From 3fd3ee50df0223b956f2f0dd419b5520e95d8d3b Mon Sep 17 00:00:00 2001 From: Daejun Park Date: Tue, 22 Dec 2020 10:57:47 +0900 Subject: [PATCH 01/11] scsi: ufs: Introduce HPB feature This is a patch for the HPB initialization and adds HPB function calls to UFS core driver. NAND flash-based storage devices, including UFS, have mechanisms to translate logical addresses of IO requests to the corresponding physical addresses of the flash storage. In UFS, Logical-address-to-Physical-address (L2P) map data, which is required to identify the physical address for the requested IOs, can only be partially stored in SRAM from NAND flash. Due to this partial loading, accessing the flash address area where the L2P information for that address is not loaded in the SRAM can result in serious performance degradation. The basic concept of HPB is to cache L2P mapping entries in host system memory so that both physical block address (PBA) and logical block address (LBA) can be delivered in HPB read command. The HPB READ command allows to read data faster than a read command in UFS since it provides the physical address (HPB Entry) of the desired logical block in addition to its logical address. The UFS device can access the physical block in NAND directly without searching and uploading L2P mapping table. This improves read performance because the NAND read operation for uploading L2P mapping table is removed. In HPB initialization, the host checks if the UFS device supports HPB feature and retrieves related device capabilities. Then, some HPB parameters are configured in the device. We measured the total start-up time of popular applications and observed the difference by enabling the HPB. Popular applications are 12 game apps and 24 non-game apps. Each target applications were launched in order. The cycle consists of running 36 applications in sequence. We repeated the cycle for observing performance improvement by L2P mapping cache hit in HPB. The Following is experiment environment: - kernel version: 4.4.0 - RAM: 8GB - UFS 2.1 (64GB) Result: +-------+----------+----------+-------+ | cycle | baseline | with HPB | diff | +-------+----------+----------+-------+ | 1 | 272.4 | 264.9 | -7.5 | | 2 | 250.4 | 248.2 | -2.2 | | 3 | 226.2 | 215.6 | -10.6 | | 4 | 230.6 | 214.8 | -15.8 | | 5 | 232.0 | 218.1 | -13.9 | | 6 | 231.9 | 212.6 | -19.3 | +-------+----------+----------+-------+ We also measured HPB performance using iozone. Here is my iozone script: iozone -r 4k -+n -i2 -ecI -t 16 -l 16 -u 16 -s $IO_RANGE/16 -F mnt/tmp_1 mnt/tmp_2 mnt/tmp_3 mnt/tmp_4 mnt/tmp_5 mnt/tmp_6 mnt/tmp_7 mnt/tmp_8 mnt/tmp_9 mnt/tmp_10 mnt/tmp_11 mnt/tmp_12 mnt/tmp_13 mnt/tmp_14 mnt/tmp_15 mnt/tmp_16 Result: +----------+--------+---------+ | IO range | HPB on | HPB off | +----------+--------+---------+ | 1 GB | 294.8 | 300.87 | | 4 GB | 293.51 | 179.35 | | 8 GB | 294.85 | 162.52 | | 16 GB | 293.45 | 156.26 | | 32 GB | 277.4 | 153.25 | +----------+--------+---------+ Reviewed-by: Bart Van Assche Reviewed-by: Can Guo Acked-by: Avri Altman Tested-by: Bean Huo Reported-by: kernel test robot Signed-off-by: Daejun Park --- Documentation/ABI/testing/sysfs-driver-ufs | 71 +++ drivers/scsi/ufs/Kconfig | 9 + drivers/scsi/ufs/Makefile | 1 + drivers/scsi/ufs/ufs-sysfs.c | 18 + drivers/scsi/ufs/ufs.h | 15 + drivers/scsi/ufs/ufshcd.c | 47 ++ drivers/scsi/ufs/ufshcd.h | 23 +- drivers/scsi/ufs/ufshpb.c | 559 +++++++++++++++++++++ drivers/scsi/ufs/ufshpb.h | 164 ++++++ 9 files changed, 906 insertions(+), 1 deletion(-) create mode 100644 drivers/scsi/ufs/ufshpb.c create mode 100644 drivers/scsi/ufs/ufshpb.h diff --git a/Documentation/ABI/testing/sysfs-driver-ufs b/Documentation/ABI/testing/sysfs-driver-ufs index 375a10f159b1..99220259da1b 100644 --- a/Documentation/ABI/testing/sysfs-driver-ufs +++ b/Documentation/ABI/testing/sysfs-driver-ufs @@ -1164,3 +1164,74 @@ Description: This node is used to set or display whether UFS WriteBooster is (if the platform supports UFSHCD_CAP_CLK_SCALING). For a platform that doesn't support UFSHCD_CAP_CLK_SCALING, we can disable/enable WriteBooster through this sysfs node. + +What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/hpb_version +Date: December 2020 +Contact: Daejun Park +Description: This entry shows the HPB specification version. + The full information about the descriptor could be found at UFS + HPB (Host Performance Booster) Extension specifications. + Example: version 1.2.3 = 0123h + The file is read only. + +What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/hpb_control +Date: December 2020 +Contact: Daejun Park +Description: This entry shows an indication of the HPB control mode. + 00h: Host control mode + 01h: Device control mode + The file is read only. + +What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/hpb_region_size +Date: December 2020 +Contact: Daejun Park +Description: This entry shows the bHPBRegionSize which can be calculated + as in the following (in bytes): + HPB Region size = 512B * 2^bHPBRegionSize + The file is read only. + +What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/hpb_number_lu +Date: December 2020 +Contact: Daejun Park +Description: This entry shows the maximum number of HPB LU supported by + the device. + 00h: HPB is not supported by the device. + 01h ~ 20h: Maximum number of HPB LU supported by the device + The file is read only. + +What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/hpb_subregion_size +Date: December 2020 +Contact: Daejun Park +Description: This entry shows the bHPBSubRegionSize, which can be + calculated as in the following (in bytes) and shall be a multiple of + logical block size: + HPB Sub-Region size = 512B x 2^bHPBSubRegionSize + bHPBSubRegionSize shall not exceed bHPBRegionSize. + The file is read only. + +What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/hpb_max_active_regions +Date: December 2020 +Contact: Daejun Park +Description: This entry shows the maximum number of active HPB regions that + is supported by the device. + The file is read only. + +What: /sys/class/scsi_device/*/device/unit_descriptor/hpb_lu_max_active_regions +Date: December 2020 +Contact: Daejun Park +Description: This entry shows the maximum number of HPB regions assigned to + the HPB logical unit. + The file is read only. + +What: /sys/class/scsi_device/*/device/unit_descriptor/hpb_pinned_region_start_offset +Date: December 2020 +Contact: Daejun Park +Description: This entry shows the start offset of HPB pinned region. + The file is read only. + +What: /sys/class/scsi_device/*/device/unit_descriptor/hpb_number_pinned_regions +Date: December 2020 +Contact: Daejun Park +Description: This entry shows the Number of HPB pinned regions assigned to + the HPB logical unit. + The file is read only. diff --git a/drivers/scsi/ufs/Kconfig b/drivers/scsi/ufs/Kconfig index d0d7ead99eaa..72c0bcb5caa9 100644 --- a/drivers/scsi/ufs/Kconfig +++ b/drivers/scsi/ufs/Kconfig @@ -181,3 +181,12 @@ config SCSI_UFS_CRYPTO Enabling this makes it possible for the kernel to use the crypto capabilities of the UFS device (if present) to perform crypto operations on data being transferred to/from the device. + +config SCSI_UFS_HPB + bool "Support UFS Host Performance Booster" + depends on SCSI_UFSHCD + help + The UFS HPB feature improves random read performance. It caches + L2P (logical to physical) map of UFS to host DRAM. The driver uses HPB + read command by piggybacking physical page number for bypassing FTL (flash + translation layer)'s L2P address translation. diff --git a/drivers/scsi/ufs/Makefile b/drivers/scsi/ufs/Makefile index 06f3a3fe4a44..7dd11cd3f6a6 100644 --- a/drivers/scsi/ufs/Makefile +++ b/drivers/scsi/ufs/Makefile @@ -8,6 +8,7 @@ ufshcd-core-y += ufshcd.o ufs-sysfs.o ufshcd-core-$(CONFIG_DEBUG_FS) += ufs-debugfs.o ufshcd-core-$(CONFIG_SCSI_UFS_BSG) += ufs_bsg.o ufshcd-core-$(CONFIG_SCSI_UFS_CRYPTO) += ufshcd-crypto.o +ufshcd-core-$(CONFIG_SCSI_UFS_HPB) += ufshpb.o obj-$(CONFIG_SCSI_UFS_DWC_TC_PCI) += tc-dwc-g210-pci.o ufshcd-dwc.o tc-dwc-g210.o obj-$(CONFIG_SCSI_UFS_DWC_TC_PLATFORM) += tc-dwc-g210-pltfrm.o ufshcd-dwc.o tc-dwc-g210.o diff --git a/drivers/scsi/ufs/ufs-sysfs.c b/drivers/scsi/ufs/ufs-sysfs.c index acc54f530f2d..2546e7a1ac4f 100644 --- a/drivers/scsi/ufs/ufs-sysfs.c +++ b/drivers/scsi/ufs/ufs-sysfs.c @@ -368,6 +368,8 @@ UFS_DEVICE_DESC_PARAM(device_version, _DEV_VER, 2); UFS_DEVICE_DESC_PARAM(number_of_secure_wpa, _NUM_SEC_WPA, 1); UFS_DEVICE_DESC_PARAM(psa_max_data_size, _PSA_MAX_DATA, 4); UFS_DEVICE_DESC_PARAM(psa_state_timeout, _PSA_TMT, 1); +UFS_DEVICE_DESC_PARAM(hpb_version, _HPB_VER, 2); +UFS_DEVICE_DESC_PARAM(hpb_control, _HPB_CONTROL, 1); UFS_DEVICE_DESC_PARAM(ext_feature_sup, _EXT_UFS_FEATURE_SUP, 4); UFS_DEVICE_DESC_PARAM(wb_presv_us_en, _WB_PRESRV_USRSPC_EN, 1); UFS_DEVICE_DESC_PARAM(wb_type, _WB_TYPE, 1); @@ -400,6 +402,8 @@ static struct attribute *ufs_sysfs_device_descriptor[] = { &dev_attr_number_of_secure_wpa.attr, &dev_attr_psa_max_data_size.attr, &dev_attr_psa_state_timeout.attr, + &dev_attr_hpb_version.attr, + &dev_attr_hpb_control.attr, &dev_attr_ext_feature_sup.attr, &dev_attr_wb_presv_us_en.attr, &dev_attr_wb_type.attr, @@ -473,6 +477,10 @@ UFS_GEOMETRY_DESC_PARAM(enh4_memory_max_alloc_units, _ENM4_MAX_NUM_UNITS, 4); UFS_GEOMETRY_DESC_PARAM(enh4_memory_capacity_adjustment_factor, _ENM4_CAP_ADJ_FCTR, 2); +UFS_GEOMETRY_DESC_PARAM(hpb_region_size, _HPB_REGION_SIZE, 1); +UFS_GEOMETRY_DESC_PARAM(hpb_number_lu, _HPB_NUMBER_LU, 1); +UFS_GEOMETRY_DESC_PARAM(hpb_subregion_size, _HPB_SUBREGION_SIZE, 1); +UFS_GEOMETRY_DESC_PARAM(hpb_max_active_regions, _HPB_MAX_ACTIVE_REGS, 2); UFS_GEOMETRY_DESC_PARAM(wb_max_alloc_units, _WB_MAX_ALLOC_UNITS, 4); UFS_GEOMETRY_DESC_PARAM(wb_max_wb_luns, _WB_MAX_WB_LUNS, 1); UFS_GEOMETRY_DESC_PARAM(wb_buff_cap_adj, _WB_BUFF_CAP_ADJ, 1); @@ -510,6 +518,10 @@ static struct attribute *ufs_sysfs_geometry_descriptor[] = { &dev_attr_enh3_memory_capacity_adjustment_factor.attr, &dev_attr_enh4_memory_max_alloc_units.attr, &dev_attr_enh4_memory_capacity_adjustment_factor.attr, + &dev_attr_hpb_region_size.attr, + &dev_attr_hpb_number_lu.attr, + &dev_attr_hpb_subregion_size.attr, + &dev_attr_hpb_max_active_regions.attr, &dev_attr_wb_max_alloc_units.attr, &dev_attr_wb_max_wb_luns.attr, &dev_attr_wb_buff_cap_adj.attr, @@ -923,6 +935,9 @@ UFS_UNIT_DESC_PARAM(provisioning_type, _PROVISIONING_TYPE, 1); UFS_UNIT_DESC_PARAM(physical_memory_resourse_count, _PHY_MEM_RSRC_CNT, 8); UFS_UNIT_DESC_PARAM(context_capabilities, _CTX_CAPABILITIES, 2); UFS_UNIT_DESC_PARAM(large_unit_granularity, _LARGE_UNIT_SIZE_M1, 1); +UFS_UNIT_DESC_PARAM(hpb_lu_max_active_regions, _HPB_LU_MAX_ACTIVE_RGNS, 2); +UFS_UNIT_DESC_PARAM(hpb_pinned_region_start_offset, _HPB_PIN_RGN_START_OFF, 2); +UFS_UNIT_DESC_PARAM(hpb_number_pinned_regions, _HPB_NUM_PIN_RGNS, 2); UFS_UNIT_DESC_PARAM(wb_buf_alloc_units, _WB_BUF_ALLOC_UNITS, 4); @@ -940,6 +955,9 @@ static struct attribute *ufs_sysfs_unit_descriptor[] = { &dev_attr_physical_memory_resourse_count.attr, &dev_attr_context_capabilities.attr, &dev_attr_large_unit_granularity.attr, + &dev_attr_hpb_lu_max_active_regions.attr, + &dev_attr_hpb_pinned_region_start_offset.attr, + &dev_attr_hpb_number_pinned_regions.attr, &dev_attr_wb_buf_alloc_units.attr, NULL, }; diff --git a/drivers/scsi/ufs/ufs.h b/drivers/scsi/ufs/ufs.h index bf1897a72532..5ead2a6d513e 100644 --- a/drivers/scsi/ufs/ufs.h +++ b/drivers/scsi/ufs/ufs.h @@ -122,6 +122,7 @@ enum flag_idn { QUERY_FLAG_IDN_WB_EN = 0x0E, QUERY_FLAG_IDN_WB_BUFF_FLUSH_EN = 0x0F, QUERY_FLAG_IDN_WB_BUFF_FLUSH_DURING_HIBERN8 = 0x10, + QUERY_FLAG_IDN_HPB_RESET = 0x11, }; /* Attribute idn for Query requests */ @@ -195,6 +196,9 @@ enum unit_desc_param { UNIT_DESC_PARAM_PHY_MEM_RSRC_CNT = 0x18, UNIT_DESC_PARAM_CTX_CAPABILITIES = 0x20, UNIT_DESC_PARAM_LARGE_UNIT_SIZE_M1 = 0x22, + UNIT_DESC_PARAM_HPB_LU_MAX_ACTIVE_RGNS = 0x23, + UNIT_DESC_PARAM_HPB_PIN_RGN_START_OFF = 0x25, + UNIT_DESC_PARAM_HPB_NUM_PIN_RGNS = 0x27, UNIT_DESC_PARAM_WB_BUF_ALLOC_UNITS = 0x29, }; @@ -235,6 +239,8 @@ enum device_desc_param { DEVICE_DESC_PARAM_PSA_MAX_DATA = 0x25, DEVICE_DESC_PARAM_PSA_TMT = 0x29, DEVICE_DESC_PARAM_PRDCT_REV = 0x2A, + DEVICE_DESC_PARAM_HPB_VER = 0x40, + DEVICE_DESC_PARAM_HPB_CONTROL = 0x42, DEVICE_DESC_PARAM_EXT_UFS_FEATURE_SUP = 0x4F, DEVICE_DESC_PARAM_WB_PRESRV_USRSPC_EN = 0x53, DEVICE_DESC_PARAM_WB_TYPE = 0x54, @@ -283,6 +289,10 @@ enum geometry_desc_param { GEOMETRY_DESC_PARAM_ENM4_MAX_NUM_UNITS = 0x3E, GEOMETRY_DESC_PARAM_ENM4_CAP_ADJ_FCTR = 0x42, GEOMETRY_DESC_PARAM_OPT_LOG_BLK_SIZE = 0x44, + GEOMETRY_DESC_PARAM_HPB_REGION_SIZE = 0x48, + GEOMETRY_DESC_PARAM_HPB_NUMBER_LU = 0x49, + GEOMETRY_DESC_PARAM_HPB_SUBREGION_SIZE = 0x4A, + GEOMETRY_DESC_PARAM_HPB_MAX_ACTIVE_REGS = 0x4B, GEOMETRY_DESC_PARAM_WB_MAX_ALLOC_UNITS = 0x4F, GEOMETRY_DESC_PARAM_WB_MAX_WB_LUNS = 0x53, GEOMETRY_DESC_PARAM_WB_BUFF_CAP_ADJ = 0x54, @@ -327,8 +337,10 @@ enum { /* Possible values for dExtendedUFSFeaturesSupport */ enum { + UFS_DEV_HPB_SUPPORT = BIT(7), UFS_DEV_WRITE_BOOSTER_SUP = BIT(8), }; +#define UFS_DEV_HPB_SUPPORT_VERSION 0x310 #define POWER_DESC_MAX_ACTV_ICC_LVLS 16 @@ -546,6 +558,9 @@ struct ufs_dev_info { bool b_rpm_dev_flush_capable; u8 b_presrv_uspc_en; + + u8 b_ufs_feature_sup; + u32 d_ext_ufs_feature_sup; }; /* diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index 36bcbb38f631..6f9d9fc8a4a4 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -23,6 +23,7 @@ #include "ufs-debugfs.h" #include "ufs_bsg.h" #include "ufshcd-crypto.h" +#include "ufshpb.h" #include #include @@ -4852,6 +4853,26 @@ static int ufshcd_change_queue_depth(struct scsi_device *sdev, int depth) return scsi_change_queue_depth(sdev, depth); } +static void ufshcd_hpb_destroy(struct ufs_hba *hba, struct scsi_device *sdev) +{ + /* skip well-known LU */ + if ((sdev->lun >= UFS_UPIU_MAX_UNIT_NUM_ID) || !ufshpb_is_allowed(hba)) + return; + + ufshpb_destroy_lu(hba, sdev); +} + +static void ufshcd_hpb_configure(struct ufs_hba *hba, struct scsi_device *sdev) +{ + /* skip well-known LU */ + if ((sdev->lun >= UFS_UPIU_MAX_UNIT_NUM_ID) || + !(hba->dev_info.b_ufs_feature_sup & UFS_DEV_HPB_SUPPORT) || + !ufshpb_is_allowed(hba)) + return; + + ufshpb_init_hpb_lu(hba, sdev); +} + /** * ufshcd_slave_configure - adjust SCSI device configurations * @sdev: pointer to SCSI device @@ -4861,6 +4882,8 @@ static int ufshcd_slave_configure(struct scsi_device *sdev) struct ufs_hba *hba = shost_priv(sdev->host); struct request_queue *q = sdev->request_queue; + ufshcd_hpb_configure(hba, sdev); + blk_queue_update_dma_pad(q, PRDT_DATA_BYTE_COUNT_PAD - 1); if (hba->quirks & UFSHCD_QUIRK_ALIGN_SG_WITH_PAGE_SIZE) blk_queue_update_dma_alignment(q, PAGE_SIZE - 1); @@ -4882,6 +4905,9 @@ static void ufshcd_slave_destroy(struct scsi_device *sdev) struct ufs_hba *hba; hba = shost_priv(sdev->host); + + ufshcd_hpb_destroy(hba, sdev); + /* Drop the reference as it won't be needed anymore */ if (ufshcd_scsi_to_upiu_lun(sdev->lun) == UFS_UPIU_UFS_DEVICE_WLUN) { unsigned long flags; @@ -6961,6 +6987,8 @@ static int ufshcd_host_reset_and_restore(struct ufs_hba *hba) * Stop the host controller and complete the requests * cleared by h/w */ + ufshpb_reset_host(hba); + ufshcd_hba_stop(hba); spin_lock_irqsave(hba->host->host_lock, flags); @@ -7393,9 +7421,14 @@ static int ufs_get_device_desc(struct ufs_hba *hba) /* getting Specification Version in big endian format */ dev_info->wspecversion = desc_buf[DEVICE_DESC_PARAM_SPEC_VER] << 8 | desc_buf[DEVICE_DESC_PARAM_SPEC_VER + 1]; + dev_info->b_ufs_feature_sup = desc_buf[DEVICE_DESC_PARAM_UFS_FEAT]; model_index = desc_buf[DEVICE_DESC_PARAM_PRDCT_NAME]; + if (dev_info->wspecversion >= UFS_DEV_HPB_SUPPORT_VERSION && + (dev_info->b_ufs_feature_sup & UFS_DEV_HPB_SUPPORT)) + ufshpb_get_dev_info(hba, desc_buf); + err = ufshcd_read_string_desc(hba, model_index, &dev_info->model, SD_ASCII_STD); if (err < 0) { @@ -7624,6 +7657,10 @@ static int ufshcd_device_geo_params_init(struct ufs_hba *hba) else if (desc_buf[GEOMETRY_DESC_PARAM_MAX_NUM_LUN] == 0) hba->dev_info.max_lu_supported = 8; + if (hba->desc_size[QUERY_DESC_IDN_GEOMETRY] >= + GEOMETRY_DESC_PARAM_HPB_MAX_ACTIVE_REGS) + ufshpb_get_geo_info(hba, desc_buf); + out: kfree(desc_buf); return err; @@ -7764,6 +7801,7 @@ static int ufshcd_add_lus(struct ufs_hba *hba) } ufs_bsg_probe(hba); + ufshpb_init(hba); scsi_scan_host(hba->host); pm_runtime_put_sync(hba->dev); @@ -7907,6 +7945,7 @@ static int ufshcd_probe_hba(struct ufs_hba *hba, bool async) /* Enable Auto-Hibernate if configured */ ufshcd_auto_hibern8_enable(hba); + ufshpb_reset(hba); out: spin_lock_irqsave(hba->host->host_lock, flags); if (ret) @@ -7956,6 +7995,9 @@ static void ufshcd_async_scan(void *data, async_cookie_t cookie) static const struct attribute_group *ufshcd_driver_groups[] = { &ufs_sysfs_unit_descriptor_group, &ufs_sysfs_lun_attributes_group, +#ifdef CONFIG_SCSI_UFS_HPB + &ufs_sysfs_hpb_stat_group, +#endif NULL, }; @@ -8672,6 +8714,8 @@ static int ufshcd_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op) req_link_state = UIC_LINK_OFF_STATE; } + ufshpb_suspend(hba); + /* * If we can't transition into any of the low power modes * just gate the clocks. @@ -8806,6 +8850,7 @@ static int ufshcd_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op) hba->clk_gating.is_suspended = false; hba->dev_info.b_rpm_dev_flush_capable = false; ufshcd_release(hba); + ufshpb_resume(hba); out: if (hba->dev_info.b_rpm_dev_flush_capable) { schedule_delayed_work(&hba->rpm_dev_flush_recheck_work, @@ -8910,6 +8955,8 @@ static int ufshcd_resume(struct ufs_hba *hba, enum ufs_pm_op pm_op) /* Enable Auto-Hibernate if configured */ ufshcd_auto_hibern8_enable(hba); + ufshpb_resume(hba); + if (hba->dev_info.b_rpm_dev_flush_capable) { hba->dev_info.b_rpm_dev_flush_capable = false; cancel_delayed_work(&hba->rpm_dev_flush_recheck_work); diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h index ee61f821f75d..c2c0b413a792 100644 --- a/drivers/scsi/ufs/ufshcd.h +++ b/drivers/scsi/ufs/ufshcd.h @@ -645,6 +645,25 @@ struct ufs_hba_variant_params { u32 wb_flush_threshold; }; +#ifdef CONFIG_SCSI_UFS_HPB +/** + * struct ufshpb_dev_info - UFSHPB device related info + * @num_lu: the number of user logical unit to check whether all lu finished + * initialization + * @rgn_size: device reported HPB region size + * @srgn_size: device reported HPB sub-region size + * @slave_conf_cnt: counter to check all lu finished initialization + * @hpb_disabled: flag to check if HPB is disabled + */ +struct ufshpb_dev_info { + int num_lu; + int rgn_size; + int srgn_size; + atomic_t slave_conf_cnt; + bool hpb_disabled; +}; +#endif + /** * struct ufs_hba - per adapter private structure * @mmio_base: UFSHCI base register address @@ -831,7 +850,9 @@ struct ufs_hba { struct device bsg_dev; struct request_queue *bsg_queue; struct delayed_work rpm_dev_flush_recheck_work; - +#ifdef CONFIG_SCSI_UFS_HPB + struct ufshpb_dev_info ufshpb_dev; +#endif #ifdef CONFIG_SCSI_UFS_CRYPTO union ufs_crypto_capabilities crypto_capabilities; union ufs_crypto_cap_entry *crypto_cap_array; diff --git a/drivers/scsi/ufs/ufshpb.c b/drivers/scsi/ufs/ufshpb.c new file mode 100644 index 000000000000..badb613ac281 --- /dev/null +++ b/drivers/scsi/ufs/ufshpb.c @@ -0,0 +1,559 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Universal Flash Storage Host Performance Booster + * + * Copyright (C) 2017-2020 Samsung Electronics Co., Ltd. + * + * Authors: + * Yongmyung Lee + * Jinyoung Choi + */ + +#include +#include + +#include "ufshcd.h" +#include "ufshpb.h" +#include "../sd.h" + +bool ufshpb_is_allowed(struct ufs_hba *hba) +{ + return !(hba->ufshpb_dev.hpb_disabled); +} + +static struct ufshpb_lu *ufshpb_get_hpb_data(struct scsi_device *sdev) +{ + return sdev->hostdata; +} + +static int ufshpb_get_state(struct ufshpb_lu *hpb) +{ + return atomic_read(&hpb->hpb_state); +} + +static void ufshpb_set_state(struct ufshpb_lu *hpb, int state) +{ + atomic_set(&hpb->hpb_state, state); +} + +static void ufshpb_init_subregion_tbl(struct ufshpb_lu *hpb, + struct ufshpb_region *rgn) +{ + int srgn_idx; + + for (srgn_idx = 0; srgn_idx < rgn->srgn_cnt; srgn_idx++) { + struct ufshpb_subregion *srgn = rgn->srgn_tbl + srgn_idx; + + srgn->rgn_idx = rgn->rgn_idx; + srgn->srgn_idx = srgn_idx; + srgn->srgn_state = HPB_SRGN_UNUSED; + } +} + +static int ufshpb_alloc_subregion_tbl(struct ufshpb_lu *hpb, + struct ufshpb_region *rgn, + int srgn_cnt) +{ + rgn->srgn_tbl = kvcalloc(srgn_cnt, sizeof(struct ufshpb_subregion), + GFP_KERNEL); + if (!rgn->srgn_tbl) + return -ENOMEM; + + rgn->srgn_cnt = srgn_cnt; + return 0; +} + +static void ufshpb_lu_parameter_init(struct ufs_hba *hba, + struct ufshpb_lu *hpb, + struct ufshpb_dev_info *hpb_dev_info, + struct ufshpb_lu_info *hpb_lu_info) +{ + u32 entries_per_rgn; + u64 rgn_mem_size, tmp; + + hpb->lu_pinned_start = hpb_lu_info->pinned_start; + hpb->lu_pinned_end = hpb_lu_info->num_pinned ? + (hpb_lu_info->pinned_start + hpb_lu_info->num_pinned - 1) + : PINNED_NOT_SET; + + rgn_mem_size = (1ULL << hpb_dev_info->rgn_size) * HPB_RGN_SIZE_UNIT + * HPB_ENTRY_SIZE; + do_div(rgn_mem_size, HPB_ENTRY_BLOCK_SIZE); + hpb->srgn_mem_size = (1ULL << hpb_dev_info->srgn_size) + * HPB_RGN_SIZE_UNIT / HPB_ENTRY_BLOCK_SIZE * HPB_ENTRY_SIZE; + + tmp = rgn_mem_size; + do_div(tmp, HPB_ENTRY_SIZE); + entries_per_rgn = (u32)tmp; + hpb->entries_per_rgn_shift = ilog2(entries_per_rgn); + hpb->entries_per_rgn_mask = entries_per_rgn - 1; + + hpb->entries_per_srgn = hpb->srgn_mem_size / HPB_ENTRY_SIZE; + hpb->entries_per_srgn_shift = ilog2(hpb->entries_per_srgn); + hpb->entries_per_srgn_mask = hpb->entries_per_srgn - 1; + + tmp = rgn_mem_size; + do_div(tmp, hpb->srgn_mem_size); + hpb->srgns_per_rgn = (int)tmp; + + hpb->rgns_per_lu = DIV_ROUND_UP(hpb_lu_info->num_blocks, + entries_per_rgn); + hpb->srgns_per_lu = DIV_ROUND_UP(hpb_lu_info->num_blocks, + (hpb->srgn_mem_size / HPB_ENTRY_SIZE)); + + hpb->pages_per_srgn = DIV_ROUND_UP(hpb->srgn_mem_size, PAGE_SIZE); +} + +static int ufshpb_alloc_region_tbl(struct ufs_hba *hba, struct ufshpb_lu *hpb) +{ + struct ufshpb_region *rgn_table, *rgn; + int rgn_idx, i; + int ret = 0; + + rgn_table = kvcalloc(hpb->rgns_per_lu, sizeof(struct ufshpb_region), + GFP_KERNEL); + if (!rgn_table) + return -ENOMEM; + + hpb->rgn_tbl = rgn_table; + + for (rgn_idx = 0; rgn_idx < hpb->rgns_per_lu; rgn_idx++) { + int srgn_cnt = hpb->srgns_per_rgn; + + rgn = rgn_table + rgn_idx; + rgn->rgn_idx = rgn_idx; + + if (rgn_idx == hpb->rgns_per_lu - 1) + srgn_cnt = ((hpb->srgns_per_lu - 1) % + hpb->srgns_per_rgn) + 1; + + ret = ufshpb_alloc_subregion_tbl(hpb, rgn, srgn_cnt); + if (ret) + goto release_srgn_table; + ufshpb_init_subregion_tbl(hpb, rgn); + + rgn->rgn_state = HPB_RGN_INACTIVE; + } + + return 0; + +release_srgn_table: + for (i = 0; i < rgn_idx; i++) { + rgn = rgn_table + i; + if (rgn->srgn_tbl) + kvfree(rgn->srgn_tbl); + } + kvfree(rgn_table); + return ret; +} + +static void ufshpb_destroy_subregion_tbl(struct ufshpb_lu *hpb, + struct ufshpb_region *rgn) +{ + int srgn_idx; + + for (srgn_idx = 0; srgn_idx < rgn->srgn_cnt; srgn_idx++) { + struct ufshpb_subregion *srgn; + + srgn = rgn->srgn_tbl + srgn_idx; + srgn->srgn_state = HPB_SRGN_UNUSED; + } +} + +static void ufshpb_destroy_region_tbl(struct ufshpb_lu *hpb) +{ + int rgn_idx; + + for (rgn_idx = 0; rgn_idx < hpb->rgns_per_lu; rgn_idx++) { + struct ufshpb_region *rgn; + + rgn = hpb->rgn_tbl + rgn_idx; + if (rgn->rgn_state != HPB_RGN_INACTIVE) { + rgn->rgn_state = HPB_RGN_INACTIVE; + + ufshpb_destroy_subregion_tbl(hpb, rgn); + } + + kvfree(rgn->srgn_tbl); + } + + kvfree(hpb->rgn_tbl); +} + +/* SYSFS functions */ +#define ufshpb_sysfs_attr_show_func(__name) \ +static ssize_t __name##_show(struct device *dev, \ + struct device_attribute *attr, char *buf) \ +{ \ + struct scsi_device *sdev = to_scsi_device(dev); \ + struct ufshpb_lu *hpb = ufshpb_get_hpb_data(sdev); \ + \ + return sysfs_emit(buf, "%llu\n", hpb->stats.__name); \ +} \ +\ +static DEVICE_ATTR_RO(__name) + +ufshpb_sysfs_attr_show_func(hit_cnt); +ufshpb_sysfs_attr_show_func(miss_cnt); +ufshpb_sysfs_attr_show_func(rb_noti_cnt); +ufshpb_sysfs_attr_show_func(rb_active_cnt); +ufshpb_sysfs_attr_show_func(rb_inactive_cnt); +ufshpb_sysfs_attr_show_func(map_req_cnt); + +static struct attribute *hpb_dev_attrs[] = { + &dev_attr_hit_cnt.attr, + &dev_attr_miss_cnt.attr, + &dev_attr_rb_noti_cnt.attr, + &dev_attr_rb_active_cnt.attr, + &dev_attr_rb_inactive_cnt.attr, + &dev_attr_map_req_cnt.attr, + NULL, +}; + +struct attribute_group ufs_sysfs_hpb_stat_group = { + .name = "hpb_sysfs", + .attrs = hpb_dev_attrs, +}; + +static void ufshpb_stat_init(struct ufshpb_lu *hpb) +{ + hpb->stats.hit_cnt = 0; + hpb->stats.miss_cnt = 0; + hpb->stats.rb_noti_cnt = 0; + hpb->stats.rb_active_cnt = 0; + hpb->stats.rb_inactive_cnt = 0; + hpb->stats.map_req_cnt = 0; +} + +static int ufshpb_lu_hpb_init(struct ufs_hba *hba, struct ufshpb_lu *hpb) +{ + int ret; + + ret = ufshpb_alloc_region_tbl(hba, hpb); + + ufshpb_stat_init(hpb); + + return 0; +} + +static struct ufshpb_lu *ufshpb_alloc_hpb_lu(struct ufs_hba *hba, int lun, + struct ufshpb_dev_info *hpb_dev_info, + struct ufshpb_lu_info *hpb_lu_info) +{ + struct ufshpb_lu *hpb; + int ret; + + hpb = kzalloc(sizeof(struct ufshpb_lu), GFP_KERNEL); + if (!hpb) + return NULL; + + hpb->lun = lun; + + ufshpb_lu_parameter_init(hba, hpb, hpb_dev_info, hpb_lu_info); + + ret = ufshpb_lu_hpb_init(hba, hpb); + if (ret) { + dev_err(hba->dev, "hpb lu init failed. ret %d", ret); + goto release_hpb; + } + + return hpb; + +release_hpb: + kfree(hpb); + return NULL; +} + +static bool ufshpb_check_hpb_reset_query(struct ufs_hba *hba) +{ + int err = 0; + bool flag_res = true; + int try; + + /* wait for the device to complete HPB reset query */ + for (try = 0; try < HPB_RESET_REQ_RETRIES; try++) { + dev_dbg(hba->dev, + "%s start flag reset polling %d times\n", + __func__, try); + + /* Poll fHpbReset flag to be cleared */ + err = ufshcd_query_flag(hba, UPIU_QUERY_OPCODE_READ_FLAG, + QUERY_FLAG_IDN_HPB_RESET, 0, &flag_res); + + if (err) { + dev_err(hba->dev, + "%s reading fHpbReset flag failed with error %d\n", + __func__, err); + return flag_res; + } + + if (!flag_res) + goto out; + + usleep_range(1000, 1100); + } + if (flag_res) { + dev_err(hba->dev, + "%s fHpbReset was not cleared by the device\n", + __func__); + } +out: + return flag_res; +} + +void ufshpb_reset(struct ufs_hba *hba) +{ + struct ufshpb_lu *hpb; + struct scsi_device *sdev; + + shost_for_each_device(sdev, hba->host) { + hpb = sdev->hostdata; + if (!hpb) + continue; + + if (ufshpb_get_state(hpb) != HPB_RESET) + continue; + + ufshpb_set_state(hpb, HPB_PRESENT); + } +} + +void ufshpb_reset_host(struct ufs_hba *hba) +{ + struct ufshpb_lu *hpb; + struct scsi_device *sdev; + + shost_for_each_device(sdev, hba->host) { + hpb = sdev->hostdata; + if (!hpb) + continue; + + if (ufshpb_get_state(hpb) != HPB_PRESENT) + continue; + ufshpb_set_state(hpb, HPB_RESET); + } +} + +void ufshpb_suspend(struct ufs_hba *hba) +{ + struct ufshpb_lu *hpb; + struct scsi_device *sdev; + + shost_for_each_device(sdev, hba->host) { + hpb = sdev->hostdata; + if (!hpb) + continue; + + if (ufshpb_get_state(hpb) != HPB_PRESENT) + continue; + ufshpb_set_state(hpb, HPB_SUSPEND); + } +} + +void ufshpb_resume(struct ufs_hba *hba) +{ + struct ufshpb_lu *hpb; + struct scsi_device *sdev; + + shost_for_each_device(sdev, hba->host) { + hpb = sdev->hostdata; + if (!hpb) + continue; + + if ((ufshpb_get_state(hpb) != HPB_PRESENT) && + (ufshpb_get_state(hpb) != HPB_SUSPEND)) + continue; + ufshpb_set_state(hpb, HPB_PRESENT); + } +} + +static int ufshpb_get_lu_info(struct ufs_hba *hba, int lun, + struct ufshpb_lu_info *hpb_lu_info) +{ + u16 max_active_rgns; + u8 lu_enable; + int size; + int ret; + char desc_buf[QUERY_DESC_MAX_SIZE]; + + ufshcd_map_desc_id_to_length(hba, QUERY_DESC_IDN_UNIT, &size); + + pm_runtime_get_sync(hba->dev); + ret = ufshcd_query_descriptor_retry(hba, UPIU_QUERY_OPCODE_READ_DESC, + QUERY_DESC_IDN_UNIT, lun, 0, + desc_buf, &size); + pm_runtime_put_sync(hba->dev); + + if (ret) { + dev_err(hba->dev, + "%s: idn: %d lun: %d query request failed", + __func__, QUERY_DESC_IDN_UNIT, lun); + return ret; + } + + lu_enable = desc_buf[UNIT_DESC_PARAM_LU_ENABLE]; + if (lu_enable != LU_ENABLED_HPB_FUNC) + return -ENODEV; + + max_active_rgns = get_unaligned_be16( + desc_buf + UNIT_DESC_PARAM_HPB_LU_MAX_ACTIVE_RGNS); + if (!max_active_rgns) { + dev_err(hba->dev, + "lun %d wrong number of max active regions\n", lun); + return -ENODEV; + } + + hpb_lu_info->num_blocks = get_unaligned_be64( + desc_buf + UNIT_DESC_PARAM_LOGICAL_BLK_COUNT); + hpb_lu_info->pinned_start = get_unaligned_be16( + desc_buf + UNIT_DESC_PARAM_HPB_PIN_RGN_START_OFF); + hpb_lu_info->num_pinned = get_unaligned_be16( + desc_buf + UNIT_DESC_PARAM_HPB_NUM_PIN_RGNS); + hpb_lu_info->max_active_rgns = max_active_rgns; + + return 0; +} + +void ufshpb_destroy_lu(struct ufs_hba *hba, struct scsi_device *sdev) +{ + struct ufshpb_lu *hpb = sdev->hostdata; + + if (!hpb) + return; + + ufshpb_set_state(hpb, HPB_FAILED); + + sdev = hpb->sdev_ufs_lu; + sdev->hostdata = NULL; + + ufshpb_destroy_region_tbl(hpb); + + list_del_init(&hpb->list_hpb_lu); + + kfree(hpb); +} + +static void ufshpb_hpb_lu_prepared(struct ufs_hba *hba) +{ + struct ufshpb_lu *hpb; + struct scsi_device *sdev; + bool init_success; + + init_success = !ufshpb_check_hpb_reset_query(hba); + + shost_for_each_device(sdev, hba->host) { + hpb = sdev->hostdata; + if (!hpb) + continue; + + if (init_success) { + ufshpb_set_state(hpb, HPB_PRESENT); + } else { + dev_err(hba->dev, "destroy HPB lu %d\n", hpb->lun); + ufshpb_destroy_lu(hba, sdev); + } + } +} + +void ufshpb_init_hpb_lu(struct ufs_hba *hba, struct scsi_device *sdev) +{ + struct ufshpb_lu *hpb; + int ret; + struct ufshpb_lu_info hpb_lu_info = { 0 }; + int lun = sdev->lun; + + if (lun >= hba->dev_info.max_lu_supported) + goto out; + + ret = ufshpb_get_lu_info(hba, lun, &hpb_lu_info); + if (ret) + goto out; + + hpb = ufshpb_alloc_hpb_lu(hba, lun, &hba->ufshpb_dev, + &hpb_lu_info); + if (!hpb) + goto out; + + hpb->sdev_ufs_lu = sdev; + sdev->hostdata = hpb; + +out: + /* All LUs are initialized */ + if (atomic_dec_and_test(&hba->ufshpb_dev.slave_conf_cnt)) + ufshpb_hpb_lu_prepared(hba); +} + +void ufshpb_get_geo_info(struct ufs_hba *hba, u8 *geo_buf) +{ + struct ufshpb_dev_info *hpb_dev_info = &hba->ufshpb_dev; + int hpb_device_max_active_rgns = 0; + int hpb_num_lu; + + hpb_num_lu = geo_buf[GEOMETRY_DESC_PARAM_HPB_NUMBER_LU]; + if (hpb_num_lu == 0) { + dev_err(hba->dev, "No HPB LU supported\n"); + hpb_dev_info->hpb_disabled = true; + return; + } + + hpb_dev_info->rgn_size = geo_buf[GEOMETRY_DESC_PARAM_HPB_REGION_SIZE]; + hpb_dev_info->srgn_size = geo_buf[GEOMETRY_DESC_PARAM_HPB_SUBREGION_SIZE]; + hpb_device_max_active_rgns = + get_unaligned_be16(geo_buf + + GEOMETRY_DESC_PARAM_HPB_MAX_ACTIVE_REGS); + + if (hpb_dev_info->rgn_size == 0 || hpb_dev_info->srgn_size == 0 || + hpb_device_max_active_rgns == 0) { + dev_err(hba->dev, "No HPB supported device\n"); + hpb_dev_info->hpb_disabled = true; + return; + } +} + +void ufshpb_get_dev_info(struct ufs_hba *hba, u8 *desc_buf) +{ + struct ufshpb_dev_info *hpb_dev_info = &hba->ufshpb_dev; + int version; + u8 hpb_mode; + + hpb_mode = desc_buf[DEVICE_DESC_PARAM_HPB_CONTROL]; + if (hpb_mode == HPB_HOST_CONTROL) { + dev_err(hba->dev, "%s: host control mode is not supported.\n", + __func__); + hpb_dev_info->hpb_disabled = true; + return; + } + + version = get_unaligned_be16(desc_buf + DEVICE_DESC_PARAM_HPB_VER); + if (version != HPB_SUPPORT_VERSION) { + dev_err(hba->dev, "%s: HPB %x version is not supported.\n", + __func__, version); + hpb_dev_info->hpb_disabled = true; + return; + } + + /* + * Get the number of user logical unit to check whether all + * scsi_device finish initialization + */ + hpb_dev_info->num_lu = desc_buf[DEVICE_DESC_PARAM_NUM_LU]; +} + +void ufshpb_init(struct ufs_hba *hba) +{ + struct ufshpb_dev_info *hpb_dev_info = &hba->ufshpb_dev; + int try; + int ret; + + if (!ufshpb_is_allowed(hba)) + return; + + atomic_set(&hpb_dev_info->slave_conf_cnt, hpb_dev_info->num_lu); + /* issue HPB reset query */ + for (try = 0; try < HPB_RESET_REQ_RETRIES; try++) { + ret = ufshcd_query_flag(hba, UPIU_QUERY_OPCODE_SET_FLAG, + QUERY_FLAG_IDN_HPB_RESET, 0, NULL); + if (!ret) + break; + } +} diff --git a/drivers/scsi/ufs/ufshpb.h b/drivers/scsi/ufs/ufshpb.h new file mode 100644 index 000000000000..50523821cac8 --- /dev/null +++ b/drivers/scsi/ufs/ufshpb.h @@ -0,0 +1,164 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Universal Flash Storage Host Performance Booster + * + * Copyright (C) 2017-2020 Samsung Electronics Co., Ltd. + * + * Authors: + * Yongmyung Lee + * Jinyoung Choi + */ + +#ifndef _UFSHPB_H_ +#define _UFSHPB_H_ + +/* hpb response UPIU macro */ +#define HPB_RSP_NONE 0x0 +#define HPB_RSP_REQ_REGION_UPDATE 0x1 +#define HPB_RSP_DEV_RESET 0x2 +#define MAX_ACTIVE_NUM 2 +#define MAX_INACTIVE_NUM 2 +#define DEV_DATA_SEG_LEN 0x14 +#define DEV_SENSE_SEG_LEN 0x12 +#define DEV_DES_TYPE 0x80 +#define DEV_ADDITIONAL_LEN 0x10 + +/* hpb map & entries macro */ +#define HPB_RGN_SIZE_UNIT 512 +#define HPB_ENTRY_BLOCK_SIZE 4096 +#define HPB_ENTRY_SIZE 0x8 +#define PINNED_NOT_SET U32_MAX + +/* hpb support chunk size */ +#define HPB_MULTI_CHUNK_HIGH 1 + +/* hpb vender defined opcode */ +#define UFSHPB_READ 0xF8 +#define UFSHPB_READ_BUFFER 0xF9 +#define UFSHPB_READ_BUFFER_ID 0x01 +#define HPB_READ_BUFFER_CMD_LENGTH 10 +#define LU_ENABLED_HPB_FUNC 0x02 + +#define HPB_RESET_REQ_RETRIES 10 + +#define HPB_SUPPORT_VERSION 0x100 + +enum UFSHPB_MODE { + HPB_HOST_CONTROL, + HPB_DEVICE_CONTROL, +}; + +enum UFSHPB_STATE { + HPB_PRESENT = 1, + HPB_SUSPEND, + HPB_FAILED, + HPB_RESET, +}; + +enum HPB_RGN_STATE { + HPB_RGN_INACTIVE, + HPB_RGN_ACTIVE, + /* pinned regions are always active */ + HPB_RGN_PINNED, +}; + +enum HPB_SRGN_STATE { + HPB_SRGN_UNUSED, + HPB_SRGN_INVALID, + HPB_SRGN_VALID, + HPB_SRGN_ISSUED, +}; + +/** + * struct ufshpb_lu_info - UFSHPB logical unit related info + * @num_blocks: the number of logical block + * @pinned_start: the start region number of pinned region + * @num_pinned: the number of pinned regions + * @max_active_rgns: maximum number of active regions + */ +struct ufshpb_lu_info { + int num_blocks; + int pinned_start; + int num_pinned; + int max_active_rgns; +}; + +struct ufshpb_subregion { + enum HPB_SRGN_STATE srgn_state; + int rgn_idx; + int srgn_idx; +}; + +struct ufshpb_region { + struct ufshpb_subregion *srgn_tbl; + enum HPB_RGN_STATE rgn_state; + int rgn_idx; + int srgn_cnt; +}; + +struct ufshpb_stats { + u64 hit_cnt; + u64 miss_cnt; + u64 rb_noti_cnt; + u64 rb_active_cnt; + u64 rb_inactive_cnt; + u64 map_req_cnt; +}; + +struct ufshpb_lu { + int lun; + struct scsi_device *sdev_ufs_lu; + struct ufshpb_region *rgn_tbl; + + atomic_t hpb_state; + + /* pinned region information */ + u32 lu_pinned_start; + u32 lu_pinned_end; + + /* HPB related configuration */ + u32 rgns_per_lu; + u32 srgns_per_lu; + int srgns_per_rgn; + u32 srgn_mem_size; + u32 entries_per_rgn_mask; + u32 entries_per_rgn_shift; + u32 entries_per_srgn; + u32 entries_per_srgn_mask; + u32 entries_per_srgn_shift; + u32 pages_per_srgn; + + struct ufshpb_stats stats; + + struct list_head list_hpb_lu; +}; + +struct ufs_hba; +struct ufshcd_lrb; + +#ifndef CONFIG_SCSI_UFS_HPB +static void ufshpb_resume(struct ufs_hba *hba) {} +static void ufshpb_suspend(struct ufs_hba *hba) {} +static void ufshpb_reset(struct ufs_hba *hba) {} +static void ufshpb_reset_host(struct ufs_hba *hba) {} +static void ufshpb_init(struct ufs_hba *hba) {} +static void ufshpb_init_hpb_lu(struct ufs_hba *hba, struct scsi_device *sdev) {} +static void ufshpb_destroy_lu(struct ufs_hba *hba, struct scsi_device *sdev) {} +static bool ufshpb_is_allowed(struct ufs_hba *hba) { return false; } +static void ufshpb_get_geo_info(struct ufs_hba *hba, u8 *geo_buf) {} +static void ufshpb_get_dev_info(struct ufs_hba *hba, u8 *desc_buf) {} +#else +void ufshpb_resume(struct ufs_hba *hba); +void ufshpb_suspend(struct ufs_hba *hba); +void ufshpb_reset(struct ufs_hba *hba); +void ufshpb_reset_host(struct ufs_hba *hba); +void ufshpb_init(struct ufs_hba *hba); +void ufshpb_init_hpb_lu(struct ufs_hba *hba, struct scsi_device *sdev); +void ufshpb_destroy_lu(struct ufs_hba *hba, struct scsi_device *sdev); +bool ufshpb_is_allowed(struct ufs_hba *hba); +void ufshpb_get_geo_info(struct ufs_hba *hba, u8 *geo_buf); +void ufshpb_get_dev_info(struct ufs_hba *hba, u8 *desc_buf); +extern struct attribute_group ufs_sysfs_hpb_stat_group; +#endif + +#endif /* End of Header */ From bde747aa2292431a07bcbd64463a3d8142fdb12f Mon Sep 17 00:00:00 2001 From: Daejun Park Date: Tue, 22 Dec 2020 10:58:28 +0900 Subject: [PATCH 02/11] scsi: ufs: L2P map management for HPB read This is a patch for managing L2P map in HPB module. The HPB divides logical addresses into several regions. A region consists of several sub-regions. The sub-region is a basic unit where L2P mapping is managed. The driver loads L2P mapping data of each sub-region. The loaded sub-region is called active-state. The HPB driver unloads L2P mapping data as region unit. The unloaded region is called inactive-state. Sub-region/region candidates to be loaded and unloaded are delivered from the UFS device. The UFS device delivers the recommended active sub-region and inactivate region to the driver using sensedata. The HPB module performs L2P mapping management on the host through the delivered information. A pinned region is a pre-set regions on the UFS device that is always activate-state. The data structure for map data request and L2P map uses mempool API, minimizing allocation overhead while avoiding static allocation. The mininum size of the memory pool used in the HPB is implemented as a module parameter, so that it can be configurable by the user. To gurantee a minimum memory pool size of 4MB: ufshpb_host_map_kbytes=4096 The map_work manages active/inactive by 2 "to-do" lists. Each hpb lun maintains 2 "to-do" lists: hpb->lh_inact_rgn - regions to be inactivated, and hpb->lh_act_srgn - subregions to be activated Those lists are maintained on IO completion. Reviewed-by: Bart Van Assche Reviewed-by: Can Guo Acked-by: Avri Altman Tested-by: Bean Huo Signed-off-by: Daejun Park --- drivers/scsi/ufs/ufs.h | 36 ++ drivers/scsi/ufs/ufshcd.c | 4 + drivers/scsi/ufs/ufshpb.c | 993 +++++++++++++++++++++++++++++++++++++- drivers/scsi/ufs/ufshpb.h | 65 +++ 4 files changed, 1083 insertions(+), 15 deletions(-) diff --git a/drivers/scsi/ufs/ufs.h b/drivers/scsi/ufs/ufs.h index 5ead2a6d513e..039421cfc1f7 100644 --- a/drivers/scsi/ufs/ufs.h +++ b/drivers/scsi/ufs/ufs.h @@ -472,6 +472,41 @@ struct utp_cmd_rsp { u8 sense_data[UFS_SENSE_SIZE]; }; +struct ufshpb_active_field { + __be16 active_rgn; + __be16 active_srgn; +}; +#define HPB_ACT_FIELD_SIZE 4 + +/** + * struct utp_hpb_rsp - Response UPIU structure + * @residual_transfer_count: Residual transfer count DW-3 + * @reserved1: Reserved double words DW-4 to DW-7 + * @sense_data_len: Sense data length DW-8 U16 + * @desc_type: Descriptor type of sense data + * @additional_len: Additional length of sense data + * @hpb_op: HPB operation type + * @reserved2: Reserved field + * @active_rgn_cnt: Active region count + * @inactive_rgn_cnt: Inactive region count + * @hpb_active_field: Recommended to read HPB region and subregion + * @hpb_inactive_field: To be inactivated HPB region and subregion + */ +struct utp_hpb_rsp { + __be32 residual_transfer_count; + __be32 reserved1[4]; + __be16 sense_data_len; + u8 desc_type; + u8 additional_len; + u8 hpb_op; + u8 reserved2; + u8 active_rgn_cnt; + u8 inactive_rgn_cnt; + struct ufshpb_active_field hpb_active_field[2]; + __be16 hpb_inactive_field[2]; +}; +#define UTP_HPB_RSP_SIZE 40 + /** * struct utp_upiu_rsp - general upiu response structure * @header: UPIU header structure DW-0 to DW-2 @@ -482,6 +517,7 @@ struct utp_upiu_rsp { struct utp_upiu_header header; union { struct utp_cmd_rsp sr; + struct utp_hpb_rsp hr; struct utp_upiu_query qr; }; }; diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index 6f9d9fc8a4a4..51bb62686e3b 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -5015,6 +5015,9 @@ ufshcd_transfer_rsp_status(struct ufs_hba *hba, struct ufshcd_lrb *lrbp) */ pm_runtime_get_noresume(hba->dev); } + + if (scsi_status == SAM_STAT_GOOD) + ufshpb_rsp_upiu(hba, lrbp); break; case UPIU_TRANSACTION_REJECT_UPIU: /* TODO: handle Reject UPIU Response */ @@ -9201,6 +9204,7 @@ EXPORT_SYMBOL(ufshcd_shutdown); void ufshcd_remove(struct ufs_hba *hba) { ufs_bsg_remove(hba); + ufshpb_remove(hba); ufs_sysfs_remove_nodes(hba->dev); blk_cleanup_queue(hba->tmf_queue); blk_mq_free_tag_set(&hba->tmf_tag_set); diff --git a/drivers/scsi/ufs/ufshpb.c b/drivers/scsi/ufs/ufshpb.c index badb613ac281..37ae61fbf36a 100644 --- a/drivers/scsi/ufs/ufshpb.c +++ b/drivers/scsi/ufs/ufshpb.c @@ -16,11 +16,73 @@ #include "ufshpb.h" #include "../sd.h" +/* memory management */ +static struct kmem_cache *ufshpb_mctx_cache; +static mempool_t *ufshpb_mctx_pool; +static mempool_t *ufshpb_page_pool; +/* A cache size of 2MB can cache ppn in the 1GB range. */ +static unsigned int ufshpb_host_map_kbytes = 2048; +static int tot_active_srgn_pages; + +static struct workqueue_struct *ufshpb_wq; + bool ufshpb_is_allowed(struct ufs_hba *hba) { return !(hba->ufshpb_dev.hpb_disabled); } +static bool ufshpb_is_general_lun(int lun) +{ + return lun < UFS_UPIU_MAX_UNIT_NUM_ID; +} + +static bool +ufshpb_is_pinned_region(struct ufshpb_lu *hpb, int rgn_idx) +{ + if (hpb->lu_pinned_end != PINNED_NOT_SET && + rgn_idx >= hpb->lu_pinned_start && + rgn_idx <= hpb->lu_pinned_end) + return true; + + return false; +} + +static void ufshpb_kick_map_work(struct ufshpb_lu *hpb) +{ + bool ret = true; + unsigned long flags; + + spin_lock_irqsave(&hpb->rsp_list_lock, flags); + if (!list_empty(&hpb->lh_inact_rgn) || !list_empty(&hpb->lh_act_srgn)) + ret = false; + spin_unlock_irqrestore(&hpb->rsp_list_lock, flags); + + if (ret) + queue_work(ufshpb_wq, &hpb->map_work); +} + +static bool ufshpb_is_hpb_rsp_valid(struct ufs_hba *hba, + struct ufshcd_lrb *lrbp, + struct utp_hpb_rsp *rsp_field) +{ + if (be16_to_cpu(rsp_field->sense_data_len) != DEV_SENSE_SEG_LEN || + rsp_field->desc_type != DEV_DES_TYPE || + rsp_field->additional_len != DEV_ADDITIONAL_LEN || + rsp_field->hpb_op == HPB_RSP_NONE || + rsp_field->active_rgn_cnt > MAX_ACTIVE_NUM || + rsp_field->inactive_rgn_cnt > MAX_INACTIVE_NUM || + (!rsp_field->active_rgn_cnt && !rsp_field->inactive_rgn_cnt)) + return false; + + if (!ufshpb_is_general_lun(lrbp->lun)) { + dev_warn(hba->dev, "ufshpb: lun(%d) not supported\n", + lrbp->lun); + return false; + } + + return true; +} + static struct ufshpb_lu *ufshpb_get_hpb_data(struct scsi_device *sdev) { return sdev->hostdata; @@ -36,13 +98,741 @@ static void ufshpb_set_state(struct ufshpb_lu *hpb, int state) atomic_set(&hpb->hpb_state, state); } +static struct ufshpb_req *ufshpb_get_map_req(struct ufshpb_lu *hpb, + struct ufshpb_subregion *srgn) +{ + struct ufshpb_req *map_req; + struct request *req; + struct bio *bio; + + map_req = kmem_cache_alloc(hpb->map_req_cache, GFP_KERNEL); + if (!map_req) + return NULL; + + req = blk_get_request(hpb->sdev_ufs_lu->request_queue, + REQ_OP_SCSI_IN, 0); + if (IS_ERR(req)) + goto free_map_req; + + bio = bio_alloc(GFP_KERNEL, hpb->pages_per_srgn); + if (!bio) { + blk_put_request(req); + goto free_map_req; + } + + map_req->hpb = hpb; + map_req->req = req; + map_req->bio = bio; + + map_req->rgn_idx = srgn->rgn_idx; + map_req->srgn_idx = srgn->srgn_idx; + map_req->mctx = srgn->mctx; + + return map_req; + +free_map_req: + kmem_cache_free(hpb->map_req_cache, map_req); + return NULL; +} + +static void ufshpb_put_map_req(struct ufshpb_lu *hpb, + struct ufshpb_req *map_req) +{ + bio_put(map_req->bio); + blk_put_request(map_req->req); + kmem_cache_free(hpb->map_req_cache, map_req); +} + +static int ufshpb_clear_dirty_bitmap(struct ufshpb_lu *hpb, + struct ufshpb_subregion *srgn) +{ + WARN_ON(!srgn->mctx); + bitmap_zero(srgn->mctx->ppn_dirty, hpb->entries_per_srgn); + return 0; +} + +static void ufshpb_update_active_info(struct ufshpb_lu *hpb, int rgn_idx, + int srgn_idx) +{ + struct ufshpb_region *rgn; + struct ufshpb_subregion *srgn; + + rgn = hpb->rgn_tbl + rgn_idx; + srgn = rgn->srgn_tbl + srgn_idx; + + list_del_init(&rgn->list_inact_rgn); + + if (list_empty(&srgn->list_act_srgn)) + list_add_tail(&srgn->list_act_srgn, &hpb->lh_act_srgn); +} + +static void ufshpb_update_inactive_info(struct ufshpb_lu *hpb, int rgn_idx) +{ + struct ufshpb_region *rgn; + struct ufshpb_subregion *srgn; + int srgn_idx; + + rgn = hpb->rgn_tbl + rgn_idx; + + for_each_sub_region(rgn, srgn_idx, srgn) + list_del_init(&srgn->list_act_srgn); + + if (list_empty(&rgn->list_inact_rgn)) + list_add_tail(&rgn->list_inact_rgn, &hpb->lh_inact_rgn); +} + +static void ufshpb_activate_subregion(struct ufshpb_lu *hpb, + struct ufshpb_subregion *srgn) +{ + struct ufshpb_region *rgn; + + /* + * If there is no mctx in subregion + * after I/O progress for HPB_READ_BUFFER, the region to which the + * subregion belongs was evicted. + * Mask sure the region must not evict in I/O progress + */ + WARN_ON(!srgn->mctx); + + rgn = hpb->rgn_tbl + srgn->rgn_idx; + + if (unlikely(rgn->rgn_state == HPB_RGN_INACTIVE)) { + dev_err(&hpb->sdev_ufs_lu->sdev_dev, + "region %d subregion %d evicted\n", + srgn->rgn_idx, srgn->srgn_idx); + srgn->srgn_state = HPB_SRGN_INVALID; + return; + } + srgn->srgn_state = HPB_SRGN_VALID; +} + +static void ufshpb_map_req_compl_fn(struct request *req, blk_status_t error) +{ + struct ufshpb_req *map_req = (struct ufshpb_req *) req->end_io_data; + struct ufshpb_lu *hpb = map_req->hpb; + struct ufshpb_subregion *srgn; + unsigned long flags; + + srgn = hpb->rgn_tbl[map_req->rgn_idx].srgn_tbl + + map_req->srgn_idx; + + ufshpb_clear_dirty_bitmap(hpb, srgn); + spin_lock_irqsave(&hpb->rgn_state_lock, flags); + ufshpb_activate_subregion(hpb, srgn); + spin_unlock_irqrestore(&hpb->rgn_state_lock, flags); + + ufshpb_put_map_req(map_req->hpb, map_req); +} + +static void ufshpb_set_read_buf_cmd(unsigned char *cdb, int rgn_idx, + int srgn_idx, int srgn_mem_size) +{ + cdb[0] = UFSHPB_READ_BUFFER; + cdb[1] = UFSHPB_READ_BUFFER_ID; + + put_unaligned_be16(rgn_idx, &cdb[2]); + put_unaligned_be16(srgn_idx, &cdb[4]); + put_unaligned_be24(srgn_mem_size, &cdb[6]); + + cdb[9] = 0x00; +} + +static int ufshpb_execute_map_req(struct ufshpb_lu *hpb, + struct ufshpb_req *map_req) +{ + struct request_queue *q; + struct request *req; + struct scsi_request *rq; + int ret = 0; + int i; + + q = hpb->sdev_ufs_lu->request_queue; + for (i = 0; i < hpb->pages_per_srgn; i++) { + ret = bio_add_pc_page(q, map_req->bio, map_req->mctx->m_page[i], + PAGE_SIZE, 0); + if (ret != PAGE_SIZE) { + dev_err(&hpb->sdev_ufs_lu->sdev_dev, + "bio_add_pc_page fail %d - %d\n", + map_req->rgn_idx, map_req->srgn_idx); + return ret; + } + } + + req = map_req->req; + + blk_rq_append_bio(req, &map_req->bio); + + req->end_io_data = map_req; + + rq = scsi_req(req); + ufshpb_set_read_buf_cmd(rq->cmd, map_req->rgn_idx, + map_req->srgn_idx, hpb->srgn_mem_size); + rq->cmd_len = HPB_READ_BUFFER_CMD_LENGTH; + + blk_execute_rq_nowait(q, NULL, req, 1, ufshpb_map_req_compl_fn); + + hpb->stats.map_req_cnt++; + return 0; +} + +static struct ufshpb_map_ctx *ufshpb_get_map_ctx(struct ufshpb_lu *hpb) +{ + struct ufshpb_map_ctx *mctx; + int i, j; + + mctx = mempool_alloc(ufshpb_mctx_pool, GFP_KERNEL); + if (!mctx) + return NULL; + + mctx->m_page = kmem_cache_alloc(hpb->m_page_cache, GFP_KERNEL); + if (!mctx->m_page) + goto release_mctx; + + mctx->ppn_dirty = bitmap_zalloc(hpb->entries_per_srgn, GFP_KERNEL); + if (!mctx->ppn_dirty) + goto release_m_page; + + for (i = 0; i < hpb->pages_per_srgn; i++) { + mctx->m_page[i] = mempool_alloc(ufshpb_page_pool, GFP_KERNEL); + if (!mctx->m_page[i]) { + for (j = 0; j < i; j++) + mempool_free(mctx->m_page[j], ufshpb_page_pool); + goto release_ppn_dirty; + } + clear_page(page_address(mctx->m_page[i])); + } + + return mctx; + +release_ppn_dirty: + bitmap_free(mctx->ppn_dirty); +release_m_page: + kmem_cache_free(hpb->m_page_cache, mctx->m_page); +release_mctx: + mempool_free(mctx, ufshpb_mctx_pool); + return NULL; +} + +static void ufshpb_put_map_ctx(struct ufshpb_lu *hpb, + struct ufshpb_map_ctx *mctx) +{ + int i; + + for (i = 0; i < hpb->pages_per_srgn; i++) + mempool_free(mctx->m_page[i], ufshpb_page_pool); + + bitmap_free(mctx->ppn_dirty); + kmem_cache_free(hpb->m_page_cache, mctx->m_page); + mempool_free(mctx, ufshpb_mctx_pool); +} + +static int ufshpb_check_srgns_issue_state(struct ufshpb_lu *hpb, + struct ufshpb_region *rgn) +{ + struct ufshpb_subregion *srgn; + int srgn_idx; + + for_each_sub_region(rgn, srgn_idx, srgn) + if (srgn->srgn_state == HPB_SRGN_ISSUED) + return -EPERM; + + return 0; +} + +static void ufshpb_add_lru_info(struct victim_select_info *lru_info, + struct ufshpb_region *rgn) +{ + rgn->rgn_state = HPB_RGN_ACTIVE; + list_add_tail(&rgn->list_lru_rgn, &lru_info->lh_lru_rgn); + atomic_inc(&lru_info->active_cnt); +} + +static void ufshpb_hit_lru_info(struct victim_select_info *lru_info, + struct ufshpb_region *rgn) +{ + list_move_tail(&rgn->list_lru_rgn, &lru_info->lh_lru_rgn); +} + +static struct ufshpb_region *ufshpb_victim_lru_info(struct ufshpb_lu *hpb) +{ + struct victim_select_info *lru_info = &hpb->lru_info; + struct ufshpb_region *rgn, *victim_rgn = NULL; + + list_for_each_entry(rgn, &lru_info->lh_lru_rgn, list_lru_rgn) { + WARN_ON(!rgn); + if (ufshpb_check_srgns_issue_state(hpb, rgn)) + continue; + + victim_rgn = rgn; + break; + } + + return victim_rgn; +} + +static void ufshpb_cleanup_lru_info(struct victim_select_info *lru_info, + struct ufshpb_region *rgn) +{ + list_del_init(&rgn->list_lru_rgn); + rgn->rgn_state = HPB_RGN_INACTIVE; + atomic_dec(&lru_info->active_cnt); +} + +static void ufshpb_purge_active_subregion(struct ufshpb_lu *hpb, + struct ufshpb_subregion *srgn) +{ + if (srgn->srgn_state != HPB_SRGN_UNUSED) { + ufshpb_put_map_ctx(hpb, srgn->mctx); + srgn->srgn_state = HPB_SRGN_UNUSED; + srgn->mctx = NULL; + } +} + +static void __ufshpb_evict_region(struct ufshpb_lu *hpb, + struct ufshpb_region *rgn) +{ + struct victim_select_info *lru_info; + struct ufshpb_subregion *srgn; + int srgn_idx; + + lru_info = &hpb->lru_info; + + dev_dbg(&hpb->sdev_ufs_lu->sdev_dev, "evict region %d\n", rgn->rgn_idx); + + ufshpb_cleanup_lru_info(lru_info, rgn); + + for_each_sub_region(rgn, srgn_idx, srgn) + ufshpb_purge_active_subregion(hpb, srgn); +} + +static int ufshpb_evict_region(struct ufshpb_lu *hpb, struct ufshpb_region *rgn) +{ + unsigned long flags; + int ret = 0; + + spin_lock_irqsave(&hpb->rgn_state_lock, flags); + if (rgn->rgn_state == HPB_RGN_PINNED) { + dev_warn(&hpb->sdev_ufs_lu->sdev_dev, + "pinned region cannot drop-out. region %d\n", + rgn->rgn_idx); + goto out; + } + if (!list_empty(&rgn->list_lru_rgn)) { + if (ufshpb_check_srgns_issue_state(hpb, rgn)) { + ret = -EBUSY; + goto out; + } + + __ufshpb_evict_region(hpb, rgn); + } +out: + spin_unlock_irqrestore(&hpb->rgn_state_lock, flags); + return ret; +} + +static int ufshpb_issue_map_req(struct ufshpb_lu *hpb, + struct ufshpb_region *rgn, + struct ufshpb_subregion *srgn) +{ + struct ufshpb_req *map_req; + unsigned long flags; + int ret; + int err = -EAGAIN; + bool alloc_required = false; + enum HPB_SRGN_STATE state = HPB_SRGN_INVALID; + + spin_lock_irqsave(&hpb->rgn_state_lock, flags); + + if (ufshpb_get_state(hpb) != HPB_PRESENT) { + dev_notice(&hpb->sdev_ufs_lu->sdev_dev, + "%s: ufshpb state is not PRESENT\n", __func__); + goto unlock_out; + } + + if ((rgn->rgn_state == HPB_RGN_INACTIVE) && + (srgn->srgn_state == HPB_SRGN_INVALID)) { + err = 0; + goto unlock_out; + } + + if (srgn->srgn_state == HPB_SRGN_UNUSED) + alloc_required = true; + + /* + * If the subregion is already ISSUED state, + * a specific event (e.g., GC or wear-leveling, etc.) occurs in + * the device and HPB response for map loading is received. + * In this case, after finishing the HPB_READ_BUFFER, + * the next HPB_READ_BUFFER is performed again to obtain the latest + * map data. + */ + if (srgn->srgn_state == HPB_SRGN_ISSUED) + goto unlock_out; + + srgn->srgn_state = HPB_SRGN_ISSUED; + spin_unlock_irqrestore(&hpb->rgn_state_lock, flags); + + if (alloc_required) { + WARN_ON(srgn->mctx); + srgn->mctx = ufshpb_get_map_ctx(hpb); + if (!srgn->mctx) { + dev_err(&hpb->sdev_ufs_lu->sdev_dev, + "get map_ctx failed. region %d - %d\n", + rgn->rgn_idx, srgn->srgn_idx); + state = HPB_SRGN_UNUSED; + goto change_srgn_state; + } + } + + map_req = ufshpb_get_map_req(hpb, srgn); + if (!map_req) + goto change_srgn_state; + + + ret = ufshpb_execute_map_req(hpb, map_req); + if (ret) { + dev_err(&hpb->sdev_ufs_lu->sdev_dev, + "%s: issue map_req failed: %d, region %d - %d\n", + __func__, ret, srgn->rgn_idx, srgn->srgn_idx); + goto free_map_req; + } + return 0; + +free_map_req: + ufshpb_put_map_req(hpb, map_req); +change_srgn_state: + spin_lock_irqsave(&hpb->rgn_state_lock, flags); + srgn->srgn_state = state; +unlock_out: + spin_unlock_irqrestore(&hpb->rgn_state_lock, flags); + return err; +} + +static int ufshpb_add_region(struct ufshpb_lu *hpb, struct ufshpb_region *rgn) +{ + struct ufshpb_region *victim_rgn; + struct victim_select_info *lru_info = &hpb->lru_info; + unsigned long flags; + int ret = 0; + + spin_lock_irqsave(&hpb->rgn_state_lock, flags); + /* + * If region belongs to lru_list, just move the region + * to the front of lru list. because the state of the region + * is already active-state + */ + if (!list_empty(&rgn->list_lru_rgn)) { + ufshpb_hit_lru_info(lru_info, rgn); + goto out; + } + + if (rgn->rgn_state == HPB_RGN_INACTIVE) { + if (atomic_read(&lru_info->active_cnt) == + lru_info->max_lru_active_cnt) { + /* + * If the maximum number of active regions + * is exceeded, evict the least recently used region. + * This case may occur when the device responds + * to the eviction information late. + * It is okay to evict the least recently used region, + * because the device could detect this region + * by not issuing HPB_READ + */ + victim_rgn = ufshpb_victim_lru_info(hpb); + if (!victim_rgn) { + dev_warn(&hpb->sdev_ufs_lu->sdev_dev, + "cannot get victim region error\n"); + ret = -ENOMEM; + goto out; + } + + dev_dbg(&hpb->sdev_ufs_lu->sdev_dev, + "LRU full (%d), choose victim %d\n", + atomic_read(&lru_info->active_cnt), + victim_rgn->rgn_idx); + __ufshpb_evict_region(hpb, victim_rgn); + } + + /* + * When a region is added to lru_info list_head, + * it is guaranteed that the subregion has been + * assigned all mctx. If failed, try to receive mctx again + * without being added to lru_info list_head + */ + ufshpb_add_lru_info(lru_info, rgn); + } +out: + spin_unlock_irqrestore(&hpb->rgn_state_lock, flags); + return ret; +} + +static void ufshpb_rsp_req_region_update(struct ufshpb_lu *hpb, + struct utp_hpb_rsp *rsp_field) +{ + int i, rgn_idx, srgn_idx; + + BUILD_BUG_ON(sizeof(struct ufshpb_active_field) != HPB_ACT_FIELD_SIZE); + /* + * If the active region and the inactive region are the same, + * we will inactivate this region. + * The device could check this (region inactivated) and + * will response the proper active region information + */ + spin_lock(&hpb->rsp_list_lock); + for (i = 0; i < rsp_field->active_rgn_cnt; i++) { + rgn_idx = + be16_to_cpu(rsp_field->hpb_active_field[i].active_rgn); + srgn_idx = + be16_to_cpu(rsp_field->hpb_active_field[i].active_srgn); + + dev_dbg(&hpb->sdev_ufs_lu->sdev_dev, + "activate(%d) region %d - %d\n", i, rgn_idx, srgn_idx); + ufshpb_update_active_info(hpb, rgn_idx, srgn_idx); + hpb->stats.rb_active_cnt++; + } + + for (i = 0; i < rsp_field->inactive_rgn_cnt; i++) { + rgn_idx = be16_to_cpu(rsp_field->hpb_inactive_field[i]); + dev_dbg(&hpb->sdev_ufs_lu->sdev_dev, + "inactivate(%d) region %d\n", i, rgn_idx); + ufshpb_update_inactive_info(hpb, rgn_idx); + hpb->stats.rb_inactive_cnt++; + } + spin_unlock(&hpb->rsp_list_lock); + + dev_dbg(&hpb->sdev_ufs_lu->sdev_dev, "Noti: #ACT %u #INACT %u\n", + rsp_field->active_rgn_cnt, rsp_field->inactive_rgn_cnt); + + queue_work(ufshpb_wq, &hpb->map_work); +} + +/* + * This function will parse recommended active subregion information in sense + * data field of response UPIU with SAM_STAT_GOOD state. + */ +void ufshpb_rsp_upiu(struct ufs_hba *hba, struct ufshcd_lrb *lrbp) +{ + struct ufshpb_lu *hpb = ufshpb_get_hpb_data(lrbp->cmd->device); + struct utp_hpb_rsp *rsp_field; + int data_seg_len; + + if (!hpb) + return; + + if (ufshpb_get_state(hpb) != HPB_PRESENT) { + dev_notice(&hpb->sdev_ufs_lu->sdev_dev, + "%s: ufshpb state is not PRESENT\n", __func__); + return; + } + + data_seg_len = be32_to_cpu(lrbp->ucd_rsp_ptr->header.dword_2) + & MASK_RSP_UPIU_DATA_SEG_LEN; + + /* To flush remained rsp_list, we queue the map_work task */ + if (!data_seg_len) { + if (!ufshpb_is_general_lun(lrbp->lun)) + return; + + ufshpb_kick_map_work(hpb); + return; + } + + /* Check HPB_UPDATE_ALERT */ + if (!(lrbp->ucd_rsp_ptr->header.dword_2 & + UPIU_HEADER_DWORD(0, 2, 0, 0))) + return; + + rsp_field = &lrbp->ucd_rsp_ptr->hr; + BUILD_BUG_ON(sizeof(struct utp_hpb_rsp) != UTP_HPB_RSP_SIZE); + + if (!ufshpb_is_hpb_rsp_valid(hba, lrbp, rsp_field)) + return; + + hpb->stats.rb_noti_cnt++; + + switch (rsp_field->hpb_op) { + case HPB_RSP_NONE: + /* nothing to do */ + break; + case HPB_RSP_REQ_REGION_UPDATE: + WARN_ON(data_seg_len != DEV_DATA_SEG_LEN); + ufshpb_rsp_req_region_update(hpb, rsp_field); + break; + case HPB_RSP_DEV_RESET: + dev_warn(&hpb->sdev_ufs_lu->sdev_dev, + "UFS device lost HPB information during PM.\n"); + break; + default: + dev_notice(&hpb->sdev_ufs_lu->sdev_dev, + "hpb_op is not available: %d\n", + rsp_field->hpb_op); + break; + } +} + +static void ufshpb_add_active_list(struct ufshpb_lu *hpb, + struct ufshpb_region *rgn, + struct ufshpb_subregion *srgn) +{ + if (!list_empty(&rgn->list_inact_rgn)) + return; + + if (!list_empty(&srgn->list_act_srgn)) { + list_move(&srgn->list_act_srgn, &hpb->lh_act_srgn); + return; + } + + list_add(&srgn->list_act_srgn, &hpb->lh_act_srgn); +} + +static void ufshpb_add_pending_evict_list(struct ufshpb_lu *hpb, + struct ufshpb_region *rgn, + struct list_head *pending_list) +{ + struct ufshpb_subregion *srgn; + int srgn_idx; + + if (!list_empty(&rgn->list_inact_rgn)) + return; + + for_each_sub_region(rgn, srgn_idx, srgn) + if (!list_empty(&srgn->list_act_srgn)) + return; + + list_add_tail(&rgn->list_inact_rgn, pending_list); +} + +static void ufshpb_run_active_subregion_list(struct ufshpb_lu *hpb) +{ + struct ufshpb_region *rgn; + struct ufshpb_subregion *srgn; + unsigned long flags; + int ret = 0; + + spin_lock_irqsave(&hpb->rsp_list_lock, flags); + while ((srgn = list_first_entry_or_null(&hpb->lh_act_srgn, + struct ufshpb_subregion, + list_act_srgn))) { + if (ufshpb_get_state(hpb) == HPB_SUSPEND) + break; + + list_del_init(&srgn->list_act_srgn); + spin_unlock_irqrestore(&hpb->rsp_list_lock, flags); + + rgn = hpb->rgn_tbl + srgn->rgn_idx; + ret = ufshpb_add_region(hpb, rgn); + if (ret) + goto active_failed; + + ret = ufshpb_issue_map_req(hpb, rgn, srgn); + if (ret) { + dev_err(&hpb->sdev_ufs_lu->sdev_dev, + "issue map_req failed. ret %d, region %d - %d\n", + ret, rgn->rgn_idx, srgn->srgn_idx); + goto active_failed; + } + spin_lock_irqsave(&hpb->rsp_list_lock, flags); + } + spin_unlock_irqrestore(&hpb->rsp_list_lock, flags); + return; + +active_failed: + dev_err(&hpb->sdev_ufs_lu->sdev_dev, "failed to activate region %d - %d, will retry\n", + rgn->rgn_idx, srgn->srgn_idx); + spin_lock_irqsave(&hpb->rsp_list_lock, flags); + ufshpb_add_active_list(hpb, rgn, srgn); + spin_unlock_irqrestore(&hpb->rsp_list_lock, flags); +} + +static void ufshpb_run_inactive_region_list(struct ufshpb_lu *hpb) +{ + struct ufshpb_region *rgn; + unsigned long flags; + int ret; + LIST_HEAD(pending_list); + + spin_lock_irqsave(&hpb->rsp_list_lock, flags); + while ((rgn = list_first_entry_or_null(&hpb->lh_inact_rgn, + struct ufshpb_region, + list_inact_rgn))) { + if (ufshpb_get_state(hpb) == HPB_SUSPEND) + break; + + list_del_init(&rgn->list_inact_rgn); + spin_unlock_irqrestore(&hpb->rsp_list_lock, flags); + + ret = ufshpb_evict_region(hpb, rgn); + if (ret) { + spin_lock_irqsave(&hpb->rsp_list_lock, flags); + ufshpb_add_pending_evict_list(hpb, rgn, &pending_list); + spin_unlock_irqrestore(&hpb->rsp_list_lock, flags); + } + + spin_lock_irqsave(&hpb->rsp_list_lock, flags); + } + + list_splice(&pending_list, &hpb->lh_inact_rgn); + spin_unlock_irqrestore(&hpb->rsp_list_lock, flags); +} + +static void ufshpb_map_work_handler(struct work_struct *work) +{ + struct ufshpb_lu *hpb = container_of(work, struct ufshpb_lu, map_work); + + if (ufshpb_get_state(hpb) != HPB_PRESENT) { + dev_notice(&hpb->sdev_ufs_lu->sdev_dev, + "%s: ufshpb state is not PRESENT\n", __func__); + return; + } + + ufshpb_run_inactive_region_list(hpb); + ufshpb_run_active_subregion_list(hpb); +} + +/* + * this function doesn't need to hold lock due to be called in init. + * (rgn_state_lock, rsp_list_lock, etc..) + */ +static int ufshpb_init_pinned_active_region(struct ufs_hba *hba, + struct ufshpb_lu *hpb, + struct ufshpb_region *rgn) +{ + struct ufshpb_subregion *srgn; + int srgn_idx, i; + int err = 0; + + for_each_sub_region(rgn, srgn_idx, srgn) { + srgn->mctx = ufshpb_get_map_ctx(hpb); + srgn->srgn_state = HPB_SRGN_INVALID; + if (!srgn->mctx) { + err = -ENOMEM; + dev_err(hba->dev, + "alloc mctx for pinned region failed\n"); + goto release; + } + + list_add_tail(&srgn->list_act_srgn, &hpb->lh_act_srgn); + } + + rgn->rgn_state = HPB_RGN_PINNED; + return 0; + +release: + for (i = 0; i < srgn_idx; i++) { + srgn = rgn->srgn_tbl + i; + ufshpb_put_map_ctx(hpb, srgn->mctx); + } + return err; +} + static void ufshpb_init_subregion_tbl(struct ufshpb_lu *hpb, struct ufshpb_region *rgn) { int srgn_idx; + struct ufshpb_subregion *srgn; - for (srgn_idx = 0; srgn_idx < rgn->srgn_cnt; srgn_idx++) { - struct ufshpb_subregion *srgn = rgn->srgn_tbl + srgn_idx; + for_each_sub_region(rgn, srgn_idx, srgn) { + INIT_LIST_HEAD(&srgn->list_act_srgn); srgn->rgn_idx = rgn->rgn_idx; srgn->srgn_idx = srgn_idx; @@ -75,6 +865,8 @@ static void ufshpb_lu_parameter_init(struct ufs_hba *hba, hpb->lu_pinned_end = hpb_lu_info->num_pinned ? (hpb_lu_info->pinned_start + hpb_lu_info->num_pinned - 1) : PINNED_NOT_SET; + hpb->lru_info.max_lru_active_cnt = + hpb_lu_info->max_active_rgns - hpb_lu_info->num_pinned; rgn_mem_size = (1ULL << hpb_dev_info->rgn_size) * HPB_RGN_SIZE_UNIT * HPB_ENTRY_SIZE; @@ -123,6 +915,9 @@ static int ufshpb_alloc_region_tbl(struct ufs_hba *hba, struct ufshpb_lu *hpb) rgn = rgn_table + rgn_idx; rgn->rgn_idx = rgn_idx; + INIT_LIST_HEAD(&rgn->list_inact_rgn); + INIT_LIST_HEAD(&rgn->list_lru_rgn); + if (rgn_idx == hpb->rgns_per_lu - 1) srgn_cnt = ((hpb->srgns_per_lu - 1) % hpb->srgns_per_rgn) + 1; @@ -132,7 +927,13 @@ static int ufshpb_alloc_region_tbl(struct ufs_hba *hba, struct ufshpb_lu *hpb) goto release_srgn_table; ufshpb_init_subregion_tbl(hpb, rgn); - rgn->rgn_state = HPB_RGN_INACTIVE; + if (ufshpb_is_pinned_region(hpb, rgn_idx)) { + ret = ufshpb_init_pinned_active_region(hba, hpb, rgn); + if (ret) + goto release_srgn_table; + } else { + rgn->rgn_state = HPB_RGN_INACTIVE; + } } return 0; @@ -151,13 +952,13 @@ static void ufshpb_destroy_subregion_tbl(struct ufshpb_lu *hpb, struct ufshpb_region *rgn) { int srgn_idx; + struct ufshpb_subregion *srgn; - for (srgn_idx = 0; srgn_idx < rgn->srgn_cnt; srgn_idx++) { - struct ufshpb_subregion *srgn; - - srgn = rgn->srgn_tbl + srgn_idx; - srgn->srgn_state = HPB_SRGN_UNUSED; - } + for_each_sub_region(rgn, srgn_idx, srgn) + if (srgn->srgn_state != HPB_SRGN_UNUSED) { + srgn->srgn_state = HPB_SRGN_UNUSED; + ufshpb_put_map_ctx(hpb, srgn->mctx); + } } static void ufshpb_destroy_region_tbl(struct ufshpb_lu *hpb) @@ -229,11 +1030,47 @@ static int ufshpb_lu_hpb_init(struct ufs_hba *hba, struct ufshpb_lu *hpb) { int ret; + spin_lock_init(&hpb->rgn_state_lock); + spin_lock_init(&hpb->rsp_list_lock); + + INIT_LIST_HEAD(&hpb->lru_info.lh_lru_rgn); + INIT_LIST_HEAD(&hpb->lh_act_srgn); + INIT_LIST_HEAD(&hpb->lh_inact_rgn); + INIT_LIST_HEAD(&hpb->list_hpb_lu); + + INIT_WORK(&hpb->map_work, ufshpb_map_work_handler); + + hpb->map_req_cache = kmem_cache_create("ufshpb_req_cache", + sizeof(struct ufshpb_req), 0, 0, NULL); + if (!hpb->map_req_cache) { + dev_err(hba->dev, "ufshpb(%d) ufshpb_req_cache create fail", + hpb->lun); + return -ENOMEM; + } + + hpb->m_page_cache = kmem_cache_create("ufshpb_m_page_cache", + sizeof(struct page *) * hpb->pages_per_srgn, + 0, 0, NULL); + if (!hpb->m_page_cache) { + dev_err(hba->dev, "ufshpb(%d) ufshpb_m_page_cache create fail", + hpb->lun); + ret = -ENOMEM; + goto release_req_cache; + } + ret = ufshpb_alloc_region_tbl(hba, hpb); + if (ret) + goto release_m_page_cache; ufshpb_stat_init(hpb); return 0; + +release_m_page_cache: + kmem_cache_destroy(hpb->m_page_cache); +release_req_cache: + kmem_cache_destroy(hpb->map_req_cache); + return ret; } static struct ufshpb_lu *ufshpb_alloc_hpb_lu(struct ufs_hba *hba, int lun, @@ -264,6 +1101,33 @@ static struct ufshpb_lu *ufshpb_alloc_hpb_lu(struct ufs_hba *hba, int lun, return NULL; } +static void ufshpb_discard_rsp_lists(struct ufshpb_lu *hpb) +{ + struct ufshpb_region *rgn, *next_rgn; + struct ufshpb_subregion *srgn, *next_srgn; + unsigned long flags; + + /* + * If the device reset occurred, the remained HPB region information + * may be stale. Therefore, by dicarding the lists of HPB response + * that remained after reset, it prevents unnecessary work. + */ + spin_lock_irqsave(&hpb->rsp_list_lock, flags); + list_for_each_entry_safe(rgn, next_rgn, &hpb->lh_inact_rgn, + list_inact_rgn) + list_del_init(&rgn->list_inact_rgn); + + list_for_each_entry_safe(srgn, next_srgn, &hpb->lh_act_srgn, + list_act_srgn) + list_del_init(&srgn->list_act_srgn); + spin_unlock_irqrestore(&hpb->rsp_list_lock, flags); +} + +static void ufshpb_cancel_jobs(struct ufshpb_lu *hpb) +{ + cancel_work_sync(&hpb->map_work); +} + static bool ufshpb_check_hpb_reset_query(struct ufs_hba *hba) { int err = 0; @@ -307,7 +1171,7 @@ void ufshpb_reset(struct ufs_hba *hba) struct scsi_device *sdev; shost_for_each_device(sdev, hba->host) { - hpb = sdev->hostdata; + hpb = ufshpb_get_hpb_data(sdev); if (!hpb) continue; @@ -324,13 +1188,15 @@ void ufshpb_reset_host(struct ufs_hba *hba) struct scsi_device *sdev; shost_for_each_device(sdev, hba->host) { - hpb = sdev->hostdata; + hpb = ufshpb_get_hpb_data(sdev); if (!hpb) continue; if (ufshpb_get_state(hpb) != HPB_PRESENT) continue; ufshpb_set_state(hpb, HPB_RESET); + ufshpb_cancel_jobs(hpb); + ufshpb_discard_rsp_lists(hpb); } } @@ -340,13 +1206,14 @@ void ufshpb_suspend(struct ufs_hba *hba) struct scsi_device *sdev; shost_for_each_device(sdev, hba->host) { - hpb = sdev->hostdata; + hpb = ufshpb_get_hpb_data(sdev); if (!hpb) continue; if (ufshpb_get_state(hpb) != HPB_PRESENT) continue; ufshpb_set_state(hpb, HPB_SUSPEND); + ufshpb_cancel_jobs(hpb); } } @@ -356,7 +1223,7 @@ void ufshpb_resume(struct ufs_hba *hba) struct scsi_device *sdev; shost_for_each_device(sdev, hba->host) { - hpb = sdev->hostdata; + hpb = ufshpb_get_hpb_data(sdev); if (!hpb) continue; @@ -364,6 +1231,7 @@ void ufshpb_resume(struct ufs_hba *hba) (ufshpb_get_state(hpb) != HPB_SUSPEND)) continue; ufshpb_set_state(hpb, HPB_PRESENT); + ufshpb_kick_map_work(hpb); } } @@ -416,7 +1284,7 @@ static int ufshpb_get_lu_info(struct ufs_hba *hba, int lun, void ufshpb_destroy_lu(struct ufs_hba *hba, struct scsi_device *sdev) { - struct ufshpb_lu *hpb = sdev->hostdata; + struct ufshpb_lu *hpb = ufshpb_get_hpb_data(sdev); if (!hpb) return; @@ -426,8 +1294,13 @@ void ufshpb_destroy_lu(struct ufs_hba *hba, struct scsi_device *sdev) sdev = hpb->sdev_ufs_lu; sdev->hostdata = NULL; + ufshpb_cancel_jobs(hpb); + ufshpb_destroy_region_tbl(hpb); + kmem_cache_destroy(hpb->map_req_cache); + kmem_cache_destroy(hpb->m_page_cache); + list_del_init(&hpb->list_hpb_lu); kfree(hpb); @@ -435,24 +1308,41 @@ void ufshpb_destroy_lu(struct ufs_hba *hba, struct scsi_device *sdev) static void ufshpb_hpb_lu_prepared(struct ufs_hba *hba) { + int pool_size; struct ufshpb_lu *hpb; struct scsi_device *sdev; bool init_success; + if (tot_active_srgn_pages == 0) { + ufshpb_remove(hba); + return; + } + init_success = !ufshpb_check_hpb_reset_query(hba); + pool_size = PAGE_ALIGN(ufshpb_host_map_kbytes * 1024) / PAGE_SIZE; + if (pool_size > tot_active_srgn_pages) { + mempool_resize(ufshpb_mctx_pool, tot_active_srgn_pages); + mempool_resize(ufshpb_page_pool, tot_active_srgn_pages); + } + shost_for_each_device(sdev, hba->host) { - hpb = sdev->hostdata; + hpb = ufshpb_get_hpb_data(sdev); if (!hpb) continue; if (init_success) { ufshpb_set_state(hpb, HPB_PRESENT); + if ((hpb->lu_pinned_end - hpb->lu_pinned_start) > 0) + queue_work(ufshpb_wq, &hpb->map_work); } else { dev_err(hba->dev, "destroy HPB lu %d\n", hpb->lun); ufshpb_destroy_lu(hba, sdev); } } + + if (!init_success) + ufshpb_remove(hba); } void ufshpb_init_hpb_lu(struct ufs_hba *hba, struct scsi_device *sdev) @@ -474,6 +1364,9 @@ void ufshpb_init_hpb_lu(struct ufs_hba *hba, struct scsi_device *sdev) if (!hpb) goto out; + tot_active_srgn_pages += hpb_lu_info.max_active_rgns * + hpb->srgns_per_rgn * hpb->pages_per_srgn; + hpb->sdev_ufs_lu = sdev; sdev->hostdata = hpb; @@ -483,6 +1376,57 @@ void ufshpb_init_hpb_lu(struct ufs_hba *hba, struct scsi_device *sdev) ufshpb_hpb_lu_prepared(hba); } +static int ufshpb_init_mem_wq(void) +{ + int ret; + unsigned int pool_size; + + ufshpb_mctx_cache = kmem_cache_create("ufshpb_mctx_cache", + sizeof(struct ufshpb_map_ctx), + 0, 0, NULL); + if (!ufshpb_mctx_cache) { + pr_err("ufshpb: cannot init mctx cache\n"); + return -ENOMEM; + } + + pool_size = PAGE_ALIGN(ufshpb_host_map_kbytes * 1024) / PAGE_SIZE; + pr_info("%s:%d ufshpb_host_map_kbytes %u pool_size %u\n", + __func__, __LINE__, ufshpb_host_map_kbytes, pool_size); + + ufshpb_mctx_pool = mempool_create_slab_pool(pool_size, + ufshpb_mctx_cache); + if (!ufshpb_mctx_pool) { + pr_err("ufshpb: cannot init mctx pool\n"); + ret = -ENOMEM; + goto release_mctx_cache; + } + + ufshpb_page_pool = mempool_create_page_pool(pool_size, 0); + if (!ufshpb_page_pool) { + pr_err("ufshpb: cannot init page pool\n"); + ret = -ENOMEM; + goto release_mctx_pool; + } + + ufshpb_wq = alloc_workqueue("ufshpb-wq", + WQ_UNBOUND | WQ_MEM_RECLAIM, 0); + if (!ufshpb_wq) { + pr_err("ufshpb: alloc workqueue failed\n"); + ret = -ENOMEM; + goto release_page_pool; + } + + return 0; + +release_page_pool: + mempool_destroy(ufshpb_page_pool); +release_mctx_pool: + mempool_destroy(ufshpb_mctx_pool); +release_mctx_cache: + kmem_cache_destroy(ufshpb_mctx_cache); + return ret; +} + void ufshpb_get_geo_info(struct ufs_hba *hba, u8 *geo_buf) { struct ufshpb_dev_info *hpb_dev_info = &hba->ufshpb_dev; @@ -548,7 +1492,13 @@ void ufshpb_init(struct ufs_hba *hba) if (!ufshpb_is_allowed(hba)) return; + if (ufshpb_init_mem_wq()) { + hpb_dev_info->hpb_disabled = true; + return; + } + atomic_set(&hpb_dev_info->slave_conf_cnt, hpb_dev_info->num_lu); + tot_active_srgn_pages = 0; /* issue HPB reset query */ for (try = 0; try < HPB_RESET_REQ_RETRIES; try++) { ret = ufshcd_query_flag(hba, UPIU_QUERY_OPCODE_SET_FLAG, @@ -557,3 +1507,16 @@ void ufshpb_init(struct ufs_hba *hba) break; } } + +void ufshpb_remove(struct ufs_hba *hba) +{ + mempool_destroy(ufshpb_page_pool); + mempool_destroy(ufshpb_mctx_pool); + kmem_cache_destroy(ufshpb_mctx_cache); + + destroy_workqueue(ufshpb_wq); +} + +module_param(ufshpb_host_map_kbytes, uint, 0644); +MODULE_PARM_DESC(ufshpb_host_map_kbytes, + "ufshpb host mapping memory kilo-bytes for ufshpb memory-pool"); diff --git a/drivers/scsi/ufs/ufshpb.h b/drivers/scsi/ufs/ufshpb.h index 50523821cac8..e40b016971ac 100644 --- a/drivers/scsi/ufs/ufshpb.h +++ b/drivers/scsi/ufs/ufshpb.h @@ -83,10 +83,19 @@ struct ufshpb_lu_info { int max_active_rgns; }; +struct ufshpb_map_ctx { + struct page **m_page; + unsigned long *ppn_dirty; +}; + struct ufshpb_subregion { + struct ufshpb_map_ctx *mctx; enum HPB_SRGN_STATE srgn_state; int rgn_idx; int srgn_idx; + + /* below information is used by rsp_list */ + struct list_head list_act_srgn; }; struct ufshpb_region { @@ -94,6 +103,43 @@ struct ufshpb_region { enum HPB_RGN_STATE rgn_state; int rgn_idx; int srgn_cnt; + + /* below information is used by rsp_list */ + struct list_head list_inact_rgn; + + /* below information is used by lru */ + struct list_head list_lru_rgn; +}; + +#define for_each_sub_region(rgn, i, srgn) \ + for ((i) = 0; \ + ((i) < (rgn)->srgn_cnt) && ((srgn) = &(rgn)->srgn_tbl[i]); \ + (i)++) + +/** + * struct ufshpb_req - UFSHPB READ BUFFER (for caching map) request structure + * @req: block layer request for READ BUFFER + * @bio: bio for holding map page + * @hpb: ufshpb_lu structure that related to the L2P map + * @mctx: L2P map information + * @rgn_idx: target region index + * @srgn_idx: target sub-region index + * @lun: target logical unit number + */ +struct ufshpb_req { + struct request *req; + struct bio *bio; + struct ufshpb_lu *hpb; + struct ufshpb_map_ctx *mctx; + + unsigned int rgn_idx; + unsigned int srgn_idx; +}; + +struct victim_select_info { + struct list_head lh_lru_rgn; /* LRU list of regions */ + int max_lru_active_cnt; /* supported hpb #region - pinned #region */ + atomic_t active_cnt; }; struct ufshpb_stats { @@ -108,10 +154,22 @@ struct ufshpb_stats { struct ufshpb_lu { int lun; struct scsi_device *sdev_ufs_lu; + + spinlock_t rgn_state_lock; /* for protect rgn/srgn state */ struct ufshpb_region *rgn_tbl; atomic_t hpb_state; + spinlock_t rsp_list_lock; + struct list_head lh_act_srgn; /* hold rsp_list_lock */ + struct list_head lh_inact_rgn; /* hold rsp_list_lock */ + + /* cached L2P map management worker */ + struct work_struct map_work; + + /* for selecting victim */ + struct victim_select_info lru_info; + /* pinned region information */ u32 lu_pinned_start; u32 lu_pinned_end; @@ -130,6 +188,9 @@ struct ufshpb_lu { struct ufshpb_stats stats; + struct kmem_cache *map_req_cache; + struct kmem_cache *m_page_cache; + struct list_head list_hpb_lu; }; @@ -137,6 +198,7 @@ struct ufs_hba; struct ufshcd_lrb; #ifndef CONFIG_SCSI_UFS_HPB +static void ufshpb_rsp_upiu(struct ufs_hba *hba, struct ufshcd_lrb *lrbp) {} static void ufshpb_resume(struct ufs_hba *hba) {} static void ufshpb_suspend(struct ufs_hba *hba) {} static void ufshpb_reset(struct ufs_hba *hba) {} @@ -144,10 +206,12 @@ static void ufshpb_reset_host(struct ufs_hba *hba) {} static void ufshpb_init(struct ufs_hba *hba) {} static void ufshpb_init_hpb_lu(struct ufs_hba *hba, struct scsi_device *sdev) {} static void ufshpb_destroy_lu(struct ufs_hba *hba, struct scsi_device *sdev) {} +static void ufshpb_remove(struct ufs_hba *hba) {} static bool ufshpb_is_allowed(struct ufs_hba *hba) { return false; } static void ufshpb_get_geo_info(struct ufs_hba *hba, u8 *geo_buf) {} static void ufshpb_get_dev_info(struct ufs_hba *hba, u8 *desc_buf) {} #else +void ufshpb_rsp_upiu(struct ufs_hba *hba, struct ufshcd_lrb *lrbp); void ufshpb_resume(struct ufs_hba *hba); void ufshpb_suspend(struct ufs_hba *hba); void ufshpb_reset(struct ufs_hba *hba); @@ -155,6 +219,7 @@ void ufshpb_reset_host(struct ufs_hba *hba); void ufshpb_init(struct ufs_hba *hba); void ufshpb_init_hpb_lu(struct ufs_hba *hba, struct scsi_device *sdev); void ufshpb_destroy_lu(struct ufs_hba *hba, struct scsi_device *sdev); +void ufshpb_remove(struct ufs_hba *hba); bool ufshpb_is_allowed(struct ufs_hba *hba); void ufshpb_get_geo_info(struct ufs_hba *hba, u8 *geo_buf); void ufshpb_get_dev_info(struct ufs_hba *hba, u8 *desc_buf); From bb4850ec573f186c47e497de4064da2e0cd3df12 Mon Sep 17 00:00:00 2001 From: Daejun Park Date: Tue, 22 Dec 2020 10:58:54 +0900 Subject: [PATCH 03/11] scsi: ufs: Prepare HPB read for cached sub-region This patch changes the read I/O to the HPB read I/O. If the logical address of the read I/O belongs to active sub-region, the HPB driver modifies the read I/O command to HPB read. It modifies the UPIU command of UFS instead of modifying the existing SCSI command. In the HPB version 1.0, the maximum read I/O size that can be converted to HPB read is 4KB. The dirty map of the active sub-region prevents an incorrect HPB read that has stale physical page number which is updated by previous write I/O. Reviewed-by: Can Guo Reviewed-by: Bart Van Assche Acked-by: Avri Altman Tested-by: Bean Huo Signed-off-by: Daejun Park --- drivers/scsi/ufs/ufshcd.c | 2 + drivers/scsi/ufs/ufshpb.c | 232 ++++++++++++++++++++++++++++++++++++++ drivers/scsi/ufs/ufshpb.h | 2 + 3 files changed, 236 insertions(+) diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index 51bb62686e3b..a7a38ae23d6f 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -2653,6 +2653,8 @@ static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd) ufshcd_comp_scsi_upiu(hba, lrbp); + ufshpb_prep(hba, lrbp); + err = ufshcd_map_sg(hba, lrbp); if (err) { lrbp->cmd = NULL; diff --git a/drivers/scsi/ufs/ufshpb.c b/drivers/scsi/ufs/ufshpb.c index 37ae61fbf36a..d3e6c5b32328 100644 --- a/drivers/scsi/ufs/ufshpb.c +++ b/drivers/scsi/ufs/ufshpb.c @@ -31,6 +31,29 @@ bool ufshpb_is_allowed(struct ufs_hba *hba) return !(hba->ufshpb_dev.hpb_disabled); } +static int ufshpb_is_valid_srgn(struct ufshpb_region *rgn, + struct ufshpb_subregion *srgn) +{ + return rgn->rgn_state != HPB_RGN_INACTIVE && + srgn->srgn_state == HPB_SRGN_VALID; +} + +static bool ufshpb_is_read_cmd(struct scsi_cmnd *cmd) +{ + return req_op(cmd->request) == REQ_OP_READ; +} + +static bool ufshpb_is_write_or_discard_cmd(struct scsi_cmnd *cmd) +{ + return op_is_write(req_op(cmd->request)) || + op_is_discard(req_op(cmd->request)); +} + +static bool ufshpb_is_support_chunk(int transfer_len) +{ + return transfer_len <= HPB_MULTI_CHUNK_HIGH; +} + static bool ufshpb_is_general_lun(int lun) { return lun < UFS_UPIU_MAX_UNIT_NUM_ID; @@ -98,6 +121,215 @@ static void ufshpb_set_state(struct ufshpb_lu *hpb, int state) atomic_set(&hpb->hpb_state, state); } +static void ufshpb_set_ppn_dirty(struct ufshpb_lu *hpb, int rgn_idx, + int srgn_idx, int srgn_offset, int cnt) +{ + struct ufshpb_region *rgn; + struct ufshpb_subregion *srgn; + int set_bit_len; + int bitmap_len = hpb->entries_per_srgn; + +next_srgn: + rgn = hpb->rgn_tbl + rgn_idx; + srgn = rgn->srgn_tbl + srgn_idx; + + if ((srgn_offset + cnt) > bitmap_len) + set_bit_len = bitmap_len - srgn_offset; + else + set_bit_len = cnt; + + if (rgn->rgn_state != HPB_RGN_INACTIVE && + srgn->srgn_state == HPB_SRGN_VALID) + bitmap_set(srgn->mctx->ppn_dirty, srgn_offset, set_bit_len); + + srgn_offset = 0; + if (++srgn_idx == hpb->srgns_per_rgn) { + srgn_idx = 0; + rgn_idx++; + } + + cnt -= set_bit_len; + if (cnt > 0) + goto next_srgn; + + WARN_ON(cnt < 0); +} + +static bool ufshpb_test_ppn_dirty(struct ufshpb_lu *hpb, int rgn_idx, + int srgn_idx, int srgn_offset, int cnt) +{ + struct ufshpb_region *rgn; + struct ufshpb_subregion *srgn; + int bitmap_len = hpb->entries_per_srgn; + int bit_len; + +next_srgn: + rgn = hpb->rgn_tbl + rgn_idx; + srgn = rgn->srgn_tbl + srgn_idx; + + if (!ufshpb_is_valid_srgn(rgn, srgn)) + return true; + + /* + * If the region state is active, mctx must be allocated. + * In this case, check whether the region is evicted or + * mctx allcation fail. + */ + WARN_ON(!srgn->mctx); + + if ((srgn_offset + cnt) > bitmap_len) + bit_len = bitmap_len - srgn_offset; + else + bit_len = cnt; + + if (find_next_bit(srgn->mctx->ppn_dirty, + bit_len, srgn_offset) >= srgn_offset) + return true; + + srgn_offset = 0; + if (++srgn_idx == hpb->srgns_per_rgn) { + srgn_idx = 0; + rgn_idx++; + } + + cnt -= bit_len; + if (cnt > 0) + goto next_srgn; + + return false; +} + +static u64 ufshpb_get_ppn(struct ufshpb_lu *hpb, + struct ufshpb_map_ctx *mctx, int pos, int *error) +{ + u64 *ppn_table; + struct page *page; + int index, offset; + + index = pos / (PAGE_SIZE / HPB_ENTRY_SIZE); + offset = pos % (PAGE_SIZE / HPB_ENTRY_SIZE); + + page = mctx->m_page[index]; + if (unlikely(!page)) { + *error = -ENOMEM; + dev_err(&hpb->sdev_ufs_lu->sdev_dev, + "error. cannot find page in mctx\n"); + return 0; + } + + ppn_table = page_address(page); + if (unlikely(!ppn_table)) { + *error = -ENOMEM; + dev_err(&hpb->sdev_ufs_lu->sdev_dev, + "error. cannot get ppn_table\n"); + return 0; + } + + return ppn_table[offset]; +} + +static void +ufshpb_get_pos_from_lpn(struct ufshpb_lu *hpb, unsigned long lpn, int *rgn_idx, + int *srgn_idx, int *offset) +{ + int rgn_offset; + + *rgn_idx = lpn >> hpb->entries_per_rgn_shift; + rgn_offset = lpn & hpb->entries_per_rgn_mask; + *srgn_idx = rgn_offset >> hpb->entries_per_srgn_shift; + *offset = rgn_offset & hpb->entries_per_srgn_mask; +} + +static void +ufshpb_set_hpb_read_to_upiu(struct ufshpb_lu *hpb, struct ufshcd_lrb *lrbp, + u32 lpn, u64 ppn, unsigned int transfer_len) +{ + unsigned char *cdb = lrbp->ucd_req_ptr->sc.cdb; + + cdb[0] = UFSHPB_READ; + + put_unaligned_be64(ppn, &cdb[6]); + cdb[14] = transfer_len; +} + +/* + * This function will set up HPB read command using host-side L2P map data. + * In HPB v1.0, maximum size of HPB read command is 4KB. + */ +void ufshpb_prep(struct ufs_hba *hba, struct ufshcd_lrb *lrbp) +{ + struct ufshpb_lu *hpb; + struct ufshpb_region *rgn; + struct ufshpb_subregion *srgn; + struct scsi_cmnd *cmd = lrbp->cmd; + u32 lpn; + u64 ppn; + unsigned long flags; + int transfer_len, rgn_idx, srgn_idx, srgn_offset; + int err = 0; + + hpb = ufshpb_get_hpb_data(cmd->device); + if (!hpb) + return; + + if (ufshpb_get_state(hpb) != HPB_PRESENT) { + dev_notice(&hpb->sdev_ufs_lu->sdev_dev, + "%s: ufshpb state is not PRESENT", __func__); + return; + } + + if (!ufshpb_is_write_or_discard_cmd(cmd) && + !ufshpb_is_read_cmd(cmd)) + return; + + transfer_len = sectors_to_logical(cmd->device, blk_rq_sectors(cmd->request)); + if (unlikely(!transfer_len)) + return; + + lpn = sectors_to_logical(cmd->device, blk_rq_pos(cmd->request)); + ufshpb_get_pos_from_lpn(hpb, lpn, &rgn_idx, &srgn_idx, &srgn_offset); + rgn = hpb->rgn_tbl + rgn_idx; + srgn = rgn->srgn_tbl + srgn_idx; + + /* If command type is WRITE or DISCARD, set bitmap as drity */ + if (ufshpb_is_write_or_discard_cmd(cmd)) { + spin_lock_irqsave(&hpb->rgn_state_lock, flags); + ufshpb_set_ppn_dirty(hpb, rgn_idx, srgn_idx, srgn_offset, + transfer_len); + spin_unlock_irqrestore(&hpb->rgn_state_lock, flags); + return; + } + + if (!ufshpb_is_support_chunk(transfer_len)) + return; + + spin_lock_irqsave(&hpb->rgn_state_lock, flags); + if (ufshpb_test_ppn_dirty(hpb, rgn_idx, srgn_idx, srgn_offset, + transfer_len)) { + hpb->stats.miss_cnt++; + spin_unlock_irqrestore(&hpb->rgn_state_lock, flags); + return; + } + + ppn = ufshpb_get_ppn(hpb, srgn->mctx, srgn_offset, &err); + spin_unlock_irqrestore(&hpb->rgn_state_lock, flags); + if (unlikely(err)) { + /* + * In this case, the region state is active, + * but the ppn table is not allocated. + * Make sure that ppn table must be allocated on + * active state. + */ + WARN_ON(true); + dev_err(hba->dev, "ufshpb_get_ppn failed. err %d\n", err); + return; + } + + ufshpb_set_hpb_read_to_upiu(hpb, lrbp, lpn, ppn, transfer_len); + + hpb->stats.hit_cnt++; +} + static struct ufshpb_req *ufshpb_get_map_req(struct ufshpb_lu *hpb, struct ufshpb_subregion *srgn) { diff --git a/drivers/scsi/ufs/ufshpb.h b/drivers/scsi/ufs/ufshpb.h index e40b016971ac..2c43a03b66b6 100644 --- a/drivers/scsi/ufs/ufshpb.h +++ b/drivers/scsi/ufs/ufshpb.h @@ -198,6 +198,7 @@ struct ufs_hba; struct ufshcd_lrb; #ifndef CONFIG_SCSI_UFS_HPB +static void ufshpb_prep(struct ufs_hba *hba, struct ufshcd_lrb *lrbp) {} static void ufshpb_rsp_upiu(struct ufs_hba *hba, struct ufshcd_lrb *lrbp) {} static void ufshpb_resume(struct ufs_hba *hba) {} static void ufshpb_suspend(struct ufs_hba *hba) {} @@ -211,6 +212,7 @@ static bool ufshpb_is_allowed(struct ufs_hba *hba) { return false; } static void ufshpb_get_geo_info(struct ufs_hba *hba, u8 *geo_buf) {} static void ufshpb_get_dev_info(struct ufs_hba *hba, u8 *desc_buf) {} #else +void ufshpb_prep(struct ufs_hba *hba, struct ufshcd_lrb *lrbp); void ufshpb_rsp_upiu(struct ufs_hba *hba, struct ufshcd_lrb *lrbp); void ufshpb_resume(struct ufs_hba *hba); void ufshpb_suspend(struct ufs_hba *hba); From 59a604355b76ca12d7a07041138616f0e91e7f79 Mon Sep 17 00:00:00 2001 From: Avri Altman Date: Wed, 2 Sep 2020 12:32:14 +0300 Subject: [PATCH 04/11] scsi: ufshpb: Cache HPB Control mode on init We will use it later, when we'll need to differentiate between device and host control modes. Signed-off-by: Avri Altman --- drivers/scsi/ufs/ufshpb.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/scsi/ufs/ufshpb.c b/drivers/scsi/ufs/ufshpb.c index d3e6c5b32328..183bdf35f2d0 100644 --- a/drivers/scsi/ufs/ufshpb.c +++ b/drivers/scsi/ufs/ufshpb.c @@ -26,6 +26,8 @@ static int tot_active_srgn_pages; static struct workqueue_struct *ufshpb_wq; +static enum UFSHPB_MODE ufshpb_mode; + bool ufshpb_is_allowed(struct ufs_hba *hba) { return !(hba->ufshpb_dev.hpb_disabled); @@ -1690,10 +1692,9 @@ void ufshpb_get_dev_info(struct ufs_hba *hba, u8 *desc_buf) { struct ufshpb_dev_info *hpb_dev_info = &hba->ufshpb_dev; int version; - u8 hpb_mode; - hpb_mode = desc_buf[DEVICE_DESC_PARAM_HPB_CONTROL]; - if (hpb_mode == HPB_HOST_CONTROL) { + ufshpb_mode = desc_buf[DEVICE_DESC_PARAM_HPB_CONTROL]; + if (ufshpb_mode == HPB_HOST_CONTROL) { dev_err(hba->dev, "%s: host control mode is not supported.\n", __func__); hpb_dev_info->hpb_disabled = true; From cd2ca4d178421cf41a7a3af7e9893fc5b21220c7 Mon Sep 17 00:00:00 2001 From: Avri Altman Date: Sun, 28 Jun 2020 15:50:28 +0300 Subject: [PATCH 05/11] scsi: ufshpb: Add host control mode support to rsp_upiu There are some limitations to activations / inactivations in host control mode - Add those. Signed-off-by: Avri Altman --- drivers/scsi/ufs/ufshpb.c | 35 +++++++++++++++++++++++++++++++++++ drivers/scsi/ufs/ufshpb.h | 6 ++++++ 2 files changed, 41 insertions(+) diff --git a/drivers/scsi/ufs/ufshpb.c b/drivers/scsi/ufs/ufshpb.c index 183bdf35f2d0..5fa1f5bc08e6 100644 --- a/drivers/scsi/ufs/ufshpb.c +++ b/drivers/scsi/ufs/ufshpb.c @@ -140,6 +140,8 @@ static void ufshpb_set_ppn_dirty(struct ufshpb_lu *hpb, int rgn_idx, else set_bit_len = cnt; + set_bit(RGN_FLAG_DIRTY, &rgn->rgn_flags); + if (rgn->rgn_state != HPB_RGN_INACTIVE && srgn->srgn_state == HPB_SRGN_VALID) bitmap_set(srgn->mctx->ppn_dirty, srgn_offset, set_bit_len); @@ -201,6 +203,11 @@ static bool ufshpb_test_ppn_dirty(struct ufshpb_lu *hpb, int rgn_idx, return false; } +static inline bool is_rgn_dirty(struct ufshpb_region *rgn) +{ + return test_bit(RGN_FLAG_DIRTY, &rgn->rgn_flags); +} + static u64 ufshpb_get_ppn(struct ufshpb_lu *hpb, struct ufshpb_map_ctx *mctx, int pos, int *error) { @@ -380,8 +387,12 @@ static void ufshpb_put_map_req(struct ufshpb_lu *hpb, static int ufshpb_clear_dirty_bitmap(struct ufshpb_lu *hpb, struct ufshpb_subregion *srgn) { + struct ufshpb_region *rgn; + WARN_ON(!srgn->mctx); bitmap_zero(srgn->mctx->ppn_dirty, hpb->entries_per_srgn); + rgn = hpb->rgn_tbl + srgn->rgn_idx; + clear_bit(RGN_FLAG_DIRTY, &rgn->rgn_flags); return 0; } @@ -814,17 +825,39 @@ static void ufshpb_rsp_req_region_update(struct ufshpb_lu *hpb, */ spin_lock(&hpb->rsp_list_lock); for (i = 0; i < rsp_field->active_rgn_cnt; i++) { + struct ufshpb_region *rgn; + rgn_idx = be16_to_cpu(rsp_field->hpb_active_field[i].active_rgn); srgn_idx = be16_to_cpu(rsp_field->hpb_active_field[i].active_srgn); + rgn = hpb->rgn_tbl + rgn_idx; + if (ufshpb_mode == HPB_HOST_CONTROL && + (rgn->rgn_state != HPB_RGN_ACTIVE || is_rgn_dirty(rgn))) { + /* + * in host control mode, subregion activation + * recommendations are only allowed to active regions. + * Also, ignore recommendations for dirty regions - the + * host will make decisions concerning those by himself + */ + continue; + } + dev_dbg(&hpb->sdev_ufs_lu->sdev_dev, "activate(%d) region %d - %d\n", i, rgn_idx, srgn_idx); ufshpb_update_active_info(hpb, rgn_idx, srgn_idx); hpb->stats.rb_active_cnt++; } + if (ufshpb_mode == HPB_HOST_CONTROL) { + /* + * in host control mode the device is not allowed to inactivate + * regions + */ + goto out_unlock; + } + for (i = 0; i < rsp_field->inactive_rgn_cnt; i++) { rgn_idx = be16_to_cpu(rsp_field->hpb_inactive_field[i]); dev_dbg(&hpb->sdev_ufs_lu->sdev_dev, @@ -832,6 +865,8 @@ static void ufshpb_rsp_req_region_update(struct ufshpb_lu *hpb, ufshpb_update_inactive_info(hpb, rgn_idx); hpb->stats.rb_inactive_cnt++; } + +out_unlock: spin_unlock(&hpb->rsp_list_lock); dev_dbg(&hpb->sdev_ufs_lu->sdev_dev, "Noti: #ACT %u #INACT %u\n", diff --git a/drivers/scsi/ufs/ufshpb.h b/drivers/scsi/ufs/ufshpb.h index 2c43a03b66b6..8a34b0f42754 100644 --- a/drivers/scsi/ufs/ufshpb.h +++ b/drivers/scsi/ufs/ufshpb.h @@ -48,6 +48,11 @@ enum UFSHPB_MODE { HPB_DEVICE_CONTROL, }; +enum HPB_RGN_FLAGS { + RGN_FLAG_UPDATE = 0, + RGN_FLAG_DIRTY, +}; + enum UFSHPB_STATE { HPB_PRESENT = 1, HPB_SUSPEND, @@ -109,6 +114,7 @@ struct ufshpb_region { /* below information is used by lru */ struct list_head list_lru_rgn; + unsigned long rgn_flags; }; #define for_each_sub_region(rgn, i, srgn) \ From 4c8ccb7fa153dbe80bf668f4c32f6d3e854079b3 Mon Sep 17 00:00:00 2001 From: Avri Altman Date: Tue, 30 Jun 2020 11:07:08 +0300 Subject: [PATCH 06/11] scsi: ufshpb: Add region's reads counter MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In host control mode, reads are the major source of activation trials. Keep track of those reads counters, for both active as well inactive regions. We reset the read counter upon write - we are only interested in "clean" reads. less intuitive however, is that we also reset it upon region's deactivation. Region deactivation is often due to the fact that eviction took place: a region become active on the expense of another. This is happening when the max-active-regions limit has crossed. If we don’t reset the counter, we will trigger a lot of trashing of the HPB database, since few reads (or even one) to the region that was deactivated, will trigger a re-activation trial. Keep those counters normalized, as we are using those reads as a comparative score, to make various decisions. If during consecutive normalizations an active region has exhaust its reads - inactivate it. Signed-off-by: Avri Altman --- drivers/scsi/ufs/ufshpb.c | 96 +++++++++++++++++++++++++++++++++------ drivers/scsi/ufs/ufshpb.h | 5 ++ 2 files changed, 86 insertions(+), 15 deletions(-) diff --git a/drivers/scsi/ufs/ufshpb.c b/drivers/scsi/ufs/ufshpb.c index 5fa1f5bc08e6..51c3607166bc 100644 --- a/drivers/scsi/ufs/ufshpb.c +++ b/drivers/scsi/ufs/ufshpb.c @@ -16,6 +16,9 @@ #include "ufshpb.h" #include "../sd.h" +#define WORK_PENDING 0 +#define ACTIVATION_THRSHLD 4 /* 4 IOs */ + /* memory management */ static struct kmem_cache *ufshpb_mctx_cache; static mempool_t *ufshpb_mctx_pool; @@ -261,6 +264,21 @@ ufshpb_set_hpb_read_to_upiu(struct ufshpb_lu *hpb, struct ufshcd_lrb *lrbp, cdb[14] = transfer_len; } +static void ufshpb_update_active_info(struct ufshpb_lu *hpb, int rgn_idx, + int srgn_idx) +{ + struct ufshpb_region *rgn; + struct ufshpb_subregion *srgn; + + rgn = hpb->rgn_tbl + rgn_idx; + srgn = rgn->srgn_tbl + srgn_idx; + + list_del_init(&rgn->list_inact_rgn); + + if (list_empty(&srgn->list_act_srgn)) + list_add_tail(&srgn->list_act_srgn, &hpb->lh_act_srgn); +} + /* * This function will set up HPB read command using host-side L2P map data. * In HPB v1.0, maximum size of HPB read command is 4KB. @@ -276,6 +294,7 @@ void ufshpb_prep(struct ufs_hba *hba, struct ufshcd_lrb *lrbp) unsigned long flags; int transfer_len, rgn_idx, srgn_idx, srgn_offset; int err = 0; + u64 reads; hpb = ufshpb_get_hpb_data(cmd->device); if (!hpb) @@ -306,12 +325,39 @@ void ufshpb_prep(struct ufs_hba *hba, struct ufshcd_lrb *lrbp) ufshpb_set_ppn_dirty(hpb, rgn_idx, srgn_idx, srgn_offset, transfer_len); spin_unlock_irqrestore(&hpb->rgn_state_lock, flags); + + if (ufshpb_mode == HPB_HOST_CONTROL) + atomic64_set(&rgn->reads, 0); + return; } + if (ufshpb_mode == HPB_HOST_CONTROL) + reads = atomic64_inc_return(&rgn->reads); + if (!ufshpb_is_support_chunk(transfer_len)) return; + if (ufshpb_mode == HPB_HOST_CONTROL) { + /* + * in host control mode, reads are the main source for + * activation trials. + */ + if (reads == ACTIVATION_THRSHLD) { + spin_lock_irqsave(&hpb->rsp_list_lock, flags); + ufshpb_update_active_info(hpb, rgn_idx, srgn_idx); + hpb->stats.rb_active_cnt++; + spin_unlock_irqrestore(&hpb->rsp_list_lock, flags); + dev_dbg(&hpb->sdev_ufs_lu->sdev_dev, + "activate region %d-%d\n", rgn_idx, srgn_idx); + } + + /* keep those counters normalized */ + if (reads > hpb->entries_per_srgn && + !test_and_set_bit(WORK_PENDING, &hpb->work_data_bits)) + schedule_work(&hpb->ufshpb_normalization_work); + } + spin_lock_irqsave(&hpb->rgn_state_lock, flags); if (ufshpb_test_ppn_dirty(hpb, rgn_idx, srgn_idx, srgn_offset, transfer_len)) { @@ -396,21 +442,6 @@ static int ufshpb_clear_dirty_bitmap(struct ufshpb_lu *hpb, return 0; } -static void ufshpb_update_active_info(struct ufshpb_lu *hpb, int rgn_idx, - int srgn_idx) -{ - struct ufshpb_region *rgn; - struct ufshpb_subregion *srgn; - - rgn = hpb->rgn_tbl + rgn_idx; - srgn = rgn->srgn_tbl + srgn_idx; - - list_del_init(&rgn->list_inact_rgn); - - if (list_empty(&srgn->list_act_srgn)) - list_add_tail(&srgn->list_act_srgn, &hpb->lh_act_srgn); -} - static void ufshpb_update_inactive_info(struct ufshpb_lu *hpb, int rgn_idx) { struct ufshpb_region *rgn; @@ -646,6 +677,9 @@ static void __ufshpb_evict_region(struct ufshpb_lu *hpb, ufshpb_cleanup_lru_info(lru_info, rgn); + if (ufshpb_mode == HPB_HOST_CONTROL) + atomic64_set(&rgn->reads, 0); + for_each_sub_region(rgn, srgn_idx, srgn) ufshpb_purge_active_subregion(hpb, srgn); } @@ -1044,6 +1078,33 @@ static void ufshpb_run_inactive_region_list(struct ufshpb_lu *hpb) spin_unlock_irqrestore(&hpb->rsp_list_lock, flags); } +static void ufshpb_normalization_work_handler(struct work_struct *work) +{ + struct ufshpb_lu *hpb; + int rgn_idx; + + hpb = container_of(work, struct ufshpb_lu, ufshpb_normalization_work); + + for (rgn_idx = 0; rgn_idx < hpb->rgns_per_lu; rgn_idx++) { + struct ufshpb_region *rgn = hpb->rgn_tbl + rgn_idx; + u64 reads = atomic64_read(&rgn->reads); + + if (reads) + atomic64_set(&rgn->reads, reads >> 1); + + if (rgn->rgn_state != HPB_RGN_ACTIVE || + atomic64_read(&rgn->reads)) + continue; + + /* if region is active but has no reads - inactivate it */ + spin_lock(&hpb->rsp_list_lock); + ufshpb_update_inactive_info(hpb, rgn->rgn_idx); + spin_unlock(&hpb->rsp_list_lock); + } + + clear_bit(WORK_PENDING, &hpb->work_data_bits); +} + static void ufshpb_map_work_handler(struct work_struct *work) { struct ufshpb_lu *hpb = container_of(work, struct ufshpb_lu, map_work); @@ -1308,6 +1369,9 @@ static int ufshpb_lu_hpb_init(struct ufs_hba *hba, struct ufshpb_lu *hpb) INIT_LIST_HEAD(&hpb->list_hpb_lu); INIT_WORK(&hpb->map_work, ufshpb_map_work_handler); + if (ufshpb_mode == HPB_HOST_CONTROL) + INIT_WORK(&hpb->ufshpb_normalization_work, + ufshpb_normalization_work_handler); hpb->map_req_cache = kmem_cache_create("ufshpb_req_cache", sizeof(struct ufshpb_req), 0, 0, NULL); @@ -1394,6 +1458,8 @@ static void ufshpb_discard_rsp_lists(struct ufshpb_lu *hpb) static void ufshpb_cancel_jobs(struct ufshpb_lu *hpb) { + if (ufshpb_mode == HPB_HOST_CONTROL) + cancel_work_sync(&hpb->ufshpb_normalization_work); cancel_work_sync(&hpb->map_work); } diff --git a/drivers/scsi/ufs/ufshpb.h b/drivers/scsi/ufs/ufshpb.h index 8a34b0f42754..b0e78728af38 100644 --- a/drivers/scsi/ufs/ufshpb.h +++ b/drivers/scsi/ufs/ufshpb.h @@ -115,6 +115,9 @@ struct ufshpb_region { /* below information is used by lru */ struct list_head list_lru_rgn; unsigned long rgn_flags; + + /* region reads - for host mode */ + atomic64_t reads; }; #define for_each_sub_region(rgn, i, srgn) \ @@ -175,6 +178,8 @@ struct ufshpb_lu { /* for selecting victim */ struct victim_select_info lru_info; + struct work_struct ufshpb_normalization_work; + unsigned long work_data_bits; /* pinned region information */ u32 lu_pinned_start; From 2fb54cd186e71d8662888023f64632f4dbcd28c3 Mon Sep 17 00:00:00 2001 From: Avri Altman Date: Tue, 30 Jun 2020 13:13:02 +0300 Subject: [PATCH 07/11] scsi: ufshpb: Make eviction depends on region's reads In host mode, eviction is considered an extreme measure. verify that the entering region has enough reads, and the exiting region has much less reads. Signed-off-by: Avri Altman --- drivers/scsi/ufs/ufshpb.c | 44 ++++++++++++++++++++++++++++++++++++--- 1 file changed, 41 insertions(+), 3 deletions(-) diff --git a/drivers/scsi/ufs/ufshpb.c b/drivers/scsi/ufs/ufshpb.c index 51c3607166bc..a16c0f2d5fac 100644 --- a/drivers/scsi/ufs/ufshpb.c +++ b/drivers/scsi/ufs/ufshpb.c @@ -18,6 +18,7 @@ #define WORK_PENDING 0 #define ACTIVATION_THRSHLD 4 /* 4 IOs */ +#define EVICTION_THRSHLD (ACTIVATION_THRSHLD << 6) /* 256 IOs */ /* memory management */ static struct kmem_cache *ufshpb_mctx_cache; @@ -639,6 +640,14 @@ static struct ufshpb_region *ufshpb_victim_lru_info(struct ufshpb_lu *hpb) if (ufshpb_check_srgns_issue_state(hpb, rgn)) continue; + /* + * in host control mode, verify that the exiting region + * has less reads + */ + if (ufshpb_mode == HPB_HOST_CONTROL && + atomic64_read(&rgn->reads) > (EVICTION_THRSHLD >> 1)) + continue; + victim_rgn = rgn; break; } @@ -789,7 +798,7 @@ static int ufshpb_issue_map_req(struct ufshpb_lu *hpb, static int ufshpb_add_region(struct ufshpb_lu *hpb, struct ufshpb_region *rgn) { - struct ufshpb_region *victim_rgn; + struct ufshpb_region *victim_rgn = NULL; struct victim_select_info *lru_info = &hpb->lru_info; unsigned long flags; int ret = 0; @@ -817,6 +826,17 @@ static int ufshpb_add_region(struct ufshpb_lu *hpb, struct ufshpb_region *rgn) * because the device could detect this region * by not issuing HPB_READ */ + + /* + * in host control mode, verify that the entering + * region has enough reads + */ + if (ufshpb_mode == HPB_HOST_CONTROL && + atomic64_read(&rgn->reads) < EVICTION_THRSHLD) { + ret = -EACCES; + goto out; + } + victim_rgn = ufshpb_victim_lru_info(hpb); if (!victim_rgn) { dev_warn(&hpb->sdev_ufs_lu->sdev_dev, @@ -1024,8 +1044,13 @@ static void ufshpb_run_active_subregion_list(struct ufshpb_lu *hpb) rgn = hpb->rgn_tbl + srgn->rgn_idx; ret = ufshpb_add_region(hpb, rgn); - if (ret) - goto active_failed; + if (ret) { + if (ret == -EACCES) { + spin_lock_irqsave(&hpb->rsp_list_lock, flags); + continue; + } + goto add_region_failed; + } ret = ufshpb_issue_map_req(hpb, rgn, srgn); if (ret) { @@ -1039,9 +1064,22 @@ static void ufshpb_run_active_subregion_list(struct ufshpb_lu *hpb) spin_unlock_irqrestore(&hpb->rsp_list_lock, flags); return; +add_region_failed: + if (ufshpb_mode == HPB_HOST_CONTROL) { + /* + * In host control mode, it is common that eviction trials + * fail, either because the entering region didn't have enough + * reads, or a poor-performing exiting region wasn't found. + * No need to re-insert those regions to the "to-be-activated" + * list. + */ + return; + } + active_failed: dev_err(&hpb->sdev_ufs_lu->sdev_dev, "failed to activate region %d - %d, will retry\n", rgn->rgn_idx, srgn->srgn_idx); + spin_lock_irqsave(&hpb->rsp_list_lock, flags); ufshpb_add_active_list(hpb, rgn, srgn); spin_unlock_irqrestore(&hpb->rsp_list_lock, flags); From 2323497df3aaad6c0917c7be4b7e5ea6c0b7447b Mon Sep 17 00:00:00 2001 From: Avri Altman Date: Tue, 30 Jun 2020 15:14:31 +0300 Subject: [PATCH 08/11] scsi: ufshpb: Region inactivation in host mode I host mode, the host is expected to send HPB-WRITE-BUFFER with buffer-id = 0x1 when it inactivates a region. Use the map-requests pool as there is no point in assigning a designated cache for umap-requests. Signed-off-by: Avri Altman --- drivers/scsi/ufs/ufshpb.c | 120 +++++++++++++++++++++++++++++++------- drivers/scsi/ufs/ufshpb.h | 4 ++ 2 files changed, 104 insertions(+), 20 deletions(-) diff --git a/drivers/scsi/ufs/ufshpb.c b/drivers/scsi/ufs/ufshpb.c index a16c0f2d5fac..c09c8dce0745 100644 --- a/drivers/scsi/ufs/ufshpb.c +++ b/drivers/scsi/ufs/ufshpb.c @@ -386,49 +386,66 @@ void ufshpb_prep(struct ufs_hba *hba, struct ufshcd_lrb *lrbp) hpb->stats.hit_cnt++; } +static struct ufshpb_req *ufshpb_get_req(struct ufshpb_lu *hpb, + int rgn_idx, enum req_opf dir) +{ + struct ufshpb_req *rq; + struct request *req; + + rq = kmem_cache_alloc(hpb->map_req_cache, GFP_KERNEL); + if (!rq) + return NULL; + + req = blk_get_request(hpb->sdev_ufs_lu->request_queue, + dir, 0); + if (IS_ERR(req)) + goto free_rq; + + rq->hpb = hpb; + rq->req = req; + rq->rgn_idx = rgn_idx; + + return rq; + +free_rq: + kmem_cache_free(hpb->map_req_cache, rq); + return NULL; +} + +static void ufshpb_put_req(struct ufshpb_lu *hpb, struct ufshpb_req *rq) +{ + blk_put_request(rq->req); + kmem_cache_free(hpb->map_req_cache, rq); +} + static struct ufshpb_req *ufshpb_get_map_req(struct ufshpb_lu *hpb, struct ufshpb_subregion *srgn) { struct ufshpb_req *map_req; - struct request *req; struct bio *bio; - map_req = kmem_cache_alloc(hpb->map_req_cache, GFP_KERNEL); + map_req = ufshpb_get_req(hpb, srgn->rgn_idx, REQ_OP_SCSI_IN); if (!map_req) return NULL; - req = blk_get_request(hpb->sdev_ufs_lu->request_queue, - REQ_OP_SCSI_IN, 0); - if (IS_ERR(req)) - goto free_map_req; - bio = bio_alloc(GFP_KERNEL, hpb->pages_per_srgn); if (!bio) { - blk_put_request(req); - goto free_map_req; + ufshpb_put_req(hpb, map_req); + return NULL; } - map_req->hpb = hpb; - map_req->req = req; map_req->bio = bio; - - map_req->rgn_idx = srgn->rgn_idx; map_req->srgn_idx = srgn->srgn_idx; map_req->mctx = srgn->mctx; return map_req; - -free_map_req: - kmem_cache_free(hpb->map_req_cache, map_req); - return NULL; } static void ufshpb_put_map_req(struct ufshpb_lu *hpb, - struct ufshpb_req *map_req) + struct ufshpb_req *map_req) { bio_put(map_req->bio); - blk_put_request(map_req->req); - kmem_cache_free(hpb->map_req_cache, map_req); + ufshpb_put_req(hpb, map_req); } static int ufshpb_clear_dirty_bitmap(struct ufshpb_lu *hpb, @@ -483,6 +500,13 @@ static void ufshpb_activate_subregion(struct ufshpb_lu *hpb, srgn->srgn_state = HPB_SRGN_VALID; } +static void ufshpb_umap_req_compl_fn(struct request *req, blk_status_t error) +{ + struct ufshpb_req *umap_req = (struct ufshpb_req *)req->end_io_data; + + ufshpb_put_req(umap_req->hpb, umap_req); +} + static void ufshpb_map_req_compl_fn(struct request *req, blk_status_t error) { struct ufshpb_req *map_req = (struct ufshpb_req *) req->end_io_data; @@ -501,6 +525,14 @@ static void ufshpb_map_req_compl_fn(struct request *req, blk_status_t error) ufshpb_put_map_req(map_req->hpb, map_req); } +static void ufshpb_set_write_buf_cmd(unsigned char *cdb, int rgn_idx) +{ + cdb[0] = UFSHPB_WRITE_BUFFER; + cdb[1] = UFSHPB_WRITE_BUFFER_ID; + put_unaligned_be16(rgn_idx, &cdb[2]); + cdb[9] = 0x00; +} + static void ufshpb_set_read_buf_cmd(unsigned char *cdb, int rgn_idx, int srgn_idx, int srgn_mem_size) { @@ -514,6 +546,27 @@ static void ufshpb_set_read_buf_cmd(unsigned char *cdb, int rgn_idx, cdb[9] = 0x00; } +static int ufshpb_execute_umap_req(struct ufshpb_lu *hpb, + struct ufshpb_req *umap_req) +{ + struct request_queue *q; + struct request *req; + struct scsi_request *rq; + + q = hpb->sdev_ufs_lu->request_queue; + req = umap_req->req; + req->timeout = 0; + req->end_io_data = (void *)umap_req; + rq = scsi_req(req); + ufshpb_set_write_buf_cmd(rq->cmd, umap_req->rgn_idx); + rq->cmd_len = HPB_WRITE_BUFFER_CMD_LENGTH; + + blk_execute_rq_nowait(q, NULL, req, 1, ufshpb_umap_req_compl_fn); + + hpb->stats.umap_req_cnt++; + return 0; +} + static int ufshpb_execute_map_req(struct ufshpb_lu *hpb, struct ufshpb_req *map_req) { @@ -673,6 +726,25 @@ static void ufshpb_purge_active_subregion(struct ufshpb_lu *hpb, } } +static int ufshpb_issue_umap_req(struct ufshpb_lu *hpb, + struct ufshpb_region *rgn) +{ + struct ufshpb_req *umap_req; + + umap_req = ufshpb_get_req(hpb, rgn->rgn_idx, REQ_OP_SCSI_OUT); + if (!umap_req) + return -ENOMEM; + + if (ufshpb_execute_umap_req(hpb, umap_req)) + goto free_umap_req; + + return 0; + +free_umap_req: + ufshpb_put_req(hpb, umap_req); + return -EAGAIN; +} + static void __ufshpb_evict_region(struct ufshpb_lu *hpb, struct ufshpb_region *rgn) { @@ -680,6 +752,11 @@ static void __ufshpb_evict_region(struct ufshpb_lu *hpb, struct ufshpb_subregion *srgn; int srgn_idx; + + if (ufshpb_mode == HPB_HOST_CONTROL && + ufshpb_issue_umap_req(hpb, rgn)) + return; + lru_info = &hpb->lru_info; dev_dbg(&hpb->sdev_ufs_lu->sdev_dev, "evict region %d\n", rgn->rgn_idx); @@ -1368,6 +1445,7 @@ ufshpb_sysfs_attr_show_func(rb_noti_cnt); ufshpb_sysfs_attr_show_func(rb_active_cnt); ufshpb_sysfs_attr_show_func(rb_inactive_cnt); ufshpb_sysfs_attr_show_func(map_req_cnt); +ufshpb_sysfs_attr_show_func(umap_req_cnt); static struct attribute *hpb_dev_attrs[] = { &dev_attr_hit_cnt.attr, @@ -1376,6 +1454,7 @@ static struct attribute *hpb_dev_attrs[] = { &dev_attr_rb_active_cnt.attr, &dev_attr_rb_inactive_cnt.attr, &dev_attr_map_req_cnt.attr, + &dev_attr_umap_req_cnt.attr, NULL, }; @@ -1392,6 +1471,7 @@ static void ufshpb_stat_init(struct ufshpb_lu *hpb) hpb->stats.rb_active_cnt = 0; hpb->stats.rb_inactive_cnt = 0; hpb->stats.map_req_cnt = 0; + hpb->stats.umap_req_cnt = 0; } static int ufshpb_lu_hpb_init(struct ufs_hba *hba, struct ufshpb_lu *hpb) diff --git a/drivers/scsi/ufs/ufshpb.h b/drivers/scsi/ufs/ufshpb.h index b0e78728af38..47a8877f9cdb 100644 --- a/drivers/scsi/ufs/ufshpb.h +++ b/drivers/scsi/ufs/ufshpb.h @@ -35,8 +35,11 @@ /* hpb vender defined opcode */ #define UFSHPB_READ 0xF8 #define UFSHPB_READ_BUFFER 0xF9 +#define UFSHPB_WRITE_BUFFER 0xFA #define UFSHPB_READ_BUFFER_ID 0x01 +#define UFSHPB_WRITE_BUFFER_ID 0x01 #define HPB_READ_BUFFER_CMD_LENGTH 10 +#define HPB_WRITE_BUFFER_CMD_LENGTH 10 #define LU_ENABLED_HPB_FUNC 0x02 #define HPB_RESET_REQ_RETRIES 10 @@ -158,6 +161,7 @@ struct ufshpb_stats { u64 rb_active_cnt; u64 rb_inactive_cnt; u64 map_req_cnt; + u64 umap_req_cnt; }; struct ufshpb_lu { From 5ba625108427f11419acf4f1c82a818fc90abece Mon Sep 17 00:00:00 2001 From: Avri Altman Date: Wed, 3 Jun 2020 18:01:07 +0300 Subject: [PATCH 09/11] scsi: ufshpb: Add hpb dev reset response The spec does not define what is the host's recommended response when the device send hpb dev reset response (oper 0x2). We will update all active hpb regions: mark them and do that on the next read. Signed-off-by: Avri Altman --- drivers/scsi/ufs/ufshpb.c | 55 ++++++++++++++++++++++++++++++++++++--- drivers/scsi/ufs/ufshpb.h | 1 + 2 files changed, 53 insertions(+), 3 deletions(-) diff --git a/drivers/scsi/ufs/ufshpb.c b/drivers/scsi/ufs/ufshpb.c index c09c8dce0745..cb99b57b4319 100644 --- a/drivers/scsi/ufs/ufshpb.c +++ b/drivers/scsi/ufs/ufshpb.c @@ -17,6 +17,7 @@ #include "../sd.h" #define WORK_PENDING 0 +#define RESET_PENDING 1 #define ACTIVATION_THRSHLD 4 /* 4 IOs */ #define EVICTION_THRSHLD (ACTIVATION_THRSHLD << 6) /* 256 IOs */ @@ -344,7 +345,8 @@ void ufshpb_prep(struct ufs_hba *hba, struct ufshcd_lrb *lrbp) * in host control mode, reads are the main source for * activation trials. */ - if (reads == ACTIVATION_THRSHLD) { + if (reads == ACTIVATION_THRSHLD || + test_and_clear_bit(RGN_FLAG_UPDATE, &rgn->rgn_flags)) { spin_lock_irqsave(&hpb->rsp_list_lock, flags); ufshpb_update_active_info(hpb, rgn_idx, srgn_idx); hpb->stats.rb_active_cnt++; @@ -1061,6 +1063,24 @@ void ufshpb_rsp_upiu(struct ufs_hba *hba, struct ufshcd_lrb *lrbp) case HPB_RSP_DEV_RESET: dev_warn(&hpb->sdev_ufs_lu->sdev_dev, "UFS device lost HPB information during PM.\n"); + + if (ufshpb_mode == HPB_HOST_CONTROL) { + struct ufshpb_lu *h; + struct scsi_device *sdev; + + shost_for_each_device(sdev, hba->host) { + h = sdev->hostdata; + if (!h) + continue; + + if (test_and_set_bit(RESET_PENDING, + &h->work_data_bits)) + continue; + + schedule_work(&h->ufshpb_lun_reset_work); + } + } + break; default: dev_notice(&hpb->sdev_ufs_lu->sdev_dev, @@ -1193,6 +1213,28 @@ static void ufshpb_run_inactive_region_list(struct ufshpb_lu *hpb) spin_unlock_irqrestore(&hpb->rsp_list_lock, flags); } +static void ufshpb_reset_work_handler(struct work_struct *work) +{ + struct ufshpb_lu *hpb; + struct victim_select_info *lru_info; + struct ufshpb_region *rgn, *next_rgn; + unsigned long flags; + + hpb = container_of(work, struct ufshpb_lu, ufshpb_lun_reset_work); + + lru_info = &hpb->lru_info; + + spin_lock_irqsave(&hpb->rgn_state_lock, flags); + + list_for_each_entry_safe(rgn, next_rgn, &lru_info->lh_lru_rgn, + list_lru_rgn) + set_bit(RGN_FLAG_UPDATE, &rgn->rgn_flags); + + spin_unlock_irqrestore(&hpb->rgn_state_lock, flags); + + clear_bit(RESET_PENDING, &hpb->work_data_bits); +} + static void ufshpb_normalization_work_handler(struct work_struct *work) { struct ufshpb_lu *hpb; @@ -1379,6 +1421,8 @@ static int ufshpb_alloc_region_tbl(struct ufs_hba *hba, struct ufshpb_lu *hpb) } else { rgn->rgn_state = HPB_RGN_INACTIVE; } + + rgn->rgn_flags = 0; } return 0; @@ -1487,9 +1531,12 @@ static int ufshpb_lu_hpb_init(struct ufs_hba *hba, struct ufshpb_lu *hpb) INIT_LIST_HEAD(&hpb->list_hpb_lu); INIT_WORK(&hpb->map_work, ufshpb_map_work_handler); - if (ufshpb_mode == HPB_HOST_CONTROL) + if (ufshpb_mode == HPB_HOST_CONTROL) { INIT_WORK(&hpb->ufshpb_normalization_work, ufshpb_normalization_work_handler); + INIT_WORK(&hpb->ufshpb_lun_reset_work, + ufshpb_reset_work_handler); + } hpb->map_req_cache = kmem_cache_create("ufshpb_req_cache", sizeof(struct ufshpb_req), 0, 0, NULL); @@ -1576,8 +1623,10 @@ static void ufshpb_discard_rsp_lists(struct ufshpb_lu *hpb) static void ufshpb_cancel_jobs(struct ufshpb_lu *hpb) { - if (ufshpb_mode == HPB_HOST_CONTROL) + if (ufshpb_mode == HPB_HOST_CONTROL) { + cancel_work_sync(&hpb->ufshpb_lun_reset_work); cancel_work_sync(&hpb->ufshpb_normalization_work); + } cancel_work_sync(&hpb->map_work); } diff --git a/drivers/scsi/ufs/ufshpb.h b/drivers/scsi/ufs/ufshpb.h index 47a8877f9cdb..4bf77169af00 100644 --- a/drivers/scsi/ufs/ufshpb.h +++ b/drivers/scsi/ufs/ufshpb.h @@ -183,6 +183,7 @@ struct ufshpb_lu { /* for selecting victim */ struct victim_select_info lru_info; struct work_struct ufshpb_normalization_work; + struct work_struct ufshpb_lun_reset_work; unsigned long work_data_bits; /* pinned region information */ From eb841aaabe0ade5e4fa840987f4fa19b1cb5c6c5 Mon Sep 17 00:00:00 2001 From: Avri Altman Date: Thu, 4 Jun 2020 15:20:33 +0300 Subject: [PATCH 10/11] scsi: ufshpb: Add "Cold" regions timer MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In order not to hang on to “cold” regions, we shall inactivate a region that has no READ access for a predefined amount of time - READ_TO_MS. For that purpose we shall monitor the active regions list, polling it on every POLLING_INTERVAL_MS. On timeout expiry we shall add the region to the "to-be-inactivated" list, unless it is clean and did not exhaust its READ_TO_EXPIRIES - another parameter. All this does not apply to pinned regions. Signed-off-by: Avri Altman --- drivers/scsi/ufs/ufshpb.c | 75 ++++++++++++++++++++++++++++++++++++++- drivers/scsi/ufs/ufshpb.h | 7 ++++ 2 files changed, 81 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/ufs/ufshpb.c b/drivers/scsi/ufs/ufshpb.c index cb99b57b4319..482f01c3b3ee 100644 --- a/drivers/scsi/ufs/ufshpb.c +++ b/drivers/scsi/ufs/ufshpb.c @@ -18,8 +18,12 @@ #define WORK_PENDING 0 #define RESET_PENDING 1 +#define TIMEOUT_WORK_PENDING 2 #define ACTIVATION_THRSHLD 4 /* 4 IOs */ #define EVICTION_THRSHLD (ACTIVATION_THRSHLD << 6) /* 256 IOs */ +#define READ_TO_MS 1000 +#define READ_TO_EXPIRIES 100 +#define POLLING_INTERVAL_MS 200 /* memory management */ static struct kmem_cache *ufshpb_mctx_cache; @@ -671,12 +675,69 @@ static int ufshpb_check_srgns_issue_state(struct ufshpb_lu *hpb, return 0; } +static void ufshpb_read_to_handler(struct work_struct *work) +{ + struct delayed_work *dwork = to_delayed_work(work); + struct ufshpb_lu *hpb; + struct victim_select_info *lru_info; + struct ufshpb_region *rgn, *next_rgn; + unsigned long flags; + LIST_HEAD(expired_list); + + hpb = container_of(dwork, struct ufshpb_lu, ufshpb_read_to_work); + + if (test_and_set_bit(TIMEOUT_WORK_PENDING, &hpb->work_data_bits)) + return; + + spin_lock_irqsave(&hpb->rgn_state_lock, flags); + + lru_info = &hpb->lru_info; + + list_for_each_entry_safe(rgn, next_rgn, &lru_info->lh_lru_rgn, + list_lru_rgn) { + bool timedout = ktime_after(ktime_get(), rgn->read_timeout); + bool dirty, expired; + + if (!timedout) + continue; + + dirty = is_rgn_dirty(rgn); + expired = atomic_dec_and_test(&rgn->read_timeout_expiries); + + if (dirty || expired) + list_add(&rgn->list_expired_rgn, &expired_list); + else + rgn->read_timeout = ktime_add_ms(ktime_get(), + READ_TO_MS); + } + + spin_unlock_irqrestore(&hpb->rgn_state_lock, flags); + + list_for_each_entry_safe(rgn, next_rgn, &expired_list, + list_expired_rgn) { + list_del_init(&rgn->list_expired_rgn); + spin_lock_irqsave(&hpb->rsp_list_lock, flags); + ufshpb_update_inactive_info(hpb, rgn->rgn_idx); + hpb->stats.rb_inactive_cnt++; + spin_unlock_irqrestore(&hpb->rsp_list_lock, flags); + } + + clear_bit(TIMEOUT_WORK_PENDING, &hpb->work_data_bits); + + schedule_delayed_work(&hpb->ufshpb_read_to_work, + msecs_to_jiffies(POLLING_INTERVAL_MS)); +} + static void ufshpb_add_lru_info(struct victim_select_info *lru_info, - struct ufshpb_region *rgn) + struct ufshpb_region *rgn) { rgn->rgn_state = HPB_RGN_ACTIVE; list_add_tail(&rgn->list_lru_rgn, &lru_info->lh_lru_rgn); atomic_inc(&lru_info->active_cnt); + if (ufshpb_mode == HPB_HOST_CONTROL) { + rgn->read_timeout = ktime_add_ms(ktime_get(), READ_TO_MS); + atomic_set(&rgn->read_timeout_expiries, READ_TO_EXPIRIES); + } } static void ufshpb_hit_lru_info(struct victim_select_info *lru_info, @@ -1404,6 +1465,7 @@ static int ufshpb_alloc_region_tbl(struct ufs_hba *hba, struct ufshpb_lu *hpb) INIT_LIST_HEAD(&rgn->list_inact_rgn); INIT_LIST_HEAD(&rgn->list_lru_rgn); + INIT_LIST_HEAD(&rgn->list_expired_rgn); if (rgn_idx == hpb->rgns_per_lu - 1) srgn_cnt = ((hpb->srgns_per_lu - 1) % @@ -1536,6 +1598,8 @@ static int ufshpb_lu_hpb_init(struct ufs_hba *hba, struct ufshpb_lu *hpb) ufshpb_normalization_work_handler); INIT_WORK(&hpb->ufshpb_lun_reset_work, ufshpb_reset_work_handler); + INIT_DELAYED_WORK(&hpb->ufshpb_read_to_work, + ufshpb_read_to_handler); } hpb->map_req_cache = kmem_cache_create("ufshpb_req_cache", @@ -1562,6 +1626,10 @@ static int ufshpb_lu_hpb_init(struct ufs_hba *hba, struct ufshpb_lu *hpb) ufshpb_stat_init(hpb); + if (ufshpb_mode == HPB_HOST_CONTROL) + schedule_delayed_work(&hpb->ufshpb_read_to_work, + msecs_to_jiffies(POLLING_INTERVAL_MS)); + return 0; release_m_page_cache: @@ -1624,6 +1692,7 @@ static void ufshpb_discard_rsp_lists(struct ufshpb_lu *hpb) static void ufshpb_cancel_jobs(struct ufshpb_lu *hpb) { if (ufshpb_mode == HPB_HOST_CONTROL) { + cancel_delayed_work_sync(&hpb->ufshpb_read_to_work); cancel_work_sync(&hpb->ufshpb_lun_reset_work); cancel_work_sync(&hpb->ufshpb_normalization_work); } @@ -1734,6 +1803,10 @@ void ufshpb_resume(struct ufs_hba *hba) continue; ufshpb_set_state(hpb, HPB_PRESENT); ufshpb_kick_map_work(hpb); + if (ufshpb_mode == HPB_HOST_CONTROL) + schedule_delayed_work(&hpb->ufshpb_read_to_work, + msecs_to_jiffies(POLLING_INTERVAL_MS)); + } } diff --git a/drivers/scsi/ufs/ufshpb.h b/drivers/scsi/ufs/ufshpb.h index 4bf77169af00..86c16a4127bd 100644 --- a/drivers/scsi/ufs/ufshpb.h +++ b/drivers/scsi/ufs/ufshpb.h @@ -121,6 +121,12 @@ struct ufshpb_region { /* region reads - for host mode */ atomic64_t reads; + + /* region "cold" timer - for host mode */ + ktime_t read_timeout; + atomic_t read_timeout_expiries; + struct list_head list_expired_rgn; + }; #define for_each_sub_region(rgn, i, srgn) \ @@ -184,6 +190,7 @@ struct ufshpb_lu { struct victim_select_info lru_info; struct work_struct ufshpb_normalization_work; struct work_struct ufshpb_lun_reset_work; + struct delayed_work ufshpb_read_to_work; unsigned long work_data_bits; /* pinned region information */ From 602e7179f73cae30158a46aa2213c1b9d86d97a5 Mon Sep 17 00:00:00 2001 From: Avri Altman Date: Wed, 2 Sep 2020 17:48:18 +0300 Subject: [PATCH 11/11] scsi: ufshpb: Add support for host control mode Support devices that report they are using host control mode. Signed-off-by: Avri Altman --- drivers/scsi/ufs/ufshpb.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/drivers/scsi/ufs/ufshpb.c b/drivers/scsi/ufs/ufshpb.c index 482f01c3b3ee..3ea9f7079189 100644 --- a/drivers/scsi/ufs/ufshpb.c +++ b/drivers/scsi/ufs/ufshpb.c @@ -2035,12 +2035,6 @@ void ufshpb_get_dev_info(struct ufs_hba *hba, u8 *desc_buf) int version; ufshpb_mode = desc_buf[DEVICE_DESC_PARAM_HPB_CONTROL]; - if (ufshpb_mode == HPB_HOST_CONTROL) { - dev_err(hba->dev, "%s: host control mode is not supported.\n", - __func__); - hpb_dev_info->hpb_disabled = true; - return; - } version = get_unaligned_be16(desc_buf + DEVICE_DESC_PARAM_HPB_VER); if (version != HPB_SUPPORT_VERSION) {