm-generic/export.h +++ b/include/asm-generic/export.h @@ -43,7 +43,6 @@ __kstrtab_\name: #ifdef CONFIG_MODVERSIONS .section ___kcrctab\sec+\name,"a" .balign KCRC_ALIGN -__kcrctab_\name: #if defined(CONFIG_MODULE_REL_CRCS) .long __crc_\name - . #else -- cgit v1.2.3 From e34212c75a68990f7215d64d725c61e57ca70357 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Mon, 12 Aug 2019 00:00:40 +0300 Subject: memory: tegra: Introduce Tegra30 EMC driver Introduce driver for the External Memory Controller (EMC) found on Tegra30 chips, it controls the external DRAM on the board. The purpose of this driver is to program memory timing for external memory on the EMC clock rate change. Acked-by: Peter De Schrijver Signed-off-by: Dmitry Osipenko Tested-by: Peter Geis Signed-off-by: Thierry Reding --- drivers/memory/tegra/Kconfig | 10 + drivers/memory/tegra/Makefile | 1 + drivers/memory/tegra/mc.c | 9 +- drivers/memory/tegra/mc.h | 30 +- drivers/memory/tegra/tegra30-emc.c | 1232 ++++++++++++++++++++++++++++++++++++ drivers/memory/tegra/tegra30.c | 42 ++ include/soc/tegra/mc.h | 2 +- 7 files changed, 1311 insertions(+), 15 deletions(-) create mode 100644 drivers/memory/tegra/tegra30-emc.c (limited to 'include') diff --git a/drivers/memory/tegra/Kconfig b/drivers/memory/tegra/Kconfig index 4680124ddcab..fbfbaada61a2 100644 --- a/drivers/memory/tegra/Kconfig +++ b/drivers/memory/tegra/Kconfig @@ -17,6 +17,16 @@ config TEGRA20_EMC This driver is required to change memory timings / clock rate for external memory. +config TEGRA30_EMC + bool "NVIDIA Tegra30 External Memory Controller driver" + default y + depends on TEGRA_MC && ARCH_TEGRA_3x_SOC + help + This driver is for the External Memory Controller (EMC) found on + Tegra30 chips. The EMC controls the external DRAM on the board. + This driver is required to change memory timings / clock rate for + external memory. + config TEGRA124_EMC bool "NVIDIA Tegra124 External Memory Controller driver" default y diff --git a/drivers/memory/tegra/Makefile b/drivers/memory/tegra/Makefile index 3971a6b7c487..3d23c4261104 100644 --- a/drivers/memory/tegra/Makefile +++ b/drivers/memory/tegra/Makefile @@ -11,5 +11,6 @@ tegra-mc-$(CONFIG_ARCH_TEGRA_210_SOC) += tegra210.o obj-$(CONFIG_TEGRA_MC) += tegra-mc.o obj-$(CONFIG_TEGRA20_EMC) += tegra20-emc.o +obj-$(CONFIG_TEGRA30_EMC) += tegra30-emc.o obj-$(CONFIG_TEGRA124_EMC) += tegra124-emc.o obj-$(CONFIG_ARCH_TEGRA_186_SOC) += tegra186.o diff --git a/drivers/memory/tegra/mc.c b/drivers/memory/tegra/mc.c index 322aa7e8b088..41ee420275f1 100644 --- a/drivers/memory/tegra/mc.c +++ b/drivers/memory/tegra/mc.c @@ -49,9 +49,6 @@ #define MC_EMEM_ADR_CFG 0x54 #define MC_EMEM_ADR_CFG_EMEM_NUMDEV BIT(0) -#define MC_TIMING_CONTROL 0xfc -#define MC_TIMING_UPDATE BIT(0) - static const struct of_device_id tegra_mc_of_match[] = { #ifdef CONFIG_ARCH_TEGRA_2x_SOC { .compatible = "nvidia,tegra20-mc-gart", .data = &tegra20_mc_soc }, @@ -308,7 +305,7 @@ static int tegra_mc_setup_latency_allowance(struct tegra_mc *mc) return 0; } -void tegra_mc_write_emem_configuration(struct tegra_mc *mc, unsigned long rate) +int tegra_mc_write_emem_configuration(struct tegra_mc *mc, unsigned long rate) { unsigned int i; struct tegra_mc_timing *timing = NULL; @@ -323,11 +320,13 @@ void tegra_mc_write_emem_configuration(struct tegra_mc *mc, unsigned long rate) if (!timing) { dev_err(mc->dev, "no memory timing registered for rate %lu\n", rate); - return; + return -EINVAL; } for (i = 0; i < mc->soc->num_emem_regs; ++i) mc_writel(mc, timing->emem_data[i], mc->soc->emem_regs[i]); + + return 0; } unsigned int tegra_mc_get_emem_device_count(struct tegra_mc *mc) diff --git a/drivers/memory/tegra/mc.h b/drivers/memory/tegra/mc.h index f9353494b708..410efc4d7e7b 100644 --- a/drivers/memory/tegra/mc.h +++ b/drivers/memory/tegra/mc.h @@ -6,20 +6,32 @@ #ifndef MEMORY_TEGRA_MC_H #define MEMORY_TEGRA_MC_H +#include #include #include #include -#define MC_INT_DECERR_MTS (1 << 16) -#define MC_INT_SECERR_SEC (1 << 13) -#define MC_INT_DECERR_VPR (1 << 12) -#define MC_INT_INVALID_APB_ASID_UPDATE (1 << 11) -#define MC_INT_INVALID_SMMU_PAGE (1 << 10) -#define MC_INT_ARBITRATION_EMEM (1 << 9) -#define MC_INT_SECURITY_VIOLATION (1 << 8) -#define MC_INT_INVALID_GART_PAGE (1 << 7) -#define MC_INT_DECERR_EMEM (1 << 6) +#define MC_INT_DECERR_MTS BIT(16) +#define MC_INT_SECERR_SEC BIT(13) +#define MC_INT_DECERR_VPR BIT(12) +#define MC_INT_INVALID_APB_ASID_UPDATE BIT(11) +#define MC_INT_INVALID_SMMU_PAGE BIT(10) +#define MC_INT_ARBITRATION_EMEM BIT(9) +#define MC_INT_SECURITY_VIOLATION BIT(8) +#define MC_INT_INVALID_GART_PAGE BIT(7) +#define MC_INT_DECERR_EMEM BIT(6) + +#define MC_EMEM_ARB_OUTSTANDING_REQ 0x94 +#define MC_EMEM_ARB_OUTSTANDING_REQ_MAX_MASK 0x1ff +#define MC_EMEM_ARB_OUTSTANDING_REQ_HOLDOFF_OVERRIDE BIT(30) +#define MC_EMEM_ARB_OUTSTANDING_REQ_LIMIT_ENABLE BIT(31) + +#define MC_EMEM_ARB_OVERRIDE 0xe8 +#define MC_EMEM_ARB_OVERRIDE_EACK_MASK 0x3 + +#define MC_TIMING_CONTROL 0xfc +#define MC_TIMING_UPDATE BIT(0) static inline u32 mc_readl(struct tegra_mc *mc, unsigned long offset) { diff --git a/drivers/memory/tegra/tegra30-emc.c b/drivers/memory/tegra/tegra30-emc.c new file mode 100644 index 000000000000..6929980bf907 --- /dev/null +++ b/drivers/memory/tegra/tegra30-emc.c @@ -0,0 +1,1232 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Tegra30 External Memory Controller driver + * + * Based on downstream driver from NVIDIA and tegra124-emc.c + * Copyright (C) 2011-2014 NVIDIA Corporation + * + * Author: Dmitry Osipenko + * Copyright (C) 2019 GRATE-DRIVER project + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "mc.h" + +#define EMC_INTSTATUS 0x000 +#define EMC_INTMASK 0x004 +#define EMC_DBG 0x008 +#define EMC_CFG 0x00c +#define EMC_REFCTRL 0x020 +#define EMC_TIMING_CONTROL 0x028 +#define EMC_RC 0x02c +#define EMC_RFC 0x030 +#define EMC_RAS 0x034 +#define EMC_RP 0x038 +#define EMC_R2W 0x03c +#define EMC_W2R 0x040 +#define EMC_R2P 0x044 +#define EMC_W2P 0x048 +#define EMC_RD_RCD 0x04c +#define EMC_WR_RCD 0x050 +#define EMC_RRD 0x054 +#define EMC_REXT 0x058 +#define EMC_WDV 0x05c +#define EMC_QUSE 0x060 +#define EMC_QRST 0x064 +#define EMC_QSAFE 0x068 +#define EMC_RDV 0x06c +#define EMC_REFRESH 0x070 +#define EMC_BURST_REFRESH_NUM 0x074 +#define EMC_PDEX2WR 0x078 +#define EMC_PDEX2RD 0x07c +#define EMC_PCHG2PDEN 0x080 +#define EMC_ACT2PDEN 0x084 +#define EMC_AR2PDEN 0x088 +#define EMC_RW2PDEN 0x08c +#define EMC_TXSR 0x090 +#define EMC_TCKE 0x094 +#define EMC_TFAW 0x098 +#define EMC_TRPAB 0x09c +#define EMC_TCLKSTABLE 0x0a0 +#define EMC_TCLKSTOP 0x0a4 +#define EMC_TREFBW 0x0a8 +#define EMC_QUSE_EXTRA 0x0ac +#define EMC_ODT_WRITE 0x0b0 +#define EMC_ODT_READ 0x0b4 +#define EMC_WEXT 0x0b8 +#define EMC_CTT 0x0bc +#define EMC_MRS_WAIT_CNT 0x0c8 +#define EMC_MRS 0x0cc +#define EMC_EMRS 0x0d0 +#define EMC_SELF_REF 0x0e0 +#define EMC_MRW 0x0e8 +#define EMC_XM2DQSPADCTRL3 0x0f8 +#define EMC_FBIO_SPARE 0x100 +#define EMC_FBIO_CFG5 0x104 +#define EMC_FBIO_CFG6 0x114 +#define EMC_CFG_RSV 0x120 +#define EMC_AUTO_CAL_CONFIG 0x2a4 +#define EMC_AUTO_CAL_INTERVAL 0x2a8 +#define EMC_AUTO_CAL_STATUS 0x2ac +#define EMC_STATUS 0x2b4 +#define EMC_CFG_2 0x2b8 +#define EMC_CFG_DIG_DLL 0x2bc +#define EMC_CFG_DIG_DLL_PERIOD 0x2c0 +#define EMC_CTT_DURATION 0x2d8 +#define EMC_CTT_TERM_CTRL 0x2dc +#define EMC_ZCAL_INTERVAL 0x2e0 +#define EMC_ZCAL_WAIT_CNT 0x2e4 +#define EMC_ZQ_CAL 0x2ec +#define EMC_XM2CMDPADCTRL 0x2f0 +#define EMC_XM2DQSPADCTRL2 0x2fc +#define EMC_XM2DQPADCTRL2 0x304 +#define EMC_XM2CLKPADCTRL 0x308 +#define EMC_XM2COMPPADCTRL 0x30c +#define EMC_XM2VTTGENPADCTRL 0x310 +#define EMC_XM2VTTGENPADCTRL2 0x314 +#define EMC_XM2QUSEPADCTRL 0x318 +#define EMC_DLL_XFORM_DQS0 0x328 +#define EMC_DLL_XFORM_DQS1 0x32c +#define EMC_DLL_XFORM_DQS2 0x330 +#define EMC_DLL_XFORM_DQS3 0x334 +#define EMC_DLL_XFORM_DQS4 0x338 +#define EMC_DLL_XFORM_DQS5 0x33c +#define EMC_DLL_XFORM_DQS6 0x340 +#define EMC_DLL_XFORM_DQS7 0x344 +#define EMC_DLL_XFORM_QUSE0 0x348 +#define EMC_DLL_XFORM_QUSE1 0x34c +#define EMC_DLL_XFORM_QUSE2 0x350 +#define EMC_DLL_XFORM_QUSE3 0x354 +#define EMC_DLL_XFORM_QUSE4 0x358 +#define EMC_DLL_XFORM_QUSE5 0x35c +#define EMC_DLL_XFORM_QUSE6 0x360 +#define EMC_DLL_XFORM_QUSE7 0x364 +#define EMC_DLL_XFORM_DQ0 0x368 +#define EMC_DLL_XFORM_DQ1 0x36c +#define EMC_DLL_XFORM_DQ2 0x370 +#define EMC_DLL_XFORM_DQ3 0x374 +#define EMC_DLI_TRIM_TXDQS0 0x3a8 +#define EMC_DLI_TRIM_TXDQS1 0x3ac +#define EMC_DLI_TRIM_TXDQS2 0x3b0 +#define EMC_DLI_TRIM_TXDQS3 0x3b4 +#define EMC_DLI_TRIM_TXDQS4 0x3b8 +#define EMC_DLI_TRIM_TXDQS5 0x3bc +#define EMC_DLI_TRIM_TXDQS6 0x3c0 +#define EMC_DLI_TRIM_TXDQS7 0x3c4 +#define EMC_STALL_THEN_EXE_BEFORE_CLKCHANGE 0x3c8 +#define EMC_STALL_THEN_EXE_AFTER_CLKCHANGE 0x3cc +#define EMC_UNSTALL_RW_AFTER_CLKCHANGE 0x3d0 +#define EMC_SEL_DPD_CTRL 0x3d8 +#define EMC_PRE_REFRESH_REQ_CNT 0x3dc +#define EMC_DYN_SELF_REF_CONTROL 0x3e0 +#define EMC_TXSRDLL 0x3e4 + +#define EMC_STATUS_TIMING_UPDATE_STALLED BIT(23) + +#define EMC_MODE_SET_DLL_RESET BIT(8) +#define EMC_MODE_SET_LONG_CNT BIT(26) + +#define EMC_SELF_REF_CMD_ENABLED BIT(0) + +#define DRAM_DEV_SEL_ALL (0 << 30) +#define DRAM_DEV_SEL_0 (2 << 30) +#define DRAM_DEV_SEL_1 (1 << 30) +#define DRAM_BROADCAST(num) \ + ((num) > 1 ? DRAM_DEV_SEL_ALL : DRAM_DEV_SEL_0) + +#define EMC_ZQ_CAL_CMD BIT(0) +#define EMC_ZQ_CAL_LONG BIT(4) +#define EMC_ZQ_CAL_LONG_CMD_DEV0 \ + (DRAM_DEV_SEL_0 | EMC_ZQ_CAL_LONG | EMC_ZQ_CAL_CMD) +#define EMC_ZQ_CAL_LONG_CMD_DEV1 \ + (DRAM_DEV_SEL_1 | EMC_ZQ_CAL_LONG | EMC_ZQ_CAL_CMD) + +#define EMC_DBG_READ_MUX_ASSEMBLY BIT(0) +#define EMC_DBG_WRITE_MUX_ACTIVE BIT(1) +#define EMC_DBG_FORCE_UPDATE BIT(2) +#define EMC_DBG_CFG_PRIORITY BIT(24) + +#define EMC_CFG5_QUSE_MODE_SHIFT 13 +#define EMC_CFG5_QUSE_MODE_MASK (7 << EMC_CFG5_QUSE_MODE_SHIFT) + +#define EMC_CFG5_QUSE_MODE_INTERNAL_LPBK 2 +#define EMC_CFG5_QUSE_MODE_PULSE_INTERN 3 + +#define EMC_SEL_DPD_CTRL_QUSE_DPD_ENABLE BIT(9) + +#define EMC_XM2COMPPADCTRL_VREF_CAL_ENABLE BIT(10) + +#define EMC_XM2QUSEPADCTRL_IVREF_ENABLE BIT(4) + +#define EMC_XM2DQSPADCTRL2_VREF_ENABLE BIT(5) +#define EMC_XM2DQSPADCTRL3_VREF_ENABLE BIT(5) + +#define EMC_AUTO_CAL_STATUS_ACTIVE BIT(31) + +#define EMC_FBIO_CFG5_DRAM_TYPE_MASK 0x3 + +#define EMC_MRS_WAIT_CNT_SHORT_WAIT_MASK 0x3ff +#define EMC_MRS_WAIT_CNT_LONG_WAIT_SHIFT 16 +#define EMC_MRS_WAIT_CNT_LONG_WAIT_MASK \ + (0x3ff << EMC_MRS_WAIT_CNT_LONG_WAIT_SHIFT) + +#define EMC_REFCTRL_DEV_SEL_MASK 0x3 +#define EMC_REFCTRL_ENABLE BIT(31) +#define EMC_REFCTRL_ENABLE_ALL(num) \ + (((num) > 1 ? 0 : 2) | EMC_REFCTRL_ENABLE) +#define EMC_REFCTRL_DISABLE_ALL(num) ((num) > 1 ? 0 : 2) + +#define EMC_CFG_PERIODIC_QRST BIT(21) +#define EMC_CFG_DYN_SREF_ENABLE BIT(28) + +#define EMC_CLKCHANGE_REQ_ENABLE BIT(0) +#define EMC_CLKCHANGE_PD_ENABLE BIT(1) +#define EMC_CLKCHANGE_SR_ENABLE BIT(2) + +#define EMC_TIMING_UPDATE BIT(0) + +#define EMC_REFRESH_OVERFLOW_INT BIT(3) +#define EMC_CLKCHANGE_COMPLETE_INT BIT(4) + +enum emc_dram_type { + DRAM_TYPE_DDR3, + DRAM_TYPE_DDR1, + DRAM_TYPE_LPDDR2, + DRAM_TYPE_DDR2, +}; + +enum emc_dll_change { + DLL_CHANGE_NONE, + DLL_CHANGE_ON, + DLL_CHANGE_OFF +}; + +static const u16 emc_timing_registers[] = { + [0] = EMC_RC, + [1] = EMC_RFC, + [2] = EMC_RAS, + [3] = EMC_RP, + [4] = EMC_R2W, + [5] = EMC_W2R, + [6] = EMC_R2P, + [7] = EMC_W2P, + [8] = EMC_RD_RCD, + [9] = EMC_WR_RCD, + [10] = EMC_RRD, + [11] = EMC_REXT, + [12] = EMC_WEXT, + [13] = EMC_WDV, + [14] = EMC_QUSE, + [15] = EMC_QRST, + [16] = EMC_QSAFE, + [17] = EMC_RDV, + [18] = EMC_REFRESH, + [19] = EMC_BURST_REFRESH_NUM, + [20] = EMC_PRE_REFRESH_REQ_CNT, + [21] = EMC_PDEX2WR, + [22] = EMC_PDEX2RD, + [23] = EMC_PCHG2PDEN, + [24] = EMC_ACT2PDEN, + [25] = EMC_AR2PDEN, + [26] = EMC_RW2PDEN, + [27] = EMC_TXSR, + [28] = EMC_TXSRDLL, + [29] = EMC_TCKE, + [30] = EMC_TFAW, + [31] = EMC_TRPAB, + [32] = EMC_TCLKSTABLE, + [33] = EMC_TCLKSTOP, + [34] = EMC_TREFBW, + [35] = EMC_QUSE_EXTRA, + [36] = EMC_FBIO_CFG6, + [37] = EMC_ODT_WRITE, + [38] = EMC_ODT_READ, + [39] = EMC_FBIO_CFG5, + [40] = EMC_CFG_DIG_DLL, + [41] = EMC_CFG_DIG_DLL_PERIOD, + [42] = EMC_DLL_XFORM_DQS0, + [43] = EMC_DLL_XFORM_DQS1, + [44] = EMC_DLL_XFORM_DQS2, + [45] = EMC_DLL_XFORM_DQS3, + [46] = EMC_DLL_XFORM_DQS4, + [47] = EMC_DLL_XFORM_DQS5, + [48] = EMC_DLL_XFORM_DQS6, + [49] = EMC_DLL_XFORM_DQS7, + [50] = EMC_DLL_XFORM_QUSE0, + [51] = EMC_DLL_XFORM_QUSE1, + [52] = EMC_DLL_XFORM_QUSE2, + [53] = EMC_DLL_XFORM_QUSE3, + [54] = EMC_DLL_XFORM_QUSE4, + [55] = EMC_DLL_XFORM_QUSE5, + [56] = EMC_DLL_XFORM_QUSE6, + [57] = EMC_DLL_XFORM_QUSE7, + [58] = EMC_DLI_TRIM_TXDQS0, + [59] = EMC_DLI_TRIM_TXDQS1, + [60] = EMC_DLI_TRIM_TXDQS2, + [61] = EMC_DLI_TRIM_TXDQS3, + [62] = EMC_DLI_TRIM_TXDQS4, + [63] = EMC_DLI_TRIM_TXDQS5, + [64] = EMC_DLI_TRIM_TXDQS6, + [65] = EMC_DLI_TRIM_TXDQS7, + [66] = EMC_DLL_XFORM_DQ0, + [67] = EMC_DLL_XFORM_DQ1, + [68] = EMC_DLL_XFORM_DQ2, + [69] = EMC_DLL_XFORM_DQ3, + [70] = EMC_XM2CMDPADCTRL, + [71] = EMC_XM2DQSPADCTRL2, + [72] = EMC_XM2DQPADCTRL2, + [73] = EMC_XM2CLKPADCTRL, + [74] = EMC_XM2COMPPADCTRL, + [75] = EMC_XM2VTTGENPADCTRL, + [76] = EMC_XM2VTTGENPADCTRL2, + [77] = EMC_XM2QUSEPADCTRL, + [78] = EMC_XM2DQSPADCTRL3, + [79] = EMC_CTT_TERM_CTRL, + [80] = EMC_ZCAL_INTERVAL, + [81] = EMC_ZCAL_WAIT_CNT, + [82] = EMC_MRS_WAIT_CNT, + [83] = EMC_AUTO_CAL_CONFIG, + [84] = EMC_CTT, + [85] = EMC_CTT_DURATION, + [86] = EMC_DYN_SELF_REF_CONTROL, + [87] = EMC_FBIO_SPARE, + [88] = EMC_CFG_RSV, +}; + +struct emc_timing { + unsigned long rate; + + u32 data[ARRAY_SIZE(emc_timing_registers)]; + + u32 emc_auto_cal_interval; + u32 emc_mode_1; + u32 emc_mode_2; + u32 emc_mode_reset; + u32 emc_zcal_cnt_long; + bool emc_cfg_periodic_qrst; + bool emc_cfg_dyn_self_ref; +}; + +struct tegra_emc { + struct device *dev; + struct tegra_mc *mc; + struct completion clk_handshake_complete; + struct notifier_block clk_nb; + struct clk *clk; + void __iomem *regs; + unsigned int irq; + + struct emc_timing *timings; + unsigned int num_timings; + + u32 mc_override; + u32 emc_cfg; + + u32 emc_mode_1; + u32 emc_mode_2; + u32 emc_mode_reset; + + bool vref_cal_toggle : 1; + bool zcal_long : 1; + bool dll_on : 1; + bool prepared : 1; + bool bad_state : 1; +}; + +static irqreturn_t tegra_emc_isr(int irq, void *data) +{ + struct tegra_emc *emc = data; + u32 intmask = EMC_REFRESH_OVERFLOW_INT | EMC_CLKCHANGE_COMPLETE_INT; + u32 status; + + status = readl_relaxed(emc->regs + EMC_INTSTATUS) & intmask; + if (!status) + return IRQ_NONE; + + /* notify about EMC-CAR handshake completion */ + if (status & EMC_CLKCHANGE_COMPLETE_INT) + complete(&emc->clk_handshake_complete); + + /* notify about HW problem */ + if (status & EMC_REFRESH_OVERFLOW_INT) + dev_err_ratelimited(emc->dev, + "refresh request overflow timeout\n"); + + /* clear interrupts */ + writel_relaxed(status, emc->regs + EMC_INTSTATUS); + + return IRQ_HANDLED; +} + +static struct emc_timing *emc_find_timing(struct tegra_emc *emc, + unsigned long rate) +{ + struct emc_timing *timing = NULL; + unsigned int i; + + for (i = 0; i < emc->num_timings; i++) { + if (emc->timings[i].rate >= rate) { + timing = &emc->timings[i]; + break; + } + } + + if (!timing) { + dev_err(emc->dev, "no timing for rate %lu\n", rate); + return NULL; + } + + return timing; +} + +static bool emc_dqs_preset(struct tegra_emc *emc, struct emc_timing *timing, + bool *schmitt_to_vref) +{ + bool preset = false; + u32 val; + + if (timing->data[71] & EMC_XM2DQSPADCTRL2_VREF_ENABLE) { + val = readl_relaxed(emc->regs + EMC_XM2DQSPADCTRL2); + + if (!(val & EMC_XM2DQSPADCTRL2_VREF_ENABLE)) { + val |= EMC_XM2DQSPADCTRL2_VREF_ENABLE; + writel_relaxed(val, emc->regs + EMC_XM2DQSPADCTRL2); + + preset = true; + } + } + + if (timing->data[78] & EMC_XM2DQSPADCTRL3_VREF_ENABLE) { + val = readl_relaxed(emc->regs + EMC_XM2DQSPADCTRL3); + + if (!(val & EMC_XM2DQSPADCTRL3_VREF_ENABLE)) { + val |= EMC_XM2DQSPADCTRL3_VREF_ENABLE; + writel_relaxed(val, emc->regs + EMC_XM2DQSPADCTRL3); + + preset = true; + } + } + + if (timing->data[77] & EMC_XM2QUSEPADCTRL_IVREF_ENABLE) { + val = readl_relaxed(emc->regs + EMC_XM2QUSEPADCTRL); + + if (!(val & EMC_XM2QUSEPADCTRL_IVREF_ENABLE)) { + val |= EMC_XM2QUSEPADCTRL_IVREF_ENABLE; + writel_relaxed(val, emc->regs + EMC_XM2QUSEPADCTRL); + + *schmitt_to_vref = true; + preset = true; + } + } + + return preset; +} + +static int emc_seq_update_timing(struct tegra_emc *emc) +{ + u32 val; + int err; + + writel_relaxed(EMC_TIMING_UPDATE, emc->regs + EMC_TIMING_CONTROL); + + err = readl_relaxed_poll_timeout_atomic(emc->regs + EMC_STATUS, val, + !(val & EMC_STATUS_TIMING_UPDATE_STALLED), + 1, 200); + if (err) { + dev_err(emc->dev, "failed to update timing: %d\n", err); + return err; + } + + return 0; +} + +static int emc_prepare_mc_clk_cfg(struct tegra_emc *emc, unsigned long rate) +{ + struct tegra_mc *mc = emc->mc; + unsigned int misc0_index = 16; + unsigned int i; + bool same; + + for (i = 0; i < mc->num_timings; i++) { + if (mc->timings[i].rate != rate) + continue; + + if (mc->timings[i].emem_data[misc0_index] & BIT(27)) + same = true; + else + same = false; + + return tegra20_clk_prepare_emc_mc_same_freq(emc->clk, same); + } + + return -EINVAL; +} + +static int emc_prepare_timing_change(struct tegra_emc *emc, unsigned long rate) +{ + struct emc_timing *timing = emc_find_timing(emc, rate); + enum emc_dll_change dll_change; + enum emc_dram_type dram_type; + bool schmitt_to_vref = false; + unsigned int pre_wait = 0; + bool qrst_used = false; + unsigned int dram_num; + unsigned int i; + u32 fbio_cfg5; + u32 emc_dbg; + u32 val; + int err; + + if (!timing || emc->bad_state) + return -EINVAL; + + dev_dbg(emc->dev, "%s: using timing rate %lu for requested rate %lu\n", + __func__, timing->rate, rate); + + emc->bad_state = true; + + err = emc_prepare_mc_clk_cfg(emc, rate); + if (err) { + dev_err(emc->dev, "mc clock preparation failed: %d\n", err); + return err; + } + + emc->vref_cal_toggle = false; + emc->mc_override = mc_readl(emc->mc, MC_EMEM_ARB_OVERRIDE); + emc->emc_cfg = readl_relaxed(emc->regs + EMC_CFG); + emc_dbg = readl_relaxed(emc->regs + EMC_DBG); + + if (emc->dll_on == !!(timing->emc_mode_1 & 0x1)) + dll_change = DLL_CHANGE_NONE; + else if (timing->emc_mode_1 & 0x1) + dll_change = DLL_CHANGE_ON; + else + dll_change = DLL_CHANGE_OFF; + + emc->dll_on = !!(timing->emc_mode_1 & 0x1); + + if (timing->data[80] && !readl_relaxed(emc->regs + EMC_ZCAL_INTERVAL)) + emc->zcal_long = true; + else + emc->zcal_long = false; + + fbio_cfg5 = readl_relaxed(emc->regs + EMC_FBIO_CFG5); + dram_type = fbio_cfg5 & EMC_FBIO_CFG5_DRAM_TYPE_MASK; + + dram_num = tegra_mc_get_emem_device_count(emc->mc); + + /* disable dynamic self-refresh */ + if (emc->emc_cfg & EMC_CFG_DYN_SREF_ENABLE) { + emc->emc_cfg &= ~EMC_CFG_DYN_SREF_ENABLE; + writel_relaxed(emc->emc_cfg, emc->regs + EMC_CFG); + + pre_wait = 5; + } + + /* update MC arbiter settings */ + val = mc_readl(emc->mc, MC_EMEM_ARB_OUTSTANDING_REQ); + if (!(val & MC_EMEM_ARB_OUTSTANDING_REQ_HOLDOFF_OVERRIDE) || + ((val & MC_EMEM_ARB_OUTSTANDING_REQ_MAX_MASK) > 0x50)) { + + val = MC_EMEM_ARB_OUTSTANDING_REQ_LIMIT_ENABLE | + MC_EMEM_ARB_OUTSTANDING_REQ_HOLDOFF_OVERRIDE | 0x50; + mc_writel(emc->mc, val, MC_EMEM_ARB_OUTSTANDING_REQ); + mc_writel(emc->mc, MC_TIMING_UPDATE, MC_TIMING_CONTROL); + } + + if (emc->mc_override & MC_EMEM_ARB_OVERRIDE_EACK_MASK) + mc_writel(emc->mc, + emc->mc_override & ~MC_EMEM_ARB_OVERRIDE_EACK_MASK, + MC_EMEM_ARB_OVERRIDE); + + /* check DQ/DQS VREF delay */ + if (emc_dqs_preset(emc, timing, &schmitt_to_vref)) { + if (pre_wait < 3) + pre_wait = 3; + } + + if (pre_wait) { + err = emc_seq_update_timing(emc); + if (err) + return err; + + udelay(pre_wait); + } + + /* disable auto-calibration if VREF mode is switching */ + if (timing->emc_auto_cal_interval) { + val = readl_relaxed(emc->regs + EMC_XM2COMPPADCTRL); + val ^= timing->data[74]; + + if (val & EMC_XM2COMPPADCTRL_VREF_CAL_ENABLE) { + writel_relaxed(0, emc->regs + EMC_AUTO_CAL_INTERVAL); + + err = readl_relaxed_poll_timeout_atomic( + emc->regs + EMC_AUTO_CAL_STATUS, val, + !(val & EMC_AUTO_CAL_STATUS_ACTIVE), 1, 300); + if (err) { + dev_err(emc->dev, + "failed to disable auto-cal: %d\n", + err); + return err; + } + + emc->vref_cal_toggle = true; + } + } + + /* program shadow registers */ + for (i = 0; i < ARRAY_SIZE(timing->data); i++) { + /* EMC_XM2CLKPADCTRL should be programmed separately */ + if (i != 73) + writel_relaxed(timing->data[i], + emc->regs + emc_timing_registers[i]); + } + + err = tegra_mc_write_emem_configuration(emc->mc, timing->rate); + if (err) + return err; + + /* DDR3: predict MRS long wait count */ + if (dram_type == DRAM_TYPE_DDR3 && dll_change == DLL_CHANGE_ON) { + u32 cnt = 512; + + if (emc->zcal_long) + cnt -= dram_num * 256; + + val = timing->data[82] & EMC_MRS_WAIT_CNT_SHORT_WAIT_MASK; + if (cnt < val) + cnt = val; + + val = timing->data[82] & ~EMC_MRS_WAIT_CNT_LONG_WAIT_MASK; + val |= (cnt << EMC_MRS_WAIT_CNT_LONG_WAIT_SHIFT) & + EMC_MRS_WAIT_CNT_LONG_WAIT_MASK; + + writel_relaxed(val, emc->regs + EMC_MRS_WAIT_CNT); + } + + /* disable interrupt since read access is prohibited after stalling */ + disable_irq(emc->irq); + + /* this read also completes the writes */ + val = readl_relaxed(emc->regs + EMC_SEL_DPD_CTRL); + + if (!(val & EMC_SEL_DPD_CTRL_QUSE_DPD_ENABLE) && schmitt_to_vref) { + u32 cur_mode, new_mode; + + cur_mode = fbio_cfg5 & EMC_CFG5_QUSE_MODE_MASK; + cur_mode >>= EMC_CFG5_QUSE_MODE_SHIFT; + + new_mode = timing->data[39] & EMC_CFG5_QUSE_MODE_MASK; + new_mode >>= EMC_CFG5_QUSE_MODE_SHIFT; + + if ((cur_mode != EMC_CFG5_QUSE_MODE_PULSE_INTERN && + cur_mode != EMC_CFG5_QUSE_MODE_INTERNAL_LPBK) || + (new_mode != EMC_CFG5_QUSE_MODE_PULSE_INTERN && + new_mode != EMC_CFG5_QUSE_MODE_INTERNAL_LPBK)) + qrst_used = true; + } + + /* flow control marker 1 */ + writel_relaxed(0x1, emc->regs + EMC_STALL_THEN_EXE_BEFORE_CLKCHANGE); + + /* enable periodic reset */ + if (qrst_used) { + writel_relaxed(emc_dbg | EMC_DBG_WRITE_MUX_ACTIVE, + emc->regs + EMC_DBG); + writel_relaxed(emc->emc_cfg | EMC_CFG_PERIODIC_QRST, + emc->regs + EMC_CFG); + writel_relaxed(emc_dbg, emc->regs + EMC_DBG); + } + + /* disable auto-refresh to save time after clock change */ + writel_relaxed(EMC_REFCTRL_DISABLE_ALL(dram_num), + emc->regs + EMC_REFCTRL); + + /* turn off DLL and enter self-refresh on DDR3 */ + if (dram_type == DRAM_TYPE_DDR3) { + if (dll_change == DLL_CHANGE_OFF) + writel_relaxed(timing->emc_mode_1, + emc->regs + EMC_EMRS); + + writel_relaxed(DRAM_BROADCAST(dram_num) | + EMC_SELF_REF_CMD_ENABLED, + emc->regs + EMC_SELF_REF); + } + + /* flow control marker 2 */ + writel_relaxed(0x1, emc->regs + EMC_STALL_THEN_EXE_AFTER_CLKCHANGE); + + /* enable write-active MUX, update unshadowed pad control */ + writel_relaxed(emc_dbg | EMC_DBG_WRITE_MUX_ACTIVE, emc->regs + EMC_DBG); + writel_relaxed(timing->data[73], emc->regs + EMC_XM2CLKPADCTRL); + + /* restore periodic QRST and disable write-active MUX */ + val = !!(emc->emc_cfg & EMC_CFG_PERIODIC_QRST); + if (qrst_used || timing->emc_cfg_periodic_qrst != val) { + if (timing->emc_cfg_periodic_qrst) + emc->emc_cfg |= EMC_CFG_PERIODIC_QRST; + else + emc->emc_cfg &= ~EMC_CFG_PERIODIC_QRST; + + writel_relaxed(emc->emc_cfg, emc->regs + EMC_CFG); + } + writel_relaxed(emc_dbg, emc->regs + EMC_DBG); + + /* exit self-refresh on DDR3 */ + if (dram_type == DRAM_TYPE_DDR3) + writel_relaxed(DRAM_BROADCAST(dram_num), + emc->regs + EMC_SELF_REF); + + /* set DRAM-mode registers */ + if (dram_type == DRAM_TYPE_DDR3) { + if (timing->emc_mode_1 != emc->emc_mode_1) + writel_relaxed(timing->emc_mode_1, + emc->regs + EMC_EMRS); + + if (timing->emc_mode_2 != emc->emc_mode_2) + writel_relaxed(timing->emc_mode_2, + emc->regs + EMC_EMRS); + + if (timing->emc_mode_reset != emc->emc_mode_reset || + dll_change == DLL_CHANGE_ON) { + val = timing->emc_mode_reset; + if (dll_change == DLL_CHANGE_ON) { + val |= EMC_MODE_SET_DLL_RESET; + val |= EMC_MODE_SET_LONG_CNT; + } else { + val &= ~EMC_MODE_SET_DLL_RESET; + } + writel_relaxed(val, emc->regs + EMC_MRS); + } + } else { + if (timing->emc_mode_2 != emc->emc_mode_2) + writel_relaxed(timing->emc_mode_2, + emc->regs + EMC_MRW); + + if (timing->emc_mode_1 != emc->emc_mode_1) + writel_relaxed(timing->emc_mode_1, + emc->regs + EMC_MRW); + } + + emc->emc_mode_1 = timing->emc_mode_1; + emc->emc_mode_2 = timing->emc_mode_2; + emc->emc_mode_reset = timing->emc_mode_reset; + + /* issue ZCAL command if turning ZCAL on */ + if (emc->zcal_long) { + writel_relaxed(EMC_ZQ_CAL_LONG_CMD_DEV0, + emc->regs + EMC_ZQ_CAL); + + if (dram_num > 1) + writel_relaxed(EMC_ZQ_CAL_LONG_CMD_DEV1, + emc->regs + EMC_ZQ_CAL); + } + + /* re-enable auto-refresh */ + writel_relaxed(EMC_REFCTRL_ENABLE_ALL(dram_num), + emc->regs + EMC_REFCTRL); + + /* flow control marker 3 */ + writel_relaxed(0x1, emc->regs + EMC_UNSTALL_RW_AFTER_CLKCHANGE); + + reinit_completion(&emc->clk_handshake_complete); + + /* interrupt can be re-enabled now */ + enable_irq(emc->irq); + + emc->bad_state = false; + emc->prepared = true; + + return 0; +} + +static int emc_complete_timing_change(struct tegra_emc *emc, + unsigned long rate) +{ + struct emc_timing *timing = emc_find_timing(emc, rate); + unsigned long timeout; + int ret; + + timeout = wait_for_completion_timeout(&emc->clk_handshake_complete, + msecs_to_jiffies(100)); + if (timeout == 0) { + dev_err(emc->dev, "emc-car handshake failed\n"); + emc->bad_state = true; + return -EIO; + } + + /* restore auto-calibration */ + if (emc->vref_cal_toggle) + writel_relaxed(timing->emc_auto_cal_interval, + emc->regs + EMC_AUTO_CAL_INTERVAL); + + /* restore dynamic self-refresh */ + if (timing->emc_cfg_dyn_self_ref) { + emc->emc_cfg |= EMC_CFG_DYN_SREF_ENABLE; + writel_relaxed(emc->emc_cfg, emc->regs + EMC_CFG); + } + + /* set number of clocks to wait after each ZQ command */ + if (emc->zcal_long) + writel_relaxed(timing->emc_zcal_cnt_long, + emc->regs + EMC_ZCAL_WAIT_CNT); + + udelay(2); + /* update restored timing */ + ret = emc_seq_update_timing(emc); + if (ret) + emc->bad_state = true; + + /* restore early ACK */ + mc_writel(emc->mc, emc->mc_override, MC_EMEM_ARB_OVERRIDE); + + emc->prepared = false; + + return ret; +} + +static int emc_unprepare_timing_change(struct tegra_emc *emc, + unsigned long rate) +{ + if (emc->prepared && !emc->bad_state) { + /* shouldn't ever happen in practice */ + dev_err(emc->dev, "timing configuration can't be reverted\n"); + emc->bad_state = true; + } + + return 0; +} + +static int emc_clk_change_notify(struct notifier_block *nb, + unsigned long msg, void *data) +{ + struct tegra_emc *emc = container_of(nb, struct tegra_emc, clk_nb); + struct clk_notifier_data *cnd = data; + int err; + + switch (msg) { + case PRE_RATE_CHANGE: + err = emc_prepare_timing_change(emc, cnd->new_rate); + break; + + case ABORT_RATE_CHANGE: + err = emc_unprepare_timing_change(emc, cnd->old_rate); + break; + + case POST_RATE_CHANGE: + err = emc_complete_timing_change(emc, cnd->new_rate); + break; + + default: + return NOTIFY_DONE; + } + + return notifier_from_errno(err); +} + +static int load_one_timing_from_dt(struct tegra_emc *emc, + struct emc_timing *timing, + struct device_node *node) +{ + u32 value; + int err; + + err = of_property_read_u32(node, "clock-frequency", &value); + if (err) { + dev_err(emc->dev, "timing %pOF: failed to read rate: %d\n", + node, err); + return err; + } + + timing->rate = value; + + err = of_property_read_u32_array(node, "nvidia,emc-configuration", + timing->data, + ARRAY_SIZE(emc_timing_registers)); + if (err) { + dev_err(emc->dev, + "timing %pOF: failed to read emc timing data: %d\n", + node, err); + return err; + } + +#define EMC_READ_BOOL(prop, dtprop) \ + timing->prop = of_property_read_bool(node, dtprop); + +#define EMC_READ_U32(prop, dtprop) \ + err = of_property_read_u32(node, dtprop, &timing->prop); \ + if (err) { \ + dev_err(emc->dev, \ + "timing %pOFn: failed to read " #prop ": %d\n", \ + node, err); \ + return err; \ + } + + EMC_READ_U32(emc_auto_cal_interval, "nvidia,emc-auto-cal-interval") + EMC_READ_U32(emc_mode_1, "nvidia,emc-mode-1") + EMC_READ_U32(emc_mode_2, "nvidia,emc-mode-2") + EMC_READ_U32(emc_mode_reset, "nvidia,emc-mode-reset") + EMC_READ_U32(emc_zcal_cnt_long, "nvidia,emc-zcal-cnt-long") + EMC_READ_BOOL(emc_cfg_dyn_self_ref, "nvidia,emc-cfg-dyn-self-ref") + EMC_READ_BOOL(emc_cfg_periodic_qrst, "nvidia,emc-cfg-periodic-qrst") + +#undef EMC_READ_U32 +#undef EMC_READ_BOOL + + dev_dbg(emc->dev, "%s: %pOF: rate %lu\n", __func__, node, timing->rate); + + return 0; +} + +static int cmp_timings(const void *_a, const void *_b) +{ + const struct emc_timing *a = _a; + const struct emc_timing *b = _b; + + if (a->rate < b->rate) + return -1; + + if (a->rate > b->rate) + return 1; + + return 0; +} + +static int emc_check_mc_timings(struct tegra_emc *emc) +{ + struct tegra_mc *mc = emc->mc; + unsigned int i; + + if (emc->num_timings != mc->num_timings) { + dev_err(emc->dev, "emc/mc timings number mismatch: %u %u\n", + emc->num_timings, mc->num_timings); + return -EINVAL; + } + + for (i = 0; i < mc->num_timings; i++) { + if (emc->timings[i].rate != mc->timings[i].rate) { + dev_err(emc->dev, + "emc/mc timing rate mismatch: %lu %lu\n", + emc->timings[i].rate, mc->timings[i].rate); + return -EINVAL; + } + } + + return 0; +} + +static int emc_load_timings_from_dt(struct tegra_emc *emc, + struct device_node *node) +{ + struct device_node *child; + struct emc_timing *timing; + int child_count; + int err; + + child_count = of_get_child_count(node); + if (!child_count) { + dev_err(emc->dev, "no memory timings in: %pOF\n", node); + return -EINVAL; + } + + emc->timings = devm_kcalloc(emc->dev, child_count, sizeof(*timing), + GFP_KERNEL); + if (!emc->timings) + return -ENOMEM; + + emc->num_timings = child_count; + timing = emc->timings; + + for_each_child_of_node(node, child) { + err = load_one_timing_from_dt(emc, timing++, child); + if (err) { + of_node_put(child); + return err; + } + } + + sort(emc->timings, emc->num_timings, sizeof(*timing), cmp_timings, + NULL); + + err = emc_check_mc_timings(emc); + if (err) + return err; + + dev_info(emc->dev, + "got %u timings for RAM code %u (min %luMHz max %luMHz)\n", + emc->num_timings, + tegra_read_ram_code(), + emc->timings[0].rate / 1000000, + emc->timings[emc->num_timings - 1].rate / 1000000); + + return 0; +} + +static struct device_node *emc_find_node_by_ram_code(struct device *dev) +{ + struct device_node *np; + u32 value, ram_code; + int err; + + ram_code = tegra_read_ram_code(); + + for_each_child_of_node(dev->of_node, np) { + err = of_property_read_u32(np, "nvidia,ram-code", &value); + if (err || value != ram_code) + continue; + + return np; + } + + dev_err(dev, "no memory timings for RAM code %u found in device-tree\n", + ram_code); + + return NULL; +} + +static int emc_setup_hw(struct tegra_emc *emc) +{ + u32 intmask = EMC_REFRESH_OVERFLOW_INT | EMC_CLKCHANGE_COMPLETE_INT; + u32 fbio_cfg5, emc_cfg, emc_dbg; + enum emc_dram_type dram_type; + + fbio_cfg5 = readl_relaxed(emc->regs + EMC_FBIO_CFG5); + dram_type = fbio_cfg5 & EMC_FBIO_CFG5_DRAM_TYPE_MASK; + + emc_cfg = readl_relaxed(emc->regs + EMC_CFG_2); + + /* enable EMC and CAR to handshake on PLL divider/source changes */ + emc_cfg |= EMC_CLKCHANGE_REQ_ENABLE; + + /* configure clock change mode accordingly to DRAM type */ + switch (dram_type) { + case DRAM_TYPE_LPDDR2: + emc_cfg |= EMC_CLKCHANGE_PD_ENABLE; + emc_cfg &= ~EMC_CLKCHANGE_SR_ENABLE; + break; + + default: + emc_cfg &= ~EMC_CLKCHANGE_SR_ENABLE; + emc_cfg &= ~EMC_CLKCHANGE_PD_ENABLE; + break; + } + + writel_relaxed(emc_cfg, emc->regs + EMC_CFG_2); + + /* initialize interrupt */ + writel_relaxed(intmask, emc->regs + EMC_INTMASK); + writel_relaxed(0xffffffff, emc->regs + EMC_INTSTATUS); + + /* ensure that unwanted debug features are disabled */ + emc_dbg = readl_relaxed(emc->regs + EMC_DBG); + emc_dbg |= EMC_DBG_CFG_PRIORITY; + emc_dbg &= ~EMC_DBG_READ_MUX_ASSEMBLY; + emc_dbg &= ~EMC_DBG_WRITE_MUX_ACTIVE; + emc_dbg &= ~EMC_DBG_FORCE_UPDATE; + writel_relaxed(emc_dbg, emc->regs + EMC_DBG); + + return 0; +} + +static long emc_round_rate(unsigned long rate, + unsigned long min_rate, + unsigned long max_rate, + void *arg) +{ + struct emc_timing *timing = NULL; + struct tegra_emc *emc = arg; + unsigned int i; + + min_rate = min(min_rate, emc->timings[emc->num_timings - 1].rate); + + for (i = 0; i < emc->num_timings; i++) { + if (emc->timings[i].rate < rate && i != emc->num_timings - 1) + continue; + + if (emc->timings[i].rate > max_rate) { + i = max(i, 1u) - 1; + + if (emc->timings[i].rate < min_rate) + break; + } + + if (emc->timings[i].rate < min_rate) + continue; + + timing = &emc->timings[i]; + break; + } + + if (!timing) { + dev_err(emc->dev, "no timing for rate %lu min %lu max %lu\n", + rate, min_rate, max_rate); + return -EINVAL; + } + + return timing->rate; +} + +static int tegra_emc_probe(struct platform_device *pdev) +{ + struct platform_device *mc; + struct device_node *np; + struct tegra_emc *emc; + int err; + + if (of_get_child_count(pdev->dev.of_node) == 0) { + dev_info(&pdev->dev, + "device-tree node doesn't have memory timings\n"); + return 0; + } + + np = of_parse_phandle(pdev->dev.of_node, "nvidia,memory-controller", 0); + if (!np) { + dev_err(&pdev->dev, "could not get memory controller node\n"); + return -ENOENT; + } + + mc = of_find_device_by_node(np); + of_node_put(np); + if (!mc) + return -ENOENT; + + np = emc_find_node_by_ram_code(&pdev->dev); + if (!np) + return -EINVAL; + + emc = devm_kzalloc(&pdev->dev, sizeof(*emc), GFP_KERNEL); + if (!emc) { + of_node_put(np); + return -ENOMEM; + } + + emc->mc = platform_get_drvdata(mc); + if (!emc->mc) + return -EPROBE_DEFER; + + init_completion(&emc->clk_handshake_complete); + emc->clk_nb.notifier_call = emc_clk_change_notify; + emc->dev = &pdev->dev; + + err = emc_load_timings_from_dt(emc, np); + of_node_put(np); + if (err) + return err; + + emc->regs = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(emc->regs)) + return PTR_ERR(emc->regs); + + err = emc_setup_hw(emc); + if (err) + return err; + + err = platform_get_irq(pdev, 0); + if (err < 0) { + dev_err(&pdev->dev, "interrupt not specified: %d\n", err); + return err; + } + emc->irq = err; + + err = devm_request_irq(&pdev->dev, emc->irq, tegra_emc_isr, 0, + dev_name(&pdev->dev), emc); + if (err) { + dev_err(&pdev->dev, "failed to request irq: %d\n", err); + return err; + } + + tegra20_clk_set_emc_round_callback(emc_round_rate, emc); + + emc->clk = devm_clk_get(&pdev->dev, "emc"); + if (IS_ERR(emc->clk)) { + err = PTR_ERR(emc->clk); + dev_err(&pdev->dev, "failed to get emc clock: %d\n", err); + goto unset_cb; + } + + err = clk_notifier_register(emc->clk, &emc->clk_nb); + if (err) { + dev_err(&pdev->dev, "failed to register clk notifier: %d\n", + err); + goto unset_cb; + } + + platform_set_drvdata(pdev, emc); + + return 0; + +unset_cb: + tegra20_clk_set_emc_round_callback(NULL, NULL); + + return err; +} + +static int tegra_emc_suspend(struct device *dev) +{ + struct tegra_emc *emc = dev_get_drvdata(dev); + + /* + * Suspending in a bad state will hang machine. The "prepared" var + * shall be always false here unless it's a kernel bug that caused + * suspending in a wrong order. + */ + if (WARN_ON(emc->prepared) || emc->bad_state) + return -EINVAL; + + emc->bad_state = true; + + return 0; +} + +static int tegra_emc_resume(struct device *dev) +{ + struct tegra_emc *emc = dev_get_drvdata(dev); + + emc_setup_hw(emc); + emc->bad_state = false; + + return 0; +} + +static const struct dev_pm_ops tegra_emc_pm_ops = { + .suspend = tegra_emc_suspend, + .resume = tegra_emc_resume, +}; + +static const struct of_device_id tegra_emc_of_match[] = { + { .compatible = "nvidia,tegra30-emc", }, + {}, +}; + +static struct platform_driver tegra_emc_driver = { + .probe = tegra_emc_probe, + .driver = { + .name = "tegra30-emc", + .of_match_table = tegra_emc_of_match, + .pm = &tegra_emc_pm_ops, + .suppress_bind_attrs = true, + }, +}; + +static int __init tegra_emc_init(void) +{ + return platform_driver_register(&tegra_emc_driver); +} +subsys_initcall(tegra_emc_init); diff --git a/drivers/memory/tegra/tegra30.c b/drivers/memory/tegra/tegra30.c index 8947bee6d032..e9d47e3d3b59 100644 --- a/drivers/memory/tegra/tegra30.c +++ b/drivers/memory/tegra/tegra30.c @@ -10,6 +10,46 @@ #include "mc.h" +#define MC_EMEM_ARB_CFG 0x90 +#define MC_EMEM_ARB_OUTSTANDING_REQ 0x94 +#define MC_EMEM_ARB_TIMING_RCD 0x98 +#define MC_EMEM_ARB_TIMING_RP 0x9c +#define MC_EMEM_ARB_TIMING_RC 0xa0 +#define MC_EMEM_ARB_TIMING_RAS 0xa4 +#define MC_EMEM_ARB_TIMING_FAW 0xa8 +#define MC_EMEM_ARB_TIMING_RRD 0xac +#define MC_EMEM_ARB_TIMING_RAP2PRE 0xb0 +#define MC_EMEM_ARB_TIMING_WAP2PRE 0xb4 +#define MC_EMEM_ARB_TIMING_R2R 0xb8 +#define MC_EMEM_ARB_TIMING_W2W 0xbc +#define MC_EMEM_ARB_TIMING_R2W 0xc0 +#define MC_EMEM_ARB_TIMING_W2R 0xc4 +#define MC_EMEM_ARB_DA_TURNS 0xd0 +#define MC_EMEM_ARB_DA_COVERS 0xd4 +#define MC_EMEM_ARB_MISC0 0xd8 +#define MC_EMEM_ARB_RING1_THROTTLE 0xe0 + +static const unsigned long tegra30_mc_emem_regs[] = { + MC_EMEM_ARB_CFG, + MC_EMEM_ARB_OUTSTANDING_REQ, + MC_EMEM_ARB_TIMING_RCD, + MC_EMEM_ARB_TIMING_RP, + MC_EMEM_ARB_TIMING_RC, + MC_EMEM_ARB_TIMING_RAS, + MC_EMEM_ARB_TIMING_FAW, + MC_EMEM_ARB_TIMING_RRD, + MC_EMEM_ARB_TIMING_RAP2PRE, + MC_EMEM_ARB_TIMING_WAP2PRE, + MC_EMEM_ARB_TIMING_R2R, + MC_EMEM_ARB_TIMING_W2W, + MC_EMEM_ARB_TIMING_R2W, + MC_EMEM_ARB_TIMING_W2R, + MC_EMEM_ARB_DA_TURNS, + MC_EMEM_ARB_DA_COVERS, + MC_EMEM_ARB_MISC0, + MC_EMEM_ARB_RING1_THROTTLE, +}; + static const struct tegra_mc_client tegra30_mc_clients[] = { { .id = 0x00, @@ -997,6 +1037,8 @@ const struct tegra_mc_soc tegra30_mc_soc = { .atom_size = 16, .client_id_mask = 0x7f, .smmu = &tegra30_smmu_soc, + .emem_regs = tegra30_mc_emem_regs, + .num_emem_regs = ARRAY_SIZE(tegra30_mc_emem_regs), .intmask = MC_INT_INVALID_SMMU_PAGE | MC_INT_SECURITY_VIOLATION | MC_INT_DECERR_EMEM, .reset_ops = &tegra_mc_reset_ops_common, diff --git a/include/soc/tegra/mc.h b/include/soc/tegra/mc.h index 16e2c2fb5f6c..1238e35653d1 100644 --- a/include/soc/tegra/mc.h +++ b/include/soc/tegra/mc.h @@ -181,7 +181,7 @@ struct tegra_mc { spinlock_t lock; }; -void tegra_mc_write_emem_configuration(struct tegra_mc *mc, unsigned long rate); +int tegra_mc_write_emem_configuration(struct tegra_mc *mc, unsigned long rate); unsigned int tegra_mc_get_emem_device_count(struct tegra_mc *mc); #endif /* __SOC_TEGRA_MC_H__ */ -- cgit v1.2.3 From 6c3a44ed3c553c324845744f30bcd1d3b07d61fd Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Sun, 10 Nov 2019 09:27:44 -0800 Subject: iommu/vt-d: Turn off translations at shutdown The intel-iommu driver assumes that the iommu state is cleaned up at the start of the new kernel. But, when we try to kexec boot something other than the Linux kernel, the cleanup cannot be relied upon. Hence, cleanup before we go down for reboot. Keeping the cleanup at initialization also, in case BIOS leaves the IOMMU enabled. I considered turning off iommu only during kexec reboot, but a clean shutdown seems always a good idea. But if someone wants to make it conditional, such as VMM live update, we can do that. There doesn't seem to be such a condition at this time. Tested that before, the info message 'DMAR: Translation was enabled for but we are not in kdump mode' would be reported for each iommu. The message will not appear when the DMA-remapping is not enabled on entry to the kernel. Signed-off-by: Deepa Dinamani Acked-by: Lu Baolu Signed-off-by: Joerg Roedel --- drivers/iommu/dmar.c | 5 ++++- drivers/iommu/intel-iommu.c | 20 ++++++++++++++++++++ include/linux/dmar.h | 2 ++ 3 files changed, 26 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c index eecd6a421667..3acfa6a25fa2 100644 --- a/drivers/iommu/dmar.c +++ b/drivers/iommu/dmar.c @@ -895,8 +895,11 @@ int __init detect_intel_iommu(void) } #ifdef CONFIG_X86 - if (!ret) + if (!ret) { x86_init.iommu.iommu_init = intel_iommu_init; + x86_platform.iommu_shutdown = intel_iommu_shutdown; + } + #endif if (dmar_tbl) { diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index f168cd8ee570..10ee8fa4b1b8 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -4762,6 +4762,26 @@ static void intel_disable_iommus(void) iommu_disable_translation(iommu); } +void intel_iommu_shutdown(void) +{ + struct dmar_drhd_unit *drhd; + struct intel_iommu *iommu = NULL; + + if (no_iommu || dmar_disabled) + return; + + down_write(&dmar_global_lock); + + /* Disable PMRs explicitly here. */ + for_each_iommu(iommu, drhd) + iommu_disable_protect_mem_regions(iommu); + + /* Make sure the IOMMUs are switched off */ + intel_disable_iommus(); + + up_write(&dmar_global_lock); +} + static inline struct intel_iommu *dev_to_intel_iommu(struct device *dev) { struct iommu_device *iommu_dev = dev_to_iommu_device(dev); diff --git a/include/linux/dmar.h b/include/linux/dmar.h index a7cf3599d9a1..f64ca27dc210 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -129,6 +129,7 @@ static inline int dmar_res_noop(struct acpi_dmar_header *hdr, void *arg) #ifdef CONFIG_INTEL_IOMMU extern int iommu_detected, no_iommu; extern int intel_iommu_init(void); +extern void intel_iommu_shutdown(void); extern int dmar_parse_one_rmrr(struct acpi_dmar_header *header, void *arg); extern int dmar_parse_one_atsr(struct acpi_dmar_header *header, void *arg); extern int dmar_check_one_atsr(struct acpi_dmar_header *hdr, void *arg); @@ -137,6 +138,7 @@ extern int dmar_iommu_hotplug(struct dmar_drhd_unit *dmaru, bool insert); extern int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info); #else /* !CONFIG_INTEL_IOMMU: */ static inline int intel_iommu_init(void) { return -ENODEV; } +static inline void intel_iommu_shutdown(void) { } #define dmar_parse_one_rmrr dmar_res_noop #define dmar_parse_one_atsr dmar_res_noop -- cgit v1.2.3 From 3bbc53f4ae1686b501d92d4a5fd400f4958c8a98 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Thu, 7 Nov 2019 10:19:24 +0100 Subject: hrtimer: Remove the comment about not used HRTIMER_SOFTIRQ The softirq `HRTIMER_SOFTIRQ' was not used since commit c6eb3f70d448 ("hrtimer: Get rid of hrtimer softirq"). But it got used again, beginning with commit 5da70160462e ("hrtimer: Implement support for softirq based hrtimers"), which did not remove the comment. Remove it now. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Link: https://lkml.kernel.org/r/20191107091924.13410-1-bigeasy@linutronix.de --- include/linux/interrupt.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 89fc59dab57d..963c3c695784 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -520,8 +520,7 @@ enum IRQ_POLL_SOFTIRQ, TASKLET_SOFTIRQ, SCHED_SOFTIRQ, - HRTIMER_SOFTIRQ, /* Unused, but kept as tools rely on the - numbering. Sigh! */ + HRTIMER_SOFTIRQ, RCU_SOFTIRQ, /* Preferable RCU should always be the last softirq */ NR_SOFTIRQS -- cgit v1.2.3 From d05a0201969045f4c488f7cf1d024089949a68b6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 12 Nov 2019 16:34:22 +0100 Subject: sunrpc: remove __KERNEL__ ifdefs Remove the __KERNEL__ ifdefs from the non-UAPI sunrpc headers, as those can't be included from user space programs. Signed-off-by: Christoph Hellwig Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/auth.h | 3 --- include/linux/sunrpc/auth_gss.h | 2 -- include/linux/sunrpc/clnt.h | 3 --- include/linux/sunrpc/gss_api.h | 2 -- include/linux/sunrpc/gss_err.h | 3 --- include/linux/sunrpc/msg_prot.h | 3 --- include/linux/sunrpc/rpc_pipe_fs.h | 3 --- include/linux/sunrpc/svcauth.h | 4 ---- include/linux/sunrpc/svcauth_gss.h | 2 -- include/linux/sunrpc/xdr.h | 3 --- include/linux/sunrpc/xprt.h | 4 ---- include/linux/sunrpc/xprtsock.h | 4 ---- 12 files changed, 36 deletions(-) (limited to 'include') diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index 5f9076fdb090..e9ec742796e7 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -10,8 +10,6 @@ #ifndef _LINUX_SUNRPC_AUTH_H #define _LINUX_SUNRPC_AUTH_H -#ifdef __KERNEL__ - #include #include #include @@ -194,5 +192,4 @@ struct rpc_cred *get_rpccred(struct rpc_cred *cred) return NULL; } -#endif /* __KERNEL__ */ #endif /* _LINUX_SUNRPC_AUTH_H */ diff --git a/include/linux/sunrpc/auth_gss.h b/include/linux/sunrpc/auth_gss.h index 30427b729070..43e481aa347a 100644 --- a/include/linux/sunrpc/auth_gss.h +++ b/include/linux/sunrpc/auth_gss.h @@ -13,7 +13,6 @@ #ifndef _LINUX_SUNRPC_AUTH_GSS_H #define _LINUX_SUNRPC_AUTH_GSS_H -#ifdef __KERNEL__ #include #include #include @@ -90,6 +89,5 @@ struct gss_cred { unsigned long gc_upcall_timestamp; }; -#endif /* __KERNEL__ */ #endif /* _LINUX_SUNRPC_AUTH_GSS_H */ diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index abc63bd1be2b..64bffcb7142b 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -109,8 +109,6 @@ struct rpc_procinfo { const char * p_name; /* name of procedure */ }; -#ifdef __KERNEL__ - struct rpc_create_args { struct net *net; int protocol; @@ -237,5 +235,4 @@ static inline int rpc_reply_expected(struct rpc_task *task) (task->tk_msg.rpc_proc->p_decode != NULL); } -#endif /* __KERNEL__ */ #endif /* _LINUX_SUNRPC_CLNT_H */ diff --git a/include/linux/sunrpc/gss_api.h b/include/linux/sunrpc/gss_api.h index 5ac5db4d295f..bd691e08be3b 100644 --- a/include/linux/sunrpc/gss_api.h +++ b/include/linux/sunrpc/gss_api.h @@ -13,7 +13,6 @@ #ifndef _LINUX_SUNRPC_GSS_API_H #define _LINUX_SUNRPC_GSS_API_H -#ifdef __KERNEL__ #include #include #include @@ -160,6 +159,5 @@ struct gss_api_mech * gss_mech_get(struct gss_api_mech *); * corresponding call to gss_mech_put. */ void gss_mech_put(struct gss_api_mech *); -#endif /* __KERNEL__ */ #endif /* _LINUX_SUNRPC_GSS_API_H */ diff --git a/include/linux/sunrpc/gss_err.h b/include/linux/sunrpc/gss_err.h index a6807867bd21..b73c329c83f2 100644 --- a/include/linux/sunrpc/gss_err.h +++ b/include/linux/sunrpc/gss_err.h @@ -34,8 +34,6 @@ #ifndef _LINUX_SUNRPC_GSS_ERR_H #define _LINUX_SUNRPC_GSS_ERR_H -#ifdef __KERNEL__ - typedef unsigned int OM_uint32; /* @@ -163,5 +161,4 @@ typedef unsigned int OM_uint32; /* XXXX This is a necessary evil until the spec is fixed */ #define GSS_S_CRED_UNAVAIL GSS_S_FAILURE -#endif /* __KERNEL__ */ #endif /* __LINUX_SUNRPC_GSS_ERR_H */ diff --git a/include/linux/sunrpc/msg_prot.h b/include/linux/sunrpc/msg_prot.h index 4722b28ec36a..bea40d9f03a1 100644 --- a/include/linux/sunrpc/msg_prot.h +++ b/include/linux/sunrpc/msg_prot.h @@ -8,8 +8,6 @@ #ifndef _LINUX_SUNRPC_MSGPROT_H_ #define _LINUX_SUNRPC_MSGPROT_H_ -#ifdef __KERNEL__ /* user programs should get these from the rpc header files */ - #define RPC_VERSION 2 /* size of an XDR encoding unit in bytes, i.e. 32bit */ @@ -217,5 +215,4 @@ typedef __be32 rpc_fraghdr; /* Assume INET6_ADDRSTRLEN will always be larger than INET_ADDRSTRLEN... */ #define RPCBIND_MAXUADDRLEN RPCBIND_MAXUADDR6LEN -#endif /* __KERNEL__ */ #endif /* _LINUX_SUNRPC_MSGPROT_H_ */ diff --git a/include/linux/sunrpc/rpc_pipe_fs.h b/include/linux/sunrpc/rpc_pipe_fs.h index e90b9bd99ded..cd188a527d16 100644 --- a/include/linux/sunrpc/rpc_pipe_fs.h +++ b/include/linux/sunrpc/rpc_pipe_fs.h @@ -2,8 +2,6 @@ #ifndef _LINUX_SUNRPC_RPC_PIPE_FS_H #define _LINUX_SUNRPC_RPC_PIPE_FS_H -#ifdef __KERNEL__ - #include struct rpc_pipe_dir_head { @@ -133,4 +131,3 @@ extern void unregister_rpc_pipefs(void); extern bool gssd_running(struct net *net); #endif -#endif diff --git a/include/linux/sunrpc/svcauth.h b/include/linux/sunrpc/svcauth.h index 3e53a6e2ada7..b0003866a249 100644 --- a/include/linux/sunrpc/svcauth.h +++ b/include/linux/sunrpc/svcauth.h @@ -10,8 +10,6 @@ #ifndef _LINUX_SUNRPC_SVCAUTH_H_ #define _LINUX_SUNRPC_SVCAUTH_H_ -#ifdef __KERNEL__ - #include #include #include @@ -185,6 +183,4 @@ static inline unsigned long hash_mem(char const *buf, int length, int bits) return full_name_hash(NULL, buf, length) >> (32 - bits); } -#endif /* __KERNEL__ */ - #endif /* _LINUX_SUNRPC_SVCAUTH_H_ */ diff --git a/include/linux/sunrpc/svcauth_gss.h b/include/linux/sunrpc/svcauth_gss.h index a4528b26c8aa..ca39a388dc22 100644 --- a/include/linux/sunrpc/svcauth_gss.h +++ b/include/linux/sunrpc/svcauth_gss.h @@ -9,7 +9,6 @@ #ifndef _LINUX_SUNRPC_SVCAUTH_GSS_H #define _LINUX_SUNRPC_SVCAUTH_GSS_H -#ifdef __KERNEL__ #include #include #include @@ -24,5 +23,4 @@ void gss_svc_shutdown_net(struct net *net); int svcauth_gss_register_pseudoflavor(u32 pseudoflavor, char * name); u32 svcauth_gss_flavor(struct auth_domain *dom); -#endif /* __KERNEL__ */ #endif /* _LINUX_SUNRPC_SVCAUTH_GSS_H */ diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index f33e5013bdfb..b41f34977995 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -11,8 +11,6 @@ #ifndef _SUNRPC_XDR_H_ #define _SUNRPC_XDR_H_ -#ifdef __KERNEL__ - #include #include #include @@ -552,6 +550,5 @@ xdr_stream_decode_uint32_array(struct xdr_stream *xdr, *array = be32_to_cpup(p); return retval; } -#endif /* __KERNEL__ */ #endif /* _SUNRPC_XDR_H_ */ diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index d783e15ba898..874205227778 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -19,8 +19,6 @@ #include #include -#ifdef __KERNEL__ - #define RPC_MIN_SLOT_TABLE (2U) #define RPC_DEF_SLOT_TABLE (16U) #define RPC_MAX_SLOT_TABLE_LIMIT (65536U) @@ -505,6 +503,4 @@ static inline void xprt_inject_disconnect(struct rpc_xprt *xprt) } #endif -#endif /* __KERNEL__*/ - #endif /* _LINUX_SUNRPC_XPRT_H */ diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h index 7638dbe7bc50..30acd67d1627 100644 --- a/include/linux/sunrpc/xprtsock.h +++ b/include/linux/sunrpc/xprtsock.h @@ -8,8 +8,6 @@ #ifndef _LINUX_SUNRPC_XPRTSOCK_H #define _LINUX_SUNRPC_XPRTSOCK_H -#ifdef __KERNEL__ - int init_socket_xprt(void); void cleanup_socket_xprt(void); @@ -90,6 +88,4 @@ struct sock_xprt { #define XPRT_SOCK_WAKE_PENDING (6) #define XPRT_SOCK_WAKE_DISCONNECT (7) -#endif /* __KERNEL__ */ - #endif /* _LINUX_SUNRPC_XPRTSOCK_H */ -- cgit v1.2.3 From fb7dd0a1ba8690527c2394c6c55f909aa87d8f44 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 12 Nov 2019 16:34:23 +0100 Subject: lockd: remove __KERNEL__ ifdefs Remove the __KERNEL__ ifdefs from the non-UAPI sunrpc headers, as those can't be included from user space programs. Signed-off-by: Christoph Hellwig Signed-off-by: J. Bruce Fields --- include/linux/lockd/debug.h | 4 ---- include/linux/lockd/lockd.h | 4 ---- 2 files changed, 8 deletions(-) (limited to 'include') diff --git a/include/linux/lockd/debug.h b/include/linux/lockd/debug.h index e536c579827f..eede2ab5246f 100644 --- a/include/linux/lockd/debug.h +++ b/include/linux/lockd/debug.h @@ -10,8 +10,6 @@ #ifndef LINUX_LOCKD_DEBUG_H #define LINUX_LOCKD_DEBUG_H -#ifdef __KERNEL__ - #include /* @@ -25,8 +23,6 @@ # define ifdebug(flag) if (0) #endif -#endif /* __KERNEL__ */ - /* * Debug flags */ diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index d294dde9e546..666f5f310a04 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -10,8 +10,6 @@ #ifndef LINUX_LOCKD_LOCKD_H #define LINUX_LOCKD_LOCKD_H -#ifdef __KERNEL__ - #include #include #include @@ -373,6 +371,4 @@ static inline int nlm_compare_locks(const struct file_lock *fl1, extern const struct lock_manager_operations nlmsvc_lock_operations; -#endif /* __KERNEL__ */ - #endif /* LINUX_LOCKD_LOCKD_H */ -- cgit v1.2.3 From 35c3363363ac7c8877b4984cdd8a2af377a4e92e Mon Sep 17 00:00:00 2001 From: Finn Thain Date: Sat, 2 Nov 2019 12:06:54 +1100 Subject: scsi: core: Clean up SG_NONE Remove SG_NONE and a related misleading comment. Update documentation. This patch does not affect behaviour as zero initialization is redundant. Cc: Jonathan Corbet Cc: Bartlomiej Zolnierkiewicz Cc: Jens Axboe Cc: Viresh Kumar Cc: Oliver Neukum Cc: Alan Stern Cc: Greg Kroah-Hartman Cc: usb-storage@lists.one-eyed-alien.net Link: https://lore.kernel.org/r/b4779b7a6563f6bd8d259ee457871c1c463c420e.1572656814.git.fthain@telegraphics.com.au Signed-off-by: Finn Thain Signed-off-by: Martin K. Petersen --- Documentation/scsi/scsi_mid_low_api.txt | 3 ++- drivers/ata/pata_arasan_cf.c | 1 - drivers/scsi/atp870u.c | 2 +- drivers/usb/storage/uas.c | 1 - include/scsi/scsi_host.h | 13 ------------- 5 files changed, 3 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/Documentation/scsi/scsi_mid_low_api.txt b/Documentation/scsi/scsi_mid_low_api.txt index c1dd4939f4ae..2a4be1c3e6db 100644 --- a/Documentation/scsi/scsi_mid_low_api.txt +++ b/Documentation/scsi/scsi_mid_low_api.txt @@ -1084,7 +1084,8 @@ of interest: commands to the adapter. this_id - scsi id of host (scsi initiator) or -1 if not known sg_tablesize - maximum scatter gather elements allowed by host. - 0 implies scatter gather not supported by host + Set this to SG_ALL or less to avoid chained SG lists. + Must be at least 1. max_sectors - maximum number of sectors (usually 512 bytes) allowed in a single SCSI command. The default value of 0 leads to a setting of SCSI_DEFAULT_MAX_SECTORS (defined in diff --git a/drivers/ata/pata_arasan_cf.c b/drivers/ata/pata_arasan_cf.c index ebecab8c3f36..135173c8d138 100644 --- a/drivers/ata/pata_arasan_cf.c +++ b/drivers/ata/pata_arasan_cf.c @@ -219,7 +219,6 @@ struct arasan_cf_dev { static struct scsi_host_template arasan_cf_sht = { ATA_BASE_SHT(DRIVER_NAME), - .sg_tablesize = SG_NONE, .dma_boundary = 0xFFFFFFFFUL, }; diff --git a/drivers/scsi/atp870u.c b/drivers/scsi/atp870u.c index e41f0bbdc9fd..c6a752309dda 100644 --- a/drivers/scsi/atp870u.c +++ b/drivers/scsi/atp870u.c @@ -1680,7 +1680,7 @@ static struct scsi_host_template atp870u_template = { .bios_param = atp870u_biosparam /* biosparm */, .can_queue = qcnt /* can_queue */, .this_id = 7 /* SCSI ID */, - .sg_tablesize = ATP870U_SCATTER /*SG_ALL*/ /*SG_NONE*/, + .sg_tablesize = ATP870U_SCATTER /*SG_ALL*/, .max_sectors = ATP870U_MAX_SECTORS, }; diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c index bf80d6f81f58..fd9c0d2c111f 100644 --- a/drivers/usb/storage/uas.c +++ b/drivers/usb/storage/uas.c @@ -879,7 +879,6 @@ static struct scsi_host_template uas_host_template = { .eh_abort_handler = uas_eh_abort_handler, .eh_device_reset_handler = uas_eh_device_reset_handler, .this_id = -1, - .sg_tablesize = SG_NONE, .skip_settle_delay = 1, .dma_boundary = PAGE_SIZE - 1, }; diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h index fccdf84ec7e2..f577647bf5f2 100644 --- a/include/scsi/scsi_host.h +++ b/include/scsi/scsi_host.h @@ -23,19 +23,6 @@ struct scsi_host_cmd_pool; struct scsi_transport_template; -/* - * The various choices mean: - * NONE: Self evident. Host adapter is not capable of scatter-gather. - * ALL: Means that the host adapter module can do scatter-gather, - * and that there is no limit to the size of the table to which - * we scatter/gather data. The value we set here is the maximum - * single element sglist. To use chained sglists, the adapter - * has to set a value beyond ALL (and correctly use the chain - * handling API. - * Anything else: Indicates the maximum number of chains that can be - * used in one scatter-gather request. - */ -#define SG_NONE 0 #define SG_ALL SG_CHUNK_SIZE #define MODE_UNKNOWN 0x00 -- cgit v1.2.3 From cf25e24db61cc9df42c47485a2ec2bff4e9a3692 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 7 Nov 2019 11:07:58 +0100 Subject: time: Rename tsk->real_start_time to ->start_boottime Since it stores CLOCK_BOOTTIME, not, as the name suggests, CLOCK_REALTIME, let's rename ->real_start_time to ->start_bootime. Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- fs/exec.c | 2 +- fs/proc/array.c | 2 +- include/linux/sched.h | 2 +- kernel/fork.c | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/fs/exec.c b/fs/exec.c index 555e93c7dec8..f4d0f3acf861 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1132,7 +1132,7 @@ static int de_thread(struct task_struct *tsk) * also take its birthdate (always earlier than our own). */ tsk->start_time = leader->start_time; - tsk->real_start_time = leader->real_start_time; + tsk->start_boottime = leader->start_boottime; BUG_ON(!same_thread_group(leader, tsk)); BUG_ON(has_group_leader_pid(tsk)); diff --git a/fs/proc/array.c b/fs/proc/array.c index 46dcb6f0eccf..5efaf3708ec6 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -533,7 +533,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, nice = task_nice(task); /* convert nsec -> ticks */ - start_time = nsec_to_clock_t(task->real_start_time); + start_time = nsec_to_clock_t(task->start_boottime); seq_put_decimal_ull(m, "", pid_nr_ns(pid, ns)); seq_puts(m, " ("); diff --git a/include/linux/sched.h b/include/linux/sched.h index 67a1d86981a9..254128952eab 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -857,7 +857,7 @@ struct task_struct { u64 start_time; /* Boot based time in nsecs: */ - u64 real_start_time; + u64 start_boottime; /* MM fault and swap info: this can arguably be seen as either mm-specific or thread-specific: */ unsigned long min_flt; diff --git a/kernel/fork.c b/kernel/fork.c index bcdf53125210..1392ee8f4848 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2130,7 +2130,7 @@ static __latent_entropy struct task_struct *copy_process( */ p->start_time = ktime_get_ns(); - p->real_start_time = ktime_get_boottime_ns(); + p->start_boottime = ktime_get_boottime_ns(); /* * Make it visible to the rest of the system, but dont wake it up yet. -- cgit v1.2.3 From bf49d9dd6fef688733e2ddbd55f7bcb57df194e4 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Fri, 18 Oct 2019 13:50:53 +0900 Subject: export,module: add SPDX GPL-2.0 license identifier to headers with no license Commit b24413180f56 ("License cleanup: add SPDX GPL-2.0 license identifier to files with no license") took care of a lot of files without any license information. These headers were not processed by the tool perhaps because they contain "GPL" in the code. I do not see any license boilerplate in them, so they fall back to GPL version 2 only, which is the project default. Signed-off-by: Masahiro Yamada Link: https://lore.kernel.org/r/20191018045053.8424-1-yamada.masahiro@socionext.com Signed-off-by: Greg Kroah-Hartman --- include/asm-generic/export.h | 1 + include/linux/export.h | 1 + include/linux/license.h | 1 + include/linux/module.h | 7 +++++-- 4 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/asm-generic/export.h b/include/asm-generic/export.h index fa577978fbbd..d0166115a825 100644 --- a/include/asm-generic/export.h +++ b/include/asm-generic/export.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ #ifndef __ASM_GENERIC_EXPORT_H #define __ASM_GENERIC_EXPORT_H diff --git a/include/linux/export.h b/include/linux/export.h index 941d075f03d6..aee5c86ae350 100644 --- a/include/linux/export.h +++ b/include/linux/export.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ #ifndef _LINUX_EXPORT_H #define _LINUX_EXPORT_H diff --git a/include/linux/license.h b/include/linux/license.h index decdbf43cb5c..7cce390f120b 100644 --- a/include/linux/license.h +++ b/include/linux/license.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ #ifndef __LICENSE_H #define __LICENSE_H diff --git a/include/linux/module.h b/include/linux/module.h index 6d20895e7739..bd165ba68617 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -1,11 +1,14 @@ -#ifndef _LINUX_MODULE_H -#define _LINUX_MODULE_H +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Dynamic loading of modules into the kernel. * * Rewritten by Richard Henderson Dec 1996 * Rewritten again by Rusty Russell, 2002 */ + +#ifndef _LINUX_MODULE_H +#define _LINUX_MODULE_H + #include #include #include -- cgit v1.2.3 From a7e335deed174a37fc6f84f69caaeff8a08f8ff8 Mon Sep 17 00:00:00 2001 From: Eric Long Date: Wed, 23 Oct 2019 14:31:32 +0800 Subject: dmaengine: sprd: Add wrap address support for link-list mode The Spreadtrum Audio compress offload mode will use 2-stage DMA transfer to save power. That means we can request 2 dma channels, one for source channel, and another one for destination channel. Once the source channel's transaction is done, it will trigger the destination channel's transaction automatically by hardware signal. In this case, the source channel will transfer data from IRAM buffer to the DSP fifo to decoding/encoding, once IRAM buffer is empty by transferring done, the destination channel will start to transfer data from DDR buffer to IRAM buffer. Since the destination channel will use link-list mode to fill the IRAM data, and IRAM buffer is allocated by 32K, and DDR buffer is larger to 2M, that means we need lots of link-list nodes to do a cyclic transfer, instead wasting lots of link-list memory, we can use wrap address support to reduce link-list node number, which means when the transfer address reaches the wrap address, the transfer address will jump to the wrap_to address specified by wrap_to register, and only 2 link-list nodes can do a cyclic transfer to transfer data from DDR to IRAM. Thus this patch adds wrap address to support this case. [Baolin Wang changes the commit message] Signed-off-by: Eric Long Signed-off-by: Baolin Wang Link: https://lore.kernel.org/r/85a5484bc1f3dd53ce6f92700ad8b35f30a0b096.1571812029.git.baolin.wang@linaro.org Signed-off-by: Vinod Koul --- drivers/dma/sprd-dma.c | 13 +++++++++++++ include/linux/dma/sprd-dma.h | 4 ++++ 2 files changed, 17 insertions(+) (limited to 'include') diff --git a/drivers/dma/sprd-dma.c b/drivers/dma/sprd-dma.c index 32402c2615de..9a31a315dbef 100644 --- a/drivers/dma/sprd-dma.c +++ b/drivers/dma/sprd-dma.c @@ -99,6 +99,7 @@ /* DMA_CHN_WARP_* register definition */ #define SPRD_DMA_HIGH_ADDR_MASK GENMASK(31, 28) #define SPRD_DMA_LOW_ADDR_MASK GENMASK(31, 0) +#define SPRD_DMA_WRAP_ADDR_MASK GENMASK(27, 0) #define SPRD_DMA_HIGH_ADDR_OFFSET 4 /* SPRD_DMA_CHN_INTC register definition */ @@ -118,6 +119,8 @@ #define SPRD_DMA_SWT_MODE_OFFSET 26 #define SPRD_DMA_REQ_MODE_OFFSET 24 #define SPRD_DMA_REQ_MODE_MASK GENMASK(1, 0) +#define SPRD_DMA_WRAP_SEL_DEST BIT(23) +#define SPRD_DMA_WRAP_EN BIT(22) #define SPRD_DMA_FIX_SEL_OFFSET 21 #define SPRD_DMA_FIX_EN_OFFSET 20 #define SPRD_DMA_LLIST_END BIT(19) @@ -804,6 +807,8 @@ static int sprd_dma_fill_desc(struct dma_chan *chan, temp |= req_mode << SPRD_DMA_REQ_MODE_OFFSET; temp |= fix_mode << SPRD_DMA_FIX_SEL_OFFSET; temp |= fix_en << SPRD_DMA_FIX_EN_OFFSET; + temp |= schan->linklist.wrap_addr ? + SPRD_DMA_WRAP_EN | SPRD_DMA_WRAP_SEL_DEST : 0; temp |= slave_cfg->src_maxburst & SPRD_DMA_FRG_LEN_MASK; hw->frg_len = temp; @@ -831,6 +836,12 @@ static int sprd_dma_fill_desc(struct dma_chan *chan, hw->llist_ptr = lower_32_bits(llist_ptr); hw->src_blk_step = (upper_32_bits(llist_ptr) << SPRD_DMA_LLIST_HIGH_SHIFT) & SPRD_DMA_LLIST_HIGH_MASK; + + if (schan->linklist.wrap_addr) { + hw->wrap_ptr |= schan->linklist.wrap_addr & + SPRD_DMA_WRAP_ADDR_MASK; + hw->wrap_to |= dst & SPRD_DMA_WRAP_ADDR_MASK; + } } else { hw->llist_ptr = 0; hw->src_blk_step = 0; @@ -939,9 +950,11 @@ sprd_dma_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, schan->linklist.phy_addr = ll_cfg->phy_addr; schan->linklist.virt_addr = ll_cfg->virt_addr; + schan->linklist.wrap_addr = ll_cfg->wrap_addr; } else { schan->linklist.phy_addr = 0; schan->linklist.virt_addr = 0; + schan->linklist.wrap_addr = 0; } /* diff --git a/include/linux/dma/sprd-dma.h b/include/linux/dma/sprd-dma.h index ab82df64682a..d09c6f6f6da5 100644 --- a/include/linux/dma/sprd-dma.h +++ b/include/linux/dma/sprd-dma.h @@ -118,6 +118,9 @@ enum sprd_dma_int_type { * struct sprd_dma_linklist - DMA link-list address structure * @virt_addr: link-list virtual address to configure link-list node * @phy_addr: link-list physical address to link DMA transfer + * @wrap_addr: the wrap address for link-list mode, which means once the + * transfer address reaches the wrap address, the next transfer address + * will jump to the address specified by wrap_to register. * * The Spreadtrum DMA controller supports the link-list mode, that means slaves * can supply several groups configurations (each configuration represents one @@ -181,6 +184,7 @@ enum sprd_dma_int_type { struct sprd_dma_linklist { unsigned long virt_addr; phys_addr_t phy_addr; + phys_addr_t wrap_addr; }; #endif -- cgit v1.2.3 From fcbb8461fd2376ba3782b5b8bd440c929b8e4980 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 7 Nov 2019 16:14:40 +0900 Subject: kbuild: remove header compile test There are both positive and negative options about this feature. At first, I thought it was a good idea, but actually Linus stated a negative opinion (https://lkml.org/lkml/2019/9/29/227). I admit it is ugly and annoying. The baseline I'd like to keep is the compile-test of uapi headers. (Otherwise, kernel developers have no way to ensure the correctness of the exported headers.) I will maintain a small build rule in usr/include/Makefile. Remove the other header test functionality. Signed-off-by: Masahiro Yamada --- Documentation/kbuild/makefiles.rst | 17 - Makefile | 1 - drivers/gpu/drm/i915/Kconfig.debug | 1 - include/Kbuild | 1185 ------------------------------------ init/Kconfig | 22 +- scripts/Makefile.build | 9 - scripts/Makefile.lib | 14 - usr/include/Makefile | 12 +- 8 files changed, 9 insertions(+), 1252 deletions(-) delete mode 100644 include/Kbuild (limited to 'include') diff --git a/Documentation/kbuild/makefiles.rst b/Documentation/kbuild/makefiles.rst index b89c88168d6a..b9b50553bfc5 100644 --- a/Documentation/kbuild/makefiles.rst +++ b/Documentation/kbuild/makefiles.rst @@ -1115,23 +1115,6 @@ When kbuild executes, the following steps are followed (roughly): In this example, extra-y is used to list object files that shall be built, but shall not be linked as part of built-in.a. - header-test-y - - header-test-y specifies headers (`*.h`) in the current directory that - should be compile tested to ensure they are self-contained, - i.e. compilable as standalone units. If CONFIG_HEADER_TEST is enabled, - this builds them as part of extra-y. - - header-test-pattern-y - - This works as a weaker version of header-test-y, and accepts wildcard - patterns. The typical usage is:: - - header-test-pattern-y += *.h - - This specifies all the files that matches to `*.h` in the current - directory, but the files in 'header-test-' are excluded. - 6.7 Commands useful for building a boot image --------------------------------------------- diff --git a/Makefile b/Makefile index 4c14d7080405..a45291d8470a 100644 --- a/Makefile +++ b/Makefile @@ -618,7 +618,6 @@ ifeq ($(KBUILD_EXTMOD),) init-y := init/ drivers-y := drivers/ sound/ drivers-$(CONFIG_SAMPLES) += samples/ -drivers-$(CONFIG_KERNEL_HEADER_TEST) += include/ net-y := net/ libs-y := lib/ core-y := usr/ diff --git a/drivers/gpu/drm/i915/Kconfig.debug b/drivers/gpu/drm/i915/Kconfig.debug index 00786a142ff0..41c8e39a73ba 100644 --- a/drivers/gpu/drm/i915/Kconfig.debug +++ b/drivers/gpu/drm/i915/Kconfig.debug @@ -7,7 +7,6 @@ config DRM_I915_WERROR # We use the dependency on !COMPILE_TEST to not be enabled in # allmodconfig or allyesconfig configurations depends on !COMPILE_TEST - select HEADER_TEST default n help Add -Werror to the build flags for (and only for) i915.ko. diff --git a/include/Kbuild b/include/Kbuild deleted file mode 100644 index ffba79483cc5..000000000000 --- a/include/Kbuild +++ /dev/null @@ -1,1185 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only - -# Add header-test-$(CONFIG_...) guard to headers that are only compiled -# for particular architectures. -# -# Headers listed in header-test- are excluded from the test coverage. -# Many headers are excluded for now because they fail to build. Please -# consider to fix headers first before adding new ones to the blacklist. -# -# Sorted alphabetically. -header-test- += acpi/acbuffer.h -header-test- += acpi/acpi.h -header-test- += acpi/acpi_bus.h -header-test- += acpi/acpi_drivers.h -header-test- += acpi/acpi_io.h -header-test- += acpi/acpi_lpat.h -header-test- += acpi/acpiosxf.h -header-test- += acpi/acpixf.h -header-test- += acpi/acrestyp.h -header-test- += acpi/actbl.h -header-test- += acpi/actbl1.h -header-test- += acpi/actbl2.h -header-test- += acpi/actbl3.h -header-test- += acpi/actypes.h -header-test- += acpi/battery.h -header-test- += acpi/cppc_acpi.h -header-test- += acpi/nfit.h -header-test- += acpi/platform/acenv.h -header-test- += acpi/platform/acenvex.h -header-test- += acpi/platform/acintel.h -header-test- += acpi/platform/aclinux.h -header-test- += acpi/platform/aclinuxex.h -header-test- += acpi/processor.h -header-test-$(CONFIG_X86) += clocksource/hyperv_timer.h -header-test- += clocksource/timer-sp804.h -header-test- += crypto/cast_common.h -header-test- += crypto/internal/cryptouser.h -header-test- += crypto/pkcs7.h -header-test- += crypto/poly1305.h -header-test- += crypto/sha3.h -header-test- += drm/ati_pcigart.h -header-test- += drm/bridge/dw_hdmi.h -header-test- += drm/bridge/dw_mipi_dsi.h -header-test- += drm/drm_audio_component.h -header-test- += drm/drm_auth.h -header-test- += drm/drm_debugfs.h -header-test- += drm/drm_debugfs_crc.h -header-test- += drm/drm_displayid.h -header-test- += drm/drm_encoder_slave.h -header-test- += drm/drm_fb_cma_helper.h -header-test- += drm/drm_fb_helper.h -header-test- += drm/drm_fixed.h -header-test- += drm/drm_format_helper.h -header-test- += drm/drm_lease.h -header-test- += drm/drm_legacy.h -header-test- += drm/drm_panel.h -header-test- += drm/drm_plane_helper.h -header-test- += drm/drm_rect.h -header-test- += drm/i915_component.h -header-test- += drm/intel-gtt.h -header-test- += drm/tinydrm/tinydrm-helpers.h -header-test- += drm/ttm/ttm_debug.h -header-test- += keys/asymmetric-parser.h -header-test- += keys/asymmetric-subtype.h -header-test- += keys/asymmetric-type.h -header-test- += keys/big_key-type.h -header-test- += keys/request_key_auth-type.h -header-test- += keys/trusted.h -header-test- += kvm/arm_arch_timer.h -header-test- += kvm/arm_pmu.h -header-test-$(CONFIG_ARM) += kvm/arm_psci.h -header-test-$(CONFIG_ARM64) += kvm/arm_psci.h -header-test- += kvm/arm_vgic.h -header-test- += linux/8250_pci.h -header-test- += linux/a.out.h -header-test- += linux/adxl.h -header-test- += linux/agpgart.h -header-test- += linux/alcor_pci.h -header-test- += linux/amba/clcd.h -header-test- += linux/amba/pl080.h -header-test- += linux/amd-iommu.h -header-test-$(CONFIG_ARM) += linux/arm-cci.h -header-test-$(CONFIG_ARM64) += linux/arm-cci.h -header-test- += linux/arm_sdei.h -header-test- += linux/asn1_decoder.h -header-test- += linux/ata_platform.h -header-test- += linux/ath9k_platform.h -header-test- += linux/atm_tcp.h -header-test- += linux/atomic-fallback.h -header-test- += linux/avf/virtchnl.h -header-test- += linux/bcm47xx_sprom.h -header-test- += linux/bcma/bcma_driver_gmac_cmn.h -header-test- += linux/bcma/bcma_driver_mips.h -header-test- += linux/bcma/bcma_driver_pci.h -header-test- += linux/bcma/bcma_driver_pcie2.h -header-test- += linux/bit_spinlock.h -header-test- += linux/blk-mq-rdma.h -header-test- += linux/blk-mq.h -header-test- += linux/blktrace_api.h -header-test- += linux/blockgroup_lock.h -header-test- += linux/bma150.h -header-test- += linux/bpf_lirc.h -header-test- += linux/bpf_types.h -header-test- += linux/bsg-lib.h -header-test- += linux/bsg.h -header-test- += linux/btf.h -header-test- += linux/btree-128.h -header-test- += linux/btree-type.h -header-test-$(CONFIG_CPU_BIG_ENDIAN) += linux/byteorder/big_endian.h -header-test- += linux/byteorder/generic.h -header-test-$(CONFIG_CPU_LITTLE_ENDIAN) += linux/byteorder/little_endian.h -header-test- += linux/c2port.h -header-test- += linux/can/dev/peak_canfd.h -header-test- += linux/can/platform/cc770.h -header-test- += linux/can/platform/sja1000.h -header-test- += linux/ceph/ceph_features.h -header-test- += linux/ceph/ceph_frag.h -header-test- += linux/ceph/ceph_fs.h -header-test- += linux/ceph/debugfs.h -header-test- += linux/ceph/msgr.h -header-test- += linux/ceph/rados.h -header-test- += linux/cgroup_subsys.h -header-test- += linux/clk/sunxi-ng.h -header-test- += linux/clk/ti.h -header-test- += linux/cn_proc.h -header-test- += linux/coda_psdev.h -header-test- += linux/compaction.h -header-test- += linux/console_struct.h -header-test- += linux/count_zeros.h -header-test- += linux/cs5535.h -header-test- += linux/cuda.h -header-test- += linux/cyclades.h -header-test- += linux/dcookies.h -header-test- += linux/delayacct.h -header-test- += linux/delayed_call.h -header-test- += linux/device-mapper.h -header-test- += linux/devpts_fs.h -header-test- += linux/dio.h -header-test- += linux/dirent.h -header-test- += linux/dlm_plock.h -header-test- += linux/dm-dirty-log.h -header-test- += linux/dm-region-hash.h -header-test- += linux/dma-debug.h -header-test- += linux/dma/mmp-pdma.h -header-test- += linux/dma/sprd-dma.h -header-test- += linux/dns_resolver.h -header-test- += linux/drbd_genl.h -header-test- += linux/drbd_genl_api.h -header-test- += linux/dw_apb_timer.h -header-test- += linux/dynamic_debug.h -header-test- += linux/dynamic_queue_limits.h -header-test- += linux/ecryptfs.h -header-test- += linux/edma.h -header-test- += linux/eeprom_93cx6.h -header-test- += linux/efs_vh.h -header-test- += linux/elevator.h -header-test- += linux/elfcore-compat.h -header-test- += linux/error-injection.h -header-test- += linux/errseq.h -header-test- += linux/eventpoll.h -header-test- += linux/ext2_fs.h -header-test- += linux/f75375s.h -header-test- += linux/falloc.h -header-test- += linux/fault-inject.h -header-test- += linux/fbcon.h -header-test- += linux/firmware/intel/stratix10-svc-client.h -header-test- += linux/firmware/meson/meson_sm.h -header-test- += linux/firmware/trusted_foundations.h -header-test- += linux/firmware/xlnx-zynqmp.h -header-test- += linux/fixp-arith.h -header-test- += linux/flat.h -header-test- += linux/fs_types.h -header-test- += linux/fs_uart_pd.h -header-test- += linux/fsi-occ.h -header-test- += linux/fsi-sbefifo.h -header-test- += linux/fsl/bestcomm/ata.h -header-test- += linux/fsl/bestcomm/bestcomm.h -header-test- += linux/fsl/bestcomm/bestcomm_priv.h -header-test- += linux/fsl/bestcomm/fec.h -header-test- += linux/fsl/bestcomm/gen_bd.h -header-test- += linux/fsl/bestcomm/sram.h -header-test- += linux/fsl_hypervisor.h -header-test- += linux/fsldma.h -header-test- += linux/ftrace_irq.h -header-test- += linux/gameport.h -header-test- += linux/genl_magic_func.h -header-test- += linux/genl_magic_struct.h -header-test- += linux/gpio/aspeed.h -header-test- += linux/gpio/gpio-reg.h -header-test- += linux/hid-debug.h -header-test- += linux/hiddev.h -header-test- += linux/hippidevice.h -header-test- += linux/hmm.h -header-test- += linux/hp_sdc.h -header-test- += linux/huge_mm.h -header-test- += linux/hugetlb_cgroup.h -header-test- += linux/hugetlb_inline.h -header-test- += linux/hwmon-vid.h -header-test- += linux/hyperv.h -header-test- += linux/i2c-algo-pca.h -header-test- += linux/i2c-algo-pcf.h -header-test- += linux/i3c/ccc.h -header-test- += linux/i3c/device.h -header-test- += linux/i3c/master.h -header-test- += linux/i8042.h -header-test- += linux/ide.h -header-test- += linux/idle_inject.h -header-test- += linux/if_frad.h -header-test- += linux/if_rmnet.h -header-test- += linux/if_tap.h -header-test- += linux/iio/accel/kxcjk_1013.h -header-test- += linux/iio/adc/ad_sigma_delta.h -header-test- += linux/iio/buffer-dma.h -header-test- += linux/iio/buffer_impl.h -header-test- += linux/iio/common/st_sensors.h -header-test- += linux/iio/common/st_sensors_i2c.h -header-test- += linux/iio/common/st_sensors_spi.h -header-test- += linux/iio/dac/ad5421.h -header-test- += linux/iio/dac/ad5504.h -header-test- += linux/iio/dac/ad5791.h -header-test- += linux/iio/dac/max517.h -header-test- += linux/iio/dac/mcp4725.h -header-test- += linux/iio/frequency/ad9523.h -header-test- += linux/iio/frequency/adf4350.h -header-test- += linux/iio/hw-consumer.h -header-test- += linux/iio/imu/adis.h -header-test- += linux/iio/sysfs.h -header-test- += linux/iio/timer/stm32-timer-trigger.h -header-test- += linux/iio/trigger.h -header-test- += linux/iio/triggered_event.h -header-test- += linux/imx-media.h -header-test- += linux/inet_diag.h -header-test- += linux/init_ohci1394_dma.h -header-test- += linux/initrd.h -header-test- += linux/input/adp5589.h -header-test- += linux/input/bu21013.h -header-test- += linux/input/cma3000.h -header-test- += linux/input/kxtj9.h -header-test- += linux/input/lm8333.h -header-test- += linux/input/sparse-keymap.h -header-test- += linux/input/touchscreen.h -header-test- += linux/input/tps6507x-ts.h -header-test-$(CONFIG_X86) += linux/intel-iommu.h -header-test- += linux/intel-ish-client-if.h -header-test- += linux/intel-pti.h -header-test- += linux/intel-svm.h -header-test- += linux/interconnect-provider.h -header-test- += linux/ioc3.h -header-test-$(CONFIG_BLOCK) += linux/iomap.h -header-test- += linux/ipack.h -header-test- += linux/irq_cpustat.h -header-test- += linux/irq_poll.h -header-test- += linux/irqchip/arm-gic-v3.h -header-test- += linux/irqchip/arm-gic-v4.h -header-test- += linux/irqchip/irq-madera.h -header-test- += linux/irqchip/irq-sa11x0.h -header-test- += linux/irqchip/mxs.h -header-test- += linux/irqchip/versatile-fpga.h -header-test- += linux/irqdesc.h -header-test- += linux/irqflags.h -header-test- += linux/iscsi_boot_sysfs.h -header-test- += linux/isdn/capiutil.h -header-test- += linux/isdn/hdlc.h -header-test- += linux/isdn_ppp.h -header-test- += linux/jbd2.h -header-test- += linux/jump_label.h -header-test- += linux/jump_label_ratelimit.h -header-test- += linux/jz4740-adc.h -header-test- += linux/kasan.h -header-test- += linux/kcore.h -header-test- += linux/kdev_t.h -header-test- += linux/kernelcapi.h -header-test- += linux/khugepaged.h -header-test- += linux/kobj_map.h -header-test- += linux/kobject_ns.h -header-test- += linux/kvm_host.h -header-test- += linux/kvm_irqfd.h -header-test- += linux/kvm_para.h -header-test- += linux/lantiq.h -header-test- += linux/lapb.h -header-test- += linux/latencytop.h -header-test- += linux/led-lm3530.h -header-test- += linux/leds-bd2802.h -header-test- += linux/leds-lp3944.h -header-test- += linux/leds-lp3952.h -header-test- += linux/leds_pwm.h -header-test- += linux/libata.h -header-test- += linux/license.h -header-test- += linux/lightnvm.h -header-test- += linux/lis3lv02d.h -header-test- += linux/list_bl.h -header-test- += linux/list_lru.h -header-test- += linux/list_nulls.h -header-test- += linux/lockd/share.h -header-test- += linux/lzo.h -header-test- += linux/mailbox/zynqmp-ipi-message.h -header-test- += linux/maple.h -header-test- += linux/mbcache.h -header-test- += linux/mbus.h -header-test- += linux/mc146818rtc.h -header-test- += linux/mc6821.h -header-test- += linux/mdev.h -header-test- += linux/mem_encrypt.h -header-test- += linux/memfd.h -header-test- += linux/mfd/88pm80x.h -header-test- += linux/mfd/88pm860x.h -header-test- += linux/mfd/abx500/ab8500-bm.h -header-test- += linux/mfd/abx500/ab8500-gpadc.h -header-test- += linux/mfd/adp5520.h -header-test- += linux/mfd/arizona/pdata.h -header-test- += linux/mfd/as3711.h -header-test- += linux/mfd/as3722.h -header-test- += linux/mfd/da903x.h -header-test- += linux/mfd/da9055/pdata.h -header-test- += linux/mfd/db8500-prcmu.h -header-test- += linux/mfd/dbx500-prcmu.h -header-test- += linux/mfd/dln2.h -header-test- += linux/mfd/dm355evm_msp.h -header-test- += linux/mfd/ds1wm.h -header-test- += linux/mfd/ezx-pcap.h -header-test- += linux/mfd/intel_msic.h -header-test- += linux/mfd/janz.h -header-test- += linux/mfd/kempld.h -header-test- += linux/mfd/lm3533.h -header-test- += linux/mfd/lp8788-isink.h -header-test- += linux/mfd/lpc_ich.h -header-test- += linux/mfd/max77693.h -header-test- += linux/mfd/max8998-private.h -header-test- += linux/mfd/menelaus.h -header-test- += linux/mfd/mt6397/core.h -header-test- += linux/mfd/palmas.h -header-test- += linux/mfd/pcf50633/backlight.h -header-test- += linux/mfd/rc5t583.h -header-test- += linux/mfd/retu.h -header-test- += linux/mfd/samsung/core.h -header-test- += linux/mfd/si476x-platform.h -header-test- += linux/mfd/si476x-reports.h -header-test- += linux/mfd/sky81452.h -header-test- += linux/mfd/smsc.h -header-test- += linux/mfd/sta2x11-mfd.h -header-test- += linux/mfd/stmfx.h -header-test- += linux/mfd/tc3589x.h -header-test- += linux/mfd/tc6387xb.h -header-test- += linux/mfd/tc6393xb.h -header-test- += linux/mfd/tps65090.h -header-test- += linux/mfd/tps6586x.h -header-test- += linux/mfd/tps65910.h -header-test- += linux/mfd/tps80031.h -header-test- += linux/mfd/ucb1x00.h -header-test- += linux/mfd/viperboard.h -header-test- += linux/mfd/wm831x/core.h -header-test- += linux/mfd/wm831x/otp.h -header-test- += linux/mfd/wm831x/pdata.h -header-test- += linux/mfd/wm8994/core.h -header-test- += linux/mfd/wm8994/pdata.h -header-test- += linux/mlx4/doorbell.h -header-test- += linux/mlx4/srq.h -header-test- += linux/mlx5/doorbell.h -header-test- += linux/mlx5/eq.h -header-test- += linux/mlx5/fs_helpers.h -header-test- += linux/mlx5/mlx5_ifc.h -header-test- += linux/mlx5/mlx5_ifc_fpga.h -header-test- += linux/mm-arch-hooks.h -header-test- += linux/mm_inline.h -header-test- += linux/mmu_context.h -header-test- += linux/mpage.h -header-test- += linux/mtd/bbm.h -header-test- += linux/mtd/cfi.h -header-test- += linux/mtd/doc2000.h -header-test- += linux/mtd/flashchip.h -header-test- += linux/mtd/ftl.h -header-test- += linux/mtd/gen_probe.h -header-test- += linux/mtd/jedec.h -header-test- += linux/mtd/nand_bch.h -header-test- += linux/mtd/nand_ecc.h -header-test- += linux/mtd/ndfc.h -header-test- += linux/mtd/onenand.h -header-test- += linux/mtd/pismo.h -header-test- += linux/mtd/plat-ram.h -header-test- += linux/mtd/spi-nor.h -header-test- += linux/mv643xx.h -header-test- += linux/mv643xx_eth.h -header-test- += linux/mvebu-pmsu.h -header-test- += linux/mxm-wmi.h -header-test- += linux/n_r3964.h -header-test- += linux/ndctl.h -header-test- += linux/nfs.h -header-test- += linux/nfs_fs_i.h -header-test- += linux/nfs_fs_sb.h -header-test- += linux/nfs_page.h -header-test- += linux/nfs_xdr.h -header-test- += linux/nfsacl.h -header-test- += linux/nl802154.h -header-test- += linux/ns_common.h -header-test- += linux/nsc_gpio.h -header-test- += linux/ntb_transport.h -header-test- += linux/nubus.h -header-test- += linux/nvme-fc-driver.h -header-test- += linux/nvme-fc.h -header-test- += linux/nvme-rdma.h -header-test- += linux/nvram.h -header-test- += linux/objagg.h -header-test- += linux/of_clk.h -header-test- += linux/of_net.h -header-test- += linux/of_pdt.h -header-test- += linux/olpc-ec.h -header-test- += linux/omap-dma.h -header-test- += linux/omap-dmaengine.h -header-test- += linux/omap-gpmc.h -header-test- += linux/omap-iommu.h -header-test- += linux/omap-mailbox.h -header-test- += linux/once.h -header-test- += linux/osq_lock.h -header-test- += linux/overflow.h -header-test- += linux/page-flags-layout.h -header-test- += linux/page-isolation.h -header-test- += linux/page_ext.h -header-test- += linux/page_owner.h -header-test- += linux/parport_pc.h -header-test- += linux/parser.h -header-test- += linux/pci-acpi.h -header-test- += linux/pci-dma-compat.h -header-test- += linux/pci_hotplug.h -header-test- += linux/pda_power.h -header-test- += linux/perf/arm_pmu.h -header-test- += linux/perf_regs.h -header-test- += linux/phy/omap_control_phy.h -header-test- += linux/phy/tegra/xusb.h -header-test- += linux/phy/ulpi_phy.h -header-test- += linux/phy_fixed.h -header-test- += linux/pipe_fs_i.h -header-test- += linux/pktcdvd.h -header-test- += linux/pl320-ipc.h -header-test- += linux/pl353-smc.h -header-test- += linux/platform_data/ad5449.h -header-test- += linux/platform_data/ad5755.h -header-test- += linux/platform_data/ad7266.h -header-test- += linux/platform_data/ad7291.h -header-test- += linux/platform_data/ad7298.h -header-test- += linux/platform_data/ad7303.h -header-test- += linux/platform_data/ad7791.h -header-test- += linux/platform_data/ad7793.h -header-test- += linux/platform_data/ad7887.h -header-test- += linux/platform_data/adau17x1.h -header-test- += linux/platform_data/adp8870.h -header-test- += linux/platform_data/ads1015.h -header-test- += linux/platform_data/ads7828.h -header-test- += linux/platform_data/apds990x.h -header-test- += linux/platform_data/arm-ux500-pm.h -header-test- += linux/platform_data/asoc-s3c.h -header-test- += linux/platform_data/at91_adc.h -header-test- += linux/platform_data/ata-pxa.h -header-test- += linux/platform_data/atmel.h -header-test- += linux/platform_data/bh1770glc.h -header-test- += linux/platform_data/brcmfmac.h -header-test- += linux/platform_data/cros_ec_commands.h -header-test- += linux/platform_data/clk-u300.h -header-test- += linux/platform_data/cyttsp4.h -header-test- += linux/platform_data/dma-coh901318.h -header-test- += linux/platform_data/dma-imx-sdma.h -header-test- += linux/platform_data/dma-mcf-edma.h -header-test- += linux/platform_data/dma-s3c24xx.h -header-test- += linux/platform_data/dmtimer-omap.h -header-test- += linux/platform_data/dsa.h -header-test- += linux/platform_data/edma.h -header-test- += linux/platform_data/elm.h -header-test- += linux/platform_data/emif_plat.h -header-test- += linux/platform_data/fsa9480.h -header-test- += linux/platform_data/g762.h -header-test- += linux/platform_data/gpio-ath79.h -header-test- += linux/platform_data/gpio-davinci.h -header-test- += linux/platform_data/gpio-dwapb.h -header-test- += linux/platform_data/gpio-htc-egpio.h -header-test- += linux/platform_data/gpmc-omap.h -header-test- += linux/platform_data/hsmmc-omap.h -header-test- += linux/platform_data/hwmon-s3c.h -header-test- += linux/platform_data/i2c-davinci.h -header-test- += linux/platform_data/i2c-imx.h -header-test- += linux/platform_data/i2c-mux-reg.h -header-test- += linux/platform_data/i2c-ocores.h -header-test- += linux/platform_data/i2c-xiic.h -header-test- += linux/platform_data/intel-spi.h -header-test- += linux/platform_data/invensense_mpu6050.h -header-test- += linux/platform_data/irda-pxaficp.h -header-test- += linux/platform_data/irda-sa11x0.h -header-test- += linux/platform_data/itco_wdt.h -header-test- += linux/platform_data/jz4740/jz4740_nand.h -header-test- += linux/platform_data/keyboard-pxa930_rotary.h -header-test- += linux/platform_data/keypad-omap.h -header-test- += linux/platform_data/leds-lp55xx.h -header-test- += linux/platform_data/leds-omap.h -header-test- += linux/platform_data/lp855x.h -header-test- += linux/platform_data/lp8727.h -header-test- += linux/platform_data/max197.h -header-test- += linux/platform_data/max3421-hcd.h -header-test- += linux/platform_data/max732x.h -header-test- += linux/platform_data/mcs.h -header-test- += linux/platform_data/mdio-bcm-unimac.h -header-test- += linux/platform_data/mdio-gpio.h -header-test- += linux/platform_data/media/si4713.h -header-test- += linux/platform_data/mlxreg.h -header-test- += linux/platform_data/mmc-omap.h -header-test- += linux/platform_data/mmc-sdhci-s3c.h -header-test- += linux/platform_data/mmp_audio.h -header-test- += linux/platform_data/mtd-orion_nand.h -header-test- += linux/platform_data/mv88e6xxx.h -header-test- += linux/platform_data/net-cw1200.h -header-test- += linux/platform_data/omap-twl4030.h -header-test- += linux/platform_data/omapdss.h -header-test- += linux/platform_data/pcf857x.h -header-test- += linux/platform_data/pixcir_i2c_ts.h -header-test- += linux/platform_data/pwm_omap_dmtimer.h -header-test- += linux/platform_data/pxa2xx_udc.h -header-test- += linux/platform_data/pxa_sdhci.h -header-test- += linux/platform_data/remoteproc-omap.h -header-test- += linux/platform_data/sa11x0-serial.h -header-test- += linux/platform_data/sc18is602.h -header-test- += linux/platform_data/sdhci-pic32.h -header-test- += linux/platform_data/serial-sccnxp.h -header-test- += linux/platform_data/sht3x.h -header-test- += linux/platform_data/shtc1.h -header-test- += linux/platform_data/si5351.h -header-test- += linux/platform_data/sky81452-backlight.h -header-test- += linux/platform_data/spi-davinci.h -header-test- += linux/platform_data/spi-ep93xx.h -header-test- += linux/platform_data/spi-mt65xx.h -header-test- += linux/platform_data/st_sensors_pdata.h -header-test- += linux/platform_data/ti-sysc.h -header-test- += linux/platform_data/timer-ixp4xx.h -header-test- += linux/platform_data/touchscreen-s3c2410.h -header-test- += linux/platform_data/tsc2007.h -header-test- += linux/platform_data/tsl2772.h -header-test- += linux/platform_data/uio_pruss.h -header-test- += linux/platform_data/usb-davinci.h -header-test- += linux/platform_data/usb-ehci-mxc.h -header-test- += linux/platform_data/usb-ehci-orion.h -header-test- += linux/platform_data/usb-mx2.h -header-test- += linux/platform_data/usb-ohci-s3c2410.h -header-test- += linux/platform_data/usb-omap.h -header-test- += linux/platform_data/usb-s3c2410_udc.h -header-test- += linux/platform_data/usb3503.h -header-test- += linux/platform_data/ux500_wdt.h -header-test- += linux/platform_data/video-clcd-versatile.h -header-test- += linux/platform_data/video-imxfb.h -header-test- += linux/platform_data/video-pxafb.h -header-test- += linux/platform_data/video_s3c.h -header-test- += linux/platform_data/voltage-omap.h -header-test- += linux/platform_data/x86/apple.h -header-test- += linux/platform_data/x86/clk-pmc-atom.h -header-test- += linux/platform_data/x86/pmc_atom.h -header-test- += linux/platform_data/xtalk-bridge.h -header-test- += linux/pm2301_charger.h -header-test- += linux/pm_wakeirq.h -header-test- += linux/pm_wakeup.h -header-test- += linux/pmbus.h -header-test- += linux/pmu.h -header-test- += linux/posix_acl.h -header-test- += linux/posix_acl_xattr.h -header-test- += linux/power/ab8500.h -header-test- += linux/power/bq27xxx_battery.h -header-test- += linux/power/generic-adc-battery.h -header-test- += linux/power/jz4740-battery.h -header-test- += linux/power/max17042_battery.h -header-test- += linux/power/max8903_charger.h -header-test- += linux/ppp-comp.h -header-test- += linux/pps-gpio.h -header-test- += linux/pr.h -header-test- += linux/proc_ns.h -header-test- += linux/processor.h -header-test- += linux/psi.h -header-test- += linux/psp-sev.h -header-test- += linux/pstore.h -header-test- += linux/ptr_ring.h -header-test- += linux/ptrace.h -header-test- += linux/qcom-geni-se.h -header-test- += linux/qed/eth_common.h -header-test- += linux/qed/fcoe_common.h -header-test- += linux/qed/iscsi_common.h -header-test- += linux/qed/iwarp_common.h -header-test- += linux/qed/qed_eth_if.h -header-test- += linux/qed/qed_fcoe_if.h -header-test- += linux/qed/rdma_common.h -header-test- += linux/qed/storage_common.h -header-test- += linux/qed/tcp_common.h -header-test- += linux/qnx6_fs.h -header-test- += linux/quicklist.h -header-test- += linux/ramfs.h -header-test- += linux/range.h -header-test- += linux/rcu_node_tree.h -header-test- += linux/rculist_bl.h -header-test- += linux/rculist_nulls.h -header-test- += linux/rcutiny.h -header-test- += linux/rcutree.h -header-test- += linux/reboot-mode.h -header-test- += linux/regulator/fixed.h -header-test- += linux/regulator/gpio-regulator.h -header-test- += linux/regulator/max8973-regulator.h -header-test- += linux/regulator/of_regulator.h -header-test- += linux/regulator/tps51632-regulator.h -header-test- += linux/regulator/tps62360.h -header-test- += linux/regulator/tps6507x.h -header-test- += linux/regulator/userspace-consumer.h -header-test- += linux/remoteproc/st_slim_rproc.h -header-test- += linux/reset/socfpga.h -header-test- += linux/reset/sunxi.h -header-test- += linux/rtc/m48t59.h -header-test- += linux/rtc/rtc-omap.h -header-test- += linux/rtc/sirfsoc_rtciobrg.h -header-test- += linux/rwlock.h -header-test- += linux/rwlock_types.h -header-test- += linux/scc.h -header-test- += linux/sched/deadline.h -header-test- += linux/sched/smt.h -header-test- += linux/sched/sysctl.h -header-test- += linux/sched_clock.h -header-test- += linux/scpi_protocol.h -header-test- += linux/scx200_gpio.h -header-test- += linux/seccomp.h -header-test- += linux/sed-opal.h -header-test- += linux/seg6_iptunnel.h -header-test- += linux/selection.h -header-test- += linux/set_memory.h -header-test- += linux/shrinker.h -header-test- += linux/sirfsoc_dma.h -header-test- += linux/skb_array.h -header-test- += linux/slab_def.h -header-test- += linux/slub_def.h -header-test- += linux/sm501.h -header-test- += linux/smc91x.h -header-test- += linux/static_key.h -header-test- += linux/soc/actions/owl-sps.h -header-test- += linux/soc/amlogic/meson-canvas.h -header-test- += linux/soc/brcmstb/brcmstb.h -header-test- += linux/soc/ixp4xx/npe.h -header-test- += linux/soc/mediatek/infracfg.h -header-test- += linux/soc/qcom/smd-rpm.h -header-test- += linux/soc/qcom/smem.h -header-test- += linux/soc/qcom/smem_state.h -header-test- += linux/soc/qcom/wcnss_ctrl.h -header-test- += linux/soc/renesas/rcar-rst.h -header-test- += linux/soc/samsung/exynos-pmu.h -header-test- += linux/soc/sunxi/sunxi_sram.h -header-test- += linux/soc/ti/ti-msgmgr.h -header-test- += linux/soc/ti/ti_sci_inta_msi.h -header-test- += linux/soc/ti/ti_sci_protocol.h -header-test- += linux/soundwire/sdw.h -header-test- += linux/soundwire/sdw_intel.h -header-test- += linux/soundwire/sdw_type.h -header-test- += linux/spi/ad7877.h -header-test- += linux/spi/ads7846.h -header-test- += linux/spi/at86rf230.h -header-test- += linux/spi/ds1305.h -header-test- += linux/spi/libertas_spi.h -header-test- += linux/spi/lms283gf05.h -header-test- += linux/spi/max7301.h -header-test- += linux/spi/mcp23s08.h -header-test- += linux/spi/rspi.h -header-test- += linux/spi/s3c24xx.h -header-test- += linux/spi/sh_msiof.h -header-test- += linux/spi/spi-fsl-dspi.h -header-test- += linux/spi/spi_bitbang.h -header-test- += linux/spi/spi_gpio.h -header-test- += linux/spi/xilinx_spi.h -header-test- += linux/spinlock_api_smp.h -header-test- += linux/spinlock_api_up.h -header-test- += linux/spinlock_types.h -header-test- += linux/splice.h -header-test- += linux/sram.h -header-test- += linux/srcutiny.h -header-test- += linux/srcutree.h -header-test- += linux/ssb/ssb_driver_chipcommon.h -header-test- += linux/ssb/ssb_driver_extif.h -header-test- += linux/ssb/ssb_driver_mips.h -header-test- += linux/ssb/ssb_driver_pci.h -header-test- += linux/ssbi.h -header-test- += linux/stackdepot.h -header-test- += linux/stmp3xxx_rtc_wdt.h -header-test- += linux/string_helpers.h -header-test- += linux/sungem_phy.h -header-test- += linux/sunrpc/msg_prot.h -header-test- += linux/sunrpc/rpc_pipe_fs.h -header-test- += linux/sunrpc/xprtmultipath.h -header-test- += linux/sunrpc/xprtsock.h -header-test- += linux/sunxi-rsb.h -header-test- += linux/svga.h -header-test- += linux/sw842.h -header-test- += linux/swapfile.h -header-test- += linux/swapops.h -header-test- += linux/swiotlb.h -header-test- += linux/sysv_fs.h -header-test- += linux/t10-pi.h -header-test- += linux/task_io_accounting.h -header-test- += linux/tick.h -header-test- += linux/timb_dma.h -header-test- += linux/timekeeping.h -header-test- += linux/timekeeping32.h -header-test- += linux/ts-nbus.h -header-test- += linux/tsacct_kern.h -header-test- += linux/tty_flip.h -header-test- += linux/tty_ldisc.h -header-test- += linux/ucb1400.h -header-test- += linux/usb/association.h -header-test- += linux/usb/cdc-wdm.h -header-test- += linux/usb/cdc_ncm.h -header-test- += linux/usb/ezusb.h -header-test- += linux/usb/gadget_configfs.h -header-test- += linux/usb/gpio_vbus.h -header-test- += linux/usb/hcd.h -header-test- += linux/usb/iowarrior.h -header-test- += linux/usb/irda.h -header-test- += linux/usb/isp116x.h -header-test- += linux/usb/isp1362.h -header-test- += linux/usb/musb.h -header-test- += linux/usb/net2280.h -header-test- += linux/usb/ohci_pdriver.h -header-test- += linux/usb/otg-fsm.h -header-test- += linux/usb/pd_ado.h -header-test- += linux/usb/r8a66597.h -header-test- += linux/usb/rndis_host.h -header-test- += linux/usb/serial.h -header-test- += linux/usb/sl811.h -header-test- += linux/usb/storage.h -header-test- += linux/usb/uas.h -header-test- += linux/usb/usb338x.h -header-test- += linux/usb/usbnet.h -header-test- += linux/usb/wusb-wa.h -header-test- += linux/usb/xhci-dbgp.h -header-test- += linux/usb_usual.h -header-test- += linux/user-return-notifier.h -header-test- += linux/userfaultfd_k.h -header-test- += linux/verification.h -header-test- += linux/vgaarb.h -header-test- += linux/via_core.h -header-test- += linux/via_i2c.h -header-test- += linux/virtio_byteorder.h -header-test- += linux/virtio_ring.h -header-test- += linux/visorbus.h -header-test- += linux/vme.h -header-test- += linux/vmstat.h -header-test- += linux/vmw_vmci_api.h -header-test- += linux/vmw_vmci_defs.h -header-test- += linux/vringh.h -header-test- += linux/vt_buffer.h -header-test- += linux/zorro.h -header-test- += linux/zpool.h -header-test- += math-emu/double.h -header-test- += math-emu/op-common.h -header-test- += math-emu/quad.h -header-test- += math-emu/single.h -header-test- += math-emu/soft-fp.h -header-test- += media/davinci/dm355_ccdc.h -header-test- += media/davinci/dm644x_ccdc.h -header-test- += media/davinci/isif.h -header-test- += media/davinci/vpbe_osd.h -header-test- += media/davinci/vpbe_types.h -header-test- += media/davinci/vpif_types.h -header-test- += media/demux.h -header-test- += media/drv-intf/soc_mediabus.h -header-test- += media/dvb_net.h -header-test- += media/fwht-ctrls.h -header-test- += media/i2c/ad9389b.h -header-test- += media/i2c/adv7343.h -header-test- += media/i2c/adv7511.h -header-test- += media/i2c/adv7842.h -header-test- += media/i2c/m5mols.h -header-test- += media/i2c/mt9m032.h -header-test- += media/i2c/mt9t112.h -header-test- += media/i2c/mt9v032.h -header-test- += media/i2c/ov2659.h -header-test- += media/i2c/ov7670.h -header-test- += media/i2c/rj54n1cb0c.h -header-test- += media/i2c/saa6588.h -header-test- += media/i2c/saa7115.h -header-test- += media/i2c/sr030pc30.h -header-test- += media/i2c/tc358743.h -header-test- += media/i2c/tda1997x.h -header-test- += media/i2c/ths7303.h -header-test- += media/i2c/tvaudio.h -header-test- += media/i2c/tvp514x.h -header-test- += media/i2c/tvp7002.h -header-test- += media/i2c/wm8775.h -header-test- += media/imx.h -header-test- += media/media-dev-allocator.h -header-test- += media/mpeg2-ctrls.h -header-test- += media/rcar-fcp.h -header-test- += media/tuner-types.h -header-test- += media/tveeprom.h -header-test- += media/v4l2-flash-led-class.h -header-test- += misc/altera.h -header-test- += misc/cxl-base.h -header-test- += misc/cxllib.h -header-test- += net/9p/9p.h -header-test- += net/9p/client.h -header-test- += net/9p/transport.h -header-test- += net/af_vsock.h -header-test- += net/ax88796.h -header-test- += net/bluetooth/hci.h -header-test- += net/bluetooth/hci_core.h -header-test- += net/bluetooth/hci_mon.h -header-test- += net/bluetooth/hci_sock.h -header-test- += net/bluetooth/l2cap.h -header-test- += net/bluetooth/mgmt.h -header-test- += net/bluetooth/rfcomm.h -header-test- += net/bluetooth/sco.h -header-test- += net/bond_options.h -header-test- += net/caif/cfsrvl.h -header-test- += net/codel_impl.h -header-test- += net/codel_qdisc.h -header-test- += net/compat.h -header-test- += net/datalink.h -header-test- += net/dcbevent.h -header-test- += net/dcbnl.h -header-test- += net/dn_dev.h -header-test- += net/dn_fib.h -header-test- += net/dn_neigh.h -header-test- += net/dn_nsp.h -header-test- += net/dn_route.h -header-test- += net/erspan.h -header-test- += net/esp.h -header-test- += net/ethoc.h -header-test- += net/firewire.h -header-test- += net/flow_offload.h -header-test- += net/fq.h -header-test- += net/fq_impl.h -header-test- += net/garp.h -header-test- += net/gtp.h -header-test- += net/gue.h -header-test- += net/hwbm.h -header-test- += net/ila.h -header-test- += net/inet6_connection_sock.h -header-test- += net/inet_common.h -header-test- += net/inet_frag.h -header-test- += net/ip6_route.h -header-test- += net/ip_vs.h -header-test- += net/ipcomp.h -header-test- += net/ipconfig.h -header-test- += net/iucv/af_iucv.h -header-test- += net/iucv/iucv.h -header-test- += net/lapb.h -header-test- += net/llc_c_ac.h -header-test- += net/llc_c_st.h -header-test- += net/llc_s_ac.h -header-test- += net/llc_s_ev.h -header-test- += net/llc_s_st.h -header-test- += net/mpls_iptunnel.h -header-test- += net/mrp.h -header-test- += net/ncsi.h -header-test- += net/netevent.h -header-test- += net/netns/can.h -header-test- += net/netns/generic.h -header-test- += net/netns/ieee802154_6lowpan.h -header-test- += net/netns/ipv4.h -header-test- += net/netns/ipv6.h -header-test- += net/netns/mpls.h -header-test- += net/netns/nftables.h -header-test- += net/netns/sctp.h -header-test- += net/netrom.h -header-test- += net/p8022.h -header-test- += net/phonet/pep.h -header-test- += net/phonet/phonet.h -header-test- += net/phonet/pn_dev.h -header-test- += net/pptp.h -header-test- += net/psample.h -header-test- += net/psnap.h -header-test- += net/regulatory.h -header-test- += net/rose.h -header-test- += net/sctp/auth.h -header-test- += net/sctp/stream_interleave.h -header-test- += net/sctp/stream_sched.h -header-test- += net/sctp/tsnmap.h -header-test- += net/sctp/ulpevent.h -header-test- += net/sctp/ulpqueue.h -header-test- += net/secure_seq.h -header-test- += net/smc.h -header-test- += net/stp.h -header-test- += net/transp_v6.h -header-test- += net/tun_proto.h -header-test- += net/udplite.h -header-test- += net/xdp.h -header-test- += net/xdp_priv.h -header-test- += pcmcia/cistpl.h -header-test- += pcmcia/ds.h -header-test- += rdma/tid_rdma_defs.h -header-test- += scsi/fc/fc_encaps.h -header-test- += scsi/fc/fc_fc2.h -header-test- += scsi/fc/fc_fcoe.h -header-test- += scsi/fc/fc_fip.h -header-test- += scsi/fc_encode.h -header-test- += scsi/fc_frame.h -header-test- += scsi/iser.h -header-test- += scsi/libfc.h -header-test- += scsi/libfcoe.h -header-test- += scsi/libsas.h -header-test- += scsi/sas_ata.h -header-test- += scsi/scsi_cmnd.h -header-test- += scsi/scsi_dbg.h -header-test- += scsi/scsi_device.h -header-test- += scsi/scsi_dh.h -header-test- += scsi/scsi_eh.h -header-test- += scsi/scsi_host.h -header-test- += scsi/scsi_ioctl.h -header-test- += scsi/scsi_request.h -header-test- += scsi/scsi_tcq.h -header-test- += scsi/scsi_transport.h -header-test- += scsi/scsi_transport_fc.h -header-test- += scsi/scsi_transport_sas.h -header-test- += scsi/scsi_transport_spi.h -header-test- += scsi/scsi_transport_srp.h -header-test- += scsi/scsicam.h -header-test- += scsi/sg.h -header-test- += soc/arc/aux.h -header-test- += soc/arc/mcip.h -header-test- += soc/arc/timers.h -header-test- += soc/brcmstb/common.h -header-test- += soc/fsl/bman.h -header-test- += soc/fsl/qe/qe.h -header-test- += soc/fsl/qe/qe_ic.h -header-test- += soc/fsl/qe/qe_tdm.h -header-test- += soc/fsl/qe/ucc.h -header-test- += soc/fsl/qe/ucc_fast.h -header-test- += soc/fsl/qe/ucc_slow.h -header-test- += soc/fsl/qman.h -header-test- += soc/nps/common.h -header-test-$(CONFIG_ARC) += soc/nps/mtm.h -header-test- += soc/qcom/cmd-db.h -header-test- += soc/qcom/rpmh.h -header-test- += soc/qcom/tcs.h -header-test- += soc/tegra/ahb.h -header-test- += soc/tegra/bpmp-abi.h -header-test- += soc/tegra/common.h -header-test- += soc/tegra/flowctrl.h -header-test- += soc/tegra/fuse.h -header-test- += soc/tegra/mc.h -header-test- += sound/ac97/compat.h -header-test- += sound/aci.h -header-test- += sound/ad1843.h -header-test- += sound/adau1373.h -header-test- += sound/ak4113.h -header-test- += sound/ak4114.h -header-test- += sound/ak4117.h -header-test- += sound/cs35l33.h -header-test- += sound/cs35l34.h -header-test- += sound/cs35l35.h -header-test- += sound/cs35l36.h -header-test- += sound/cs4271.h -header-test- += sound/cs42l52.h -header-test- += sound/cs8427.h -header-test- += sound/da7218.h -header-test- += sound/da7219-aad.h -header-test- += sound/da7219.h -header-test- += sound/da9055.h -header-test- += sound/emu8000.h -header-test- += sound/emux_synth.h -header-test- += sound/hda_component.h -header-test- += sound/hda_hwdep.h -header-test- += sound/hda_i915.h -header-test- += sound/hwdep.h -header-test- += sound/i2c.h -header-test- += sound/l3.h -header-test- += sound/max98088.h -header-test- += sound/max98095.h -header-test- += sound/mixer_oss.h -header-test- += sound/omap-hdmi-audio.h -header-test- += sound/pcm_drm_eld.h -header-test- += sound/pcm_iec958.h -header-test- += sound/pcm_oss.h -header-test- += sound/pxa2xx-lib.h -header-test- += sound/rt286.h -header-test- += sound/rt298.h -header-test- += sound/rt5645.h -header-test- += sound/rt5659.h -header-test- += sound/rt5660.h -header-test- += sound/rt5665.h -header-test- += sound/rt5670.h -header-test- += sound/s3c24xx_uda134x.h -header-test- += sound/seq_device.h -header-test- += sound/seq_kernel.h -header-test- += sound/seq_midi_emul.h -header-test- += sound/seq_oss.h -header-test- += sound/soc-acpi-intel-match.h -header-test- += sound/soc-dai.h -header-test- += sound/soc-dapm.h -header-test- += sound/soc-dpcm.h -header-test- += sound/sof/control.h -header-test- += sound/sof/dai-intel.h -header-test- += sound/sof/dai.h -header-test- += sound/sof/header.h -header-test- += sound/sof/info.h -header-test- += sound/sof/pm.h -header-test- += sound/sof/stream.h -header-test- += sound/sof/topology.h -header-test- += sound/sof/trace.h -header-test- += sound/sof/xtensa.h -header-test- += sound/spear_spdif.h -header-test- += sound/sta32x.h -header-test- += sound/sta350.h -header-test- += sound/tea6330t.h -header-test- += sound/tlv320aic32x4.h -header-test- += sound/tlv320dac33-plat.h -header-test- += sound/uda134x.h -header-test- += sound/wavefront.h -header-test- += sound/wm8903.h -header-test- += sound/wm8904.h -header-test- += sound/wm8960.h -header-test- += sound/wm8962.h -header-test- += sound/wm8993.h -header-test- += sound/wm8996.h -header-test- += sound/wm9081.h -header-test- += sound/wm9090.h -header-test- += target/iscsi/iscsi_target_stat.h -header-test- += trace/bpf_probe.h -header-test- += trace/events/9p.h -header-test- += trace/events/afs.h -header-test- += trace/events/asoc.h -header-test- += trace/events/bcache.h -header-test- += trace/events/block.h -header-test- += trace/events/cachefiles.h -header-test- += trace/events/cgroup.h -header-test- += trace/events/clk.h -header-test- += trace/events/cma.h -header-test- += trace/events/ext4.h -header-test- += trace/events/f2fs.h -header-test- += trace/events/fs_dax.h -header-test- += trace/events/fscache.h -header-test- += trace/events/fsi.h -header-test- += trace/events/fsi_master_ast_cf.h -header-test- += trace/events/fsi_master_gpio.h -header-test- += trace/events/huge_memory.h -header-test- += trace/events/ib_mad.h -header-test- += trace/events/ib_umad.h -header-test- += trace/events/iscsi.h -header-test- += trace/events/jbd2.h -header-test- += trace/events/kvm.h -header-test- += trace/events/kyber.h -header-test- += trace/events/libata.h -header-test- += trace/events/mce.h -header-test- += trace/events/mdio.h -header-test- += trace/events/migrate.h -header-test- += trace/events/mmflags.h -header-test- += trace/events/nbd.h -header-test- += trace/events/nilfs2.h -header-test- += trace/events/pwc.h -header-test- += trace/events/rdma.h -header-test- += trace/events/rpcgss.h -header-test- += trace/events/rpcrdma.h -header-test- += trace/events/rxrpc.h -header-test- += trace/events/scsi.h -header-test- += trace/events/siox.h -header-test- += trace/events/spi.h -header-test- += trace/events/swiotlb.h -header-test- += trace/events/syscalls.h -header-test- += trace/events/target.h -header-test- += trace/events/thermal_power_allocator.h -header-test- += trace/events/timer.h -header-test- += trace/events/wbt.h -header-test- += trace/events/xen.h -header-test- += trace/perf.h -header-test- += trace/trace_events.h -header-test- += uapi/drm/vmwgfx_drm.h -header-test- += uapi/linux/a.out.h -header-test- += uapi/linux/coda.h -header-test- += uapi/linux/coda_psdev.h -header-test- += uapi/linux/errqueue.h -header-test- += uapi/linux/eventpoll.h -header-test- += uapi/linux/hdlc/ioctl.h -header-test- += uapi/linux/input.h -header-test- += uapi/linux/kvm.h -header-test- += uapi/linux/kvm_para.h -header-test- += uapi/linux/lightnvm.h -header-test- += uapi/linux/mic_common.h -header-test- += uapi/linux/mman.h -header-test- += uapi/linux/nilfs2_ondisk.h -header-test- += uapi/linux/patchkey.h -header-test- += uapi/linux/ptrace.h -header-test- += uapi/linux/scc.h -header-test- += uapi/linux/seg6_iptunnel.h -header-test- += uapi/linux/smc_diag.h -header-test- += uapi/linux/timex.h -header-test- += uapi/linux/videodev2.h -header-test- += uapi/scsi/scsi_bsg_fc.h -header-test- += uapi/sound/asound.h -header-test- += uapi/sound/sof/eq.h -header-test- += uapi/sound/sof/fw.h -header-test- += uapi/sound/sof/header.h -header-test- += uapi/sound/sof/manifest.h -header-test- += uapi/sound/sof/trace.h -header-test- += uapi/xen/evtchn.h -header-test- += uapi/xen/gntdev.h -header-test- += uapi/xen/privcmd.h -header-test- += vdso/vsyscall.h -header-test- += video/broadsheetfb.h -header-test- += video/cvisionppc.h -header-test- += video/gbe.h -header-test- += video/kyro.h -header-test- += video/maxinefb.h -header-test- += video/metronomefb.h -header-test- += video/neomagic.h -header-test- += video/of_display_timing.h -header-test- += video/omapvrfb.h -header-test- += video/s1d13xxxfb.h -header-test- += video/sstfb.h -header-test- += video/tgafb.h -header-test- += video/udlfb.h -header-test- += video/uvesafb.h -header-test- += video/vga.h -header-test- += video/w100fb.h -header-test- += xen/acpi.h -header-test- += xen/arm/hypercall.h -header-test- += xen/arm/page-coherent.h -header-test- += xen/arm/page.h -header-test- += xen/balloon.h -header-test- += xen/events.h -header-test- += xen/features.h -header-test- += xen/grant_table.h -header-test- += xen/hvm.h -header-test- += xen/interface/callback.h -header-test- += xen/interface/event_channel.h -header-test- += xen/interface/grant_table.h -header-test- += xen/interface/hvm/dm_op.h -header-test- += xen/interface/hvm/hvm_op.h -header-test- += xen/interface/hvm/hvm_vcpu.h -header-test- += xen/interface/hvm/params.h -header-test- += xen/interface/hvm/start_info.h -header-test- += xen/interface/io/9pfs.h -header-test- += xen/interface/io/blkif.h -header-test- += xen/interface/io/console.h -header-test- += xen/interface/io/displif.h -header-test- += xen/interface/io/fbif.h -header-test- += xen/interface/io/kbdif.h -header-test- += xen/interface/io/netif.h -header-test- += xen/interface/io/pciif.h -header-test- += xen/interface/io/protocols.h -header-test- += xen/interface/io/pvcalls.h -header-test- += xen/interface/io/ring.h -header-test- += xen/interface/io/sndif.h -header-test- += xen/interface/io/tpmif.h -header-test- += xen/interface/io/vscsiif.h -header-test- += xen/interface/io/xs_wire.h -header-test- += xen/interface/memory.h -header-test- += xen/interface/nmi.h -header-test- += xen/interface/physdev.h -header-test- += xen/interface/platform.h -header-test- += xen/interface/sched.h -header-test- += xen/interface/vcpu.h -header-test- += xen/interface/version.h -header-test- += xen/interface/xen-mca.h -header-test- += xen/interface/xen.h -header-test- += xen/interface/xenpmu.h -header-test- += xen/mem-reservation.h -header-test- += xen/page.h -header-test- += xen/platform_pci.h -header-test- += xen/swiotlb-xen.h -header-test- += xen/xen-front-pgdir-shbuf.h -header-test- += xen/xen-ops.h -header-test- += xen/xen.h -header-test- += xen/xenbus.h - -# Do not include directly -header-test- += linux/compiler-clang.h -header-test- += linux/compiler-gcc.h -header-test- += linux/patchkey.h -header-test- += linux/rwlock_api_smp.h -header-test- += linux/spinlock_types_up.h -header-test- += linux/spinlock_up.h -header-test- += linux/wimax/debug.h -header-test- += rdma/uverbs_named_ioctl.h - -# asm-generic/*.h is used by asm/*.h, and should not be included directly -header-test- += asm-generic/% uapi/asm-generic/% - -# Timestamp files touched by Kconfig -header-test- += config/% - -# Timestamp files touched by scripts/adjust_autoksyms.sh -header-test- += ksym/% - -# You could compile-test these, but maybe not so useful... -header-test- += dt-bindings/% - -# Do not test generated headers. Stale headers are often left over when you -# traverse the git history without cleaning. -header-test- += generated/% - -# The rest are compile-tested -header-test-pattern-y += */*.h */*/*.h */*/*/*.h */*/*/*/*.h diff --git a/init/Kconfig b/init/Kconfig index b4daad2bac23..8d1667fc4415 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -104,29 +104,9 @@ config COMPILE_TEST here. If you are a user/distributor, say N here to exclude useless drivers to be distributed. -config HEADER_TEST - bool "Compile test headers that should be standalone compilable" - help - Compile test headers listed in header-test-y target to ensure they are - self-contained, i.e. compilable as standalone units. - - If you are a developer or tester and want to ensure the requested - headers are self-contained, say Y here. Otherwise, choose N. - -config KERNEL_HEADER_TEST - bool "Compile test kernel headers" - depends on HEADER_TEST - help - Headers in include/ are used to build external moduls. - Compile test them to ensure they are self-contained, i.e. - compilable as standalone units. - - If you are a developer or tester and want to ensure the headers - in include/ are self-contained, say Y here. Otherwise, choose N. - config UAPI_HEADER_TEST bool "Compile test UAPI headers" - depends on HEADER_TEST && HEADERS_INSTALL && CC_CAN_LINK + depends on HEADERS_INSTALL && CC_CAN_LINK help Compile test headers exported to user-space to ensure they are self-contained, i.e. compilable as standalone units. diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 7eabbb66a65c..b734ac8a654e 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -283,15 +283,6 @@ quiet_cmd_cc_lst_c = MKLST $@ $(obj)/%.lst: $(src)/%.c FORCE $(call if_changed_dep,cc_lst_c) -# header test (header-test-y, header-test-m target) -# --------------------------------------------------------------------------- - -quiet_cmd_cc_s_h = CC $@ - cmd_cc_s_h = $(CC) $(c_flags) -S -o $@ -x c /dev/null -include $< - -$(obj)/%.h.s: $(src)/%.h FORCE - $(call if_changed_dep,cc_s_h) - # Compile assembler sources (.S) # --------------------------------------------------------------------------- diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index 179d55af5852..3fa32f83b2d7 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -65,20 +65,6 @@ extra-y += $(patsubst %.dtb,%.dt.yaml, $(dtb-y)) extra-$(CONFIG_OF_ALL_DTBS) += $(patsubst %.dtb,%.dt.yaml, $(dtb-)) endif -# Test self-contained headers - -# Wildcard searches in $(srctree)/$(src)/, but not in $(objtree)/$(obj)/. -# Stale generated headers are often left over, so pattern matching should -# be avoided. Please notice $(srctree)/$(src)/ and $(objtree)/$(obj) point -# to the same location for in-tree building. So, header-test-pattern-y should -# be used with care. -header-test-y += $(filter-out $(header-test-), \ - $(patsubst $(srctree)/$(src)/%, %, \ - $(wildcard $(addprefix $(srctree)/$(src)/, \ - $(header-test-pattern-y))))) - -extra-$(CONFIG_HEADER_TEST) += $(addsuffix .s, $(header-test-y) $(header-test-m)) - # Add subdir path extra-y := $(addprefix $(obj)/,$(extra-y)) diff --git a/usr/include/Makefile b/usr/include/Makefile index 3e1adab089a4..325f4d0f2e73 100644 --- a/usr/include/Makefile +++ b/usr/include/Makefile @@ -95,9 +95,13 @@ endif # asm-generic/*.h is used by asm/*.h, and should not be included directly header-test- += asm-generic/% -# The rest are compile-tested -header-test-y += $(filter-out $(header-test-), \ - $(patsubst $(obj)/%,%, $(wildcard \ - $(addprefix $(obj)/, *.h */*.h */*/*.h */*/*/*.h)))) +extra-y := $(patsubst %.h,%.hdrtest, $(filter-out $(header-test-), \ + $(patsubst $(obj)/%,%, $(shell find $(obj) -name '*.h')))) + +quiet_cmd_hdrtest = HDRTEST $< + cmd_hdrtest = $(CC) $(c_flags) -S -o /dev/null -x c /dev/null -include $<; touch $@ + +$(obj)/%.hdrtest: $(obj)/%.h FORCE + $(call if_changed_dep,hdrtest) clean-files += $(filter-out Makefile, $(notdir $(wildcard $(obj)/*))) -- cgit v1.2.3 From 020003f763e24e4ed0bb3d8909f3940891536d5d Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Thu, 14 Nov 2019 08:25:28 -0800 Subject: bus: ti-sysc: Add module enable quirk for audio AESS We must set the autogating bit on enable for AESS (Audio Engine SubSystem) when probed with ti-sysc interconnect target module driver. Otherwise it won't idle properly. Cc: Peter Ujfalusi Tested-by: Peter Ujfalusi Signed-off-by: Tony Lindgren --- drivers/bus/ti-sysc.c | 14 +++++++++++++- include/linux/platform_data/ti-sysc.h | 1 + 2 files changed, 14 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index 97b85493aa43..99d7356e245b 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -1242,6 +1242,8 @@ static const struct sysc_revision_quirk sysc_revision_quirks[] = { SYSC_QUIRK_SWSUP_SIDLE), /* Quirks that need to be set based on detected module */ + SYSC_QUIRK("aess", 0, 0, 0x10, -1, 0x40000000, 0xffffffff, + SYSC_MODULE_QUIRK_AESS), SYSC_QUIRK("hdq1w", 0, 0, 0x14, 0x18, 0x00000006, 0xffffffff, SYSC_MODULE_QUIRK_HDQ1W), SYSC_QUIRK("hdq1w", 0, 0, 0x14, 0x18, 0x0000000a, 0xffffffff, @@ -1270,7 +1272,6 @@ static const struct sysc_revision_quirk sysc_revision_quirks[] = { #ifdef DEBUG SYSC_QUIRK("adc", 0, 0, 0x10, -1, 0x47300001, 0xffffffff, 0), SYSC_QUIRK("atl", 0, 0, -1, -1, 0x0a070100, 0xffffffff, 0), - SYSC_QUIRK("aess", 0, 0, 0x10, -1, 0x40000000, 0xffffffff, 0), SYSC_QUIRK("cm", 0, 0, -1, -1, 0x40000301, 0xffffffff, 0), SYSC_QUIRK("control", 0, 0, 0x10, -1, 0x40000900, 0xffffffff, 0), SYSC_QUIRK("cpgmac", 0, 0x1200, 0x1208, 0x1204, 0x4edb1902, @@ -1402,6 +1403,14 @@ static void sysc_clk_enable_quirk_hdq1w(struct sysc *ddata) sysc_write(ddata, offset, val); } +/* AESS (Audio Engine SubSystem) needs autogating set after enable */ +static void sysc_module_enable_quirk_aess(struct sysc *ddata) +{ + int offset = 0x7c; /* AESS_AUTO_GATING_ENABLE */ + + sysc_write(ddata, offset, 1); +} + /* I2C needs extra enable bit toggling for reset */ static void sysc_clk_quirk_i2c(struct sysc *ddata, bool enable) { @@ -1484,6 +1493,9 @@ static void sysc_init_module_quirks(struct sysc *ddata) return; } + if (ddata->cfg.quirks & SYSC_MODULE_QUIRK_AESS) + ddata->module_enable_quirk = sysc_module_enable_quirk_aess; + if (ddata->cfg.quirks & SYSC_MODULE_QUIRK_SGX) ddata->module_enable_quirk = sysc_module_enable_quirk_sgx; diff --git a/include/linux/platform_data/ti-sysc.h b/include/linux/platform_data/ti-sysc.h index b5b7a3423ca8..0b9380475144 100644 --- a/include/linux/platform_data/ti-sysc.h +++ b/include/linux/platform_data/ti-sysc.h @@ -49,6 +49,7 @@ struct sysc_regbits { s8 emufree_shift; }; +#define SYSC_MODULE_QUIRK_AESS BIT(19) #define SYSC_MODULE_QUIRK_SGX BIT(18) #define SYSC_MODULE_QUIRK_HDQ1W BIT(17) #define SYSC_MODULE_QUIRK_I2C BIT(16) -- cgit v1.2.3 From d41efb522e902364ab09c782d511c1bedc388ddd Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 4 Nov 2019 22:30:52 -0500 Subject: fs/namei.c: pull positivity check into follow_managed() There are 4 callers; two proceed to check if result is positive and fail with ENOENT if it isn't; one (in handle_lookup_down()) is guaranteed to yield positive and one (in lookup_fast()) is _preceded_ by positivity check. However, follow_managed() on a negative dentry is a (fairly cheap) no-op on anything other than autofs. And negative autofs dentries are never hashed, so lookup_fast() is not going to run into one of those. Moreover, successful follow_managed() on a _positive_ dentry never yields a negative one (and we significantly rely upon that in callers of lookup_fast()). In other words, we can easily transpose the positivity check and the call of follow_managed() in lookup_fast(). And that allows to fold the positivity check *into* follow_managed(), simplifying life for the code downstream of its calls. Signed-off-by: Al Viro --- fs/namei.c | 34 +++++++++++----------------------- include/linux/dcache.h | 5 +++++ 2 files changed, 16 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/fs/namei.c b/fs/namei.c index 671c3c1a3425..ef55155d152f 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1206,25 +1206,25 @@ static int follow_automount(struct path *path, struct nameidata *nd, * - Flagged as automount point * * This may only be called in refwalk mode. + * On success path->dentry is known positive. * * Serialization is taken care of in namespace.c */ static int follow_managed(struct path *path, struct nameidata *nd) { struct vfsmount *mnt = path->mnt; /* held by caller, must be left alone */ - unsigned managed; + unsigned flags; bool need_mntput = false; int ret = 0; /* Given that we're not holding a lock here, we retain the value in a * local variable for each dentry as we look at it so that we don't see * the components of that value change under us */ - while (managed = READ_ONCE(path->dentry->d_flags), - managed &= DCACHE_MANAGED_DENTRY, - unlikely(managed != 0)) { + while (flags = READ_ONCE(path->dentry->d_flags), + unlikely(flags & DCACHE_MANAGED_DENTRY)) { /* Allow the filesystem to manage the transit without i_mutex * being held. */ - if (managed & DCACHE_MANAGE_TRANSIT) { + if (flags & DCACHE_MANAGE_TRANSIT) { BUG_ON(!path->dentry->d_op); BUG_ON(!path->dentry->d_op->d_manage); ret = path->dentry->d_op->d_manage(path, false); @@ -1233,7 +1233,7 @@ static int follow_managed(struct path *path, struct nameidata *nd) } /* Transit to a mounted filesystem. */ - if (managed & DCACHE_MOUNTED) { + if (flags & DCACHE_MOUNTED) { struct vfsmount *mounted = lookup_mnt(path); if (mounted) { dput(path->dentry); @@ -1252,7 +1252,7 @@ static int follow_managed(struct path *path, struct nameidata *nd) } /* Handle an automount point */ - if (managed & DCACHE_NEED_AUTOMOUNT) { + if (flags & DCACHE_NEED_AUTOMOUNT) { ret = follow_automount(path, nd, &need_mntput); if (ret < 0) break; @@ -1265,10 +1265,12 @@ static int follow_managed(struct path *path, struct nameidata *nd) if (need_mntput && path->mnt == mnt) mntput(path->mnt); - if (ret == -EISDIR || !ret) - ret = 1; if (need_mntput) nd->flags |= LOOKUP_JUMPED; + if (ret == -EISDIR || !ret) + ret = 1; + if (ret > 0 && unlikely(d_flags_negative(flags))) + ret = -ENOENT; if (unlikely(ret < 0)) path_put_conditional(path, nd); return ret; @@ -1617,10 +1619,6 @@ static int lookup_fast(struct nameidata *nd, dput(dentry); return status; } - if (unlikely(d_is_negative(dentry))) { - dput(dentry); - return -ENOENT; - } path->mnt = mnt; path->dentry = dentry; @@ -1807,11 +1805,6 @@ static int walk_component(struct nameidata *nd, int flags) if (unlikely(err < 0)) return err; - if (unlikely(d_is_negative(path.dentry))) { - path_to_nameidata(&path, nd); - return -ENOENT; - } - seq = 0; /* we are already out of RCU mode */ inode = d_backing_inode(path.dentry); } @@ -3352,11 +3345,6 @@ static int do_last(struct nameidata *nd, if (unlikely(error < 0)) return error; - if (unlikely(d_is_negative(path.dentry))) { - path_to_nameidata(&path, nd); - return -ENOENT; - } - /* * create/update audit record if it already exists. */ diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 10090f11ab95..c1488cc84fd9 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -440,6 +440,11 @@ static inline bool d_is_negative(const struct dentry *dentry) return d_is_miss(dentry); } +static inline bool d_flags_negative(unsigned flags) +{ + return (flags & DCACHE_ENTRY_TYPE) == DCACHE_MISS_TYPE; +} + static inline bool d_is_positive(const struct dentry *dentry) { return !d_is_negative(dentry); -- cgit v1.2.3 From 6c2d4798a8d16cf4f3a28c3cd4af4f1dcbbb4d04 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 31 Oct 2019 01:21:58 -0400 Subject: new helper: lookup_positive_unlocked() Most of the callers of lookup_one_len_unlocked() treat negatives are ERR_PTR(-ENOENT). Provide a helper that would do just that. Note that a pinned positive dentry remains positive - it's ->d_inode is stable, etc.; a pinned _negative_ dentry can become positive at any point as long as you are not holding its parent at least shared. So using lookup_one_len_unlocked() needs to be careful; lookup_positive_unlocked() is safer and that's what the callers end up open-coding anyway. Signed-off-by: Al Viro --- fs/cifs/cifsfs.c | 7 +------ fs/debugfs/inode.c | 6 +----- fs/kernfs/mount.c | 2 +- fs/namei.c | 20 ++++++++++++++++++++ fs/nfsd/nfs3xdr.c | 4 +--- fs/nfsd/nfs4xdr.c | 11 +---------- fs/overlayfs/namei.c | 24 ++++++++---------------- fs/quota/dquot.c | 7 +------ include/linux/namei.h | 1 + 9 files changed, 35 insertions(+), 47 deletions(-) (limited to 'include') diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index c049c7b3aa87..8c8600e53339 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -719,11 +719,6 @@ cifs_get_root(struct smb_vol *vol, struct super_block *sb) struct inode *dir = d_inode(dentry); struct dentry *child; - if (!dir) { - dput(dentry); - dentry = ERR_PTR(-ENOENT); - break; - } if (!S_ISDIR(dir->i_mode)) { dput(dentry); dentry = ERR_PTR(-ENOTDIR); @@ -740,7 +735,7 @@ cifs_get_root(struct smb_vol *vol, struct super_block *sb) while (*s && *s != sep) s++; - child = lookup_one_len_unlocked(p, dentry, s - p); + child = lookup_positive_unlocked(p, dentry, s - p); dput(dentry); dentry = child; } while (!IS_ERR(dentry)); diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 7b975dbb2bb4..f4d8df5e4714 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -299,13 +299,9 @@ struct dentry *debugfs_lookup(const char *name, struct dentry *parent) if (!parent) parent = debugfs_mount->mnt_root; - dentry = lookup_one_len_unlocked(name, parent, strlen(name)); + dentry = lookup_positive_unlocked(name, parent, strlen(name)); if (IS_ERR(dentry)) return NULL; - if (!d_really_is_positive(dentry)) { - dput(dentry); - return NULL; - } return dentry; } EXPORT_SYMBOL_GPL(debugfs_lookup); diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index 6c12fac2c287..d62cec6d838d 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -200,7 +200,7 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn, dput(dentry); return ERR_PTR(-EINVAL); } - dtmp = lookup_one_len_unlocked(kntmp->name, dentry, + dtmp = lookup_positive_unlocked(kntmp->name, dentry, strlen(kntmp->name)); dput(dentry); if (IS_ERR(dtmp)) diff --git a/fs/namei.c b/fs/namei.c index ef55155d152f..6f72fb7ef5ad 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2557,6 +2557,26 @@ struct dentry *lookup_one_len_unlocked(const char *name, } EXPORT_SYMBOL(lookup_one_len_unlocked); +/* + * Like lookup_one_len_unlocked(), except that it yields ERR_PTR(-ENOENT) + * on negatives. Returns known positive or ERR_PTR(); that's what + * most of the users want. Note that pinned negative with unlocked parent + * _can_ become positive at any time, so callers of lookup_one_len_unlocked() + * need to be very careful; pinned positives have ->d_inode stable, so + * this one avoids such problems. + */ +struct dentry *lookup_positive_unlocked(const char *name, + struct dentry *base, int len) +{ + struct dentry *ret = lookup_one_len_unlocked(name, base, len); + if (!IS_ERR(ret) && d_is_negative(ret)) { + dput(ret); + ret = ERR_PTR(-ENOENT); + } + return ret; +} +EXPORT_SYMBOL(lookup_positive_unlocked); + #ifdef CONFIG_UNIX98_PTYS int path_pts(struct path *path) { diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 86e5658651f1..195ab7a0fc89 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -863,13 +863,11 @@ compose_entry_fh(struct nfsd3_readdirres *cd, struct svc_fh *fhp, } else dchild = dget(dparent); } else - dchild = lookup_one_len_unlocked(name, dparent, namlen); + dchild = lookup_positive_unlocked(name, dparent, namlen); if (IS_ERR(dchild)) return rv; if (d_mountpoint(dchild)) goto out; - if (d_really_is_negative(dchild)) - goto out; if (dchild->d_inode->i_ino != ino) goto out; rv = fh_compose(fhp, exp, dchild, &cd->fh); diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 533d0fc3c96b..b09237431ae2 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -2991,18 +2991,9 @@ nfsd4_encode_dirent_fattr(struct xdr_stream *xdr, struct nfsd4_readdir *cd, __be32 nfserr; int ignore_crossmnt = 0; - dentry = lookup_one_len_unlocked(name, cd->rd_fhp->fh_dentry, namlen); + dentry = lookup_positive_unlocked(name, cd->rd_fhp->fh_dentry, namlen); if (IS_ERR(dentry)) return nfserrno(PTR_ERR(dentry)); - if (d_really_is_negative(dentry)) { - /* - * we're not holding the i_mutex here, so there's - * a window where this directory entry could have gone - * away. - */ - dput(dentry); - return nfserr_noent; - } exp_get(exp); /* diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index e9717c2f7d45..c269d6033525 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -200,7 +200,7 @@ static int ovl_lookup_single(struct dentry *base, struct ovl_lookup_data *d, int err; bool last_element = !post[0]; - this = lookup_one_len_unlocked(name, base, namelen); + this = lookup_positive_unlocked(name, base, namelen); if (IS_ERR(this)) { err = PTR_ERR(this); this = NULL; @@ -208,8 +208,6 @@ static int ovl_lookup_single(struct dentry *base, struct ovl_lookup_data *d, goto out; goto out_err; } - if (!this->d_inode) - goto put_and_out; if (ovl_dentry_weird(this)) { /* Don't support traversing automounts and other weirdness */ @@ -651,7 +649,7 @@ struct dentry *ovl_get_index_fh(struct ovl_fs *ofs, struct ovl_fh *fh) if (err) return ERR_PTR(err); - index = lookup_one_len_unlocked(name.name, ofs->indexdir, name.len); + index = lookup_positive_unlocked(name.name, ofs->indexdir, name.len); kfree(name.name); if (IS_ERR(index)) { if (PTR_ERR(index) == -ENOENT) @@ -659,9 +657,7 @@ struct dentry *ovl_get_index_fh(struct ovl_fs *ofs, struct ovl_fh *fh) return index; } - if (d_is_negative(index)) - err = 0; - else if (ovl_is_whiteout(index)) + if (ovl_is_whiteout(index)) err = -ESTALE; else if (ovl_dentry_weird(index)) err = -EIO; @@ -685,7 +681,7 @@ struct dentry *ovl_lookup_index(struct ovl_fs *ofs, struct dentry *upper, if (err) return ERR_PTR(err); - index = lookup_one_len_unlocked(name.name, ofs->indexdir, name.len); + index = lookup_positive_unlocked(name.name, ofs->indexdir, name.len); if (IS_ERR(index)) { err = PTR_ERR(index); if (err == -ENOENT) { @@ -700,9 +696,7 @@ struct dentry *ovl_lookup_index(struct ovl_fs *ofs, struct dentry *upper, } inode = d_inode(index); - if (d_is_negative(index)) { - goto out_dput; - } else if (ovl_is_whiteout(index) && !verify) { + if (ovl_is_whiteout(index) && !verify) { /* * When index lookup is called with !verify for decoding an * overlay file handle, a whiteout index implies that decode @@ -1131,7 +1125,7 @@ bool ovl_lower_positive(struct dentry *dentry) struct dentry *this; struct dentry *lowerdir = poe->lowerstack[i].dentry; - this = lookup_one_len_unlocked(name->name, lowerdir, + this = lookup_positive_unlocked(name->name, lowerdir, name->len); if (IS_ERR(this)) { switch (PTR_ERR(this)) { @@ -1148,10 +1142,8 @@ bool ovl_lower_positive(struct dentry *dentry) break; } } else { - if (this->d_inode) { - positive = !ovl_is_whiteout(this); - done = true; - } + positive = !ovl_is_whiteout(this); + done = true; dput(this); } } diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 6e826b454082..a37e1b117721 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -2507,15 +2507,10 @@ int dquot_quota_on_mount(struct super_block *sb, char *qf_name, struct dentry *dentry; int error; - dentry = lookup_one_len_unlocked(qf_name, sb->s_root, strlen(qf_name)); + dentry = lookup_positive_unlocked(qf_name, sb->s_root, strlen(qf_name)); if (IS_ERR(dentry)) return PTR_ERR(dentry); - if (d_really_is_negative(dentry)) { - error = -ENOENT; - goto out; - } - error = security_quota_on(dentry); if (!error) error = vfs_load_quota_inode(d_inode(dentry), type, format_id, diff --git a/include/linux/namei.h b/include/linux/namei.h index 397a08ade6a2..7fe7b87a3ded 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -60,6 +60,7 @@ extern int kern_path_mountpoint(int, const char *, struct path *, unsigned int); extern struct dentry *try_lookup_one_len(const char *, struct dentry *, int); extern struct dentry *lookup_one_len(const char *, struct dentry *, int); extern struct dentry *lookup_one_len_unlocked(const char *, struct dentry *, int); +extern struct dentry *lookup_positive_unlocked(const char *, struct dentry *, int); extern int follow_down_one(struct path *); extern int follow_down(struct path *); -- cgit v1.2.3 From d46bca2b5d06cbb5f3e66945080f275bcfab7181 Mon Sep 17 00:00:00 2001 From: Lina Iyer Date: Fri, 15 Nov 2019 15:11:44 -0700 Subject: irqdomain: Add bus token DOMAIN_BUS_WAKEUP A single controller can handle normal interrupts and wake-up interrupts independently, with a different numbering space. It is thus crucial to allow the driver for such a controller discriminate between the two. A simple way to do so is to tag the wake-up irqdomain with a "bus token" that indicates the wake-up domain. This slightly abuses the notion of bus, but also radically simplifies the design of such a driver. Between two evils, we choose the least damaging. Suggested-by: Stephen Boyd Signed-off-by: Lina Iyer Signed-off-by: Marc Zyngier Reviewed-by: Stephen Boyd Link: https://lore.kernel.org/r/1573855915-9841-2-git-send-email-ilina@codeaurora.org --- include/linux/irqdomain.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 583e7abd07f9..3c340dbc5a1f 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -83,6 +83,7 @@ enum irq_domain_bus_token { DOMAIN_BUS_IPI, DOMAIN_BUS_FSL_MC_MSI, DOMAIN_BUS_TI_SCI_INTA_MSI, + DOMAIN_BUS_WAKEUP, }; /** -- cgit v1.2.3 From 4a169a95d885fe5c050bac1a21d43c86ba955bcf Mon Sep 17 00:00:00 2001 From: Maulik Shah Date: Fri, 15 Nov 2019 15:11:49 -0700 Subject: genirq: Introduce irq_chip_get/set_parent_state calls On certain QTI chipsets some GPIOs are direct-connect interrupts to the GIC to be used as regular interrupt lines. When the GPIOs are not used for interrupt generation the interrupt line is disabled. But disabling the interrupt at GIC does not prevent the interrupt to be reported as pending at GIC_ISPEND. Later, when drivers call enable_irq() on the interrupt, an unwanted interrupt occurs. Introduce get and set methods for irqchip's parent to clear it's pending irq state. This then can be invoked by the GPIO interrupt controller on the parents in it hierarchy to clear the interrupt before enabling the interrupt. Signed-off-by: Maulik Shah Signed-off-by: Lina Iyer Signed-off-by: Marc Zyngier Reviewed-by: Stephen Boyd Link: https://lore.kernel.org/r/1573855915-9841-7-git-send-email-ilina@codeaurora.org [updated commit text and minor code fixes] --- include/linux/irq.h | 6 ++++++ kernel/irq/chip.c | 44 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 50 insertions(+) (limited to 'include') diff --git a/include/linux/irq.h b/include/linux/irq.h index fb301cf29148..7853eb9301f2 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -610,6 +610,12 @@ extern int irq_chip_pm_put(struct irq_data *data); #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY extern void handle_fasteoi_ack_irq(struct irq_desc *desc); extern void handle_fasteoi_mask_irq(struct irq_desc *desc); +extern int irq_chip_set_parent_state(struct irq_data *data, + enum irqchip_irq_state which, + bool val); +extern int irq_chip_get_parent_state(struct irq_data *data, + enum irqchip_irq_state which, + bool *state); extern void irq_chip_enable_parent(struct irq_data *data); extern void irq_chip_disable_parent(struct irq_data *data); extern void irq_chip_ack_parent(struct irq_data *data); diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index b76703b2c0af..b3fa2d87d2f3 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -1297,6 +1297,50 @@ EXPORT_SYMBOL_GPL(handle_fasteoi_mask_irq); #endif /* CONFIG_IRQ_FASTEOI_HIERARCHY_HANDLERS */ +/** + * irq_chip_set_parent_state - set the state of a parent interrupt. + * + * @data: Pointer to interrupt specific data + * @which: State to be restored (one of IRQCHIP_STATE_*) + * @val: Value corresponding to @which + * + * Conditional success, if the underlying irqchip does not implement it. + */ +int irq_chip_set_parent_state(struct irq_data *data, + enum irqchip_irq_state which, + bool val) +{ + data = data->parent_data; + + if (!data || !data->chip->irq_set_irqchip_state) + return 0; + + return data->chip->irq_set_irqchip_state(data, which, val); +} +EXPORT_SYMBOL_GPL(irq_chip_set_parent_state); + +/** + * irq_chip_get_parent_state - get the state of a parent interrupt. + * + * @data: Pointer to interrupt specific data + * @which: one of IRQCHIP_STATE_* the caller wants to know + * @state: a pointer to a boolean where the state is to be stored + * + * Conditional success, if the underlying irqchip does not implement it. + */ +int irq_chip_get_parent_state(struct irq_data *data, + enum irqchip_irq_state which, + bool *state) +{ + data = data->parent_data; + + if (!data || !data->chip->irq_get_irqchip_state) + return 0; + + return data->chip->irq_get_irqchip_state(data, which, state); +} +EXPORT_SYMBOL_GPL(irq_chip_get_parent_state); + /** * irq_chip_enable_parent - Enable the parent interrupt (defaults to unmask if * NULL) -- cgit v1.2.3 From 81ef8bf88065b07d597c723ca5b0f1f10a808de4 Mon Sep 17 00:00:00 2001 From: Lina Iyer Date: Fri, 15 Nov 2019 15:11:47 -0700 Subject: irqchip/qcom-pdc: Add irqdomain for wakeup capable GPIOs Introduce a new domain for wakeup capable GPIOs. The domain can be requested using the bus token DOMAIN_BUS_WAKEUP. In the following patches, we will specify PDC as the wakeup-parent for the TLMM GPIO irqchip. Requesting a wakeup GPIO will setup the GPIO and the corresponding PDC interrupt as its parent. Co-developed-by: Stephen Boyd Signed-off-by: Stephen Boyd Signed-off-by: Lina Iyer Signed-off-by: Marc Zyngier Reviewed-by: Stephen Boyd Link: https://lore.kernel.org/r/1573855915-9841-5-git-send-email-ilina@codeaurora.org --- drivers/irqchip/qcom-pdc.c | 104 +++++++++++++++++++++++++++++++++++++++---- include/linux/soc/qcom/irq.h | 21 +++++++++ 2 files changed, 116 insertions(+), 9 deletions(-) create mode 100644 include/linux/soc/qcom/irq.h (limited to 'include') diff --git a/drivers/irqchip/qcom-pdc.c b/drivers/irqchip/qcom-pdc.c index 527c29e212bd..4f2c76229fb7 100644 --- a/drivers/irqchip/qcom-pdc.c +++ b/drivers/irqchip/qcom-pdc.c @@ -13,12 +13,13 @@ #include #include #include +#include #include -#include #include #include #define PDC_MAX_IRQS 168 +#define PDC_MAX_GPIO_IRQS 256 #define CLEAR_INTR(reg, intr) (reg & ~(1 << intr)) #define ENABLE_INTR(reg, intr) (reg | (1 << intr)) @@ -26,6 +27,8 @@ #define IRQ_ENABLE_BANK 0x10 #define IRQ_i_CFG 0x110 +#define PDC_NO_PARENT_IRQ ~0UL + struct pdc_pin_region { u32 pin_base; u32 parent_base; @@ -65,23 +68,35 @@ static void pdc_enable_intr(struct irq_data *d, bool on) static void qcom_pdc_gic_disable(struct irq_data *d) { + if (d->hwirq == GPIO_NO_WAKE_IRQ) + return; + pdc_enable_intr(d, false); irq_chip_disable_parent(d); } static void qcom_pdc_gic_enable(struct irq_data *d) { + if (d->hwirq == GPIO_NO_WAKE_IRQ) + return; + pdc_enable_intr(d, true); irq_chip_enable_parent(d); } static void qcom_pdc_gic_mask(struct irq_data *d) { + if (d->hwirq == GPIO_NO_WAKE_IRQ) + return; + irq_chip_mask_parent(d); } static void qcom_pdc_gic_unmask(struct irq_data *d) { + if (d->hwirq == GPIO_NO_WAKE_IRQ) + return; + irq_chip_unmask_parent(d); } @@ -124,6 +139,9 @@ static int qcom_pdc_gic_set_type(struct irq_data *d, unsigned int type) int pin_out = d->hwirq; enum pdc_irq_config_bits pdc_type; + if (pin_out == GPIO_NO_WAKE_IRQ) + return 0; + switch (type) { case IRQ_TYPE_EDGE_RISING: pdc_type = PDC_EDGE_RISING; @@ -181,8 +199,7 @@ static irq_hw_number_t get_parent_hwirq(int pin) return (region->parent_base + pin - region->pin_base); } - WARN_ON(1); - return ~0UL; + return PDC_NO_PARENT_IRQ; } static int qcom_pdc_translate(struct irq_domain *d, struct irq_fwspec *fwspec, @@ -211,17 +228,17 @@ static int qcom_pdc_alloc(struct irq_domain *domain, unsigned int virq, ret = qcom_pdc_translate(domain, fwspec, &hwirq, &type); if (ret) - return -EINVAL; - - parent_hwirq = get_parent_hwirq(hwirq); - if (parent_hwirq == ~0UL) - return -EINVAL; + return ret; ret = irq_domain_set_hwirq_and_chip(domain, virq, hwirq, &qcom_pdc_gic_chip, NULL); if (ret) return ret; + parent_hwirq = get_parent_hwirq(hwirq); + if (parent_hwirq == PDC_NO_PARENT_IRQ) + return 0; + if (type & IRQ_TYPE_EDGE_BOTH) type = IRQ_TYPE_EDGE_RISING; @@ -244,6 +261,60 @@ static const struct irq_domain_ops qcom_pdc_ops = { .free = irq_domain_free_irqs_common, }; +static int qcom_pdc_gpio_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *data) +{ + struct irq_fwspec *fwspec = data; + struct irq_fwspec parent_fwspec; + irq_hw_number_t hwirq, parent_hwirq; + unsigned int type; + int ret; + + ret = qcom_pdc_translate(domain, fwspec, &hwirq, &type); + if (ret) + return ret; + + ret = irq_domain_set_hwirq_and_chip(domain, virq, hwirq, + &qcom_pdc_gic_chip, NULL); + if (ret) + return ret; + + if (hwirq == GPIO_NO_WAKE_IRQ) + return 0; + + parent_hwirq = get_parent_hwirq(hwirq); + if (parent_hwirq == PDC_NO_PARENT_IRQ) + return 0; + + if (type & IRQ_TYPE_EDGE_BOTH) + type = IRQ_TYPE_EDGE_RISING; + + if (type & IRQ_TYPE_LEVEL_MASK) + type = IRQ_TYPE_LEVEL_HIGH; + + parent_fwspec.fwnode = domain->parent->fwnode; + parent_fwspec.param_count = 3; + parent_fwspec.param[0] = 0; + parent_fwspec.param[1] = parent_hwirq; + parent_fwspec.param[2] = type; + + return irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, + &parent_fwspec); +} + +static int qcom_pdc_gpio_domain_select(struct irq_domain *d, + struct irq_fwspec *fwspec, + enum irq_domain_bus_token bus_token) +{ + return bus_token == DOMAIN_BUS_WAKEUP; +} + +static const struct irq_domain_ops qcom_pdc_gpio_ops = { + .select = qcom_pdc_gpio_domain_select, + .alloc = qcom_pdc_gpio_alloc, + .free = irq_domain_free_irqs_common, +}; + static int pdc_setup_pin_mapping(struct device_node *np) { int ret, n; @@ -282,7 +353,7 @@ static int pdc_setup_pin_mapping(struct device_node *np) static int qcom_pdc_init(struct device_node *node, struct device_node *parent) { - struct irq_domain *parent_domain, *pdc_domain; + struct irq_domain *parent_domain, *pdc_domain, *pdc_gpio_domain; int ret; pdc_base = of_iomap(node, 0); @@ -313,8 +384,23 @@ static int qcom_pdc_init(struct device_node *node, struct device_node *parent) goto fail; } + pdc_gpio_domain = irq_domain_create_hierarchy(parent_domain, + IRQ_DOMAIN_FLAG_QCOM_PDC_WAKEUP, + PDC_MAX_GPIO_IRQS, + of_fwnode_handle(node), + &qcom_pdc_gpio_ops, NULL); + if (!pdc_gpio_domain) { + pr_err("%pOF: PDC domain add failed for GPIO domain\n", node); + ret = -ENOMEM; + goto remove; + } + + irq_domain_update_bus_token(pdc_gpio_domain, DOMAIN_BUS_WAKEUP); + return 0; +remove: + irq_domain_remove(pdc_domain); fail: kfree(pdc_region); iounmap(pdc_base); diff --git a/include/linux/soc/qcom/irq.h b/include/linux/soc/qcom/irq.h new file mode 100644 index 000000000000..637c0bfa89e7 --- /dev/null +++ b/include/linux/soc/qcom/irq.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __QCOM_IRQ_H +#define __QCOM_IRQ_H + +#include + +#define GPIO_NO_WAKE_IRQ ~0U + +/** + * QCOM specific IRQ domain flags that distinguishes the handling of wakeup + * capable interrupts by different interrupt controllers. + * + * IRQ_DOMAIN_FLAG_QCOM_PDC_WAKEUP: Line must be masked at TLMM and the + * interrupt configuration is done at PDC + * IRQ_DOMAIN_FLAG_QCOM_MPM_WAKEUP: Interrupt configuration is handled at TLMM + */ +#define IRQ_DOMAIN_FLAG_QCOM_PDC_WAKEUP (IRQ_DOMAIN_FLAG_NONCORE << 0) +#define IRQ_DOMAIN_FLAG_QCOM_MPM_WAKEUP (IRQ_DOMAIN_FLAG_NONCORE << 1) + +#endif -- cgit v1.2.3 From e35a6ae0eb3a7cc451e8d8db55e9b938a95de416 Mon Sep 17 00:00:00 2001 From: Lina Iyer Date: Fri, 15 Nov 2019 15:11:51 -0700 Subject: pinctrl/msm: Setup GPIO chip in hierarchy Some GPIOs are marked as wakeup capable and are routed to another interrupt controller that is an always-domain and can detect interrupts even when most of the SoC is powered off. The wakeup interrupt controller wakes up the GIC and replays the interrupt at the GIC. Setup the TLMM irqchip in hierarchy with the wakeup interrupt controller and ensure the wakeup GPIOs are handled correctly. Co-developed-by: Maulik Shah Signed-off-by: Lina Iyer Signed-off-by: Marc Zyngier Reviewed-by: Stephen Boyd Link: https://lore.kernel.org/r/1573855915-9841-9-git-send-email-ilina@codeaurora.org ---- Changes in v2: - Address review comments - Fix Co-developed-by tag Changes in v1: - Address minor review comments - Remove redundant call to set irq handler - Move irq_domain_qcom_handle_wakeup() to this patch Changes in RFC v2: - Rebase on top of GPIO hierarchy support in linux-next - Set the chained irq handler for summary line --- drivers/pinctrl/qcom/pinctrl-msm.c | 112 ++++++++++++++++++++++++++++++++++++- drivers/pinctrl/qcom/pinctrl-msm.h | 14 +++++ include/linux/soc/qcom/irq.h | 13 +++++ 3 files changed, 137 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c index 763da0be10d6..978838464093 100644 --- a/drivers/pinctrl/qcom/pinctrl-msm.c +++ b/drivers/pinctrl/qcom/pinctrl-msm.c @@ -23,6 +23,8 @@ #include #include +#include + #include "../core.h" #include "../pinconf.h" #include "pinctrl-msm.h" @@ -44,6 +46,7 @@ * @enabled_irqs: Bitmap of currently enabled irqs. * @dual_edge_irqs: Bitmap of irqs that need sw emulated dual edge * detection. + * @skip_wake_irqs: Skip IRQs that are handled by wakeup interrupt controller * @soc; Reference to soc_data of platform specific data. * @regs: Base addresses for the TLMM tiles. */ @@ -61,6 +64,7 @@ struct msm_pinctrl { DECLARE_BITMAP(dual_edge_irqs, MAX_NR_GPIO); DECLARE_BITMAP(enabled_irqs, MAX_NR_GPIO); + DECLARE_BITMAP(skip_wake_irqs, MAX_NR_GPIO); const struct msm_pinctrl_soc_data *soc; void __iomem *regs[MAX_NR_TILES]; @@ -707,6 +711,12 @@ static void msm_gpio_irq_mask(struct irq_data *d) unsigned long flags; u32 val; + if (d->parent_data) + irq_chip_mask_parent(d); + + if (test_bit(d->hwirq, pctrl->skip_wake_irqs)) + return; + g = &pctrl->soc->groups[d->hwirq]; raw_spin_lock_irqsave(&pctrl->lock, flags); @@ -751,6 +761,12 @@ static void msm_gpio_irq_clear_unmask(struct irq_data *d, bool status_clear) unsigned long flags; u32 val; + if (d->parent_data) + irq_chip_unmask_parent(d); + + if (test_bit(d->hwirq, pctrl->skip_wake_irqs)) + return; + g = &pctrl->soc->groups[d->hwirq]; raw_spin_lock_irqsave(&pctrl->lock, flags); @@ -778,10 +794,35 @@ static void msm_gpio_irq_clear_unmask(struct irq_data *d, bool status_clear) static void msm_gpio_irq_enable(struct irq_data *d) { + /* + * Clear the interrupt that may be pending before we enable + * the line. + * This is especially a problem with the GPIOs routed to the + * PDC. These GPIOs are direct-connect interrupts to the GIC. + * Disabling the interrupt line at the PDC does not prevent + * the interrupt from being latched at the GIC. The state at + * GIC needs to be cleared before enabling. + */ + if (d->parent_data) { + irq_chip_set_parent_state(d, IRQCHIP_STATE_PENDING, 0); + irq_chip_enable_parent(d); + } msm_gpio_irq_clear_unmask(d, true); } +static void msm_gpio_irq_disable(struct irq_data *d) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct msm_pinctrl *pctrl = gpiochip_get_data(gc); + + if (d->parent_data) + irq_chip_disable_parent(d); + + if (!test_bit(d->hwirq, pctrl->skip_wake_irqs)) + msm_gpio_irq_mask(d); +} + static void msm_gpio_irq_unmask(struct irq_data *d) { msm_gpio_irq_clear_unmask(d, false); @@ -795,6 +836,9 @@ static void msm_gpio_irq_ack(struct irq_data *d) unsigned long flags; u32 val; + if (test_bit(d->hwirq, pctrl->skip_wake_irqs)) + return; + g = &pctrl->soc->groups[d->hwirq]; raw_spin_lock_irqsave(&pctrl->lock, flags); @@ -820,6 +864,12 @@ static int msm_gpio_irq_set_type(struct irq_data *d, unsigned int type) unsigned long flags; u32 val; + if (d->parent_data) + irq_chip_set_type_parent(d, type); + + if (test_bit(d->hwirq, pctrl->skip_wake_irqs)) + return 0; + g = &pctrl->soc->groups[d->hwirq]; raw_spin_lock_irqsave(&pctrl->lock, flags); @@ -912,6 +962,15 @@ static int msm_gpio_irq_set_wake(struct irq_data *d, unsigned int on) struct msm_pinctrl *pctrl = gpiochip_get_data(gc); unsigned long flags; + /* + * While they may not wake up when the TLMM is powered off, + * some GPIOs would like to wakeup the system from suspend + * when TLMM is powered on. To allow that, enable the GPIO + * summary line to be wakeup capable at GIC. + */ + if (d->parent_data) + irq_chip_set_wake_parent(d, on); + raw_spin_lock_irqsave(&pctrl->lock, flags); irq_set_irq_wake(pctrl->irq, on); @@ -990,6 +1049,30 @@ static void msm_gpio_irq_handler(struct irq_desc *desc) chained_irq_exit(chip, desc); } +static int msm_gpio_wakeirq(struct gpio_chip *gc, + unsigned int child, + unsigned int child_type, + unsigned int *parent, + unsigned int *parent_type) +{ + struct msm_pinctrl *pctrl = gpiochip_get_data(gc); + const struct msm_gpio_wakeirq_map *map; + int i; + + *parent = GPIO_NO_WAKE_IRQ; + *parent_type = IRQ_TYPE_EDGE_RISING; + + for (i = 0; i < pctrl->soc->nwakeirq_map; i++) { + map = &pctrl->soc->wakeirq_map[i]; + if (map->gpio == child) { + *parent = map->wakeirq; + break; + } + } + + return 0; +} + static bool msm_gpio_needs_valid_mask(struct msm_pinctrl *pctrl) { if (pctrl->soc->reserved_gpios) @@ -1002,8 +1085,10 @@ static int msm_gpio_init(struct msm_pinctrl *pctrl) { struct gpio_chip *chip; struct gpio_irq_chip *girq; - int ret; - unsigned ngpio = pctrl->soc->ngpios; + int i, ret; + unsigned gpio, ngpio = pctrl->soc->ngpios; + struct device_node *np; + bool skip; if (WARN_ON(ngpio > MAX_NR_GPIO)) return -EINVAL; @@ -1020,17 +1105,40 @@ static int msm_gpio_init(struct msm_pinctrl *pctrl) pctrl->irq_chip.name = "msmgpio"; pctrl->irq_chip.irq_enable = msm_gpio_irq_enable; + pctrl->irq_chip.irq_disable = msm_gpio_irq_disable; pctrl->irq_chip.irq_mask = msm_gpio_irq_mask; pctrl->irq_chip.irq_unmask = msm_gpio_irq_unmask; pctrl->irq_chip.irq_ack = msm_gpio_irq_ack; + pctrl->irq_chip.irq_eoi = irq_chip_eoi_parent; pctrl->irq_chip.irq_set_type = msm_gpio_irq_set_type; pctrl->irq_chip.irq_set_wake = msm_gpio_irq_set_wake; pctrl->irq_chip.irq_request_resources = msm_gpio_irq_reqres; pctrl->irq_chip.irq_release_resources = msm_gpio_irq_relres; + np = of_parse_phandle(pctrl->dev->of_node, "wakeup-parent", 0); + if (np) { + chip->irq.parent_domain = irq_find_matching_host(np, + DOMAIN_BUS_WAKEUP); + of_node_put(np); + if (!chip->irq.parent_domain) + return -EPROBE_DEFER; + chip->irq.child_to_parent_hwirq = msm_gpio_wakeirq; + + /* + * Let's skip handling the GPIOs, if the parent irqchip + * is handling the direct connect IRQ of the GPIO. + */ + skip = irq_domain_qcom_handle_wakeup(chip->irq.parent_domain); + for (i = 0; skip && i < pctrl->soc->nwakeirq_map; i++) { + gpio = pctrl->soc->wakeirq_map[i].gpio; + set_bit(gpio, pctrl->skip_wake_irqs); + } + } + girq = &chip->irq; girq->chip = &pctrl->irq_chip; girq->parent_handler = msm_gpio_irq_handler; + girq->fwnode = pctrl->dev->fwnode; girq->num_parents = 1; girq->parents = devm_kcalloc(pctrl->dev, 1, sizeof(*girq->parents), GFP_KERNEL); diff --git a/drivers/pinctrl/qcom/pinctrl-msm.h b/drivers/pinctrl/qcom/pinctrl-msm.h index 48569cda8471..9452da18a78b 100644 --- a/drivers/pinctrl/qcom/pinctrl-msm.h +++ b/drivers/pinctrl/qcom/pinctrl-msm.h @@ -91,6 +91,16 @@ struct msm_pingroup { unsigned intr_detection_width:5; }; +/** + * struct msm_gpio_wakeirq_map - Map of GPIOs and their wakeup pins + * @gpio: The GPIOs that are wakeup capable + * @wakeirq: The interrupt at the always-on interrupt controller + */ +struct msm_gpio_wakeirq_map { + unsigned int gpio; + unsigned int wakeirq; +}; + /** * struct msm_pinctrl_soc_data - Qualcomm pin controller driver configuration * @pins: An array describing all pins the pin controller affects. @@ -101,6 +111,8 @@ struct msm_pingroup { * @ngroups: The numbmer of entries in @groups. * @ngpio: The number of pingroups the driver should expose as GPIOs. * @pull_no_keeper: The SoC does not support keeper bias. + * @wakeirq_map: The map of wakeup capable GPIOs and the pin at PDC/MPM + * @nwakeirq_map: The number of entries in @wakeirq_map */ struct msm_pinctrl_soc_data { const struct pinctrl_pin_desc *pins; @@ -114,6 +126,8 @@ struct msm_pinctrl_soc_data { const char *const *tiles; unsigned int ntiles; const int *reserved_gpios; + const struct msm_gpio_wakeirq_map *wakeirq_map; + unsigned int nwakeirq_map; }; extern const struct dev_pm_ops msm_pinctrl_dev_pm_ops; diff --git a/include/linux/soc/qcom/irq.h b/include/linux/soc/qcom/irq.h index 637c0bfa89e7..9e1ece58e55b 100644 --- a/include/linux/soc/qcom/irq.h +++ b/include/linux/soc/qcom/irq.h @@ -18,4 +18,17 @@ #define IRQ_DOMAIN_FLAG_QCOM_PDC_WAKEUP (IRQ_DOMAIN_FLAG_NONCORE << 0) #define IRQ_DOMAIN_FLAG_QCOM_MPM_WAKEUP (IRQ_DOMAIN_FLAG_NONCORE << 1) +/** + * irq_domain_qcom_handle_wakeup: Return if the domain handles interrupt + * configuration + * @d: irq domain + * + * This QCOM specific irq domain call returns if the interrupt controller + * requires the interrupt be masked at the child interrupt controller. + */ +static inline bool irq_domain_qcom_handle_wakeup(const struct irq_domain *d) +{ + return (d->flags & IRQ_DOMAIN_FLAG_QCOM_PDC_WAKEUP); +} + #endif -- cgit v1.2.3 From 9e8d42a0f7eb9056f8bdb241b91738b5a2923f4c Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Fri, 8 Nov 2019 18:35:53 +0100 Subject: percpu-refcount: Use normal instead of RCU-sched" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This is a revert of commit a4244454df129 ("percpu-refcount: use RCU-sched insted of normal RCU") which claims the only reason for using RCU-sched is "rcu_read_[un]lock() … are slightly more expensive than preempt_disable/enable()" and "As the RCU critical sections are extremely short, using sched-RCU shouldn't have any latency implications." The problem with using RCU-sched here is that it disables preemption and the release callback (called from percpu_ref_put_many()) must not acquire any sleeping locks like spinlock_t. This breaks PREEMPT_RT because some of the users acquire spinlock_t locks in their callbacks. Using rcu_read_lock() on PREEMPTION=n kernels is not any different compared to rcu_read_lock_sched(). On PREEMPTION=y kernels there are already performance issues due to additional preemption points. Looking at the code, the rcu_read_lock() is just an increment and unlock is almost just a decrement unless there is something special to do. Both are functions while disabling preemption is inlined. Doing a small benchmark, the minimal amount of time required was mostly the same. The average time required was higher due to the higher MAX value (which could be preemption). With DEBUG_PREEMPT=y it is rcu_read_lock_sched() that takes a little longer due to the additional debug code. Convert back to normal RCU. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Dennis Zhou --- include/linux/percpu-refcount.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h index 7aef0abc194a..390031e816dc 100644 --- a/include/linux/percpu-refcount.h +++ b/include/linux/percpu-refcount.h @@ -186,14 +186,14 @@ static inline void percpu_ref_get_many(struct percpu_ref *ref, unsigned long nr) { unsigned long __percpu *percpu_count; - rcu_read_lock_sched(); + rcu_read_lock(); if (__ref_is_percpu(ref, &percpu_count)) this_cpu_add(*percpu_count, nr); else atomic_long_add(nr, &ref->count); - rcu_read_unlock_sched(); + rcu_read_unlock(); } /** @@ -223,7 +223,7 @@ static inline bool percpu_ref_tryget(struct percpu_ref *ref) unsigned long __percpu *percpu_count; bool ret; - rcu_read_lock_sched(); + rcu_read_lock(); if (__ref_is_percpu(ref, &percpu_count)) { this_cpu_inc(*percpu_count); @@ -232,7 +232,7 @@ static inline bool percpu_ref_tryget(struct percpu_ref *ref) ret = atomic_long_inc_not_zero(&ref->count); } - rcu_read_unlock_sched(); + rcu_read_unlock(); return ret; } @@ -257,7 +257,7 @@ static inline bool percpu_ref_tryget_live(struct percpu_ref *ref) unsigned long __percpu *percpu_count; bool ret = false; - rcu_read_lock_sched(); + rcu_read_lock(); if (__ref_is_percpu(ref, &percpu_count)) { this_cpu_inc(*percpu_count); @@ -266,7 +266,7 @@ static inline bool percpu_ref_tryget_live(struct percpu_ref *ref) ret = atomic_long_inc_not_zero(&ref->count); } - rcu_read_unlock_sched(); + rcu_read_unlock(); return ret; } @@ -285,14 +285,14 @@ static inline void percpu_ref_put_many(struct percpu_ref *ref, unsigned long nr) { unsigned long __percpu *percpu_count; - rcu_read_lock_sched(); + rcu_read_lock(); if (__ref_is_percpu(ref, &percpu_count)) this_cpu_sub(*percpu_count, nr); else if (unlikely(atomic_long_sub_and_test(nr, &ref->count))) ref->release(ref); - rcu_read_unlock_sched(); + rcu_read_unlock(); } /** -- cgit v1.2.3 From 5ca470a0c3886b80ec13c3a19e9aae4c2f469202 Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Fri, 4 Oct 2019 10:39:55 -0600 Subject: docs: Add request_irq() documentation While checking the results of the :c:func: removal, I noticed that there was no documentation for request_irq(), and request_threaded_irq() was not mentioned at all. Add a kerneldoc comment for request_irq() and add request_threaded_irq() to the list of functions. Reviewed-by: Thomas Gleixner Signed-off-by: Jonathan Corbet --- Documentation/core-api/genericirq.rst | 2 ++ include/linux/interrupt.h | 13 +++++++++++++ 2 files changed, 15 insertions(+) (limited to 'include') diff --git a/Documentation/core-api/genericirq.rst b/Documentation/core-api/genericirq.rst index 2e6c99e3ce3b..8f06d885c310 100644 --- a/Documentation/core-api/genericirq.rst +++ b/Documentation/core-api/genericirq.rst @@ -127,6 +127,8 @@ The high-level Driver API consists of following functions: - request_irq() +- request_threaded_irq() + - free_irq() - disable_irq() diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 89fc59dab57d..ba873ec7e09d 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -140,6 +140,19 @@ request_threaded_irq(unsigned int irq, irq_handler_t handler, irq_handler_t thread_fn, unsigned long flags, const char *name, void *dev); +/** + * request_irq - Add a handler for an interrupt line + * @irq: The interrupt line to allocate + * @handler: Function to be called when the IRQ occurs. + * Primary handler for threaded interrupts + * If NULL, the default primary handler is installed + * @flags: Handling flags + * @name: Name of the device generating this interrupt + * @dev: A cookie passed to the handler function + * + * This call allocates an interrupt and establishes a handler; see + * the documentation for request_threaded_irq() for details. + */ static inline int __must_check request_irq(unsigned int irq, irq_handler_t handler, unsigned long flags, const char *name, void *dev) -- cgit v1.2.3 From 3c4d77b68928df6c2bf07f4c3ba8e5d5e490bf4e Mon Sep 17 00:00:00 2001 From: Nick Crews Date: Thu, 24 Oct 2019 16:28:05 -0600 Subject: platform/chrome: wilco_ec: Add charging config driver Add a device to control the charging algorithm used on Wilco devices, which will be picked up by the drivers/power/supply/wilco-charger.c driver. See Documentation/ABI/testing/sysfs-class-power-wilco for the userspace interface and other info. Signed-off-by: Nick Crews Signed-off-by: Enric Balletbo i Serra --- drivers/platform/chrome/wilco_ec/core.c | 15 ++++++++++++++- include/linux/platform_data/wilco-ec.h | 2 ++ 2 files changed, 16 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/platform/chrome/wilco_ec/core.c b/drivers/platform/chrome/wilco_ec/core.c index 3724bf4b77c6..9a438ebae3ed 100644 --- a/drivers/platform/chrome/wilco_ec/core.c +++ b/drivers/platform/chrome/wilco_ec/core.c @@ -93,6 +93,16 @@ static int wilco_ec_probe(struct platform_device *pdev) goto unregister_rtc; } + /* Register child device to be found by charger config driver. */ + ec->charger_pdev = platform_device_register_data(dev, "wilco-charger", + PLATFORM_DEVID_AUTO, + NULL, 0); + if (IS_ERR(ec->charger_pdev)) { + dev_err(dev, "Failed to create charger platform device\n"); + ret = PTR_ERR(ec->charger_pdev); + goto remove_sysfs; + } + /* Register child device that will be found by the telemetry driver. */ ec->telem_pdev = platform_device_register_data(dev, "wilco_telem", PLATFORM_DEVID_AUTO, @@ -100,11 +110,13 @@ static int wilco_ec_probe(struct platform_device *pdev) if (IS_ERR(ec->telem_pdev)) { dev_err(dev, "Failed to create telemetry platform device\n"); ret = PTR_ERR(ec->telem_pdev); - goto remove_sysfs; + goto unregister_charge_config; } return 0; +unregister_charge_config: + platform_device_unregister(ec->charger_pdev); remove_sysfs: wilco_ec_remove_sysfs(ec); unregister_rtc: @@ -120,6 +132,7 @@ static int wilco_ec_remove(struct platform_device *pdev) { struct wilco_ec_device *ec = platform_get_drvdata(pdev); + platform_device_unregister(ec->charger_pdev); wilco_ec_remove_sysfs(ec); platform_device_unregister(ec->telem_pdev); platform_device_unregister(ec->rtc_pdev); diff --git a/include/linux/platform_data/wilco-ec.h b/include/linux/platform_data/wilco-ec.h index ad03b586a095..0d104e780632 100644 --- a/include/linux/platform_data/wilco-ec.h +++ b/include/linux/platform_data/wilco-ec.h @@ -29,6 +29,7 @@ * @data_size: Size of the data buffer used for EC communication. * @debugfs_pdev: The child platform_device used by the debugfs sub-driver. * @rtc_pdev: The child platform_device used by the RTC sub-driver. + * @charger_pdev: Child platform_device used by the charger config sub-driver. * @telem_pdev: The child platform_device used by the telemetry sub-driver. */ struct wilco_ec_device { @@ -41,6 +42,7 @@ struct wilco_ec_device { size_t data_size; struct platform_device *debugfs_pdev; struct platform_device *rtc_pdev; + struct platform_device *charger_pdev; struct platform_device *telem_pdev; }; -- cgit v1.2.3 From 119a3cb6d687259f2be333351c1c5d634204e68b Mon Sep 17 00:00:00 2001 From: Daniel Campello Date: Wed, 6 Nov 2019 09:33:19 -0700 Subject: platform/chrome: wilco_ec: Add keyboard backlight LED support The EC is in charge of controlling the keyboard backlight on the Wilco platform. We expose a standard LED class device named platform::kbd_backlight. Since the EC will never change the backlight level of its own accord, we don't need to implement a brightness_get() method. Signed-off-by: Nick Crews Signed-off-by: Daniel Campello Reviewed-by: Daniel Campello Signed-off-by: Enric Balletbo i Serra --- drivers/platform/chrome/wilco_ec/Kconfig | 2 +- drivers/platform/chrome/wilco_ec/Makefile | 3 +- drivers/platform/chrome/wilco_ec/core.c | 13 +- drivers/platform/chrome/wilco_ec/keyboard_leds.c | 191 +++++++++++++++++++++++ include/linux/platform_data/wilco-ec.h | 13 ++ 5 files changed, 216 insertions(+), 6 deletions(-) create mode 100644 drivers/platform/chrome/wilco_ec/keyboard_leds.c (limited to 'include') diff --git a/drivers/platform/chrome/wilco_ec/Kconfig b/drivers/platform/chrome/wilco_ec/Kconfig index 89007b0bc743..365f30e116ee 100644 --- a/drivers/platform/chrome/wilco_ec/Kconfig +++ b/drivers/platform/chrome/wilco_ec/Kconfig @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only config WILCO_EC tristate "ChromeOS Wilco Embedded Controller" - depends on ACPI && X86 && CROS_EC_LPC + depends on ACPI && X86 && CROS_EC_LPC && LEDS_CLASS help If you say Y here, you get support for talking to the ChromeOS Wilco EC over an eSPI bus. This uses a simple byte-level protocol diff --git a/drivers/platform/chrome/wilco_ec/Makefile b/drivers/platform/chrome/wilco_ec/Makefile index bc817164596e..ecb3145cab18 100644 --- a/drivers/platform/chrome/wilco_ec/Makefile +++ b/drivers/platform/chrome/wilco_ec/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 -wilco_ec-objs := core.o mailbox.o properties.o sysfs.o +wilco_ec-objs := core.o keyboard_leds.o mailbox.o \ + properties.o sysfs.o obj-$(CONFIG_WILCO_EC) += wilco_ec.o wilco_ec_debugfs-objs := debugfs.o obj-$(CONFIG_WILCO_EC_DEBUGFS) += wilco_ec_debugfs.o diff --git a/drivers/platform/chrome/wilco_ec/core.c b/drivers/platform/chrome/wilco_ec/core.c index 9a438ebae3ed..5210c357feef 100644 --- a/drivers/platform/chrome/wilco_ec/core.c +++ b/drivers/platform/chrome/wilco_ec/core.c @@ -5,10 +5,6 @@ * Copyright 2018 Google LLC * * This is the entry point for the drivers that control the Wilco EC. - * This driver is responsible for several tasks: - * - Initialize the register interface that is used by wilco_ec_mailbox() - * - Create a platform device which is picked up by the debugfs driver - * - Create a platform device which is picked up by the RTC driver */ #include @@ -87,6 +83,15 @@ static int wilco_ec_probe(struct platform_device *pdev) goto unregister_debugfs; } + /* Set up the keyboard backlight LEDs. */ + ret = wilco_keyboard_leds_init(ec); + if (ret < 0) { + dev_err(dev, + "Failed to initialize keyboard LEDs: %d\n", + ret); + goto unregister_rtc; + } + ret = wilco_ec_add_sysfs(ec); if (ret < 0) { dev_err(dev, "Failed to create sysfs entries: %d", ret); diff --git a/drivers/platform/chrome/wilco_ec/keyboard_leds.c b/drivers/platform/chrome/wilco_ec/keyboard_leds.c new file mode 100644 index 000000000000..bb0edf51dfda --- /dev/null +++ b/drivers/platform/chrome/wilco_ec/keyboard_leds.c @@ -0,0 +1,191 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Keyboard backlight LED driver for the Wilco Embedded Controller + * + * Copyright 2019 Google LLC + * + * Since the EC will never change the backlight level of its own accord, + * we don't need to implement a brightness_get() method. + */ + +#include +#include +#include +#include +#include + +#define WILCO_EC_COMMAND_KBBL 0x75 +#define WILCO_KBBL_MODE_FLAG_PWM BIT(1) /* Set brightness by percent. */ +#define WILCO_KBBL_DEFAULT_BRIGHTNESS 0 + +struct wilco_keyboard_leds { + struct wilco_ec_device *ec; + struct led_classdev keyboard; +}; + +enum wilco_kbbl_subcommand { + WILCO_KBBL_SUBCMD_GET_FEATURES = 0x00, + WILCO_KBBL_SUBCMD_GET_STATE = 0x01, + WILCO_KBBL_SUBCMD_SET_STATE = 0x02, +}; + +/** + * struct wilco_keyboard_leds_msg - Message to/from EC for keyboard LED control. + * @command: Always WILCO_EC_COMMAND_KBBL. + * @status: Set by EC to 0 on success, 0xFF on failure. + * @subcmd: One of enum wilco_kbbl_subcommand. + * @reserved3: Should be 0. + * @mode: Bit flags for used mode, we want to use WILCO_KBBL_MODE_FLAG_PWM. + * @reserved5to8: Should be 0. + * @percent: Brightness in 0-100. Only meaningful in PWM mode. + * @reserved10to15: Should be 0. + */ +struct wilco_keyboard_leds_msg { + u8 command; + u8 status; + u8 subcmd; + u8 reserved3; + u8 mode; + u8 reserved5to8[4]; + u8 percent; + u8 reserved10to15[6]; +} __packed; + +/* Send a request, get a response, and check that the response is good. */ +static int send_kbbl_msg(struct wilco_ec_device *ec, + struct wilco_keyboard_leds_msg *request, + struct wilco_keyboard_leds_msg *response) +{ + struct wilco_ec_message msg; + int ret; + + memset(&msg, 0, sizeof(msg)); + msg.type = WILCO_EC_MSG_LEGACY; + msg.request_data = request; + msg.request_size = sizeof(*request); + msg.response_data = response; + msg.response_size = sizeof(*response); + + ret = wilco_ec_mailbox(ec, &msg); + if (ret < 0) { + dev_err(ec->dev, + "Failed sending keyboard LEDs command: %d", ret); + return ret; + } + + if (response->status) { + dev_err(ec->dev, + "EC reported failure sending keyboard LEDs command: %d", + response->status); + return -EIO; + } + + return 0; +} + +static int set_kbbl(struct wilco_ec_device *ec, enum led_brightness brightness) +{ + struct wilco_keyboard_leds_msg request; + struct wilco_keyboard_leds_msg response; + + memset(&request, 0, sizeof(request)); + request.command = WILCO_EC_COMMAND_KBBL; + request.subcmd = WILCO_KBBL_SUBCMD_SET_STATE; + request.mode = WILCO_KBBL_MODE_FLAG_PWM; + request.percent = brightness; + + return send_kbbl_msg(ec, &request, &response); +} + +static int kbbl_exist(struct wilco_ec_device *ec, bool *exists) +{ + struct wilco_keyboard_leds_msg request; + struct wilco_keyboard_leds_msg response; + int ret; + + memset(&request, 0, sizeof(request)); + request.command = WILCO_EC_COMMAND_KBBL; + request.subcmd = WILCO_KBBL_SUBCMD_GET_FEATURES; + + ret = send_kbbl_msg(ec, &request, &response); + if (ret < 0) + return ret; + + *exists = response.status != 0xFF; + + return 0; +} + +/** + * kbbl_init() - Initialize the state of the keyboard backlight. + * @ec: EC device to talk to. + * + * Gets the current brightness, ensuring that the BIOS already initialized the + * backlight to PWM mode. If not in PWM mode, then the current brightness is + * meaningless, so set the brightness to WILCO_KBBL_DEFAULT_BRIGHTNESS. + * + * Return: Final brightness of the keyboard, or negative error code on failure. + */ +static int kbbl_init(struct wilco_ec_device *ec) +{ + struct wilco_keyboard_leds_msg request; + struct wilco_keyboard_leds_msg response; + int ret; + + memset(&request, 0, sizeof(request)); + request.command = WILCO_EC_COMMAND_KBBL; + request.subcmd = WILCO_KBBL_SUBCMD_GET_STATE; + + ret = send_kbbl_msg(ec, &request, &response); + if (ret < 0) + return ret; + + if (response.mode & WILCO_KBBL_MODE_FLAG_PWM) + return response.percent; + + ret = set_kbbl(ec, WILCO_KBBL_DEFAULT_BRIGHTNESS); + if (ret < 0) + return ret; + + return WILCO_KBBL_DEFAULT_BRIGHTNESS; +} + +static int wilco_keyboard_leds_set(struct led_classdev *cdev, + enum led_brightness brightness) +{ + struct wilco_keyboard_leds *wkl = + container_of(cdev, struct wilco_keyboard_leds, keyboard); + return set_kbbl(wkl->ec, brightness); +} + +int wilco_keyboard_leds_init(struct wilco_ec_device *ec) +{ + struct wilco_keyboard_leds *wkl; + bool leds_exist; + int ret; + + ret = kbbl_exist(ec, &leds_exist); + if (ret < 0) { + dev_err(ec->dev, + "Failed checking keyboard LEDs support: %d", ret); + return ret; + } + if (!leds_exist) + return 0; + + wkl = devm_kzalloc(ec->dev, sizeof(*wkl), GFP_KERNEL); + if (!wkl) + return -ENOMEM; + + wkl->ec = ec; + wkl->keyboard.name = "platform::kbd_backlight"; + wkl->keyboard.max_brightness = 100; + wkl->keyboard.flags = LED_CORE_SUSPENDRESUME; + wkl->keyboard.brightness_set_blocking = wilco_keyboard_leds_set; + ret = kbbl_init(ec); + if (ret < 0) + return ret; + wkl->keyboard.brightness = ret; + + return devm_led_classdev_register(ec->dev, &wkl->keyboard); +} diff --git a/include/linux/platform_data/wilco-ec.h b/include/linux/platform_data/wilco-ec.h index 0d104e780632..afede15a95bf 100644 --- a/include/linux/platform_data/wilco-ec.h +++ b/include/linux/platform_data/wilco-ec.h @@ -122,6 +122,19 @@ struct wilco_ec_message { */ int wilco_ec_mailbox(struct wilco_ec_device *ec, struct wilco_ec_message *msg); +/** + * wilco_keyboard_leds_init() - Set up the keyboard backlight LEDs. + * @ec: EC device to query. + * + * After this call, the keyboard backlight will be exposed through a an LED + * device at /sys/class/leds. + * + * This may sleep because it uses wilco_ec_mailbox(). + * + * Return: 0 on success, negative error code on failure. + */ +int wilco_keyboard_leds_init(struct wilco_ec_device *ec); + /* * A Property is typically a data item that is stored to NVRAM * by the EC. Each of these data items has an index associated -- cgit v1.2.3 From e9d3009cb936bd0faf0719f68d98ad8afb1e613b Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Wed, 13 Nov 2019 14:05:08 -0800 Subject: scsi: target: iscsi: Wait for all commands to finish before freeing a session The iSCSI target driver is the only target driver that does not wait for ongoing commands to finish before freeing a session. Make the iSCSI target driver wait for ongoing commands to finish before freeing a session. This patch fixes the following KASAN complaint: BUG: KASAN: use-after-free in __lock_acquire+0xb1a/0x2710 Read of size 8 at addr ffff8881154eca70 by task kworker/0:2/247 CPU: 0 PID: 247 Comm: kworker/0:2 Not tainted 5.4.0-rc1-dbg+ #6 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-1 04/01/2014 Workqueue: target_completion target_complete_ok_work [target_core_mod] Call Trace: dump_stack+0x8a/0xd6 print_address_description.constprop.0+0x40/0x60 __kasan_report.cold+0x1b/0x33 kasan_report+0x16/0x20 __asan_load8+0x58/0x90 __lock_acquire+0xb1a/0x2710 lock_acquire+0xd3/0x200 _raw_spin_lock_irqsave+0x43/0x60 target_release_cmd_kref+0x162/0x7f0 [target_core_mod] target_put_sess_cmd+0x2e/0x40 [target_core_mod] lio_check_stop_free+0x12/0x20 [iscsi_target_mod] transport_cmd_check_stop_to_fabric+0xd8/0xe0 [target_core_mod] target_complete_ok_work+0x1b0/0x790 [target_core_mod] process_one_work+0x549/0xa40 worker_thread+0x7a/0x5d0 kthread+0x1bc/0x210 ret_from_fork+0x24/0x30 Allocated by task 889: save_stack+0x23/0x90 __kasan_kmalloc.constprop.0+0xcf/0xe0 kasan_slab_alloc+0x12/0x20 kmem_cache_alloc+0xf6/0x360 transport_alloc_session+0x29/0x80 [target_core_mod] iscsi_target_login_thread+0xcd6/0x18f0 [iscsi_target_mod] kthread+0x1bc/0x210 ret_from_fork+0x24/0x30 Freed by task 1025: save_stack+0x23/0x90 __kasan_slab_free+0x13a/0x190 kasan_slab_free+0x12/0x20 kmem_cache_free+0x146/0x400 transport_free_session+0x179/0x2f0 [target_core_mod] transport_deregister_session+0x130/0x180 [target_core_mod] iscsit_close_session+0x12c/0x350 [iscsi_target_mod] iscsit_logout_post_handler+0x136/0x380 [iscsi_target_mod] iscsit_response_queue+0x8de/0xbe0 [iscsi_target_mod] iscsi_target_tx_thread+0x27f/0x370 [iscsi_target_mod] kthread+0x1bc/0x210 ret_from_fork+0x24/0x30 The buggy address belongs to the object at ffff8881154ec9c0 which belongs to the cache se_sess_cache of size 352 The buggy address is located 176 bytes inside of 352-byte region [ffff8881154ec9c0, ffff8881154ecb20) The buggy address belongs to the page: page:ffffea0004553b00 refcount:1 mapcount:0 mapping:ffff888101755400 index:0x0 compound_mapcount: 0 flags: 0x2fff000000010200(slab|head) raw: 2fff000000010200 dead000000000100 dead000000000122 ffff888101755400 raw: 0000000000000000 0000000080130013 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff8881154ec900: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff8881154ec980: fc fc fc fc fc fc fc fc fb fb fb fb fb fb fb fb >ffff8881154eca00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff8881154eca80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8881154ecb00: fb fb fb fb fc fc fc fc fc fc fc fc fc fc fc fc Cc: Mike Christie Link: https://lore.kernel.org/r/20191113220508.198257-3-bvanassche@acm.org Reviewed-by: Roman Bolshakov Signed-off-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- drivers/target/iscsi/iscsi_target.c | 10 ++++++++-- include/scsi/iscsi_proto.h | 1 + 2 files changed, 9 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index 09e55ea0bf5d..7251a87bb576 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -1165,7 +1165,9 @@ int iscsit_setup_scsi_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd, hdr->cmdsn, be32_to_cpu(hdr->data_length), payload_length, conn->cid); - target_get_sess_cmd(&cmd->se_cmd, true); + if (target_get_sess_cmd(&cmd->se_cmd, true) < 0) + return iscsit_add_reject_cmd(cmd, + ISCSI_REASON_WAITING_FOR_LOGOUT, buf); cmd->sense_reason = transport_lookup_cmd_lun(&cmd->se_cmd, scsilun_to_int(&hdr->lun)); @@ -2002,7 +2004,9 @@ iscsit_handle_task_mgt_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd, conn->sess->se_sess, 0, DMA_NONE, TCM_SIMPLE_TAG, cmd->sense_buffer + 2); - target_get_sess_cmd(&cmd->se_cmd, true); + if (target_get_sess_cmd(&cmd->se_cmd, true) < 0) + return iscsit_add_reject_cmd(cmd, + ISCSI_REASON_WAITING_FOR_LOGOUT, buf); /* * TASK_REASSIGN for ERL=2 / connection stays inside of @@ -4230,6 +4234,8 @@ int iscsit_close_connection( * must wait until they have completed. */ iscsit_check_conn_usage_count(conn); + target_sess_cmd_list_set_waiting(sess->se_sess); + target_wait_for_sess_cmds(sess->se_sess); ahash_request_free(conn->conn_tx_hash); if (conn->conn_rx_hash) { diff --git a/include/scsi/iscsi_proto.h b/include/scsi/iscsi_proto.h index b71b5c4f418c..533f56733ba8 100644 --- a/include/scsi/iscsi_proto.h +++ b/include/scsi/iscsi_proto.h @@ -627,6 +627,7 @@ struct iscsi_reject { #define ISCSI_REASON_BOOKMARK_INVALID 9 #define ISCSI_REASON_BOOKMARK_NO_RESOURCES 10 #define ISCSI_REASON_NEGOTIATION_RESET 11 +#define ISCSI_REASON_WAITING_FOR_LOGOUT 12 /* Max. number of Key=Value pairs in a text message */ #define MAX_KEY_VALUE_PAIRS 8192 -- cgit v1.2.3 From ec11e5c213cc20cac5e8310728b06793448b9f6d Mon Sep 17 00:00:00 2001 From: Jon Derrick Date: Tue, 12 Nov 2019 05:47:53 -0700 Subject: PCI: vmd: Add device id for VMD device 8086:9A0B This patch adds support for this VMD device which supports the bus restriction mode. Signed-off-by: Jon Derrick Signed-off-by: Lorenzo Pieralisi --- drivers/pci/controller/vmd.c | 2 ++ include/linux/pci_ids.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include') diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c index 15302a17ee3f..6bff95115d28 100644 --- a/drivers/pci/controller/vmd.c +++ b/drivers/pci/controller/vmd.c @@ -868,6 +868,8 @@ static const struct pci_device_id vmd_ids[] = { {PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_VMD_28C0), .driver_data = VMD_FEAT_HAS_MEMBAR_SHADOW | VMD_FEAT_HAS_BUS_RESTRICTIONS,}, + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_VMD_9A0B), + .driver_data = VMD_FEAT_HAS_BUS_RESTRICTIONS,}, {0,} }; MODULE_DEVICE_TABLE(pci, vmd_ids); diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 21a572469a4e..2302d133af6f 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -3006,6 +3006,7 @@ #define PCI_DEVICE_ID_INTEL_84460GX 0x84ea #define PCI_DEVICE_ID_INTEL_IXP4XX 0x8500 #define PCI_DEVICE_ID_INTEL_IXP2800 0x9004 +#define PCI_DEVICE_ID_INTEL_VMD_9A0B 0x9a0b #define PCI_DEVICE_ID_INTEL_S21152BB 0xb152 #define PCI_VENDOR_ID_SCALEMP 0x8686 -- cgit v1.2.3 From 331f63457165a30c708280de2c77f1742c6351dc Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 30 Oct 2019 17:30:57 -0500 Subject: PCI: of: Add inbound resource parsing to helpers Extend devm_of_pci_get_host_bridge_resources() and pci_parse_request_of_pci_ranges() helpers to also parse the inbound addresses from DT 'dma-ranges' and populate a resource list with the translated addresses. This will help ensure 'dma-ranges' is always parsed in a consistent way. Tested-by: Srinath Mannam Tested-by: Thomas Petazzoni # for AArdvark Signed-off-by: Rob Herring Signed-off-by: Lorenzo Pieralisi Reviewed-by: Srinath Mannam Reviewed-by: Andrew Murray Acked-by: Gustavo Pimentel Cc: Jingoo Han Cc: Gustavo Pimentel Cc: Lorenzo Pieralisi Cc: Bjorn Helgaas Cc: Thomas Petazzoni Cc: Will Deacon Cc: Linus Walleij Cc: Toan Le Cc: Ley Foon Tan Cc: Tom Joseph Cc: Ray Jui Cc: Scott Branden Cc: bcm-kernel-feedback-list@broadcom.com Cc: Ryder Lee Cc: Karthikeyan Mitran Cc: Hou Zhiqiang Cc: Simon Horman Cc: Shawn Lin Cc: Heiko Stuebner Cc: Michal Simek Cc: rfi@lists.rocketboards.org Cc: linux-mediatek@lists.infradead.org Cc: linux-renesas-soc@vger.kernel.org Cc: linux-rockchip@lists.infradead.org --- drivers/pci/controller/dwc/pcie-designware-host.c | 3 +- drivers/pci/controller/pci-aardvark.c | 2 +- drivers/pci/controller/pci-ftpci100.c | 3 +- drivers/pci/controller/pci-host-common.c | 2 +- drivers/pci/controller/pci-v3-semi.c | 3 +- drivers/pci/controller/pci-versatile.c | 3 +- drivers/pci/controller/pci-xgene.c | 3 +- drivers/pci/controller/pcie-altera.c | 2 +- drivers/pci/controller/pcie-cadence-host.c | 2 +- drivers/pci/controller/pcie-iproc-platform.c | 3 +- drivers/pci/controller/pcie-mediatek.c | 2 +- drivers/pci/controller/pcie-mobiveil.c | 3 +- drivers/pci/controller/pcie-rcar.c | 3 +- drivers/pci/controller/pcie-rockchip-host.c | 3 +- drivers/pci/controller/pcie-xilinx-nwl.c | 3 +- drivers/pci/controller/pcie-xilinx.c | 3 +- drivers/pci/of.c | 61 ++++++++++++++++++++--- drivers/pci/pci.h | 8 ++- include/linux/pci.h | 9 ++-- 19 files changed, 93 insertions(+), 28 deletions(-) (limited to 'include') diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c index aeec8b65eb97..f7b1d80c4a0a 100644 --- a/drivers/pci/controller/dwc/pcie-designware-host.c +++ b/drivers/pci/controller/dwc/pcie-designware-host.c @@ -342,7 +342,8 @@ int dw_pcie_host_init(struct pcie_port *pp) if (!bridge) return -ENOMEM; - ret = pci_parse_request_of_pci_ranges(dev, &bridge->windows, NULL); + ret = pci_parse_request_of_pci_ranges(dev, &bridge->windows, + &bridge->dma_ranges, NULL); if (ret) return ret; diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c index 9cbeba507f0c..b34eaa2cd762 100644 --- a/drivers/pci/controller/pci-aardvark.c +++ b/drivers/pci/controller/pci-aardvark.c @@ -939,7 +939,7 @@ static int advk_pcie_probe(struct platform_device *pdev) } ret = pci_parse_request_of_pci_ranges(dev, &bridge->windows, - &bus); + &bridge->dma_ranges, &bus); if (ret) { dev_err(dev, "Failed to parse resources\n"); return ret; diff --git a/drivers/pci/controller/pci-ftpci100.c b/drivers/pci/controller/pci-ftpci100.c index 75603348b88a..66288b94e92d 100644 --- a/drivers/pci/controller/pci-ftpci100.c +++ b/drivers/pci/controller/pci-ftpci100.c @@ -477,7 +477,8 @@ static int faraday_pci_probe(struct platform_device *pdev) if (IS_ERR(p->base)) return PTR_ERR(p->base); - ret = pci_parse_request_of_pci_ranges(dev, &host->windows, NULL); + ret = pci_parse_request_of_pci_ranges(dev, &host->windows, + &host->dma_ranges, NULL); if (ret) return ret; diff --git a/drivers/pci/controller/pci-host-common.c b/drivers/pci/controller/pci-host-common.c index c8cb9c5188a4..250a3fc80ec6 100644 --- a/drivers/pci/controller/pci-host-common.c +++ b/drivers/pci/controller/pci-host-common.c @@ -27,7 +27,7 @@ static struct pci_config_window *gen_pci_init(struct device *dev, struct pci_config_window *cfg; /* Parse our PCI ranges and request their resources */ - err = pci_parse_request_of_pci_ranges(dev, resources, &bus_range); + err = pci_parse_request_of_pci_ranges(dev, resources, NULL, &bus_range); if (err) return ERR_PTR(err); diff --git a/drivers/pci/controller/pci-v3-semi.c b/drivers/pci/controller/pci-v3-semi.c index 96677520f6c1..2209c7671115 100644 --- a/drivers/pci/controller/pci-v3-semi.c +++ b/drivers/pci/controller/pci-v3-semi.c @@ -776,7 +776,8 @@ static int v3_pci_probe(struct platform_device *pdev) if (IS_ERR(v3->config_base)) return PTR_ERR(v3->config_base); - ret = pci_parse_request_of_pci_ranges(dev, &host->windows, NULL); + ret = pci_parse_request_of_pci_ranges(dev, &host->windows, + &host->dma_ranges, NULL); if (ret) return ret; diff --git a/drivers/pci/controller/pci-versatile.c b/drivers/pci/controller/pci-versatile.c index eae1b859990b..b911359b6d81 100644 --- a/drivers/pci/controller/pci-versatile.c +++ b/drivers/pci/controller/pci-versatile.c @@ -92,7 +92,8 @@ static int versatile_pci_probe(struct platform_device *pdev) if (IS_ERR(versatile_cfg_base[1])) return PTR_ERR(versatile_cfg_base[1]); - ret = pci_parse_request_of_pci_ranges(dev, &bridge->windows, NULL); + ret = pci_parse_request_of_pci_ranges(dev, &bridge->windows, + NULL, NULL); if (ret) return ret; diff --git a/drivers/pci/controller/pci-xgene.c b/drivers/pci/controller/pci-xgene.c index 7d0f0395a479..9408269d943d 100644 --- a/drivers/pci/controller/pci-xgene.c +++ b/drivers/pci/controller/pci-xgene.c @@ -627,7 +627,8 @@ static int xgene_pcie_probe(struct platform_device *pdev) if (ret) return ret; - ret = pci_parse_request_of_pci_ranges(dev, &bridge->windows, NULL); + ret = pci_parse_request_of_pci_ranges(dev, &bridge->windows, + &bridge->dma_ranges, NULL); if (ret) return ret; diff --git a/drivers/pci/controller/pcie-altera.c b/drivers/pci/controller/pcie-altera.c index ba025efeae28..b447c3e4abad 100644 --- a/drivers/pci/controller/pcie-altera.c +++ b/drivers/pci/controller/pcie-altera.c @@ -800,7 +800,7 @@ static int altera_pcie_probe(struct platform_device *pdev) } ret = pci_parse_request_of_pci_ranges(dev, &bridge->windows, - NULL); + &bridge->dma_ranges, NULL); if (ret) { dev_err(dev, "Failed add resources\n"); return ret; diff --git a/drivers/pci/controller/pcie-cadence-host.c b/drivers/pci/controller/pcie-cadence-host.c index 97e251090b4f..a8f7a6284c3e 100644 --- a/drivers/pci/controller/pcie-cadence-host.c +++ b/drivers/pci/controller/pcie-cadence-host.c @@ -211,7 +211,7 @@ static int cdns_pcie_host_init(struct device *dev, int err; /* Parse our PCI ranges and request their resources */ - err = pci_parse_request_of_pci_ranges(dev, resources, &bus_range); + err = pci_parse_request_of_pci_ranges(dev, resources, NULL, &bus_range); if (err) return err; diff --git a/drivers/pci/controller/pcie-iproc-platform.c b/drivers/pci/controller/pcie-iproc-platform.c index 375d815f7301..ff0a81a632a1 100644 --- a/drivers/pci/controller/pcie-iproc-platform.c +++ b/drivers/pci/controller/pcie-iproc-platform.c @@ -95,7 +95,8 @@ static int iproc_pcie_pltfm_probe(struct platform_device *pdev) if (IS_ERR(pcie->phy)) return PTR_ERR(pcie->phy); - ret = pci_parse_request_of_pci_ranges(dev, &bridge->windows, NULL); + ret = pci_parse_request_of_pci_ranges(dev, &bridge->windows, + &bridge->dma_ranges, NULL); if (ret) { dev_err(dev, "unable to get PCI host bridge resources\n"); return ret; diff --git a/drivers/pci/controller/pcie-mediatek.c b/drivers/pci/controller/pcie-mediatek.c index d9206a3cd56b..cb982891b22b 100644 --- a/drivers/pci/controller/pcie-mediatek.c +++ b/drivers/pci/controller/pcie-mediatek.c @@ -1034,7 +1034,7 @@ static int mtk_pcie_setup(struct mtk_pcie *pcie) int err; err = pci_parse_request_of_pci_ranges(dev, windows, - &bus); + &host->dma_ranges, &bus); if (err) return err; diff --git a/drivers/pci/controller/pcie-mobiveil.c b/drivers/pci/controller/pcie-mobiveil.c index 4eab8624ce4d..257ba49c177c 100644 --- a/drivers/pci/controller/pcie-mobiveil.c +++ b/drivers/pci/controller/pcie-mobiveil.c @@ -875,7 +875,8 @@ static int mobiveil_pcie_probe(struct platform_device *pdev) } /* parse the host bridge base addresses from the device tree file */ - ret = pci_parse_request_of_pci_ranges(dev, &bridge->windows, NULL); + ret = pci_parse_request_of_pci_ranges(dev, &bridge->windows, + &bridge->dma_ranges, NULL); if (ret) { dev_err(dev, "Getting bridge resources failed\n"); return ret; diff --git a/drivers/pci/controller/pcie-rcar.c b/drivers/pci/controller/pcie-rcar.c index f6a669a9af41..b8d6e86a5539 100644 --- a/drivers/pci/controller/pcie-rcar.c +++ b/drivers/pci/controller/pcie-rcar.c @@ -1138,7 +1138,8 @@ static int rcar_pcie_probe(struct platform_device *pdev) pcie->dev = dev; platform_set_drvdata(pdev, pcie); - err = pci_parse_request_of_pci_ranges(dev, &pcie->resources, NULL); + err = pci_parse_request_of_pci_ranges(dev, &pcie->resources, + &bridge->dma_ranges, NULL); if (err) goto err_free_bridge; diff --git a/drivers/pci/controller/pcie-rockchip-host.c b/drivers/pci/controller/pcie-rockchip-host.c index f375e55ea02e..ee83f8494ee9 100644 --- a/drivers/pci/controller/pcie-rockchip-host.c +++ b/drivers/pci/controller/pcie-rockchip-host.c @@ -1004,7 +1004,8 @@ static int rockchip_pcie_probe(struct platform_device *pdev) if (err < 0) goto err_deinit_port; - err = pci_parse_request_of_pci_ranges(dev, &bridge->windows, &bus_res); + err = pci_parse_request_of_pci_ranges(dev, &bridge->windows, + &bridge->dma_ranges, &bus_res); if (err) goto err_remove_irq_domain; diff --git a/drivers/pci/controller/pcie-xilinx-nwl.c b/drivers/pci/controller/pcie-xilinx-nwl.c index e135a4b60489..9bd1427f2fd6 100644 --- a/drivers/pci/controller/pcie-xilinx-nwl.c +++ b/drivers/pci/controller/pcie-xilinx-nwl.c @@ -843,7 +843,8 @@ static int nwl_pcie_probe(struct platform_device *pdev) return err; } - err = pci_parse_request_of_pci_ranges(dev, &bridge->windows, NULL); + err = pci_parse_request_of_pci_ranges(dev, &bridge->windows, + &bridge->dma_ranges, NULL); if (err) { dev_err(dev, "Getting bridge resources failed\n"); return err; diff --git a/drivers/pci/controller/pcie-xilinx.c b/drivers/pci/controller/pcie-xilinx.c index 257702288787..98e55297815b 100644 --- a/drivers/pci/controller/pcie-xilinx.c +++ b/drivers/pci/controller/pcie-xilinx.c @@ -645,7 +645,8 @@ static int xilinx_pcie_probe(struct platform_device *pdev) return err; } - err = pci_parse_request_of_pci_ranges(dev, &bridge->windows, NULL); + err = pci_parse_request_of_pci_ranges(dev, &bridge->windows, + &bridge->dma_ranges, NULL); if (err) { dev_err(dev, "Getting bridge resources failed\n"); return err; diff --git a/drivers/pci/of.c b/drivers/pci/of.c index f3da49a31db4..1dfde6f9e82d 100644 --- a/drivers/pci/of.c +++ b/drivers/pci/of.c @@ -257,14 +257,16 @@ EXPORT_SYMBOL_GPL(of_pci_check_probe_only); */ int devm_of_pci_get_host_bridge_resources(struct device *dev, unsigned char busno, unsigned char bus_max, - struct list_head *resources, resource_size_t *io_base) + struct list_head *resources, + struct list_head *ib_resources, + resource_size_t *io_base) { struct device_node *dev_node = dev->of_node; struct resource *res, tmp_res; struct resource *bus_range; struct of_pci_range range; struct of_pci_range_parser parser; - char range_type[4]; + const char *range_type; int err; if (io_base) @@ -298,12 +300,12 @@ int devm_of_pci_get_host_bridge_resources(struct device *dev, for_each_of_pci_range(&parser, &range) { /* Read next ranges element */ if ((range.flags & IORESOURCE_TYPE_BITS) == IORESOURCE_IO) - snprintf(range_type, 4, " IO"); + range_type = "IO"; else if ((range.flags & IORESOURCE_TYPE_BITS) == IORESOURCE_MEM) - snprintf(range_type, 4, "MEM"); + range_type = "MEM"; else - snprintf(range_type, 4, "err"); - dev_info(dev, " %s %#010llx..%#010llx -> %#010llx\n", + range_type = "err"; + dev_info(dev, " %6s %#012llx..%#012llx -> %#012llx\n", range_type, range.cpu_addr, range.cpu_addr + range.size - 1, range.pci_addr); @@ -340,6 +342,48 @@ int devm_of_pci_get_host_bridge_resources(struct device *dev, pci_add_resource_offset(resources, res, res->start - range.pci_addr); } + /* Check for dma-ranges property */ + if (!ib_resources) + return 0; + err = of_pci_dma_range_parser_init(&parser, dev_node); + if (err) + return 0; + + dev_dbg(dev, "Parsing dma-ranges property...\n"); + for_each_of_pci_range(&parser, &range) { + struct resource_entry *entry; + /* + * If we failed translation or got a zero-sized region + * then skip this range + */ + if (((range.flags & IORESOURCE_TYPE_BITS) != IORESOURCE_MEM) || + range.cpu_addr == OF_BAD_ADDR || range.size == 0) + continue; + + dev_info(dev, " %6s %#012llx..%#012llx -> %#012llx\n", + "IB MEM", range.cpu_addr, + range.cpu_addr + range.size - 1, range.pci_addr); + + + err = of_pci_range_to_resource(&range, dev_node, &tmp_res); + if (err) + continue; + + res = devm_kmemdup(dev, &tmp_res, sizeof(tmp_res), GFP_KERNEL); + if (!res) { + err = -ENOMEM; + goto failed; + } + + /* Keep the resource list sorted */ + resource_list_for_each_entry(entry, ib_resources) + if (entry->res->start > res->start) + break; + + pci_add_resource_offset(&entry->node, res, + res->start - range.pci_addr); + } + return 0; failed: @@ -482,6 +526,7 @@ EXPORT_SYMBOL_GPL(of_irq_parse_and_map_pci); int pci_parse_request_of_pci_ranges(struct device *dev, struct list_head *resources, + struct list_head *ib_resources, struct resource **bus_range) { int err, res_valid = 0; @@ -489,8 +534,10 @@ int pci_parse_request_of_pci_ranges(struct device *dev, struct resource_entry *win, *tmp; INIT_LIST_HEAD(resources); + if (ib_resources) + INIT_LIST_HEAD(ib_resources); err = devm_of_pci_get_host_bridge_resources(dev, 0, 0xff, resources, - &iobase); + ib_resources, &iobase); if (err) return err; diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 3f6947ee3324..6692c4fe4290 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -633,11 +633,15 @@ static inline void pci_release_bus_of_node(struct pci_bus *bus) { } #if defined(CONFIG_OF_ADDRESS) int devm_of_pci_get_host_bridge_resources(struct device *dev, unsigned char busno, unsigned char bus_max, - struct list_head *resources, resource_size_t *io_base); + struct list_head *resources, + struct list_head *ib_resources, + resource_size_t *io_base); #else static inline int devm_of_pci_get_host_bridge_resources(struct device *dev, unsigned char busno, unsigned char bus_max, - struct list_head *resources, resource_size_t *io_base) + struct list_head *resources, + struct list_head *ib_resources, + resource_size_t *io_base) { return -EINVAL; } diff --git a/include/linux/pci.h b/include/linux/pci.h index f9088c89a534..5cb94916eaa1 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2278,6 +2278,7 @@ struct irq_domain; struct irq_domain *pci_host_bridge_of_msi_domain(struct pci_bus *bus); int pci_parse_request_of_pci_ranges(struct device *dev, struct list_head *resources, + struct list_head *ib_resources, struct resource **bus_range); /* Arch may override this (weak) */ @@ -2286,9 +2287,11 @@ struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus); #else /* CONFIG_OF */ static inline struct irq_domain * pci_host_bridge_of_msi_domain(struct pci_bus *bus) { return NULL; } -static inline int pci_parse_request_of_pci_ranges(struct device *dev, - struct list_head *resources, - struct resource **bus_range) +static inline int +pci_parse_request_of_pci_ranges(struct device *dev, + struct list_head *resources, + struct list_head *ib_resources, + struct resource **bus_range) { return -EINVAL; } -- cgit v1.2.3 From 12bcae44bf48595c71898330076576075590e15b Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Mon, 7 Oct 2019 07:52:28 -0500 Subject: PCI/PM: Use pci_WARN() to include device information Add and use pci_WARN() wrappers so warnings include device information. Link: https://lore.kernel.org/r/20191017212851.54237-3-helgaas@kernel.org Signed-off-by: Bjorn Helgaas Reviewed-by: Rafael J. Wysocki --- drivers/pci/pci-driver.c | 34 +++++++++++++++++----------------- include/linux/pci.h | 8 ++++++++ 2 files changed, 25 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 407b1df5ea7c..5337cbbd69de 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -585,9 +585,9 @@ static int pci_legacy_suspend(struct device *dev, pm_message_t state) if (!pci_dev->state_saved && pci_dev->current_state != PCI_D0 && pci_dev->current_state != PCI_UNKNOWN) { - WARN_ONCE(pci_dev->current_state != prev, - "PCI PM: Device state not saved by %pS\n", - drv->suspend); + pci_WARN_ONCE(pci_dev, pci_dev->current_state != prev, + "PCI PM: Device state not saved by %pS\n", + drv->suspend); } } @@ -612,9 +612,9 @@ static int pci_legacy_suspend_late(struct device *dev, pm_message_t state) if (!pci_dev->state_saved && pci_dev->current_state != PCI_D0 && pci_dev->current_state != PCI_UNKNOWN) { - WARN_ONCE(pci_dev->current_state != prev, - "PCI PM: Device state not saved by %pS\n", - drv->suspend_late); + pci_WARN_ONCE(pci_dev, pci_dev->current_state != prev, + "PCI PM: Device state not saved by %pS\n", + drv->suspend_late); goto Fixup; } } @@ -670,8 +670,8 @@ static bool pci_has_legacy_pm_support(struct pci_dev *pci_dev) * supported as well. Drivers are supposed to support either the * former, or the latter, but not both at the same time. */ - WARN(ret && drv->driver.pm, "driver %s device %04x:%04x\n", - drv->name, pci_dev->vendor, pci_dev->device); + pci_WARN(pci_dev, ret && drv->driver.pm, "device %04x:%04x\n", + pci_dev->vendor, pci_dev->device); return ret; } @@ -794,9 +794,9 @@ static int pci_pm_suspend(struct device *dev) if (!pci_dev->state_saved && pci_dev->current_state != PCI_D0 && pci_dev->current_state != PCI_UNKNOWN) { - WARN_ONCE(pci_dev->current_state != prev, - "PCI PM: State of device not saved by %pS\n", - pm->suspend); + pci_WARN_ONCE(pci_dev, pci_dev->current_state != prev, + "PCI PM: State of device not saved by %pS\n", + pm->suspend); } } @@ -842,9 +842,9 @@ static int pci_pm_suspend_noirq(struct device *dev) if (!pci_dev->state_saved && pci_dev->current_state != PCI_D0 && pci_dev->current_state != PCI_UNKNOWN) { - WARN_ONCE(pci_dev->current_state != prev, - "PCI PM: State of device not saved by %pS\n", - pm->suspend_noirq); + pci_WARN_ONCE(pci_dev, pci_dev->current_state != prev, + "PCI PM: State of device not saved by %pS\n", + pm->suspend_noirq); goto Fixup; } } @@ -1311,9 +1311,9 @@ static int pci_pm_runtime_suspend(struct device *dev) if (pm && pm->runtime_suspend && !pci_dev->state_saved && pci_dev->current_state != PCI_D0 && pci_dev->current_state != PCI_UNKNOWN) { - WARN_ONCE(pci_dev->current_state != prev, - "PCI PM: State of device not saved by %pS\n", - pm->runtime_suspend); + pci_WARN_ONCE(pci_dev, pci_dev->current_state != prev, + "PCI PM: State of device not saved by %pS\n", + pm->runtime_suspend); return 0; } diff --git a/include/linux/pci.h b/include/linux/pci.h index f9088c89a534..4846306d521c 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2400,4 +2400,12 @@ void pci_uevent_ers(struct pci_dev *pdev, enum pci_ers_result err_type); #define pci_info_ratelimited(pdev, fmt, arg...) \ dev_info_ratelimited(&(pdev)->dev, fmt, ##arg) +#define pci_WARN(pdev, condition, fmt, arg...) \ + WARN(condition, "%s %s: " fmt, \ + dev_driver_string(&(pdev)->dev), pci_name(pdev), ##arg) + +#define pci_WARN_ONCE(pdev, condition, fmt, arg...) \ + WARN_ONCE(condition, "%s %s: " fmt, \ + dev_driver_string(&(pdev)->dev), pci_name(pdev), ##arg) + #endif /* LINUX_PCI_H */ -- cgit v1.2.3 From 89cdbc3546354c359558a1809133902028c57da4 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Thu, 31 Oct 2019 17:53:04 -0500 Subject: PCI/PM: Remove unused pci_driver.resume_early() hook The struct pci_driver.resume_early() hook is one of the legacy PCI power management callbacks, and there are no remaining users of it. Remove it. Link: https://lore.kernel.org/r/20191101204558.210235-6-helgaas@kernel.org Signed-off-by: Bjorn Helgaas Reviewed-by: Rafael J. Wysocki --- Documentation/power/pci.rst | 2 +- drivers/pci/pci-driver.c | 23 ++++++----------------- include/linux/pci.h | 2 -- 3 files changed, 7 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/Documentation/power/pci.rst b/Documentation/power/pci.rst index a90e82c70a3b..ff7029b94068 100644 --- a/Documentation/power/pci.rst +++ b/Documentation/power/pci.rst @@ -692,7 +692,7 @@ controlling the runtime power management of their devices. At the time of this writing there are two ways to define power management callbacks for a PCI device driver, the recommended one, based on using a dev_pm_ops structure described in Documentation/driver-api/pm/devices.rst, and -the "legacy" one, in which the .suspend(), .suspend_late(), .resume_early(), and +the "legacy" one, in which the .suspend(), .suspend_late(), and .resume() callbacks from struct pci_driver are used. The legacy approach, however, doesn't allow one to define runtime power management callbacks and is not really suitable for any new drivers. Therefore it is not covered by this diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 5337cbbd69de..fc372c2d529a 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -630,15 +630,6 @@ Fixup: return 0; } -static int pci_legacy_resume_early(struct device *dev) -{ - struct pci_dev *pci_dev = to_pci_dev(dev); - struct pci_driver *drv = pci_dev->driver; - - return drv && drv->resume_early ? - drv->resume_early(pci_dev) : 0; -} - static int pci_legacy_resume(struct device *dev) { struct pci_dev *pci_dev = to_pci_dev(dev); @@ -662,8 +653,7 @@ static void pci_pm_default_suspend(struct pci_dev *pci_dev) static bool pci_has_legacy_pm_support(struct pci_dev *pci_dev) { struct pci_driver *drv = pci_dev->driver; - bool ret = drv && (drv->suspend || drv->suspend_late || drv->resume - || drv->resume_early); + bool ret = drv && (drv->suspend || drv->suspend_late || drv->resume); /* * Legacy PM support is used by default, so warn if the new framework is @@ -944,7 +934,7 @@ static int pci_pm_resume_noirq(struct device *dev) pcie_pme_root_status_cleanup(pci_dev); if (pci_has_legacy_pm_support(pci_dev)) - return pci_legacy_resume_early(dev); + return 0; if (pm && pm->resume_noirq) return pm->resume_noirq(dev); @@ -1074,9 +1064,8 @@ static int pci_pm_thaw_noirq(struct device *dev) } /* - * Both the legacy ->resume_early() and the new pm->thaw_noirq() - * callbacks assume the device has been returned to D0 and its - * config state has been restored. + * The pm->thaw_noirq() callback assumes the device has been + * returned to D0 and its config state has been restored. * * In addition, pci_restore_state() restores MSI-X state in MMIO * space, which requires the device to be in D0, so return it to D0 @@ -1087,7 +1076,7 @@ static int pci_pm_thaw_noirq(struct device *dev) pci_restore_state(pci_dev); if (pci_has_legacy_pm_support(pci_dev)) - return pci_legacy_resume_early(dev); + return 0; if (pm && pm->thaw_noirq) return pm->thaw_noirq(dev); @@ -1219,7 +1208,7 @@ static int pci_pm_restore_noirq(struct device *dev) pci_fixup_device(pci_fixup_resume_early, pci_dev); if (pci_has_legacy_pm_support(pci_dev)) - return pci_legacy_resume_early(dev); + return 0; if (pm && pm->restore_noirq) return pm->restore_noirq(dev); diff --git a/include/linux/pci.h b/include/linux/pci.h index 4846306d521c..dd4596fc1208 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -806,7 +806,6 @@ struct module; * context, so it can sleep. * @suspend: Put device into low power state. * @suspend_late: Put device into low power state. - * @resume_early: Wake device from low power state. * @resume: Wake device from low power state. * (Please see Documentation/power/pci.rst for descriptions * of PCI Power Management and the related functions.) @@ -830,7 +829,6 @@ struct pci_driver { void (*remove)(struct pci_dev *dev); /* Device removed (NULL if not a hot-plug capable driver) */ int (*suspend)(struct pci_dev *dev, pm_message_t state); /* Device suspended */ int (*suspend_late)(struct pci_dev *dev, pm_message_t state); - int (*resume_early)(struct pci_dev *dev); int (*resume)(struct pci_dev *dev); /* Device woken up */ void (*shutdown)(struct pci_dev *dev); int (*sriov_configure)(struct pci_dev *dev, int num_vfs); /* On PF */ -- cgit v1.2.3 From 1a1daf097e21e544dd3e7c0ff620d78a9795fbf2 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Thu, 31 Oct 2019 17:37:54 -0500 Subject: PCI/PM: Remove unused pci_driver.suspend_late() hook The struct pci_driver.suspend_late() hook is one of the legacy PCI power management callbacks, and there are no remaining users of it. Remove it. Link: https://lore.kernel.org/r/20191101204558.210235-7-helgaas@kernel.org Signed-off-by: Bjorn Helgaas Reviewed-by: Rafael J. Wysocki --- Documentation/power/pci.rst | 10 +++++----- drivers/pci/pci-driver.c | 22 +--------------------- include/linux/pci.h | 2 -- 3 files changed, 6 insertions(+), 28 deletions(-) (limited to 'include') diff --git a/Documentation/power/pci.rst b/Documentation/power/pci.rst index ff7029b94068..0924d29636ad 100644 --- a/Documentation/power/pci.rst +++ b/Documentation/power/pci.rst @@ -692,11 +692,11 @@ controlling the runtime power management of their devices. At the time of this writing there are two ways to define power management callbacks for a PCI device driver, the recommended one, based on using a dev_pm_ops structure described in Documentation/driver-api/pm/devices.rst, and -the "legacy" one, in which the .suspend(), .suspend_late(), and -.resume() callbacks from struct pci_driver are used. The legacy approach, -however, doesn't allow one to define runtime power management callbacks and is -not really suitable for any new drivers. Therefore it is not covered by this -document (refer to the source code to learn more about it). +the "legacy" one, in which the .suspend() and .resume() callbacks from struct +pci_driver are used. The legacy approach, however, doesn't allow one to define +runtime power management callbacks and is not really suitable for any new +drivers. Therefore it is not covered by this document (refer to the source code +to learn more about it). It is recommended that all PCI device drivers define a struct dev_pm_ops object containing pointers to power management (PM) callbacks that will be executed by diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index fc372c2d529a..e89fd90eaa93 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -599,32 +599,12 @@ static int pci_legacy_suspend(struct device *dev, pm_message_t state) static int pci_legacy_suspend_late(struct device *dev, pm_message_t state) { struct pci_dev *pci_dev = to_pci_dev(dev); - struct pci_driver *drv = pci_dev->driver; - - if (drv && drv->suspend_late) { - pci_power_t prev = pci_dev->current_state; - int error; - - error = drv->suspend_late(pci_dev, state); - suspend_report_result(drv->suspend_late, error); - if (error) - return error; - - if (!pci_dev->state_saved && pci_dev->current_state != PCI_D0 - && pci_dev->current_state != PCI_UNKNOWN) { - pci_WARN_ONCE(pci_dev, pci_dev->current_state != prev, - "PCI PM: Device state not saved by %pS\n", - drv->suspend_late); - goto Fixup; - } - } if (!pci_dev->state_saved) pci_save_state(pci_dev); pci_pm_set_unknown_state(pci_dev); -Fixup: pci_fixup_device(pci_fixup_suspend_late, pci_dev); return 0; @@ -653,7 +633,7 @@ static void pci_pm_default_suspend(struct pci_dev *pci_dev) static bool pci_has_legacy_pm_support(struct pci_dev *pci_dev) { struct pci_driver *drv = pci_dev->driver; - bool ret = drv && (drv->suspend || drv->suspend_late || drv->resume); + bool ret = drv && (drv->suspend || drv->resume); /* * Legacy PM support is used by default, so warn if the new framework is diff --git a/include/linux/pci.h b/include/linux/pci.h index dd4596fc1208..9b0e35e09874 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -805,7 +805,6 @@ struct module; * The remove function always gets called from process * context, so it can sleep. * @suspend: Put device into low power state. - * @suspend_late: Put device into low power state. * @resume: Wake device from low power state. * (Please see Documentation/power/pci.rst for descriptions * of PCI Power Management and the related functions.) @@ -828,7 +827,6 @@ struct pci_driver { int (*probe)(struct pci_dev *dev, const struct pci_device_id *id); /* New device inserted */ void (*remove)(struct pci_dev *dev); /* Device removed (NULL if not a hot-plug capable driver) */ int (*suspend)(struct pci_dev *dev, pm_message_t state); /* Device suspended */ - int (*suspend_late)(struct pci_dev *dev, pm_message_t state); int (*resume)(struct pci_dev *dev); /* Device woken up */ void (*shutdown)(struct pci_dev *dev); int (*sriov_configure)(struct pci_dev *dev, int num_vfs); /* On PF */ -- cgit v1.2.3 From d6aa37cd04fdafaf31ae89691e537535df43ca78 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 5 Nov 2019 11:30:36 +0100 Subject: PCI/PM: Avoid exporting __pci_complete_power_transition() Notice that radeon_set_suspend(), which is the only caller of __pci_complete_power_transition() outside of pci.c, really only cares about the pci_platform_power_transition() invoked by it, so export the latter instead of it, update the radeon driver to call pci_platform_power_transition() directly and make __pci_complete_power_transition() static. Code rearrangement, no intentional functional impact. Link: https://lore.kernel.org/r/1731661.ykamz2Tiuf@kreacher Signed-off-by: Rafael J. Wysocki Signed-off-by: Bjorn Helgaas Reviewed-by: Mika Westerberg --- drivers/pci/pci.c | 6 +++--- drivers/video/fbdev/aty/radeon_pm.c | 2 +- include/linux/pci.h | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 56bc79e33286..2f53234f9e91 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -963,7 +963,7 @@ void pci_refresh_power_state(struct pci_dev *dev) * @dev: PCI device to handle. * @state: State to put the device into. */ -static int pci_platform_power_transition(struct pci_dev *dev, pci_power_t state) +int pci_platform_power_transition(struct pci_dev *dev, pci_power_t state) { int error; @@ -979,6 +979,7 @@ static int pci_platform_power_transition(struct pci_dev *dev, pci_power_t state) return error; } +EXPORT_SYMBOL_GPL(pci_platform_power_transition); /** * pci_wakeup - Wake up a PCI device @@ -1061,7 +1062,7 @@ void pci_bus_set_current_state(struct pci_bus *bus, pci_power_t state) * * This function should not be called directly by device drivers. */ -int __pci_complete_power_transition(struct pci_dev *dev, pci_power_t state) +static int __pci_complete_power_transition(struct pci_dev *dev, pci_power_t state) { int ret; @@ -1073,7 +1074,6 @@ int __pci_complete_power_transition(struct pci_dev *dev, pci_power_t state) pci_bus_set_current_state(dev->subordinate, PCI_D3cold); return ret; } -EXPORT_SYMBOL_GPL(__pci_complete_power_transition); /** * pci_set_power_state - Set the power state of a PCI device diff --git a/drivers/video/fbdev/aty/radeon_pm.c b/drivers/video/fbdev/aty/radeon_pm.c index 2dc5703eac51..7c4483c7f313 100644 --- a/drivers/video/fbdev/aty/radeon_pm.c +++ b/drivers/video/fbdev/aty/radeon_pm.c @@ -2593,7 +2593,7 @@ static void radeon_set_suspend(struct radeonfb_info *rinfo, int suspend) * calling pci_set_power_state() */ radeonfb_whack_power_state(rinfo, PCI_D2); - __pci_complete_power_transition(rinfo->pdev, PCI_D2); + pci_platform_power_transition(rinfo->pdev, PCI_D2); } else { printk(KERN_DEBUG "radeonfb (%s): switching to D0 state...\n", pci_name(rinfo->pdev)); diff --git a/include/linux/pci.h b/include/linux/pci.h index 9b0e35e09874..86976cccdfe3 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1228,7 +1228,7 @@ struct pci_cap_saved_state *pci_find_saved_ext_cap(struct pci_dev *dev, int pci_add_cap_save_buffer(struct pci_dev *dev, char cap, unsigned int size); int pci_add_ext_cap_save_buffer(struct pci_dev *dev, u16 cap, unsigned int size); -int __pci_complete_power_transition(struct pci_dev *dev, pci_power_t state); +int pci_platform_power_transition(struct pci_dev *dev, pci_power_t state); int pci_set_power_state(struct pci_dev *dev, pci_power_t state); pci_power_t pci_choose_state(struct pci_dev *dev, pm_message_t state); bool pci_pme_capable(struct pci_dev *dev, pci_power_t state); -- cgit v1.2.3 From c9b465683a554212c3dd92915ed2088849c513bf Mon Sep 17 00:00:00 2001 From: Gwendal Grignou Date: Tue, 19 Nov 2019 13:45:45 +0100 Subject: platform/chrome: cros_ec: Put docs with the code To avoid doc rot, put function documentations with code, not header. Use kernel-doc style comments for exported functions. Signed-off-by: Gwendal Grignou Acked-by: Jonathan Cameron Signed-off-by: Enric Balletbo i Serra --- drivers/platform/chrome/cros_ec.c | 33 +++++++++ drivers/platform/chrome/cros_ec_proto.c | 70 +++++++++++++++++++ include/linux/platform_data/cros_ec_proto.h | 103 ---------------------------- 3 files changed, 103 insertions(+), 103 deletions(-) (limited to 'include') diff --git a/drivers/platform/chrome/cros_ec.c b/drivers/platform/chrome/cros_ec.c index fd77e6fa74c2..9b2d07422e17 100644 --- a/drivers/platform/chrome/cros_ec.c +++ b/drivers/platform/chrome/cros_ec.c @@ -104,6 +104,15 @@ static int cros_ec_sleep_event(struct cros_ec_device *ec_dev, u8 sleep_event) return ret; } +/** + * cros_ec_register() - Register a new ChromeOS EC, using the provided info. + * @ec_dev: Device to register. + * + * Before calling this, allocate a pointer to a new device and then fill + * in all the fields up to the --private-- marker. + * + * Return: 0 on success or negative error code. + */ int cros_ec_register(struct cros_ec_device *ec_dev) { struct device *dev = ec_dev->dev; @@ -198,6 +207,14 @@ int cros_ec_register(struct cros_ec_device *ec_dev) } EXPORT_SYMBOL(cros_ec_register); +/** + * cros_ec_unregister() - Remove a ChromeOS EC. + * @ec_dev: Device to unregister. + * + * Call this to deregister a ChromeOS EC, then clean up any private data. + * + * Return: 0 on success or negative error code. + */ int cros_ec_unregister(struct cros_ec_device *ec_dev) { if (ec_dev->pd) @@ -209,6 +226,14 @@ int cros_ec_unregister(struct cros_ec_device *ec_dev) EXPORT_SYMBOL(cros_ec_unregister); #ifdef CONFIG_PM_SLEEP +/** + * cros_ec_suspend() - Handle a suspend operation for the ChromeOS EC device. + * @ec_dev: Device to suspend. + * + * This can be called by drivers to handle a suspend event. + * + * Return: 0 on success or negative error code. + */ int cros_ec_suspend(struct cros_ec_device *ec_dev) { struct device *dev = ec_dev->dev; @@ -243,6 +268,14 @@ static void cros_ec_report_events_during_suspend(struct cros_ec_device *ec_dev) 1, ec_dev); } +/** + * cros_ec_resume() - Handle a resume operation for the ChromeOS EC device. + * @ec_dev: Device to resume. + * + * This can be called by drivers to handle a resume event. + * + * Return: 0 on success or negative error code. + */ int cros_ec_resume(struct cros_ec_device *ec_dev) { int ret; diff --git a/drivers/platform/chrome/cros_ec_proto.c b/drivers/platform/chrome/cros_ec_proto.c index f659f96bda12..7db58771ec77 100644 --- a/drivers/platform/chrome/cros_ec_proto.c +++ b/drivers/platform/chrome/cros_ec_proto.c @@ -117,6 +117,17 @@ static int send_command(struct cros_ec_device *ec_dev, return ret; } +/** + * cros_ec_prepare_tx() - Prepare an outgoing message in the output buffer. + * @ec_dev: Device to register. + * @msg: Message to write. + * + * This is intended to be used by all ChromeOS EC drivers, but at present + * only SPI uses it. Once LPC uses the same protocol it can start using it. + * I2C could use it now, with a refactor of the existing code. + * + * Return: 0 on success or negative error code. + */ int cros_ec_prepare_tx(struct cros_ec_device *ec_dev, struct cros_ec_command *msg) { @@ -141,6 +152,16 @@ int cros_ec_prepare_tx(struct cros_ec_device *ec_dev, } EXPORT_SYMBOL(cros_ec_prepare_tx); +/** + * cros_ec_check_result() - Check ec_msg->result. + * @ec_dev: EC device. + * @msg: Message to check. + * + * This is used by ChromeOS EC drivers to check the ec_msg->result for + * errors and to warn about them. + * + * Return: 0 on success or negative error code. + */ int cros_ec_check_result(struct cros_ec_device *ec_dev, struct cros_ec_command *msg) { @@ -326,6 +347,13 @@ static int cros_ec_get_host_command_version_mask(struct cros_ec_device *ec_dev, return ret; } +/** + * cros_ec_query_all() - Query the protocol version supported by the + * ChromeOS EC. + * @ec_dev: Device to register. + * + * Return: 0 on success or negative error code. + */ int cros_ec_query_all(struct cros_ec_device *ec_dev) { struct device *dev = ec_dev->dev; @@ -453,6 +481,16 @@ exit: } EXPORT_SYMBOL(cros_ec_query_all); +/** + * cros_ec_cmd_xfer() - Send a command to the ChromeOS EC. + * @ec_dev: EC device. + * @msg: Message to write. + * + * Call this to send a command to the ChromeOS EC. This should be used + * instead of calling the EC's cmd_xfer() callback directly. + * + * Return: 0 on success or negative error code. + */ int cros_ec_cmd_xfer(struct cros_ec_device *ec_dev, struct cros_ec_command *msg) { @@ -500,6 +538,18 @@ int cros_ec_cmd_xfer(struct cros_ec_device *ec_dev, } EXPORT_SYMBOL(cros_ec_cmd_xfer); +/** + * cros_ec_cmd_xfer_status() - Send a command to the ChromeOS EC. + * @ec_dev: EC device. + * @msg: Message to write. + * + * This function is identical to cros_ec_cmd_xfer, except it returns success + * status only if both the command was transmitted successfully and the EC + * replied with success status. It's not necessary to check msg->result when + * using this function. + * + * Return: The number of bytes transferred on success or negative error code. + */ int cros_ec_cmd_xfer_status(struct cros_ec_device *ec_dev, struct cros_ec_command *msg) { @@ -584,6 +634,16 @@ static int get_keyboard_state_event(struct cros_ec_device *ec_dev) return ec_dev->event_size; } +/** + * cros_ec_get_next_event() - Fetch next event from the ChromeOS EC. + * @ec_dev: Device to fetch event from. + * @wake_event: Pointer to a bool set to true upon return if the event might be + * treated as a wake event. Ignored if null. + * + * Return: negative error code on errors; 0 for no data; or else number of + * bytes received (i.e., an event was retrieved successfully). Event types are + * written out to @ec_dev->event_data.event_type on success. + */ int cros_ec_get_next_event(struct cros_ec_device *ec_dev, bool *wake_event) { u8 event_type; @@ -628,6 +688,16 @@ int cros_ec_get_next_event(struct cros_ec_device *ec_dev, bool *wake_event) } EXPORT_SYMBOL(cros_ec_get_next_event); +/** + * cros_ec_get_host_event() - Return a mask of event set by the ChromeOS EC. + * @ec_dev: Device to fetch event from. + * + * When MKBP is supported, when the EC raises an interrupt, we collect the + * events raised and call the functions in the ec notifier. This function + * is a helper to know which events are raised. + * + * Return: 0 on error or non-zero bitmask of one or more EC_HOST_EVENT_*. + */ u32 cros_ec_get_host_event(struct cros_ec_device *ec_dev) { u32 host_event; diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h index eab7036cda09..0d4e4aaed37a 100644 --- a/include/linux/platform_data/cros_ec_proto.h +++ b/include/linux/platform_data/cros_ec_proto.h @@ -187,133 +187,30 @@ struct cros_ec_platform { u16 cmd_offset; }; -/** - * cros_ec_suspend() - Handle a suspend operation for the ChromeOS EC device. - * @ec_dev: Device to suspend. - * - * This can be called by drivers to handle a suspend event. - * - * Return: 0 on success or negative error code. - */ int cros_ec_suspend(struct cros_ec_device *ec_dev); -/** - * cros_ec_resume() - Handle a resume operation for the ChromeOS EC device. - * @ec_dev: Device to resume. - * - * This can be called by drivers to handle a resume event. - * - * Return: 0 on success or negative error code. - */ int cros_ec_resume(struct cros_ec_device *ec_dev); -/** - * cros_ec_prepare_tx() - Prepare an outgoing message in the output buffer. - * @ec_dev: Device to register. - * @msg: Message to write. - * - * This is intended to be used by all ChromeOS EC drivers, but at present - * only SPI uses it. Once LPC uses the same protocol it can start using it. - * I2C could use it now, with a refactor of the existing code. - * - * Return: 0 on success or negative error code. - */ int cros_ec_prepare_tx(struct cros_ec_device *ec_dev, struct cros_ec_command *msg); -/** - * cros_ec_check_result() - Check ec_msg->result. - * @ec_dev: EC device. - * @msg: Message to check. - * - * This is used by ChromeOS EC drivers to check the ec_msg->result for - * errors and to warn about them. - * - * Return: 0 on success or negative error code. - */ int cros_ec_check_result(struct cros_ec_device *ec_dev, struct cros_ec_command *msg); -/** - * cros_ec_cmd_xfer() - Send a command to the ChromeOS EC. - * @ec_dev: EC device. - * @msg: Message to write. - * - * Call this to send a command to the ChromeOS EC. This should be used - * instead of calling the EC's cmd_xfer() callback directly. - * - * Return: 0 on success or negative error code. - */ int cros_ec_cmd_xfer(struct cros_ec_device *ec_dev, struct cros_ec_command *msg); -/** - * cros_ec_cmd_xfer_status() - Send a command to the ChromeOS EC. - * @ec_dev: EC device. - * @msg: Message to write. - * - * This function is identical to cros_ec_cmd_xfer, except it returns success - * status only if both the command was transmitted successfully and the EC - * replied with success status. It's not necessary to check msg->result when - * using this function. - * - * Return: The number of bytes transferred on success or negative error code. - */ int cros_ec_cmd_xfer_status(struct cros_ec_device *ec_dev, struct cros_ec_command *msg); -/** - * cros_ec_register() - Register a new ChromeOS EC, using the provided info. - * @ec_dev: Device to register. - * - * Before calling this, allocate a pointer to a new device and then fill - * in all the fields up to the --private-- marker. - * - * Return: 0 on success or negative error code. - */ int cros_ec_register(struct cros_ec_device *ec_dev); -/** - * cros_ec_unregister() - Remove a ChromeOS EC. - * @ec_dev: Device to unregister. - * - * Call this to deregister a ChromeOS EC, then clean up any private data. - * - * Return: 0 on success or negative error code. - */ int cros_ec_unregister(struct cros_ec_device *ec_dev); -/** - * cros_ec_query_all() - Query the protocol version supported by the - * ChromeOS EC. - * @ec_dev: Device to register. - * - * Return: 0 on success or negative error code. - */ int cros_ec_query_all(struct cros_ec_device *ec_dev); -/** - * cros_ec_get_next_event() - Fetch next event from the ChromeOS EC. - * @ec_dev: Device to fetch event from. - * @wake_event: Pointer to a bool set to true upon return if the event might be - * treated as a wake event. Ignored if null. - * - * Return: negative error code on errors; 0 for no data; or else number of - * bytes received (i.e., an event was retrieved successfully). Event types are - * written out to @ec_dev->event_data.event_type on success. - */ int cros_ec_get_next_event(struct cros_ec_device *ec_dev, bool *wake_event); -/** - * cros_ec_get_host_event() - Return a mask of event set by the ChromeOS EC. - * @ec_dev: Device to fetch event from. - * - * When MKBP is supported, when the EC raises an interrupt, we collect the - * events raised and call the functions in the ec notifier. This function - * is a helper to know which events are raised. - * - * Return: 0 on error or non-zero bitmask of one or more EC_HOST_EVENT_*. - */ u32 cros_ec_get_host_event(struct cros_ec_device *ec_dev); #endif /* __LINUX_CROS_EC_PROTO_H */ -- cgit v1.2.3 From a16b2e28190255a0729c27902fa88fb8fff39bb0 Mon Sep 17 00:00:00 2001 From: Gwendal Grignou Date: Tue, 19 Nov 2019 13:45:45 +0100 Subject: mfd / platform: cros_ec: Add sensor_count and make check_features public Add a new function to return the number of MEMS sensors available in a ChromeOS Embedded Controller. It uses MOTIONSENSE_CMD_DUMP if available or a specific memory map ACPI registers to find out. Also, make check_features public as it can be useful for other drivers to know what the Embedded Controller supports. Signed-off-by: Gwendal Grignou Acked-by: Lee Jones Signed-off-by: Enric Balletbo i Serra --- drivers/mfd/cros_ec_dev.c | 32 -------- drivers/platform/chrome/cros_ec_proto.c | 117 ++++++++++++++++++++++++++++ include/linux/platform_data/cros_ec_proto.h | 5 ++ 3 files changed, 122 insertions(+), 32 deletions(-) (limited to 'include') diff --git a/drivers/mfd/cros_ec_dev.c b/drivers/mfd/cros_ec_dev.c index 6e6dfd6c1871..a35104e35cb4 100644 --- a/drivers/mfd/cros_ec_dev.c +++ b/drivers/mfd/cros_ec_dev.c @@ -112,38 +112,6 @@ static const struct mfd_cell cros_ec_vbc_cells[] = { { .name = "cros-ec-vbc", } }; -static int cros_ec_check_features(struct cros_ec_dev *ec, int feature) -{ - struct cros_ec_command *msg; - int ret; - - if (ec->features[0] == -1U && ec->features[1] == -1U) { - /* features bitmap not read yet */ - msg = kzalloc(sizeof(*msg) + sizeof(ec->features), GFP_KERNEL); - if (!msg) - return -ENOMEM; - - msg->command = EC_CMD_GET_FEATURES + ec->cmd_offset; - msg->insize = sizeof(ec->features); - - ret = cros_ec_cmd_xfer_status(ec->ec_dev, msg); - if (ret < 0) { - dev_warn(ec->dev, "cannot get EC features: %d/%d\n", - ret, msg->result); - memset(ec->features, 0, sizeof(ec->features)); - } else { - memcpy(ec->features, msg->data, sizeof(ec->features)); - } - - dev_dbg(ec->dev, "EC features %08x %08x\n", - ec->features[0], ec->features[1]); - - kfree(msg); - } - - return ec->features[feature / 32] & EC_FEATURE_MASK_0(feature); -} - static void cros_ec_class_release(struct device *dev) { kfree(to_cros_ec_dev(dev)); diff --git a/drivers/platform/chrome/cros_ec_proto.c b/drivers/platform/chrome/cros_ec_proto.c index 7db58771ec77..12bdd1f3aee9 100644 --- a/drivers/platform/chrome/cros_ec_proto.c +++ b/drivers/platform/chrome/cros_ec_proto.c @@ -717,3 +717,120 @@ u32 cros_ec_get_host_event(struct cros_ec_device *ec_dev) return host_event; } EXPORT_SYMBOL(cros_ec_get_host_event); + +/** + * cros_ec_check_features() - Test for the presence of EC features + * + * @ec: EC device, does not have to be connected directly to the AP, + * can be daisy chained through another device. + * @feature: One of ec_feature_code bit. + * + * Call this function to test whether the ChromeOS EC supports a feature. + * + * Return: 1 if supported, 0 if not + */ +int cros_ec_check_features(struct cros_ec_dev *ec, int feature) +{ + struct cros_ec_command *msg; + int ret; + + if (ec->features[0] == -1U && ec->features[1] == -1U) { + /* features bitmap not read yet */ + msg = kzalloc(sizeof(*msg) + sizeof(ec->features), GFP_KERNEL); + if (!msg) + return -ENOMEM; + + msg->command = EC_CMD_GET_FEATURES + ec->cmd_offset; + msg->insize = sizeof(ec->features); + + ret = cros_ec_cmd_xfer_status(ec->ec_dev, msg); + if (ret < 0) { + dev_warn(ec->dev, "cannot get EC features: %d/%d\n", + ret, msg->result); + memset(ec->features, 0, sizeof(ec->features)); + } else { + memcpy(ec->features, msg->data, sizeof(ec->features)); + } + + dev_dbg(ec->dev, "EC features %08x %08x\n", + ec->features[0], ec->features[1]); + + kfree(msg); + } + + return ec->features[feature / 32] & EC_FEATURE_MASK_0(feature); +} +EXPORT_SYMBOL_GPL(cros_ec_check_features); + +/** + * cros_ec_get_sensor_count() - Return the number of MEMS sensors supported. + * + * @ec: EC device, does not have to be connected directly to the AP, + * can be daisy chained through another device. + * Return: < 0 in case of error. + */ +int cros_ec_get_sensor_count(struct cros_ec_dev *ec) +{ + /* + * Issue a command to get the number of sensor reported. + * If not supported, check for legacy mode. + */ + int ret, sensor_count; + struct ec_params_motion_sense *params; + struct ec_response_motion_sense *resp; + struct cros_ec_command *msg; + struct cros_ec_device *ec_dev = ec->ec_dev; + u8 status; + + msg = kzalloc(sizeof(*msg) + max(sizeof(*params), sizeof(*resp)), + GFP_KERNEL); + if (!msg) + return -ENOMEM; + + msg->version = 1; + msg->command = EC_CMD_MOTION_SENSE_CMD + ec->cmd_offset; + msg->outsize = sizeof(*params); + msg->insize = sizeof(*resp); + + params = (struct ec_params_motion_sense *)msg->data; + params->cmd = MOTIONSENSE_CMD_DUMP; + + ret = cros_ec_cmd_xfer(ec->ec_dev, msg); + if (ret < 0) { + sensor_count = ret; + } else if (msg->result != EC_RES_SUCCESS) { + sensor_count = -EPROTO; + } else { + resp = (struct ec_response_motion_sense *)msg->data; + sensor_count = resp->dump.sensor_count; + } + kfree(msg); + + /* + * Check legacy mode: Let's find out if sensors are accessible + * via LPC interface. + */ + if (sensor_count == -EPROTO && + ec->cmd_offset == 0 && + ec_dev->cmd_readmem) { + ret = ec_dev->cmd_readmem(ec_dev, EC_MEMMAP_ACC_STATUS, + 1, &status); + if (ret >= 0 && + (status & EC_MEMMAP_ACC_STATUS_PRESENCE_BIT)) { + /* + * We have 2 sensors, one in the lid, one in the base. + */ + sensor_count = 2; + } else { + /* + * EC uses LPC interface and no sensors are presented. + */ + sensor_count = 0; + } + } else if (sensor_count == -EPROTO) { + /* EC responded, but does not understand DUMP command. */ + sensor_count = 0; + } + return sensor_count; +} +EXPORT_SYMBOL_GPL(cros_ec_get_sensor_count); diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h index 0d4e4aaed37a..f3de0662135d 100644 --- a/include/linux/platform_data/cros_ec_proto.h +++ b/include/linux/platform_data/cros_ec_proto.h @@ -12,6 +12,7 @@ #include #include +#include #include #define CROS_EC_DEV_NAME "cros_ec" @@ -213,4 +214,8 @@ int cros_ec_get_next_event(struct cros_ec_device *ec_dev, bool *wake_event); u32 cros_ec_get_host_event(struct cros_ec_device *ec_dev); +int cros_ec_check_features(struct cros_ec_dev *ec, int feature); + +int cros_ec_get_sensor_count(struct cros_ec_dev *ec); + #endif /* __LINUX_CROS_EC_PROTO_H */ -- cgit v1.2.3 From 53067471188c4066fc393ab892d0a74482eac000 Mon Sep 17 00:00:00 2001 From: Gwendal Grignou Date: Tue, 19 Nov 2019 13:45:45 +0100 Subject: iio / platform: cros_ec: Add cros-ec-sensorhub driver Similar to HID sensor stack, the new driver sits between cros-ec-dev and the IIO device drivers: The EC based IIO device topology would be: iio:device1 -> ...0/0000:00:1f.0/PNP0C09:00/GOOG0004:00/cros-ec-dev.6.auto/ cros-ec-sensorhub.7.auto/ cros-ec-accel.15.auto/ iio:device1 It will be expanded to control EC sensor FIFO. Signed-off-by: Gwendal Grignou Reviewed-by: Jonathan Cameron [Fix "unknown type name 'uint32_t'" type errors] Reported-by: kbuild test robot Signed-off-by: Enric Balletbo i Serra --- drivers/iio/common/cros_ec_sensors/Kconfig | 2 +- drivers/platform/chrome/Kconfig | 12 ++ drivers/platform/chrome/Makefile | 1 + drivers/platform/chrome/cros_ec_sensorhub.c | 199 ++++++++++++++++++++++++ include/linux/platform_data/cros_ec_sensorhub.h | 22 +++ 5 files changed, 235 insertions(+), 1 deletion(-) create mode 100644 drivers/platform/chrome/cros_ec_sensorhub.c create mode 100644 include/linux/platform_data/cros_ec_sensorhub.h (limited to 'include') diff --git a/drivers/iio/common/cros_ec_sensors/Kconfig b/drivers/iio/common/cros_ec_sensors/Kconfig index cdbb29cfb907..fefad9572790 100644 --- a/drivers/iio/common/cros_ec_sensors/Kconfig +++ b/drivers/iio/common/cros_ec_sensors/Kconfig @@ -4,7 +4,7 @@ # config IIO_CROS_EC_SENSORS_CORE tristate "ChromeOS EC Sensors Core" - depends on SYSFS && CROS_EC + depends on SYSFS && CROS_EC_SENSORHUB select IIO_BUFFER select IIO_TRIGGERED_BUFFER help diff --git a/drivers/platform/chrome/Kconfig b/drivers/platform/chrome/Kconfig index ee5f08ea57b6..884ac9a287f2 100644 --- a/drivers/platform/chrome/Kconfig +++ b/drivers/platform/chrome/Kconfig @@ -190,6 +190,18 @@ config CROS_EC_DEBUGFS To compile this driver as a module, choose M here: the module will be called cros_ec_debugfs. +config CROS_EC_SENSORHUB + tristate "ChromeOS EC MEMS Sensor Hub" + depends on CROS_EC + help + Allow loading IIO sensors. This driver is loaded by MFD and will in + turn query the EC and register the sensors. + It also spreads the sensor data coming from the EC to the IIO sensor + object. + + To compile this driver as a module, choose M here: the + module will be called cros_ec_sensorhub. + config CROS_EC_SYSFS tristate "ChromeOS EC control and information through sysfs" depends on MFD_CROS_EC_DEV && SYSFS diff --git a/drivers/platform/chrome/Makefile b/drivers/platform/chrome/Makefile index 477ec3d1d1c9..aacd5920d8a1 100644 --- a/drivers/platform/chrome/Makefile +++ b/drivers/platform/chrome/Makefile @@ -19,6 +19,7 @@ obj-$(CONFIG_CROS_EC_CHARDEV) += cros_ec_chardev.o obj-$(CONFIG_CROS_EC_LIGHTBAR) += cros_ec_lightbar.o obj-$(CONFIG_CROS_EC_VBC) += cros_ec_vbc.o obj-$(CONFIG_CROS_EC_DEBUGFS) += cros_ec_debugfs.o +obj-$(CONFIG_CROS_EC_SENSORHUB) += cros_ec_sensorhub.o obj-$(CONFIG_CROS_EC_SYSFS) += cros_ec_sysfs.o obj-$(CONFIG_CROS_USBPD_LOGGER) += cros_usbpd_logger.o diff --git a/drivers/platform/chrome/cros_ec_sensorhub.c b/drivers/platform/chrome/cros_ec_sensorhub.c new file mode 100644 index 000000000000..04d8879689e9 --- /dev/null +++ b/drivers/platform/chrome/cros_ec_sensorhub.c @@ -0,0 +1,199 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Sensor HUB driver that discovers sensors behind a ChromeOS Embedded + * Controller. + * + * Copyright 2019 Google LLC + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define DRV_NAME "cros-ec-sensorhub" + +static void cros_ec_sensorhub_free_sensor(void *arg) +{ + struct platform_device *pdev = arg; + + platform_device_unregister(pdev); +} + +static int cros_ec_sensorhub_allocate_sensor(struct device *parent, + char *sensor_name, + int sensor_num) +{ + struct cros_ec_sensor_platform sensor_platforms = { + .sensor_num = sensor_num, + }; + struct platform_device *pdev; + + pdev = platform_device_register_data(parent, sensor_name, + PLATFORM_DEVID_AUTO, + &sensor_platforms, + sizeof(sensor_platforms)); + if (IS_ERR(pdev)) + return PTR_ERR(pdev); + + return devm_add_action_or_reset(parent, + cros_ec_sensorhub_free_sensor, + pdev); +} + +static int cros_ec_sensorhub_register(struct device *dev, + struct cros_ec_sensorhub *sensorhub) +{ + int sensor_type[MOTIONSENSE_TYPE_MAX] = { 0 }; + struct cros_ec_dev *ec = sensorhub->ec; + struct ec_params_motion_sense *params; + struct ec_response_motion_sense *resp; + struct cros_ec_command *msg; + int ret, i, sensor_num; + char *name; + + sensor_num = cros_ec_get_sensor_count(ec); + if (sensor_num < 0) { + dev_err(dev, + "Unable to retrieve sensor information (err:%d)\n", + sensor_num); + return sensor_num; + } + + if (sensor_num == 0) { + dev_err(dev, "Zero sensors reported.\n"); + return -EINVAL; + } + + /* Prepare a message to send INFO command to each sensor. */ + msg = kzalloc(sizeof(*msg) + max(sizeof(*params), sizeof(*resp)), + GFP_KERNEL); + if (!msg) + return -ENOMEM; + + msg->version = 1; + msg->command = EC_CMD_MOTION_SENSE_CMD + ec->cmd_offset; + msg->outsize = sizeof(*params); + msg->insize = sizeof(*resp); + params = (struct ec_params_motion_sense *)msg->data; + resp = (struct ec_response_motion_sense *)msg->data; + + for (i = 0; i < sensor_num; i++) { + params->cmd = MOTIONSENSE_CMD_INFO; + params->info.sensor_num = i; + + ret = cros_ec_cmd_xfer_status(ec->ec_dev, msg); + if (ret < 0) { + dev_warn(dev, "no info for EC sensor %d : %d/%d\n", + i, ret, msg->result); + continue; + } + + switch (resp->info.type) { + case MOTIONSENSE_TYPE_ACCEL: + name = "cros-ec-accel"; + break; + case MOTIONSENSE_TYPE_BARO: + name = "cros-ec-baro"; + break; + case MOTIONSENSE_TYPE_GYRO: + name = "cros-ec-gyro"; + break; + case MOTIONSENSE_TYPE_MAG: + name = "cros-ec-mag"; + break; + case MOTIONSENSE_TYPE_PROX: + name = "cros-ec-prox"; + break; + case MOTIONSENSE_TYPE_LIGHT: + name = "cros-ec-light"; + break; + case MOTIONSENSE_TYPE_ACTIVITY: + name = "cros-ec-activity"; + break; + default: + dev_warn(dev, "unknown type %d\n", resp->info.type); + continue; + } + + ret = cros_ec_sensorhub_allocate_sensor(dev, name, i); + if (ret) + goto error; + + sensor_type[resp->info.type]++; + } + + if (sensor_type[MOTIONSENSE_TYPE_ACCEL] >= 2) + ec->has_kb_wake_angle = true; + + if (cros_ec_check_features(ec, + EC_FEATURE_REFINED_TABLET_MODE_HYSTERESIS)) { + ret = cros_ec_sensorhub_allocate_sensor(dev, + "cros-ec-lid-angle", + 0); + if (ret) + goto error; + } + + kfree(msg); + return 0; + +error: + kfree(msg); + return ret; +} + +static int cros_ec_sensorhub_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct cros_ec_sensorhub *data; + int ret; + int i; + + data = devm_kzalloc(dev, sizeof(struct cros_ec_sensorhub), GFP_KERNEL); + if (!data) + return -ENOMEM; + + data->ec = dev_get_drvdata(dev->parent); + dev_set_drvdata(dev, data); + + /* Check whether this EC is a sensor hub. */ + if (cros_ec_check_features(data->ec, EC_FEATURE_MOTION_SENSE)) { + ret = cros_ec_sensorhub_register(dev, data); + if (ret) + return ret; + } else { + /* + * If the device has sensors but does not claim to + * be a sensor hub, we are in legacy mode. + */ + for (i = 0; i < 2; i++) { + ret = cros_ec_sensorhub_allocate_sensor(dev, + "cros-ec-accel-legacy", i); + if (ret) + return ret; + } + } + + return 0; +} + +static struct platform_driver cros_ec_sensorhub_driver = { + .driver = { + .name = DRV_NAME, + }, + .probe = cros_ec_sensorhub_probe, +}; + +module_platform_driver(cros_ec_sensorhub_driver); + +MODULE_ALIAS("platform:" DRV_NAME); +MODULE_AUTHOR("Gwendal Grignou "); +MODULE_DESCRIPTION("ChromeOS EC MEMS Sensor Hub Driver"); +MODULE_LICENSE("GPL"); diff --git a/include/linux/platform_data/cros_ec_sensorhub.h b/include/linux/platform_data/cros_ec_sensorhub.h new file mode 100644 index 000000000000..5f6f9bb65079 --- /dev/null +++ b/include/linux/platform_data/cros_ec_sensorhub.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Chrome OS EC MEMS Sensor Hub driver. + * + * Copyright 2019 Google LLC + */ + +#ifndef __LINUX_PLATFORM_DATA_CROS_EC_SENSORHUB_H +#define __LINUX_PLATFORM_DATA_CROS_EC_SENSORHUB_H + +#include + +/** + * struct cros_ec_sensorhub - Sensor Hub device data. + * + * @ec: Embedded Controller where the hub is located. + */ +struct cros_ec_sensorhub { + struct cros_ec_dev *ec; +}; + +#endif /* __LINUX_PLATFORM_DATA_CROS_EC_SENSORHUB_H */ -- cgit v1.2.3 From d60ac88a62df71cb12b2d60d2dae5658fb4eab43 Mon Sep 17 00:00:00 2001 From: Gwendal Grignou Date: Tue, 19 Nov 2019 13:45:45 +0100 Subject: mfd / platform / iio: cros_ec: Register sensor through sensorhub Remove the duplicated code in MFD, since MFD just registers cros-ec-sensorhub if at least one sensor is present. Change IIO cros-ec driver to get the pointer to the cros-ec-dev through cros-ec-sensorhub. Signed-off-by: Gwendal Grignou Acked-by: Jonathan Cameron Acked-by: Lee Jones Signed-off-by: Enric Balletbo i Serra --- drivers/iio/accel/cros_ec_accel_legacy.c | 6 - .../iio/common/cros_ec_sensors/cros_ec_sensors.c | 6 - .../common/cros_ec_sensors/cros_ec_sensors_core.c | 4 +- drivers/iio/light/cros_ec_light_prox.c | 6 - drivers/mfd/cros_ec_dev.c | 203 ++------------------- include/linux/platform_data/cros_ec_proto.h | 8 - include/linux/platform_data/cros_ec_sensorhub.h | 8 + 7 files changed, 23 insertions(+), 218 deletions(-) (limited to 'include') diff --git a/drivers/iio/accel/cros_ec_accel_legacy.c b/drivers/iio/accel/cros_ec_accel_legacy.c index fcc3f999e482..65f85faf6f31 100644 --- a/drivers/iio/accel/cros_ec_accel_legacy.c +++ b/drivers/iio/accel/cros_ec_accel_legacy.c @@ -163,16 +163,10 @@ static const struct iio_chan_spec cros_ec_accel_legacy_channels[] = { static int cros_ec_accel_legacy_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; - struct cros_ec_dev *ec = dev_get_drvdata(dev->parent); struct iio_dev *indio_dev; struct cros_ec_sensors_core_state *state; int ret; - if (!ec || !ec->ec_dev) { - dev_warn(&pdev->dev, "No EC device found.\n"); - return -EINVAL; - } - indio_dev = devm_iio_device_alloc(&pdev->dev, sizeof(*state)); if (!indio_dev) return -ENOMEM; diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c index a6987726eeb8..7dce04473467 100644 --- a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c +++ b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c @@ -222,17 +222,11 @@ static const struct iio_info ec_sensors_info = { static int cros_ec_sensors_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; - struct cros_ec_dev *ec_dev = dev_get_drvdata(dev->parent); struct iio_dev *indio_dev; struct cros_ec_sensors_state *state; struct iio_chan_spec *channel; int ret, i; - if (!ec_dev || !ec_dev->ec_dev) { - dev_warn(&pdev->dev, "No CROS EC device found.\n"); - return -EINVAL; - } - indio_dev = devm_iio_device_alloc(&pdev->dev, sizeof(*state)); if (!indio_dev) return -ENOMEM; diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c index d2609e6feda4..81a7f692de2f 100644 --- a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c +++ b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c @@ -18,6 +18,7 @@ #include #include #include +#include #include static char *cros_ec_loc[] = { @@ -88,7 +89,8 @@ int cros_ec_sensors_core_init(struct platform_device *pdev, { struct device *dev = &pdev->dev; struct cros_ec_sensors_core_state *state = iio_priv(indio_dev); - struct cros_ec_dev *ec = dev_get_drvdata(pdev->dev.parent); + struct cros_ec_sensorhub *sensor_hub = dev_get_drvdata(dev->parent); + struct cros_ec_dev *ec = sensor_hub->ec; struct cros_ec_sensor_platform *sensor_platform = dev_get_platdata(dev); u32 ver_mask; int ret, i; diff --git a/drivers/iio/light/cros_ec_light_prox.c b/drivers/iio/light/cros_ec_light_prox.c index c5263b563fc1..d85a391e50c5 100644 --- a/drivers/iio/light/cros_ec_light_prox.c +++ b/drivers/iio/light/cros_ec_light_prox.c @@ -169,17 +169,11 @@ static const struct iio_info cros_ec_light_prox_info = { static int cros_ec_light_prox_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; - struct cros_ec_dev *ec_dev = dev_get_drvdata(dev->parent); struct iio_dev *indio_dev; struct cros_ec_light_prox_state *state; struct iio_chan_spec *channel; int ret; - if (!ec_dev || !ec_dev->ec_dev) { - dev_warn(dev, "No CROS EC device found.\n"); - return -EINVAL; - } - indio_dev = devm_iio_device_alloc(dev, sizeof(*state)); if (!indio_dev) return -ENOMEM; diff --git a/drivers/mfd/cros_ec_dev.c b/drivers/mfd/cros_ec_dev.c index a35104e35cb4..c4b977a5dd96 100644 --- a/drivers/mfd/cros_ec_dev.c +++ b/drivers/mfd/cros_ec_dev.c @@ -78,6 +78,10 @@ static const struct mfd_cell cros_ec_rtc_cells[] = { { .name = "cros-ec-rtc", }, }; +static const struct mfd_cell cros_ec_sensorhub_cells[] = { + { .name = "cros-ec-sensorhub", }, +}; + static const struct mfd_cell cros_usbpd_charger_cells[] = { { .name = "cros-usbpd-charger", }, { .name = "cros-usbpd-logger", }, @@ -117,192 +121,6 @@ static void cros_ec_class_release(struct device *dev) kfree(to_cros_ec_dev(dev)); } -static void cros_ec_sensors_register(struct cros_ec_dev *ec) -{ - /* - * Issue a command to get the number of sensor reported. - * Build an array of sensors driver and register them all. - */ - int ret, i, id, sensor_num; - struct mfd_cell *sensor_cells; - struct cros_ec_sensor_platform *sensor_platforms; - int sensor_type[MOTIONSENSE_TYPE_MAX]; - struct ec_params_motion_sense *params; - struct ec_response_motion_sense *resp; - struct cros_ec_command *msg; - - msg = kzalloc(sizeof(struct cros_ec_command) + - max(sizeof(*params), sizeof(*resp)), GFP_KERNEL); - if (msg == NULL) - return; - - msg->version = 2; - msg->command = EC_CMD_MOTION_SENSE_CMD + ec->cmd_offset; - msg->outsize = sizeof(*params); - msg->insize = sizeof(*resp); - - params = (struct ec_params_motion_sense *)msg->data; - params->cmd = MOTIONSENSE_CMD_DUMP; - - ret = cros_ec_cmd_xfer_status(ec->ec_dev, msg); - if (ret < 0) { - dev_warn(ec->dev, "cannot get EC sensor information: %d/%d\n", - ret, msg->result); - goto error; - } - - resp = (struct ec_response_motion_sense *)msg->data; - sensor_num = resp->dump.sensor_count; - /* - * Allocate 2 extra sensors if lid angle sensor and/or FIFO are needed. - */ - sensor_cells = kcalloc(sensor_num + 2, sizeof(struct mfd_cell), - GFP_KERNEL); - if (sensor_cells == NULL) - goto error; - - sensor_platforms = kcalloc(sensor_num, - sizeof(struct cros_ec_sensor_platform), - GFP_KERNEL); - if (sensor_platforms == NULL) - goto error_platforms; - - memset(sensor_type, 0, sizeof(sensor_type)); - id = 0; - for (i = 0; i < sensor_num; i++) { - params->cmd = MOTIONSENSE_CMD_INFO; - params->info.sensor_num = i; - ret = cros_ec_cmd_xfer_status(ec->ec_dev, msg); - if (ret < 0) { - dev_warn(ec->dev, "no info for EC sensor %d : %d/%d\n", - i, ret, msg->result); - continue; - } - switch (resp->info.type) { - case MOTIONSENSE_TYPE_ACCEL: - sensor_cells[id].name = "cros-ec-accel"; - break; - case MOTIONSENSE_TYPE_BARO: - sensor_cells[id].name = "cros-ec-baro"; - break; - case MOTIONSENSE_TYPE_GYRO: - sensor_cells[id].name = "cros-ec-gyro"; - break; - case MOTIONSENSE_TYPE_MAG: - sensor_cells[id].name = "cros-ec-mag"; - break; - case MOTIONSENSE_TYPE_PROX: - sensor_cells[id].name = "cros-ec-prox"; - break; - case MOTIONSENSE_TYPE_LIGHT: - sensor_cells[id].name = "cros-ec-light"; - break; - case MOTIONSENSE_TYPE_ACTIVITY: - sensor_cells[id].name = "cros-ec-activity"; - break; - default: - dev_warn(ec->dev, "unknown type %d\n", resp->info.type); - continue; - } - sensor_platforms[id].sensor_num = i; - sensor_cells[id].id = sensor_type[resp->info.type]; - sensor_cells[id].platform_data = &sensor_platforms[id]; - sensor_cells[id].pdata_size = - sizeof(struct cros_ec_sensor_platform); - - sensor_type[resp->info.type]++; - id++; - } - - if (sensor_type[MOTIONSENSE_TYPE_ACCEL] >= 2) - ec->has_kb_wake_angle = true; - - if (cros_ec_check_features(ec, EC_FEATURE_MOTION_SENSE_FIFO)) { - sensor_cells[id].name = "cros-ec-ring"; - id++; - } - if (cros_ec_check_features(ec, - EC_FEATURE_REFINED_TABLET_MODE_HYSTERESIS)) { - sensor_cells[id].name = "cros-ec-lid-angle"; - id++; - } - - ret = mfd_add_devices(ec->dev, 0, sensor_cells, id, - NULL, 0, NULL); - if (ret) - dev_err(ec->dev, "failed to add EC sensors\n"); - - kfree(sensor_platforms); -error_platforms: - kfree(sensor_cells); -error: - kfree(msg); -} - -static struct cros_ec_sensor_platform sensor_platforms[] = { - { .sensor_num = 0 }, - { .sensor_num = 1 } -}; - -static const struct mfd_cell cros_ec_accel_legacy_cells[] = { - { - .name = "cros-ec-accel-legacy", - .platform_data = &sensor_platforms[0], - .pdata_size = sizeof(struct cros_ec_sensor_platform), - }, - { - .name = "cros-ec-accel-legacy", - .platform_data = &sensor_platforms[1], - .pdata_size = sizeof(struct cros_ec_sensor_platform), - } -}; - -static void cros_ec_accel_legacy_register(struct cros_ec_dev *ec) -{ - struct cros_ec_device *ec_dev = ec->ec_dev; - u8 status; - int ret; - - /* - * ECs that need legacy support are the main EC, directly connected to - * the AP. - */ - if (ec->cmd_offset != 0) - return; - - /* - * Check if EC supports direct memory reads and if EC has - * accelerometers. - */ - if (ec_dev->cmd_readmem) { - ret = ec_dev->cmd_readmem(ec_dev, EC_MEMMAP_ACC_STATUS, 1, - &status); - if (ret < 0) { - dev_warn(ec->dev, "EC direct read error.\n"); - return; - } - - /* Check if EC has accelerometers. */ - if (!(status & EC_MEMMAP_ACC_STATUS_PRESENCE_BIT)) { - dev_info(ec->dev, "EC does not have accelerometers.\n"); - return; - } - } - - /* - * The device may still support accelerometers: - * it would be an older ARM based device that do not suppor the - * EC_CMD_GET_FEATURES command. - * - * Register 2 accelerometers, we will fail in the IIO driver if there - * are no sensors. - */ - ret = mfd_add_hotplug_devices(ec->dev, cros_ec_accel_legacy_cells, - ARRAY_SIZE(cros_ec_accel_legacy_cells)); - if (ret) - dev_err(ec_dev->dev, "failed to add EC sensors\n"); -} - static int ec_device_probe(struct platform_device *pdev) { int retval = -ENOMEM; @@ -358,11 +176,14 @@ static int ec_device_probe(struct platform_device *pdev) goto failed; /* check whether this EC is a sensor hub. */ - if (cros_ec_check_features(ec, EC_FEATURE_MOTION_SENSE)) - cros_ec_sensors_register(ec); - else - /* Workaroud for older EC firmware */ - cros_ec_accel_legacy_register(ec); + if (cros_ec_get_sensor_count(ec) > 0) { + retval = mfd_add_hotplug_devices(ec->dev, + cros_ec_sensorhub_cells, + ARRAY_SIZE(cros_ec_sensorhub_cells)); + if (retval) + dev_err(ec->dev, "failed to add %s subdevice: %d\n", + cros_ec_sensorhub_cells->name, retval); + } /* * The following subdevices can be detected by sending the diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h index f3de0662135d..691f9e953a96 100644 --- a/include/linux/platform_data/cros_ec_proto.h +++ b/include/linux/platform_data/cros_ec_proto.h @@ -168,14 +168,6 @@ struct cros_ec_device { struct platform_device *pd; }; -/** - * struct cros_ec_sensor_platform - ChromeOS EC sensor platform information. - * @sensor_num: Id of the sensor, as reported by the EC. - */ -struct cros_ec_sensor_platform { - u8 sensor_num; -}; - /** * struct cros_ec_platform - ChromeOS EC platform information. * @ec_name: Name of EC device (e.g. 'cros-ec', 'cros-pd', ...) diff --git a/include/linux/platform_data/cros_ec_sensorhub.h b/include/linux/platform_data/cros_ec_sensorhub.h index 5f6f9bb65079..bef7ffc7fce1 100644 --- a/include/linux/platform_data/cros_ec_sensorhub.h +++ b/include/linux/platform_data/cros_ec_sensorhub.h @@ -10,6 +10,14 @@ #include +/** + * struct cros_ec_sensor_platform - ChromeOS EC sensor platform information. + * @sensor_num: Id of the sensor, as reported by the EC. + */ +struct cros_ec_sensor_platform { + u8 sensor_num; +}; + /** * struct cros_ec_sensorhub - Sensor Hub device data. * -- cgit v1.2.3 From 05a3c420eaa6857cb20afe7e3a3c39ed94a3b2c1 Mon Sep 17 00:00:00 2001 From: Gwendal Grignou Date: Tue, 19 Nov 2019 13:45:46 +0100 Subject: platform/chrome: cros-ec: Record event timestamp in the hard irq To improve sensor timestamp precision, given EC and AP are in different time domains, the AP needs to try to record the exact moment an event was signalled to the AP by the EC as soon as possible after it happens. First thing in the hard irq is the best place for this. Signed-off-by: Gwendal Grignou Acked-by: Jonathan Cameron Acked-by: Lee Jones Signed-off-by: Enric Balletbo i Serra --- drivers/platform/chrome/cros_ec.c | 17 ++++++++++++++--- drivers/platform/chrome/cros_ec_ishtp.c | 17 +++++++++++++++-- drivers/platform/chrome/cros_ec_lpc.c | 2 ++ include/linux/platform_data/cros_ec_proto.h | 16 ++++++++++++++++ 4 files changed, 47 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/platform/chrome/cros_ec.c b/drivers/platform/chrome/cros_ec.c index 9b2d07422e17..925f84dbf621 100644 --- a/drivers/platform/chrome/cros_ec.c +++ b/drivers/platform/chrome/cros_ec.c @@ -31,6 +31,15 @@ static struct cros_ec_platform pd_p = { .cmd_offset = EC_CMD_PASSTHRU_OFFSET(CROS_EC_DEV_PD_INDEX), }; +static irqreturn_t ec_irq_handler(int irq, void *data) +{ + struct cros_ec_device *ec_dev = data; + + ec_dev->last_event_time = cros_ec_get_time_ns(); + + return IRQ_WAKE_THREAD; +} + static irqreturn_t ec_irq_thread(int irq, void *data) { struct cros_ec_device *ec_dev = data; @@ -141,9 +150,11 @@ int cros_ec_register(struct cros_ec_device *ec_dev) } if (ec_dev->irq) { - err = devm_request_threaded_irq(dev, ec_dev->irq, NULL, - ec_irq_thread, IRQF_TRIGGER_LOW | IRQF_ONESHOT, - "chromeos-ec", ec_dev); + err = devm_request_threaded_irq(dev, ec_dev->irq, + ec_irq_handler, + ec_irq_thread, + IRQF_TRIGGER_LOW | IRQF_ONESHOT, + "chromeos-ec", ec_dev); if (err) { dev_err(dev, "Failed to request IRQ %d: %d", ec_dev->irq, err); diff --git a/drivers/platform/chrome/cros_ec_ishtp.c b/drivers/platform/chrome/cros_ec_ishtp.c index 25ca2c894b4d..5c848f22b44b 100644 --- a/drivers/platform/chrome/cros_ec_ishtp.c +++ b/drivers/platform/chrome/cros_ec_ishtp.c @@ -200,13 +200,14 @@ static int ish_send(struct ishtp_cl_data *client_data, * process_recv() - Received and parse incoming packet * @cros_ish_cl: Client instance to get stats * @rb_in_proc: Host interface message buffer + * @timestamp: Timestamp of when parent callback started * * Parse the incoming packet. If it is a response packet then it will * update per instance flags and wake up the caller waiting to for the * response. If it is an event packet then it will schedule event work. */ static void process_recv(struct ishtp_cl *cros_ish_cl, - struct ishtp_cl_rb *rb_in_proc) + struct ishtp_cl_rb *rb_in_proc, ktime_t timestamp) { size_t data_len = rb_in_proc->buf_idx; struct ishtp_cl_data *client_data = @@ -295,6 +296,11 @@ error_wake_up: break; case CROS_MKBP_EVENT: + /* + * Set timestamp from beginning of function since we actually + * got an incoming MKBP event + */ + client_data->ec_dev->last_event_time = timestamp; /* The event system doesn't send any data in buffer */ schedule_work(&client_data->work_ec_evt); @@ -322,10 +328,17 @@ static void ish_event_cb(struct ishtp_cl_device *cl_device) { struct ishtp_cl_rb *rb_in_proc; struct ishtp_cl *cros_ish_cl = ishtp_get_drvdata(cl_device); + ktime_t timestamp; + + /* + * Take timestamp as close to hardware interrupt as possible for sensor + * timestamps. + */ + timestamp = cros_ec_get_time_ns(); while ((rb_in_proc = ishtp_cl_rx_get_rb(cros_ish_cl)) != NULL) { /* Decide what to do with received data */ - process_recv(cros_ish_cl, rb_in_proc); + process_recv(cros_ish_cl, rb_in_proc, timestamp); } } diff --git a/drivers/platform/chrome/cros_ec_lpc.c b/drivers/platform/chrome/cros_ec_lpc.c index 7d10d909435f..3c77496e164d 100644 --- a/drivers/platform/chrome/cros_ec_lpc.c +++ b/drivers/platform/chrome/cros_ec_lpc.c @@ -313,6 +313,8 @@ static void cros_ec_lpc_acpi_notify(acpi_handle device, u32 value, void *data) { struct cros_ec_device *ec_dev = data; + ec_dev->last_event_time = cros_ec_get_time_ns(); + if (ec_dev->mkbp_event_supported && cros_ec_get_next_event(ec_dev, NULL) > 0) blocking_notifier_call_chain(&ec_dev->event_notifier, 0, diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h index 691f9e953a96..02dc34f366d7 100644 --- a/include/linux/platform_data/cros_ec_proto.h +++ b/include/linux/platform_data/cros_ec_proto.h @@ -122,6 +122,8 @@ struct cros_ec_command { * @event_data: Raw payload transferred with the MKBP event. * @event_size: Size in bytes of the event data. * @host_event_wake_mask: Mask of host events that cause wake from suspend. + * @last_event_time: exact time from the hard irq when we got notified of + * a new event. * @ec: The platform_device used by the mfd driver to interface with the * main EC. * @pd: The platform_device used by the mfd driver to interface with the @@ -162,6 +164,7 @@ struct cros_ec_device { int event_size; u32 host_event_wake_mask; u32 last_resume_result; + ktime_t last_event_time; /* The platform devices used by the mfd driver */ struct platform_device *ec; @@ -210,4 +213,17 @@ int cros_ec_check_features(struct cros_ec_dev *ec, int feature); int cros_ec_get_sensor_count(struct cros_ec_dev *ec); +/** + * cros_ec_get_time_ns() - Return time in ns. + * + * This is the function used to record the time for last_event_time in struct + * cros_ec_device during the hard irq. + * + * Return: ktime_t format since boot. + */ +static inline ktime_t cros_ec_get_time_ns(void) +{ + return ktime_get_boottime_ns(); +} + #endif /* __LINUX_CROS_EC_PROTO_H */ -- cgit v1.2.3 From 3300fdd630d4d3d96e3ba9af63a740d3a4e8fc61 Mon Sep 17 00:00:00 2001 From: Enrico Granata Date: Tue, 19 Nov 2019 13:45:46 +0100 Subject: platform/chrome: cros_ec: handle MKBP more events flag The ChromeOS EC has support for signaling to the host that a single IRQ can serve multiple MKBP (Matrix KeyBoard Protocol) events. Doing this serves an optimization purpose, as it minimizes the number of round-trips into the interrupt handling machinery, and it proves beneficial to sensor timestamping as it keeps the desired synchronization of event times between the two processors. This patch adds kernel support for this EC feature, allowing the ec_irq to loop until all events have been served. Signed-off-by: Enrico Granata Signed-off-by: Gwendal Grignou Reviewed-by: Jonathan Cameron Acked-by: Lee Jones Signed-off-by: Enric Balletbo i Serra --- drivers/platform/chrome/cros_ec.c | 34 ++++++++++-- drivers/platform/chrome/cros_ec_ishtp.c | 8 +-- drivers/platform/chrome/cros_ec_lpc.c | 15 ++++-- drivers/platform/chrome/cros_ec_proto.c | 80 ++++++++++++++++++----------- drivers/platform/chrome/cros_ec_rpmsg.c | 19 ++----- include/linux/platform_data/cros_ec_proto.h | 12 +++-- 6 files changed, 107 insertions(+), 61 deletions(-) (limited to 'include') diff --git a/drivers/platform/chrome/cros_ec.c b/drivers/platform/chrome/cros_ec.c index d3dfa27171e6..6d6ce86a1408 100644 --- a/drivers/platform/chrome/cros_ec.c +++ b/drivers/platform/chrome/cros_ec.c @@ -40,13 +40,23 @@ static irqreturn_t ec_irq_handler(int irq, void *data) return IRQ_WAKE_THREAD; } -static irqreturn_t ec_irq_thread(int irq, void *data) +/** + * cros_ec_handle_event() - process and forward pending events on EC + * @ec_dev: Device with events to process. + * + * Call this function in a loop when the kernel is notified that the EC has + * pending events. + * + * Return: true if more events are still pending and this function should be + * called again. + */ +bool cros_ec_handle_event(struct cros_ec_device *ec_dev) { - struct cros_ec_device *ec_dev = data; - bool wake_event = true; + bool wake_event; + bool ec_has_more_events; int ret; - ret = cros_ec_get_next_event(ec_dev, &wake_event); + ret = cros_ec_get_next_event(ec_dev, &wake_event, &ec_has_more_events); /* * Signal only if wake host events or any interrupt if @@ -59,6 +69,20 @@ static irqreturn_t ec_irq_thread(int irq, void *data) if (ret > 0) blocking_notifier_call_chain(&ec_dev->event_notifier, 0, ec_dev); + + return ec_has_more_events; +} +EXPORT_SYMBOL(cros_ec_handle_event); + +static irqreturn_t ec_irq_thread(int irq, void *data) +{ + struct cros_ec_device *ec_dev = data; + bool ec_has_more_events; + + do { + ec_has_more_events = cros_ec_handle_event(ec_dev); + } while (ec_has_more_events); + return IRQ_HANDLED; } @@ -274,7 +298,7 @@ EXPORT_SYMBOL(cros_ec_suspend); static void cros_ec_report_events_during_suspend(struct cros_ec_device *ec_dev) { while (ec_dev->mkbp_event_supported && - cros_ec_get_next_event(ec_dev, NULL) > 0) + cros_ec_get_next_event(ec_dev, NULL, NULL) > 0) blocking_notifier_call_chain(&ec_dev->event_notifier, 1, ec_dev); } diff --git a/drivers/platform/chrome/cros_ec_ishtp.c b/drivers/platform/chrome/cros_ec_ishtp.c index 5c848f22b44b..e5996821d08b 100644 --- a/drivers/platform/chrome/cros_ec_ishtp.c +++ b/drivers/platform/chrome/cros_ec_ishtp.c @@ -136,11 +136,11 @@ static void ish_evt_handler(struct work_struct *work) struct ishtp_cl_data *client_data = container_of(work, struct ishtp_cl_data, work_ec_evt); struct cros_ec_device *ec_dev = client_data->ec_dev; + bool ec_has_more_events; - if (cros_ec_get_next_event(ec_dev, NULL) > 0) { - blocking_notifier_call_chain(&ec_dev->event_notifier, - 0, ec_dev); - } + do { + ec_has_more_events = cros_ec_handle_event(ec_dev); + } while (ec_has_more_events); } /** diff --git a/drivers/platform/chrome/cros_ec_lpc.c b/drivers/platform/chrome/cros_ec_lpc.c index 3c77496e164d..dccf479c6625 100644 --- a/drivers/platform/chrome/cros_ec_lpc.c +++ b/drivers/platform/chrome/cros_ec_lpc.c @@ -312,13 +312,20 @@ static int cros_ec_lpc_readmem(struct cros_ec_device *ec, unsigned int offset, static void cros_ec_lpc_acpi_notify(acpi_handle device, u32 value, void *data) { struct cros_ec_device *ec_dev = data; + bool ec_has_more_events; + int ret; ec_dev->last_event_time = cros_ec_get_time_ns(); - if (ec_dev->mkbp_event_supported && - cros_ec_get_next_event(ec_dev, NULL) > 0) - blocking_notifier_call_chain(&ec_dev->event_notifier, 0, - ec_dev); + if (ec_dev->mkbp_event_supported) + do { + ret = cros_ec_get_next_event(ec_dev, NULL, + &ec_has_more_events); + if (ret > 0) + blocking_notifier_call_chain( + &ec_dev->event_notifier, 0, + ec_dev); + } while (ec_has_more_events); if (value == ACPI_NOTIFY_DEVICE_WAKE) pm_system_wakeup(); diff --git a/drivers/platform/chrome/cros_ec_proto.c b/drivers/platform/chrome/cros_ec_proto.c index 12bdd1f3aee9..da1b1c450433 100644 --- a/drivers/platform/chrome/cros_ec_proto.c +++ b/drivers/platform/chrome/cros_ec_proto.c @@ -456,7 +456,10 @@ int cros_ec_query_all(struct cros_ec_device *ec_dev) if (ret < 0 || ver_mask == 0) ec_dev->mkbp_event_supported = 0; else - ec_dev->mkbp_event_supported = 1; + ec_dev->mkbp_event_supported = fls(ver_mask); + + dev_dbg(ec_dev->dev, "MKBP support version %u\n", + ec_dev->mkbp_event_supported - 1); /* Probe if host sleep v1 is supported for S0ix failure detection. */ ret = cros_ec_get_host_command_version_mask(ec_dev, @@ -569,6 +572,7 @@ EXPORT_SYMBOL(cros_ec_cmd_xfer_status); static int get_next_event_xfer(struct cros_ec_device *ec_dev, struct cros_ec_command *msg, + struct ec_response_get_next_event_v1 *event, int version, uint32_t size) { int ret; @@ -581,7 +585,7 @@ static int get_next_event_xfer(struct cros_ec_device *ec_dev, ret = cros_ec_cmd_xfer(ec_dev, msg); if (ret > 0) { ec_dev->event_size = ret - 1; - memcpy(&ec_dev->event_data, msg->data, ret); + ec_dev->event_data = *event; } return ret; @@ -589,30 +593,26 @@ static int get_next_event_xfer(struct cros_ec_device *ec_dev, static int get_next_event(struct cros_ec_device *ec_dev) { - u8 buffer[sizeof(struct cros_ec_command) + sizeof(ec_dev->event_data)]; - struct cros_ec_command *msg = (struct cros_ec_command *)&buffer; - static int cmd_version = 1; - int ret; + struct { + struct cros_ec_command msg; + struct ec_response_get_next_event_v1 event; + } __packed buf; + struct cros_ec_command *msg = &buf.msg; + struct ec_response_get_next_event_v1 *event = &buf.event; + const int cmd_version = ec_dev->mkbp_event_supported - 1; + memset(msg, 0, sizeof(*msg)); if (ec_dev->suspended) { dev_dbg(ec_dev->dev, "Device suspended.\n"); return -EHOSTDOWN; } - if (cmd_version == 1) { - ret = get_next_event_xfer(ec_dev, msg, cmd_version, - sizeof(struct ec_response_get_next_event_v1)); - if (ret < 0 || msg->result != EC_RES_INVALID_VERSION) - return ret; - - /* Fallback to version 0 for future send attempts */ - cmd_version = 0; - } - - ret = get_next_event_xfer(ec_dev, msg, cmd_version, + if (cmd_version == 0) + return get_next_event_xfer(ec_dev, msg, event, 0, sizeof(struct ec_response_get_next_event)); - return ret; + return get_next_event_xfer(ec_dev, msg, event, cmd_version, + sizeof(struct ec_response_get_next_event_v1)); } static int get_keyboard_state_event(struct cros_ec_device *ec_dev) @@ -639,32 +639,55 @@ static int get_keyboard_state_event(struct cros_ec_device *ec_dev) * @ec_dev: Device to fetch event from. * @wake_event: Pointer to a bool set to true upon return if the event might be * treated as a wake event. Ignored if null. + * @has_more_events: Pointer to bool set to true if more than one event is + * pending. + * Some EC will set this flag to indicate cros_ec_get_next_event() + * can be called multiple times in a row. + * It is an optimization to prevent issuing a EC command for + * nothing or wait for another interrupt from the EC to process + * the next message. + * Ignored if null. * * Return: negative error code on errors; 0 for no data; or else number of * bytes received (i.e., an event was retrieved successfully). Event types are * written out to @ec_dev->event_data.event_type on success. */ -int cros_ec_get_next_event(struct cros_ec_device *ec_dev, bool *wake_event) +int cros_ec_get_next_event(struct cros_ec_device *ec_dev, + bool *wake_event, + bool *has_more_events) { u8 event_type; u32 host_event; int ret; - if (!ec_dev->mkbp_event_supported) { - ret = get_keyboard_state_event(ec_dev); - if (ret <= 0) - return ret; + /* + * Default value for wake_event. + * Wake up on keyboard event, wake up for spurious interrupt or link + * error to the EC. + */ + if (wake_event) + *wake_event = true; - if (wake_event) - *wake_event = true; + /* + * Default value for has_more_events. + * EC will raise another interrupt if AP does not process all events + * anyway. + */ + if (has_more_events) + *has_more_events = false; - return ret; - } + if (!ec_dev->mkbp_event_supported) + return get_keyboard_state_event(ec_dev); ret = get_next_event(ec_dev); if (ret <= 0) return ret; + if (has_more_events) + *has_more_events = ec_dev->event_data.event_type & + EC_MKBP_HAS_MORE_EVENTS; + ec_dev->event_data.event_type &= EC_MKBP_EVENT_TYPE_MASK; + if (wake_event) { event_type = ec_dev->event_data.event_type; host_event = cros_ec_get_host_event(ec_dev); @@ -679,9 +702,6 @@ int cros_ec_get_next_event(struct cros_ec_device *ec_dev, bool *wake_event) else if (host_event && !(host_event & ec_dev->host_event_wake_mask)) *wake_event = false; - /* Consider all other events as wake events. */ - else - *wake_event = true; } return ret; diff --git a/drivers/platform/chrome/cros_ec_rpmsg.c b/drivers/platform/chrome/cros_ec_rpmsg.c index 0c3738c3244d..bd068afe43b5 100644 --- a/drivers/platform/chrome/cros_ec_rpmsg.c +++ b/drivers/platform/chrome/cros_ec_rpmsg.c @@ -143,22 +143,11 @@ cros_ec_rpmsg_host_event_function(struct work_struct *host_event_work) struct cros_ec_rpmsg, host_event_work); struct cros_ec_device *ec_dev = dev_get_drvdata(&ec_rpmsg->rpdev->dev); - bool wake_event = true; - int ret; - - ret = cros_ec_get_next_event(ec_dev, &wake_event); - - /* - * Signal only if wake host events or any interrupt if - * cros_ec_get_next_event() returned an error (default value for - * wake_event is true) - */ - if (wake_event && device_may_wakeup(ec_dev->dev)) - pm_wakeup_event(ec_dev->dev, 0); + bool ec_has_more_events; - if (ret > 0) - blocking_notifier_call_chain(&ec_dev->event_notifier, - 0, ec_dev); + do { + ec_has_more_events = cros_ec_handle_event(ec_dev); + } while (ec_has_more_events); } static int cros_ec_rpmsg_callback(struct rpmsg_device *rpdev, void *data, diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h index 02dc34f366d7..30098a551523 100644 --- a/include/linux/platform_data/cros_ec_proto.h +++ b/include/linux/platform_data/cros_ec_proto.h @@ -116,7 +116,9 @@ struct cros_ec_command { * code. * @pkt_xfer: Send packet to EC and get response. * @lock: One transaction at a time. - * @mkbp_event_supported: True if this EC supports the MKBP event protocol. + * @mkbp_event_supported: 0 if MKBP not supported. Otherwise its value is + * the maximum supported version of the MKBP host event + * command + 1. * @host_sleep_v1: True if this EC supports the sleep v1 command. * @event_notifier: Interrupt event notifier for transport devices. * @event_data: Raw payload transferred with the MKBP event. @@ -156,7 +158,7 @@ struct cros_ec_device { int (*pkt_xfer)(struct cros_ec_device *ec, struct cros_ec_command *msg); struct mutex lock; - bool mkbp_event_supported; + u8 mkbp_event_supported; bool host_sleep_v1; struct blocking_notifier_head event_notifier; @@ -205,7 +207,9 @@ int cros_ec_unregister(struct cros_ec_device *ec_dev); int cros_ec_query_all(struct cros_ec_device *ec_dev); -int cros_ec_get_next_event(struct cros_ec_device *ec_dev, bool *wake_event); +int cros_ec_get_next_event(struct cros_ec_device *ec_dev, + bool *wake_event, + bool *has_more_events); u32 cros_ec_get_host_event(struct cros_ec_device *ec_dev); @@ -213,6 +217,8 @@ int cros_ec_check_features(struct cros_ec_dev *ec, int feature); int cros_ec_get_sensor_count(struct cros_ec_dev *ec); +bool cros_ec_handle_event(struct cros_ec_device *ec_dev); + /** * cros_ec_get_time_ns() - Return time in ns. * -- cgit v1.2.3 From bbd8810d399812f2016713565e4d8ff8f1508aa6 Mon Sep 17 00:00:00 2001 From: Krzysztof Wilczynski Date: Tue, 3 Sep 2019 13:30:59 +0200 Subject: PCI: Remove unused includes and superfluous struct declaration Remove and from being included directly as part of the include/linux/of_pci.h, and remove superfluous declaration of struct of_phandle_args. Move users of include to include and directly rather than rely on both being included transitively through . Link: https://lore.kernel.org/r/20190903113059.2901-1-kw@linux.com Signed-off-by: Krzysztof Wilczynski Signed-off-by: Bjorn Helgaas Reviewed-by: Rob Herring --- drivers/iommu/of_iommu.c | 2 ++ drivers/irqchip/irq-gic-v2m.c | 1 + drivers/irqchip/irq-gic-v3-its-pci-msi.c | 1 + drivers/pci/controller/dwc/pcie-designware-host.c | 1 + drivers/pci/controller/pci-aardvark.c | 1 + drivers/pci/controller/pci-thunder-pem.c | 1 + drivers/pci/pci.c | 1 + drivers/pci/probe.c | 1 + include/linux/of_pci.h | 5 ++--- 9 files changed, 11 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c index 614a93aa5305..026ad2b29dcd 100644 --- a/drivers/iommu/of_iommu.c +++ b/drivers/iommu/of_iommu.c @@ -8,6 +8,8 @@ #include #include #include +#include +#include #include #include #include diff --git a/drivers/irqchip/irq-gic-v2m.c b/drivers/irqchip/irq-gic-v2m.c index e88e75c22b6a..fbec07d634ad 100644 --- a/drivers/irqchip/irq-gic-v2m.c +++ b/drivers/irqchip/irq-gic-v2m.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/irqchip/irq-gic-v3-its-pci-msi.c b/drivers/irqchip/irq-gic-v3-its-pci-msi.c index 229d586c3d7a..87711e0f8014 100644 --- a/drivers/irqchip/irq-gic-v3-its-pci-msi.c +++ b/drivers/irqchip/irq-gic-v3-its-pci-msi.c @@ -5,6 +5,7 @@ */ #include +#include #include #include #include diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c index 0f36a926059a..43ce6de70374 100644 --- a/drivers/pci/controller/dwc/pcie-designware-host.c +++ b/drivers/pci/controller/dwc/pcie-designware-host.c @@ -10,6 +10,7 @@ #include #include +#include #include #include #include diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c index fc0fe4d4de49..3a05f6ca95b0 100644 --- a/drivers/pci/controller/pci-aardvark.c +++ b/drivers/pci/controller/pci-aardvark.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include diff --git a/drivers/pci/controller/pci-thunder-pem.c b/drivers/pci/controller/pci-thunder-pem.c index f127ce8bd4ef..9491e266b1ea 100644 --- a/drivers/pci/controller/pci-thunder-pem.c +++ b/drivers/pci/controller/pci-thunder-pem.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index e7982af9a5d8..2d36995e4ea5 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 3d5271a7a849..7c5d68b807ef 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include #include diff --git a/include/linux/of_pci.h b/include/linux/of_pci.h index 21a89c4880fa..29658c0ee71f 100644 --- a/include/linux/of_pci.h +++ b/include/linux/of_pci.h @@ -2,11 +2,10 @@ #ifndef __OF_PCI_H #define __OF_PCI_H -#include -#include +#include +#include struct pci_dev; -struct of_phandle_args; struct device_node; #if IS_ENABLED(CONFIG_OF) && IS_ENABLED(CONFIG_PCI) -- cgit v1.2.3 From bbdb2f5ecdf1e66b2f09710134db3c2e5c43a958 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 12 Nov 2019 11:07:36 -0600 Subject: PCI: Add #defines for Enter Compliance, Transmit Margin Add definitions for the Enter Compliance and Transmit Margin fields of the PCIe Link Control 2 register. Link: https://lore.kernel.org/r/20191112173503.176611-2-helgaas@kernel.org Signed-off-by: Bjorn Helgaas Reviewed-by: Alex Deucher --- include/uapi/linux/pci_regs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index 29d6e93fd15e..5869e5778a05 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -673,6 +673,8 @@ #define PCI_EXP_LNKCTL2_TLS_8_0GT 0x0003 /* Supported Speed 8GT/s */ #define PCI_EXP_LNKCTL2_TLS_16_0GT 0x0004 /* Supported Speed 16GT/s */ #define PCI_EXP_LNKCTL2_TLS_32_0GT 0x0005 /* Supported Speed 32GT/s */ +#define PCI_EXP_LNKCTL2_ENTER_COMP 0x0010 /* Enter Compliance */ +#define PCI_EXP_LNKCTL2_TX_MARGIN 0x0380 /* Transmit Margin */ #define PCI_EXP_LNKSTA2 50 /* Link Status 2 */ #define PCI_CAP_EXP_ENDPOINT_SIZEOF_V2 52 /* v2 endpoints with link end here */ #define PCI_EXP_SLTCAP2 52 /* Slot Capabilities 2 */ -- cgit v1.2.3 From a264abad51d8ecb7954a2f6d9f1885b38daffc74 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 20 Nov 2019 16:25:52 -0500 Subject: SUNRPC: Capture completion of all RPC tasks RPC tasks on the backchannel never invoke xprt_complete_rqst(), so there is no way to report their tk_status at completion. Also, any RPC task that exits via rpc_exit_task() before it is replied to will also disappear without a trace. Introduce a trace point that is symmetrical with rpc_task_begin that captures the termination status of each RPC task. Sample trace output for callback requests initiated on the server: kworker/u8:12-448 [003] 127.025240: rpc_task_end: task:50@3 flags=ASYNC|DYNAMIC|SOFT|SOFTCONN|SENT runstate=RUNNING|ACTIVE status=0 action=rpc_exit_task kworker/u8:12-448 [002] 127.567310: rpc_task_end: task:51@3 flags=ASYNC|DYNAMIC|SOFT|SOFTCONN|SENT runstate=RUNNING|ACTIVE status=0 action=rpc_exit_task kworker/u8:12-448 [001] 130.506817: rpc_task_end: task:52@3 flags=ASYNC|DYNAMIC|SOFT|SOFTCONN|SENT runstate=RUNNING|ACTIVE status=0 action=rpc_exit_task Odd, though, that I never see trace_rpc_task_complete, either in the forward or backchannel. Should it be removed? Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/trace/events/sunrpc.h | 1 + net/sunrpc/sched.c | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 378233fe5ac7..205bf28bcada 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -165,6 +165,7 @@ DECLARE_EVENT_CLASS(rpc_task_running, DEFINE_RPC_RUNNING_EVENT(begin); DEFINE_RPC_RUNNING_EVENT(run_action); DEFINE_RPC_RUNNING_EVENT(complete); +DEFINE_RPC_RUNNING_EVENT(end); DECLARE_EVENT_CLASS(rpc_task_queued, diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 987c4b1f0b17..9c79548c6847 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -824,6 +824,7 @@ rpc_reset_task_statistics(struct rpc_task *task) */ void rpc_exit_task(struct rpc_task *task) { + trace_rpc_task_end(task, task->tk_action); task->tk_action = NULL; if (task->tk_ops->rpc_count_stats) task->tk_ops->rpc_count_stats(task, task->tk_calldata); -- cgit v1.2.3 From ba30e27405afa0b13b79532a345977b3e58ad501 Mon Sep 17 00:00:00 2001 From: Dennis Zhou Date: Mon, 25 Nov 2019 14:28:04 -0800 Subject: Revert "percpu: add __percpu to SHIFT_PERCPU_PTR" This reverts commit 825dbc6ff7a3a063ea91be7d94af940080b0c991. I mistakenly applied this and only now have thought about it a little more and had time to evaluate a kbuild error for dmaengine. Once we're calling RELOC_HIDE, we're moving back into the __kernel address space and letting users interact with the actual memory address rather than in __percpu which is before adding the offsets. Signed-off-by: Dennis Zhou --- include/linux/percpu-defs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index a49b6c702598..a6fabd865211 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -229,7 +229,7 @@ do { \ * pointer value. The weird cast keeps both GCC and sparse happy. */ #define SHIFT_PERCPU_PTR(__p, __offset) \ - RELOC_HIDE((typeof(*(__p)) __kernel __percpu __force *)(__p), (__offset)) + RELOC_HIDE((typeof(*(__p)) __kernel __force *)(__p), (__offset)) #define per_cpu_ptr(ptr, cpu) \ ({ \ -- cgit v1.2.3 From 02a65a0bfbef5c644f520885a0a85b45b9703cf3 Mon Sep 17 00:00:00 2001 From: Piotr Maziarz Date: Tue, 26 Nov 2019 11:06:31 +0100 Subject: tracing: Fix __print_hex_dump scope undef is needed for parsing __print_hex_dump in traceevent lib. Link: http://lkml.kernel.org/r/1574762791-14883-1-git-send-email-piotrx.maziarz@linux.intel.com Signed-off-by: Piotr Maziarz Signed-off-by: Cezary Rojewski Signed-off-by: Steven Rostedt (VMware) --- include/trace/trace_events.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h index 7089760d4c7a..472b33d23a10 100644 --- a/include/trace/trace_events.h +++ b/include/trace/trace_events.h @@ -757,6 +757,7 @@ static inline void ftrace_test_probe_##call(void) \ #undef __get_str #undef __get_bitmask #undef __print_array +#undef __print_hex_dump #undef TP_printk #define TP_printk(fmt, args...) "\"" fmt "\", " __stringify(args) -- cgit v1.2.3 From d41b0e64d206f8948212b4d0f30c330db95c9636 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 14 Oct 2019 12:04:52 +0200 Subject: PCI/MSI: Remove unused pci_irq_get_node() The function pci_irq_get_node() is not used by anyone in the tree, so just delete it. Link: https://lore.kernel.org/r/20191014100452.GA6699@kroah.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Bjorn Helgaas Reviewed-by: Andrew Murray --- drivers/pci/msi.c | 16 ---------------- include/linux/pci.h | 6 ------ 2 files changed, 22 deletions(-) (limited to 'include') diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index 0884bedcfc7a..f95fe23830f0 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -1315,22 +1315,6 @@ const struct cpumask *pci_irq_get_affinity(struct pci_dev *dev, int nr) } EXPORT_SYMBOL(pci_irq_get_affinity); -/** - * pci_irq_get_node - return the NUMA node of a particular MSI vector - * @pdev: PCI device to operate on - * @vec: device-relative interrupt vector index (0-based). - */ -int pci_irq_get_node(struct pci_dev *pdev, int vec) -{ - const struct cpumask *mask; - - mask = pci_irq_get_affinity(pdev, vec); - if (mask) - return local_memory_node(cpu_to_node(cpumask_first(mask))); - return dev_to_node(&pdev->dev); -} -EXPORT_SYMBOL(pci_irq_get_node); - struct pci_dev *msi_desc_to_pci_dev(struct msi_desc *desc) { return to_pci_dev(desc->dev); diff --git a/include/linux/pci.h b/include/linux/pci.h index f9088c89a534..755d8c0176b9 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1454,7 +1454,6 @@ int pci_alloc_irq_vectors_affinity(struct pci_dev *dev, unsigned int min_vecs, void pci_free_irq_vectors(struct pci_dev *dev); int pci_irq_vector(struct pci_dev *dev, unsigned int nr); const struct cpumask *pci_irq_get_affinity(struct pci_dev *pdev, int vec); -int pci_irq_get_node(struct pci_dev *pdev, int vec); #else static inline int pci_msi_vec_count(struct pci_dev *dev) { return -ENOSYS; } @@ -1497,11 +1496,6 @@ static inline const struct cpumask *pci_irq_get_affinity(struct pci_dev *pdev, { return cpu_possible_mask; } - -static inline int pci_irq_get_node(struct pci_dev *pdev, int vec) -{ - return first_online_node; -} #endif /** -- cgit v1.2.3 From a1b39bae16a62ce4aae02d958224f19316d98b24 Mon Sep 17 00:00:00 2001 From: Michal Simek Date: Fri, 25 Oct 2019 08:10:37 +0200 Subject: asm-generic: Make msi.h a mandatory include/asm header msi.h is generic for all architectures except x86, which has its own version. Enabling MSI by adding msi.h to every architecture's Kbuild is just an additional step which doesn't need to be done. Make msi.h mandatory in the asm-generic/Kbuild so we don't have to do it for each architecture. Suggested-by: Christoph Hellwig Link: https://lore.kernel.org/r/c991669e29a79b1a8e28c3b4b3a125801a693de8.1571983829.git.michal.simek@xilinx.com Tested-by: Paul Walmsley # build only, rv32/rv64 Signed-off-by: Michal Simek Signed-off-by: Bjorn Helgaas Reviewed-by: Masahiro Yamada Acked-by: Waiman Long Acked-by: Paul Walmsley # arch/riscv --- arch/arc/include/asm/Kbuild | 1 - arch/arm/include/asm/Kbuild | 1 - arch/arm64/include/asm/Kbuild | 1 - arch/mips/include/asm/Kbuild | 1 - arch/powerpc/include/asm/Kbuild | 1 - arch/riscv/include/asm/Kbuild | 1 - arch/sparc/include/asm/Kbuild | 1 - include/asm-generic/Kbuild | 1 + 8 files changed, 1 insertion(+), 7 deletions(-) (limited to 'include') diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild index 393d4f5e1450..1b505694691e 100644 --- a/arch/arc/include/asm/Kbuild +++ b/arch/arc/include/asm/Kbuild @@ -17,7 +17,6 @@ generic-y += local64.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h generic-y += mmiowb.h -generic-y += msi.h generic-y += parport.h generic-y += percpu.h generic-y += preempt.h diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild index 68ca86f85eb7..fa579b23b4df 100644 --- a/arch/arm/include/asm/Kbuild +++ b/arch/arm/include/asm/Kbuild @@ -12,7 +12,6 @@ generic-y += local.h generic-y += local64.h generic-y += mm-arch-hooks.h generic-y += mmiowb.h -generic-y += msi.h generic-y += parport.h generic-y += preempt.h generic-y += seccomp.h diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild index 98a5405c8558..bd23f87d6c55 100644 --- a/arch/arm64/include/asm/Kbuild +++ b/arch/arm64/include/asm/Kbuild @@ -16,7 +16,6 @@ generic-y += local64.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h generic-y += mmiowb.h -generic-y += msi.h generic-y += qrwlock.h generic-y += qspinlock.h generic-y += serial.h diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild index c8b595c60910..61b0fc2026e6 100644 --- a/arch/mips/include/asm/Kbuild +++ b/arch/mips/include/asm/Kbuild @@ -13,7 +13,6 @@ generic-y += irq_work.h generic-y += local64.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h -generic-y += msi.h generic-y += parport.h generic-y += percpu.h generic-y += preempt.h diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild index 64870c7be4a3..17726f2e46de 100644 --- a/arch/powerpc/include/asm/Kbuild +++ b/arch/powerpc/include/asm/Kbuild @@ -10,4 +10,3 @@ generic-y += local64.h generic-y += mcs_spinlock.h generic-y += preempt.h generic-y += vtime.h -generic-y += msi.h diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild index 16970f246860..1efaeddf1e4b 100644 --- a/arch/riscv/include/asm/Kbuild +++ b/arch/riscv/include/asm/Kbuild @@ -22,7 +22,6 @@ generic-y += kvm_para.h generic-y += local.h generic-y += local64.h generic-y += mm-arch-hooks.h -generic-y += msi.h generic-y += percpu.h generic-y += preempt.h generic-y += sections.h diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild index b6212164847b..62de2eb2773d 100644 --- a/arch/sparc/include/asm/Kbuild +++ b/arch/sparc/include/asm/Kbuild @@ -18,7 +18,6 @@ generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h generic-y += mmiowb.h generic-y += module.h -generic-y += msi.h generic-y += preempt.h generic-y += serial.h generic-y += trace_clock.h diff --git a/include/asm-generic/Kbuild b/include/asm-generic/Kbuild index adff14fcb8e4..ddfee1bd9dc1 100644 --- a/include/asm-generic/Kbuild +++ b/include/asm-generic/Kbuild @@ -4,4 +4,5 @@ # (This file is not included when SRCARCH=um since UML borrows several # asm headers from the host architecutre.) +mandatory-y += msi.h mandatory-y += simd.h -- cgit v1.2.3 From a8de1304b7df30e3a14f2a8b9709bb4ff31a0385 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 13 Nov 2019 16:12:02 +0900 Subject: libfdt: define INT32_MAX and UINT32_MAX in libfdt_env.h The DTC v1.5.1 added references to (U)INT32_MAX. This is no problem for user-space programs since defines (U)INT32_MAX along with (u)int32_t. For the kernel space, libfdt_env.h needs to be adjusted before we pull in the changes. In the kernel, we usually use s/u32 instead of (u)int32_t for the fixed-width types. Accordingly, we already have S/U32_MAX for their max values. So, we should not add (U)INT32_MAX to any more. Instead, add them to the in-kernel libfdt_env.h to compile the latest libfdt. Signed-off-by: Masahiro Yamada Signed-off-by: Rob Herring --- arch/arm/boot/compressed/libfdt_env.h | 4 +++- arch/powerpc/boot/libfdt_env.h | 2 ++ include/linux/libfdt_env.h | 3 +++ 3 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/arch/arm/boot/compressed/libfdt_env.h b/arch/arm/boot/compressed/libfdt_env.h index b36c0289a308..6a0f1f524466 100644 --- a/arch/arm/boot/compressed/libfdt_env.h +++ b/arch/arm/boot/compressed/libfdt_env.h @@ -2,11 +2,13 @@ #ifndef _ARM_LIBFDT_ENV_H #define _ARM_LIBFDT_ENV_H +#include #include #include #include -#define INT_MAX ((int)(~0U>>1)) +#define INT32_MAX S32_MAX +#define UINT32_MAX U32_MAX typedef __be16 fdt16_t; typedef __be32 fdt32_t; diff --git a/arch/powerpc/boot/libfdt_env.h b/arch/powerpc/boot/libfdt_env.h index 2abc8e83b95e..9757d4f6331e 100644 --- a/arch/powerpc/boot/libfdt_env.h +++ b/arch/powerpc/boot/libfdt_env.h @@ -6,6 +6,8 @@ #include #define INT_MAX ((int)(~0U>>1)) +#define UINT32_MAX ((u32)~0U) +#define INT32_MAX ((s32)(UINT32_MAX >> 1)) #include "of.h" diff --git a/include/linux/libfdt_env.h b/include/linux/libfdt_env.h index 2231eb855e8f..cea8574a29b1 100644 --- a/include/linux/libfdt_env.h +++ b/include/linux/libfdt_env.h @@ -7,6 +7,9 @@ #include +#define INT32_MAX S32_MAX +#define UINT32_MAX U32_MAX + typedef __be16 fdt16_t; typedef __be32 fdt32_t; typedef __be64 fdt64_t; -- cgit v1.2.3 From 82995cc6c5ae4bf4d72edef381a085e52d5b5905 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 25 Mar 2019 16:38:32 +0000 Subject: libceph, rbd, ceph: convert to use the new mount API Convert the ceph filesystem to the new internal mount API as the old one will be obsoleted and removed. This allows greater flexibility in communication of mount parameters between userspace, the VFS and the filesystem. See Documentation/filesystems/mount_api.txt for more information. [ Numerous string handling, leak and regression fixes; rbd conversion was particularly broken and had to be redone almost from scratch. ] Signed-off-by: David Howells Signed-off-by: Jeff Layton Signed-off-by: Ilya Dryomov --- drivers/block/rbd.c | 262 ++++++++++-------- fs/ceph/cache.c | 9 +- fs/ceph/cache.h | 5 +- fs/ceph/super.c | 646 ++++++++++++++++++++++--------------------- fs/ceph/super.h | 1 - include/linux/ceph/libceph.h | 10 +- net/ceph/ceph_common.c | 419 +++++++++++++--------------- net/ceph/messenger.c | 2 - 8 files changed, 681 insertions(+), 673 deletions(-) (limited to 'include') diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 3a40b5f60810..2b184563cd32 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -34,7 +34,7 @@ #include #include #include -#include +#include #include #include @@ -838,34 +838,34 @@ enum { Opt_queue_depth, Opt_alloc_size, Opt_lock_timeout, - Opt_last_int, /* int args above */ Opt_pool_ns, - Opt_last_string, /* string args above */ Opt_read_only, Opt_read_write, Opt_lock_on_read, Opt_exclusive, Opt_notrim, - Opt_err }; -static match_table_t rbd_opts_tokens = { - {Opt_queue_depth, "queue_depth=%d"}, - {Opt_alloc_size, "alloc_size=%d"}, - {Opt_lock_timeout, "lock_timeout=%d"}, - /* int args above */ - {Opt_pool_ns, "_pool_ns=%s"}, - /* string args above */ - {Opt_read_only, "read_only"}, - {Opt_read_only, "ro"}, /* Alternate spelling */ - {Opt_read_write, "read_write"}, - {Opt_read_write, "rw"}, /* Alternate spelling */ - {Opt_lock_on_read, "lock_on_read"}, - {Opt_exclusive, "exclusive"}, - {Opt_notrim, "notrim"}, - {Opt_err, NULL} +static const struct fs_parameter_spec rbd_param_specs[] = { + fsparam_u32 ("alloc_size", Opt_alloc_size), + fsparam_flag ("exclusive", Opt_exclusive), + fsparam_flag ("lock_on_read", Opt_lock_on_read), + fsparam_u32 ("lock_timeout", Opt_lock_timeout), + fsparam_flag ("notrim", Opt_notrim), + fsparam_string ("_pool_ns", Opt_pool_ns), + fsparam_u32 ("queue_depth", Opt_queue_depth), + fsparam_flag ("read_only", Opt_read_only), + fsparam_flag ("read_write", Opt_read_write), + fsparam_flag ("ro", Opt_read_only), + fsparam_flag ("rw", Opt_read_write), + {} +}; + +static const struct fs_parameter_description rbd_parameters = { + .name = "rbd", + .specs = rbd_param_specs, }; struct rbd_options { @@ -886,87 +886,12 @@ struct rbd_options { #define RBD_EXCLUSIVE_DEFAULT false #define RBD_TRIM_DEFAULT true -struct parse_rbd_opts_ctx { +struct rbd_parse_opts_ctx { struct rbd_spec *spec; + struct ceph_options *copts; struct rbd_options *opts; }; -static int parse_rbd_opts_token(char *c, void *private) -{ - struct parse_rbd_opts_ctx *pctx = private; - substring_t argstr[MAX_OPT_ARGS]; - int token, intval, ret; - - token = match_token(c, rbd_opts_tokens, argstr); - if (token < Opt_last_int) { - ret = match_int(&argstr[0], &intval); - if (ret < 0) { - pr_err("bad option arg (not int) at '%s'\n", c); - return ret; - } - dout("got int token %d val %d\n", token, intval); - } else if (token > Opt_last_int && token < Opt_last_string) { - dout("got string token %d val %s\n", token, argstr[0].from); - } else { - dout("got token %d\n", token); - } - - switch (token) { - case Opt_queue_depth: - if (intval < 1) { - pr_err("queue_depth out of range\n"); - return -EINVAL; - } - pctx->opts->queue_depth = intval; - break; - case Opt_alloc_size: - if (intval < SECTOR_SIZE) { - pr_err("alloc_size out of range\n"); - return -EINVAL; - } - if (!is_power_of_2(intval)) { - pr_err("alloc_size must be a power of 2\n"); - return -EINVAL; - } - pctx->opts->alloc_size = intval; - break; - case Opt_lock_timeout: - /* 0 is "wait forever" (i.e. infinite timeout) */ - if (intval < 0 || intval > INT_MAX / 1000) { - pr_err("lock_timeout out of range\n"); - return -EINVAL; - } - pctx->opts->lock_timeout = msecs_to_jiffies(intval * 1000); - break; - case Opt_pool_ns: - kfree(pctx->spec->pool_ns); - pctx->spec->pool_ns = match_strdup(argstr); - if (!pctx->spec->pool_ns) - return -ENOMEM; - break; - case Opt_read_only: - pctx->opts->read_only = true; - break; - case Opt_read_write: - pctx->opts->read_only = false; - break; - case Opt_lock_on_read: - pctx->opts->lock_on_read = true; - break; - case Opt_exclusive: - pctx->opts->exclusive = true; - break; - case Opt_notrim: - pctx->opts->trim = false; - break; - default: - /* libceph prints "bad option" msg */ - return -EINVAL; - } - - return 0; -} - static char* obj_op_name(enum obj_operation_type op_type) { switch (op_type) { @@ -6423,6 +6348,122 @@ static inline char *dup_token(const char **buf, size_t *lenp) return dup; } +static int rbd_parse_param(struct fs_parameter *param, + struct rbd_parse_opts_ctx *pctx) +{ + struct rbd_options *opt = pctx->opts; + struct fs_parse_result result; + int token, ret; + + ret = ceph_parse_param(param, pctx->copts, NULL); + if (ret != -ENOPARAM) + return ret; + + token = fs_parse(NULL, &rbd_parameters, param, &result); + dout("%s fs_parse '%s' token %d\n", __func__, param->key, token); + if (token < 0) { + if (token == -ENOPARAM) { + return invalf(NULL, "rbd: Unknown parameter '%s'", + param->key); + } + return token; + } + + switch (token) { + case Opt_queue_depth: + if (result.uint_32 < 1) + goto out_of_range; + opt->queue_depth = result.uint_32; + break; + case Opt_alloc_size: + if (result.uint_32 < SECTOR_SIZE) + goto out_of_range; + if (!is_power_of_2(result.uint_32)) { + return invalf(NULL, "rbd: alloc_size must be a power of 2"); + } + opt->alloc_size = result.uint_32; + break; + case Opt_lock_timeout: + /* 0 is "wait forever" (i.e. infinite timeout) */ + if (result.uint_32 > INT_MAX / 1000) + goto out_of_range; + opt->lock_timeout = msecs_to_jiffies(result.uint_32 * 1000); + break; + case Opt_pool_ns: + kfree(pctx->spec->pool_ns); + pctx->spec->pool_ns = param->string; + param->string = NULL; + break; + case Opt_read_only: + opt->read_only = true; + break; + case Opt_read_write: + opt->read_only = false; + break; + case Opt_lock_on_read: + opt->lock_on_read = true; + break; + case Opt_exclusive: + opt->exclusive = true; + break; + case Opt_notrim: + opt->trim = false; + break; + default: + BUG(); + } + + return 0; + +out_of_range: + return invalf(NULL, "rbd: %s out of range", param->key); +} + +/* + * This duplicates most of generic_parse_monolithic(), untying it from + * fs_context and skipping standard superblock and security options. + */ +static int rbd_parse_options(char *options, struct rbd_parse_opts_ctx *pctx) +{ + char *key; + int ret = 0; + + dout("%s '%s'\n", __func__, options); + while ((key = strsep(&options, ",")) != NULL) { + if (*key) { + struct fs_parameter param = { + .key = key, + .type = fs_value_is_string, + }; + char *value = strchr(key, '='); + size_t v_len = 0; + + if (value) { + if (value == key) + continue; + *value++ = 0; + v_len = strlen(value); + } + + + if (v_len > 0) { + param.string = kmemdup_nul(value, v_len, + GFP_KERNEL); + if (!param.string) + return -ENOMEM; + } + param.size = v_len; + + ret = rbd_parse_param(¶m, pctx); + kfree(param.string); + if (ret) + break; + } + } + + return ret; +} + /* * Parse the options provided for an "rbd add" (i.e., rbd image * mapping) request. These arrive via a write to /sys/bus/rbd/add, @@ -6474,8 +6515,7 @@ static int rbd_add_parse_args(const char *buf, const char *mon_addrs; char *snap_name; size_t mon_addrs_size; - struct parse_rbd_opts_ctx pctx = { 0 }; - struct ceph_options *copts; + struct rbd_parse_opts_ctx pctx = { 0 }; int ret; /* The first four tokens are required */ @@ -6486,7 +6526,7 @@ static int rbd_add_parse_args(const char *buf, return -EINVAL; } mon_addrs = buf; - mon_addrs_size = len + 1; + mon_addrs_size = len; buf += len; ret = -EINVAL; @@ -6536,6 +6576,10 @@ static int rbd_add_parse_args(const char *buf, *(snap_name + len) = '\0'; pctx.spec->snap_name = snap_name; + pctx.copts = ceph_alloc_options(); + if (!pctx.copts) + goto out_mem; + /* Initialize all rbd options to the defaults */ pctx.opts = kzalloc(sizeof(*pctx.opts), GFP_KERNEL); @@ -6550,27 +6594,27 @@ static int rbd_add_parse_args(const char *buf, pctx.opts->exclusive = RBD_EXCLUSIVE_DEFAULT; pctx.opts->trim = RBD_TRIM_DEFAULT; - copts = ceph_parse_options(options, mon_addrs, - mon_addrs + mon_addrs_size - 1, - parse_rbd_opts_token, &pctx); - if (IS_ERR(copts)) { - ret = PTR_ERR(copts); + ret = ceph_parse_mon_ips(mon_addrs, mon_addrs_size, pctx.copts, NULL); + if (ret) goto out_err; - } - kfree(options); - *ceph_opts = copts; + ret = rbd_parse_options(options, &pctx); + if (ret) + goto out_err; + + *ceph_opts = pctx.copts; *opts = pctx.opts; *rbd_spec = pctx.spec; - + kfree(options); return 0; + out_mem: ret = -ENOMEM; out_err: kfree(pctx.opts); + ceph_destroy_options(pctx.copts); rbd_spec_put(pctx.spec); kfree(options); - return ret; } diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c index b2ec29eeb4c4..73f24f307a4a 100644 --- a/fs/ceph/cache.c +++ b/fs/ceph/cache.c @@ -8,6 +8,7 @@ #include +#include #include "super.h" #include "cache.h" @@ -49,7 +50,7 @@ void ceph_fscache_unregister(void) fscache_unregister_netfs(&ceph_cache_netfs); } -int ceph_fscache_register_fs(struct ceph_fs_client* fsc) +int ceph_fscache_register_fs(struct ceph_fs_client* fsc, struct fs_context *fc) { const struct ceph_fsid *fsid = &fsc->client->fsid; const char *fscache_uniq = fsc->mount_options->fscache_uniq; @@ -66,8 +67,8 @@ int ceph_fscache_register_fs(struct ceph_fs_client* fsc) if (uniq_len && memcmp(ent->uniquifier, fscache_uniq, uniq_len)) continue; - pr_err("fscache cookie already registered for fsid %pU\n", fsid); - pr_err(" use fsc=%%s mount option to specify a uniquifier\n"); + errorf(fc, "ceph: fscache cookie already registered for fsid %pU, use fsc= option", + fsid); err = -EBUSY; goto out_unlock; } @@ -95,7 +96,7 @@ int ceph_fscache_register_fs(struct ceph_fs_client* fsc) list_add_tail(&ent->list, &ceph_fscache_list); } else { kfree(ent); - pr_err("unable to register fscache cookie for fsid %pU\n", + errorf(fc, "ceph: unable to register fscache cookie for fsid %pU", fsid); /* all other fs ignore this error */ } diff --git a/fs/ceph/cache.h b/fs/ceph/cache.h index e486fac3434d..89dbdd1eb14a 100644 --- a/fs/ceph/cache.h +++ b/fs/ceph/cache.h @@ -16,7 +16,7 @@ extern struct fscache_netfs ceph_cache_netfs; int ceph_fscache_register(void); void ceph_fscache_unregister(void); -int ceph_fscache_register_fs(struct ceph_fs_client* fsc); +int ceph_fscache_register_fs(struct ceph_fs_client* fsc, struct fs_context *fc); void ceph_fscache_unregister_fs(struct ceph_fs_client* fsc); void ceph_fscache_register_inode_cookie(struct inode *inode); @@ -88,7 +88,8 @@ static inline void ceph_fscache_unregister(void) { } -static inline int ceph_fscache_register_fs(struct ceph_fs_client* fsc) +static inline int ceph_fscache_register_fs(struct ceph_fs_client* fsc, + struct fs_context *fc) { return 0; } diff --git a/fs/ceph/super.c b/fs/ceph/super.c index b47f43fc2d68..9c9a7c68eea3 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -9,7 +9,8 @@ #include #include #include -#include +#include +#include #include #include #include @@ -138,280 +139,308 @@ enum { Opt_readdir_max_entries, Opt_readdir_max_bytes, Opt_congestion_kb, - Opt_last_int, /* int args above */ Opt_snapdirname, Opt_mds_namespace, - Opt_fscache_uniq, Opt_recover_session, - Opt_last_string, + Opt_source, /* string args above */ Opt_dirstat, - Opt_nodirstat, Opt_rbytes, - Opt_norbytes, Opt_asyncreaddir, - Opt_noasyncreaddir, Opt_dcache, - Opt_nodcache, Opt_ino32, - Opt_noino32, Opt_fscache, - Opt_nofscache, Opt_poolperm, - Opt_nopoolperm, Opt_require_active_mds, - Opt_norequire_active_mds, -#ifdef CONFIG_CEPH_FS_POSIX_ACL Opt_acl, -#endif - Opt_noacl, Opt_quotadf, - Opt_noquotadf, Opt_copyfrom, - Opt_nocopyfrom, }; -static match_table_t fsopt_tokens = { - {Opt_wsize, "wsize=%d"}, - {Opt_rsize, "rsize=%d"}, - {Opt_rasize, "rasize=%d"}, - {Opt_caps_wanted_delay_min, "caps_wanted_delay_min=%d"}, - {Opt_caps_wanted_delay_max, "caps_wanted_delay_max=%d"}, - {Opt_caps_max, "caps_max=%d"}, - {Opt_readdir_max_entries, "readdir_max_entries=%d"}, - {Opt_readdir_max_bytes, "readdir_max_bytes=%d"}, - {Opt_congestion_kb, "write_congestion_kb=%d"}, - /* int args above */ - {Opt_snapdirname, "snapdirname=%s"}, - {Opt_mds_namespace, "mds_namespace=%s"}, - {Opt_recover_session, "recover_session=%s"}, - {Opt_fscache_uniq, "fsc=%s"}, - /* string args above */ - {Opt_dirstat, "dirstat"}, - {Opt_nodirstat, "nodirstat"}, - {Opt_rbytes, "rbytes"}, - {Opt_norbytes, "norbytes"}, - {Opt_asyncreaddir, "asyncreaddir"}, - {Opt_noasyncreaddir, "noasyncreaddir"}, - {Opt_dcache, "dcache"}, - {Opt_nodcache, "nodcache"}, - {Opt_ino32, "ino32"}, - {Opt_noino32, "noino32"}, - {Opt_fscache, "fsc"}, - {Opt_nofscache, "nofsc"}, - {Opt_poolperm, "poolperm"}, - {Opt_nopoolperm, "nopoolperm"}, - {Opt_require_active_mds, "require_active_mds"}, - {Opt_norequire_active_mds, "norequire_active_mds"}, -#ifdef CONFIG_CEPH_FS_POSIX_ACL - {Opt_acl, "acl"}, -#endif - {Opt_noacl, "noacl"}, - {Opt_quotadf, "quotadf"}, - {Opt_noquotadf, "noquotadf"}, - {Opt_copyfrom, "copyfrom"}, - {Opt_nocopyfrom, "nocopyfrom"}, - {-1, NULL} +enum ceph_recover_session_mode { + ceph_recover_session_no, + ceph_recover_session_clean +}; + +static const struct fs_parameter_enum ceph_mount_param_enums[] = { + { Opt_recover_session, "no", ceph_recover_session_no }, + { Opt_recover_session, "clean", ceph_recover_session_clean }, + {} +}; + +static const struct fs_parameter_spec ceph_mount_param_specs[] = { + fsparam_flag_no ("acl", Opt_acl), + fsparam_flag_no ("asyncreaddir", Opt_asyncreaddir), + fsparam_u32 ("caps_max", Opt_caps_max), + fsparam_u32 ("caps_wanted_delay_max", Opt_caps_wanted_delay_max), + fsparam_u32 ("caps_wanted_delay_min", Opt_caps_wanted_delay_min), + fsparam_s32 ("write_congestion_kb", Opt_congestion_kb), + fsparam_flag_no ("copyfrom", Opt_copyfrom), + fsparam_flag_no ("dcache", Opt_dcache), + fsparam_flag_no ("dirstat", Opt_dirstat), + __fsparam (fs_param_is_string, "fsc", Opt_fscache, + fs_param_neg_with_no | fs_param_v_optional), + fsparam_flag_no ("ino32", Opt_ino32), + fsparam_string ("mds_namespace", Opt_mds_namespace), + fsparam_flag_no ("poolperm", Opt_poolperm), + fsparam_flag_no ("quotadf", Opt_quotadf), + fsparam_u32 ("rasize", Opt_rasize), + fsparam_flag_no ("rbytes", Opt_rbytes), + fsparam_s32 ("readdir_max_bytes", Opt_readdir_max_bytes), + fsparam_s32 ("readdir_max_entries", Opt_readdir_max_entries), + fsparam_enum ("recover_session", Opt_recover_session), + fsparam_flag_no ("require_active_mds", Opt_require_active_mds), + fsparam_u32 ("rsize", Opt_rsize), + fsparam_string ("snapdirname", Opt_snapdirname), + fsparam_string ("source", Opt_source), + fsparam_u32 ("wsize", Opt_wsize), + {} +}; + +static const struct fs_parameter_description ceph_mount_parameters = { + .name = "ceph", + .specs = ceph_mount_param_specs, + .enums = ceph_mount_param_enums, }; -static int parse_fsopt_token(char *c, void *private) +struct ceph_parse_opts_ctx { + struct ceph_options *copts; + struct ceph_mount_options *opts; +}; + +/* + * Parse the source parameter. Distinguish the server list from the path. + * Internally we do not include the leading '/' in the path. + * + * The source will look like: + * [,...]:[] + * where + * is [:] + * is optional, but if present must begin with '/' + */ +static int ceph_parse_source(struct fs_parameter *param, struct fs_context *fc) { - struct ceph_mount_options *fsopt = private; - substring_t argstr[MAX_OPT_ARGS]; - int token, intval, ret; + struct ceph_parse_opts_ctx *pctx = fc->fs_private; + struct ceph_mount_options *fsopt = pctx->opts; + char *dev_name = param->string, *dev_name_end; + int ret; - token = match_token((char *)c, fsopt_tokens, argstr); - if (token < 0) - return -EINVAL; + dout("%s '%s'\n", __func__, dev_name); + if (!dev_name || !*dev_name) + return invalf(fc, "ceph: Empty source"); - if (token < Opt_last_int) { - ret = match_int(&argstr[0], &intval); - if (ret < 0) { - pr_err("bad option arg (not int) at '%s'\n", c); - return ret; + dev_name_end = strchr(dev_name, '/'); + if (dev_name_end) { + if (strlen(dev_name_end) > 1) { + kfree(fsopt->server_path); + fsopt->server_path = kstrdup(dev_name_end, GFP_KERNEL); + if (!fsopt->server_path) + return -ENOMEM; } - dout("got int token %d val %d\n", token, intval); - } else if (token > Opt_last_int && token < Opt_last_string) { - dout("got string token %d val %s\n", token, - argstr[0].from); } else { - dout("got token %d\n", token); + dev_name_end = dev_name + strlen(dev_name); } + dev_name_end--; /* back up to ':' separator */ + if (dev_name_end < dev_name || *dev_name_end != ':') + return invalf(fc, "ceph: No path or : separator in source"); + + dout("device name '%.*s'\n", (int)(dev_name_end - dev_name), dev_name); + if (fsopt->server_path) + dout("server path '%s'\n", fsopt->server_path); + + ret = ceph_parse_mon_ips(param->string, dev_name_end - dev_name, + pctx->copts, fc); + if (ret) + return ret; + + fc->source = param->string; + param->string = NULL; + return 0; +} + +static int ceph_parse_mount_param(struct fs_context *fc, + struct fs_parameter *param) +{ + struct ceph_parse_opts_ctx *pctx = fc->fs_private; + struct ceph_mount_options *fsopt = pctx->opts; + struct fs_parse_result result; + unsigned int mode; + int token, ret; + + ret = ceph_parse_param(param, pctx->copts, fc); + if (ret != -ENOPARAM) + return ret; + + token = fs_parse(fc, &ceph_mount_parameters, param, &result); + dout("%s fs_parse '%s' token %d\n", __func__, param->key, token); + if (token < 0) + return token; + switch (token) { case Opt_snapdirname: kfree(fsopt->snapdir_name); - fsopt->snapdir_name = kstrndup(argstr[0].from, - argstr[0].to-argstr[0].from, - GFP_KERNEL); - if (!fsopt->snapdir_name) - return -ENOMEM; + fsopt->snapdir_name = param->string; + param->string = NULL; break; case Opt_mds_namespace: kfree(fsopt->mds_namespace); - fsopt->mds_namespace = kstrndup(argstr[0].from, - argstr[0].to-argstr[0].from, - GFP_KERNEL); - if (!fsopt->mds_namespace) - return -ENOMEM; + fsopt->mds_namespace = param->string; + param->string = NULL; break; case Opt_recover_session: - if (!strncmp(argstr[0].from, "no", - argstr[0].to - argstr[0].from)) { + mode = result.uint_32; + if (mode == ceph_recover_session_no) fsopt->flags &= ~CEPH_MOUNT_OPT_CLEANRECOVER; - } else if (!strncmp(argstr[0].from, "clean", - argstr[0].to - argstr[0].from)) { + else if (mode == ceph_recover_session_clean) fsopt->flags |= CEPH_MOUNT_OPT_CLEANRECOVER; - } else { - return -EINVAL; - } - break; - case Opt_fscache_uniq: -#ifdef CONFIG_CEPH_FSCACHE - kfree(fsopt->fscache_uniq); - fsopt->fscache_uniq = kstrndup(argstr[0].from, - argstr[0].to-argstr[0].from, - GFP_KERNEL); - if (!fsopt->fscache_uniq) - return -ENOMEM; - fsopt->flags |= CEPH_MOUNT_OPT_FSCACHE; + else + BUG(); break; -#else - pr_err("fscache support is disabled\n"); - return -EINVAL; -#endif + case Opt_source: + if (fc->source) + return invalf(fc, "ceph: Multiple sources specified"); + return ceph_parse_source(param, fc); case Opt_wsize: - if (intval < (int)PAGE_SIZE || intval > CEPH_MAX_WRITE_SIZE) - return -EINVAL; - fsopt->wsize = ALIGN(intval, PAGE_SIZE); + if (result.uint_32 < PAGE_SIZE || + result.uint_32 > CEPH_MAX_WRITE_SIZE) + goto out_of_range; + fsopt->wsize = ALIGN(result.uint_32, PAGE_SIZE); break; case Opt_rsize: - if (intval < (int)PAGE_SIZE || intval > CEPH_MAX_READ_SIZE) - return -EINVAL; - fsopt->rsize = ALIGN(intval, PAGE_SIZE); + if (result.uint_32 < PAGE_SIZE || + result.uint_32 > CEPH_MAX_READ_SIZE) + goto out_of_range; + fsopt->rsize = ALIGN(result.uint_32, PAGE_SIZE); break; case Opt_rasize: - if (intval < 0) - return -EINVAL; - fsopt->rasize = ALIGN(intval, PAGE_SIZE); + fsopt->rasize = ALIGN(result.uint_32, PAGE_SIZE); break; case Opt_caps_wanted_delay_min: - if (intval < 1) - return -EINVAL; - fsopt->caps_wanted_delay_min = intval; + if (result.uint_32 < 1) + goto out_of_range; + fsopt->caps_wanted_delay_min = result.uint_32; break; case Opt_caps_wanted_delay_max: - if (intval < 1) - return -EINVAL; - fsopt->caps_wanted_delay_max = intval; + if (result.uint_32 < 1) + goto out_of_range; + fsopt->caps_wanted_delay_max = result.uint_32; break; case Opt_caps_max: - if (intval < 0) - return -EINVAL; - fsopt->caps_max = intval; + fsopt->caps_max = result.uint_32; break; case Opt_readdir_max_entries: - if (intval < 1) - return -EINVAL; - fsopt->max_readdir = intval; + if (result.uint_32 < 1) + goto out_of_range; + fsopt->max_readdir = result.uint_32; break; case Opt_readdir_max_bytes: - if (intval < (int)PAGE_SIZE && intval != 0) - return -EINVAL; - fsopt->max_readdir_bytes = intval; + if (result.uint_32 < PAGE_SIZE && result.uint_32 != 0) + goto out_of_range; + fsopt->max_readdir_bytes = result.uint_32; break; case Opt_congestion_kb: - if (intval < 1024) /* at least 1M */ - return -EINVAL; - fsopt->congestion_kb = intval; + if (result.uint_32 < 1024) /* at least 1M */ + goto out_of_range; + fsopt->congestion_kb = result.uint_32; break; case Opt_dirstat: - fsopt->flags |= CEPH_MOUNT_OPT_DIRSTAT; - break; - case Opt_nodirstat: - fsopt->flags &= ~CEPH_MOUNT_OPT_DIRSTAT; + if (!result.negated) + fsopt->flags |= CEPH_MOUNT_OPT_DIRSTAT; + else + fsopt->flags &= ~CEPH_MOUNT_OPT_DIRSTAT; break; case Opt_rbytes: - fsopt->flags |= CEPH_MOUNT_OPT_RBYTES; - break; - case Opt_norbytes: - fsopt->flags &= ~CEPH_MOUNT_OPT_RBYTES; + if (!result.negated) + fsopt->flags |= CEPH_MOUNT_OPT_RBYTES; + else + fsopt->flags &= ~CEPH_MOUNT_OPT_RBYTES; break; case Opt_asyncreaddir: - fsopt->flags &= ~CEPH_MOUNT_OPT_NOASYNCREADDIR; - break; - case Opt_noasyncreaddir: - fsopt->flags |= CEPH_MOUNT_OPT_NOASYNCREADDIR; + if (!result.negated) + fsopt->flags &= ~CEPH_MOUNT_OPT_NOASYNCREADDIR; + else + fsopt->flags |= CEPH_MOUNT_OPT_NOASYNCREADDIR; break; case Opt_dcache: - fsopt->flags |= CEPH_MOUNT_OPT_DCACHE; - break; - case Opt_nodcache: - fsopt->flags &= ~CEPH_MOUNT_OPT_DCACHE; + if (!result.negated) + fsopt->flags |= CEPH_MOUNT_OPT_DCACHE; + else + fsopt->flags &= ~CEPH_MOUNT_OPT_DCACHE; break; case Opt_ino32: - fsopt->flags |= CEPH_MOUNT_OPT_INO32; - break; - case Opt_noino32: - fsopt->flags &= ~CEPH_MOUNT_OPT_INO32; + if (!result.negated) + fsopt->flags |= CEPH_MOUNT_OPT_INO32; + else + fsopt->flags &= ~CEPH_MOUNT_OPT_INO32; break; + case Opt_fscache: #ifdef CONFIG_CEPH_FSCACHE - fsopt->flags |= CEPH_MOUNT_OPT_FSCACHE; kfree(fsopt->fscache_uniq); fsopt->fscache_uniq = NULL; + if (result.negated) { + fsopt->flags &= ~CEPH_MOUNT_OPT_FSCACHE; + } else { + fsopt->flags |= CEPH_MOUNT_OPT_FSCACHE; + fsopt->fscache_uniq = param->string; + param->string = NULL; + } break; #else - pr_err("fscache support is disabled\n"); - return -EINVAL; + return invalf(fc, "ceph: fscache support is disabled"); #endif - case Opt_nofscache: - fsopt->flags &= ~CEPH_MOUNT_OPT_FSCACHE; - kfree(fsopt->fscache_uniq); - fsopt->fscache_uniq = NULL; - break; case Opt_poolperm: - fsopt->flags &= ~CEPH_MOUNT_OPT_NOPOOLPERM; - break; - case Opt_nopoolperm: - fsopt->flags |= CEPH_MOUNT_OPT_NOPOOLPERM; + if (!result.negated) + fsopt->flags &= ~CEPH_MOUNT_OPT_NOPOOLPERM; + else + fsopt->flags |= CEPH_MOUNT_OPT_NOPOOLPERM; break; case Opt_require_active_mds: - fsopt->flags &= ~CEPH_MOUNT_OPT_MOUNTWAIT; - break; - case Opt_norequire_active_mds: - fsopt->flags |= CEPH_MOUNT_OPT_MOUNTWAIT; + if (!result.negated) + fsopt->flags &= ~CEPH_MOUNT_OPT_MOUNTWAIT; + else + fsopt->flags |= CEPH_MOUNT_OPT_MOUNTWAIT; break; case Opt_quotadf: - fsopt->flags &= ~CEPH_MOUNT_OPT_NOQUOTADF; - break; - case Opt_noquotadf: - fsopt->flags |= CEPH_MOUNT_OPT_NOQUOTADF; + if (!result.negated) + fsopt->flags &= ~CEPH_MOUNT_OPT_NOQUOTADF; + else + fsopt->flags |= CEPH_MOUNT_OPT_NOQUOTADF; break; case Opt_copyfrom: - fsopt->flags &= ~CEPH_MOUNT_OPT_NOCOPYFROM; - break; - case Opt_nocopyfrom: - fsopt->flags |= CEPH_MOUNT_OPT_NOCOPYFROM; + if (!result.negated) + fsopt->flags &= ~CEPH_MOUNT_OPT_NOCOPYFROM; + else + fsopt->flags |= CEPH_MOUNT_OPT_NOCOPYFROM; break; -#ifdef CONFIG_CEPH_FS_POSIX_ACL case Opt_acl: - fsopt->sb_flags |= SB_POSIXACL; - break; + if (!result.negated) { +#ifdef CONFIG_CEPH_FS_POSIX_ACL + fc->sb_flags |= SB_POSIXACL; +#else + return invalf(fc, "ceph: POSIX ACL support is disabled"); #endif - case Opt_noacl: - fsopt->sb_flags &= ~SB_POSIXACL; + } else { + fc->sb_flags &= ~SB_POSIXACL; + } break; default: - BUG_ON(token); + BUG(); } return 0; + +out_of_range: + return invalf(fc, "ceph: %s out of range", param->key); } static void destroy_mount_options(struct ceph_mount_options *args) { dout("destroy_mount_options %p\n", args); + if (!args) + return; + kfree(args->snapdir_name); kfree(args->mds_namespace); kfree(args->server_path); @@ -459,91 +488,6 @@ static int compare_mount_options(struct ceph_mount_options *new_fsopt, return ceph_compare_options(new_opt, fsc->client); } -static int parse_mount_options(struct ceph_mount_options **pfsopt, - struct ceph_options **popt, - int flags, char *options, - const char *dev_name) -{ - struct ceph_mount_options *fsopt; - const char *dev_name_end; - int err; - - if (!dev_name || !*dev_name) - return -EINVAL; - - fsopt = kzalloc(sizeof(*fsopt), GFP_KERNEL); - if (!fsopt) - return -ENOMEM; - - dout("parse_mount_options %p, dev_name '%s'\n", fsopt, dev_name); - - fsopt->sb_flags = flags; - fsopt->flags = CEPH_MOUNT_OPT_DEFAULT; - - fsopt->wsize = CEPH_MAX_WRITE_SIZE; - fsopt->rsize = CEPH_MAX_READ_SIZE; - fsopt->rasize = CEPH_RASIZE_DEFAULT; - fsopt->snapdir_name = kstrdup(CEPH_SNAPDIRNAME_DEFAULT, GFP_KERNEL); - if (!fsopt->snapdir_name) { - err = -ENOMEM; - goto out; - } - - fsopt->caps_wanted_delay_min = CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT; - fsopt->caps_wanted_delay_max = CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT; - fsopt->max_readdir = CEPH_MAX_READDIR_DEFAULT; - fsopt->max_readdir_bytes = CEPH_MAX_READDIR_BYTES_DEFAULT; - fsopt->congestion_kb = default_congestion_kb(); - - /* - * Distinguish the server list from the path in "dev_name". - * Internally we do not include the leading '/' in the path. - * - * "dev_name" will look like: - * [,...]:[] - * where - * is [:] - * is optional, but if present must begin with '/' - */ - dev_name_end = strchr(dev_name, '/'); - if (dev_name_end) { - if (strlen(dev_name_end) > 1) { - fsopt->server_path = kstrdup(dev_name_end, GFP_KERNEL); - if (!fsopt->server_path) { - err = -ENOMEM; - goto out; - } - } - } else { - dev_name_end = dev_name + strlen(dev_name); - } - err = -EINVAL; - dev_name_end--; /* back up to ':' separator */ - if (dev_name_end < dev_name || *dev_name_end != ':') { - pr_err("device name is missing path (no : separator in %s)\n", - dev_name); - goto out; - } - dout("device name '%.*s'\n", (int)(dev_name_end - dev_name), dev_name); - if (fsopt->server_path) - dout("server path '%s'\n", fsopt->server_path); - - *popt = ceph_parse_options(options, dev_name, dev_name_end, - parse_fsopt_token, (void *)fsopt); - if (IS_ERR(*popt)) { - err = PTR_ERR(*popt); - goto out; - } - - /* success */ - *pfsopt = fsopt; - return 0; - -out: - destroy_mount_options(fsopt); - return err; -} - /** * ceph_show_options - Show mount options in /proc/mounts * @m: seq_file to write to @@ -587,7 +531,7 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root) seq_puts(m, ",noquotadf"); #ifdef CONFIG_CEPH_FS_POSIX_ACL - if (fsopt->sb_flags & SB_POSIXACL) + if (root->d_sb->s_flags & SB_POSIXACL) seq_puts(m, ",acl"); else seq_puts(m, ",noacl"); @@ -860,12 +804,6 @@ static void ceph_umount_begin(struct super_block *sb) fsc->filp_gen++; // invalidate open files } -static int ceph_remount(struct super_block *sb, int *flags, char *data) -{ - sync_filesystem(sb); - return 0; -} - static const struct super_operations ceph_super_ops = { .alloc_inode = ceph_alloc_inode, .free_inode = ceph_free_inode, @@ -874,7 +812,6 @@ static const struct super_operations ceph_super_ops = { .evict_inode = ceph_evict_inode, .sync_fs = ceph_sync_fs, .put_super = ceph_put_super, - .remount_fs = ceph_remount, .show_options = ceph_show_options, .statfs = ceph_statfs, .umount_begin = ceph_umount_begin, @@ -935,7 +872,8 @@ out: /* * mount: join the ceph cluster, and open root directory. */ -static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc) +static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc, + struct fs_context *fc) { int err; unsigned long started = jiffies; /* note the start time */ @@ -952,7 +890,7 @@ static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc) /* setup fscache */ if (fsc->mount_options->flags & CEPH_MOUNT_OPT_FSCACHE) { - err = ceph_fscache_register_fs(fsc); + err = ceph_fscache_register_fs(fsc, fc); if (err < 0) goto out; } @@ -987,18 +925,16 @@ out: return ERR_PTR(err); } -static int ceph_set_super(struct super_block *s, void *data) +static int ceph_set_super(struct super_block *s, struct fs_context *fc) { - struct ceph_fs_client *fsc = data; + struct ceph_fs_client *fsc = s->s_fs_info; int ret; - dout("set_super %p data %p\n", s, data); + dout("set_super %p\n", s); - s->s_flags = fsc->mount_options->sb_flags; s->s_maxbytes = MAX_LFS_FILESIZE; s->s_xattr = ceph_xattr_handlers; - s->s_fs_info = fsc; fsc->sb = s; fsc->max_file_size = 1ULL << 40; /* temp value until we get mdsmap */ @@ -1010,24 +946,18 @@ static int ceph_set_super(struct super_block *s, void *data) s->s_time_min = 0; s->s_time_max = U32_MAX; - ret = set_anon_super(s, NULL); /* what is that second arg for? */ + ret = set_anon_super_fc(s, fc); if (ret != 0) - goto fail; - - return ret; - -fail: - s->s_fs_info = NULL; - fsc->sb = NULL; + fsc->sb = NULL; return ret; } /* * share superblock if same fs AND options */ -static int ceph_compare_super(struct super_block *sb, void *data) +static int ceph_compare_super(struct super_block *sb, struct fs_context *fc) { - struct ceph_fs_client *new = data; + struct ceph_fs_client *new = fc->s_fs_info; struct ceph_mount_options *fsopt = new->mount_options; struct ceph_options *opt = new->client->options; struct ceph_fs_client *other = ceph_sb_to_client(sb); @@ -1043,7 +973,7 @@ static int ceph_compare_super(struct super_block *sb, void *data) dout("fsid doesn't match\n"); return 0; } - if (fsopt->sb_flags != other->mount_options->sb_flags) { + if (fc->sb_flags != (sb->s_flags & ~SB_BORN)) { dout("flags differ\n"); return 0; } @@ -1073,46 +1003,46 @@ static int ceph_setup_bdi(struct super_block *sb, struct ceph_fs_client *fsc) return 0; } -static struct dentry *ceph_mount(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data) +static int ceph_get_tree(struct fs_context *fc) { + struct ceph_parse_opts_ctx *pctx = fc->fs_private; struct super_block *sb; struct ceph_fs_client *fsc; struct dentry *res; + int (*compare_super)(struct super_block *, struct fs_context *) = + ceph_compare_super; int err; - int (*compare_super)(struct super_block *, void *) = ceph_compare_super; - struct ceph_mount_options *fsopt = NULL; - struct ceph_options *opt = NULL; - dout("ceph_mount\n"); + dout("ceph_get_tree\n"); + + if (!fc->source) + return invalf(fc, "ceph: No source"); #ifdef CONFIG_CEPH_FS_POSIX_ACL - flags |= SB_POSIXACL; + fc->sb_flags |= SB_POSIXACL; #endif - err = parse_mount_options(&fsopt, &opt, flags, data, dev_name); - if (err < 0) { - res = ERR_PTR(err); - goto out_final; - } /* create client (which we may/may not use) */ - fsc = create_fs_client(fsopt, opt); + fsc = create_fs_client(pctx->opts, pctx->copts); + pctx->opts = NULL; + pctx->copts = NULL; if (IS_ERR(fsc)) { - res = ERR_CAST(fsc); + err = PTR_ERR(fsc); goto out_final; } err = ceph_mdsc_init(fsc); - if (err < 0) { - res = ERR_PTR(err); + if (err < 0) goto out; - } if (ceph_test_opt(fsc->client, NOSHARE)) compare_super = NULL; - sb = sget(fs_type, compare_super, ceph_set_super, flags, fsc); + + fc->s_fs_info = fsc; + sb = sget_fc(fc, compare_super, ceph_set_super); + fc->s_fs_info = NULL; if (IS_ERR(sb)) { - res = ERR_CAST(sb); + err = PTR_ERR(sb); goto out; } @@ -1123,18 +1053,19 @@ static struct dentry *ceph_mount(struct file_system_type *fs_type, } else { dout("get_sb using new client %p\n", fsc); err = ceph_setup_bdi(sb, fsc); - if (err < 0) { - res = ERR_PTR(err); + if (err < 0) goto out_splat; - } } - res = ceph_real_mount(fsc); - if (IS_ERR(res)) + res = ceph_real_mount(fsc, fc); + if (IS_ERR(res)) { + err = PTR_ERR(res); goto out_splat; + } dout("root %p inode %p ino %llx.%llx\n", res, d_inode(res), ceph_vinop(d_inode(res))); - return res; + fc->root = fsc->sb->s_root; + return 0; out_splat: ceph_mdsc_close_sessions(fsc->mdsc); @@ -1144,8 +1075,79 @@ out_splat: out: destroy_fs_client(fsc); out_final: - dout("ceph_mount fail %ld\n", PTR_ERR(res)); - return res; + dout("ceph_get_tree fail %d\n", err); + return err; +} + +static void ceph_free_fc(struct fs_context *fc) +{ + struct ceph_parse_opts_ctx *pctx = fc->fs_private; + + if (pctx) { + destroy_mount_options(pctx->opts); + ceph_destroy_options(pctx->copts); + kfree(pctx); + } +} + +static int ceph_reconfigure_fc(struct fs_context *fc) +{ + sync_filesystem(fc->root->d_sb); + return 0; +} + +static const struct fs_context_operations ceph_context_ops = { + .free = ceph_free_fc, + .parse_param = ceph_parse_mount_param, + .get_tree = ceph_get_tree, + .reconfigure = ceph_reconfigure_fc, +}; + +/* + * Set up the filesystem mount context. + */ +static int ceph_init_fs_context(struct fs_context *fc) +{ + struct ceph_parse_opts_ctx *pctx; + struct ceph_mount_options *fsopt; + + pctx = kzalloc(sizeof(*pctx), GFP_KERNEL); + if (!pctx) + return -ENOMEM; + + pctx->copts = ceph_alloc_options(); + if (!pctx->copts) + goto nomem; + + pctx->opts = kzalloc(sizeof(*pctx->opts), GFP_KERNEL); + if (!pctx->opts) + goto nomem; + + fsopt = pctx->opts; + fsopt->flags = CEPH_MOUNT_OPT_DEFAULT; + + fsopt->wsize = CEPH_MAX_WRITE_SIZE; + fsopt->rsize = CEPH_MAX_READ_SIZE; + fsopt->rasize = CEPH_RASIZE_DEFAULT; + fsopt->snapdir_name = kstrdup(CEPH_SNAPDIRNAME_DEFAULT, GFP_KERNEL); + if (!fsopt->snapdir_name) + goto nomem; + + fsopt->caps_wanted_delay_min = CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT; + fsopt->caps_wanted_delay_max = CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT; + fsopt->max_readdir = CEPH_MAX_READDIR_DEFAULT; + fsopt->max_readdir_bytes = CEPH_MAX_READDIR_BYTES_DEFAULT; + fsopt->congestion_kb = default_congestion_kb(); + + fc->fs_private = pctx; + fc->ops = &ceph_context_ops; + return 0; + +nomem: + destroy_mount_options(pctx->opts); + ceph_destroy_options(pctx->copts); + kfree(pctx); + return -ENOMEM; } static void ceph_kill_sb(struct super_block *s) @@ -1172,7 +1174,7 @@ static void ceph_kill_sb(struct super_block *s) static struct file_system_type ceph_fs_type = { .owner = THIS_MODULE, .name = "ceph", - .mount = ceph_mount, + .init_fs_context = ceph_init_fs_context, .kill_sb = ceph_kill_sb, .fs_flags = FS_RENAME_DOES_D_MOVE, }; diff --git a/fs/ceph/super.h b/fs/ceph/super.h index e31c0177fcc6..f0f9cb7447ac 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -74,7 +74,6 @@ struct ceph_mount_options { int flags; - int sb_flags; int wsize; /* max write size */ int rsize; /* max read size */ diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index b9dbda1c26aa..8fe9b80e80a5 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -280,10 +280,12 @@ extern const char *ceph_msg_type_name(int type); extern int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid); extern void *ceph_kvmalloc(size_t size, gfp_t flags); -extern struct ceph_options *ceph_parse_options(char *options, - const char *dev_name, const char *dev_name_end, - int (*parse_extra_token)(char *c, void *private), - void *private); +struct fs_parameter; +struct ceph_options *ceph_alloc_options(void); +int ceph_parse_mon_ips(const char *buf, size_t len, struct ceph_options *opt, + struct fs_context *fc); +int ceph_parse_param(struct fs_parameter *param, struct ceph_options *opt, + struct fs_context *fc); int ceph_print_client_options(struct seq_file *m, struct ceph_client *client, bool show_all); extern void ceph_destroy_options(struct ceph_options *opt); diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index 2d568246803f..a9d6c97b5b0d 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -11,7 +11,7 @@ #include #include #include -#include +#include #include #include #include @@ -254,58 +254,77 @@ enum { Opt_mount_timeout, Opt_osd_idle_ttl, Opt_osd_request_timeout, - Opt_last_int, /* int args above */ Opt_fsid, Opt_name, Opt_secret, Opt_key, Opt_ip, - Opt_last_string, /* string args above */ Opt_share, - Opt_noshare, Opt_crc, - Opt_nocrc, Opt_cephx_require_signatures, - Opt_nocephx_require_signatures, Opt_cephx_sign_messages, - Opt_nocephx_sign_messages, Opt_tcp_nodelay, - Opt_notcp_nodelay, Opt_abort_on_full, }; -static match_table_t opt_tokens = { - {Opt_osdtimeout, "osdtimeout=%d"}, - {Opt_osdkeepalivetimeout, "osdkeepalive=%d"}, - {Opt_mount_timeout, "mount_timeout=%d"}, - {Opt_osd_idle_ttl, "osd_idle_ttl=%d"}, - {Opt_osd_request_timeout, "osd_request_timeout=%d"}, - /* int args above */ - {Opt_fsid, "fsid=%s"}, - {Opt_name, "name=%s"}, - {Opt_secret, "secret=%s"}, - {Opt_key, "key=%s"}, - {Opt_ip, "ip=%s"}, - /* string args above */ - {Opt_share, "share"}, - {Opt_noshare, "noshare"}, - {Opt_crc, "crc"}, - {Opt_nocrc, "nocrc"}, - {Opt_cephx_require_signatures, "cephx_require_signatures"}, - {Opt_nocephx_require_signatures, "nocephx_require_signatures"}, - {Opt_cephx_sign_messages, "cephx_sign_messages"}, - {Opt_nocephx_sign_messages, "nocephx_sign_messages"}, - {Opt_tcp_nodelay, "tcp_nodelay"}, - {Opt_notcp_nodelay, "notcp_nodelay"}, - {Opt_abort_on_full, "abort_on_full"}, - {-1, NULL} +static const struct fs_parameter_spec ceph_param_specs[] = { + fsparam_flag ("abort_on_full", Opt_abort_on_full), + fsparam_flag_no ("cephx_require_signatures", Opt_cephx_require_signatures), + fsparam_flag_no ("cephx_sign_messages", Opt_cephx_sign_messages), + fsparam_flag_no ("crc", Opt_crc), + fsparam_string ("fsid", Opt_fsid), + fsparam_string ("ip", Opt_ip), + fsparam_string ("key", Opt_key), + fsparam_u32 ("mount_timeout", Opt_mount_timeout), + fsparam_string ("name", Opt_name), + fsparam_u32 ("osd_idle_ttl", Opt_osd_idle_ttl), + fsparam_u32 ("osd_request_timeout", Opt_osd_request_timeout), + fsparam_u32 ("osdkeepalive", Opt_osdkeepalivetimeout), + __fsparam (fs_param_is_s32, "osdtimeout", Opt_osdtimeout, + fs_param_deprecated), + fsparam_string ("secret", Opt_secret), + fsparam_flag_no ("share", Opt_share), + fsparam_flag_no ("tcp_nodelay", Opt_tcp_nodelay), + {} +}; + +static const struct fs_parameter_description ceph_parameters = { + .name = "libceph", + .specs = ceph_param_specs, }; +struct ceph_options *ceph_alloc_options(void) +{ + struct ceph_options *opt; + + opt = kzalloc(sizeof(*opt), GFP_KERNEL); + if (!opt) + return NULL; + + opt->mon_addr = kcalloc(CEPH_MAX_MON, sizeof(*opt->mon_addr), + GFP_KERNEL); + if (!opt->mon_addr) { + kfree(opt); + return NULL; + } + + opt->flags = CEPH_OPT_DEFAULT; + opt->osd_keepalive_timeout = CEPH_OSD_KEEPALIVE_DEFAULT; + opt->mount_timeout = CEPH_MOUNT_TIMEOUT_DEFAULT; + opt->osd_idle_ttl = CEPH_OSD_IDLE_TTL_DEFAULT; + opt->osd_request_timeout = CEPH_OSD_REQUEST_TIMEOUT_DEFAULT; + return opt; +} +EXPORT_SYMBOL(ceph_alloc_options); + void ceph_destroy_options(struct ceph_options *opt) { dout("destroy_options %p\n", opt); + if (!opt) + return; + kfree(opt->name); if (opt->key) { ceph_crypto_key_destroy(opt->key); @@ -317,7 +336,9 @@ void ceph_destroy_options(struct ceph_options *opt) EXPORT_SYMBOL(ceph_destroy_options); /* get secret from key store */ -static int get_secret(struct ceph_crypto_key *dst, const char *name) { +static int get_secret(struct ceph_crypto_key *dst, const char *name, + struct fs_context *fc) +{ struct key *ukey; int key_err; int err = 0; @@ -330,20 +351,20 @@ static int get_secret(struct ceph_crypto_key *dst, const char *name) { key_err = PTR_ERR(ukey); switch (key_err) { case -ENOKEY: - pr_warn("ceph: Mount failed due to key not found: %s\n", - name); + errorf(fc, "libceph: Failed due to key not found: %s", + name); break; case -EKEYEXPIRED: - pr_warn("ceph: Mount failed due to expired key: %s\n", - name); + errorf(fc, "libceph: Failed due to expired key: %s", + name); break; case -EKEYREVOKED: - pr_warn("ceph: Mount failed due to revoked key: %s\n", - name); + errorf(fc, "libceph: Failed due to revoked key: %s", + name); break; default: - pr_warn("ceph: Mount failed due to unknown key error %d: %s\n", - key_err, name); + errorf(fc, "libceph: Failed due to key error %d: %s", + key_err, name); } err = -EPERM; goto out; @@ -361,217 +382,157 @@ out: return err; } -struct ceph_options * -ceph_parse_options(char *options, const char *dev_name, - const char *dev_name_end, - int (*parse_extra_token)(char *c, void *private), - void *private) +int ceph_parse_mon_ips(const char *buf, size_t len, struct ceph_options *opt, + struct fs_context *fc) { - struct ceph_options *opt; - const char *c; - int err = -ENOMEM; - substring_t argstr[MAX_OPT_ARGS]; - - opt = kzalloc(sizeof(*opt), GFP_KERNEL); - if (!opt) - return ERR_PTR(-ENOMEM); - opt->mon_addr = kcalloc(CEPH_MAX_MON, sizeof(*opt->mon_addr), - GFP_KERNEL); - if (!opt->mon_addr) - goto out; - - dout("parse_options %p options '%s' dev_name '%s'\n", opt, options, - dev_name); - - /* start with defaults */ - opt->flags = CEPH_OPT_DEFAULT; - opt->osd_keepalive_timeout = CEPH_OSD_KEEPALIVE_DEFAULT; - opt->mount_timeout = CEPH_MOUNT_TIMEOUT_DEFAULT; - opt->osd_idle_ttl = CEPH_OSD_IDLE_TTL_DEFAULT; - opt->osd_request_timeout = CEPH_OSD_REQUEST_TIMEOUT_DEFAULT; + int ret; - /* get mon ip(s) */ /* ip1[:port1][,ip2[:port2]...] */ - err = ceph_parse_ips(dev_name, dev_name_end, opt->mon_addr, - CEPH_MAX_MON, &opt->num_mon); - if (err < 0) - goto out; + ret = ceph_parse_ips(buf, buf + len, opt->mon_addr, CEPH_MAX_MON, + &opt->num_mon); + if (ret) { + errorf(fc, "libceph: Failed to parse monitor IPs: %d", ret); + return ret; + } - /* parse mount options */ - while ((c = strsep(&options, ",")) != NULL) { - int token, intval; - if (!*c) - continue; - err = -EINVAL; - token = match_token((char *)c, opt_tokens, argstr); - if (token < 0 && parse_extra_token) { - /* extra? */ - err = parse_extra_token((char *)c, private); - if (err < 0) { - pr_err("bad option at '%s'\n", c); - goto out; - } - continue; - } - if (token < Opt_last_int) { - err = match_int(&argstr[0], &intval); - if (err < 0) { - pr_err("bad option arg (not int) at '%s'\n", c); - goto out; - } - dout("got int token %d val %d\n", token, intval); - } else if (token > Opt_last_int && token < Opt_last_string) { - dout("got string token %d val %s\n", token, - argstr[0].from); - } else { - dout("got token %d\n", token); + return 0; +} +EXPORT_SYMBOL(ceph_parse_mon_ips); + +int ceph_parse_param(struct fs_parameter *param, struct ceph_options *opt, + struct fs_context *fc) +{ + struct fs_parse_result result; + int token, err; + + token = fs_parse(fc, &ceph_parameters, param, &result); + dout("%s fs_parse '%s' token %d\n", __func__, param->key, token); + if (token < 0) + return token; + + switch (token) { + case Opt_ip: + err = ceph_parse_ips(param->string, + param->string + param->size, + &opt->my_addr, + 1, NULL); + if (err) { + errorf(fc, "libceph: Failed to parse ip: %d", err); + return err; } - switch (token) { - case Opt_ip: - err = ceph_parse_ips(argstr[0].from, - argstr[0].to, - &opt->my_addr, - 1, NULL); - if (err < 0) - goto out; - opt->flags |= CEPH_OPT_MYIP; - break; + opt->flags |= CEPH_OPT_MYIP; + break; - case Opt_fsid: - err = parse_fsid(argstr[0].from, &opt->fsid); - if (err == 0) - opt->flags |= CEPH_OPT_FSID; - break; - case Opt_name: - kfree(opt->name); - opt->name = kstrndup(argstr[0].from, - argstr[0].to-argstr[0].from, - GFP_KERNEL); - if (!opt->name) { - err = -ENOMEM; - goto out; - } - break; - case Opt_secret: - ceph_crypto_key_destroy(opt->key); - kfree(opt->key); - - opt->key = kzalloc(sizeof(*opt->key), GFP_KERNEL); - if (!opt->key) { - err = -ENOMEM; - goto out; - } - err = ceph_crypto_key_unarmor(opt->key, argstr[0].from); - if (err < 0) - goto out; - break; - case Opt_key: - ceph_crypto_key_destroy(opt->key); - kfree(opt->key); - - opt->key = kzalloc(sizeof(*opt->key), GFP_KERNEL); - if (!opt->key) { - err = -ENOMEM; - goto out; - } - err = get_secret(opt->key, argstr[0].from); - if (err < 0) - goto out; - break; + case Opt_fsid: + err = parse_fsid(param->string, &opt->fsid); + if (err) { + errorf(fc, "libceph: Failed to parse fsid: %d", err); + return err; + } + opt->flags |= CEPH_OPT_FSID; + break; + case Opt_name: + kfree(opt->name); + opt->name = param->string; + param->string = NULL; + break; + case Opt_secret: + ceph_crypto_key_destroy(opt->key); + kfree(opt->key); - /* misc */ - case Opt_osdtimeout: - pr_warn("ignoring deprecated osdtimeout option\n"); - break; - case Opt_osdkeepalivetimeout: - /* 0 isn't well defined right now, reject it */ - if (intval < 1 || intval > INT_MAX / 1000) { - pr_err("osdkeepalive out of range\n"); - err = -EINVAL; - goto out; - } - opt->osd_keepalive_timeout = - msecs_to_jiffies(intval * 1000); - break; - case Opt_osd_idle_ttl: - /* 0 isn't well defined right now, reject it */ - if (intval < 1 || intval > INT_MAX / 1000) { - pr_err("osd_idle_ttl out of range\n"); - err = -EINVAL; - goto out; - } - opt->osd_idle_ttl = msecs_to_jiffies(intval * 1000); - break; - case Opt_mount_timeout: - /* 0 is "wait forever" (i.e. infinite timeout) */ - if (intval < 0 || intval > INT_MAX / 1000) { - pr_err("mount_timeout out of range\n"); - err = -EINVAL; - goto out; - } - opt->mount_timeout = msecs_to_jiffies(intval * 1000); - break; - case Opt_osd_request_timeout: - /* 0 is "wait forever" (i.e. infinite timeout) */ - if (intval < 0 || intval > INT_MAX / 1000) { - pr_err("osd_request_timeout out of range\n"); - err = -EINVAL; - goto out; - } - opt->osd_request_timeout = msecs_to_jiffies(intval * 1000); - break; + opt->key = kzalloc(sizeof(*opt->key), GFP_KERNEL); + if (!opt->key) + return -ENOMEM; + err = ceph_crypto_key_unarmor(opt->key, param->string); + if (err) { + errorf(fc, "libceph: Failed to parse secret: %d", err); + return err; + } + break; + case Opt_key: + ceph_crypto_key_destroy(opt->key); + kfree(opt->key); - case Opt_share: + opt->key = kzalloc(sizeof(*opt->key), GFP_KERNEL); + if (!opt->key) + return -ENOMEM; + return get_secret(opt->key, param->string, fc); + + case Opt_osdtimeout: + warnf(fc, "libceph: Ignoring osdtimeout"); + break; + case Opt_osdkeepalivetimeout: + /* 0 isn't well defined right now, reject it */ + if (result.uint_32 < 1 || result.uint_32 > INT_MAX / 1000) + goto out_of_range; + opt->osd_keepalive_timeout = + msecs_to_jiffies(result.uint_32 * 1000); + break; + case Opt_osd_idle_ttl: + /* 0 isn't well defined right now, reject it */ + if (result.uint_32 < 1 || result.uint_32 > INT_MAX / 1000) + goto out_of_range; + opt->osd_idle_ttl = msecs_to_jiffies(result.uint_32 * 1000); + break; + case Opt_mount_timeout: + /* 0 is "wait forever" (i.e. infinite timeout) */ + if (result.uint_32 > INT_MAX / 1000) + goto out_of_range; + opt->mount_timeout = msecs_to_jiffies(result.uint_32 * 1000); + break; + case Opt_osd_request_timeout: + /* 0 is "wait forever" (i.e. infinite timeout) */ + if (result.uint_32 > INT_MAX / 1000) + goto out_of_range; + opt->osd_request_timeout = + msecs_to_jiffies(result.uint_32 * 1000); + break; + + case Opt_share: + if (!result.negated) opt->flags &= ~CEPH_OPT_NOSHARE; - break; - case Opt_noshare: + else opt->flags |= CEPH_OPT_NOSHARE; - break; - - case Opt_crc: + break; + case Opt_crc: + if (!result.negated) opt->flags &= ~CEPH_OPT_NOCRC; - break; - case Opt_nocrc: + else opt->flags |= CEPH_OPT_NOCRC; - break; - - case Opt_cephx_require_signatures: + break; + case Opt_cephx_require_signatures: + if (!result.negated) opt->flags &= ~CEPH_OPT_NOMSGAUTH; - break; - case Opt_nocephx_require_signatures: + else opt->flags |= CEPH_OPT_NOMSGAUTH; - break; - case Opt_cephx_sign_messages: + break; + case Opt_cephx_sign_messages: + if (!result.negated) opt->flags &= ~CEPH_OPT_NOMSGSIGN; - break; - case Opt_nocephx_sign_messages: + else opt->flags |= CEPH_OPT_NOMSGSIGN; - break; - - case Opt_tcp_nodelay: + break; + case Opt_tcp_nodelay: + if (!result.negated) opt->flags |= CEPH_OPT_TCP_NODELAY; - break; - case Opt_notcp_nodelay: + else opt->flags &= ~CEPH_OPT_TCP_NODELAY; - break; + break; - case Opt_abort_on_full: - opt->flags |= CEPH_OPT_ABORT_ON_FULL; - break; + case Opt_abort_on_full: + opt->flags |= CEPH_OPT_ABORT_ON_FULL; + break; - default: - BUG_ON(token); - } + default: + BUG(); } - /* success */ - return opt; + return 0; -out: - ceph_destroy_options(opt); - return ERR_PTR(err); +out_of_range: + return invalf(fc, "libceph: %s out of range", param->key); } -EXPORT_SYMBOL(ceph_parse_options); +EXPORT_SYMBOL(ceph_parse_param); int ceph_print_client_options(struct seq_file *m, struct ceph_client *client, bool show_all) diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index e4cb3db2ee77..5b4bd8261002 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -2004,10 +2004,8 @@ int ceph_parse_ips(const char *c, const char *end, return 0; bad: - pr_err("parse_ips bad ip '%.*s'\n", (int)(end - c), c); return ret; } -EXPORT_SYMBOL(ceph_parse_ips); static int process_banner(struct ceph_connection *con) { -- cgit v1.2.3 From 22945688acd4d0ec2620b0670a53110401ed9c59 Mon Sep 17 00:00:00 2001 From: Bharata B Rao Date: Mon, 25 Nov 2019 08:36:30 +0530 Subject: KVM: PPC: Book3S HV: Support reset of secure guest Add support for reset of secure guest via a new ioctl KVM_PPC_SVM_OFF. This ioctl will be issued by QEMU during reset and includes the the following steps: - Release all device pages of the secure guest. - Ask UV to terminate the guest via UV_SVM_TERMINATE ucall - Unpin the VPA pages so that they can be migrated back to secure side when guest becomes secure again. This is required because pinned pages can't be migrated. - Reinit the partition scoped page tables After these steps, guest is ready to issue UV_ESM call once again to switch to secure mode. Signed-off-by: Bharata B Rao Signed-off-by: Sukadev Bhattiprolu [Implementation of uv_svm_terminate() and its call from guest shutdown path] Signed-off-by: Ram Pai [Unpinning of VPA pages] Signed-off-by: Paul Mackerras --- Documentation/virt/kvm/api.txt | 18 +++++++ arch/powerpc/include/asm/kvm_ppc.h | 1 + arch/powerpc/include/asm/ultravisor-api.h | 1 + arch/powerpc/include/asm/ultravisor.h | 5 ++ arch/powerpc/kvm/book3s_hv.c | 90 +++++++++++++++++++++++++++++++ arch/powerpc/kvm/powerpc.c | 12 +++++ include/uapi/linux/kvm.h | 1 + 7 files changed, 128 insertions(+) (limited to 'include') diff --git a/Documentation/virt/kvm/api.txt b/Documentation/virt/kvm/api.txt index 49183add44e7..9fecec6b4e86 100644 --- a/Documentation/virt/kvm/api.txt +++ b/Documentation/virt/kvm/api.txt @@ -4149,6 +4149,24 @@ Valid values for 'action': #define KVM_PMU_EVENT_ALLOW 0 #define KVM_PMU_EVENT_DENY 1 +4.121 KVM_PPC_SVM_OFF + +Capability: basic +Architectures: powerpc +Type: vm ioctl +Parameters: none +Returns: 0 on successful completion, +Errors: + EINVAL: if ultravisor failed to terminate the secure guest + ENOMEM: if hypervisor failed to allocate new radix page tables for guest + +This ioctl is used to turn off the secure mode of the guest or transition +the guest from secure mode to normal mode. This is invoked when the guest +is reset. This has no effect if called for a normal guest. + +This ioctl issues an ultravisor call to terminate the secure guest, +unpins the VPA pages and releases all the device pages that are used to +track the secure pages by hypervisor. 5. The kvm_run structure ------------------------ diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index d63f649fe713..3d2f871241a8 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -322,6 +322,7 @@ struct kvmppc_ops { int size); int (*store_to_eaddr)(struct kvm_vcpu *vcpu, ulong *eaddr, void *ptr, int size); + int (*svm_off)(struct kvm *kvm); }; extern struct kvmppc_ops *kvmppc_hv_ops; diff --git a/arch/powerpc/include/asm/ultravisor-api.h b/arch/powerpc/include/asm/ultravisor-api.h index 4b0d044caa2a..b66f6db7be6c 100644 --- a/arch/powerpc/include/asm/ultravisor-api.h +++ b/arch/powerpc/include/asm/ultravisor-api.h @@ -34,5 +34,6 @@ #define UV_UNSHARE_PAGE 0xF134 #define UV_UNSHARE_ALL_PAGES 0xF140 #define UV_PAGE_INVAL 0xF138 +#define UV_SVM_TERMINATE 0xF13C #endif /* _ASM_POWERPC_ULTRAVISOR_API_H */ diff --git a/arch/powerpc/include/asm/ultravisor.h b/arch/powerpc/include/asm/ultravisor.h index b8e59b7b4ac8..790b0e63681f 100644 --- a/arch/powerpc/include/asm/ultravisor.h +++ b/arch/powerpc/include/asm/ultravisor.h @@ -77,4 +77,9 @@ static inline int uv_page_inval(u64 lpid, u64 gpa, u64 page_shift) return ucall_norets(UV_PAGE_INVAL, lpid, gpa, page_shift); } +static inline int uv_svm_terminate(u64 lpid) +{ + return ucall_norets(UV_SVM_TERMINATE, lpid); +} + #endif /* _ASM_POWERPC_ULTRAVISOR_H */ diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index a8e815648b0a..dc53578193ee 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -4983,6 +4983,7 @@ static void kvmppc_core_destroy_vm_hv(struct kvm *kvm) if (nesting_enabled(kvm)) kvmhv_release_all_nested(kvm); kvm->arch.process_table = 0; + uv_svm_terminate(kvm->arch.lpid); kvmhv_set_ptbl_entry(kvm->arch.lpid, 0, 0); } @@ -5425,6 +5426,94 @@ static int kvmhv_store_to_eaddr(struct kvm_vcpu *vcpu, ulong *eaddr, void *ptr, return rc; } +static void unpin_vpa_reset(struct kvm *kvm, struct kvmppc_vpa *vpa) +{ + unpin_vpa(kvm, vpa); + vpa->gpa = 0; + vpa->pinned_addr = NULL; + vpa->dirty = false; + vpa->update_pending = 0; +} + +/* + * IOCTL handler to turn off secure mode of guest + * + * - Release all device pages + * - Issue ucall to terminate the guest on the UV side + * - Unpin the VPA pages. + * - Reinit the partition scoped page tables + */ +static int kvmhv_svm_off(struct kvm *kvm) +{ + struct kvm_vcpu *vcpu; + int mmu_was_ready; + int srcu_idx; + int ret = 0; + int i; + + if (!(kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START)) + return ret; + + mutex_lock(&kvm->arch.mmu_setup_lock); + mmu_was_ready = kvm->arch.mmu_ready; + if (kvm->arch.mmu_ready) { + kvm->arch.mmu_ready = 0; + /* order mmu_ready vs. vcpus_running */ + smp_mb(); + if (atomic_read(&kvm->arch.vcpus_running)) { + kvm->arch.mmu_ready = 1; + ret = -EBUSY; + goto out; + } + } + + srcu_idx = srcu_read_lock(&kvm->srcu); + for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + struct kvm_memory_slot *memslot; + struct kvm_memslots *slots = __kvm_memslots(kvm, i); + + if (!slots) + continue; + + kvm_for_each_memslot(memslot, slots) { + kvmppc_uvmem_drop_pages(memslot, kvm); + uv_unregister_mem_slot(kvm->arch.lpid, memslot->id); + } + } + srcu_read_unlock(&kvm->srcu, srcu_idx); + + ret = uv_svm_terminate(kvm->arch.lpid); + if (ret != U_SUCCESS) { + ret = -EINVAL; + goto out; + } + + /* + * When secure guest is reset, all the guest pages are sent + * to UV via UV_PAGE_IN before the non-boot vcpus get a + * chance to run and unpin their VPA pages. Unpinning of all + * VPA pages is done here explicitly so that VPA pages + * can be migrated to the secure side. + * + * This is required to for the secure SMP guest to reboot + * correctly. + */ + kvm_for_each_vcpu(i, vcpu, kvm) { + spin_lock(&vcpu->arch.vpa_update_lock); + unpin_vpa_reset(kvm, &vcpu->arch.dtl); + unpin_vpa_reset(kvm, &vcpu->arch.slb_shadow); + unpin_vpa_reset(kvm, &vcpu->arch.vpa); + spin_unlock(&vcpu->arch.vpa_update_lock); + } + + kvmppc_setup_partition_table(kvm); + kvm->arch.secure_guest = 0; + kvm->arch.mmu_ready = mmu_was_ready; +out: + mutex_unlock(&kvm->arch.mmu_setup_lock); + return ret; +} + static struct kvmppc_ops kvm_ops_hv = { .get_sregs = kvm_arch_vcpu_ioctl_get_sregs_hv, .set_sregs = kvm_arch_vcpu_ioctl_set_sregs_hv, @@ -5468,6 +5557,7 @@ static struct kvmppc_ops kvm_ops_hv = { .enable_nested = kvmhv_enable_nested, .load_from_eaddr = kvmhv_load_from_eaddr, .store_to_eaddr = kvmhv_store_to_eaddr, + .svm_off = kvmhv_svm_off, }; static int kvm_init_subcore_bitmap(void) diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 9e085e931d74..416fb3d2a1d0 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -31,6 +31,8 @@ #include #include #endif +#include +#include #include "timing.h" #include "irq.h" @@ -2413,6 +2415,16 @@ long kvm_arch_vm_ioctl(struct file *filp, r = -EFAULT; break; } + case KVM_PPC_SVM_OFF: { + struct kvm *kvm = filp->private_data; + + r = 0; + if (!kvm->arch.kvm_ops->svm_off) + goto out; + + r = kvm->arch.kvm_ops->svm_off(kvm); + break; + } default: { struct kvm *kvm = filp->private_data; r = kvm->arch.kvm_ops->arch_vm_ioctl(filp, ioctl, arg); diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index e6f17c8e2dba..f0a16b4adbbd 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1348,6 +1348,7 @@ struct kvm_s390_ucas_mapping { #define KVM_PPC_GET_CPU_CHAR _IOR(KVMIO, 0xb1, struct kvm_ppc_cpu_char) /* Available with KVM_CAP_PMU_EVENT_FILTER */ #define KVM_SET_PMU_EVENT_FILTER _IOW(KVMIO, 0xb2, struct kvm_pmu_event_filter) +#define KVM_PPC_SVM_OFF _IO(KVMIO, 0xb3) /* ioctl for vm fd */ #define KVM_CREATE_DEVICE _IOWR(KVMIO, 0xe0, struct kvm_create_device) -- cgit v1.2.3 From ba1e78a1dc0ca3e92f0be82279e6ba24177af7d6 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 21 Nov 2019 19:41:51 +0100 Subject: cpuidle: Drop disabled field from struct cpuidle_state After recent cpuidle updates the "disabled" field in struct cpuidle_state is only used by two drivers (intel_idle and shmobile cpuidle) for marking unusable idle states, but that may as well be achieved with the help of a state flag, so define an "unusable" idle state flag, CPUIDLE_FLAG_UNUSABLE, make the drivers in question use it instead of the "disabled" field and make the core set CPUIDLE_STATE_DISABLED_BY_DRIVER for the idle states with that flag set. After the above changes, the "disabled" field in struct cpuidle_state is not used any more, so drop it. No intentional functional impact. Signed-off-by: Rafael J. Wysocki --- arch/sh/kernel/cpu/shmobile/cpuidle.c | 8 ++++---- drivers/cpuidle/cpuidle.c | 2 +- drivers/cpuidle/poll_state.c | 1 - drivers/idle/intel_idle.c | 6 +++--- include/linux/cpuidle.h | 2 +- 5 files changed, 9 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/arch/sh/kernel/cpu/shmobile/cpuidle.c b/arch/sh/kernel/cpu/shmobile/cpuidle.c index dbd2cdec2ddb..b0f9c8f8fd14 100644 --- a/arch/sh/kernel/cpu/shmobile/cpuidle.c +++ b/arch/sh/kernel/cpu/shmobile/cpuidle.c @@ -67,7 +67,7 @@ static struct cpuidle_driver cpuidle_driver = { .enter = cpuidle_sleep_enter, .name = "C2", .desc = "SuperH Sleep Mode [SF]", - .disabled = true, + .flags = CPUIDLE_FLAG_UNUSABLE, }, { .exit_latency = 2300, @@ -76,7 +76,7 @@ static struct cpuidle_driver cpuidle_driver = { .enter = cpuidle_sleep_enter, .name = "C3", .desc = "SuperH Mobile Standby Mode [SF]", - .disabled = true, + .flags = CPUIDLE_FLAG_UNUSABLE, }, }, .safe_state_index = 0, @@ -86,10 +86,10 @@ static struct cpuidle_driver cpuidle_driver = { int __init sh_mobile_setup_cpuidle(void) { if (sh_mobile_sleep_supported & SUSP_SH_SF) - cpuidle_driver.states[1].disabled = false; + cpuidle_driver.states[1].flags = CPUIDLE_FLAG_NONE; if (sh_mobile_sleep_supported & SUSP_SH_STANDBY) - cpuidle_driver.states[2].disabled = false; + cpuidle_driver.states[2].flags = CPUIDLE_FLAG_NONE; return cpuidle_register(&cpuidle_driver, NULL); } diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 569dbac443bd..0005be5ea2b4 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -572,7 +572,7 @@ static int __cpuidle_register_device(struct cpuidle_device *dev) return -EINVAL; for (i = 0; i < drv->state_count; i++) - if (drv->states[i].disabled) + if (drv->states[i].flags & CPUIDLE_FLAG_UNUSABLE) dev->states_usage[i].disable |= CPUIDLE_STATE_DISABLED_BY_DRIVER; per_cpu(cpuidle_devices, dev->cpu) = dev; diff --git a/drivers/cpuidle/poll_state.c b/drivers/cpuidle/poll_state.c index 9f1ace9c53da..f7e83613ae94 100644 --- a/drivers/cpuidle/poll_state.c +++ b/drivers/cpuidle/poll_state.c @@ -53,7 +53,6 @@ void cpuidle_poll_state_init(struct cpuidle_driver *drv) state->target_residency_ns = 0; state->power_usage = -1; state->enter = poll_idle; - state->disabled = false; state->flags = CPUIDLE_FLAG_POLLING; } EXPORT_SYMBOL_GPL(cpuidle_poll_state_init); diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 347b08b56042..75fd2a7b0842 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -1291,8 +1291,8 @@ static void sklh_idle_state_table_update(void) return; } - skl_cstates[5].disabled = 1; /* C8-SKL */ - skl_cstates[6].disabled = 1; /* C9-SKL */ + skl_cstates[5].flags |= CPUIDLE_FLAG_UNUSABLE; /* C8-SKL */ + skl_cstates[6].flags |= CPUIDLE_FLAG_UNUSABLE; /* C9-SKL */ } /* * intel_idle_state_table_update() @@ -1355,7 +1355,7 @@ static void __init intel_idle_cpuidle_driver_init(void) continue; /* if state marked as disabled, skip it */ - if (cpuidle_state_table[cstate].disabled != 0) { + if (cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_UNUSABLE) { pr_debug("state %s is disabled\n", cpuidle_state_table[cstate].name); continue; diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 2dbe46b7c213..1dabe36bd011 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -54,7 +54,6 @@ struct cpuidle_state { unsigned int exit_latency; /* in US */ int power_usage; /* in mW */ unsigned int target_residency; /* in US */ - bool disabled; /* disabled on all CPUs */ int (*enter) (struct cpuidle_device *dev, struct cpuidle_driver *drv, @@ -77,6 +76,7 @@ struct cpuidle_state { #define CPUIDLE_FLAG_POLLING BIT(0) /* polling state */ #define CPUIDLE_FLAG_COUPLED BIT(1) /* state applies to multiple cpus */ #define CPUIDLE_FLAG_TIMER_STOP BIT(2) /* timer is stopped on this state */ +#define CPUIDLE_FLAG_UNUSABLE BIT(3) /* avoid using this state */ struct cpuidle_device_kobj; struct cpuidle_state_kobj; -- cgit v1.2.3 From c6a3aea93571a5393602256d8f74772bd64c8225 Mon Sep 17 00:00:00 2001 From: Leonard Crestez Date: Tue, 26 Nov 2019 17:17:11 +0200 Subject: PM / QoS: Redefine FREQ_QOS_MAX_DEFAULT_VALUE to S32_MAX QOS requests for DEFAULT_VALUE are supposed to be ignored but this is not the case for FREQ_QOS_MAX. Adding one request for MAX_DEFAULT_VALUE and one for a real value will cause freq_qos_read_value to unexpectedly return MAX_DEFAULT_VALUE (-1). This happens because freq_qos max value is aggregated with PM_QOS_MIN but FREQ_QOS_MAX_DEFAULT_VALUE is (-1) so it's smaller than other values. Fix this by redefining FREQ_QOS_MAX_DEFAULT_VALUE to S32_MAX. Looking at current users for freq_qos it seems that none of them create requests for FREQ_QOS_MAX_DEFAULT_VALUE. Fixes: 77751a466ebd ("PM: QoS: Introduce frequency QoS") Signed-off-by: Leonard Crestez Reported-by: Matthias Kaehlcke Reviewed-by: Matthias Kaehlcke Cc: 5.4+ # 5.4+ Signed-off-by: Rafael J. Wysocki --- include/linux/pm_qos.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h index ebf5ef17cc2a..24a6263c9931 100644 --- a/include/linux/pm_qos.h +++ b/include/linux/pm_qos.h @@ -256,7 +256,7 @@ static inline s32 dev_pm_qos_raw_resume_latency(struct device *dev) #endif #define FREQ_QOS_MIN_DEFAULT_VALUE 0 -#define FREQ_QOS_MAX_DEFAULT_VALUE (-1) +#define FREQ_QOS_MAX_DEFAULT_VALUE S32_MAX enum freq_qos_req_type { FREQ_QOS_MIN = 1, -- cgit v1.2.3 From 342035f66c866f4ad750477b21b210e98d1f6818 Mon Sep 17 00:00:00 2001 From: Leonard Crestez Date: Tue, 26 Nov 2019 17:17:12 +0200 Subject: PM / QoS: Reorder pm_qos/freq_qos/dev_pm_qos structs This allows dev_pm_qos to embed freq_qos structs, which is done in the next patch. Separate commit to make it easier to review. Signed-off-by: Leonard Crestez Reviewed-by: Matthias Kaehlcke Signed-off-by: Rafael J. Wysocki --- include/linux/pm_qos.h | 74 ++++++++++++++++++++++++++------------------------ 1 file changed, 38 insertions(+), 36 deletions(-) (limited to 'include') diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h index 24a6263c9931..678fec6da5b9 100644 --- a/include/linux/pm_qos.h +++ b/include/linux/pm_qos.h @@ -49,21 +49,6 @@ struct pm_qos_flags_request { s32 flags; /* Do not change to 64 bit */ }; -enum dev_pm_qos_req_type { - DEV_PM_QOS_RESUME_LATENCY = 1, - DEV_PM_QOS_LATENCY_TOLERANCE, - DEV_PM_QOS_FLAGS, -}; - -struct dev_pm_qos_request { - enum dev_pm_qos_req_type type; - union { - struct plist_node pnode; - struct pm_qos_flags_request flr; - } data; - struct device *dev; -}; - enum pm_qos_type { PM_QOS_UNITIALIZED, PM_QOS_MAX, /* return the largest value */ @@ -90,6 +75,44 @@ struct pm_qos_flags { s32 effective_flags; /* Do not change to 64 bit */ }; + +#define FREQ_QOS_MIN_DEFAULT_VALUE 0 +#define FREQ_QOS_MAX_DEFAULT_VALUE S32_MAX + +enum freq_qos_req_type { + FREQ_QOS_MIN = 1, + FREQ_QOS_MAX, +}; + +struct freq_constraints { + struct pm_qos_constraints min_freq; + struct blocking_notifier_head min_freq_notifiers; + struct pm_qos_constraints max_freq; + struct blocking_notifier_head max_freq_notifiers; +}; + +struct freq_qos_request { + enum freq_qos_req_type type; + struct plist_node pnode; + struct freq_constraints *qos; +}; + + +enum dev_pm_qos_req_type { + DEV_PM_QOS_RESUME_LATENCY = 1, + DEV_PM_QOS_LATENCY_TOLERANCE, + DEV_PM_QOS_FLAGS, +}; + +struct dev_pm_qos_request { + enum dev_pm_qos_req_type type; + union { + struct plist_node pnode; + struct pm_qos_flags_request flr; + } data; + struct device *dev; +}; + struct dev_pm_qos { struct pm_qos_constraints resume_latency; struct pm_qos_constraints latency_tolerance; @@ -255,27 +278,6 @@ static inline s32 dev_pm_qos_raw_resume_latency(struct device *dev) } #endif -#define FREQ_QOS_MIN_DEFAULT_VALUE 0 -#define FREQ_QOS_MAX_DEFAULT_VALUE S32_MAX - -enum freq_qos_req_type { - FREQ_QOS_MIN = 1, - FREQ_QOS_MAX, -}; - -struct freq_constraints { - struct pm_qos_constraints min_freq; - struct blocking_notifier_head min_freq_notifiers; - struct pm_qos_constraints max_freq; - struct blocking_notifier_head max_freq_notifiers; -}; - -struct freq_qos_request { - enum freq_qos_req_type type; - struct plist_node pnode; - struct freq_constraints *qos; -}; - static inline int freq_qos_request_active(struct freq_qos_request *req) { return !IS_ERR_OR_NULL(req->qos); -- cgit v1.2.3 From 36a8015f89e40f7c9c91cc7e6d028fa288dad27b Mon Sep 17 00:00:00 2001 From: Leonard Crestez Date: Tue, 26 Nov 2019 17:17:13 +0200 Subject: PM / QoS: Restore DEV_PM_QOS_MIN/MAX_FREQUENCY Support for adding per-device frequency limits was removed in commit 2aac8bdf7a0f ("PM: QoS: Drop frequency QoS types from device PM QoS") after cpufreq switched to use a new "freq_constraints" construct. Restore support for per-device freq limits but base this upon freq_constraints. This is primarily meant to be used by the devfreq subsystem. This removes the "static" marking on freq_qos_apply but does not export it for modules. Signed-off-by: Leonard Crestez Reviewed-by: Matthias Kaehlcke Tested-by: Matthias Kaehlcke Signed-off-by: Rafael J. Wysocki --- drivers/base/power/qos.c | 73 ++++++++++++++++++++++++++++++++++++++++++++---- include/linux/pm_qos.h | 12 ++++++++ kernel/power/qos.c | 4 ++- 3 files changed, 82 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c index 350dcafd751f..8e93167f1783 100644 --- a/drivers/base/power/qos.c +++ b/drivers/base/power/qos.c @@ -115,10 +115,20 @@ s32 dev_pm_qos_read_value(struct device *dev, enum dev_pm_qos_req_type type) spin_lock_irqsave(&dev->power.lock, flags); - if (type == DEV_PM_QOS_RESUME_LATENCY) { + switch (type) { + case DEV_PM_QOS_RESUME_LATENCY: ret = IS_ERR_OR_NULL(qos) ? PM_QOS_RESUME_LATENCY_NO_CONSTRAINT : pm_qos_read_value(&qos->resume_latency); - } else { + break; + case DEV_PM_QOS_MIN_FREQUENCY: + ret = IS_ERR_OR_NULL(qos) ? PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE + : freq_qos_read_value(&qos->freq, FREQ_QOS_MIN); + break; + case DEV_PM_QOS_MAX_FREQUENCY: + ret = IS_ERR_OR_NULL(qos) ? PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE + : freq_qos_read_value(&qos->freq, FREQ_QOS_MAX); + break; + default: WARN_ON(1); ret = 0; } @@ -159,6 +169,10 @@ static int apply_constraint(struct dev_pm_qos_request *req, req->dev->power.set_latency_tolerance(req->dev, value); } break; + case DEV_PM_QOS_MIN_FREQUENCY: + case DEV_PM_QOS_MAX_FREQUENCY: + ret = freq_qos_apply(&req->data.freq, action, value); + break; case DEV_PM_QOS_FLAGS: ret = pm_qos_update_flags(&qos->flags, &req->data.flr, action, value); @@ -209,6 +223,8 @@ static int dev_pm_qos_constraints_allocate(struct device *dev) c->no_constraint_value = PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT; c->type = PM_QOS_MIN; + freq_constraints_init(&qos->freq); + INIT_LIST_HEAD(&qos->flags.list); spin_lock_irq(&dev->power.lock); @@ -269,6 +285,20 @@ void dev_pm_qos_constraints_destroy(struct device *dev) memset(req, 0, sizeof(*req)); } + c = &qos->freq.min_freq; + plist_for_each_entry_safe(req, tmp, &c->list, data.freq.pnode) { + apply_constraint(req, PM_QOS_REMOVE_REQ, + PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE); + memset(req, 0, sizeof(*req)); + } + + c = &qos->freq.max_freq; + plist_for_each_entry_safe(req, tmp, &c->list, data.freq.pnode) { + apply_constraint(req, PM_QOS_REMOVE_REQ, + PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE); + memset(req, 0, sizeof(*req)); + } + f = &qos->flags; list_for_each_entry_safe(req, tmp, &f->list, data.flr.node) { apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE); @@ -314,11 +344,22 @@ static int __dev_pm_qos_add_request(struct device *dev, ret = dev_pm_qos_constraints_allocate(dev); trace_dev_pm_qos_add_request(dev_name(dev), type, value); - if (!ret) { - req->dev = dev; - req->type = type; + if (ret) + return ret; + + req->dev = dev; + req->type = type; + if (req->type == DEV_PM_QOS_MIN_FREQUENCY) + ret = freq_qos_add_request(&dev->power.qos->freq, + &req->data.freq, + FREQ_QOS_MIN, value); + else if (req->type == DEV_PM_QOS_MAX_FREQUENCY) + ret = freq_qos_add_request(&dev->power.qos->freq, + &req->data.freq, + FREQ_QOS_MAX, value); + else ret = apply_constraint(req, PM_QOS_ADD_REQ, value); - } + return ret; } @@ -382,6 +423,10 @@ static int __dev_pm_qos_update_request(struct dev_pm_qos_request *req, case DEV_PM_QOS_LATENCY_TOLERANCE: curr_value = req->data.pnode.prio; break; + case DEV_PM_QOS_MIN_FREQUENCY: + case DEV_PM_QOS_MAX_FREQUENCY: + curr_value = req->data.freq.pnode.prio; + break; case DEV_PM_QOS_FLAGS: curr_value = req->data.flr.flags; break; @@ -507,6 +552,14 @@ int dev_pm_qos_add_notifier(struct device *dev, struct notifier_block *notifier, ret = blocking_notifier_chain_register(dev->power.qos->resume_latency.notifiers, notifier); break; + case DEV_PM_QOS_MIN_FREQUENCY: + ret = freq_qos_add_notifier(&dev->power.qos->freq, + FREQ_QOS_MIN, notifier); + break; + case DEV_PM_QOS_MAX_FREQUENCY: + ret = freq_qos_add_notifier(&dev->power.qos->freq, + FREQ_QOS_MAX, notifier); + break; default: WARN_ON(1); ret = -EINVAL; @@ -546,6 +599,14 @@ int dev_pm_qos_remove_notifier(struct device *dev, ret = blocking_notifier_chain_unregister(dev->power.qos->resume_latency.notifiers, notifier); break; + case DEV_PM_QOS_MIN_FREQUENCY: + ret = freq_qos_remove_notifier(&dev->power.qos->freq, + FREQ_QOS_MIN, notifier); + break; + case DEV_PM_QOS_MAX_FREQUENCY: + ret = freq_qos_remove_notifier(&dev->power.qos->freq, + FREQ_QOS_MAX, notifier); + break; default: WARN_ON(1); ret = -EINVAL; diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h index 678fec6da5b9..19eafca5680e 100644 --- a/include/linux/pm_qos.h +++ b/include/linux/pm_qos.h @@ -34,6 +34,8 @@ enum pm_qos_flags_status { #define PM_QOS_RESUME_LATENCY_NO_CONSTRAINT PM_QOS_LATENCY_ANY #define PM_QOS_RESUME_LATENCY_NO_CONSTRAINT_NS PM_QOS_LATENCY_ANY_NS #define PM_QOS_LATENCY_TOLERANCE_DEFAULT_VALUE 0 +#define PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE 0 +#define PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE FREQ_QOS_MAX_DEFAULT_VALUE #define PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT (-1) #define PM_QOS_FLAG_NO_POWER_OFF (1 << 0) @@ -101,6 +103,8 @@ struct freq_qos_request { enum dev_pm_qos_req_type { DEV_PM_QOS_RESUME_LATENCY = 1, DEV_PM_QOS_LATENCY_TOLERANCE, + DEV_PM_QOS_MIN_FREQUENCY, + DEV_PM_QOS_MAX_FREQUENCY, DEV_PM_QOS_FLAGS, }; @@ -109,6 +113,7 @@ struct dev_pm_qos_request { union { struct plist_node pnode; struct pm_qos_flags_request flr; + struct freq_qos_request freq; } data; struct device *dev; }; @@ -116,6 +121,7 @@ struct dev_pm_qos_request { struct dev_pm_qos { struct pm_qos_constraints resume_latency; struct pm_qos_constraints latency_tolerance; + struct freq_constraints freq; struct pm_qos_flags flags; struct dev_pm_qos_request *resume_latency_req; struct dev_pm_qos_request *latency_tolerance_req; @@ -214,6 +220,10 @@ static inline s32 dev_pm_qos_read_value(struct device *dev, switch (type) { case DEV_PM_QOS_RESUME_LATENCY: return PM_QOS_RESUME_LATENCY_NO_CONSTRAINT; + case DEV_PM_QOS_MIN_FREQUENCY: + return PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE; + case DEV_PM_QOS_MAX_FREQUENCY: + return PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE; default: WARN_ON(1); return 0; @@ -293,6 +303,8 @@ int freq_qos_add_request(struct freq_constraints *qos, enum freq_qos_req_type type, s32 value); int freq_qos_update_request(struct freq_qos_request *req, s32 new_value); int freq_qos_remove_request(struct freq_qos_request *req); +int freq_qos_apply(struct freq_qos_request *req, + enum pm_qos_req_action action, s32 value); int freq_qos_add_notifier(struct freq_constraints *qos, enum freq_qos_req_type type, diff --git a/kernel/power/qos.c b/kernel/power/qos.c index a45cba7df0ae..83edf8698118 100644 --- a/kernel/power/qos.c +++ b/kernel/power/qos.c @@ -714,8 +714,10 @@ s32 freq_qos_read_value(struct freq_constraints *qos, * @req: Constraint request to apply. * @action: Action to perform (add/update/remove). * @value: Value to assign to the QoS request. + * + * This is only meant to be called from inside pm_qos, not drivers. */ -static int freq_qos_apply(struct freq_qos_request *req, +int freq_qos_apply(struct freq_qos_request *req, enum pm_qos_req_action action, s32 value) { int ret; -- cgit v1.2.3 From e1608f3fa857b600045b6df7f7dadc70eeaa4496 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 29 Nov 2019 23:29:11 +0100 Subject: bpf: Avoid setting bpf insns pages read-only when prog is jited For the case where the interpreter is compiled out or when the prog is jited it is completely unnecessary to set the BPF insn pages as read-only. In fact, on frequent churn of BPF programs, it could lead to performance degradation of the system over time since it would break the direct map down to 4k pages when calling set_memory_ro() for the insn buffer on x86-64 / arm64 and there is no reverse operation. Thus, avoid breaking up large pages for data maps, and only limit this to the module range used by the JIT where it is necessary to set the image read-only and executable. Suggested-by: Peter Zijlstra Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20191129222911.3710-1-daniel@iogearbox.net --- include/linux/filter.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index 1b1e8b8f88da..a141cb07e76a 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -776,8 +776,12 @@ bpf_ctx_narrow_access_offset(u32 off, u32 size, u32 size_default) static inline void bpf_prog_lock_ro(struct bpf_prog *fp) { - set_vm_flush_reset_perms(fp); - set_memory_ro((unsigned long)fp, fp->pages); +#ifndef CONFIG_BPF_JIT_ALWAYS_ON + if (!fp->jited) { + set_vm_flush_reset_perms(fp); + set_memory_ro((unsigned long)fp, fp->pages); + } +#endif } static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) -- cgit v1.2.3 From 040b5cfbcefa263ccf2c118c4938308606bb7ed8 Mon Sep 17 00:00:00 2001 From: Martin Varghese Date: Mon, 2 Dec 2019 10:49:51 +0530 Subject: Fixed updating of ethertype in function skb_mpls_pop The skb_mpls_pop was not updating ethertype of an ethernet packet if the packet was originally received from a non ARPHRD_ETHER device. In the below OVS data path flow, since the device corresponding to port 7 is an l3 device (ARPHRD_NONE) the skb_mpls_pop function does not update the ethertype of the packet even though the previous push_eth action had added an ethernet header to the packet. recirc_id(0),in_port(7),eth_type(0x8847), mpls(label=12/0xfffff,tc=0/0,ttl=0/0x0,bos=1/1), actions:push_eth(src=00:00:00:00:00:00,dst=00:00:00:00:00:00), pop_mpls(eth_type=0x800),4 Fixes: ed246cee09b9 ("net: core: move pop MPLS functionality from OvS to core helper") Signed-off-by: Martin Varghese Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 ++- net/core/skbuff.c | 6 ++++-- net/openvswitch/actions.c | 3 ++- net/sched/act_mpls.c | 4 +++- 4 files changed, 11 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 7af5bec7d3b0..5aea72fe8498 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3530,7 +3530,8 @@ int skb_vlan_pop(struct sk_buff *skb); int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci); int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, int mac_len); -int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len); +int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len, + bool ethernet); int skb_mpls_update_lse(struct sk_buff *skb, __be32 mpls_lse); int skb_mpls_dec_ttl(struct sk_buff *skb); struct sk_buff *pskb_extract(struct sk_buff *skb, int off, int to_copy, diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 867e61df00db..312e80e86898 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -5529,12 +5529,14 @@ EXPORT_SYMBOL_GPL(skb_mpls_push); * @skb: buffer * @next_proto: ethertype of header after popped MPLS header * @mac_len: length of the MAC header + * @ethernet: flag to indicate if ethernet header is present in packet * * Expects skb->data at mac header. * * Returns 0 on success, -errno otherwise. */ -int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len) +int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len, + bool ethernet) { int err; @@ -5553,7 +5555,7 @@ int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len) skb_reset_mac_header(skb); skb_set_network_header(skb, mac_len); - if (skb->dev && skb->dev->type == ARPHRD_ETHER) { + if (ethernet) { struct ethhdr *hdr; /* use mpls_hdr() to get ethertype to account for VLANs. */ diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 12936c151cc0..91e210061bb3 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -179,7 +179,8 @@ static int pop_mpls(struct sk_buff *skb, struct sw_flow_key *key, { int err; - err = skb_mpls_pop(skb, ethertype, skb->mac_len); + err = skb_mpls_pop(skb, ethertype, skb->mac_len, + ovs_key_mac_proto(key) == MAC_PROTO_ETHERNET); if (err) return err; diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c index 325eddcc6621..a7d856203af1 100644 --- a/net/sched/act_mpls.c +++ b/net/sched/act_mpls.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) /* Copyright (C) 2019 Netronome Systems, Inc. */ +#include #include #include #include @@ -76,7 +77,8 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a, switch (p->tcfm_action) { case TCA_MPLS_ACT_POP: - if (skb_mpls_pop(skb, p->tcfm_proto, mac_len)) + if (skb_mpls_pop(skb, p->tcfm_proto, mac_len, + skb->dev && skb->dev->type == ARPHRD_ETHER)) goto drop; break; case TCA_MPLS_ACT_PUSH: -- cgit v1.2.3 From e38e486d66e2a3b902768fd71c32dbf10f77e1cb Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 2 Dec 2019 08:49:47 +0100 Subject: ALSA: hda: Modify stream stripe mask only when needed The recent commit in HD-audio stream management for changing the stripe control seems causing a regression on some platforms. The stripe control is currently used only by HDMI codec, and applying the stripe mask unconditionally may lead to scratchy and static noises as seen on some MacBooks. For addressing the regression, this patch changes the stream management code to apply the stripe mask conditionally only when the codec driver requested. Fixes: 9b6f7e7a296e ("ALSA: hda: program stripe bits for controller") BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=204477 Tested-by: Michael Pobega Cc: Link: https://lore.kernel.org/r/20191202074947.1617-1-tiwai@suse.de Signed-off-by: Takashi Iwai --- include/sound/hdaudio.h | 1 + sound/hda/hdac_stream.c | 19 ++++++++++++------- sound/pci/hda/patch_hdmi.c | 5 +++++ 3 files changed, 18 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/sound/hdaudio.h b/include/sound/hdaudio.h index b260c5fd2337..e05b95e83d5a 100644 --- a/include/sound/hdaudio.h +++ b/include/sound/hdaudio.h @@ -493,6 +493,7 @@ struct hdac_stream { bool prepared:1; bool no_period_wakeup:1; bool locked:1; + bool stripe:1; /* apply stripe control */ /* timestamp */ unsigned long start_wallclk; /* start + minimum wallclk */ diff --git a/sound/hda/hdac_stream.c b/sound/hda/hdac_stream.c index d8fe7ff0cd58..f9707fb05efe 100644 --- a/sound/hda/hdac_stream.c +++ b/sound/hda/hdac_stream.c @@ -96,12 +96,14 @@ void snd_hdac_stream_start(struct hdac_stream *azx_dev, bool fresh_start) 1 << azx_dev->index, 1 << azx_dev->index); /* set stripe control */ - if (azx_dev->substream) - stripe_ctl = snd_hdac_get_stream_stripe_ctl(bus, azx_dev->substream); - else - stripe_ctl = 0; - snd_hdac_stream_updateb(azx_dev, SD_CTL_3B, SD_CTL_STRIPE_MASK, - stripe_ctl); + if (azx_dev->stripe) { + if (azx_dev->substream) + stripe_ctl = snd_hdac_get_stream_stripe_ctl(bus, azx_dev->substream); + else + stripe_ctl = 0; + snd_hdac_stream_updateb(azx_dev, SD_CTL_3B, SD_CTL_STRIPE_MASK, + stripe_ctl); + } /* set DMA start and interrupt mask */ snd_hdac_stream_updateb(azx_dev, SD_CTL, 0, SD_CTL_DMA_START | SD_INT_MASK); @@ -118,7 +120,10 @@ void snd_hdac_stream_clear(struct hdac_stream *azx_dev) snd_hdac_stream_updateb(azx_dev, SD_CTL, SD_CTL_DMA_START | SD_INT_MASK, 0); snd_hdac_stream_writeb(azx_dev, SD_STS, SD_INT_MASK); /* to be sure */ - snd_hdac_stream_updateb(azx_dev, SD_CTL_3B, SD_CTL_STRIPE_MASK, 0); + if (azx_dev->stripe) { + snd_hdac_stream_updateb(azx_dev, SD_CTL_3B, SD_CTL_STRIPE_MASK, 0); + azx_dev->stripe = 0; + } azx_dev->running = false; } EXPORT_SYMBOL_GPL(snd_hdac_stream_clear); diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 0032bba8cc9d..ed4e98a1057a 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -32,6 +32,7 @@ #include #include "hda_local.h" #include "hda_jack.h" +#include "hda_controller.h" static bool static_hdmi_pcm; module_param(static_hdmi_pcm, bool, 0644); @@ -1249,6 +1250,10 @@ static int hdmi_pcm_open(struct hda_pcm_stream *hinfo, per_pin->cvt_nid = per_cvt->cvt_nid; hinfo->nid = per_cvt->cvt_nid; + /* flip stripe flag for the assigned stream if supported */ + if (get_wcaps(codec, per_cvt->cvt_nid) & AC_WCAP_STRIPE) + azx_stream(get_azx_dev(substream))->stripe = 1; + snd_hda_set_dev_select(codec, per_pin->pin_nid, per_pin->dev_id); snd_hda_codec_write_cache(codec, per_pin->pin_nid, 0, AC_VERB_SET_CONNECT_SEL, -- cgit v1.2.3 From 9e0afe3910ff7e5493c5d8ebe3b499994b5e0272 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Tue, 3 Dec 2019 11:20:37 +0100 Subject: firmware: dmi: Remember the memory type Store the memory type while walking the memory slots, and provide a way to retrieve it later. Signed-off-by: Jean Delvare --- drivers/firmware/dmi_scan.c | 25 ++++++++++++++++++++++++- include/linux/dmi.h | 2 ++ 2 files changed, 26 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c index 1e21fc3e9851..6f28e515fdc0 100644 --- a/drivers/firmware/dmi_scan.c +++ b/drivers/firmware/dmi_scan.c @@ -35,6 +35,7 @@ static struct dmi_memdev_info { const char *bank; u64 size; /* bytes */ u16 handle; + u8 type; /* DDR2, DDR3, DDR4 etc */ } *dmi_memdev; static int dmi_memdev_nr; @@ -391,7 +392,7 @@ static void __init save_mem_devices(const struct dmi_header *dm, void *v) u64 bytes; u16 size; - if (dm->type != DMI_ENTRY_MEM_DEVICE || dm->length < 0x12) + if (dm->type != DMI_ENTRY_MEM_DEVICE || dm->length < 0x13) return; if (nr >= dmi_memdev_nr) { pr_warn(FW_BUG "Too many DIMM entries in SMBIOS table\n"); @@ -400,6 +401,7 @@ static void __init save_mem_devices(const struct dmi_header *dm, void *v) dmi_memdev[nr].handle = get_unaligned(&dm->handle); dmi_memdev[nr].device = dmi_string(dm, d[0x10]); dmi_memdev[nr].bank = dmi_string(dm, d[0x11]); + dmi_memdev[nr].type = d[0x12]; size = get_unaligned((u16 *)&d[0xC]); if (size == 0) @@ -1128,3 +1130,24 @@ u64 dmi_memdev_size(u16 handle) return ~0ull; } EXPORT_SYMBOL_GPL(dmi_memdev_size); + +/** + * dmi_memdev_type - get the memory type + * @handle: DMI structure handle + * + * Return the DMI memory type of the module in the slot associated with the + * given DMI handle, or 0x0 if no such DMI handle exists. + */ +u8 dmi_memdev_type(u16 handle) +{ + int n; + + if (dmi_memdev) { + for (n = 0; n < dmi_memdev_nr; n++) { + if (handle == dmi_memdev[n].handle) + return dmi_memdev[n].type; + } + } + return 0x0; /* Not a valid value */ +} +EXPORT_SYMBOL_GPL(dmi_memdev_type); diff --git a/include/linux/dmi.h b/include/linux/dmi.h index 8de8c4f15163..13a48b167e2d 100644 --- a/include/linux/dmi.h +++ b/include/linux/dmi.h @@ -113,6 +113,7 @@ extern int dmi_walk(void (*decode)(const struct dmi_header *, void *), extern bool dmi_match(enum dmi_field f, const char *str); extern void dmi_memdev_name(u16 handle, const char **bank, const char **device); extern u64 dmi_memdev_size(u16 handle); +extern u8 dmi_memdev_type(u16 handle); #else @@ -142,6 +143,7 @@ static inline bool dmi_match(enum dmi_field f, const char *str) static inline void dmi_memdev_name(u16 handle, const char **bank, const char **device) { } static inline u64 dmi_memdev_size(u16 handle) { return ~0ul; } +static inline u8 dmi_memdev_type(u16 handle) { return 0x0; } static inline const struct dmi_system_id * dmi_first_match(const struct dmi_system_id *list) { return NULL; } -- cgit v1.2.3 From 7c2378800cf7ac87e2663afa7f39d102871f0c28 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Tue, 3 Dec 2019 11:20:37 +0100 Subject: firmware: dmi: Add dmi_memdev_handle Add a utility function dmi_memdev_handle() which returns the DMI handle associated with a given memory slot. This will allow kernel drivers to iterate over the memory slots. Signed-off-by: Jean Delvare --- drivers/firmware/dmi_scan.c | 16 ++++++++++++++++ include/linux/dmi.h | 2 ++ 2 files changed, 18 insertions(+) (limited to 'include') diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c index 6f28e515fdc0..2045566d622f 100644 --- a/drivers/firmware/dmi_scan.c +++ b/drivers/firmware/dmi_scan.c @@ -1151,3 +1151,19 @@ u8 dmi_memdev_type(u16 handle) return 0x0; /* Not a valid value */ } EXPORT_SYMBOL_GPL(dmi_memdev_type); + +/** + * dmi_memdev_handle - get the DMI handle of a memory slot + * @slot: slot number + * + * Return the DMI handle associated with a given memory slot, or %0xFFFF + * if there is no such slot. + */ +u16 dmi_memdev_handle(int slot) +{ + if (dmi_memdev && slot >= 0 && slot < dmi_memdev_nr) + return dmi_memdev[slot].handle; + + return 0xffff; /* Not a valid value */ +} +EXPORT_SYMBOL_GPL(dmi_memdev_handle); diff --git a/include/linux/dmi.h b/include/linux/dmi.h index 13a48b167e2d..927f8a8b7a1d 100644 --- a/include/linux/dmi.h +++ b/include/linux/dmi.h @@ -114,6 +114,7 @@ extern bool dmi_match(enum dmi_field f, const char *str); extern void dmi_memdev_name(u16 handle, const char **bank, const char **device); extern u64 dmi_memdev_size(u16 handle); extern u8 dmi_memdev_type(u16 handle); +extern u16 dmi_memdev_handle(int slot); #else @@ -144,6 +145,7 @@ static inline void dmi_memdev_name(u16 handle, const char **bank, const char **device) { } static inline u64 dmi_memdev_size(u16 handle) { return ~0ul; } static inline u8 dmi_memdev_type(u16 handle) { return 0x0; } +static inline u16 dmi_memdev_handle(int slot) { return 0xffff; } static inline const struct dmi_system_id * dmi_first_match(const struct dmi_system_id *list) { return NULL; } -- cgit v1.2.3 From 03b1230ca12a12e045d83b0357792075bf94a1e0 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 2 Dec 2019 18:50:25 -0700 Subject: io_uring: ensure async punted sendmsg/recvmsg requests copy data Just like commit f67676d160c6 for read/write requests, this one ensures that the msghdr data is fully copied if we need to punt a recvmsg or sendmsg system call to async context. Signed-off-by: Jens Axboe --- fs/io_uring.c | 145 +++++++++++++++++++++++++++++++++++++++++++------ include/linux/socket.h | 15 +++-- net/socket.c | 60 ++++++-------------- 3 files changed, 156 insertions(+), 64 deletions(-) (limited to 'include') diff --git a/fs/io_uring.c b/fs/io_uring.c index 1689aea55527..2700382ebcc7 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -308,6 +308,13 @@ struct io_timeout { struct io_timeout_data *data; }; +struct io_async_msghdr { + struct iovec fast_iov[UIO_FASTIOV]; + struct iovec *iov; + struct sockaddr __user *uaddr; + struct msghdr msg; +}; + struct io_async_rw { struct iovec fast_iov[UIO_FASTIOV]; struct iovec *iov; @@ -319,6 +326,7 @@ struct io_async_ctx { struct io_uring_sqe sqe; union { struct io_async_rw rw; + struct io_async_msghdr msg; }; }; @@ -1991,12 +1999,25 @@ static int io_sync_file_range(struct io_kiocb *req, return 0; } +static int io_sendmsg_prep(struct io_kiocb *req, struct io_async_ctx *io) +{ #if defined(CONFIG_NET) -static int io_send_recvmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe, - struct io_kiocb **nxt, bool force_nonblock, - long (*fn)(struct socket *, struct user_msghdr __user *, - unsigned int)) + const struct io_uring_sqe *sqe = req->sqe; + struct user_msghdr __user *msg; + unsigned flags; + + flags = READ_ONCE(sqe->msg_flags); + msg = (struct user_msghdr __user *)(unsigned long) READ_ONCE(sqe->addr); + return sendmsg_copy_msghdr(&io->msg.msg, msg, flags, &io->msg.iov); +#else + return 0; +#endif +} + +static int io_sendmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe, + struct io_kiocb **nxt, bool force_nonblock) { +#if defined(CONFIG_NET) struct socket *sock; int ret; @@ -2005,7 +2026,9 @@ static int io_send_recvmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe, sock = sock_from_file(req->file, &ret); if (sock) { - struct user_msghdr __user *msg; + struct io_async_ctx io, *copy; + struct sockaddr_storage addr; + struct msghdr *kmsg; unsigned flags; flags = READ_ONCE(sqe->msg_flags); @@ -2014,32 +2037,59 @@ static int io_send_recvmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe, else if (force_nonblock) flags |= MSG_DONTWAIT; - msg = (struct user_msghdr __user *) (unsigned long) - READ_ONCE(sqe->addr); + if (req->io) { + kmsg = &req->io->msg.msg; + kmsg->msg_name = &addr; + } else { + kmsg = &io.msg.msg; + kmsg->msg_name = &addr; + io.msg.iov = io.msg.fast_iov; + ret = io_sendmsg_prep(req, &io); + if (ret) + goto out; + } - ret = fn(sock, msg, flags); - if (force_nonblock && ret == -EAGAIN) + ret = __sys_sendmsg_sock(sock, kmsg, flags); + if (force_nonblock && ret == -EAGAIN) { + copy = kmalloc(sizeof(*copy), GFP_KERNEL); + if (!copy) { + ret = -ENOMEM; + goto out; + } + memcpy(©->msg, &io.msg, sizeof(copy->msg)); + req->io = copy; + memcpy(&req->io->sqe, req->sqe, sizeof(*req->sqe)); + req->sqe = &req->io->sqe; return ret; + } if (ret == -ERESTARTSYS) ret = -EINTR; } +out: io_cqring_add_event(req, ret); if (ret < 0 && (req->flags & REQ_F_LINK)) req->flags |= REQ_F_FAIL_LINK; io_put_req_find_next(req, nxt); return 0; -} +#else + return -EOPNOTSUPP; #endif +} -static int io_sendmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe, - struct io_kiocb **nxt, bool force_nonblock) +static int io_recvmsg_prep(struct io_kiocb *req, struct io_async_ctx *io) { #if defined(CONFIG_NET) - return io_send_recvmsg(req, sqe, nxt, force_nonblock, - __sys_sendmsg_sock); + const struct io_uring_sqe *sqe = req->sqe; + struct user_msghdr __user *msg; + unsigned flags; + + flags = READ_ONCE(sqe->msg_flags); + msg = (struct user_msghdr __user *)(unsigned long) READ_ONCE(sqe->addr); + return recvmsg_copy_msghdr(&io->msg.msg, msg, flags, &io->msg.uaddr, + &io->msg.iov); #else - return -EOPNOTSUPP; + return 0; #endif } @@ -2047,8 +2097,63 @@ static int io_recvmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe, struct io_kiocb **nxt, bool force_nonblock) { #if defined(CONFIG_NET) - return io_send_recvmsg(req, sqe, nxt, force_nonblock, - __sys_recvmsg_sock); + struct socket *sock; + int ret; + + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + + sock = sock_from_file(req->file, &ret); + if (sock) { + struct user_msghdr __user *msg; + struct io_async_ctx io, *copy; + struct sockaddr_storage addr; + struct msghdr *kmsg; + unsigned flags; + + flags = READ_ONCE(sqe->msg_flags); + if (flags & MSG_DONTWAIT) + req->flags |= REQ_F_NOWAIT; + else if (force_nonblock) + flags |= MSG_DONTWAIT; + + msg = (struct user_msghdr __user *) (unsigned long) + READ_ONCE(sqe->addr); + if (req->io) { + kmsg = &req->io->msg.msg; + kmsg->msg_name = &addr; + } else { + kmsg = &io.msg.msg; + kmsg->msg_name = &addr; + io.msg.iov = io.msg.fast_iov; + ret = io_recvmsg_prep(req, &io); + if (ret) + goto out; + } + + ret = __sys_recvmsg_sock(sock, kmsg, msg, io.msg.uaddr, flags); + if (force_nonblock && ret == -EAGAIN) { + copy = kmalloc(sizeof(*copy), GFP_KERNEL); + if (!copy) { + ret = -ENOMEM; + goto out; + } + memcpy(copy, &io, sizeof(*copy)); + req->io = copy; + memcpy(&req->io->sqe, req->sqe, sizeof(*req->sqe)); + req->sqe = &req->io->sqe; + return ret; + } + if (ret == -ERESTARTSYS) + ret = -EINTR; + } + +out: + io_cqring_add_event(req, ret); + if (ret < 0 && (req->flags & REQ_F_LINK)) + req->flags |= REQ_F_FAIL_LINK; + io_put_req_find_next(req, nxt); + return 0; #else return -EOPNOTSUPP; #endif @@ -2721,6 +2826,12 @@ static int io_req_defer_prep(struct io_kiocb *req, struct io_async_ctx *io) case IORING_OP_WRITE_FIXED: ret = io_write_prep(req, &iovec, &iter, true); break; + case IORING_OP_SENDMSG: + ret = io_sendmsg_prep(req, io); + break; + case IORING_OP_RECVMSG: + ret = io_recvmsg_prep(req, io); + break; default: req->io = io; return 0; diff --git a/include/linux/socket.h b/include/linux/socket.h index 4bde63021c09..903507fb901f 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -378,12 +378,19 @@ extern int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, extern int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, unsigned int flags, bool forbid_cmsg_compat); -extern long __sys_sendmsg_sock(struct socket *sock, - struct user_msghdr __user *msg, +extern long __sys_sendmsg_sock(struct socket *sock, struct msghdr *msg, unsigned int flags); -extern long __sys_recvmsg_sock(struct socket *sock, - struct user_msghdr __user *msg, +extern long __sys_recvmsg_sock(struct socket *sock, struct msghdr *msg, + struct user_msghdr __user *umsg, + struct sockaddr __user *uaddr, unsigned int flags); +extern int sendmsg_copy_msghdr(struct msghdr *msg, + struct user_msghdr __user *umsg, unsigned flags, + struct iovec **iov); +extern int recvmsg_copy_msghdr(struct msghdr *msg, + struct user_msghdr __user *umsg, unsigned flags, + struct sockaddr __user **uaddr, + struct iovec **iov); /* helpers which do the actual work for syscalls */ extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size, diff --git a/net/socket.c b/net/socket.c index ea28cbb9e2e7..0fb0820edeec 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2346,9 +2346,9 @@ out: return err; } -static int sendmsg_copy_msghdr(struct msghdr *msg, - struct user_msghdr __user *umsg, unsigned flags, - struct iovec **iov) +int sendmsg_copy_msghdr(struct msghdr *msg, + struct user_msghdr __user *umsg, unsigned flags, + struct iovec **iov) { int err; @@ -2390,27 +2390,14 @@ static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg, /* * BSD sendmsg interface */ -long __sys_sendmsg_sock(struct socket *sock, struct user_msghdr __user *umsg, +long __sys_sendmsg_sock(struct socket *sock, struct msghdr *msg, unsigned int flags) { - struct iovec iovstack[UIO_FASTIOV], *iov = iovstack; - struct sockaddr_storage address; - struct msghdr msg = { .msg_name = &address }; - ssize_t err; - - err = sendmsg_copy_msghdr(&msg, umsg, flags, &iov); - if (err) - return err; /* disallow ancillary data requests from this path */ - if (msg.msg_control || msg.msg_controllen) { - err = -EINVAL; - goto out; - } + if (msg->msg_control || msg->msg_controllen) + return -EINVAL; - err = ____sys_sendmsg(sock, &msg, flags, NULL, 0); -out: - kfree(iov); - return err; + return ____sys_sendmsg(sock, msg, flags, NULL, 0); } long __sys_sendmsg(int fd, struct user_msghdr __user *msg, unsigned int flags, @@ -2516,10 +2503,10 @@ SYSCALL_DEFINE4(sendmmsg, int, fd, struct mmsghdr __user *, mmsg, return __sys_sendmmsg(fd, mmsg, vlen, flags, true); } -static int recvmsg_copy_msghdr(struct msghdr *msg, - struct user_msghdr __user *umsg, unsigned flags, - struct sockaddr __user **uaddr, - struct iovec **iov) +int recvmsg_copy_msghdr(struct msghdr *msg, + struct user_msghdr __user *umsg, unsigned flags, + struct sockaddr __user **uaddr, + struct iovec **iov) { ssize_t err; @@ -2609,28 +2596,15 @@ static int ___sys_recvmsg(struct socket *sock, struct user_msghdr __user *msg, * BSD recvmsg interface */ -long __sys_recvmsg_sock(struct socket *sock, struct user_msghdr __user *umsg, - unsigned int flags) +long __sys_recvmsg_sock(struct socket *sock, struct msghdr *msg, + struct user_msghdr __user *umsg, + struct sockaddr __user *uaddr, unsigned int flags) { - struct iovec iovstack[UIO_FASTIOV], *iov = iovstack; - struct sockaddr_storage address; - struct msghdr msg = { .msg_name = &address }; - struct sockaddr __user *uaddr; - ssize_t err; - - err = recvmsg_copy_msghdr(&msg, umsg, flags, &uaddr, &iov); - if (err) - return err; /* disallow ancillary data requests from this path */ - if (msg.msg_control || msg.msg_controllen) { - err = -EINVAL; - goto out; - } + if (msg->msg_control || msg->msg_controllen) + return -EINVAL; - err = ____sys_recvmsg(sock, &msg, umsg, uaddr, flags, 0); -out: - kfree(iov); - return err; + return ____sys_recvmsg(sock, msg, umsg, uaddr, flags, 0); } long __sys_recvmsg(int fd, struct user_msghdr __user *msg, unsigned int flags, -- cgit v1.2.3 From f499a021ea8c9f70321fce3d674d8eca5bbeee2c Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 2 Dec 2019 16:28:46 -0700 Subject: io_uring: ensure async punted connect requests copy data Just like commit f67676d160c6 for read/write requests, this one ensures that the sockaddr data has been copied for IORING_OP_CONNECT if we need to punt the request to async context. Signed-off-by: Jens Axboe --- fs/io_uring.c | 51 ++++++++++++++++++++++++++++++++++++++++++++++---- include/linux/socket.h | 5 ++--- net/socket.c | 16 ++++++++-------- 3 files changed, 57 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/fs/io_uring.c b/fs/io_uring.c index 2700382ebcc7..5fcd89c507ec 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -308,6 +308,10 @@ struct io_timeout { struct io_timeout_data *data; }; +struct io_async_connect { + struct sockaddr_storage address; +}; + struct io_async_msghdr { struct iovec fast_iov[UIO_FASTIOV]; struct iovec *iov; @@ -327,6 +331,7 @@ struct io_async_ctx { union { struct io_async_rw rw; struct io_async_msghdr msg; + struct io_async_connect connect; }; }; @@ -2195,11 +2200,26 @@ static int io_accept(struct io_kiocb *req, const struct io_uring_sqe *sqe, #endif } +static int io_connect_prep(struct io_kiocb *req, struct io_async_ctx *io) +{ +#if defined(CONFIG_NET) + const struct io_uring_sqe *sqe = req->sqe; + struct sockaddr __user *addr; + int addr_len; + + addr = (struct sockaddr __user *) (unsigned long) READ_ONCE(sqe->addr); + addr_len = READ_ONCE(sqe->addr2); + return move_addr_to_kernel(addr, addr_len, &io->connect.address); +#else + return 0; +#endif +} + static int io_connect(struct io_kiocb *req, const struct io_uring_sqe *sqe, struct io_kiocb **nxt, bool force_nonblock) { #if defined(CONFIG_NET) - struct sockaddr __user *addr; + struct io_async_ctx __io, *io; unsigned file_flags; int addr_len, ret; @@ -2208,15 +2228,35 @@ static int io_connect(struct io_kiocb *req, const struct io_uring_sqe *sqe, if (sqe->ioprio || sqe->len || sqe->buf_index || sqe->rw_flags) return -EINVAL; - addr = (struct sockaddr __user *) (unsigned long) READ_ONCE(sqe->addr); addr_len = READ_ONCE(sqe->addr2); file_flags = force_nonblock ? O_NONBLOCK : 0; - ret = __sys_connect_file(req->file, addr, addr_len, file_flags); - if (ret == -EAGAIN && force_nonblock) + if (req->io) { + io = req->io; + } else { + ret = io_connect_prep(req, &__io); + if (ret) + goto out; + io = &__io; + } + + ret = __sys_connect_file(req->file, &io->connect.address, addr_len, + file_flags); + if (ret == -EAGAIN && force_nonblock) { + io = kmalloc(sizeof(*io), GFP_KERNEL); + if (!io) { + ret = -ENOMEM; + goto out; + } + memcpy(&io->connect, &__io.connect, sizeof(io->connect)); + req->io = io; + memcpy(&io->sqe, req->sqe, sizeof(*req->sqe)); + req->sqe = &io->sqe; return -EAGAIN; + } if (ret == -ERESTARTSYS) ret = -EINTR; +out: if (ret < 0 && (req->flags & REQ_F_LINK)) req->flags |= REQ_F_FAIL_LINK; io_cqring_add_event(req, ret); @@ -2832,6 +2872,9 @@ static int io_req_defer_prep(struct io_kiocb *req, struct io_async_ctx *io) case IORING_OP_RECVMSG: ret = io_recvmsg_prep(req, io); break; + case IORING_OP_CONNECT: + ret = io_connect_prep(req, io); + break; default: req->io = io; return 0; diff --git a/include/linux/socket.h b/include/linux/socket.h index 903507fb901f..2d2313403101 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -406,9 +406,8 @@ extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags); extern int __sys_socket(int family, int type, int protocol); extern int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen); -extern int __sys_connect_file(struct file *file, - struct sockaddr __user *uservaddr, int addrlen, - int file_flags); +extern int __sys_connect_file(struct file *file, struct sockaddr_storage *addr, + int addrlen, int file_flags); extern int __sys_connect(int fd, struct sockaddr __user *uservaddr, int addrlen); extern int __sys_listen(int fd, int backlog); diff --git a/net/socket.c b/net/socket.c index 0fb0820edeec..b343db1489bd 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1826,26 +1826,22 @@ SYSCALL_DEFINE3(accept, int, fd, struct sockaddr __user *, upeer_sockaddr, * include the -EINPROGRESS status for such sockets. */ -int __sys_connect_file(struct file *file, struct sockaddr __user *uservaddr, +int __sys_connect_file(struct file *file, struct sockaddr_storage *address, int addrlen, int file_flags) { struct socket *sock; - struct sockaddr_storage address; int err; sock = sock_from_file(file, &err); if (!sock) goto out; - err = move_addr_to_kernel(uservaddr, addrlen, &address); - if (err < 0) - goto out; err = - security_socket_connect(sock, (struct sockaddr *)&address, addrlen); + security_socket_connect(sock, (struct sockaddr *)address, addrlen); if (err) goto out; - err = sock->ops->connect(sock, (struct sockaddr *)&address, addrlen, + err = sock->ops->connect(sock, (struct sockaddr *)address, addrlen, sock->file->f_flags | file_flags); out: return err; @@ -1858,7 +1854,11 @@ int __sys_connect(int fd, struct sockaddr __user *uservaddr, int addrlen) f = fdget(fd); if (f.file) { - ret = __sys_connect_file(f.file, uservaddr, addrlen, 0); + struct sockaddr_storage address; + + ret = move_addr_to_kernel(uservaddr, addrlen, &address); + if (!ret) + ret = __sys_connect_file(f.file, &address, addrlen, 0); if (f.flags) fput(f.file); } -- cgit v1.2.3 From da8c96906990f1108cb626ee7865e69267a3263b Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 2 Dec 2019 18:51:26 -0700 Subject: io_uring: mark us with IORING_FEAT_SUBMIT_STABLE If this flag is set, applications can be certain that any data for async offload has been consumed when the kernel has consumed the SQE. Signed-off-by: Jens Axboe --- fs/io_uring.c | 3 ++- include/uapi/linux/io_uring.h | 1 + 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/fs/io_uring.c b/fs/io_uring.c index 5fcd89c507ec..c47a08afcee5 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -5077,7 +5077,8 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p) if (ret < 0) goto err; - p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP; + p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP | + IORING_FEAT_SUBMIT_STABLE; trace_io_uring_create(ret, ctx, p->sq_entries, p->cq_entries, p->flags); return ret; err: diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 4637ed1d9949..eabccb46edd1 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -157,6 +157,7 @@ struct io_uring_params { */ #define IORING_FEAT_SINGLE_MMAP (1U << 0) #define IORING_FEAT_NODROP (1U << 1) +#define IORING_FEAT_SUBMIT_STABLE (1U << 2) /* * io_uring_register(2) opcodes and arguments -- cgit v1.2.3 From 795ee49c1a28d1b3eeb2b463f18d557700fc6153 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Sat, 30 Nov 2019 23:23:52 +0300 Subject: block: optimise bvec_iter_advance() bvec_iter_advance() is quite popular, but compilers fail to do proper alias analysis and optimise it good enough. The assembly is checked for gcc 9.2, x86-64. - remove @iter->bi_size from min(...), as it's always less than @bytes. Modify at the beginning and forget about it. - the compiler isn't able to collapse memory dependencies and remove writes in the loop. Help it by explicitely using local vars. Signed-off-by: Arvind Sankar Signed-off-by: Pavel Begunkov Signed-off-by: Jens Axboe --- include/linux/bvec.h | 22 ++++++++++------------ 1 file changed, 10 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/bvec.h b/include/linux/bvec.h index a032f01e928c..679a42253170 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -87,26 +87,24 @@ struct bvec_iter_all { static inline bool bvec_iter_advance(const struct bio_vec *bv, struct bvec_iter *iter, unsigned bytes) { + unsigned int idx = iter->bi_idx; + if (WARN_ONCE(bytes > iter->bi_size, "Attempted to advance past end of bvec iter\n")) { iter->bi_size = 0; return false; } - while (bytes) { - const struct bio_vec *cur = bv + iter->bi_idx; - unsigned len = min3(bytes, iter->bi_size, - cur->bv_len - iter->bi_bvec_done); - - bytes -= len; - iter->bi_size -= len; - iter->bi_bvec_done += len; + iter->bi_size -= bytes; + bytes += iter->bi_bvec_done; - if (iter->bi_bvec_done == cur->bv_len) { - iter->bi_bvec_done = 0; - iter->bi_idx++; - } + while (bytes && bytes >= bv[idx].bv_len) { + bytes -= bv[idx].bv_len; + idx++; } + + iter->bi_idx = idx; + iter->bi_bvec_done = bytes; return true; } -- cgit v1.2.3 From 9b38bb4b1e6de47b379afaad2c707df639bb4dc7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 3 Dec 2019 10:39:04 +0100 Subject: block: simplify blkdev_nr_zones Simplify the arguments to blkdev_nr_zones by passing a gendisk instead of the block_device and capacity. This also removes the need for __blkdev_nr_zones as all callers are outside the fast path and can deal with the additional branch. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-zoned.c | 26 ++++++++------------------ block/ioctl.c | 2 +- drivers/md/dm-zoned-target.c | 2 +- include/linux/blkdev.h | 5 ++--- 4 files changed, 12 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 618786f8275c..65a9bdc9fe27 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -70,30 +70,20 @@ void __blk_req_zone_write_unlock(struct request *rq) } EXPORT_SYMBOL_GPL(__blk_req_zone_write_unlock); -static inline unsigned int __blkdev_nr_zones(struct request_queue *q, - sector_t nr_sectors) -{ - sector_t zone_sectors = blk_queue_zone_sectors(q); - - return (nr_sectors + zone_sectors - 1) >> ilog2(zone_sectors); -} - /** * blkdev_nr_zones - Get number of zones - * @bdev: Target block device + * @disk: Target gendisk * - * Description: - * Return the total number of zones of a zoned block device. - * For a regular block device, the number of zones is always 0. + * Return the total number of zones of a zoned block device. For a block + * device without zone capabilities, the number of zones is always 0. */ -unsigned int blkdev_nr_zones(struct block_device *bdev) +unsigned int blkdev_nr_zones(struct gendisk *disk) { - struct request_queue *q = bdev_get_queue(bdev); + sector_t zone_sectors = blk_queue_zone_sectors(disk->queue); - if (!blk_queue_is_zoned(q)) + if (!blk_queue_is_zoned(disk->queue)) return 0; - - return __blkdev_nr_zones(q, get_capacity(bdev->bd_disk)); + return (get_capacity(disk) + zone_sectors - 1) >> ilog2(zone_sectors); } EXPORT_SYMBOL_GPL(blkdev_nr_zones); @@ -447,7 +437,7 @@ static int blk_update_zone_info(struct gendisk *disk, unsigned int nr_zones, int blk_revalidate_disk_zones(struct gendisk *disk) { struct request_queue *q = disk->queue; - unsigned int nr_zones = __blkdev_nr_zones(q, get_capacity(disk)); + unsigned int nr_zones = blkdev_nr_zones(disk); struct blk_revalidate_zone_args args = { .disk = disk }; int ret = 0; diff --git a/block/ioctl.c b/block/ioctl.c index 7ac8a66c9787..5de98b97af2a 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -512,7 +512,7 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, case BLKGETZONESZ: return put_uint(arg, bdev_zone_sectors(bdev)); case BLKGETNRZONES: - return put_uint(arg, blkdev_nr_zones(bdev)); + return put_uint(arg, blkdev_nr_zones(bdev->bd_disk)); case HDIO_GETGEO: return blkdev_getgeo(bdev, argp); case BLKRAGET: diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c index 4574e0dedbd6..70a1063161c0 100644 --- a/drivers/md/dm-zoned-target.c +++ b/drivers/md/dm-zoned-target.c @@ -727,7 +727,7 @@ static int dmz_get_zoned_device(struct dm_target *ti, char *path) dev->zone_nr_blocks = dmz_sect2blk(dev->zone_nr_sectors); dev->zone_nr_blocks_shift = ilog2(dev->zone_nr_blocks); - dev->nr_zones = blkdev_nr_zones(dev->bdev); + dev->nr_zones = blkdev_nr_zones(dev->bdev->bd_disk); dmz->dev = dev; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6012e2592628..c5852de402b6 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -357,8 +357,7 @@ typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx, #define BLK_ALL_ZONES ((unsigned int)-1) int blkdev_report_zones(struct block_device *bdev, sector_t sector, unsigned int nr_zones, report_zones_cb cb, void *data); - -extern unsigned int blkdev_nr_zones(struct block_device *bdev); +unsigned int blkdev_nr_zones(struct gendisk *disk); extern int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op, sector_t sectors, sector_t nr_sectors, gfp_t gfp_mask); @@ -371,7 +370,7 @@ extern int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode, #else /* CONFIG_BLK_DEV_ZONED */ -static inline unsigned int blkdev_nr_zones(struct block_device *bdev) +static inline unsigned int blkdev_nr_zones(struct gendisk *disk) { return 0; } -- cgit v1.2.3 From f216fdd77b5654f8c4f6fac6020d6aabc58878ef Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 3 Dec 2019 10:39:05 +0100 Subject: block: replace seq_zones_bitmap with conv_zones_bitmap MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Invert the meaning of seq_zones_bitmap by keeping a bitmap of conventional zones. This allows not having a bitmap for devices that do not have conventional zones. Reviewed-by: Javier González Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-zoned.c | 18 +++++++++--------- include/linux/blkdev.h | 14 ++++++++------ 2 files changed, 17 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 65a9bdc9fe27..9c3931051f4f 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -332,15 +332,15 @@ static inline unsigned long *blk_alloc_zone_bitmap(int node, void blk_queue_free_zone_bitmaps(struct request_queue *q) { - kfree(q->seq_zones_bitmap); - q->seq_zones_bitmap = NULL; + kfree(q->conv_zones_bitmap); + q->conv_zones_bitmap = NULL; kfree(q->seq_zones_wlock); q->seq_zones_wlock = NULL; } struct blk_revalidate_zone_args { struct gendisk *disk; - unsigned long *seq_zones_bitmap; + unsigned long *conv_zones_bitmap; unsigned long *seq_zones_wlock; sector_t sector; }; @@ -394,8 +394,8 @@ static int blk_revalidate_zone_cb(struct blk_zone *zone, unsigned int idx, return -ENODEV; } - if (zone->type != BLK_ZONE_TYPE_CONVENTIONAL) - set_bit(idx, args->seq_zones_bitmap); + if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL) + set_bit(idx, args->conv_zones_bitmap); args->sector += zone->len; return 0; @@ -415,8 +415,8 @@ static int blk_update_zone_info(struct gendisk *disk, unsigned int nr_zones, args->seq_zones_wlock = blk_alloc_zone_bitmap(q->node, nr_zones); if (!args->seq_zones_wlock) return -ENOMEM; - args->seq_zones_bitmap = blk_alloc_zone_bitmap(q->node, nr_zones); - if (!args->seq_zones_bitmap) + args->conv_zones_bitmap = blk_alloc_zone_bitmap(q->node, nr_zones); + if (!args->conv_zones_bitmap) return -ENOMEM; ret = disk->fops->report_zones(disk, 0, nr_zones, @@ -465,7 +465,7 @@ int blk_revalidate_disk_zones(struct gendisk *disk) if (ret >= 0) { q->nr_zones = nr_zones; swap(q->seq_zones_wlock, args.seq_zones_wlock); - swap(q->seq_zones_bitmap, args.seq_zones_bitmap); + swap(q->conv_zones_bitmap, args.conv_zones_bitmap); ret = 0; } else { pr_warn("%s: failed to revalidate zones\n", disk->disk_name); @@ -474,7 +474,7 @@ int blk_revalidate_disk_zones(struct gendisk *disk) blk_mq_unfreeze_queue(q); kfree(args.seq_zones_wlock); - kfree(args.seq_zones_bitmap); + kfree(args.conv_zones_bitmap); return ret; } EXPORT_SYMBOL_GPL(blk_revalidate_disk_zones); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c5852de402b6..503c4d4c5884 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -503,9 +503,9 @@ struct request_queue { /* * Zoned block device information for request dispatch control. * nr_zones is the total number of zones of the device. This is always - * 0 for regular block devices. seq_zones_bitmap is a bitmap of nr_zones - * bits which indicates if a zone is conventional (bit clear) or - * sequential (bit set). seq_zones_wlock is a bitmap of nr_zones + * 0 for regular block devices. conv_zones_bitmap is a bitmap of nr_zones + * bits which indicates if a zone is conventional (bit set) or + * sequential (bit clear). seq_zones_wlock is a bitmap of nr_zones * bits which indicates if a zone is write locked, that is, if a write * request targeting the zone was dispatched. All three fields are * initialized by the low level device driver (e.g. scsi/sd.c). @@ -518,7 +518,7 @@ struct request_queue { * blk_mq_unfreeze_queue(). */ unsigned int nr_zones; - unsigned long *seq_zones_bitmap; + unsigned long *conv_zones_bitmap; unsigned long *seq_zones_wlock; #endif /* CONFIG_BLK_DEV_ZONED */ @@ -723,9 +723,11 @@ static inline unsigned int blk_queue_zone_no(struct request_queue *q, static inline bool blk_queue_zone_is_seq(struct request_queue *q, sector_t sector) { - if (!blk_queue_is_zoned(q) || !q->seq_zones_bitmap) + if (!blk_queue_is_zoned(q)) return false; - return test_bit(blk_queue_zone_no(q, sector), q->seq_zones_bitmap); + if (!q->conv_zones_bitmap) + return true; + return !test_bit(blk_queue_zone_no(q, sector), q->conv_zones_bitmap); } #else /* CONFIG_BLK_DEV_ZONED */ static inline unsigned int blk_queue_nr_zones(struct request_queue *q) -- cgit v1.2.3 From ae58954d8734c44298f55ed71e683ea944994fab Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 3 Dec 2019 10:39:07 +0100 Subject: block: don't handle bio based drivers in blk_revalidate_disk_zones MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit bio based drivers only need to update q->nr_zones. Do that manually instead of overloading blk_revalidate_disk_zones to keep that function simpler for the next round of changes that will rely even more on the request based functionality. Reviewed-by: Javier González Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-zoned.c | 16 +++++----------- drivers/block/null_blk_main.c | 12 +++++++++--- drivers/md/dm-table.c | 12 +++++++----- include/linux/blkdev.h | 5 ----- 4 files changed, 21 insertions(+), 24 deletions(-) (limited to 'include') diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 0131f9e14bd1..51d427659ce7 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -419,8 +419,9 @@ static int blk_revalidate_zone_cb(struct blk_zone *zone, unsigned int idx, * * Helper function for low-level device drivers to (re) allocate and initialize * a disk request queue zone bitmaps. This functions should normally be called - * within the disk ->revalidate method. For BIO based queues, no zone bitmap - * is allocated. + * within the disk ->revalidate method for blk-mq based drivers. For BIO based + * drivers only q->nr_zones needs to be updated so that the sysfs exposed value + * is correct. */ int blk_revalidate_disk_zones(struct gendisk *disk) { @@ -433,15 +434,8 @@ int blk_revalidate_disk_zones(struct gendisk *disk) if (WARN_ON_ONCE(!blk_queue_is_zoned(q))) return -EIO; - - /* - * BIO based queues do not use a scheduler so only q->nr_zones - * needs to be updated so that the sysfs exposed value is correct. - */ - if (!queue_is_mq(q)) { - q->nr_zones = args.nr_zones; - return 0; - } + if (WARN_ON_ONCE(!queue_is_mq(q))) + return -EIO; /* * Ensure that all memory allocations in this context are done as diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk_main.c index dd6026289fbf..068cd0ae6e2c 100644 --- a/drivers/block/null_blk_main.c +++ b/drivers/block/null_blk_main.c @@ -1576,11 +1576,17 @@ static int null_gendisk_register(struct nullb *nullb) disk->queue = nullb->q; strncpy(disk->disk_name, nullb->disk_name, DISK_NAME_LEN); +#ifdef CONFIG_BLK_DEV_ZONED if (nullb->dev->zoned) { - ret = blk_revalidate_disk_zones(disk); - if (ret) - return ret; + if (queue_is_mq(nullb->q)) { + ret = blk_revalidate_disk_zones(disk); + if (ret) + return ret; + } else { + nullb->q->nr_zones = blkdev_nr_zones(disk); + } } +#endif add_disk(disk); return 0; diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 2ae0c1913766..0a2cc197f62b 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -1954,12 +1954,14 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, /* * For a zoned target, the number of zones should be updated for the * correct value to be exposed in sysfs queue/nr_zones. For a BIO based - * target, this is all that is needed. For a request based target, the - * queue zone bitmaps must also be updated. - * Use blk_revalidate_disk_zones() to handle this. + * target, this is all that is needed. */ - if (blk_queue_is_zoned(q)) - blk_revalidate_disk_zones(t->md->disk); +#ifdef CONFIG_BLK_DEV_ZONED + if (blk_queue_is_zoned(q)) { + WARN_ON_ONCE(queue_is_mq(q)); + q->nr_zones = blkdev_nr_zones(t->md->disk); + } +#endif /* Allow reads to exceed readahead limits */ q->backing_dev_info->io_pages = limits->max_sectors >> (PAGE_SHIFT - 9); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 503c4d4c5884..47eb22a3b7f9 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -375,11 +375,6 @@ static inline unsigned int blkdev_nr_zones(struct gendisk *disk) return 0; } -static inline int blk_revalidate_disk_zones(struct gendisk *disk) -{ - return 0; -} - static inline int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) -- cgit v1.2.3 From 8ffb055beae58574d3e77b4bf9d4d15eace1ca27 Mon Sep 17 00:00:00 2001 From: Yoshiki Komachi Date: Tue, 3 Dec 2019 19:40:12 +0900 Subject: cls_flower: Fix the behavior using port ranges with hw-offload The recent commit 5c72299fba9d ("net: sched: cls_flower: Classify packets using port ranges") had added filtering based on port ranges to tc flower. However the commit missed necessary changes in hw-offload code, so the feature gave rise to generating incorrect offloaded flow keys in NIC. One more detailed example is below: $ tc qdisc add dev eth0 ingress $ tc filter add dev eth0 ingress protocol ip flower ip_proto tcp \ dst_port 100-200 action drop With the setup above, an exact match filter with dst_port == 0 will be installed in NIC by hw-offload. IOW, the NIC will have a rule which is equivalent to the following one. $ tc qdisc add dev eth0 ingress $ tc filter add dev eth0 ingress protocol ip flower ip_proto tcp \ dst_port 0 action drop The behavior was caused by the flow dissector which extracts packet data into the flow key in the tc flower. More specifically, regardless of exact match or specified port ranges, fl_init_dissector() set the FLOW_DISSECTOR_KEY_PORTS flag in struct flow_dissector to extract port numbers from skb in skb_flow_dissect() called by fl_classify(). Note that device drivers received the same struct flow_dissector object as used in skb_flow_dissect(). Thus, offloaded drivers could not identify which of these is used because the FLOW_DISSECTOR_KEY_PORTS flag was set to struct flow_dissector in either case. This patch adds the new FLOW_DISSECTOR_KEY_PORTS_RANGE flag and the new tp_range field in struct fl_flow_key to recognize which filters are applied to offloaded drivers. At this point, when filters based on port ranges passed to drivers, drivers return the EOPNOTSUPP error because they do not support the feature (the newly created FLOW_DISSECTOR_KEY_PORTS_RANGE flag). Fixes: 5c72299fba9d ("net: sched: cls_flower: Classify packets using port ranges") Signed-off-by: Yoshiki Komachi Signed-off-by: David S. Miller --- include/net/flow_dissector.h | 1 + net/core/flow_dissector.c | 37 ++++++++++---- net/sched/cls_flower.c | 118 ++++++++++++++++++++++++------------------- 3 files changed, 95 insertions(+), 61 deletions(-) (limited to 'include') diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index b8c20e9f343e..d93017a7ce5c 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -235,6 +235,7 @@ enum flow_dissector_key_id { FLOW_DISSECTOR_KEY_IPV4_ADDRS, /* struct flow_dissector_key_ipv4_addrs */ FLOW_DISSECTOR_KEY_IPV6_ADDRS, /* struct flow_dissector_key_ipv6_addrs */ FLOW_DISSECTOR_KEY_PORTS, /* struct flow_dissector_key_ports */ + FLOW_DISSECTOR_KEY_PORTS_RANGE, /* struct flow_dissector_key_ports */ FLOW_DISSECTOR_KEY_ICMP, /* struct flow_dissector_key_icmp */ FLOW_DISSECTOR_KEY_ETH_ADDRS, /* struct flow_dissector_key_eth_addrs */ FLOW_DISSECTOR_KEY_TIPC, /* struct flow_dissector_key_tipc */ diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index ca871657a4c4..69395b804709 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -759,6 +759,31 @@ __skb_flow_dissect_tcp(const struct sk_buff *skb, key_tcp->flags = (*(__be16 *) &tcp_flag_word(th) & htons(0x0FFF)); } +static void +__skb_flow_dissect_ports(const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + void *target_container, void *data, int nhoff, + u8 ip_proto, int hlen) +{ + enum flow_dissector_key_id dissector_ports = FLOW_DISSECTOR_KEY_MAX; + struct flow_dissector_key_ports *key_ports; + + if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS)) + dissector_ports = FLOW_DISSECTOR_KEY_PORTS; + else if (dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_PORTS_RANGE)) + dissector_ports = FLOW_DISSECTOR_KEY_PORTS_RANGE; + + if (dissector_ports == FLOW_DISSECTOR_KEY_MAX) + return; + + key_ports = skb_flow_dissector_target(flow_dissector, + dissector_ports, + target_container); + key_ports->ports = __skb_flow_get_ports(skb, nhoff, ip_proto, + data, hlen); +} + static void __skb_flow_dissect_ipv4(const struct sk_buff *skb, struct flow_dissector *flow_dissector, @@ -928,7 +953,6 @@ bool __skb_flow_dissect(const struct net *net, struct flow_dissector_key_control *key_control; struct flow_dissector_key_basic *key_basic; struct flow_dissector_key_addrs *key_addrs; - struct flow_dissector_key_ports *key_ports; struct flow_dissector_key_tags *key_tags; struct flow_dissector_key_vlan *key_vlan; struct bpf_prog *attached = NULL; @@ -1383,14 +1407,9 @@ ip_proto_again: break; } - if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS) && - !(key_control->flags & FLOW_DIS_IS_FRAGMENT)) { - key_ports = skb_flow_dissector_target(flow_dissector, - FLOW_DISSECTOR_KEY_PORTS, - target_container); - key_ports->ports = __skb_flow_get_ports(skb, nhoff, ip_proto, - data, hlen); - } + if (!(key_control->flags & FLOW_DIS_IS_FRAGMENT)) + __skb_flow_dissect_ports(skb, flow_dissector, target_container, + data, nhoff, ip_proto, hlen); /* Process result of IP proto processing */ switch (fdret) { diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index c307ee1d6ca6..6c68971d99df 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -56,8 +56,13 @@ struct fl_flow_key { struct flow_dissector_key_ip ip; struct flow_dissector_key_ip enc_ip; struct flow_dissector_key_enc_opts enc_opts; - struct flow_dissector_key_ports tp_min; - struct flow_dissector_key_ports tp_max; + union { + struct flow_dissector_key_ports tp; + struct { + struct flow_dissector_key_ports tp_min; + struct flow_dissector_key_ports tp_max; + }; + } tp_range; struct flow_dissector_key_ct ct; } __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */ @@ -200,19 +205,19 @@ static bool fl_range_port_dst_cmp(struct cls_fl_filter *filter, { __be16 min_mask, max_mask, min_val, max_val; - min_mask = htons(filter->mask->key.tp_min.dst); - max_mask = htons(filter->mask->key.tp_max.dst); - min_val = htons(filter->key.tp_min.dst); - max_val = htons(filter->key.tp_max.dst); + min_mask = htons(filter->mask->key.tp_range.tp_min.dst); + max_mask = htons(filter->mask->key.tp_range.tp_max.dst); + min_val = htons(filter->key.tp_range.tp_min.dst); + max_val = htons(filter->key.tp_range.tp_max.dst); if (min_mask && max_mask) { - if (htons(key->tp.dst) < min_val || - htons(key->tp.dst) > max_val) + if (htons(key->tp_range.tp.dst) < min_val || + htons(key->tp_range.tp.dst) > max_val) return false; /* skb does not have min and max values */ - mkey->tp_min.dst = filter->mkey.tp_min.dst; - mkey->tp_max.dst = filter->mkey.tp_max.dst; + mkey->tp_range.tp_min.dst = filter->mkey.tp_range.tp_min.dst; + mkey->tp_range.tp_max.dst = filter->mkey.tp_range.tp_max.dst; } return true; } @@ -223,19 +228,19 @@ static bool fl_range_port_src_cmp(struct cls_fl_filter *filter, { __be16 min_mask, max_mask, min_val, max_val; - min_mask = htons(filter->mask->key.tp_min.src); - max_mask = htons(filter->mask->key.tp_max.src); - min_val = htons(filter->key.tp_min.src); - max_val = htons(filter->key.tp_max.src); + min_mask = htons(filter->mask->key.tp_range.tp_min.src); + max_mask = htons(filter->mask->key.tp_range.tp_max.src); + min_val = htons(filter->key.tp_range.tp_min.src); + max_val = htons(filter->key.tp_range.tp_max.src); if (min_mask && max_mask) { - if (htons(key->tp.src) < min_val || - htons(key->tp.src) > max_val) + if (htons(key->tp_range.tp.src) < min_val || + htons(key->tp_range.tp.src) > max_val) return false; /* skb does not have min and max values */ - mkey->tp_min.src = filter->mkey.tp_min.src; - mkey->tp_max.src = filter->mkey.tp_max.src; + mkey->tp_range.tp_min.src = filter->mkey.tp_range.tp_min.src; + mkey->tp_range.tp_max.src = filter->mkey.tp_range.tp_max.src; } return true; } @@ -734,23 +739,25 @@ static void fl_set_key_val(struct nlattr **tb, static int fl_set_key_port_range(struct nlattr **tb, struct fl_flow_key *key, struct fl_flow_key *mask) { - fl_set_key_val(tb, &key->tp_min.dst, - TCA_FLOWER_KEY_PORT_DST_MIN, &mask->tp_min.dst, - TCA_FLOWER_UNSPEC, sizeof(key->tp_min.dst)); - fl_set_key_val(tb, &key->tp_max.dst, - TCA_FLOWER_KEY_PORT_DST_MAX, &mask->tp_max.dst, - TCA_FLOWER_UNSPEC, sizeof(key->tp_max.dst)); - fl_set_key_val(tb, &key->tp_min.src, - TCA_FLOWER_KEY_PORT_SRC_MIN, &mask->tp_min.src, - TCA_FLOWER_UNSPEC, sizeof(key->tp_min.src)); - fl_set_key_val(tb, &key->tp_max.src, - TCA_FLOWER_KEY_PORT_SRC_MAX, &mask->tp_max.src, - TCA_FLOWER_UNSPEC, sizeof(key->tp_max.src)); - - if ((mask->tp_min.dst && mask->tp_max.dst && - htons(key->tp_max.dst) <= htons(key->tp_min.dst)) || - (mask->tp_min.src && mask->tp_max.src && - htons(key->tp_max.src) <= htons(key->tp_min.src))) + fl_set_key_val(tb, &key->tp_range.tp_min.dst, + TCA_FLOWER_KEY_PORT_DST_MIN, &mask->tp_range.tp_min.dst, + TCA_FLOWER_UNSPEC, sizeof(key->tp_range.tp_min.dst)); + fl_set_key_val(tb, &key->tp_range.tp_max.dst, + TCA_FLOWER_KEY_PORT_DST_MAX, &mask->tp_range.tp_max.dst, + TCA_FLOWER_UNSPEC, sizeof(key->tp_range.tp_max.dst)); + fl_set_key_val(tb, &key->tp_range.tp_min.src, + TCA_FLOWER_KEY_PORT_SRC_MIN, &mask->tp_range.tp_min.src, + TCA_FLOWER_UNSPEC, sizeof(key->tp_range.tp_min.src)); + fl_set_key_val(tb, &key->tp_range.tp_max.src, + TCA_FLOWER_KEY_PORT_SRC_MAX, &mask->tp_range.tp_max.src, + TCA_FLOWER_UNSPEC, sizeof(key->tp_range.tp_max.src)); + + if ((mask->tp_range.tp_min.dst && mask->tp_range.tp_max.dst && + htons(key->tp_range.tp_max.dst) <= + htons(key->tp_range.tp_min.dst)) || + (mask->tp_range.tp_min.src && mask->tp_range.tp_max.src && + htons(key->tp_range.tp_max.src) <= + htons(key->tp_range.tp_min.src))) return -EINVAL; return 0; @@ -1509,9 +1516,10 @@ static void fl_init_dissector(struct flow_dissector *dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4); FL_KEY_SET_IF_MASKED(mask, keys, cnt, FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6); - if (FL_KEY_IS_MASKED(mask, tp) || - FL_KEY_IS_MASKED(mask, tp_min) || FL_KEY_IS_MASKED(mask, tp_max)) - FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_PORTS, tp); + FL_KEY_SET_IF_MASKED(mask, keys, cnt, + FLOW_DISSECTOR_KEY_PORTS, tp); + FL_KEY_SET_IF_MASKED(mask, keys, cnt, + FLOW_DISSECTOR_KEY_PORTS_RANGE, tp_range); FL_KEY_SET_IF_MASKED(mask, keys, cnt, FLOW_DISSECTOR_KEY_IP, ip); FL_KEY_SET_IF_MASKED(mask, keys, cnt, @@ -1560,8 +1568,10 @@ static struct fl_flow_mask *fl_create_new_mask(struct cls_fl_head *head, fl_mask_copy(newmask, mask); - if ((newmask->key.tp_min.dst && newmask->key.tp_max.dst) || - (newmask->key.tp_min.src && newmask->key.tp_max.src)) + if ((newmask->key.tp_range.tp_min.dst && + newmask->key.tp_range.tp_max.dst) || + (newmask->key.tp_range.tp_min.src && + newmask->key.tp_range.tp_max.src)) newmask->flags |= TCA_FLOWER_MASK_FLAGS_RANGE; err = fl_init_mask_hashtable(newmask); @@ -2159,18 +2169,22 @@ static int fl_dump_key_val(struct sk_buff *skb, static int fl_dump_key_port_range(struct sk_buff *skb, struct fl_flow_key *key, struct fl_flow_key *mask) { - if (fl_dump_key_val(skb, &key->tp_min.dst, TCA_FLOWER_KEY_PORT_DST_MIN, - &mask->tp_min.dst, TCA_FLOWER_UNSPEC, - sizeof(key->tp_min.dst)) || - fl_dump_key_val(skb, &key->tp_max.dst, TCA_FLOWER_KEY_PORT_DST_MAX, - &mask->tp_max.dst, TCA_FLOWER_UNSPEC, - sizeof(key->tp_max.dst)) || - fl_dump_key_val(skb, &key->tp_min.src, TCA_FLOWER_KEY_PORT_SRC_MIN, - &mask->tp_min.src, TCA_FLOWER_UNSPEC, - sizeof(key->tp_min.src)) || - fl_dump_key_val(skb, &key->tp_max.src, TCA_FLOWER_KEY_PORT_SRC_MAX, - &mask->tp_max.src, TCA_FLOWER_UNSPEC, - sizeof(key->tp_max.src))) + if (fl_dump_key_val(skb, &key->tp_range.tp_min.dst, + TCA_FLOWER_KEY_PORT_DST_MIN, + &mask->tp_range.tp_min.dst, TCA_FLOWER_UNSPEC, + sizeof(key->tp_range.tp_min.dst)) || + fl_dump_key_val(skb, &key->tp_range.tp_max.dst, + TCA_FLOWER_KEY_PORT_DST_MAX, + &mask->tp_range.tp_max.dst, TCA_FLOWER_UNSPEC, + sizeof(key->tp_range.tp_max.dst)) || + fl_dump_key_val(skb, &key->tp_range.tp_min.src, + TCA_FLOWER_KEY_PORT_SRC_MIN, + &mask->tp_range.tp_min.src, TCA_FLOWER_UNSPEC, + sizeof(key->tp_range.tp_min.src)) || + fl_dump_key_val(skb, &key->tp_range.tp_max.src, + TCA_FLOWER_KEY_PORT_SRC_MAX, + &mask->tp_range.tp_max.src, TCA_FLOWER_UNSPEC, + sizeof(key->tp_range.tp_max.src))) return -1; return 0; -- cgit v1.2.3 From 0f109f0e9a608c381846b3f2270a6a7b72158cb4 Mon Sep 17 00:00:00 2001 From: Corentin Labbe Date: Thu, 21 Nov 2019 08:14:42 +0000 Subject: agp: move AGPGART_MINOR to include/linux/miscdevice.h This patch move the define for AGPGART_MINOR to include/linux/miscdevice.h. It is better that all minor number definitions are in the same place. Signed-off-by: Corentin Labbe Acked-by: Arnd Bergmann Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/1574324085-4338-3-git-send-email-clabbe@baylibre.com --- include/linux/agpgart.h | 2 -- include/linux/miscdevice.h | 1 + 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/agpgart.h b/include/linux/agpgart.h index c6b61ca97053..21b34a96cfd8 100644 --- a/include/linux/agpgart.h +++ b/include/linux/agpgart.h @@ -30,8 +30,6 @@ #include #include -#define AGPGART_MINOR 175 - struct agp_info { struct agp_version version; /* version of the driver */ u32 bridge_id; /* bridge vendor/device */ diff --git a/include/linux/miscdevice.h b/include/linux/miscdevice.h index 3247a3dc7934..6f2ca42152a0 100644 --- a/include/linux/miscdevice.h +++ b/include/linux/miscdevice.h @@ -33,6 +33,7 @@ #define SGI_MMTIMER 153 #define STORE_QUEUE_MINOR 155 /* unused */ #define I2O_MINOR 166 +#define AGPGART_MINOR 175 #define HWRNG_MINOR 183 #define MICROCODE_MINOR 184 #define IRNET_MINOR 187 -- cgit v1.2.3 From c4e85f73afb6384123e5ef1bba3315b2e3ad031e Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Wed, 4 Dec 2019 15:35:52 +0100 Subject: net: ipv6: add net argument to ip6_dst_lookup_flow This will be used in the conversion of ipv6_stub to ip6_dst_lookup_flow, as some modules currently pass a net argument without a socket to ip6_dst_lookup. This is equivalent to commit 343d60aada5a ("ipv6: change ipv6_stub_impl.ipv6_dst_lookup to take net argument"). Signed-off-by: Sabrina Dubroca Signed-off-by: David S. Miller --- include/net/ipv6.h | 2 +- net/dccp/ipv6.c | 6 +++--- net/ipv6/af_inet6.c | 2 +- net/ipv6/datagram.c | 2 +- net/ipv6/inet6_connection_sock.c | 4 ++-- net/ipv6/ip6_output.c | 8 ++++---- net/ipv6/raw.c | 2 +- net/ipv6/syncookies.c | 2 +- net/ipv6/tcp_ipv6.c | 4 ++-- net/l2tp/l2tp_ip6.c | 2 +- net/sctp/ipv6.c | 4 ++-- 11 files changed, 19 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index d04b7abe2a4c..4e95f6df508c 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -1022,7 +1022,7 @@ static inline struct sk_buff *ip6_finish_skb(struct sock *sk) int ip6_dst_lookup(struct net *net, struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6); -struct dst_entry *ip6_dst_lookup_flow(const struct sock *sk, struct flowi6 *fl6, +struct dst_entry *ip6_dst_lookup_flow(struct net *net, const struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst); struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst, diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 25aab672fc99..1e5e08cc0bfc 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -210,7 +210,7 @@ static int dccp_v6_send_response(const struct sock *sk, struct request_sock *req final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final); rcu_read_unlock(); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); dst = NULL; @@ -282,7 +282,7 @@ static void dccp_v6_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb) security_skb_classify_flow(rxskb, flowi6_to_flowi(&fl6)); /* sk = NULL, but it is safe for now. RST socket required. */ - dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL); + dst = ip6_dst_lookup_flow(sock_net(ctl_sk), ctl_sk, &fl6, NULL); if (!IS_ERR(dst)) { skb_dst_set(skb, dst); ip6_xmit(ctl_sk, skb, &fl6, 0, NULL, 0, 0); @@ -912,7 +912,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk)); final_p = fl6_update_dst(&fl6, opt, &final); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto failure; diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 60e2ff91a5b3..e84e8b1ffbc7 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -765,7 +765,7 @@ int inet6_sk_rebuild_header(struct sock *sk) &final); rcu_read_unlock(); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { sk->sk_route_caps = 0; sk->sk_err_soft = -PTR_ERR(dst); diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 96f939248d2f..390bedde21a5 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -85,7 +85,7 @@ int ip6_datagram_dst_update(struct sock *sk, bool fix_sk_saddr) final_p = fl6_update_dst(&fl6, opt, &final); rcu_read_unlock(); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto out; diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 0a0945a5b30d..fe9cb8d1adca 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -48,7 +48,7 @@ struct dst_entry *inet6_csk_route_req(const struct sock *sk, fl6->flowi6_uid = sk->sk_uid; security_req_classify_flow(req, flowi6_to_flowi(fl6)); - dst = ip6_dst_lookup_flow(sk, fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p); if (IS_ERR(dst)) return NULL; @@ -103,7 +103,7 @@ static struct dst_entry *inet6_csk_route_socket(struct sock *sk, dst = __inet6_csk_dst_check(sk, np->dst_cookie); if (!dst) { - dst = ip6_dst_lookup_flow(sk, fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p); if (!IS_ERR(dst)) ip6_dst_store(sk, dst, NULL, NULL); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 945508a7cb0f..087304427bbb 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1144,19 +1144,19 @@ EXPORT_SYMBOL_GPL(ip6_dst_lookup); * It returns a valid dst pointer on success, or a pointer encoded * error code. */ -struct dst_entry *ip6_dst_lookup_flow(const struct sock *sk, struct flowi6 *fl6, +struct dst_entry *ip6_dst_lookup_flow(struct net *net, const struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst) { struct dst_entry *dst = NULL; int err; - err = ip6_dst_lookup_tail(sock_net(sk), sk, &dst, fl6); + err = ip6_dst_lookup_tail(net, sk, &dst, fl6); if (err) return ERR_PTR(err); if (final_dst) fl6->daddr = *final_dst; - return xfrm_lookup_route(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0); + return xfrm_lookup_route(net, dst, flowi6_to_flowi(fl6), sk, 0); } EXPORT_SYMBOL_GPL(ip6_dst_lookup_flow); @@ -1188,7 +1188,7 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, if (dst) return dst; - dst = ip6_dst_lookup_flow(sk, fl6, final_dst); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_dst); if (connected && !IS_ERR(dst)) ip6_sk_dst_store_flow(sk, dst_clone(dst), fl6); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index a77f6b7d3a7c..dfe5e603ffe1 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -925,7 +925,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto out; diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 16632e02e9b0..30915f6f31e3 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -235,7 +235,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) fl6.flowi6_uid = sk->sk_uid; security_req_classify_flow(req, flowi6_to_flowi(&fl6)); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) goto out_free; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 81f51335e326..df5fd9109696 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -275,7 +275,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto failure; @@ -906,7 +906,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 * Underlying function will use this to retrieve the network * namespace */ - dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL); + dst = ip6_dst_lookup_flow(sock_net(ctl_sk), ctl_sk, &fl6, NULL); if (!IS_ERR(dst)) { skb_dst_set(buff, dst); ip6_xmit(ctl_sk, buff, &fl6, fl6.flowi6_mark, NULL, tclass, diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 802f19aba7e3..d148766f40d1 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -615,7 +615,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto out; diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index dd860fea0148..bc734cfaa29e 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -275,7 +275,7 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final); rcu_read_unlock(); - dst = ip6_dst_lookup_flow(sk, fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p); if (!asoc || saddr) goto out; @@ -328,7 +328,7 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, fl6->saddr = laddr->a.v6.sin6_addr; fl6->fl6_sport = laddr->a.v6.sin6_port; final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final); - bdst = ip6_dst_lookup_flow(sk, fl6, final_p); + bdst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p); if (IS_ERR(bdst)) continue; -- cgit v1.2.3 From 6c8991f41546c3c472503dff1ea9daaddf9331c2 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Wed, 4 Dec 2019 15:35:53 +0100 Subject: net: ipv6_stub: use ip6_dst_lookup_flow instead of ip6_dst_lookup ipv6_stub uses the ip6_dst_lookup function to allow other modules to perform IPv6 lookups. However, this function skips the XFRM layer entirely. All users of ipv6_stub->ip6_dst_lookup use ip_route_output_flow (via the ip_route_output_key and ip_route_output helpers) for their IPv4 lookups, which calls xfrm_lookup_route(). This patch fixes this inconsistent behavior by switching the stub to ip6_dst_lookup_flow, which also calls xfrm_lookup_route(). This requires some changes in all the callers, as these two functions take different arguments and have different return types. Fixes: 5f81bd2e5d80 ("ipv6: export a stub for IPv6 symbols used by vxlan") Reported-by: Xiumei Mu Signed-off-by: Sabrina Dubroca Signed-off-by: David S. Miller --- drivers/infiniband/core/addr.c | 7 +++---- drivers/infiniband/sw/rxe/rxe_net.c | 8 +++++--- drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c | 8 ++++---- drivers/net/geneve.c | 4 +++- drivers/net/vxlan.c | 8 +++----- include/net/ipv6_stubs.h | 6 ++++-- net/core/lwt_bpf.c | 4 +--- net/ipv6/addrconf_core.c | 11 ++++++----- net/ipv6/af_inet6.c | 2 +- net/mpls/af_mpls.c | 7 +++---- net/tipc/udp_media.c | 9 ++++++--- 11 files changed, 39 insertions(+), 35 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c index 6d7ec371e7b2..606fa6d86685 100644 --- a/drivers/infiniband/core/addr.c +++ b/drivers/infiniband/core/addr.c @@ -421,16 +421,15 @@ static int addr6_resolve(struct sockaddr *src_sock, (const struct sockaddr_in6 *)dst_sock; struct flowi6 fl6; struct dst_entry *dst; - int ret; memset(&fl6, 0, sizeof fl6); fl6.daddr = dst_in->sin6_addr; fl6.saddr = src_in->sin6_addr; fl6.flowi6_oif = addr->bound_dev_if; - ret = ipv6_stub->ipv6_dst_lookup(addr->net, NULL, &dst, &fl6); - if (ret < 0) - return ret; + dst = ipv6_stub->ipv6_dst_lookup_flow(addr->net, NULL, &fl6, NULL); + if (IS_ERR(dst)) + return PTR_ERR(dst); if (ipv6_addr_any(&src_in->sin6_addr)) src_in->sin6_addr = fl6.saddr; diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c index 5a3474f9351b..312c2fc961c0 100644 --- a/drivers/infiniband/sw/rxe/rxe_net.c +++ b/drivers/infiniband/sw/rxe/rxe_net.c @@ -117,10 +117,12 @@ static struct dst_entry *rxe_find_route6(struct net_device *ndev, memcpy(&fl6.daddr, daddr, sizeof(*daddr)); fl6.flowi6_proto = IPPROTO_UDP; - if (unlikely(ipv6_stub->ipv6_dst_lookup(sock_net(recv_sockets.sk6->sk), - recv_sockets.sk6->sk, &ndst, &fl6))) { + ndst = ipv6_stub->ipv6_dst_lookup_flow(sock_net(recv_sockets.sk6->sk), + recv_sockets.sk6->sk, &fl6, + NULL); + if (unlikely(IS_ERR(ndst))) { pr_err_ratelimited("no route to %pI6\n", daddr); - goto put; + return NULL; } if (unlikely(ndst->error)) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index 6ed87534d314..c754987278a9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -297,10 +297,10 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv, int ret; - ret = ipv6_stub->ipv6_dst_lookup(dev_net(mirred_dev), NULL, &dst, - fl6); - if (ret < 0) - return ret; + dst = ipv6_stub->ipv6_dst_lookup_flow(dev_net(mirred_dev), NULL, fl6, + NULL); + if (IS_ERR(dst)) + return PTR_ERR(dst); if (!(*out_ttl)) *out_ttl = ip6_dst_hoplimit(dst); diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 3ab24fdccd3b..5c6b7fc04ea6 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -853,7 +853,9 @@ static struct dst_entry *geneve_get_v6_dst(struct sk_buff *skb, if (dst) return dst; } - if (ipv6_stub->ipv6_dst_lookup(geneve->net, gs6->sock->sk, &dst, fl6)) { + dst = ipv6_stub->ipv6_dst_lookup_flow(geneve->net, gs6->sock->sk, fl6, + NULL); + if (IS_ERR(dst)) { netdev_dbg(dev, "no route to %pI6\n", &fl6->daddr); return ERR_PTR(-ENETUNREACH); } diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index bf04bc2e68c2..4c34375c2e22 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2275,7 +2275,6 @@ static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan, bool use_cache = ip_tunnel_dst_cache_usable(skb, info); struct dst_entry *ndst; struct flowi6 fl6; - int err; if (!sock6) return ERR_PTR(-EIO); @@ -2298,10 +2297,9 @@ static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan, fl6.fl6_dport = dport; fl6.fl6_sport = sport; - err = ipv6_stub->ipv6_dst_lookup(vxlan->net, - sock6->sock->sk, - &ndst, &fl6); - if (unlikely(err < 0)) { + ndst = ipv6_stub->ipv6_dst_lookup_flow(vxlan->net, sock6->sock->sk, + &fl6, NULL); + if (unlikely(IS_ERR(ndst))) { netdev_dbg(dev, "no route to %pI6\n", daddr); return ERR_PTR(-ENETUNREACH); } diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h index 5c93e942c50b..3e7d2c0e79ca 100644 --- a/include/net/ipv6_stubs.h +++ b/include/net/ipv6_stubs.h @@ -24,8 +24,10 @@ struct ipv6_stub { const struct in6_addr *addr); int (*ipv6_sock_mc_drop)(struct sock *sk, int ifindex, const struct in6_addr *addr); - int (*ipv6_dst_lookup)(struct net *net, struct sock *sk, - struct dst_entry **dst, struct flowi6 *fl6); + struct dst_entry *(*ipv6_dst_lookup_flow)(struct net *net, + const struct sock *sk, + struct flowi6 *fl6, + const struct in6_addr *final_dst); int (*ipv6_route_input)(struct sk_buff *skb); struct fib6_table *(*fib6_get_table)(struct net *net, u32 id); diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c index 74cfb8b5ab33..99a6de52b21d 100644 --- a/net/core/lwt_bpf.c +++ b/net/core/lwt_bpf.c @@ -230,9 +230,7 @@ static int bpf_lwt_xmit_reroute(struct sk_buff *skb) fl6.daddr = iph6->daddr; fl6.saddr = iph6->saddr; - err = ipv6_stub->ipv6_dst_lookup(net, skb->sk, &dst, &fl6); - if (unlikely(err)) - goto err; + dst = ipv6_stub->ipv6_dst_lookup_flow(net, skb->sk, &fl6, NULL); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto err; diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c index 2fc079284ca4..ea00ce3d4117 100644 --- a/net/ipv6/addrconf_core.c +++ b/net/ipv6/addrconf_core.c @@ -129,11 +129,12 @@ int inet6addr_validator_notifier_call_chain(unsigned long val, void *v) } EXPORT_SYMBOL(inet6addr_validator_notifier_call_chain); -static int eafnosupport_ipv6_dst_lookup(struct net *net, struct sock *u1, - struct dst_entry **u2, - struct flowi6 *u3) +static struct dst_entry *eafnosupport_ipv6_dst_lookup_flow(struct net *net, + const struct sock *sk, + struct flowi6 *fl6, + const struct in6_addr *final_dst) { - return -EAFNOSUPPORT; + return ERR_PTR(-EAFNOSUPPORT); } static int eafnosupport_ipv6_route_input(struct sk_buff *skb) @@ -190,7 +191,7 @@ static int eafnosupport_ip6_del_rt(struct net *net, struct fib6_info *rt) } const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) { - .ipv6_dst_lookup = eafnosupport_ipv6_dst_lookup, + .ipv6_dst_lookup_flow = eafnosupport_ipv6_dst_lookup_flow, .ipv6_route_input = eafnosupport_ipv6_route_input, .fib6_get_table = eafnosupport_fib6_get_table, .fib6_table_lookup = eafnosupport_fib6_table_lookup, diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index e84e8b1ffbc7..d727c3b41495 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -946,7 +946,7 @@ static int ipv6_route_input(struct sk_buff *skb) static const struct ipv6_stub ipv6_stub_impl = { .ipv6_sock_mc_join = ipv6_sock_mc_join, .ipv6_sock_mc_drop = ipv6_sock_mc_drop, - .ipv6_dst_lookup = ip6_dst_lookup, + .ipv6_dst_lookup_flow = ip6_dst_lookup_flow, .ipv6_route_input = ipv6_route_input, .fib6_get_table = fib6_get_table, .fib6_table_lookup = fib6_table_lookup, diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index c312741df2ce..4701edffb1f7 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -617,16 +617,15 @@ static struct net_device *inet6_fib_lookup_dev(struct net *net, struct net_device *dev; struct dst_entry *dst; struct flowi6 fl6; - int err; if (!ipv6_stub) return ERR_PTR(-EAFNOSUPPORT); memset(&fl6, 0, sizeof(fl6)); memcpy(&fl6.daddr, addr, sizeof(struct in6_addr)); - err = ipv6_stub->ipv6_dst_lookup(net, NULL, &dst, &fl6); - if (err) - return ERR_PTR(err); + dst = ipv6_stub->ipv6_dst_lookup_flow(net, NULL, &fl6, NULL); + if (IS_ERR(dst)) + return ERR_CAST(dst); dev = dst->dev; dev_hold(dev); diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index 86aaa4d3e781..ed113735c019 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -195,10 +195,13 @@ static int tipc_udp_xmit(struct net *net, struct sk_buff *skb, .saddr = src->ipv6, .flowi6_proto = IPPROTO_UDP }; - err = ipv6_stub->ipv6_dst_lookup(net, ub->ubsock->sk, - &ndst, &fl6); - if (err) + ndst = ipv6_stub->ipv6_dst_lookup_flow(net, + ub->ubsock->sk, + &fl6, NULL); + if (IS_ERR(ndst)) { + err = PTR_ERR(ndst); goto tx_error; + } dst_cache_set_ip6(cache, ndst, &fl6.saddr); } ttl = ip6_dst_hoplimit(ndst); -- cgit v1.2.3 From d04ac224b1688f005a84f764cfe29844f8e9da08 Mon Sep 17 00:00:00 2001 From: Martin Varghese Date: Thu, 5 Dec 2019 05:57:22 +0530 Subject: net: Fixed updating of ethertype in skb_mpls_push() The skb_mpls_push was not updating ethertype of an ethernet packet if the packet was originally received from a non ARPHRD_ETHER device. In the below OVS data path flow, since the device corresponding to port 7 is an l3 device (ARPHRD_NONE) the skb_mpls_push function does not update the ethertype of the packet even though the previous push_eth action had added an ethernet header to the packet. recirc_id(0),in_port(7),eth_type(0x0800),ipv4(tos=0/0xfc,ttl=64,frag=no), actions:push_eth(src=00:00:00:00:00:00,dst=00:00:00:00:00:00), push_mpls(label=13,tc=0,ttl=64,bos=1,eth_type=0x8847),4 Fixes: 8822e270d697 ("net: core: move push MPLS functionality from OvS to core helper") Signed-off-by: Martin Varghese Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 +- net/core/skbuff.c | 4 ++-- net/openvswitch/actions.c | 3 ++- net/sched/act_mpls.c | 3 ++- 4 files changed, 7 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 5aea72fe8498..e9133bcf0544 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3529,7 +3529,7 @@ int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci); int skb_vlan_pop(struct sk_buff *skb); int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci); int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, - int mac_len); + int mac_len, bool ethernet); int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len, bool ethernet); int skb_mpls_update_lse(struct sk_buff *skb, __be32 mpls_lse); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 312e80e86898..973a71f4bc89 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -5484,7 +5484,7 @@ static void skb_mod_eth_type(struct sk_buff *skb, struct ethhdr *hdr, * Returns 0 on success, -errno otherwise. */ int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, - int mac_len) + int mac_len, bool ethernet) { struct mpls_shim_hdr *lse; int err; @@ -5515,7 +5515,7 @@ int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, lse->label_stack_entry = mpls_lse; skb_postpush_rcsum(skb, lse, MPLS_HLEN); - if (skb->dev && skb->dev->type == ARPHRD_ETHER) + if (ethernet) skb_mod_eth_type(skb, eth_hdr(skb), mpls_proto); skb->protocol = mpls_proto; diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 91e210061bb3..4c8395462303 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -166,7 +166,8 @@ static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key, int err; err = skb_mpls_push(skb, mpls->mpls_lse, mpls->mpls_ethertype, - skb->mac_len); + skb->mac_len, + ovs_key_mac_proto(key) == MAC_PROTO_ETHERNET); if (err) return err; diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c index a7d856203af1..be3f215cd027 100644 --- a/net/sched/act_mpls.c +++ b/net/sched/act_mpls.c @@ -83,7 +83,8 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a, break; case TCA_MPLS_ACT_PUSH: new_lse = tcf_mpls_get_lse(NULL, p, !eth_p_mpls(skb->protocol)); - if (skb_mpls_push(skb, new_lse, p->tcfm_proto, mac_len)) + if (skb_mpls_push(skb, new_lse, p->tcfm_proto, mac_len, + skb->dev && skb->dev->type == ARPHRD_ETHER)) goto drop; break; case TCA_MPLS_ACT_MODIFY: -- cgit v1.2.3 From 25b2f1b77a92b4d850d40eca50d446dd25c09934 Mon Sep 17 00:00:00 2001 From: Mathew King Date: Wed, 4 Dec 2019 17:27:47 -0800 Subject: Input: add privacy screen toggle keycode Add keycode for toggling electronic privacy screen to the keycodes definition. Some new laptops have a privacy screen which can be toggled with a key on the keyboard. Signed-off-by: Mathew King Link: https://lore.kernel.org/r/20191017163208.235518-1-mathewk@chromium.org Signed-off-by: Dmitry Torokhov --- include/uapi/linux/input-event-codes.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h index 85387c76c24f..05d8b4f4f82f 100644 --- a/include/uapi/linux/input-event-codes.h +++ b/include/uapi/linux/input-event-codes.h @@ -649,6 +649,8 @@ */ #define KEY_DATA 0x277 #define KEY_ONSCREEN_KEYBOARD 0x278 +/* Electronic privacy screen control */ +#define KEY_PRIVACY_SCREEN_TOGGLE 0x279 #define BTN_TRIGGER_HAPPY 0x2c0 #define BTN_TRIGGER_HAPPY1 0x2c0 -- cgit v1.2.3 From 9d7ea9a297e6445d567056f15b469dde13ca4134 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Wed, 4 Dec 2019 16:49:50 -0800 Subject: mm/vmstat: add helpers to get vmstat item names for each enum type Statistics in vmstat is combined from counters with different structure, but names for them are merged into one array. This patch adds trivial helpers to get name for each item: const char *zone_stat_name(enum zone_stat_item item); const char *numa_stat_name(enum numa_stat_item item); const char *node_stat_name(enum node_stat_item item); const char *writeback_stat_name(enum writeback_stat_item item); const char *vm_event_name(enum vm_event_item item); Names for enum writeback_stat_item are folded in the middle of vmstat_text so this patch moves declaration into header to calculate offset of following items. Also this patch reuses piece of node stat names for lru list names: const char *lru_list_name(enum lru_list lru); This returns common lru list names: "inactive_anon", "active_anon", "inactive_file", "active_file", "unevictable". [khlebnikov@yandex-team.ru: do not use size of vmstat_text as count of /proc/vmstat items] Link: http://lkml.kernel.org/r/157152151769.4139.15423465513138349343.stgit@buzz Link: https://lore.kernel.org/linux-mm/cd1c42ae-281f-c8a8-70ac-1d01d417b2e1@infradead.org/T/#u Link: http://lkml.kernel.org/r/157113012325.453.562783073839432766.stgit@buzz Signed-off-by: Konstantin Khlebnikov Reviewed-by: Andrew Morton Cc: Randy Dunlap Cc: Michal Hocko Cc: Vladimir Davydov Cc: Johannes Weiner Cc: YueHaibing Cc: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/node.c | 9 +++------ include/linux/vmstat.h | 50 +++++++++++++++++++++++++++++++++++++++++++++++++ mm/vmstat.c | 51 ++++++++++++++++++++------------------------------ 3 files changed, 73 insertions(+), 37 deletions(-) (limited to 'include') diff --git a/drivers/base/node.c b/drivers/base/node.c index 296546ffed6c..98a31bafc8a2 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -496,20 +496,17 @@ static ssize_t node_read_vmstat(struct device *dev, int n = 0; for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) - n += sprintf(buf+n, "%s %lu\n", vmstat_text[i], + n += sprintf(buf+n, "%s %lu\n", zone_stat_name(i), sum_zone_node_page_state(nid, i)); #ifdef CONFIG_NUMA for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) - n += sprintf(buf+n, "%s %lu\n", - vmstat_text[i + NR_VM_ZONE_STAT_ITEMS], + n += sprintf(buf+n, "%s %lu\n", numa_stat_name(i), sum_zone_numa_state(nid, i)); #endif for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) - n += sprintf(buf+n, "%s %lu\n", - vmstat_text[i + NR_VM_ZONE_STAT_ITEMS + - NR_VM_NUMA_STAT_ITEMS], + n += sprintf(buf+n, "%s %lu\n", node_stat_name(i), node_page_state(pgdat, i)); return n; diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index bdeda4b079fe..b995d8b680c2 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -31,6 +31,12 @@ struct reclaim_stat { unsigned nr_unmap_fail; }; +enum writeback_stat_item { + NR_DIRTY_THRESHOLD, + NR_DIRTY_BG_THRESHOLD, + NR_VM_WRITEBACK_STAT_ITEMS, +}; + #ifdef CONFIG_VM_EVENT_COUNTERS /* * Light weight per cpu counter implementation. @@ -381,4 +387,48 @@ static inline void __mod_zone_freepage_state(struct zone *zone, int nr_pages, extern const char * const vmstat_text[]; +static inline const char *zone_stat_name(enum zone_stat_item item) +{ + return vmstat_text[item]; +} + +#ifdef CONFIG_NUMA +static inline const char *numa_stat_name(enum numa_stat_item item) +{ + return vmstat_text[NR_VM_ZONE_STAT_ITEMS + + item]; +} +#endif /* CONFIG_NUMA */ + +static inline const char *node_stat_name(enum node_stat_item item) +{ + return vmstat_text[NR_VM_ZONE_STAT_ITEMS + + NR_VM_NUMA_STAT_ITEMS + + item]; +} + +static inline const char *lru_list_name(enum lru_list lru) +{ + return node_stat_name(NR_LRU_BASE + lru) + 3; // skip "nr_" +} + +static inline const char *writeback_stat_name(enum writeback_stat_item item) +{ + return vmstat_text[NR_VM_ZONE_STAT_ITEMS + + NR_VM_NUMA_STAT_ITEMS + + NR_VM_NODE_STAT_ITEMS + + item]; +} + +#ifdef CONFIG_VM_EVENT_COUNTERS +static inline const char *vm_event_name(enum vm_event_item item) +{ + return vmstat_text[NR_VM_ZONE_STAT_ITEMS + + NR_VM_NUMA_STAT_ITEMS + + NR_VM_NODE_STAT_ITEMS + + NR_VM_WRITEBACK_STAT_ITEMS + + item]; +} +#endif /* CONFIG_VM_EVENT_COUNTERS */ + #endif /* _LINUX_VMSTAT_H */ diff --git a/mm/vmstat.c b/mm/vmstat.c index a8222041bd44..fa627329428b 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1134,7 +1134,7 @@ const char * const vmstat_text[] = { "numa_other", #endif - /* Node-based counters */ + /* enum node_stat_item counters */ "nr_inactive_anon", "nr_active_anon", "nr_inactive_file", @@ -1564,10 +1564,8 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, if (is_zone_first_populated(pgdat, zone)) { seq_printf(m, "\n per-node stats"); for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) { - seq_printf(m, "\n %-12s %lu", - vmstat_text[i + NR_VM_ZONE_STAT_ITEMS + - NR_VM_NUMA_STAT_ITEMS], - node_page_state(pgdat, i)); + seq_printf(m, "\n %-12s %lu", node_stat_name(i), + node_page_state(pgdat, i)); } } seq_printf(m, @@ -1600,14 +1598,13 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, } for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) - seq_printf(m, "\n %-12s %lu", vmstat_text[i], - zone_page_state(zone, i)); + seq_printf(m, "\n %-12s %lu", zone_stat_name(i), + zone_page_state(zone, i)); #ifdef CONFIG_NUMA for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) - seq_printf(m, "\n %-12s %lu", - vmstat_text[i + NR_VM_ZONE_STAT_ITEMS], - zone_numa_state_snapshot(zone, i)); + seq_printf(m, "\n %-12s %lu", numa_stat_name(i), + zone_numa_state_snapshot(zone, i)); #endif seq_printf(m, "\n pagesets"); @@ -1658,31 +1655,23 @@ static const struct seq_operations zoneinfo_op = { .show = zoneinfo_show, }; -enum writeback_stat_item { - NR_DIRTY_THRESHOLD, - NR_DIRTY_BG_THRESHOLD, - NR_VM_WRITEBACK_STAT_ITEMS, -}; +#define NR_VMSTAT_ITEMS (NR_VM_ZONE_STAT_ITEMS + \ + NR_VM_NUMA_STAT_ITEMS + \ + NR_VM_NODE_STAT_ITEMS + \ + NR_VM_WRITEBACK_STAT_ITEMS + \ + (IS_ENABLED(CONFIG_VM_EVENT_COUNTERS) ? \ + NR_VM_EVENT_ITEMS : 0)) static void *vmstat_start(struct seq_file *m, loff_t *pos) { unsigned long *v; - int i, stat_items_size; + int i; - if (*pos >= ARRAY_SIZE(vmstat_text)) + if (*pos >= NR_VMSTAT_ITEMS) return NULL; - stat_items_size = NR_VM_ZONE_STAT_ITEMS * sizeof(unsigned long) + - NR_VM_NUMA_STAT_ITEMS * sizeof(unsigned long) + - NR_VM_NODE_STAT_ITEMS * sizeof(unsigned long) + - NR_VM_WRITEBACK_STAT_ITEMS * sizeof(unsigned long); - -#ifdef CONFIG_VM_EVENT_COUNTERS - stat_items_size += sizeof(struct vm_event_state); -#endif - BUILD_BUG_ON(stat_items_size != - ARRAY_SIZE(vmstat_text) * sizeof(unsigned long)); - v = kmalloc(stat_items_size, GFP_KERNEL); + BUILD_BUG_ON(ARRAY_SIZE(vmstat_text) < NR_VMSTAT_ITEMS); + v = kmalloc_array(NR_VMSTAT_ITEMS, sizeof(unsigned long), GFP_KERNEL); m->private = v; if (!v) return ERR_PTR(-ENOMEM); @@ -1715,7 +1704,7 @@ static void *vmstat_start(struct seq_file *m, loff_t *pos) static void *vmstat_next(struct seq_file *m, void *arg, loff_t *pos) { (*pos)++; - if (*pos >= ARRAY_SIZE(vmstat_text)) + if (*pos >= NR_VMSTAT_ITEMS) return NULL; return (unsigned long *)m->private + *pos; } @@ -1781,7 +1770,7 @@ int vmstat_refresh(struct ctl_table *table, int write, val = atomic_long_read(&vm_zone_stat[i]); if (val < 0) { pr_warn("%s: %s %ld\n", - __func__, vmstat_text[i], val); + __func__, zone_stat_name(i), val); err = -EINVAL; } } @@ -1790,7 +1779,7 @@ int vmstat_refresh(struct ctl_table *table, int write, val = atomic_long_read(&vm_numa_stat[i]); if (val < 0) { pr_warn("%s: %s %ld\n", - __func__, vmstat_text[i + NR_VM_ZONE_STAT_ITEMS], val); + __func__, numa_stat_name(i), val); err = -EINVAL; } } -- cgit v1.2.3 From ebc5d83d04438116c24dcc556b0ab6c8ef64b77e Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Wed, 4 Dec 2019 16:49:53 -0800 Subject: mm/memcontrol: use vmstat names for printing statistics Use common names from vmstat array when possible. This gives not much difference in code size for now, but should help in keeping interfaces consistent. add/remove: 0/2 grow/shrink: 2/0 up/down: 70/-72 (-2) Function old new delta memory_stat_format 984 1050 +66 memcg_stat_show 957 961 +4 memcg1_event_names 32 - -32 mem_cgroup_lru_names 40 - -40 Total: Before=14485337, After=14485335, chg -0.00% Link: http://lkml.kernel.org/r/157113012508.453.80391533767219371.stgit@buzz Signed-off-by: Konstantin Khlebnikov Acked-by: Andrew Morton Cc: Michal Hocko Cc: Vladimir Davydov Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmstat.h | 4 ++-- mm/memcontrol.c | 52 +++++++++++++++++++++----------------------------- mm/vmstat.c | 9 +++++---- 3 files changed, 29 insertions(+), 36 deletions(-) (limited to 'include') diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index b995d8b680c2..292485f3d24d 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -420,7 +420,7 @@ static inline const char *writeback_stat_name(enum writeback_stat_item item) item]; } -#ifdef CONFIG_VM_EVENT_COUNTERS +#if defined(CONFIG_VM_EVENT_COUNTERS) || defined(CONFIG_MEMCG) static inline const char *vm_event_name(enum vm_event_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + @@ -429,6 +429,6 @@ static inline const char *vm_event_name(enum vm_event_item item) NR_VM_WRITEBACK_STAT_ITEMS + item]; } -#endif /* CONFIG_VM_EVENT_COUNTERS */ +#endif /* CONFIG_VM_EVENT_COUNTERS || CONFIG_MEMCG */ #endif /* _LINUX_VMSTAT_H */ diff --git a/mm/memcontrol.c b/mm/memcontrol.c index bc01423277c5..c5b5f74cfd4d 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -98,14 +98,6 @@ static bool do_memsw_account(void) return !cgroup_subsys_on_dfl(memory_cgrp_subsys) && do_swap_account; } -static const char *const mem_cgroup_lru_names[] = { - "inactive_anon", - "active_anon", - "inactive_file", - "active_file", - "unevictable", -}; - #define THRESHOLDS_EVENTS_TARGET 128 #define SOFTLIMIT_EVENTS_TARGET 1024 @@ -1421,7 +1413,7 @@ static char *memory_stat_format(struct mem_cgroup *memcg) PAGE_SIZE); for (i = 0; i < NR_LRU_LISTS; i++) - seq_buf_printf(&s, "%s %llu\n", mem_cgroup_lru_names[i], + seq_buf_printf(&s, "%s %llu\n", lru_list_name(i), (u64)memcg_page_state(memcg, NR_LRU_BASE + i) * PAGE_SIZE); @@ -1434,8 +1426,10 @@ static char *memory_stat_format(struct mem_cgroup *memcg) /* Accumulated memory events */ - seq_buf_printf(&s, "pgfault %lu\n", memcg_events(memcg, PGFAULT)); - seq_buf_printf(&s, "pgmajfault %lu\n", memcg_events(memcg, PGMAJFAULT)); + seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGFAULT), + memcg_events(memcg, PGFAULT)); + seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGMAJFAULT), + memcg_events(memcg, PGMAJFAULT)); seq_buf_printf(&s, "workingset_refault %lu\n", memcg_page_state(memcg, WORKINGSET_REFAULT)); @@ -1444,22 +1438,27 @@ static char *memory_stat_format(struct mem_cgroup *memcg) seq_buf_printf(&s, "workingset_nodereclaim %lu\n", memcg_page_state(memcg, WORKINGSET_NODERECLAIM)); - seq_buf_printf(&s, "pgrefill %lu\n", memcg_events(memcg, PGREFILL)); + seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGREFILL), + memcg_events(memcg, PGREFILL)); seq_buf_printf(&s, "pgscan %lu\n", memcg_events(memcg, PGSCAN_KSWAPD) + memcg_events(memcg, PGSCAN_DIRECT)); seq_buf_printf(&s, "pgsteal %lu\n", memcg_events(memcg, PGSTEAL_KSWAPD) + memcg_events(memcg, PGSTEAL_DIRECT)); - seq_buf_printf(&s, "pgactivate %lu\n", memcg_events(memcg, PGACTIVATE)); - seq_buf_printf(&s, "pgdeactivate %lu\n", memcg_events(memcg, PGDEACTIVATE)); - seq_buf_printf(&s, "pglazyfree %lu\n", memcg_events(memcg, PGLAZYFREE)); - seq_buf_printf(&s, "pglazyfreed %lu\n", memcg_events(memcg, PGLAZYFREED)); + seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGACTIVATE), + memcg_events(memcg, PGACTIVATE)); + seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGDEACTIVATE), + memcg_events(memcg, PGDEACTIVATE)); + seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGLAZYFREE), + memcg_events(memcg, PGLAZYFREE)); + seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGLAZYFREED), + memcg_events(memcg, PGLAZYFREED)); #ifdef CONFIG_TRANSPARENT_HUGEPAGE - seq_buf_printf(&s, "thp_fault_alloc %lu\n", + seq_buf_printf(&s, "%s %lu\n", vm_event_name(THP_FAULT_ALLOC), memcg_events(memcg, THP_FAULT_ALLOC)); - seq_buf_printf(&s, "thp_collapse_alloc %lu\n", + seq_buf_printf(&s, "%s %lu\n", vm_event_name(THP_COLLAPSE_ALLOC), memcg_events(memcg, THP_COLLAPSE_ALLOC)); #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ @@ -3742,13 +3741,6 @@ static const unsigned int memcg1_events[] = { PGMAJFAULT, }; -static const char *const memcg1_event_names[] = { - "pgpgin", - "pgpgout", - "pgfault", - "pgmajfault", -}; - static int memcg_stat_show(struct seq_file *m, void *v) { struct mem_cgroup *memcg = mem_cgroup_from_seq(m); @@ -3757,7 +3749,6 @@ static int memcg_stat_show(struct seq_file *m, void *v) unsigned int i; BUILD_BUG_ON(ARRAY_SIZE(memcg1_stat_names) != ARRAY_SIZE(memcg1_stats)); - BUILD_BUG_ON(ARRAY_SIZE(mem_cgroup_lru_names) != NR_LRU_LISTS); for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) { if (memcg1_stats[i] == MEMCG_SWAP && !do_memsw_account()) @@ -3768,11 +3759,11 @@ static int memcg_stat_show(struct seq_file *m, void *v) } for (i = 0; i < ARRAY_SIZE(memcg1_events); i++) - seq_printf(m, "%s %lu\n", memcg1_event_names[i], + seq_printf(m, "%s %lu\n", vm_event_name(memcg1_events[i]), memcg_events_local(memcg, memcg1_events[i])); for (i = 0; i < NR_LRU_LISTS; i++) - seq_printf(m, "%s %lu\n", mem_cgroup_lru_names[i], + seq_printf(m, "%s %lu\n", lru_list_name(i), memcg_page_state_local(memcg, NR_LRU_BASE + i) * PAGE_SIZE); @@ -3797,11 +3788,12 @@ static int memcg_stat_show(struct seq_file *m, void *v) } for (i = 0; i < ARRAY_SIZE(memcg1_events); i++) - seq_printf(m, "total_%s %llu\n", memcg1_event_names[i], + seq_printf(m, "total_%s %llu\n", + vm_event_name(memcg1_events[i]), (u64)memcg_events(memcg, memcg1_events[i])); for (i = 0; i < NR_LRU_LISTS; i++) - seq_printf(m, "total_%s %llu\n", mem_cgroup_lru_names[i], + seq_printf(m, "total_%s %llu\n", lru_list_name(i), (u64)memcg_page_state(memcg, NR_LRU_BASE + i) * PAGE_SIZE); diff --git a/mm/vmstat.c b/mm/vmstat.c index fa627329428b..78d53378db99 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1084,7 +1084,8 @@ int fragmentation_index(struct zone *zone, unsigned int order) } #endif -#if defined(CONFIG_PROC_FS) || defined(CONFIG_SYSFS) || defined(CONFIG_NUMA) +#if defined(CONFIG_PROC_FS) || defined(CONFIG_SYSFS) || \ + defined(CONFIG_NUMA) || defined(CONFIG_MEMCG) #ifdef CONFIG_ZONE_DMA #define TEXT_FOR_DMA(xx) xx "_dma", #else @@ -1172,7 +1173,7 @@ const char * const vmstat_text[] = { "nr_dirty_threshold", "nr_dirty_background_threshold", -#ifdef CONFIG_VM_EVENT_COUNTERS +#if defined(CONFIG_VM_EVENT_COUNTERS) || defined(CONFIG_MEMCG) /* enum vm_event_item counters */ "pgpgin", "pgpgout", @@ -1291,9 +1292,9 @@ const char * const vmstat_text[] = { "swap_ra", "swap_ra_hit", #endif -#endif /* CONFIG_VM_EVENTS_COUNTERS */ +#endif /* CONFIG_VM_EVENT_COUNTERS || CONFIG_MEMCG */ }; -#endif /* CONFIG_PROC_FS || CONFIG_SYSFS || CONFIG_NUMA */ +#endif /* CONFIG_PROC_FS || CONFIG_SYSFS || CONFIG_NUMA || CONFIG_MEMCG */ #if (defined(CONFIG_DEBUG_FS) && defined(CONFIG_COMPACTION)) || \ defined(CONFIG_PROC_FS) -- cgit v1.2.3 From 9573e8f70a82bcbac95b1ea222ac9d5e50266f9f Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Wed, 4 Dec 2019 16:50:08 -0800 Subject: include/linux/proc_fs.h: fix confusing macro arg name state_size and ops are in the wrong position. Link: http://lkml.kernel.org/r/20190910021747.11216-1-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Reviewed-by: Andrew Morton Acked-by: Aleksa Sarai Reviewed-by: Christian Brauner Cc: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/proc_fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index a705aa2d03f9..0640be56dcbd 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -58,8 +58,8 @@ extern int remove_proc_subtree(const char *, struct proc_dir_entry *); struct proc_dir_entry *proc_create_net_data(const char *name, umode_t mode, struct proc_dir_entry *parent, const struct seq_operations *ops, unsigned int state_size, void *data); -#define proc_create_net(name, mode, parent, state_size, ops) \ - proc_create_net_data(name, mode, parent, state_size, ops, NULL) +#define proc_create_net(name, mode, parent, ops, state_size) \ + proc_create_net_data(name, mode, parent, ops, state_size, NULL) struct proc_dir_entry *proc_create_net_single(const char *name, umode_t mode, struct proc_dir_entry *parent, int (*show)(struct seq_file *, void *), void *data); -- cgit v1.2.3 From d5ffb71b633cd5c4b8cce633c9d6448dced4eb74 Mon Sep 17 00:00:00 2001 From: Alessio Balsini Date: Wed, 4 Dec 2019 16:50:14 -0800 Subject: include/linux/sysctl.h: inline braces for ctl_table and ctl_table_header Fix coding style of "struct ctl_table" and "struct ctl_table_header" to have inline braces. Besides the wide use of this proposed cose style, this change helps to find at a glance the struct definition when navigating the code. Link: http://lkml.kernel.org/r/20190903154906.188651-1-balsini@android.com Signed-off-by: Alessio Balsini Acked-by: Luis Chamberlain Cc: Kees Cook Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sysctl.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 6df477329b76..02fa84493f23 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -120,8 +120,7 @@ static inline void *proc_sys_poll_event(struct ctl_table_poll *poll) struct ctl_table_poll name = __CTL_TABLE_POLL_INITIALIZER(name) /* A sysctl table is an array of struct ctl_table: */ -struct ctl_table -{ +struct ctl_table { const char *procname; /* Text ID for /proc/sys, or zero */ void *data; int maxlen; @@ -140,8 +139,7 @@ struct ctl_node { /* struct ctl_table_header is used to maintain dynamic lists of struct ctl_table trees. */ -struct ctl_table_header -{ +struct ctl_table_header { union { struct { struct ctl_table *ctl_table; -- cgit v1.2.3 From 8788994376d84d627450fd0d67deb6a66ddf07d7 Mon Sep 17 00:00:00 2001 From: Rikard Falkeborn Date: Wed, 4 Dec 2019 16:50:20 -0800 Subject: linux/build_bug.h: change type to int Having BUILD_BUG_ON_ZERO produce a value of type size_t leads to awkward casts in cases where the result needs to be signed, or of smaller type than size_t. To avoid this, cast the value to int instead and rely on implicit type conversions when a larger or unsigned type is needed. Link: http://lkml.kernel.org/r/20190811184938.1796-3-rikard.falkeborn@gmail.com Signed-off-by: Rikard Falkeborn Suggested-by: Masahiro Yamada Reviewed-by: Kees Cook Reviewed-by: Masahiro Yamada Cc: Joe Perches Cc: Johannes Berg Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/build_bug.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/build_bug.h b/include/linux/build_bug.h index 0fe5426f2bdc..e3a0be2c90ad 100644 --- a/include/linux/build_bug.h +++ b/include/linux/build_bug.h @@ -9,11 +9,11 @@ #else /* __CHECKER__ */ /* * Force a compilation error if condition is true, but also produce a - * result (of value 0 and type size_t), so the expression can be used + * result (of value 0 and type int), so the expression can be used * e.g. in a structure initializer (or where-ever else comma expressions * aren't permitted). */ -#define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:(-!!(e)); })) +#define BUILD_BUG_ON_ZERO(e) ((int)(sizeof(struct { int:(-!!(e)); }))) #endif /* __CHECKER__ */ /* Force a compilation error if a constant expression is not a power of 2 */ -- cgit v1.2.3 From 1a18374fc370da5a335b061fe94ebf677b07bd1d Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 4 Dec 2019 16:50:23 -0800 Subject: linux/scc.h: make uapi linux/scc.h self-contained Userspace cannot compile CC usr/include/linux/scc.h.s In file included from :32:0: usr/include/linux/scc.h:20:20: error: `SIOCDEVPRIVATE' undeclared here (not in a function) SIOCSCCRESERVED = SIOCDEVPRIVATE, ^~~~~~~~~~~~~~ Include to make it self-contained, and add it to the compile-test coverage. Link: http://lkml.kernel.org/r/20191108055809.26969-1-yamada.masahiro@socionext.com Signed-off-by: Masahiro Yamada Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/uapi/linux/scc.h | 1 + usr/include/Makefile | 1 - 2 files changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/scc.h b/include/uapi/linux/scc.h index c5bc7f747755..947edb17ce9d 100644 --- a/include/uapi/linux/scc.h +++ b/include/uapi/linux/scc.h @@ -4,6 +4,7 @@ #ifndef _UAPI_SCC_H #define _UAPI_SCC_H +#include /* selection of hardware types */ diff --git a/usr/include/Makefile b/usr/include/Makefile index 24543a30b9f0..5acd9bb6d714 100644 --- a/usr/include/Makefile +++ b/usr/include/Makefile @@ -40,7 +40,6 @@ header-test- += linux/omapfb.h header-test- += linux/patchkey.h header-test- += linux/phonet.h header-test- += linux/reiserfs_xattr.h -header-test- += linux/scc.h header-test- += linux/sctp.h header-test- += linux/signal.h header-test- += linux/sysctl.h -- cgit v1.2.3 From 885e68e8b7b1328aa1e28b27e13fbfb5f020d269 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 4 Dec 2019 16:50:32 -0800 Subject: kernel.h: update comment about simple_strto() functions There were discussions in the past about use cases for simple_strto() functions and, in some rare cases, they have a benefit over kstrto() ones. Update a comment to reduce confusion about special use cases. Link: http://lkml.kernel.org/r/20190801192904.41087-1-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Suggested-by: Miguel Ojeda Cc: Geert Uytterhoeven Cc: Mans Rullgard Cc: Petr Mladek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 09f759228e3f..3adcb39fa6f5 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -348,8 +348,7 @@ int __must_check kstrtoll(const char *s, unsigned int base, long long *res); * @res: Where to write the result of the conversion on success. * * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. - * Used as a replacement for the obsolete simple_strtoull. Return code must - * be checked. + * Used as a replacement for the simple_strtoull. Return code must be checked. */ static inline int __must_check kstrtoul(const char *s, unsigned int base, unsigned long *res) { @@ -377,8 +376,7 @@ static inline int __must_check kstrtoul(const char *s, unsigned int base, unsign * @res: Where to write the result of the conversion on success. * * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. - * Used as a replacement for the obsolete simple_strtoull. Return code must - * be checked. + * Used as a replacement for the simple_strtoull. Return code must be checked. */ static inline int __must_check kstrtol(const char *s, unsigned int base, long *res) { @@ -454,7 +452,18 @@ static inline int __must_check kstrtos32_from_user(const char __user *s, size_t return kstrtoint_from_user(s, count, base, res); } -/* Obsolete, do not use. Use kstrto instead */ +/* + * Use kstrto instead. + * + * NOTE: simple_strto does not check for the range overflow and, + * depending on the input, may give interesting results. + * + * Use these functions if and only if you cannot use kstrto, because + * the conversion ends on the first non-digit character, which may be far + * beyond the supported range. It might be useful to parse the strings like + * 10x50 or 12:21 without altering original string or temporary buffer in use. + * Keep in mind above caveat. + */ extern unsigned long simple_strtoul(const char *,char **,unsigned int); extern long simple_strtol(const char *,char **,unsigned int); -- cgit v1.2.3 From 260a2679e5cbfb3d8a4cf6cd1cb6f57e89c7e543 Mon Sep 17 00:00:00 2001 From: Xiaoming Ni Date: Wed, 4 Dec 2019 16:50:47 -0800 Subject: kernel/notifier.c: remove blocking_notifier_chain_cond_register() blocking_notifier_chain_cond_register() does not consider system_booting state, which is the only difference between this function and blocking_notifier_cain_register(). This can be a bug and is a piece of duplicate code. Delete blocking_notifier_chain_cond_register() Link: http://lkml.kernel.org/r/1568861888-34045-4-git-send-email-nixiaoming@huawei.com Signed-off-by: Xiaoming Ni Reviewed-by: Andrew Morton Cc: Alan Stern Cc: Alexey Dobriyan Cc: Andy Lutomirski Cc: Anna Schumaker Cc: Arjan van de Ven Cc: Chuck Lever Cc: David S. Miller Cc: Ingo Molnar Cc: J. Bruce Fields Cc: Jeff Layton Cc: Nadia Derbey Cc: "Paul E. McKenney" Cc: Sam Protsenko Cc: Thomas Gleixner Cc: Trond Myklebust Cc: Vasily Averin Cc: Viresh Kumar Cc: YueHaibing Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/notifier.h | 4 ---- kernel/notifier.c | 23 ----------------------- net/sunrpc/rpc_pipe.c | 2 +- 3 files changed, 1 insertion(+), 28 deletions(-) (limited to 'include') diff --git a/include/linux/notifier.h b/include/linux/notifier.h index 0096a05395e3..018947611483 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -150,10 +150,6 @@ extern int raw_notifier_chain_register(struct raw_notifier_head *nh, extern int srcu_notifier_chain_register(struct srcu_notifier_head *nh, struct notifier_block *nb); -extern int blocking_notifier_chain_cond_register( - struct blocking_notifier_head *nh, - struct notifier_block *nb); - extern int atomic_notifier_chain_unregister(struct atomic_notifier_head *nh, struct notifier_block *nb); extern int blocking_notifier_chain_unregister(struct blocking_notifier_head *nh, diff --git a/kernel/notifier.c b/kernel/notifier.c index e3d221f092fe..63d7501ac638 100644 --- a/kernel/notifier.c +++ b/kernel/notifier.c @@ -220,29 +220,6 @@ int blocking_notifier_chain_register(struct blocking_notifier_head *nh, } EXPORT_SYMBOL_GPL(blocking_notifier_chain_register); -/** - * blocking_notifier_chain_cond_register - Cond add notifier to a blocking notifier chain - * @nh: Pointer to head of the blocking notifier chain - * @n: New entry in notifier chain - * - * Adds a notifier to a blocking notifier chain, only if not already - * present in the chain. - * Must be called in process context. - * - * Currently always returns zero. - */ -int blocking_notifier_chain_cond_register(struct blocking_notifier_head *nh, - struct notifier_block *n) -{ - int ret; - - down_write(&nh->rwsem); - ret = notifier_chain_register(&nh->head, n); - up_write(&nh->rwsem); - return ret; -} -EXPORT_SYMBOL_GPL(blocking_notifier_chain_cond_register); - /** * blocking_notifier_chain_unregister - Remove notifier from a blocking notifier chain * @nh: Pointer to head of the blocking notifier chain diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index b71a39ded930..39e14d5edaf1 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -51,7 +51,7 @@ static BLOCKING_NOTIFIER_HEAD(rpc_pipefs_notifier_list); int rpc_pipefs_notifier_register(struct notifier_block *nb) { - return blocking_notifier_chain_cond_register(&rpc_pipefs_notifier_list, nb); + return blocking_notifier_chain_register(&rpc_pipefs_notifier_list, nb); } EXPORT_SYMBOL_GPL(rpc_pipefs_notifier_register); -- cgit v1.2.3 From 169c474fb22d8a5e909e172f177b957546d0519d Mon Sep 17 00:00:00 2001 From: William Breathitt Gray Date: Wed, 4 Dec 2019 16:50:57 -0800 Subject: bitops: introduce the for_each_set_clump8 macro Pach series "Introduce the for_each_set_clump8 macro", v18. While adding GPIO get_multiple/set_multiple callback support for various drivers, I noticed a pattern of looping manifesting that would be useful standardized as a macro. This patchset introduces the for_each_set_clump8 macro and utilizes it in several GPIO drivers. The for_each_set_clump macro8 facilitates a for-loop syntax that iterates over a memory region entire groups of set bits at a time. For example, suppose you would like to iterate over a 32-bit integer 8 bits at a time, skipping over 8-bit groups with no set bit, where XXXXXXXX represents the current 8-bit group: Example: 10111110 00000000 11111111 00110011 First loop: 10111110 00000000 11111111 XXXXXXXX Second loop: 10111110 00000000 XXXXXXXX 00110011 Third loop: XXXXXXXX 00000000 11111111 00110011 Each iteration of the loop returns the next 8-bit group that has at least one set bit. The for_each_set_clump8 macro has four parameters: * start: set to the bit offset of the current clump * clump: set to the current clump value * bits: bitmap to search within * size: bitmap size in number of bits In this version of the patchset, the for_each_set_clump macro has been reimplemented and simplified based on the suggestions provided by Rasmus Villemoes and Andy Shevchenko in the version 4 submission. In particular, the function of the for_each_set_clump macro has been restricted to handle only 8-bit clumps; the drivers that use the for_each_set_clump macro only handle 8-bit ports so a generic for_each_set_clump implementation is not necessary. Thus, a solution for large clumps (i.e. those larger than the width of a bitmap word) can be postponed until a driver appears that actually requires such a generic for_each_set_clump implementation. For what it's worth, a semi-generic for_each_set_clump (i.e. for clumps smaller than the width of a bitmap word) can be implemented by simply replacing the hardcoded '8' and '0xFF' instances with respective variables. I have not yet had a need for such an implementation, and since it falls short of a true generic for_each_set_clump function, I have decided to forgo such an implementation for now. In addition, the bitmap_get_value8 and bitmap_set_value8 functions are introduced to get and set 8-bit values respectively. Their use is based on the behavior suggested in the patchset version 4 review. This patch (of 14): This macro iterates for each 8-bit group of bits (clump) with set bits, within a bitmap memory region. For each iteration, "start" is set to the bit offset of the found clump, while the respective clump value is stored to the location pointed by "clump". Additionally, the bitmap_get_value8 and bitmap_set_value8 functions are introduced to respectively get and set an 8-bit value in a bitmap memory region. [gustavo@embeddedor.com: fix potential sign-extension overflow] Link: http://lkml.kernel.org/r/20191015184657.GA26541@embeddedor [akpm@linux-foundation.org: s/ULL/UL/, per Joe] [vilhelm.gray@gmail.com: add for_each_set_clump8 documentation] Link: http://lkml.kernel.org/r/20191016161825.301082-1-vilhelm.gray@gmail.com Link: http://lkml.kernel.org/r/893c3b4f03266c9496137cc98ac2b1bd27f92c73.1570641097.git.vilhelm.gray@gmail.com Signed-off-by: William Breathitt Gray Signed-off-by: Gustavo A. R. Silva Suggested-by: Andy Shevchenko Suggested-by: Rasmus Villemoes Suggested-by: Lukas Wunner Tested-by: Andy Shevchenko Cc: Arnd Bergmann Cc: Linus Walleij Cc: Bartosz Golaszewski Cc: Masahiro Yamada Cc: Geert Uytterhoeven Cc: Phil Reid Cc: Geert Uytterhoeven Cc: Mathias Duckeck Cc: Morten Hein Tiljeset Cc: Sean Nyekjaer Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/bitops/find.h | 17 +++++++++++++++++ include/linux/bitmap.h | 35 +++++++++++++++++++++++++++++++++++ include/linux/bitops.h | 12 ++++++++++++ lib/find_bit.c | 14 ++++++++++++++ 4 files changed, 78 insertions(+) (limited to 'include') diff --git a/include/asm-generic/bitops/find.h b/include/asm-generic/bitops/find.h index 8a1ee10014de..9fdf21302fdf 100644 --- a/include/asm-generic/bitops/find.h +++ b/include/asm-generic/bitops/find.h @@ -80,4 +80,21 @@ extern unsigned long find_first_zero_bit(const unsigned long *addr, #endif /* CONFIG_GENERIC_FIND_FIRST_BIT */ +/** + * find_next_clump8 - find next 8-bit clump with set bits in a memory region + * @clump: location to store copy of found clump + * @addr: address to base the search on + * @size: bitmap size in number of bits + * @offset: bit offset at which to start searching + * + * Returns the bit offset for the next set clump; the found clump value is + * copied to the location pointed by @clump. If no bits are set, returns @size. + */ +extern unsigned long find_next_clump8(unsigned long *clump, + const unsigned long *addr, + unsigned long size, unsigned long offset); + +#define find_first_clump8(clump, bits, size) \ + find_next_clump8((clump), (bits), (size), 0) + #endif /*_ASM_GENERIC_BITOPS_FIND_H_ */ diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 29fc933df3bf..9f046609e809 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -66,6 +66,8 @@ * bitmap_allocate_region(bitmap, pos, order) Allocate specified bit region * bitmap_from_arr32(dst, buf, nbits) Copy nbits from u32[] buf to dst * bitmap_to_arr32(buf, src, nbits) Copy nbits from buf to u32[] dst + * bitmap_get_value8(map, start) Get 8bit value from map at start + * bitmap_set_value8(map, value, start) Set 8bit value to map at start * * Note, bitmap_zero() and bitmap_fill() operate over the region of * unsigned longs, that is, bits behind bitmap till the unsigned long @@ -489,6 +491,39 @@ static inline void bitmap_from_u64(unsigned long *dst, u64 mask) dst[1] = mask >> 32; } +/** + * bitmap_get_value8 - get an 8-bit value within a memory region + * @map: address to the bitmap memory region + * @start: bit offset of the 8-bit value; must be a multiple of 8 + * + * Returns the 8-bit value located at the @start bit offset within the @src + * memory region. + */ +static inline unsigned long bitmap_get_value8(const unsigned long *map, + unsigned long start) +{ + const size_t index = BIT_WORD(start); + const unsigned long offset = start % BITS_PER_LONG; + + return (map[index] >> offset) & 0xFF; +} + +/** + * bitmap_set_value8 - set an 8-bit value within a memory region + * @map: address to the bitmap memory region + * @value: the 8-bit value; values wider than 8 bits may clobber bitmap + * @start: bit offset of the 8-bit value; must be a multiple of 8 + */ +static inline void bitmap_set_value8(unsigned long *map, unsigned long value, + unsigned long start) +{ + const size_t index = BIT_WORD(start); + const unsigned long offset = start % BITS_PER_LONG; + + map[index] &= ~(0xFFUL << offset); + map[index] |= value << offset; +} + #endif /* __ASSEMBLY__ */ #endif /* __LINUX_BITMAP_H */ diff --git a/include/linux/bitops.h b/include/linux/bitops.h index c94a9ff9f082..e479067c202c 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -47,6 +47,18 @@ extern unsigned long __sw_hweight64(__u64 w); (bit) < (size); \ (bit) = find_next_zero_bit((addr), (size), (bit) + 1)) +/** + * for_each_set_clump8 - iterate over bitmap for each 8-bit clump with set bits + * @start: bit offset to start search and to store the current iteration offset + * @clump: location to store copy of current 8-bit clump + * @bits: bitmap address to base the search on + * @size: bitmap size in number of bits + */ +#define for_each_set_clump8(start, clump, bits, size) \ + for ((start) = find_first_clump8(&(clump), (bits), (size)); \ + (start) < (size); \ + (start) = find_next_clump8(&(clump), (bits), (size), (start) + 8)) + static inline int get_bitmask_order(unsigned int count) { int order; diff --git a/lib/find_bit.c b/lib/find_bit.c index 5c51eb45178a..e35a76b291e6 100644 --- a/lib/find_bit.c +++ b/lib/find_bit.c @@ -214,3 +214,17 @@ EXPORT_SYMBOL(find_next_bit_le); #endif #endif /* __BIG_ENDIAN */ + +unsigned long find_next_clump8(unsigned long *clump, const unsigned long *addr, + unsigned long size, unsigned long offset) +{ + offset = find_next_bit(addr, size, offset); + if (offset == size) + return size; + + offset = round_down(offset, 8); + *clump = bitmap_get_value8(addr, offset); + + return offset; +} +EXPORT_SYMBOL(find_next_clump8); -- cgit v1.2.3 From 11d43e62f693c66c8c76c2ea2349e0f3c5764964 Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Wed, 4 Dec 2019 16:51:47 -0800 Subject: lib/rbtree: set successor's parent unconditionally Both in Case 2 and 3, we exchange n and s. This mean no matter whether child2 is NULL or not, successor's parent should be assigned to node's. This patch takes this step out to make it explicit and reduce the ambiguity. Besides, this step reduces some symbol size like rb_erase(). KERN_CONFIG upstream patched OPT_FOR_PERF 877 870 OPT_FOR_SIZE 635 621 Link: http://lkml.kernel.org/r/20191028021442.5450-1-richardw.yang@linux.intel.com Signed-off-by: Wei Yang Acked-by: Peter Zijlstra (Intel) Reviewed-by: Michel Lespinasse Reviewed-by: Davidlohr Bueso Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rbtree_augmented.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/rbtree_augmented.h b/include/linux/rbtree_augmented.h index fdd421b8d9ae..99c42e1a74b8 100644 --- a/include/linux/rbtree_augmented.h +++ b/include/linux/rbtree_augmented.h @@ -283,14 +283,13 @@ __rb_erase_augmented(struct rb_node *node, struct rb_root *root, __rb_change_child(node, successor, tmp, root); if (child2) { - successor->__rb_parent_color = pc; rb_set_parent_color(child2, parent, RB_BLACK); rebalance = NULL; } else { unsigned long pc2 = successor->__rb_parent_color; - successor->__rb_parent_color = pc; rebalance = __rb_is_black(pc2) ? parent : NULL; } + successor->__rb_parent_color = pc; tmp = successor; } -- cgit v1.2.3 From 8b7569a224a18953b9aee29c375e439b8a6eeb05 Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Wed, 4 Dec 2019 16:51:50 -0800 Subject: lib/rbtree: get successor's color directly After move parent assignment out, we can check the color directly. Link: http://lkml.kernel.org/r/20191028021442.5450-2-richardw.yang@linux.intel.com Signed-off-by: Wei Yang Acked-by: Peter Zijlstra (Intel) Reviewed-by: Michel Lespinasse Reviewed-by: Davidlohr Bueso Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rbtree_augmented.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/rbtree_augmented.h b/include/linux/rbtree_augmented.h index 99c42e1a74b8..724b0d036b57 100644 --- a/include/linux/rbtree_augmented.h +++ b/include/linux/rbtree_augmented.h @@ -286,8 +286,7 @@ __rb_erase_augmented(struct rb_node *node, struct rb_root *root, rb_set_parent_color(child2, parent, RB_BLACK); rebalance = NULL; } else { - unsigned long pc2 = successor->__rb_parent_color; - rebalance = __rb_is_black(pc2) ? parent : NULL; + rebalance = rb_is_black(successor) ? parent : NULL; } successor->__rb_parent_color = pc; tmp = successor; -- cgit v1.2.3 From 964975ac6677c97ae61ec9d6969dd5d03f18d1c3 Mon Sep 17 00:00:00 2001 From: Huang Shijie Date: Wed, 4 Dec 2019 16:52:03 -0800 Subject: lib/genalloc.c: rename addr_in_gen_pool to gen_pool_has_addr Follow the kernel conventions, rename addr_in_gen_pool to gen_pool_has_addr. [sjhuang@iluvatar.ai: fix Documentation/ too] Link: http://lkml.kernel.org/r/20181229015914.5573-1-sjhuang@iluvatar.ai Link: http://lkml.kernel.org/r/20181228083950.20398-1-sjhuang@iluvatar.ai Signed-off-by: Huang Shijie Reviewed-by: Andrew Morton Cc: Russell King Cc: Arnd Bergmann Cc: Greg Kroah-Hartman Cc: Christoph Hellwig Cc: Marek Szyprowski Cc: Robin Murphy Cc: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/core-api/genalloc.rst | 2 +- arch/arm/mm/dma-mapping.c | 2 +- drivers/misc/sram-exec.c | 2 +- include/linux/genalloc.h | 2 +- kernel/dma/remap.c | 2 +- lib/genalloc.c | 6 +++--- 6 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/Documentation/core-api/genalloc.rst b/Documentation/core-api/genalloc.rst index 098a46f55798..a5af2cbf58a5 100644 --- a/Documentation/core-api/genalloc.rst +++ b/Documentation/core-api/genalloc.rst @@ -129,7 +129,7 @@ writing of special-purpose memory allocators in the future. :functions: gen_pool_for_each_chunk .. kernel-doc:: lib/genalloc.c - :functions: addr_in_gen_pool + :functions: gen_pool_has_addr .. kernel-doc:: lib/genalloc.c :functions: gen_pool_avail diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 1df6eb42f22e..e822af0d9219 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -529,7 +529,7 @@ static void *__alloc_from_pool(size_t size, struct page **ret_page) static bool __in_atomic_pool(void *start, size_t size) { - return addr_in_gen_pool(atomic_pool, (unsigned long)start, size); + return gen_pool_has_addr(atomic_pool, (unsigned long)start, size); } static int __free_from_pool(void *start, size_t size) diff --git a/drivers/misc/sram-exec.c b/drivers/misc/sram-exec.c index 426ad912b441..d054e2842a5f 100644 --- a/drivers/misc/sram-exec.c +++ b/drivers/misc/sram-exec.c @@ -96,7 +96,7 @@ void *sram_exec_copy(struct gen_pool *pool, void *dst, void *src, if (!part) return NULL; - if (!addr_in_gen_pool(pool, (unsigned long)dst, size)) + if (!gen_pool_has_addr(pool, (unsigned long)dst, size)) return NULL; base = (unsigned long)part->base; diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h index 4bd583bd6934..5b14a0f38124 100644 --- a/include/linux/genalloc.h +++ b/include/linux/genalloc.h @@ -206,7 +206,7 @@ extern struct gen_pool *devm_gen_pool_create(struct device *dev, int min_alloc_order, int nid, const char *name); extern struct gen_pool *gen_pool_get(struct device *dev, const char *name); -bool addr_in_gen_pool(struct gen_pool *pool, unsigned long start, +extern bool gen_pool_has_addr(struct gen_pool *pool, unsigned long start, size_t size); #ifdef CONFIG_OF diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c index d47bd40fc0f5..d14cbc83986a 100644 --- a/kernel/dma/remap.c +++ b/kernel/dma/remap.c @@ -178,7 +178,7 @@ bool dma_in_atomic_pool(void *start, size_t size) if (unlikely(!atomic_pool)) return false; - return addr_in_gen_pool(atomic_pool, (unsigned long)start, size); + return gen_pool_has_addr(atomic_pool, (unsigned long)start, size); } void *dma_alloc_from_pool(size_t size, struct page **ret_page, gfp_t flags) diff --git a/lib/genalloc.c b/lib/genalloc.c index af9a57422186..7f1244b5294a 100644 --- a/lib/genalloc.c +++ b/lib/genalloc.c @@ -540,7 +540,7 @@ void gen_pool_for_each_chunk(struct gen_pool *pool, EXPORT_SYMBOL(gen_pool_for_each_chunk); /** - * addr_in_gen_pool - checks if an address falls within the range of a pool + * gen_pool_has_addr - checks if an address falls within the range of a pool * @pool: the generic memory pool * @start: start address * @size: size of the region @@ -548,7 +548,7 @@ EXPORT_SYMBOL(gen_pool_for_each_chunk); * Check if the range of addresses falls within the specified pool. Returns * true if the entire range is contained in the pool and false otherwise. */ -bool addr_in_gen_pool(struct gen_pool *pool, unsigned long start, +bool gen_pool_has_addr(struct gen_pool *pool, unsigned long start, size_t size) { bool found = false; @@ -567,7 +567,7 @@ bool addr_in_gen_pool(struct gen_pool *pool, unsigned long start, rcu_read_unlock(); return found; } -EXPORT_SYMBOL(addr_in_gen_pool); +EXPORT_SYMBOL(gen_pool_has_addr); /** * gen_pool_avail - get available free space of the pool -- cgit v1.2.3 From 6d13de1489b6bf539695f96d945de3860e6d5e17 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 4 Dec 2019 16:52:40 -0800 Subject: uaccess: disallow > INT_MAX copy sizes As we've done with VFS, string operations, etc, reject usercopy sizes larger than INT_MAX, which would be nice to have for catching bugs related to size calculation overflows[1]. This adds 10 bytes to x86_64 defconfig text and 1980 bytes to the data section: text data bss dec hex filename 19691167 5134320 1646664 26472151 193eed7 vmlinux.before 19691177 5136300 1646664 26474141 193f69d vmlinux.after [1] https://marc.info/?l=linux-s390&m=156631939010493&w=2 Link: http://lkml.kernel.org/r/201908251612.F9902D7A@keescook Signed-off-by: Kees Cook Suggested-by: Dan Carpenter Cc: Alexander Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/thread_info.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index 659a4400517b..e93e249a4e9b 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -147,6 +147,8 @@ check_copy_size(const void *addr, size_t bytes, bool is_source) __bad_copy_to(); return false; } + if (WARN_ON_ONCE(bytes > INT_MAX)) + return false; check_object_size(addr, bytes, is_source); return true; } -- cgit v1.2.3 From eec028c9386ed1a692aa01a85b55952202b41619 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Wed, 4 Dec 2019 16:52:43 -0800 Subject: kcov: remote coverage support Patch series " kcov: collect coverage from usb and vhost", v3. This patchset extends kcov to allow collecting coverage from backgound kernel threads. This extension requires custom annotations for each of the places where coverage collection is desired. This patchset implements this for hub events in the USB subsystem and for vhost workers. See the first patch description for details about the kcov extension. The other two patches apply this kcov extension to USB and vhost. Examples of other subsystems that might potentially benefit from this when custom annotations are added (the list is based on process_one_work() callers for bugs recently reported by syzbot): 1. fs: writeback wb_workfn() worker, 2. net: addrconf_dad_work()/addrconf_verify_work() workers, 3. net: neigh_periodic_work() worker, 4. net/p9: p9_write_work()/p9_read_work() workers, 5. block: blk_mq_run_work_fn() worker. These patches have been used to enable coverage-guided USB fuzzing with syzkaller for the last few years, see the details here: https://github.com/google/syzkaller/blob/master/docs/linux/external_fuzzing_usb.md This patchset has been pushed to the public Linux kernel Gerrit instance: https://linux-review.googlesource.com/c/linux/kernel/git/torvalds/linux/+/1524 This patch (of 3): Add background thread coverage collection ability to kcov. With KCOV_ENABLE coverage is collected only for syscalls that are issued from the current process. With KCOV_REMOTE_ENABLE it's possible to collect coverage for arbitrary parts of the kernel code, provided that those parts are annotated with kcov_remote_start()/kcov_remote_stop(). This allows to collect coverage from two types of kernel background threads: the global ones, that are spawned during kernel boot in a limited number of instances (e.g. one USB hub_event() worker thread is spawned per USB HCD); and the local ones, that are spawned when a user interacts with some kernel interface (e.g. vhost workers). To enable collecting coverage from a global background thread, a unique global handle must be assigned and passed to the corresponding kcov_remote_start() call. Then a userspace process can pass a list of such handles to the KCOV_REMOTE_ENABLE ioctl in the handles array field of the kcov_remote_arg struct. This will attach the used kcov device to the code sections, that are referenced by those handles. Since there might be many local background threads spawned from different userspace processes, we can't use a single global handle per annotation. Instead, the userspace process passes a non-zero handle through the common_handle field of the kcov_remote_arg struct. This common handle gets saved to the kcov_handle field in the current task_struct and needs to be passed to the newly spawned threads via custom annotations. Those threads should in turn be annotated with kcov_remote_start()/kcov_remote_stop(). Internally kcov stores handles as u64 integers. The top byte of a handle is used to denote the id of a subsystem that this handle belongs to, and the lower 4 bytes are used to denote the id of a thread instance within that subsystem. A reserved value 0 is used as a subsystem id for common handles as they don't belong to a particular subsystem. The bytes 4-7 are currently reserved and must be zero. In the future the number of bytes used for the subsystem or handle ids might be increased. When a particular userspace process collects coverage by via a common handle, kcov will collect coverage for each code section that is annotated to use the common handle obtained as kcov_handle from the current task_struct. However non common handles allow to collect coverage selectively from different subsystems. Link: http://lkml.kernel.org/r/e90e315426a384207edbec1d6aa89e43008e4caf.1572366574.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Cc: Dmitry Vyukov Cc: Greg Kroah-Hartman Cc: Alan Stern Cc: "Michael S. Tsirkin" Cc: Jason Wang Cc: Arnd Bergmann Cc: Steven Rostedt Cc: David Windsor Cc: Elena Reshetova Cc: Anders Roxell Cc: Alexander Potapenko Cc: Marco Elver Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/dev-tools/kcov.rst | 129 +++++++++ include/linux/kcov.h | 23 ++ include/linux/sched.h | 8 + include/uapi/linux/kcov.h | 28 ++ kernel/kcov.c | 547 ++++++++++++++++++++++++++++++++++++--- 5 files changed, 700 insertions(+), 35 deletions(-) (limited to 'include') diff --git a/Documentation/dev-tools/kcov.rst b/Documentation/dev-tools/kcov.rst index 42b612677799..36890b026e77 100644 --- a/Documentation/dev-tools/kcov.rst +++ b/Documentation/dev-tools/kcov.rst @@ -34,6 +34,7 @@ Profiling data will only become accessible once debugfs has been mounted:: Coverage collection ------------------- + The following program demonstrates coverage collection from within a test program using kcov: @@ -128,6 +129,7 @@ only need to enable coverage (disable happens automatically on thread end). Comparison operands collection ------------------------------ + Comparison operands collection is similar to coverage collection: .. code-block:: c @@ -202,3 +204,130 @@ Comparison operands collection is similar to coverage collection: Note that the kcov modes (coverage collection or comparison operands) are mutually exclusive. + +Remote coverage collection +-------------------------- + +With KCOV_ENABLE coverage is collected only for syscalls that are issued +from the current process. With KCOV_REMOTE_ENABLE it's possible to collect +coverage for arbitrary parts of the kernel code, provided that those parts +are annotated with kcov_remote_start()/kcov_remote_stop(). + +This allows to collect coverage from two types of kernel background +threads: the global ones, that are spawned during kernel boot in a limited +number of instances (e.g. one USB hub_event() worker thread is spawned per +USB HCD); and the local ones, that are spawned when a user interacts with +some kernel interface (e.g. vhost workers). + +To enable collecting coverage from a global background thread, a unique +global handle must be assigned and passed to the corresponding +kcov_remote_start() call. Then a userspace process can pass a list of such +handles to the KCOV_REMOTE_ENABLE ioctl in the handles array field of the +kcov_remote_arg struct. This will attach the used kcov device to the code +sections, that are referenced by those handles. + +Since there might be many local background threads spawned from different +userspace processes, we can't use a single global handle per annotation. +Instead, the userspace process passes a non-zero handle through the +common_handle field of the kcov_remote_arg struct. This common handle gets +saved to the kcov_handle field in the current task_struct and needs to be +passed to the newly spawned threads via custom annotations. Those threads +should in turn be annotated with kcov_remote_start()/kcov_remote_stop(). + +Internally kcov stores handles as u64 integers. The top byte of a handle +is used to denote the id of a subsystem that this handle belongs to, and +the lower 4 bytes are used to denote the id of a thread instance within +that subsystem. A reserved value 0 is used as a subsystem id for common +handles as they don't belong to a particular subsystem. The bytes 4-7 are +currently reserved and must be zero. In the future the number of bytes +used for the subsystem or handle ids might be increased. + +When a particular userspace proccess collects coverage by via a common +handle, kcov will collect coverage for each code section that is annotated +to use the common handle obtained as kcov_handle from the current +task_struct. However non common handles allow to collect coverage +selectively from different subsystems. + +.. code-block:: c + + struct kcov_remote_arg { + unsigned trace_mode; + unsigned area_size; + unsigned num_handles; + uint64_t common_handle; + uint64_t handles[0]; + }; + + #define KCOV_INIT_TRACE _IOR('c', 1, unsigned long) + #define KCOV_DISABLE _IO('c', 101) + #define KCOV_REMOTE_ENABLE _IOW('c', 102, struct kcov_remote_arg) + + #define COVER_SIZE (64 << 10) + + #define KCOV_TRACE_PC 0 + + #define KCOV_SUBSYSTEM_COMMON (0x00ull << 56) + #define KCOV_SUBSYSTEM_USB (0x01ull << 56) + + #define KCOV_SUBSYSTEM_MASK (0xffull << 56) + #define KCOV_INSTANCE_MASK (0xffffffffull) + + static inline __u64 kcov_remote_handle(__u64 subsys, __u64 inst) + { + if (subsys & ~KCOV_SUBSYSTEM_MASK || inst & ~KCOV_INSTANCE_MASK) + return 0; + return subsys | inst; + } + + #define KCOV_COMMON_ID 0x42 + #define KCOV_USB_BUS_NUM 1 + + int main(int argc, char **argv) + { + int fd; + unsigned long *cover, n, i; + struct kcov_remote_arg *arg; + + fd = open("/sys/kernel/debug/kcov", O_RDWR); + if (fd == -1) + perror("open"), exit(1); + if (ioctl(fd, KCOV_INIT_TRACE, COVER_SIZE)) + perror("ioctl"), exit(1); + cover = (unsigned long*)mmap(NULL, COVER_SIZE * sizeof(unsigned long), + PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + if ((void*)cover == MAP_FAILED) + perror("mmap"), exit(1); + + /* Enable coverage collection via common handle and from USB bus #1. */ + arg = calloc(1, sizeof(*arg) + sizeof(uint64_t)); + if (!arg) + perror("calloc"), exit(1); + arg->trace_mode = KCOV_TRACE_PC; + arg->area_size = COVER_SIZE; + arg->num_handles = 1; + arg->common_handle = kcov_remote_handle(KCOV_SUBSYSTEM_COMMON, + KCOV_COMMON_ID); + arg->handles[0] = kcov_remote_handle(KCOV_SUBSYSTEM_USB, + KCOV_USB_BUS_NUM); + if (ioctl(fd, KCOV_REMOTE_ENABLE, arg)) + perror("ioctl"), free(arg), exit(1); + free(arg); + + /* + * Here the user needs to trigger execution of a kernel code section + * that is either annotated with the common handle, or to trigger some + * activity on USB bus #1. + */ + sleep(2); + + n = __atomic_load_n(&cover[0], __ATOMIC_RELAXED); + for (i = 0; i < n; i++) + printf("0x%lx\n", cover[i + 1]); + if (ioctl(fd, KCOV_DISABLE, 0)) + perror("ioctl"), exit(1); + if (munmap(cover, COVER_SIZE * sizeof(unsigned long))) + perror("munmap"), exit(1); + if (close(fd)) + perror("close"), exit(1); + return 0; + } diff --git a/include/linux/kcov.h b/include/linux/kcov.h index b76a1807028d..a10e84707d82 100644 --- a/include/linux/kcov.h +++ b/include/linux/kcov.h @@ -37,12 +37,35 @@ do { \ (t)->kcov_mode &= ~KCOV_IN_CTXSW; \ } while (0) +/* See Documentation/dev-tools/kcov.rst for usage details. */ +void kcov_remote_start(u64 handle); +void kcov_remote_stop(void); +u64 kcov_common_handle(void); + +static inline void kcov_remote_start_common(u64 id) +{ + kcov_remote_start(kcov_remote_handle(KCOV_SUBSYSTEM_COMMON, id)); +} + +static inline void kcov_remote_start_usb(u64 id) +{ + kcov_remote_start(kcov_remote_handle(KCOV_SUBSYSTEM_USB, id)); +} + #else static inline void kcov_task_init(struct task_struct *t) {} static inline void kcov_task_exit(struct task_struct *t) {} static inline void kcov_prepare_switch(struct task_struct *t) {} static inline void kcov_finish_switch(struct task_struct *t) {} +static inline void kcov_remote_start(u64 handle) {} +static inline void kcov_remote_stop(void) {} +static inline u64 kcov_common_handle(void) +{ + return 0; +} +static inline void kcov_remote_start_common(u64 id) {} +static inline void kcov_remote_start_usb(u64 id) {} #endif /* CONFIG_KCOV */ #endif /* _LINUX_KCOV_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 0cd97d9dd021..467d26046416 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1210,6 +1210,8 @@ struct task_struct { #endif /* CONFIG_TRACING */ #ifdef CONFIG_KCOV + /* See kernel/kcov.c for more details. */ + /* Coverage collection mode enabled for this task (0 if disabled): */ unsigned int kcov_mode; @@ -1221,6 +1223,12 @@ struct task_struct { /* KCOV descriptor wired with this task or NULL: */ struct kcov *kcov; + + /* KCOV common handle for remote coverage collection: */ + u64 kcov_handle; + + /* KCOV sequence number: */ + int kcov_sequence; #endif #ifdef CONFIG_MEMCG diff --git a/include/uapi/linux/kcov.h b/include/uapi/linux/kcov.h index 9529867717a8..409d3ad1e6e2 100644 --- a/include/uapi/linux/kcov.h +++ b/include/uapi/linux/kcov.h @@ -4,9 +4,24 @@ #include +/* + * Argument for KCOV_REMOTE_ENABLE ioctl, see Documentation/dev-tools/kcov.rst + * and the comment before kcov_remote_start() for usage details. + */ +struct kcov_remote_arg { + unsigned int trace_mode; /* KCOV_TRACE_PC or KCOV_TRACE_CMP */ + unsigned int area_size; /* Length of coverage buffer in words */ + unsigned int num_handles; /* Size of handles array */ + __u64 common_handle; + __u64 handles[0]; +}; + +#define KCOV_REMOTE_MAX_HANDLES 0x100 + #define KCOV_INIT_TRACE _IOR('c', 1, unsigned long) #define KCOV_ENABLE _IO('c', 100) #define KCOV_DISABLE _IO('c', 101) +#define KCOV_REMOTE_ENABLE _IOW('c', 102, struct kcov_remote_arg) enum { /* @@ -32,4 +47,17 @@ enum { #define KCOV_CMP_SIZE(n) ((n) << 1) #define KCOV_CMP_MASK KCOV_CMP_SIZE(3) +#define KCOV_SUBSYSTEM_COMMON (0x00ull << 56) +#define KCOV_SUBSYSTEM_USB (0x01ull << 56) + +#define KCOV_SUBSYSTEM_MASK (0xffull << 56) +#define KCOV_INSTANCE_MASK (0xffffffffull) + +static inline __u64 kcov_remote_handle(__u64 subsys, __u64 inst) +{ + if (subsys & ~KCOV_SUBSYSTEM_MASK || inst & ~KCOV_INSTANCE_MASK) + return 0; + return subsys | inst; +} + #endif /* _LINUX_KCOV_IOCTLS_H */ diff --git a/kernel/kcov.c b/kernel/kcov.c index 2ee38727844a..f50354202dbe 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -21,8 +22,11 @@ #include #include #include +#include #include +#define kcov_debug(fmt, ...) pr_debug("%s: " fmt, __func__, ##__VA_ARGS__) + /* Number of 64-bit words written per one comparison: */ #define KCOV_WORDS_PER_CMP 4 @@ -44,19 +48,100 @@ struct kcov { * Reference counter. We keep one for: * - opened file descriptor * - task with enabled coverage (we can't unwire it from another task) + * - each code section for remote coverage collection */ refcount_t refcount; /* The lock protects mode, size, area and t. */ spinlock_t lock; enum kcov_mode mode; - /* Size of arena (in long's for KCOV_MODE_TRACE). */ - unsigned size; + /* Size of arena (in long's). */ + unsigned int size; /* Coverage buffer shared with user space. */ void *area; /* Task for which we collect coverage, or NULL. */ struct task_struct *t; + /* Collecting coverage from remote (background) threads. */ + bool remote; + /* Size of remote area (in long's). */ + unsigned int remote_size; + /* + * Sequence is incremented each time kcov is reenabled, used by + * kcov_remote_stop(), see the comment there. + */ + int sequence; }; +struct kcov_remote_area { + struct list_head list; + unsigned int size; +}; + +struct kcov_remote { + u64 handle; + struct kcov *kcov; + struct hlist_node hnode; +}; + +static DEFINE_SPINLOCK(kcov_remote_lock); +static DEFINE_HASHTABLE(kcov_remote_map, 4); +static struct list_head kcov_remote_areas = LIST_HEAD_INIT(kcov_remote_areas); + +/* Must be called with kcov_remote_lock locked. */ +static struct kcov_remote *kcov_remote_find(u64 handle) +{ + struct kcov_remote *remote; + + hash_for_each_possible(kcov_remote_map, remote, hnode, handle) { + if (remote->handle == handle) + return remote; + } + return NULL; +} + +static struct kcov_remote *kcov_remote_add(struct kcov *kcov, u64 handle) +{ + struct kcov_remote *remote; + + if (kcov_remote_find(handle)) + return ERR_PTR(-EEXIST); + remote = kmalloc(sizeof(*remote), GFP_ATOMIC); + if (!remote) + return ERR_PTR(-ENOMEM); + remote->handle = handle; + remote->kcov = kcov; + hash_add(kcov_remote_map, &remote->hnode, handle); + return remote; +} + +/* Must be called with kcov_remote_lock locked. */ +static struct kcov_remote_area *kcov_remote_area_get(unsigned int size) +{ + struct kcov_remote_area *area; + struct list_head *pos; + + kcov_debug("size = %u\n", size); + list_for_each(pos, &kcov_remote_areas) { + area = list_entry(pos, struct kcov_remote_area, list); + if (area->size == size) { + list_del(&area->list); + kcov_debug("rv = %px\n", area); + return area; + } + } + kcov_debug("rv = NULL\n"); + return NULL; +} + +/* Must be called with kcov_remote_lock locked. */ +static void kcov_remote_area_put(struct kcov_remote_area *area, + unsigned int size) +{ + kcov_debug("area = %px, size = %u\n", area, size); + INIT_LIST_HEAD(&area->list); + area->size = size; + list_add(&area->list, &kcov_remote_areas); +} + static notrace bool check_kcov_mode(enum kcov_mode needed_mode, struct task_struct *t) { unsigned int mode; @@ -73,7 +158,7 @@ static notrace bool check_kcov_mode(enum kcov_mode needed_mode, struct task_stru * in_interrupt() returns false (e.g. preempt_schedule_irq()). * READ_ONCE()/barrier() effectively provides load-acquire wrt * interrupts, there are paired barrier()/WRITE_ONCE() in - * kcov_ioctl_locked(). + * kcov_start(). */ barrier(); return mode == needed_mode; @@ -227,6 +312,78 @@ void notrace __sanitizer_cov_trace_switch(u64 val, u64 *cases) EXPORT_SYMBOL(__sanitizer_cov_trace_switch); #endif /* ifdef CONFIG_KCOV_ENABLE_COMPARISONS */ +static void kcov_start(struct task_struct *t, unsigned int size, + void *area, enum kcov_mode mode, int sequence) +{ + kcov_debug("t = %px, size = %u, area = %px\n", t, size, area); + /* Cache in task struct for performance. */ + t->kcov_size = size; + t->kcov_area = area; + /* See comment in check_kcov_mode(). */ + barrier(); + WRITE_ONCE(t->kcov_mode, mode); + t->kcov_sequence = sequence; +} + +static void kcov_stop(struct task_struct *t) +{ + WRITE_ONCE(t->kcov_mode, KCOV_MODE_DISABLED); + barrier(); + t->kcov_size = 0; + t->kcov_area = NULL; +} + +static void kcov_task_reset(struct task_struct *t) +{ + kcov_stop(t); + t->kcov = NULL; + t->kcov_sequence = 0; + t->kcov_handle = 0; +} + +void kcov_task_init(struct task_struct *t) +{ + kcov_task_reset(t); + t->kcov_handle = current->kcov_handle; +} + +static void kcov_reset(struct kcov *kcov) +{ + kcov->t = NULL; + kcov->mode = KCOV_MODE_INIT; + kcov->remote = false; + kcov->remote_size = 0; + kcov->sequence++; +} + +static void kcov_remote_reset(struct kcov *kcov) +{ + int bkt; + struct kcov_remote *remote; + struct hlist_node *tmp; + + spin_lock(&kcov_remote_lock); + hash_for_each_safe(kcov_remote_map, bkt, tmp, remote, hnode) { + if (remote->kcov != kcov) + continue; + kcov_debug("removing handle %llx\n", remote->handle); + hash_del(&remote->hnode); + kfree(remote); + } + /* Do reset before unlock to prevent races with kcov_remote_start(). */ + kcov_reset(kcov); + spin_unlock(&kcov_remote_lock); +} + +static void kcov_disable(struct task_struct *t, struct kcov *kcov) +{ + kcov_task_reset(t); + if (kcov->remote) + kcov_remote_reset(kcov); + else + kcov_reset(kcov); +} + static void kcov_get(struct kcov *kcov) { refcount_inc(&kcov->refcount); @@ -235,20 +392,12 @@ static void kcov_get(struct kcov *kcov) static void kcov_put(struct kcov *kcov) { if (refcount_dec_and_test(&kcov->refcount)) { + kcov_remote_reset(kcov); vfree(kcov->area); kfree(kcov); } } -void kcov_task_init(struct task_struct *t) -{ - WRITE_ONCE(t->kcov_mode, KCOV_MODE_DISABLED); - barrier(); - t->kcov_size = 0; - t->kcov_area = NULL; - t->kcov = NULL; -} - void kcov_task_exit(struct task_struct *t) { struct kcov *kcov; @@ -256,15 +405,36 @@ void kcov_task_exit(struct task_struct *t) kcov = t->kcov; if (kcov == NULL) return; + spin_lock(&kcov->lock); + kcov_debug("t = %px, kcov->t = %px\n", t, kcov->t); + /* + * For KCOV_ENABLE devices we want to make sure that t->kcov->t == t, + * which comes down to: + * WARN_ON(!kcov->remote && kcov->t != t); + * + * For KCOV_REMOTE_ENABLE devices, the exiting task is either: + * 2. A remote task between kcov_remote_start() and kcov_remote_stop(). + * In this case we should print a warning right away, since a task + * shouldn't be exiting when it's in a kcov coverage collection + * section. Here t points to the task that is collecting remote + * coverage, and t->kcov->t points to the thread that created the + * kcov device. Which means that to detect this case we need to + * check that t != t->kcov->t, and this gives us the following: + * WARN_ON(kcov->remote && kcov->t != t); + * + * 2. The task that created kcov exiting without calling KCOV_DISABLE, + * and then again we can make sure that t->kcov->t == t: + * WARN_ON(kcov->remote && kcov->t != t); + * + * By combining all three checks into one we get: + */ if (WARN_ON(kcov->t != t)) { spin_unlock(&kcov->lock); return; } /* Just to not leave dangling references behind. */ - kcov_task_init(t); - kcov->t = NULL; - kcov->mode = KCOV_MODE_INIT; + kcov_disable(t, kcov); spin_unlock(&kcov->lock); kcov_put(kcov); } @@ -313,6 +483,7 @@ static int kcov_open(struct inode *inode, struct file *filep) if (!kcov) return -ENOMEM; kcov->mode = KCOV_MODE_DISABLED; + kcov->sequence = 1; refcount_set(&kcov->refcount, 1); spin_lock_init(&kcov->lock); filep->private_data = kcov; @@ -325,6 +496,20 @@ static int kcov_close(struct inode *inode, struct file *filep) return 0; } +static int kcov_get_mode(unsigned long arg) +{ + if (arg == KCOV_TRACE_PC) + return KCOV_MODE_TRACE_PC; + else if (arg == KCOV_TRACE_CMP) +#ifdef CONFIG_KCOV_ENABLE_COMPARISONS + return KCOV_MODE_TRACE_CMP; +#else + return -ENOTSUPP; +#endif + else + return -EINVAL; +} + /* * Fault in a lazily-faulted vmalloc area before it can be used by * __santizer_cov_trace_pc(), to avoid recursion issues if any code on the @@ -340,14 +525,35 @@ static void kcov_fault_in_area(struct kcov *kcov) READ_ONCE(area[offset]); } +static inline bool kcov_check_handle(u64 handle, bool common_valid, + bool uncommon_valid, bool zero_valid) +{ + if (handle & ~(KCOV_SUBSYSTEM_MASK | KCOV_INSTANCE_MASK)) + return false; + switch (handle & KCOV_SUBSYSTEM_MASK) { + case KCOV_SUBSYSTEM_COMMON: + return (handle & KCOV_INSTANCE_MASK) ? + common_valid : zero_valid; + case KCOV_SUBSYSTEM_USB: + return uncommon_valid; + default: + return false; + } + return false; +} + static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd, unsigned long arg) { struct task_struct *t; unsigned long size, unused; + int mode, i; + struct kcov_remote_arg *remote_arg; + struct kcov_remote *remote; switch (cmd) { case KCOV_INIT_TRACE: + kcov_debug("KCOV_INIT_TRACE\n"); /* * Enable kcov in trace mode and setup buffer size. * Must happen before anything else. @@ -366,6 +572,7 @@ static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd, kcov->mode = KCOV_MODE_INIT; return 0; case KCOV_ENABLE: + kcov_debug("KCOV_ENABLE\n"); /* * Enable coverage for the current task. * At this point user must have been enabled trace mode, @@ -378,29 +585,20 @@ static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd, t = current; if (kcov->t != NULL || t->kcov != NULL) return -EBUSY; - if (arg == KCOV_TRACE_PC) - kcov->mode = KCOV_MODE_TRACE_PC; - else if (arg == KCOV_TRACE_CMP) -#ifdef CONFIG_KCOV_ENABLE_COMPARISONS - kcov->mode = KCOV_MODE_TRACE_CMP; -#else - return -ENOTSUPP; -#endif - else - return -EINVAL; + mode = kcov_get_mode(arg); + if (mode < 0) + return mode; kcov_fault_in_area(kcov); - /* Cache in task struct for performance. */ - t->kcov_size = kcov->size; - t->kcov_area = kcov->area; - /* See comment in check_kcov_mode(). */ - barrier(); - WRITE_ONCE(t->kcov_mode, kcov->mode); + kcov->mode = mode; + kcov_start(t, kcov->size, kcov->area, kcov->mode, + kcov->sequence); t->kcov = kcov; kcov->t = t; - /* This is put either in kcov_task_exit() or in KCOV_DISABLE. */ + /* Put either in kcov_task_exit() or in KCOV_DISABLE. */ kcov_get(kcov); return 0; case KCOV_DISABLE: + kcov_debug("KCOV_DISABLE\n"); /* Disable coverage for the current task. */ unused = arg; if (unused != 0 || current->kcov != kcov) @@ -408,11 +606,65 @@ static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd, t = current; if (WARN_ON(kcov->t != t)) return -EINVAL; - kcov_task_init(t); - kcov->t = NULL; - kcov->mode = KCOV_MODE_INIT; + kcov_disable(t, kcov); kcov_put(kcov); return 0; + case KCOV_REMOTE_ENABLE: + kcov_debug("KCOV_REMOTE_ENABLE\n"); + if (kcov->mode != KCOV_MODE_INIT || !kcov->area) + return -EINVAL; + t = current; + if (kcov->t != NULL || t->kcov != NULL) + return -EBUSY; + remote_arg = (struct kcov_remote_arg *)arg; + mode = kcov_get_mode(remote_arg->trace_mode); + if (mode < 0) + return mode; + if (remote_arg->area_size > LONG_MAX / sizeof(unsigned long)) + return -EINVAL; + kcov->mode = mode; + t->kcov = kcov; + kcov->t = t; + kcov->remote = true; + kcov->remote_size = remote_arg->area_size; + spin_lock(&kcov_remote_lock); + for (i = 0; i < remote_arg->num_handles; i++) { + kcov_debug("handle %llx\n", remote_arg->handles[i]); + if (!kcov_check_handle(remote_arg->handles[i], + false, true, false)) { + spin_unlock(&kcov_remote_lock); + kcov_disable(t, kcov); + return -EINVAL; + } + remote = kcov_remote_add(kcov, remote_arg->handles[i]); + if (IS_ERR(remote)) { + spin_unlock(&kcov_remote_lock); + kcov_disable(t, kcov); + return PTR_ERR(remote); + } + } + if (remote_arg->common_handle) { + kcov_debug("common handle %llx\n", + remote_arg->common_handle); + if (!kcov_check_handle(remote_arg->common_handle, + true, false, false)) { + spin_unlock(&kcov_remote_lock); + kcov_disable(t, kcov); + return -EINVAL; + } + remote = kcov_remote_add(kcov, + remote_arg->common_handle); + if (IS_ERR(remote)) { + spin_unlock(&kcov_remote_lock); + kcov_disable(t, kcov); + return PTR_ERR(remote); + } + t->kcov_handle = remote_arg->common_handle; + } + spin_unlock(&kcov_remote_lock); + /* Put either in kcov_task_exit() or in KCOV_DISABLE. */ + kcov_get(kcov); + return 0; default: return -ENOTTY; } @@ -422,11 +674,35 @@ static long kcov_ioctl(struct file *filep, unsigned int cmd, unsigned long arg) { struct kcov *kcov; int res; + struct kcov_remote_arg *remote_arg = NULL; + unsigned int remote_num_handles; + unsigned long remote_arg_size; + + if (cmd == KCOV_REMOTE_ENABLE) { + if (get_user(remote_num_handles, (unsigned __user *)(arg + + offsetof(struct kcov_remote_arg, num_handles)))) + return -EFAULT; + if (remote_num_handles > KCOV_REMOTE_MAX_HANDLES) + return -EINVAL; + remote_arg_size = struct_size(remote_arg, handles, + remote_num_handles); + remote_arg = memdup_user((void __user *)arg, remote_arg_size); + if (IS_ERR(remote_arg)) + return PTR_ERR(remote_arg); + if (remote_arg->num_handles != remote_num_handles) { + kfree(remote_arg); + return -EINVAL; + } + arg = (unsigned long)remote_arg; + } kcov = filep->private_data; spin_lock(&kcov->lock); res = kcov_ioctl_locked(kcov, cmd, arg); spin_unlock(&kcov->lock); + + kfree(remote_arg); + return res; } @@ -438,6 +714,207 @@ static const struct file_operations kcov_fops = { .release = kcov_close, }; +/* + * kcov_remote_start() and kcov_remote_stop() can be used to annotate a section + * of code in a kernel background thread to allow kcov to be used to collect + * coverage from that part of code. + * + * The handle argument of kcov_remote_start() identifies a code section that is + * used for coverage collection. A userspace process passes this handle to + * KCOV_REMOTE_ENABLE ioctl to make the used kcov device start collecting + * coverage for the code section identified by this handle. + * + * The usage of these annotations in the kernel code is different depending on + * the type of the kernel thread whose code is being annotated. + * + * For global kernel threads that are spawned in a limited number of instances + * (e.g. one USB hub_event() worker thread is spawned per USB HCD), each + * instance must be assigned a unique 4-byte instance id. The instance id is + * then combined with a 1-byte subsystem id to get a handle via + * kcov_remote_handle(subsystem_id, instance_id). + * + * For local kernel threads that are spawned from system calls handler when a + * user interacts with some kernel interface (e.g. vhost workers), a handle is + * passed from a userspace process as the common_handle field of the + * kcov_remote_arg struct (note, that the user must generate a handle by using + * kcov_remote_handle() with KCOV_SUBSYSTEM_COMMON as the subsystem id and an + * arbitrary 4-byte non-zero number as the instance id). This common handle + * then gets saved into the task_struct of the process that issued the + * KCOV_REMOTE_ENABLE ioctl. When this proccess issues system calls that spawn + * kernel threads, the common handle must be retrived via kcov_common_handle() + * and passed to the spawned threads via custom annotations. Those kernel + * threads must in turn be annotated with kcov_remote_start(common_handle) and + * kcov_remote_stop(). All of the threads that are spawned by the same process + * obtain the same handle, hence the name "common". + * + * See Documentation/dev-tools/kcov.rst for more details. + * + * Internally, this function looks up the kcov device associated with the + * provided handle, allocates an area for coverage collection, and saves the + * pointers to kcov and area into the current task_struct to allow coverage to + * be collected via __sanitizer_cov_trace_pc() + * In turns kcov_remote_stop() clears those pointers from task_struct to stop + * collecting coverage and copies all collected coverage into the kcov area. + */ +void kcov_remote_start(u64 handle) +{ + struct kcov_remote *remote; + void *area; + struct task_struct *t; + unsigned int size; + enum kcov_mode mode; + int sequence; + + if (WARN_ON(!kcov_check_handle(handle, true, true, true))) + return; + if (WARN_ON(!in_task())) + return; + t = current; + /* + * Check that kcov_remote_start is not called twice + * nor called by user tasks (with enabled kcov). + */ + if (WARN_ON(t->kcov)) + return; + + kcov_debug("handle = %llx\n", handle); + + spin_lock(&kcov_remote_lock); + remote = kcov_remote_find(handle); + if (!remote) { + kcov_debug("no remote found"); + spin_unlock(&kcov_remote_lock); + return; + } + /* Put in kcov_remote_stop(). */ + kcov_get(remote->kcov); + t->kcov = remote->kcov; + /* + * Read kcov fields before unlock to prevent races with + * KCOV_DISABLE / kcov_remote_reset(). + */ + size = remote->kcov->remote_size; + mode = remote->kcov->mode; + sequence = remote->kcov->sequence; + area = kcov_remote_area_get(size); + spin_unlock(&kcov_remote_lock); + + if (!area) { + area = vmalloc(size * sizeof(unsigned long)); + if (!area) { + t->kcov = NULL; + kcov_put(remote->kcov); + return; + } + } + /* Reset coverage size. */ + *(u64 *)area = 0; + + kcov_debug("area = %px, size = %u", area, size); + + kcov_start(t, size, area, mode, sequence); + +} +EXPORT_SYMBOL(kcov_remote_start); + +static void kcov_move_area(enum kcov_mode mode, void *dst_area, + unsigned int dst_area_size, void *src_area) +{ + u64 word_size = sizeof(unsigned long); + u64 count_size, entry_size_log; + u64 dst_len, src_len; + void *dst_entries, *src_entries; + u64 dst_occupied, dst_free, bytes_to_move, entries_moved; + + kcov_debug("%px %u <= %px %lu\n", + dst_area, dst_area_size, src_area, *(unsigned long *)src_area); + + switch (mode) { + case KCOV_MODE_TRACE_PC: + dst_len = READ_ONCE(*(unsigned long *)dst_area); + src_len = *(unsigned long *)src_area; + count_size = sizeof(unsigned long); + entry_size_log = __ilog2_u64(sizeof(unsigned long)); + break; + case KCOV_MODE_TRACE_CMP: + dst_len = READ_ONCE(*(u64 *)dst_area); + src_len = *(u64 *)src_area; + count_size = sizeof(u64); + BUILD_BUG_ON(!is_power_of_2(KCOV_WORDS_PER_CMP)); + entry_size_log = __ilog2_u64(sizeof(u64) * KCOV_WORDS_PER_CMP); + break; + default: + WARN_ON(1); + return; + } + + /* As arm can't divide u64 integers use log of entry size. */ + if (dst_len > ((dst_area_size * word_size - count_size) >> + entry_size_log)) + return; + dst_occupied = count_size + (dst_len << entry_size_log); + dst_free = dst_area_size * word_size - dst_occupied; + bytes_to_move = min(dst_free, src_len << entry_size_log); + dst_entries = dst_area + dst_occupied; + src_entries = src_area + count_size; + memcpy(dst_entries, src_entries, bytes_to_move); + entries_moved = bytes_to_move >> entry_size_log; + + switch (mode) { + case KCOV_MODE_TRACE_PC: + WRITE_ONCE(*(unsigned long *)dst_area, dst_len + entries_moved); + break; + case KCOV_MODE_TRACE_CMP: + WRITE_ONCE(*(u64 *)dst_area, dst_len + entries_moved); + break; + default: + break; + } +} + +/* See the comment before kcov_remote_start() for usage details. */ +void kcov_remote_stop(void) +{ + struct task_struct *t = current; + struct kcov *kcov = t->kcov; + void *area = t->kcov_area; + unsigned int size = t->kcov_size; + int sequence = t->kcov_sequence; + + if (!kcov) { + kcov_debug("no kcov found\n"); + return; + } + + kcov_stop(t); + t->kcov = NULL; + + spin_lock(&kcov->lock); + /* + * KCOV_DISABLE could have been called between kcov_remote_start() + * and kcov_remote_stop(), hence the check. + */ + kcov_debug("move if: %d == %d && %d\n", + sequence, kcov->sequence, (int)kcov->remote); + if (sequence == kcov->sequence && kcov->remote) + kcov_move_area(kcov->mode, kcov->area, kcov->size, area); + spin_unlock(&kcov->lock); + + spin_lock(&kcov_remote_lock); + kcov_remote_area_put(area, size); + spin_unlock(&kcov_remote_lock); + + kcov_put(kcov); +} +EXPORT_SYMBOL(kcov_remote_stop); + +/* See the comment before kcov_remote_start() for usage details. */ +u64 kcov_common_handle(void) +{ + return current->kcov_handle; +} +EXPORT_SYMBOL(kcov_common_handle); + static int __init kcov_init(void) { /* -- cgit v1.2.3 From 5b009673594d569674a9e0e60109f6a1723075b0 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 4 Dec 2019 16:52:57 -0800 Subject: arch: ipcbuf.h: make uapi asm/ipcbuf.h self-contained Userspace cannot compile due to some missing type definitions. For example, building it for x86 fails as follows: CC usr/include/asm/ipcbuf.h.s In file included from usr/include/asm/ipcbuf.h:1:0, from :32: usr/include/asm-generic/ipcbuf.h:21:2: error: unknown type name `__kernel_key_t' __kernel_key_t key; ^~~~~~~~~~~~~~ usr/include/asm-generic/ipcbuf.h:22:2: error: unknown type name `__kernel_uid32_t' __kernel_uid32_t uid; ^~~~~~~~~~~~~~~~ usr/include/asm-generic/ipcbuf.h:23:2: error: unknown type name `__kernel_gid32_t' __kernel_gid32_t gid; ^~~~~~~~~~~~~~~~ usr/include/asm-generic/ipcbuf.h:24:2: error: unknown type name `__kernel_uid32_t' __kernel_uid32_t cuid; ^~~~~~~~~~~~~~~~ usr/include/asm-generic/ipcbuf.h:25:2: error: unknown type name `__kernel_gid32_t' __kernel_gid32_t cgid; ^~~~~~~~~~~~~~~~ usr/include/asm-generic/ipcbuf.h:26:2: error: unknown type name `__kernel_mode_t' __kernel_mode_t mode; ^~~~~~~~~~~~~~~ usr/include/asm-generic/ipcbuf.h:28:35: error: `__kernel_mode_t' undeclared here (not in a function) unsigned char __pad1[4 - sizeof(__kernel_mode_t)]; ^~~~~~~~~~~~~~~ usr/include/asm-generic/ipcbuf.h:31:2: error: unknown type name `__kernel_ulong_t' __kernel_ulong_t __unused1; ^~~~~~~~~~~~~~~~ usr/include/asm-generic/ipcbuf.h:32:2: error: unknown type name `__kernel_ulong_t' __kernel_ulong_t __unused2; ^~~~~~~~~~~~~~~~ It is just a matter of missing include directive. Include to make it self-contained, and add it to the compile-test coverage. Link: http://lkml.kernel.org/r/20191030063855.9989-1-yamada.masahiro@socionext.com Signed-off-by: Masahiro Yamada Cc: Arnd Bergmann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/s390/include/uapi/asm/ipcbuf.h | 2 ++ arch/sparc/include/uapi/asm/ipcbuf.h | 2 ++ arch/xtensa/include/uapi/asm/ipcbuf.h | 2 ++ include/uapi/asm-generic/ipcbuf.h | 2 ++ usr/include/Makefile | 1 - 5 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/arch/s390/include/uapi/asm/ipcbuf.h b/arch/s390/include/uapi/asm/ipcbuf.h index 5b1c4f47c656..1030cd186899 100644 --- a/arch/s390/include/uapi/asm/ipcbuf.h +++ b/arch/s390/include/uapi/asm/ipcbuf.h @@ -2,6 +2,8 @@ #ifndef __S390_IPCBUF_H__ #define __S390_IPCBUF_H__ +#include + /* * The user_ipc_perm structure for S/390 architecture. * Note extra padding because this structure is passed back and forth diff --git a/arch/sparc/include/uapi/asm/ipcbuf.h b/arch/sparc/include/uapi/asm/ipcbuf.h index 9d0d125500e2..5b933a598a33 100644 --- a/arch/sparc/include/uapi/asm/ipcbuf.h +++ b/arch/sparc/include/uapi/asm/ipcbuf.h @@ -2,6 +2,8 @@ #ifndef __SPARC_IPCBUF_H #define __SPARC_IPCBUF_H +#include + /* * The ipc64_perm structure for sparc/sparc64 architecture. * Note extra padding because this structure is passed back and forth diff --git a/arch/xtensa/include/uapi/asm/ipcbuf.h b/arch/xtensa/include/uapi/asm/ipcbuf.h index a57afa0b606f..3bd0642f6660 100644 --- a/arch/xtensa/include/uapi/asm/ipcbuf.h +++ b/arch/xtensa/include/uapi/asm/ipcbuf.h @@ -12,6 +12,8 @@ #ifndef _XTENSA_IPCBUF_H #define _XTENSA_IPCBUF_H +#include + /* * Pad space is left for: * - 32-bit mode_t and seq diff --git a/include/uapi/asm-generic/ipcbuf.h b/include/uapi/asm-generic/ipcbuf.h index 7d80dbd336fb..41a01b494fc7 100644 --- a/include/uapi/asm-generic/ipcbuf.h +++ b/include/uapi/asm-generic/ipcbuf.h @@ -2,6 +2,8 @@ #ifndef __ASM_GENERIC_IPCBUF_H #define __ASM_GENERIC_IPCBUF_H +#include + /* * The generic ipc64_perm structure: * Note extra padding because this structure is passed back and forth diff --git a/usr/include/Makefile b/usr/include/Makefile index 5acd9bb6d714..00cc763ec488 100644 --- a/usr/include/Makefile +++ b/usr/include/Makefile @@ -16,7 +16,6 @@ override c_flags = $(UAPI_CFLAGS) -Wp,-MD,$(depfile) -I$(objtree)/usr/include # Please consider to fix the header first. # # Sorted alphabetically. -header-test- += asm/ipcbuf.h header-test- += asm/msgbuf.h header-test- += asm/sembuf.h header-test- += asm/shmbuf.h -- cgit v1.2.3 From 9ef0e004181956e158fb7ceb9b43810a193f80cd Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 4 Dec 2019 16:53:00 -0800 Subject: arch: msgbuf.h: make uapi asm/msgbuf.h self-contained Userspace cannot compile due to some missing type definitions. For example, building it for x86 fails as follows: CC usr/include/asm/msgbuf.h.s In file included from usr/include/asm/msgbuf.h:6:0, from :32: usr/include/asm-generic/msgbuf.h:25:20: error: field `msg_perm' has incomplete type struct ipc64_perm msg_perm; ^~~~~~~~ usr/include/asm-generic/msgbuf.h:27:2: error: unknown type name `__kernel_time_t' __kernel_time_t msg_stime; /* last msgsnd time */ ^~~~~~~~~~~~~~~ usr/include/asm-generic/msgbuf.h:28:2: error: unknown type name `__kernel_time_t' __kernel_time_t msg_rtime; /* last msgrcv time */ ^~~~~~~~~~~~~~~ usr/include/asm-generic/msgbuf.h:29:2: error: unknown type name `__kernel_time_t' __kernel_time_t msg_ctime; /* last change time */ ^~~~~~~~~~~~~~~ usr/include/asm-generic/msgbuf.h:41:2: error: unknown type name `__kernel_pid_t' __kernel_pid_t msg_lspid; /* pid of last msgsnd */ ^~~~~~~~~~~~~~ usr/include/asm-generic/msgbuf.h:42:2: error: unknown type name `__kernel_pid_t' __kernel_pid_t msg_lrpid; /* last receive pid */ ^~~~~~~~~~~~~~ It is just a matter of missing include directive. Include to make it self-contained, and add it to the compile-test coverage. Link: http://lkml.kernel.org/r/20191030063855.9989-2-yamada.masahiro@socionext.com Signed-off-by: Masahiro Yamada Cc: Arnd Bergmann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/mips/include/uapi/asm/msgbuf.h | 1 + arch/parisc/include/uapi/asm/msgbuf.h | 1 + arch/powerpc/include/uapi/asm/msgbuf.h | 2 ++ arch/sparc/include/uapi/asm/msgbuf.h | 2 ++ arch/x86/include/uapi/asm/msgbuf.h | 3 +++ arch/xtensa/include/uapi/asm/msgbuf.h | 2 ++ include/uapi/asm-generic/msgbuf.h | 2 ++ usr/include/Makefile | 1 - 8 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/arch/mips/include/uapi/asm/msgbuf.h b/arch/mips/include/uapi/asm/msgbuf.h index 9e0c2e230274..128af72f2dfe 100644 --- a/arch/mips/include/uapi/asm/msgbuf.h +++ b/arch/mips/include/uapi/asm/msgbuf.h @@ -2,6 +2,7 @@ #ifndef _ASM_MSGBUF_H #define _ASM_MSGBUF_H +#include /* * The msqid64_ds structure for the MIPS architecture. diff --git a/arch/parisc/include/uapi/asm/msgbuf.h b/arch/parisc/include/uapi/asm/msgbuf.h index 3b877335da38..3b4de5b668c3 100644 --- a/arch/parisc/include/uapi/asm/msgbuf.h +++ b/arch/parisc/include/uapi/asm/msgbuf.h @@ -3,6 +3,7 @@ #define _PARISC_MSGBUF_H #include +#include /* * The msqid64_ds structure for parisc architecture, copied from sparc. diff --git a/arch/powerpc/include/uapi/asm/msgbuf.h b/arch/powerpc/include/uapi/asm/msgbuf.h index 969bd83e4d3d..7919b2ba41b5 100644 --- a/arch/powerpc/include/uapi/asm/msgbuf.h +++ b/arch/powerpc/include/uapi/asm/msgbuf.h @@ -2,6 +2,8 @@ #ifndef _ASM_POWERPC_MSGBUF_H #define _ASM_POWERPC_MSGBUF_H +#include + /* * The msqid64_ds structure for the PowerPC architecture. * Note extra padding because this structure is passed back and forth diff --git a/arch/sparc/include/uapi/asm/msgbuf.h b/arch/sparc/include/uapi/asm/msgbuf.h index eeeb91933280..0954552da188 100644 --- a/arch/sparc/include/uapi/asm/msgbuf.h +++ b/arch/sparc/include/uapi/asm/msgbuf.h @@ -2,6 +2,8 @@ #ifndef _SPARC_MSGBUF_H #define _SPARC_MSGBUF_H +#include + /* * The msqid64_ds structure for sparc64 architecture. * Note extra padding because this structure is passed back and forth diff --git a/arch/x86/include/uapi/asm/msgbuf.h b/arch/x86/include/uapi/asm/msgbuf.h index 7c5bb43ed8af..b3d0664fadc9 100644 --- a/arch/x86/include/uapi/asm/msgbuf.h +++ b/arch/x86/include/uapi/asm/msgbuf.h @@ -5,6 +5,9 @@ #if !defined(__x86_64__) || !defined(__ILP32__) #include #else + +#include + /* * The msqid64_ds structure for x86 architecture with x32 ABI. * diff --git a/arch/xtensa/include/uapi/asm/msgbuf.h b/arch/xtensa/include/uapi/asm/msgbuf.h index d6915e9f071c..1ed2c85b693a 100644 --- a/arch/xtensa/include/uapi/asm/msgbuf.h +++ b/arch/xtensa/include/uapi/asm/msgbuf.h @@ -17,6 +17,8 @@ #ifndef _XTENSA_MSGBUF_H #define _XTENSA_MSGBUF_H +#include + struct msqid64_ds { struct ipc64_perm msg_perm; #ifdef __XTENSA_EB__ diff --git a/include/uapi/asm-generic/msgbuf.h b/include/uapi/asm-generic/msgbuf.h index af95aa89012e..6504d7b741ce 100644 --- a/include/uapi/asm-generic/msgbuf.h +++ b/include/uapi/asm-generic/msgbuf.h @@ -3,6 +3,8 @@ #define __ASM_GENERIC_MSGBUF_H #include +#include + /* * generic msqid64_ds structure. * diff --git a/usr/include/Makefile b/usr/include/Makefile index 00cc763ec488..6bd22f83b0df 100644 --- a/usr/include/Makefile +++ b/usr/include/Makefile @@ -16,7 +16,6 @@ override c_flags = $(UAPI_CFLAGS) -Wp,-MD,$(depfile) -I$(objtree)/usr/include # Please consider to fix the header first. # # Sorted alphabetically. -header-test- += asm/msgbuf.h header-test- += asm/sembuf.h header-test- += asm/shmbuf.h header-test- += asm/signal.h -- cgit v1.2.3 From 0fb9dc28679a627f84974165c8011e0630529ece Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 4 Dec 2019 16:53:03 -0800 Subject: arch: sembuf.h: make uapi asm/sembuf.h self-contained Userspace cannot compile due to some missing type definitions. For example, building it for x86 fails as follows: CC usr/include/asm/sembuf.h.s In file included from :32:0: usr/include/asm/sembuf.h:17:20: error: field `sem_perm' has incomplete type struct ipc64_perm sem_perm; /* permissions .. see ipc.h */ ^~~~~~~~ usr/include/asm/sembuf.h:24:2: error: unknown type name `__kernel_time_t' __kernel_time_t sem_otime; /* last semop time */ ^~~~~~~~~~~~~~~ usr/include/asm/sembuf.h:25:2: error: unknown type name `__kernel_ulong_t' __kernel_ulong_t __unused1; ^~~~~~~~~~~~~~~~ usr/include/asm/sembuf.h:26:2: error: unknown type name `__kernel_time_t' __kernel_time_t sem_ctime; /* last change time */ ^~~~~~~~~~~~~~~ usr/include/asm/sembuf.h:27:2: error: unknown type name `__kernel_ulong_t' __kernel_ulong_t __unused2; ^~~~~~~~~~~~~~~~ usr/include/asm/sembuf.h:29:2: error: unknown type name `__kernel_ulong_t' __kernel_ulong_t sem_nsems; /* no. of semaphores in array */ ^~~~~~~~~~~~~~~~ usr/include/asm/sembuf.h:30:2: error: unknown type name `__kernel_ulong_t' __kernel_ulong_t __unused3; ^~~~~~~~~~~~~~~~ usr/include/asm/sembuf.h:31:2: error: unknown type name `__kernel_ulong_t' __kernel_ulong_t __unused4; ^~~~~~~~~~~~~~~~ It is just a matter of missing include directive. Include to make it self-contained, and add it to the compile-test coverage. Link: http://lkml.kernel.org/r/20191030063855.9989-3-yamada.masahiro@socionext.com Signed-off-by: Masahiro Yamada Cc: Arnd Bergmann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/mips/include/uapi/asm/sembuf.h | 2 ++ arch/parisc/include/uapi/asm/sembuf.h | 1 + arch/powerpc/include/uapi/asm/sembuf.h | 2 ++ arch/sparc/include/uapi/asm/sembuf.h | 2 ++ arch/x86/include/uapi/asm/sembuf.h | 2 ++ arch/xtensa/include/uapi/asm/sembuf.h | 1 + include/uapi/asm-generic/sembuf.h | 1 + usr/include/Makefile | 1 - 8 files changed, 11 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/arch/mips/include/uapi/asm/sembuf.h b/arch/mips/include/uapi/asm/sembuf.h index 43e1b4a2f68a..ba7fe0c89e7d 100644 --- a/arch/mips/include/uapi/asm/sembuf.h +++ b/arch/mips/include/uapi/asm/sembuf.h @@ -2,6 +2,8 @@ #ifndef _ASM_SEMBUF_H #define _ASM_SEMBUF_H +#include + /* * The semid64_ds structure for the MIPS architecture. * Note extra padding because this structure is passed back and forth diff --git a/arch/parisc/include/uapi/asm/sembuf.h b/arch/parisc/include/uapi/asm/sembuf.h index 8241cf126018..e2ca4301c7fb 100644 --- a/arch/parisc/include/uapi/asm/sembuf.h +++ b/arch/parisc/include/uapi/asm/sembuf.h @@ -3,6 +3,7 @@ #define _PARISC_SEMBUF_H #include +#include /* * The semid64_ds structure for parisc architecture. diff --git a/arch/powerpc/include/uapi/asm/sembuf.h b/arch/powerpc/include/uapi/asm/sembuf.h index 008ae77c6746..85e96ccb5f0f 100644 --- a/arch/powerpc/include/uapi/asm/sembuf.h +++ b/arch/powerpc/include/uapi/asm/sembuf.h @@ -2,6 +2,8 @@ #ifndef _ASM_POWERPC_SEMBUF_H #define _ASM_POWERPC_SEMBUF_H +#include + /* * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License diff --git a/arch/sparc/include/uapi/asm/sembuf.h b/arch/sparc/include/uapi/asm/sembuf.h index cbcbaa4e7128..10621d066d79 100644 --- a/arch/sparc/include/uapi/asm/sembuf.h +++ b/arch/sparc/include/uapi/asm/sembuf.h @@ -2,6 +2,8 @@ #ifndef _SPARC_SEMBUF_H #define _SPARC_SEMBUF_H +#include + /* * The semid64_ds structure for sparc architecture. * Note extra padding because this structure is passed back and forth diff --git a/arch/x86/include/uapi/asm/sembuf.h b/arch/x86/include/uapi/asm/sembuf.h index 93030e97269a..71205b02a191 100644 --- a/arch/x86/include/uapi/asm/sembuf.h +++ b/arch/x86/include/uapi/asm/sembuf.h @@ -2,6 +2,8 @@ #ifndef _ASM_X86_SEMBUF_H #define _ASM_X86_SEMBUF_H +#include + /* * The semid64_ds structure for x86 architecture. * Note extra padding because this structure is passed back and forth diff --git a/arch/xtensa/include/uapi/asm/sembuf.h b/arch/xtensa/include/uapi/asm/sembuf.h index 09f348d643f1..3b9cdd406dfe 100644 --- a/arch/xtensa/include/uapi/asm/sembuf.h +++ b/arch/xtensa/include/uapi/asm/sembuf.h @@ -22,6 +22,7 @@ #define _XTENSA_SEMBUF_H #include +#include struct semid64_ds { struct ipc64_perm sem_perm; /* permissions .. see ipc.h */ diff --git a/include/uapi/asm-generic/sembuf.h b/include/uapi/asm-generic/sembuf.h index 137606018c6a..0e709bd3d730 100644 --- a/include/uapi/asm-generic/sembuf.h +++ b/include/uapi/asm-generic/sembuf.h @@ -3,6 +3,7 @@ #define __ASM_GENERIC_SEMBUF_H #include +#include /* * The semid64_ds structure for x86 architecture. diff --git a/usr/include/Makefile b/usr/include/Makefile index 6bd22f83b0df..4a753a48767b 100644 --- a/usr/include/Makefile +++ b/usr/include/Makefile @@ -16,7 +16,6 @@ override c_flags = $(UAPI_CFLAGS) -Wp,-MD,$(depfile) -I$(objtree)/usr/include # Please consider to fix the header first. # # Sorted alphabetically. -header-test- += asm/sembuf.h header-test- += asm/shmbuf.h header-test- += asm/signal.h header-test- += asm/ucontext.h -- cgit v1.2.3 From 30544ed5de431fe25d3793e4dd5a058d877c4d77 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 4 Dec 2019 16:53:26 -0800 Subject: lib/bitmap: introduce bitmap_replace() helper In some drivers we want to have a single operation over bitmap which is an equivalent to: *dst = (*old & ~(*mask)) | (*new & *mask) Introduce bitmap_replace() helper for this. Link: http://lkml.kernel.org/r/20191022172922.61232-8-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Acked-by: Linus Walleij Cc: Rasmus Villemoes Cc: Bartosz Golaszewski Cc: Geert Uytterhoeven Cc: Marek Vasut Cc: Thomas Petazzoni Cc: William Breathitt Gray Cc: Yury Norov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 16 ++++++++++++++++ lib/bitmap.c | 12 ++++++++++++ lib/test_bitmap.c | 38 ++++++++++++++++++++++++++++++++++++++ 3 files changed, 66 insertions(+) (limited to 'include') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 9f046609e809..ff335b22f23c 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -53,6 +53,7 @@ * bitmap_find_next_zero_area_off(buf, len, pos, n, mask) as above * bitmap_shift_right(dst, src, n, nbits) *dst = *src >> n * bitmap_shift_left(dst, src, n, nbits) *dst = *src << n + * bitmap_replace(dst, old, new, mask, nbits) *dst = (*old & ~(*mask)) | (*new & *mask) * bitmap_remap(dst, src, old, new, nbits) *dst = map(old, new)(src) * bitmap_bitremap(oldbit, old, new, nbits) newbit = map(old, new)(oldbit) * bitmap_onto(dst, orig, relmap, nbits) *dst = orig relative to relmap @@ -140,6 +141,9 @@ extern void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); extern int __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); +extern void __bitmap_replace(unsigned long *dst, + const unsigned long *old, const unsigned long *new, + const unsigned long *mask, unsigned int nbits); extern int __bitmap_intersects(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); extern int __bitmap_subset(const unsigned long *bitmap1, @@ -434,6 +438,18 @@ static inline void bitmap_shift_left(unsigned long *dst, const unsigned long *sr __bitmap_shift_left(dst, src, shift, nbits); } +static inline void bitmap_replace(unsigned long *dst, + const unsigned long *old, + const unsigned long *new, + const unsigned long *mask, + unsigned int nbits) +{ + if (small_const_nbits(nbits)) + *dst = (*old & ~(*mask)) | (*new & *mask); + else + __bitmap_replace(dst, old, new, mask, nbits); +} + static inline int bitmap_parse(const char *buf, unsigned int buflen, unsigned long *maskp, int nmaskbits) { diff --git a/lib/bitmap.c b/lib/bitmap.c index f9e834841e94..4250519d7d1c 100644 --- a/lib/bitmap.c +++ b/lib/bitmap.c @@ -222,6 +222,18 @@ int __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1, } EXPORT_SYMBOL(__bitmap_andnot); +void __bitmap_replace(unsigned long *dst, + const unsigned long *old, const unsigned long *new, + const unsigned long *mask, unsigned int nbits) +{ + unsigned int k; + unsigned int nr = BITS_TO_LONGS(nbits); + + for (k = 0; k < nr; k++) + dst[k] = (old[k] & ~mask[k]) | (new[k] & mask[k]); +} +EXPORT_SYMBOL(__bitmap_replace); + int __bitmap_intersects(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c index 4544847cf81e..e14a15ac250b 100644 --- a/lib/test_bitmap.c +++ b/lib/test_bitmap.c @@ -42,6 +42,19 @@ static const unsigned long exp2[] __initconst = { BITMAP_FROM_U64(0xffffffff77777777ULL), }; +/* Fibonacci sequence */ +static const unsigned long exp2_to_exp3_mask[] __initconst = { + BITMAP_FROM_U64(0x008000020020212eULL), +}; +/* exp3_0_1 = (exp2[0] & ~exp2_to_exp3_mask) | (exp2[1] & exp2_to_exp3_mask) */ +static const unsigned long exp3_0_1[] __initconst = { + BITMAP_FROM_U64(0x33b3333311313137ULL), +}; +/* exp3_1_0 = (exp2[1] & ~exp2_to_exp3_mask) | (exp2[0] & exp2_to_exp3_mask) */ +static const unsigned long exp3_1_0[] __initconst = { + BITMAP_FROM_U64(0xff7fffff77575751ULL), +}; + static bool __init __check_eq_uint(const char *srcfile, unsigned int line, const unsigned int exp_uint, unsigned int x) @@ -257,6 +270,30 @@ static void __init test_copy(void) expect_eq_pbl("0-108,128-1023", bmap2, 1024); } +#define EXP2_IN_BITS (sizeof(exp2) * 8) + +static void __init test_replace(void) +{ + unsigned int nbits = 64; + DECLARE_BITMAP(bmap, 1024); + + bitmap_zero(bmap, 1024); + bitmap_replace(bmap, &exp2[0], &exp2[1], exp2_to_exp3_mask, nbits); + expect_eq_bitmap(bmap, exp3_0_1, nbits); + + bitmap_zero(bmap, 1024); + bitmap_replace(bmap, &exp2[1], &exp2[0], exp2_to_exp3_mask, nbits); + expect_eq_bitmap(bmap, exp3_1_0, nbits); + + bitmap_fill(bmap, 1024); + bitmap_replace(bmap, &exp2[0], &exp2[1], exp2_to_exp3_mask, nbits); + expect_eq_bitmap(bmap, exp3_0_1, nbits); + + bitmap_fill(bmap, 1024); + bitmap_replace(bmap, &exp2[1], &exp2[0], exp2_to_exp3_mask, nbits); + expect_eq_bitmap(bmap, exp3_1_0, nbits); +} + #define PARSE_TIME 0x1 struct test_bitmap_parselist{ @@ -476,6 +513,7 @@ static void __init selftest(void) test_zero_clear(); test_fill_set(); test_copy(); + test_replace(); test_bitmap_arr32(); test_bitmap_parselist(); test_bitmap_parselist_user(); -- cgit v1.2.3 From f949286c668aed5aa24acdb5838be9cfd9513bd3 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Wed, 4 Dec 2019 16:54:32 -0800 Subject: mm: remove __ARCH_HAS_4LEVEL_HACK and include/asm-generic/4level-fixup.h There are no architectures that use include/asm-generic/4level-fixup.h therefore it can be removed along with __ARCH_HAS_4LEVEL_HACK define. Link: http://lkml.kernel.org/r/1572938135-31886-14-git-send-email-rppt@kernel.org Signed-off-by: Mike Rapoport Cc: Anatoly Pugachev Cc: Anton Ivanov Cc: Arnd Bergmann Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Ungerer Cc: Helge Deller Cc: "James E.J. Bottomley" Cc: Jeff Dike Cc: "Kirill A. Shutemov" Cc: Mark Salter Cc: Matt Turner Cc: Michal Simek Cc: Peter Rosin Cc: Richard Weinberger Cc: Rolf Eike Beer Cc: Russell King Cc: Russell King Cc: Sam Creasey Cc: Vincent Chen Cc: Vineet Gupta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/4level-fixup.h | 39 -------------------------------------- include/linux/mm.h | 10 +++++----- mm/memory.c | 8 -------- 3 files changed, 5 insertions(+), 52 deletions(-) delete mode 100644 include/asm-generic/4level-fixup.h (limited to 'include') diff --git a/include/asm-generic/4level-fixup.h b/include/asm-generic/4level-fixup.h deleted file mode 100644 index c86cf7cb4bba..000000000000 --- a/include/asm-generic/4level-fixup.h +++ /dev/null @@ -1,39 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _4LEVEL_FIXUP_H -#define _4LEVEL_FIXUP_H - -#define __ARCH_HAS_4LEVEL_HACK -#define __PAGETABLE_PUD_FOLDED 1 - -#define PUD_SHIFT PGDIR_SHIFT -#define PUD_SIZE PGDIR_SIZE -#define PUD_MASK PGDIR_MASK -#define PTRS_PER_PUD 1 - -#define pud_t pgd_t - -#define pmd_alloc(mm, pud, address) \ - ((unlikely(pgd_none(*(pud))) && __pmd_alloc(mm, pud, address))? \ - NULL: pmd_offset(pud, address)) - -#define pud_offset(pgd, start) (pgd) -#define pud_none(pud) 0 -#define pud_bad(pud) 0 -#define pud_present(pud) 1 -#define pud_ERROR(pud) do { } while (0) -#define pud_clear(pud) pgd_clear(pud) -#define pud_val(pud) pgd_val(pud) -#define pud_populate(mm, pud, pmd) pgd_populate(mm, pud, pmd) -#define pud_page(pud) pgd_page(pud) -#define pud_page_vaddr(pud) pgd_page_vaddr(pud) - -#undef pud_free_tlb -#define pud_free_tlb(tlb, x, addr) do { } while (0) -#define pud_free(mm, x) do { } while (0) - -#undef pud_addr_end -#define pud_addr_end(addr, end) (end) - -#include - -#endif diff --git a/include/linux/mm.h b/include/linux/mm.h index 8b0ef04b6d15..c97ea3b694e6 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1838,12 +1838,12 @@ static inline void mm_dec_nr_ptes(struct mm_struct *mm) {} int __pte_alloc(struct mm_struct *mm, pmd_t *pmd); int __pte_alloc_kernel(pmd_t *pmd); +#if defined(CONFIG_MMU) + /* - * The following ifdef needed to get the 4level-fixup.h header to work. - * Remove it when 4level-fixup.h has been removed. + * The following ifdef needed to get the 5level-fixup.h header to work. + * Remove it when 5level-fixup.h has been removed. */ -#if defined(CONFIG_MMU) && !defined(__ARCH_HAS_4LEVEL_HACK) - #ifndef __ARCH_HAS_5LEVEL_HACK static inline p4d_t *p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) @@ -1865,7 +1865,7 @@ static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long a return (unlikely(pud_none(*pud)) && __pmd_alloc(mm, pud, address))? NULL: pmd_offset(pud, address); } -#endif /* CONFIG_MMU && !__ARCH_HAS_4LEVEL_HACK */ +#endif /* CONFIG_MMU */ #if USE_SPLIT_PTE_PTLOCKS #if ALLOC_SPLIT_PTLOCKS diff --git a/mm/memory.c b/mm/memory.c index e455160e0f75..606da187d1de 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4197,19 +4197,11 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) smp_wmb(); /* See comment in __pte_alloc */ ptl = pud_lock(mm, pud); -#ifndef __ARCH_HAS_4LEVEL_HACK if (!pud_present(*pud)) { mm_inc_nr_pmds(mm); pud_populate(mm, pud, new); } else /* Another has populated it */ pmd_free(mm, new); -#else - if (!pgd_present(*pud)) { - mm_inc_nr_pmds(mm); - pgd_populate(mm, pud, new); - } else /* Another has populated it */ - pmd_free(mm, new); -#endif /* __ARCH_HAS_4LEVEL_HACK */ spin_unlock(ptl); return 0; } -- cgit v1.2.3 From 61ff72f4016804b99d28988a57e65c217f01769d Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Thu, 28 Nov 2019 08:47:51 +0800 Subject: printk: Drop pr_warning definition With all pr_warning are removed, saftely drop pr_warning definition. Link: http://lkml.kernel.org/r/20191128004752.35268-4-wangkefeng.wang@huawei.com To: joe@perches.com To: linux-kernel@vger.kernel.org Cc: gregkh@linuxfoundation.org Cc: tj@kernel.org Cc: arnd@arndb.de Cc: sergey.senozhatsky@gmail.com Cc: rostedt@goodmis.org Signed-off-by: Kefeng Wang Signed-off-by: Petr Mladek --- include/linux/printk.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/printk.h b/include/linux/printk.h index c09d67edda3a..1e6108b8d15f 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -302,9 +302,8 @@ extern int kptr_restrict; printk(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__) #define pr_err(fmt, ...) \ printk(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__) -#define pr_warning(fmt, ...) \ +#define pr_warn(fmt, ...) \ printk(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__) -#define pr_warn pr_warning #define pr_notice(fmt, ...) \ printk(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__) #define pr_info(fmt, ...) \ -- cgit v1.2.3 From dbad3408896c3c5722ec9cda065468b3df16c5bf Mon Sep 17 00:00:00 2001 From: John Hurley Date: Thu, 5 Dec 2019 17:03:34 +0000 Subject: net: core: rename indirect block ingress cb function With indirect blocks, a driver can register for callbacks from a device that is does not 'own', for example, a tunnel device. When registering to or unregistering from a new device, a callback is triggered to generate a bind/unbind event. This, in turn, allows the driver to receive any existing rules or to properly clean up installed rules. When first added, it was assumed that all indirect block registrations would be for ingress offloads. However, the NFP driver can, in some instances, support clsact qdisc binds for egress offload. Change the name of the indirect block callback command in flow_offload to remove the 'ingress' identifier from it. While this does not change functionality, a follow up patch will implement a more more generic callback than just those currently just supporting ingress offload. Fixes: 4d12ba42787b ("nfp: flower: allow offloading of matches on 'internal' ports") Signed-off-by: John Hurley Acked-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/net/flow_offload.h | 15 ++++++------- net/core/flow_offload.c | 45 +++++++++++++++++++-------------------- net/netfilter/nf_tables_offload.c | 6 +++--- net/sched/cls_api.c | 4 ++-- 4 files changed, 34 insertions(+), 36 deletions(-) (limited to 'include') diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 86c567f531f3..c6f7bd22db60 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -380,19 +380,18 @@ static inline void flow_block_init(struct flow_block *flow_block) typedef int flow_indr_block_bind_cb_t(struct net_device *dev, void *cb_priv, enum tc_setup_type type, void *type_data); -typedef void flow_indr_block_ing_cmd_t(struct net_device *dev, - flow_indr_block_bind_cb_t *cb, - void *cb_priv, - enum flow_block_command command); +typedef void flow_indr_block_cmd_t(struct net_device *dev, + flow_indr_block_bind_cb_t *cb, void *cb_priv, + enum flow_block_command command); -struct flow_indr_block_ing_entry { - flow_indr_block_ing_cmd_t *cb; +struct flow_indr_block_entry { + flow_indr_block_cmd_t *cb; struct list_head list; }; -void flow_indr_add_block_ing_cb(struct flow_indr_block_ing_entry *entry); +void flow_indr_add_block_cb(struct flow_indr_block_entry *entry); -void flow_indr_del_block_ing_cb(struct flow_indr_block_ing_entry *entry); +void flow_indr_del_block_cb(struct flow_indr_block_entry *entry); int __flow_indr_block_cb_register(struct net_device *dev, void *cb_priv, flow_indr_block_bind_cb_t *cb, diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c index cf52d9c422fa..45b6a59ac124 100644 --- a/net/core/flow_offload.c +++ b/net/core/flow_offload.c @@ -283,7 +283,7 @@ int flow_block_cb_setup_simple(struct flow_block_offload *f, } EXPORT_SYMBOL(flow_block_cb_setup_simple); -static LIST_HEAD(block_ing_cb_list); +static LIST_HEAD(block_cb_list); static struct rhashtable indr_setup_block_ht; @@ -391,20 +391,19 @@ static void flow_indr_block_cb_del(struct flow_indr_block_cb *indr_block_cb) kfree(indr_block_cb); } -static DEFINE_MUTEX(flow_indr_block_ing_cb_lock); +static DEFINE_MUTEX(flow_indr_block_cb_lock); -static void flow_block_ing_cmd(struct net_device *dev, - flow_indr_block_bind_cb_t *cb, - void *cb_priv, - enum flow_block_command command) +static void flow_block_cmd(struct net_device *dev, + flow_indr_block_bind_cb_t *cb, void *cb_priv, + enum flow_block_command command) { - struct flow_indr_block_ing_entry *entry; + struct flow_indr_block_entry *entry; - mutex_lock(&flow_indr_block_ing_cb_lock); - list_for_each_entry(entry, &block_ing_cb_list, list) { + mutex_lock(&flow_indr_block_cb_lock); + list_for_each_entry(entry, &block_cb_list, list) { entry->cb(dev, cb, cb_priv, command); } - mutex_unlock(&flow_indr_block_ing_cb_lock); + mutex_unlock(&flow_indr_block_cb_lock); } int __flow_indr_block_cb_register(struct net_device *dev, void *cb_priv, @@ -424,8 +423,8 @@ int __flow_indr_block_cb_register(struct net_device *dev, void *cb_priv, if (err) goto err_dev_put; - flow_block_ing_cmd(dev, indr_block_cb->cb, indr_block_cb->cb_priv, - FLOW_BLOCK_BIND); + flow_block_cmd(dev, indr_block_cb->cb, indr_block_cb->cb_priv, + FLOW_BLOCK_BIND); return 0; @@ -464,8 +463,8 @@ void __flow_indr_block_cb_unregister(struct net_device *dev, if (!indr_block_cb) return; - flow_block_ing_cmd(dev, indr_block_cb->cb, indr_block_cb->cb_priv, - FLOW_BLOCK_UNBIND); + flow_block_cmd(dev, indr_block_cb->cb, indr_block_cb->cb_priv, + FLOW_BLOCK_UNBIND); flow_indr_block_cb_del(indr_block_cb); flow_indr_block_dev_put(indr_dev); @@ -499,21 +498,21 @@ void flow_indr_block_call(struct net_device *dev, } EXPORT_SYMBOL_GPL(flow_indr_block_call); -void flow_indr_add_block_ing_cb(struct flow_indr_block_ing_entry *entry) +void flow_indr_add_block_cb(struct flow_indr_block_entry *entry) { - mutex_lock(&flow_indr_block_ing_cb_lock); - list_add_tail(&entry->list, &block_ing_cb_list); - mutex_unlock(&flow_indr_block_ing_cb_lock); + mutex_lock(&flow_indr_block_cb_lock); + list_add_tail(&entry->list, &block_cb_list); + mutex_unlock(&flow_indr_block_cb_lock); } -EXPORT_SYMBOL_GPL(flow_indr_add_block_ing_cb); +EXPORT_SYMBOL_GPL(flow_indr_add_block_cb); -void flow_indr_del_block_ing_cb(struct flow_indr_block_ing_entry *entry) +void flow_indr_del_block_cb(struct flow_indr_block_entry *entry) { - mutex_lock(&flow_indr_block_ing_cb_lock); + mutex_lock(&flow_indr_block_cb_lock); list_del(&entry->list); - mutex_unlock(&flow_indr_block_ing_cb_lock); + mutex_unlock(&flow_indr_block_cb_lock); } -EXPORT_SYMBOL_GPL(flow_indr_del_block_ing_cb); +EXPORT_SYMBOL_GPL(flow_indr_del_block_cb); static int __init init_flow_indr_rhashtable(void) { diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index 68f17a6921d8..431f3b803bfb 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -588,7 +588,7 @@ static int nft_offload_netdev_event(struct notifier_block *this, return NOTIFY_DONE; } -static struct flow_indr_block_ing_entry block_ing_entry = { +static struct flow_indr_block_entry block_ing_entry = { .cb = nft_indr_block_cb, .list = LIST_HEAD_INIT(block_ing_entry.list), }; @@ -605,13 +605,13 @@ int nft_offload_init(void) if (err < 0) return err; - flow_indr_add_block_ing_cb(&block_ing_entry); + flow_indr_add_block_cb(&block_ing_entry); return 0; } void nft_offload_exit(void) { - flow_indr_del_block_ing_cb(&block_ing_entry); + flow_indr_del_block_cb(&block_ing_entry); unregister_netdevice_notifier(&nft_offload_netdev_notifier); } diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 20d60b8fcb70..75b48083614e 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -3626,7 +3626,7 @@ static struct pernet_operations tcf_net_ops = { .size = sizeof(struct tcf_net), }; -static struct flow_indr_block_ing_entry block_ing_entry = { +static struct flow_indr_block_entry block_ing_entry = { .cb = tc_indr_block_get_and_ing_cmd, .list = LIST_HEAD_INIT(block_ing_entry.list), }; @@ -3643,7 +3643,7 @@ static int __init tc_filter_init(void) if (err) goto err_register_pernet_subsys; - flow_indr_add_block_ing_cb(&block_ing_entry); + flow_indr_add_block_cb(&block_ing_entry); rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_new_tfilter, NULL, RTNL_FLAG_DOIT_UNLOCKED); -- cgit v1.2.3 From 04d26e7b159a396372646a480f4caa166d1b6720 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Fri, 6 Dec 2019 12:38:36 +0100 Subject: tcp: fix rejected syncookies due to stale timestamps If no synflood happens for a long enough period of time, then the synflood timestamp isn't refreshed and jiffies can advance so much that time_after32() can't accurately compare them any more. Therefore, we can end up in a situation where time_after32(now, last_overflow + HZ) returns false, just because these two values are too far apart. In that case, the synflood timestamp isn't updated as it should be, which can trick tcp_synq_no_recent_overflow() into rejecting valid syncookies. For example, let's consider the following scenario on a system with HZ=1000: * The synflood timestamp is 0, either because that's the timestamp of the last synflood or, more commonly, because we're working with a freshly created socket. * We receive a new SYN, which triggers synflood protection. Let's say that this happens when jiffies == 2147484649 (that is, 'synflood timestamp' + HZ + 2^31 + 1). * Then tcp_synq_overflow() doesn't update the synflood timestamp, because time_after32(2147484649, 1000) returns false. With: - 2147484649: the value of jiffies, aka. 'now'. - 1000: the value of 'last_overflow' + HZ. * A bit later, we receive the ACK completing the 3WHS. But cookie_v[46]_check() rejects it because tcp_synq_no_recent_overflow() says that we're not under synflood. That's because time_after32(2147484649, 120000) returns false. With: - 2147484649: the value of jiffies, aka. 'now'. - 120000: the value of 'last_overflow' + TCP_SYNCOOKIE_VALID. Of course, in reality jiffies would have increased a bit, but this condition will last for the next 119 seconds, which is far enough to accommodate for jiffie's growth. Fix this by updating the overflow timestamp whenever jiffies isn't within the [last_overflow, last_overflow + HZ] range. That shouldn't have any performance impact since the update still happens at most once per second. Now we're guaranteed to have fresh timestamps while under synflood, so tcp_synq_no_recent_overflow() can safely use it with time_after32() in such situations. Stale timestamps can still make tcp_synq_no_recent_overflow() return the wrong verdict when not under synflood. This will be handled in the next patch. For 64 bits architectures, the problem was introduced with the conversion of ->tw_ts_recent_stamp to 32 bits integer by commit cca9bab1b72c ("tcp: use monotonic timestamps for PAWS"). The problem has always been there on 32 bits architectures. Fixes: cca9bab1b72c ("tcp: use monotonic timestamps for PAWS") Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Guillaume Nault Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/time.h | 13 +++++++++++++ include/net/tcp.h | 5 +++-- 2 files changed, 16 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/time.h b/include/linux/time.h index 0760a4f5a15c..8e10b9dbd8c2 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -97,4 +97,17 @@ static inline bool itimerspec64_valid(const struct itimerspec64 *its) */ #define time_after32(a, b) ((s32)((u32)(b) - (u32)(a)) < 0) #define time_before32(b, a) time_after32(a, b) + +/** + * time_between32 - check if a 32-bit timestamp is within a given time range + * @t: the time which may be within [l,h] + * @l: the lower bound of the range + * @h: the higher bound of the range + * + * time_before32(t, l, h) returns true if @l <= @t <= @h. All operands are + * treated as 32-bit integers. + * + * Equivalent to !(time_before32(@t, @l) || time_after32(@t, @h)). + */ +#define time_between32(t, l, h) ((u32)(h) - (u32)(l) >= (u32)(t) - (u32)(l)) #endif diff --git a/include/net/tcp.h b/include/net/tcp.h index 36f195fb576a..7d734ba391fc 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -494,14 +494,15 @@ static inline void tcp_synq_overflow(const struct sock *sk) reuse = rcu_dereference(sk->sk_reuseport_cb); if (likely(reuse)) { last_overflow = READ_ONCE(reuse->synq_overflow_ts); - if (time_after32(now, last_overflow + HZ)) + if (!time_between32(now, last_overflow, + last_overflow + HZ)) WRITE_ONCE(reuse->synq_overflow_ts, now); return; } } last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp; - if (time_after32(now, last_overflow + HZ)) + if (!time_between32(now, last_overflow, last_overflow + HZ)) tcp_sk(sk)->rx_opt.ts_recent_stamp = now; } -- cgit v1.2.3 From cb44a08f8647fd2e8db5cc9ac27cd8355fa392d8 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Fri, 6 Dec 2019 12:38:43 +0100 Subject: tcp: tighten acceptance of ACKs not matching a child socket When no synflood occurs, the synflood timestamp isn't updated. Therefore it can be so old that time_after32() can consider it to be in the future. That's a problem for tcp_synq_no_recent_overflow() as it may report that a recent overflow occurred while, in fact, it's just that jiffies has grown past 'last_overflow' + TCP_SYNCOOKIE_VALID + 2^31. Spurious detection of recent overflows lead to extra syncookie verification in cookie_v[46]_check(). At that point, the verification should fail and the packet dropped. But we should have dropped the packet earlier as we didn't even send a syncookie. Let's refine tcp_synq_no_recent_overflow() to report a recent overflow only if jiffies is within the [last_overflow, last_overflow + TCP_SYNCOOKIE_VALID] interval. This way, no spurious recent overflow is reported when jiffies wraps and 'last_overflow' becomes in the future from the point of view of time_after32(). However, if jiffies wraps and enters the [last_overflow, last_overflow + TCP_SYNCOOKIE_VALID] interval (with 'last_overflow' being a stale synflood timestamp), then tcp_synq_no_recent_overflow() still erroneously reports an overflow. In such cases, we have to rely on syncookie verification to drop the packet. We unfortunately have no way to differentiate between a fresh and a stale syncookie timestamp. In practice, using last_overflow as lower bound is problematic. If the synflood timestamp is concurrently updated between the time we read jiffies and the moment we store the timestamp in 'last_overflow', then 'now' becomes smaller than 'last_overflow' and tcp_synq_no_recent_overflow() returns true, potentially dropping a valid syncookie. Reading jiffies after loading the timestamp could fix the problem, but that'd require a memory barrier. Let's just accommodate for potential timestamp growth instead and extend the interval using 'last_overflow - HZ' as lower bound. Signed-off-by: Guillaume Nault Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 7d734ba391fc..43e04e14c41e 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -518,13 +518,23 @@ static inline bool tcp_synq_no_recent_overflow(const struct sock *sk) reuse = rcu_dereference(sk->sk_reuseport_cb); if (likely(reuse)) { last_overflow = READ_ONCE(reuse->synq_overflow_ts); - return time_after32(now, last_overflow + - TCP_SYNCOOKIE_VALID); + return !time_between32(now, last_overflow - HZ, + last_overflow + + TCP_SYNCOOKIE_VALID); } } last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp; - return time_after32(now, last_overflow + TCP_SYNCOOKIE_VALID); + + /* If last_overflow <= jiffies <= last_overflow + TCP_SYNCOOKIE_VALID, + * then we're under synflood. However, we have to use + * 'last_overflow - HZ' as lower bound. That's because a concurrent + * tcp_synq_overflow() could update .ts_recent_stamp after we read + * jiffies but before we store .ts_recent_stamp into last_overflow, + * which could lead to rejecting a valid syncookie. + */ + return !time_between32(now, last_overflow - HZ, + last_overflow + TCP_SYNCOOKIE_VALID); } static inline u32 tcp_cookie_time(void) -- cgit v1.2.3 From 721c8dafad26ccfa90ff659ee19755e3377b829d Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Fri, 6 Dec 2019 12:38:49 +0100 Subject: tcp: Protect accesses to .ts_recent_stamp with {READ,WRITE}_ONCE() Syncookies borrow the ->rx_opt.ts_recent_stamp field to store the timestamp of the last synflood. Protect them with READ_ONCE() and WRITE_ONCE() since reads and writes aren't serialised. Use of .rx_opt.ts_recent_stamp for storing the synflood timestamp was introduced by a0f82f64e269 ("syncookies: remove last_synq_overflow from struct tcp_sock"). But unprotected accesses were already there when timestamp was stored in .last_synq_overflow. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Guillaume Nault Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 43e04e14c41e..86b9a8766648 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -501,9 +501,9 @@ static inline void tcp_synq_overflow(const struct sock *sk) } } - last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp; + last_overflow = READ_ONCE(tcp_sk(sk)->rx_opt.ts_recent_stamp); if (!time_between32(now, last_overflow, last_overflow + HZ)) - tcp_sk(sk)->rx_opt.ts_recent_stamp = now; + WRITE_ONCE(tcp_sk(sk)->rx_opt.ts_recent_stamp, now); } /* syncookies: no recent synqueue overflow on this listening socket? */ @@ -524,7 +524,7 @@ static inline bool tcp_synq_no_recent_overflow(const struct sock *sk) } } - last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp; + last_overflow = READ_ONCE(tcp_sk(sk)->rx_opt.ts_recent_stamp); /* If last_overflow <= jiffies <= last_overflow + TCP_SYNCOOKIE_VALID, * then we're under synflood. However, we have to use -- cgit v1.2.3 From 501a90c945103e8627406763dac418f20f3837b2 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 5 Dec 2019 20:43:46 -0800 Subject: inet: protect against too small mtu values. syzbot was once again able to crash a host by setting a very small mtu on loopback device. Let's make inetdev_valid_mtu() available in include/net/ip.h, and use it in ip_setup_cork(), so that we protect both ip_append_page() and __ip_append_data() Also add a READ_ONCE() when the device mtu is read. Pairs this lockless read with one WRITE_ONCE() in __dev_set_mtu(), even if other code paths might write over this field. Add a big comment in include/linux/netdevice.h about dev->mtu needing READ_ONCE()/WRITE_ONCE() annotations. Hopefully we will add the missing ones in followup patches. [1] refcount_t: saturated; leaking memory. WARNING: CPU: 0 PID: 9464 at lib/refcount.c:22 refcount_warn_saturate+0x138/0x1f0 lib/refcount.c:22 Kernel panic - not syncing: panic_on_warn set ... CPU: 0 PID: 9464 Comm: syz-executor850 Not tainted 5.4.0-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x197/0x210 lib/dump_stack.c:118 panic+0x2e3/0x75c kernel/panic.c:221 __warn.cold+0x2f/0x3e kernel/panic.c:582 report_bug+0x289/0x300 lib/bug.c:195 fixup_bug arch/x86/kernel/traps.c:174 [inline] fixup_bug arch/x86/kernel/traps.c:169 [inline] do_error_trap+0x11b/0x200 arch/x86/kernel/traps.c:267 do_invalid_op+0x37/0x50 arch/x86/kernel/traps.c:286 invalid_op+0x23/0x30 arch/x86/entry/entry_64.S:1027 RIP: 0010:refcount_warn_saturate+0x138/0x1f0 lib/refcount.c:22 Code: 06 31 ff 89 de e8 c8 f5 e6 fd 84 db 0f 85 6f ff ff ff e8 7b f4 e6 fd 48 c7 c7 e0 71 4f 88 c6 05 56 a6 a4 06 01 e8 c7 a8 b7 fd <0f> 0b e9 50 ff ff ff e8 5c f4 e6 fd 0f b6 1d 3d a6 a4 06 31 ff 89 RSP: 0018:ffff88809689f550 EFLAGS: 00010286 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffffffff815e4336 RDI: ffffed1012d13e9c RBP: ffff88809689f560 R08: ffff88809c50a3c0 R09: fffffbfff15d31b1 R10: fffffbfff15d31b0 R11: ffffffff8ae98d87 R12: 0000000000000001 R13: 0000000000040100 R14: ffff888099041104 R15: ffff888218d96e40 refcount_add include/linux/refcount.h:193 [inline] skb_set_owner_w+0x2b6/0x410 net/core/sock.c:1999 sock_wmalloc+0xf1/0x120 net/core/sock.c:2096 ip_append_page+0x7ef/0x1190 net/ipv4/ip_output.c:1383 udp_sendpage+0x1c7/0x480 net/ipv4/udp.c:1276 inet_sendpage+0xdb/0x150 net/ipv4/af_inet.c:821 kernel_sendpage+0x92/0xf0 net/socket.c:3794 sock_sendpage+0x8b/0xc0 net/socket.c:936 pipe_to_sendpage+0x2da/0x3c0 fs/splice.c:458 splice_from_pipe_feed fs/splice.c:512 [inline] __splice_from_pipe+0x3ee/0x7c0 fs/splice.c:636 splice_from_pipe+0x108/0x170 fs/splice.c:671 generic_splice_sendpage+0x3c/0x50 fs/splice.c:842 do_splice_from fs/splice.c:861 [inline] direct_splice_actor+0x123/0x190 fs/splice.c:1035 splice_direct_to_actor+0x3b4/0xa30 fs/splice.c:990 do_splice_direct+0x1da/0x2a0 fs/splice.c:1078 do_sendfile+0x597/0xd00 fs/read_write.c:1464 __do_sys_sendfile64 fs/read_write.c:1525 [inline] __se_sys_sendfile64 fs/read_write.c:1511 [inline] __x64_sys_sendfile64+0x1dd/0x220 fs/read_write.c:1511 do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x441409 Code: e8 ac e8 ff ff 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 eb 08 fc ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007fffb64c4f78 EFLAGS: 00000246 ORIG_RAX: 0000000000000028 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 0000000000441409 RDX: 0000000000000000 RSI: 0000000000000006 RDI: 0000000000000005 RBP: 0000000000073b8a R08: 0000000000000010 R09: 0000000000000010 R10: 0000000000010001 R11: 0000000000000246 R12: 0000000000402180 R13: 0000000000402210 R14: 0000000000000000 R15: 0000000000000000 Kernel Offset: disabled Rebooting in 86400 seconds.. Fixes: 1470ddf7f8ce ("inet: Remove explicit write references to sk/inet in ip_append_data") Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: David S. Miller --- include/linux/netdevice.h | 5 +++++ include/net/ip.h | 5 +++++ net/core/dev.c | 3 ++- net/ipv4/devinet.c | 5 ----- net/ipv4/ip_output.c | 13 ++++++++----- 5 files changed, 20 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index cf0923579af4..9ef20389622d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1881,6 +1881,11 @@ struct net_device { unsigned char if_port; unsigned char dma; + /* Note : dev->mtu is often read without holding a lock. + * Writers usually hold RTNL. + * It is recommended to use READ_ONCE() to annotate the reads, + * and to use WRITE_ONCE() to annotate the writes. + */ unsigned int mtu; unsigned int min_mtu; unsigned int max_mtu; diff --git a/include/net/ip.h b/include/net/ip.h index 02d68e346f67..5b317c9f4470 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -760,4 +760,9 @@ int ip_misc_proc_init(void); int rtm_getroute_parse_ip_proto(struct nlattr *attr, u8 *ip_proto, u8 family, struct netlink_ext_ack *extack); +static inline bool inetdev_valid_mtu(unsigned int mtu) +{ + return likely(mtu >= IPV4_MIN_MTU); +} + #endif /* _IP_H */ diff --git a/net/core/dev.c b/net/core/dev.c index e7c027fb4808..2c277b8aba38 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -8188,7 +8188,8 @@ int __dev_set_mtu(struct net_device *dev, int new_mtu) if (ops->ndo_change_mtu) return ops->ndo_change_mtu(dev, new_mtu); - dev->mtu = new_mtu; + /* Pairs with all the lockless reads of dev->mtu in the stack */ + WRITE_ONCE(dev->mtu, new_mtu); return 0; } EXPORT_SYMBOL(__dev_set_mtu); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index a4b5bd4d2c89..e4632bd2026d 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1496,11 +1496,6 @@ skip: } } -static bool inetdev_valid_mtu(unsigned int mtu) -{ - return mtu >= IPV4_MIN_MTU; -} - static void inetdev_send_gratuitous_arp(struct net_device *dev, struct in_device *in_dev) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 9d83cb320dcb..14db1e0b8a6e 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1258,15 +1258,18 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, cork->addr = ipc->addr; } - /* - * We steal reference to this route, caller should not release it - */ - *rtp = NULL; cork->fragsize = ip_sk_use_pmtu(sk) ? - dst_mtu(&rt->dst) : rt->dst.dev->mtu; + dst_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu); + + if (!inetdev_valid_mtu(cork->fragsize)) + return -ENETUNREACH; cork->gso_size = ipc->gso_size; + cork->dst = &rt->dst; + /* We stole this route, caller should not release it. */ + *rtp = NULL; + cork->length = 0; cork->ttl = ipc->ttl; cork->tos = ipc->tos; -- cgit v1.2.3 From a28c8b9db8a1014aa572cd19a3bdb9ddebd3e555 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 7 Dec 2019 13:21:01 -0800 Subject: pipe: remove 'waiting_writers' merging logic This code is ancient, and goes back to when we only had a single page for the pipe buffers. The exact history is hidden in the mists of time (ie "before git", and in fact predates the BK repository too). At that long-ago point in time, it actually helped to try to merge big back-and-forth pipe reads and writes, and not limit pipe reads to the single pipe buffer in length just because that was all we had at a time. However, since then we've expanded the pipe buffers to multiple pages, and this logic really doesn't seem to make sense. And a lot of it is somewhat questionable (ie "hmm, the user asked for a non-blocking read, but we see that there's a writer pending, so let's wait anyway to get the extra data that the writer will have"). But more importantly, it makes the "go to sleep" logic much less obvious, and considering the wakeup issues we've had, I want to make for less of those kinds of things. Cc: David Howells Signed-off-by: Linus Torvalds --- fs/pipe.c | 19 +++++-------------- fs/splice.c | 21 ++++----------------- include/linux/pipe_fs_i.h | 2 -- 3 files changed, 9 insertions(+), 33 deletions(-) (limited to 'include') diff --git a/fs/pipe.c b/fs/pipe.c index bcc2192d33e2..58f236c65bea 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -348,18 +348,11 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to) if (!pipe->writers) break; - if (!pipe->waiting_writers) { - /* syscall merging: Usually we must not sleep - * if O_NONBLOCK is set, or if we got some data. - * But if a writer sleeps in kernel space, then - * we can wait for that data without violating POSIX. - */ - if (ret) - break; - if (filp->f_flags & O_NONBLOCK) { - ret = -EAGAIN; - break; - } + if (ret) + break; + if (filp->f_flags & O_NONBLOCK) { + ret = -EAGAIN; + break; } if (signal_pending(current)) { if (!ret) @@ -540,9 +533,7 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) wake_up_interruptible_sync_poll(&pipe->wait, EPOLLIN | EPOLLRDNORM); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); } - pipe->waiting_writers++; pipe_wait(pipe); - pipe->waiting_writers--; was_empty = pipe_empty(head, pipe->tail); } diff --git a/fs/splice.c b/fs/splice.c index fa1f3773c8cd..3009652a41c8 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -559,7 +559,7 @@ static int splice_from_pipe_next(struct pipe_inode_info *pipe, struct splice_des if (!pipe->writers) return 0; - if (!pipe->waiting_writers && sd->num_spliced) + if (sd->num_spliced) return 0; if (sd->flags & SPLICE_F_NONBLOCK) @@ -1098,9 +1098,7 @@ static int wait_for_space(struct pipe_inode_info *pipe, unsigned flags) return -EAGAIN; if (signal_pending(current)) return -ERESTARTSYS; - pipe->waiting_writers++; pipe_wait(pipe); - pipe->waiting_writers--; } } @@ -1482,11 +1480,9 @@ static int ipipe_prep(struct pipe_inode_info *pipe, unsigned int flags) } if (!pipe->writers) break; - if (!pipe->waiting_writers) { - if (flags & SPLICE_F_NONBLOCK) { - ret = -EAGAIN; - break; - } + if (flags & SPLICE_F_NONBLOCK) { + ret = -EAGAIN; + break; } pipe_wait(pipe); } @@ -1527,9 +1523,7 @@ static int opipe_prep(struct pipe_inode_info *pipe, unsigned int flags) ret = -ERESTARTSYS; break; } - pipe->waiting_writers++; pipe_wait(pipe); - pipe->waiting_writers--; } pipe_unlock(pipe); @@ -1751,13 +1745,6 @@ static int link_pipe(struct pipe_inode_info *ipipe, i_tail++; } while (len); - /* - * return EAGAIN if we have the potential of some data in the - * future, otherwise just return 0 - */ - if (!ret && ipipe->waiting_writers && (flags & SPLICE_F_NONBLOCK)) - ret = -EAGAIN; - pipe_unlock(ipipe); pipe_unlock(opipe); diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 44f2245debda..dbcfa6892384 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -38,7 +38,6 @@ struct pipe_buffer { * @readers: number of current readers of this pipe * @writers: number of current writers of this pipe * @files: number of struct file referring this pipe (protected by ->i_lock) - * @waiting_writers: number of writers blocked waiting for room * @r_counter: reader counter * @w_counter: writer counter * @fasync_readers: reader side fasync @@ -56,7 +55,6 @@ struct pipe_inode_info { unsigned int readers; unsigned int writers; unsigned int files; - unsigned int waiting_writers; unsigned int r_counter; unsigned int w_counter; struct page *tmp_page; -- cgit v1.2.3