- Kernel - mailweb.openeuler.org

[PATCH openEuler-1.0-LTS 1/3] arm64/mpam: remove __init macro to support driver probe
by Yang Yingliang 24 Dec '21

24 Dec '21

From: Xingang Wang <wangxingang5(a)huawei.com> ascend inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I49RB2 CVE: NA --------------------------------------------------- To support device tree boot for arm64 mpam, the __init macro might be used by the dts driver. This remove the necessary __init macro for the related functions. Signed-off-by: Xingang Wang <wangxingang5(a)huawei.com> Reviewed-by: Wang ShaoBo <bobo.shaobowang(a)huawei.com> Acked-by: Xie XiuQi <xiexiuqi(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/arm64/include/asm/resctrl.h | 2 +- arch/arm64/kernel/mpam/mpam_device.c | 14 +++++++------- arch/arm64/kernel/mpam/mpam_internal.h | 2 +- arch/arm64/kernel/mpam/mpam_resctrl.c | 2 +- fs/resctrlfs.c | 2 +- include/linux/arm_mpam.h | 14 +++++++------- 6 files changed, 18 insertions(+), 18 deletions(-) diff --git a/arch/arm64/include/asm/resctrl.h b/arch/arm64/include/asm/resctrl.h index ff4ce56430d1f..3fceaa482e5a3 100644 --- a/arch/arm64/include/asm/resctrl.h +++ b/arch/arm64/include/asm/resctrl.h @@ -424,7 +424,7 @@ int resctrl_update_groups_config(struct rdtgroup *rdtgrp); #define RESCTRL_MAX_CLOSID 32 -int __init resctrl_group_init(void); +int resctrl_group_init(void); void post_resctrl_mount(void); diff --git a/arch/arm64/kernel/mpam/mpam_device.c b/arch/arm64/kernel/mpam/mpam_device.c index c0615f6947a1f..4139b4476a836 100644 --- a/arch/arm64/kernel/mpam/mpam_device.c +++ b/arch/arm64/kernel/mpam/mpam_device.c @@ -534,7 +534,7 @@ static void mpam_disable_irqs(void) * Scheduled by mpam_discovery_complete() once all devices have been created. * Also scheduled when new devices are probed when new CPUs come online. */ -static void __init mpam_enable(struct work_struct *work) +static void mpam_enable(struct work_struct *work) { int err; unsigned long flags; @@ -761,7 +761,7 @@ static struct mpam_class * __init mpam_class_get(u8 level_idx, * class/component structures may be allocated. * Returns the new device, or an ERR_PTR(). */ -struct mpam_device * __init +struct mpam_device * __mpam_device_create(u8 level_idx, enum mpam_class_types type, int component_id, const struct cpumask *fw_affinity, phys_addr_t hwpage_address) @@ -810,7 +810,7 @@ __mpam_device_create(u8 level_idx, enum mpam_class_types type, return dev; } -void __init mpam_device_set_error_irq(struct mpam_device *dev, u32 irq, +void mpam_device_set_error_irq(struct mpam_device *dev, u32 irq, u32 flags) { unsigned long irq_save_flags; @@ -821,7 +821,7 @@ void __init mpam_device_set_error_irq(struct mpam_device *dev, u32 irq, spin_unlock_irqrestore(&dev->lock, irq_save_flags); } -void __init mpam_device_set_overflow_irq(struct mpam_device *dev, u32 irq, +void mpam_device_set_overflow_irq(struct mpam_device *dev, u32 irq, u32 flags) { unsigned long irq_save_flags; @@ -864,7 +864,7 @@ static inline u16 mpam_cpu_max_pmg(void) /* * prepare for initializing devices. */ -int __init mpam_discovery_start(void) +int mpam_discovery_start(void) { if (!mpam_cpus_have_feature()) return -EOPNOTSUPP; @@ -1104,7 +1104,7 @@ static int mpam_cpu_offline(unsigned int cpu) return 0; } -int __init mpam_discovery_complete(void) +int mpam_discovery_complete(void) { int ret = 0; @@ -1121,7 +1121,7 @@ int __init mpam_discovery_complete(void) return ret; } -void __init mpam_discovery_failed(void) +void mpam_discovery_failed(void) { struct mpam_class *class, *tmp; diff --git a/arch/arm64/kernel/mpam/mpam_internal.h b/arch/arm64/kernel/mpam/mpam_internal.h index cfaef82428aa5..7b84ea54975aa 100644 --- a/arch/arm64/kernel/mpam/mpam_internal.h +++ b/arch/arm64/kernel/mpam/mpam_internal.h @@ -329,7 +329,7 @@ int mpam_resctrl_setup(void); struct raw_resctrl_resource * mpam_get_raw_resctrl_resource(u32 level); -int __init mpam_resctrl_init(void); +int mpam_resctrl_init(void); int mpam_resctrl_set_default_cpu(unsigned int cpu); void mpam_resctrl_clear_default_cpu(unsigned int cpu); diff --git a/arch/arm64/kernel/mpam/mpam_resctrl.c b/arch/arm64/kernel/mpam/mpam_resctrl.c index 51cdefebaeba8..1ad4cd49762a3 100644 --- a/arch/arm64/kernel/mpam/mpam_resctrl.c +++ b/arch/arm64/kernel/mpam/mpam_resctrl.c @@ -2209,7 +2209,7 @@ static int __init mpam_setup(char *str) } __setup("mpam", mpam_setup); -int __init mpam_resctrl_init(void) +int mpam_resctrl_init(void) { mpam_init_padding(); diff --git a/fs/resctrlfs.c b/fs/resctrlfs.c index 11741c87eb0af..ea9df7d77b95a 100644 --- a/fs/resctrlfs.c +++ b/fs/resctrlfs.c @@ -1029,7 +1029,7 @@ static int __init resctrl_group_setup_root(void) * * Return: 0 on success or -errno */ -int __init resctrl_group_init(void) +int resctrl_group_init(void) { int ret = 0; diff --git a/include/linux/arm_mpam.h b/include/linux/arm_mpam.h index 44d0690ae8c4b..a242d4fdff8b3 100644 --- a/include/linux/arm_mpam.h +++ b/include/linux/arm_mpam.h @@ -16,7 +16,7 @@ enum mpam_class_types { MPAM_CLASS_UNKNOWN, /* Everything else, e.g. TLBs etc */ }; -struct mpam_device * __init +struct mpam_device * __mpam_device_create(u8 level_idx, enum mpam_class_types type, int component_id, const struct cpumask *fw_affinity, phys_addr_t hwpage_address); @@ -54,9 +54,9 @@ mpam_device_create_memory(int nid, phys_addr_t hwpage_address) return __mpam_device_create(~0, MPAM_CLASS_MEMORY, nid, &dev_affinity, hwpage_address); } -int __init mpam_discovery_start(void); -int __init mpam_discovery_complete(void); -void __init mpam_discovery_failed(void); +int mpam_discovery_start(void); +int mpam_discovery_complete(void); +void mpam_discovery_failed(void); enum mpam_enable_type { MPAM_ENABLE_DENIED = 0, @@ -71,12 +71,12 @@ extern enum mpam_enable_type mpam_enabled; #define mpam_irq_flags_to_acpi(x) ((x & MPAM_IRQ_MODE_LEVEL) ? \ ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE) -void __init mpam_device_set_error_irq(struct mpam_device *dev, u32 irq, +void mpam_device_set_error_irq(struct mpam_device *dev, u32 irq, u32 flags); -void __init mpam_device_set_overflow_irq(struct mpam_device *dev, u32 irq, +void mpam_device_set_overflow_irq(struct mpam_device *dev, u32 irq, u32 flags); -static inline int __init mpam_register_device_irq(struct mpam_device *dev, +static inline int mpam_register_device_irq(struct mpam_device *dev, u32 overflow_interrupt, u32 overflow_flags, u32 error_interrupt, u32 error_flags) { -- 2.25.1

1 2

[openEuler-5.10 01/19] drm/hisilicon: Support i2c driver algorithms for bit-shift adapters
by Zheng Zengkai 23 Dec '21

23 Dec '21

From: Ma Hai <mahai1(a)huawei.com> mainline inclusion from mainline-v5.12-rc2 commit 4eb4d99dfe3018d86f4529112aa7082f43b6996a category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4M6CD?from=project-issue CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/d… ---------------------------------------------------------------------- Adding driver implementation to support i2c driver algorithms for bit-shift adapters, so hibmc will using the interface provided by drm to read edid. Signed-off-by: Ma Hai <mahai1(a)huawei.com> Signed-off-by: Tian Tao <tiantao6(a)hisilicon.com> Reviewed-by: Thomas Zimmermann <tzimmermann(a)suse.de> Reviewed-by: Li Dongming <lidongming5(a)huawei.com> Link: https://patchwork.freedesktop.org/patch/msgid/1600778670-60370-2-git-send-e… Acked-by: Xie XiuQi <xiexiuqi(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- drivers/gpu/drm/hisilicon/hibmc/Makefile | 2 +- .../gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h | 25 ++++- .../gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c | 99 +++++++++++++++++++ .../gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c | 2 +- 4 files changed, 125 insertions(+), 3 deletions(-) create mode 100644 drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c diff --git a/drivers/gpu/drm/hisilicon/hibmc/Makefile b/drivers/gpu/drm/hisilicon/hibmc/Makefile index f99132715597..684ef794eb7c 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/Makefile +++ b/drivers/gpu/drm/hisilicon/hibmc/Makefile @@ -1,4 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only -hibmc-drm-y := hibmc_drm_drv.o hibmc_drm_de.o hibmc_drm_vdac.o hibmc_ttm.o +hibmc-drm-y := hibmc_drm_drv.o hibmc_drm_de.o hibmc_drm_vdac.o hibmc_ttm.o hibmc_drm_i2c.o obj-$(CONFIG_DRM_HISI_HIBMC) += hibmc-drm.o diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h index 197485e2fe0b..87d2aad0bb5e 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h @@ -14,11 +14,23 @@ #ifndef HIBMC_DRM_DRV_H #define HIBMC_DRM_DRV_H +#include <linux/gpio/consumer.h> +#include <linux/i2c-algo-bit.h> +#include <linux/i2c.h> + +#include <drm/drm_edid.h> #include <drm/drm_fb_helper.h> #include <drm/drm_framebuffer.h> struct drm_device; +struct hibmc_connector { + struct drm_connector base; + + struct i2c_adapter adapter; + struct i2c_algo_bit_data bit_data; +}; + struct hibmc_drm_private { /* hw */ void __iomem *mmio; @@ -31,10 +43,20 @@ struct hibmc_drm_private { struct drm_plane primary_plane; struct drm_crtc crtc; struct drm_encoder encoder; - struct drm_connector connector; + struct hibmc_connector connector; bool mode_config_initialized; }; +static inline struct hibmc_connector *to_hibmc_connector(struct drm_connector *connector) +{ + return container_of(connector, struct hibmc_connector, base); +} + +static inline struct hibmc_drm_private *to_hibmc_drm_private(struct drm_device *dev) +{ + return dev->dev_private; +} + void hibmc_set_power_mode(struct hibmc_drm_private *priv, unsigned int power_mode); void hibmc_set_current_gate(struct hibmc_drm_private *priv, @@ -47,6 +69,7 @@ int hibmc_mm_init(struct hibmc_drm_private *hibmc); void hibmc_mm_fini(struct hibmc_drm_private *hibmc); int hibmc_dumb_create(struct drm_file *file, struct drm_device *dev, struct drm_mode_create_dumb *args); +int hibmc_ddc_create(struct drm_device *drm_dev, struct hibmc_connector *connector); extern const struct drm_mode_config_funcs hibmc_mode_funcs; diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c new file mode 100644 index 000000000000..86d712090d87 --- /dev/null +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c @@ -0,0 +1,99 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Hisilicon Hibmc SoC drm driver + * + * Based on the bochs drm driver. + * + * Copyright (c) 2016 Huawei Limited. + * + * Author: + * Tian Tao <tiantao6(a)hisilicon.com> + */ + +#include <linux/delay.h> +#include <linux/pci.h> + +#include <drm/drm_atomic_helper.h> +#include <drm/drm_probe_helper.h> + +#include "hibmc_drm_drv.h" + +#define GPIO_DATA 0x0802A0 +#define GPIO_DATA_DIRECTION 0x0802A4 + +#define I2C_SCL_MASK BIT(0) +#define I2C_SDA_MASK BIT(1) + +static void hibmc_set_i2c_signal(void *data, u32 mask, int value) +{ + struct hibmc_connector *hibmc_connector = data; + struct hibmc_drm_private *priv = to_hibmc_drm_private(hibmc_connector->base.dev); + u32 tmp_dir = readl(priv->mmio + GPIO_DATA_DIRECTION); + + if (value) { + tmp_dir &= ~mask; + writel(tmp_dir, priv->mmio + GPIO_DATA_DIRECTION); + } else { + u32 tmp_data = readl(priv->mmio + GPIO_DATA); + + tmp_data &= ~mask; + writel(tmp_data, priv->mmio + GPIO_DATA); + + tmp_dir |= mask; + writel(tmp_dir, priv->mmio + GPIO_DATA_DIRECTION); + } +} + +static int hibmc_get_i2c_signal(void *data, u32 mask) +{ + struct hibmc_connector *hibmc_connector = data; + struct hibmc_drm_private *priv = to_hibmc_drm_private(hibmc_connector->base.dev); + u32 tmp_dir = readl(priv->mmio + GPIO_DATA_DIRECTION); + + if ((tmp_dir & mask) != mask) { + tmp_dir &= ~mask; + writel(tmp_dir, priv->mmio + GPIO_DATA_DIRECTION); + } + + return (readl(priv->mmio + GPIO_DATA) & mask) ? 1 : 0; +} + +static void hibmc_ddc_setsda(void *data, int state) +{ + hibmc_set_i2c_signal(data, I2C_SDA_MASK, state); +} + +static void hibmc_ddc_setscl(void *data, int state) +{ + hibmc_set_i2c_signal(data, I2C_SCL_MASK, state); +} + +static int hibmc_ddc_getsda(void *data) +{ + return hibmc_get_i2c_signal(data, I2C_SDA_MASK); +} + +static int hibmc_ddc_getscl(void *data) +{ + return hibmc_get_i2c_signal(data, I2C_SCL_MASK); +} + +int hibmc_ddc_create(struct drm_device *drm_dev, + struct hibmc_connector *connector) +{ + connector->adapter.owner = THIS_MODULE; + connector->adapter.class = I2C_CLASS_DDC; + snprintf(connector->adapter.name, I2C_NAME_SIZE, "HIS i2c bit bus"); + connector->adapter.dev.parent = &drm_dev->pdev->dev; + i2c_set_adapdata(&connector->adapter, connector); + connector->adapter.algo_data = &connector->bit_data; + + connector->bit_data.udelay = 20; + connector->bit_data.timeout = usecs_to_jiffies(2000); + connector->bit_data.data = connector; + connector->bit_data.setsda = hibmc_ddc_setsda; + connector->bit_data.setscl = hibmc_ddc_setscl; + connector->bit_data.getsda = hibmc_ddc_getsda; + connector->bit_data.getscl = hibmc_ddc_getscl; + + return i2c_bit_add_bus(&connector->adapter); +} diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c index 376a05ddbc2f..c8b14afbcbed 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c @@ -78,7 +78,7 @@ int hibmc_vdac_init(struct hibmc_drm_private *priv) { struct drm_device *dev = priv->dev; struct drm_encoder *encoder = &priv->encoder; - struct drm_connector *connector = &priv->connector; + struct drm_connector *connector = &priv->connector.base; int ret; encoder->possible_crtcs = 0x1; -- 2.20.1

1 18

[PATCH openEuler-1.0-LTS 1/3] arm64/mpam: Fix mpam corrupt when cpu online
by Yang Yingliang 23 Dec '21

23 Dec '21

From: Wang ShaoBo <bobo.shaobowang(a)huawei.com> hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I3YAI3 CVE: NA ------------------------------------------------- The following error occurred occasionally on a machine that supports MPAM: [ 13.321386][ T658] Unable to handle kernel paging request at virtual address ffff80001115816c [ 13.326013][ T684] hid-generic 0003:12D1:0003.0002: input,hidraw1: USB HID v1.10 Mouse [Keyboard/Mouse KVM 1.1.0] on usb-0000:7a:01.0-1.1/input1 [ 13.340558][ T658] Mem abort info: [ 13.340563][ T658] ESR = 0x86000007 [ 13.352567][ T5] hub 6-1:1.0: USB hub found [ 13.364750][ T658] EC = 0x21: IABT (current EL), IL = 32 bits [ 13.369891][ T5] hub 6-1:1.0: 4 ports detected [ 13.373871][ T658] SET = 0, FnV = 0 [ 13.396107][ T658] EA = 0, S1PTW = 0 [ 13.400599][ T658] swapper pgtable: 64k pages, 48-bit VAs, pgdp=0000000029540000 [ 13.408726][ T658] [ffff80001115816c] pgd=0000205fffff0003, p4d=0000205fffff0003, pud=0000205fffff0003, pmd=0000205ffffe0003, pte=0000000000000000 [ 13.423346][ T658] Internal error: Oops: 86000007 [#1] SMP [ 13.429720][ T658] Modules linked in: [ 13.434243][ T658] CPU: 72 PID: 658 Comm: kworker/72:1 Not tainted 5.10.0-4.17.0.28.oe1.aarch64 #1 [ 13.443966][ T658] Hardware name: Huawei TaiShan 200 (Model 2280)/BC82AMDDA, BIOS 1.70 01/07/2021 [ 13.453683][ T658] Workqueue: events mpam_enable [ 13.459206][ T658] pstate: 20c00009 (nzCv daif +PAN +UAO -TCO BTYPE=--) [ 13.466625][ T658] pc : mpam_enable+0x194/0x1d8 [ 13.472019][ T658] lr : mpam_enable+0x194/0x1d8 [ 13.477301][ T658] sp : ffff80004664fd70 [ 13.481937][ T658] x29: ffff80004664fd70 x28: 0000000000000000 [ 13.488578][ T658] x27: ffff00400484a648 x26: ffff800011b71080 [ 13.495306][ T658] x25: 0000000000000000 x24: ffff800011b6cda0 [ 13.502001][ T658] x23: ffff800011646f18 x22: ffff800011b6cd80 [ 13.508684][ T658] x21: ffff800011b6c000 x20: ffff800011646f08 [ 13.515425][ T658] x19: ffff800011646f70 x18: 0000000000000020 [ 13.522075][ T658] x17: 000000001790b332 x16: 0000000000000001 [ 13.528785][ T658] x15: ffffffffffffffff x14: ff00000000000000 [ 13.535464][ T658] x13: ffffffffffffffff x12: 0000000000000006 [ 13.542045][ T658] x11: 00000091cea718e2 x10: 0000000000000b90 [ 13.548735][ T658] x9 : ffff80001009ebac x8 : ffff2040061aabf0 [ 13.555383][ T658] x7 : ffffa05f8dca0000 x6 : 000000000000000f [ 13.561924][ T658] x5 : 0000000000000000 x4 : ffff2040061aa000 [ 13.568613][ T658] x3 : ffff80001164dfa0 x2 : 00000000ffffffff [ 13.575267][ T658] x1 : ffffa05f8dca0000 x0 : 00000000000000c1 [ 13.581813][ T658] Call trace: [ 13.585600][ T658] mpam_enable+0x194/0x1d8 [ 13.590450][ T658] process_one_work+0x1cc/0x390 [ 13.595654][ T658] worker_thread+0x70/0x2f0 [ 13.600499][ T658] kthread+0x118/0x120 [ 13.604935][ T658] ret_from_fork+0x10/0x18 [ 13.609717][ T658] Code: bad PC value [ 13.613944][ T658] ---[ end trace f1e305d2c339f67f ]--- [ 13.753818][ T658] Kernel panic - not syncing: Oops: Fatal exception [ 13.760885][ T658] SMP: stopping secondary CPUs [ 13.765933][ T658] Kernel Offset: disabled [ 13.770516][ T658] CPU features: 0x8040002,22208a38 [ 13.775862][ T658] Memory Limit: none [ 13.913929][ T658] ---[ end Kernel panic - not syncing: The process of MPAM devices initialization is like this: mpam_discovery_start() ... // discover devices mpam_discovery_complete() // hang up the mpam_online/offline_cpu callbacks -=> mpam_cpu_online() // probe all devices -=> mpam_enable() // prepare for resctrl (1) -=> cpuhp_remove_state() // clean resctrl internal structure (2) -=> cpuhp_setup_state() // rehang mpam_online/offline_cpu callbacks -=> mpam_cpu_online() // it does not call mpam_enable again -=> mpam_resctrl_cpu_online() // pull up resctrl Re-hang process of mpam_cpu_online/offline callbacks should not be disturbed by irqs, to ensure that CPU context is reliable before re-entering mpam_cpu_online(), which always happens between (1) and (2). Fixes: 2ab89c893faf ("arm64/mpam: resctrl: Re-synchronise resctrl's view of online CPUs") Signed-off-by: Wang ShaoBo <bobo.shaobowang(a)huawei.com> Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/arm64/kernel/mpam/mpam_device.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm64/kernel/mpam/mpam_device.c b/arch/arm64/kernel/mpam/mpam_device.c index f8840274b902f..c0615f6947a1f 100644 --- a/arch/arm64/kernel/mpam/mpam_device.c +++ b/arch/arm64/kernel/mpam/mpam_device.c @@ -593,9 +593,11 @@ static void __init mpam_enable(struct work_struct *work) pr_err("Failed to setup/init resctrl\n"); mutex_unlock(&mpam_devices_lock); + local_irq_disable(); mpam_cpuhp_state = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "mpam:online", mpam_cpu_online, mpam_cpu_offline); + local_irq_enable(); if (mpam_cpuhp_state <= 0) pr_err("Failed to re-register 'dyn' cpuhp callbacks"); mutex_unlock(&mpam_cpuhp_lock); -- 2.25.1

1 2

[PATCH openEuler-1.0-LTS 1/2] kprobes: Set unoptimized flag after unoptimizing code
by Yang Yingliang 22 Dec '21

22 Dec '21

From: Masami Hiramatsu <mhiramat(a)kernel.org> stable inclusion from stable-v4.19.108 commit 39af044d1ccb207da43af5c060bb0fb0dd548b3e category: bugfix bugzilla: NA CVE: NA ------------------------------------------------- commit f66c0447cca1281116224d474cdb37d6a18e4b5b upstream. Set the unoptimized flag after confirming the code is completely unoptimized. Without this fix, when a kprobe hits the intermediate modified instruction (the first byte is replaced by an INT3, but later bytes can still be a jump address operand) while unoptimizing, it can return to the middle byte of the modified code, which causes an invalid instruction exception in the kernel. Usually, this is a rare case, but if we put a probe on the function call while text patching, it always causes a kernel panic as below: # echo p text_poke+5 > kprobe_events # echo 1 > events/kprobes/enable # echo 0 > events/kprobes/enable invalid opcode: 0000 [#1] PREEMPT SMP PTI RIP: 0010:text_poke+0x9/0x50 Call Trace: arch_unoptimize_kprobe+0x22/0x28 arch_unoptimize_kprobes+0x39/0x87 kprobe_optimizer+0x6e/0x290 process_one_work+0x2a0/0x610 worker_thread+0x28/0x3d0 ? process_one_work+0x610/0x610 kthread+0x10d/0x130 ? kthread_park+0x80/0x80 ret_from_fork+0x3a/0x50 text_poke() is used for patching the code in optprobes. This can happen even if we blacklist text_poke() and other functions, because there is a small time window during which we show the intermediate code to other CPUs. [ mingo: Edited the changelog. ] Tested-by: Alexei Starovoitov <ast(a)kernel.org> Signed-off-by: Masami Hiramatsu <mhiramat(a)kernel.org> Cc: Andy Lutomirski <luto(a)kernel.org> Cc: Borislav Petkov <bp(a)alien8.de> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Steven Rostedt <rostedt(a)goodmis.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: bristot(a)redhat.com Fixes: 6274de4984a6 ("kprobes: Support delayed unoptimizing") Link: https://lkml.kernel.org/r/157483422375.25881.13508326028469515760.stgit@dev… Signed-off-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Yang Jihong <yangjihong1(a)huawei.com> Reviewed-by: Kuohai Xu <xukuohai(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- kernel/kprobes.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/kernel/kprobes.c b/kernel/kprobes.c index f6e6edaf964c1..666243fff573d 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -523,6 +523,8 @@ static void do_unoptimize_kprobes(void) arch_unoptimize_kprobes(&unoptimizing_list, &freeing_list); /* Loop free_list for disarming */ list_for_each_entry_safe(op, tmp, &freeing_list, list) { + /* Switching from detour code to origin */ + op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; /* Disarm probes if marked disabled */ if (kprobe_disabled(&op->kp)) arch_disarm_kprobe(&op->kp); @@ -662,6 +664,7 @@ static void force_unoptimize_kprobe(struct optimized_kprobe *op) { lockdep_assert_cpus_held(); arch_unoptimize_kprobe(op); + op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; if (kprobe_disabled(&op->kp)) arch_disarm_kprobe(&op->kp); } @@ -689,7 +692,6 @@ static void unoptimize_kprobe(struct kprobe *p, bool force) return; } - op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; if (!list_empty(&op->list)) { /* Dequeue from the optimization queue */ list_del_init(&op->list); -- 2.25.1

1 1

[PATCH openEuler-1.0-LTS] cpufreq: schedutil: Destroy mutex before kobject_put() frees the memory
by Yang Yingliang 22 Dec '21

22 Dec '21

From: James Morse <james.morse(a)arm.com> stable inclusion from linux-4.19.209 commit 3cb9595e23d879824ebcefeabdf5156bc288000c -------------------------------- [ Upstream commit cdef1196608892b9a46caa5f2b64095a7f0be60c ] Since commit e5c6b312ce3c ("cpufreq: schedutil: Use kobject release() method to free sugov_tunables") kobject_put() has kfree()d the attr_set before gov_attr_set_put() returns. kobject_put() isn't the last user of attr_set in gov_attr_set_put(), the subsequent mutex_destroy() triggers a use-after-free: | BUG: KASAN: use-after-free in mutex_is_locked+0x20/0x60 | Read of size 8 at addr ffff000800ca4250 by task cpuhp/2/20 | | CPU: 2 PID: 20 Comm: cpuhp/2 Not tainted 5.15.0-rc1 #12369 | Hardware name: ARM LTD ARM Juno Development Platform/ARM Juno Development | Platform, BIOS EDK II Jul 30 2018 | Call trace: | dump_backtrace+0x0/0x380 | show_stack+0x1c/0x30 | dump_stack_lvl+0x8c/0xb8 | print_address_description.constprop.0+0x74/0x2b8 | kasan_report+0x1f4/0x210 | kasan_check_range+0xfc/0x1a4 | __kasan_check_read+0x38/0x60 | mutex_is_locked+0x20/0x60 | mutex_destroy+0x80/0x100 | gov_attr_set_put+0xfc/0x150 | sugov_exit+0x78/0x190 | cpufreq_offline.isra.0+0x2c0/0x660 | cpuhp_cpufreq_offline+0x14/0x24 | cpuhp_invoke_callback+0x430/0x6d0 | cpuhp_thread_fun+0x1b0/0x624 | smpboot_thread_fn+0x5e0/0xa6c | kthread+0x3a0/0x450 | ret_from_fork+0x10/0x20 Swap the order of the calls. Fixes: e5c6b312ce3c ("cpufreq: schedutil: Use kobject release() method to free sugov_tunables") Cc: 4.7+ <stable(a)vger.kernel.org> # 4.7+ Signed-off-by: James Morse <james.morse(a)arm.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki(a)intel.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/cpufreq/cpufreq_governor_attr_set.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/cpufreq/cpufreq_governor_attr_set.c b/drivers/cpufreq/cpufreq_governor_attr_set.c index 52841f807a7eb..45fdf30cade39 100644 --- a/drivers/cpufreq/cpufreq_governor_attr_set.c +++ b/drivers/cpufreq/cpufreq_governor_attr_set.c @@ -77,8 +77,8 @@ unsigned int gov_attr_set_put(struct gov_attr_set *attr_set, struct list_head *l if (count) return count; - kobject_put(&attr_set->kobj); mutex_destroy(&attr_set->update_lock); + kobject_put(&attr_set->kobj); return 0; } EXPORT_SYMBOL_GPL(gov_attr_set_put); -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS v3] scsi:spraid: support Ramaxel's spraid driver
by Yanling Song 22 Dec '21

22 Dec '21

Ramaxel inclusion category: features bugzilla: https://gitee.com/openeuler/kernel/issues/I4NJIB CVE: NA v2->v3: 1. Add deconfig for hulk in arm64 and x86 v1->v2: 1. Add deconfig for arm64 and x86 Support Ramaxel's SPRxxx Raid controller Signed-off-by: Yanling Song <songyl(a)ramaxel.com> Reviewed-by: Jiang Yu<yujiang(a)ramaxel.com> --- arch/arm64/configs/hulk_defconfig | 1 + arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/hulk_defconfig | 3 +- arch/x86/configs/openeuler_defconfig | 1 + drivers/scsi/Kconfig | 1 + drivers/scsi/Makefile | 1 + drivers/scsi/spraid/Kconfig | 13 + drivers/scsi/spraid/Makefile | 7 + drivers/scsi/spraid/spraid.h | 746 +++++ drivers/scsi/spraid/spraid_main.c | 3875 ++++++++++++++++++++++++ 10 files changed, 4648 insertions(+), 1 deletion(-) create mode 100644 drivers/scsi/spraid/Kconfig create mode 100644 drivers/scsi/spraid/Makefile create mode 100644 drivers/scsi/spraid/spraid.h create mode 100644 drivers/scsi/spraid/spraid_main.c diff --git a/arch/arm64/configs/hulk_defconfig b/arch/arm64/configs/hulk_defconfig index bc350c41b333..71517c091c43 100644 --- a/arch/arm64/configs/hulk_defconfig +++ b/arch/arm64/configs/hulk_defconfig @@ -2149,6 +2149,7 @@ CONFIG_SCSI_MPT2SAS_MAX_SGE=128 CONFIG_SCSI_MPT3SAS_MAX_SGE=128 CONFIG_SCSI_MPT2SAS=m CONFIG_SCSI_SMARTPQI=m +CONFIG_RAMAXEL_SPRAID=m # CONFIG_SCSI_UFSHCD is not set # CONFIG_SCSI_HPTIOP is not set CONFIG_LIBFC=m diff --git a/arch/arm64/configs/openeuler_defconfig b/arch/arm64/configs/openeuler_defconfig index d2167c80757f..47b0931b91bf 100644 --- a/arch/arm64/configs/openeuler_defconfig +++ b/arch/arm64/configs/openeuler_defconfig @@ -2143,6 +2143,7 @@ CONFIG_SCSI_MPT2SAS_MAX_SGE=128 CONFIG_SCSI_MPT3SAS_MAX_SGE=128 CONFIG_SCSI_MPT2SAS=m CONFIG_SCSI_SMARTPQI=m +CONFIG_RAMAXEL_SPRAID=m # CONFIG_SCSI_UFSHCD is not set # CONFIG_SCSI_HPTIOP is not set CONFIG_LIBFC=m diff --git a/arch/x86/configs/hulk_defconfig b/arch/x86/configs/hulk_defconfig index 983d52ccad82..536ffb38c00c 100644 --- a/arch/x86/configs/hulk_defconfig +++ b/arch/x86/configs/hulk_defconfig @@ -1,4 +1,4 @@ -# + # Automatically generated file; DO NOT EDIT. # Linux/x86 4.19.21 Kernel Configuration # @@ -2177,6 +2177,7 @@ CONFIG_SCSI_MPT2SAS_MAX_SGE=128 CONFIG_SCSI_MPT3SAS_MAX_SGE=128 CONFIG_SCSI_MPT2SAS=m CONFIG_SCSI_SMARTPQI=m +CONFIG_RAMAXEL_SPRAID=m # CONFIG_SCSI_UFSHCD is not set # CONFIG_SCSI_HPTIOP is not set # CONFIG_SCSI_BUSLOGIC is not set diff --git a/arch/x86/configs/openeuler_defconfig b/arch/x86/configs/openeuler_defconfig index 7043426d9780..786186288fea 100644 --- a/arch/x86/configs/openeuler_defconfig +++ b/arch/x86/configs/openeuler_defconfig @@ -2182,6 +2182,7 @@ CONFIG_SCSI_MPT2SAS_MAX_SGE=128 CONFIG_SCSI_MPT3SAS_MAX_SGE=128 CONFIG_SCSI_MPT2SAS=m CONFIG_SCSI_SMARTPQI=m +CONFIG_RAMAXEL_SPRAID=m # CONFIG_SCSI_UFSHCD is not set # CONFIG_SCSI_HPTIOP is not set # CONFIG_SCSI_BUSLOGIC is not set diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig index 8450484184e3..63d2aaa22834 100644 --- a/drivers/scsi/Kconfig +++ b/drivers/scsi/Kconfig @@ -522,6 +522,7 @@ source "drivers/scsi/megaraid/Kconfig.megaraid" source "drivers/scsi/mpt3sas/Kconfig" source "drivers/scsi/smartpqi/Kconfig" source "drivers/scsi/ufs/Kconfig" +source "drivers/scsi/spraid/Kconfig" config SCSI_HPTIOP tristate "HighPoint RocketRAID 3xxx/4xxx Controller support" diff --git a/drivers/scsi/Makefile b/drivers/scsi/Makefile index 2973693f6dcc..4056cf26e09e 100644 --- a/drivers/scsi/Makefile +++ b/drivers/scsi/Makefile @@ -94,6 +94,7 @@ obj-$(CONFIG_SCSI_ZALON) += zalon7xx.o obj-$(CONFIG_SCSI_DC395x) += dc395x.o obj-$(CONFIG_SCSI_AM53C974) += esp_scsi.o am53c974.o obj-$(CONFIG_CXLFLASH) += cxlflash/ +obj-$(CONFIG_RAMAXEL_SPRAID) += spraid/ obj-$(CONFIG_MEGARAID_LEGACY) += megaraid.o obj-$(CONFIG_MEGARAID_NEWGEN) += megaraid/ obj-$(CONFIG_MEGARAID_SAS) += megaraid/ diff --git a/drivers/scsi/spraid/Kconfig b/drivers/scsi/spraid/Kconfig new file mode 100644 index 000000000000..bfbba3db8db0 --- /dev/null +++ b/drivers/scsi/spraid/Kconfig @@ -0,0 +1,13 @@ +# +# Ramaxel driver configuration +# + +config RAMAXEL_SPRAID + tristate "Ramaxel spraid Adapter" + depends on PCI && SCSI + select BLK_DEV_BSGLIB + depends on ARM64 || X86_64 + help + This driver supports Ramaxel SPRxxx serial + raid controller, which has PCIE Gen4 interface + with host and supports SAS/SATA Hdd/ssd. diff --git a/drivers/scsi/spraid/Makefile b/drivers/scsi/spraid/Makefile new file mode 100644 index 000000000000..aadc2ffd37eb --- /dev/null +++ b/drivers/scsi/spraid/Makefile @@ -0,0 +1,7 @@ +# +# Makefile for the Ramaxel device drivers. +# + +obj-$(CONFIG_RAMAXEL_SPRAID) += spraid.o + +spraid-objs := spraid_main.o \ No newline at end of file diff --git a/drivers/scsi/spraid/spraid.h b/drivers/scsi/spraid/spraid.h new file mode 100644 index 000000000000..c1e4980e18e5 --- /dev/null +++ b/drivers/scsi/spraid/spraid.h @@ -0,0 +1,746 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2021 Ramaxel Memory Technology, Ltd */ + +#ifndef __SPRAID_H_ +#define __SPRAID_H_ + +#define SPRAID_CAP_MQES(cap) ((cap) & 0xffff) +#define SPRAID_CAP_STRIDE(cap) (((cap) >> 32) & 0xf) +#define SPRAID_CAP_MPSMIN(cap) (((cap) >> 48) & 0xf) +#define SPRAID_CAP_MPSMAX(cap) (((cap) >> 52) & 0xf) +#define SPRAID_CAP_TIMEOUT(cap) (((cap) >> 24) & 0xff) +#define SPRAID_CAP_DMAMASK(cap) (((cap) >> 37) & 0xff) + +#define SPRAID_DEFAULT_MAX_CHANNEL 4 +#define SPRAID_DEFAULT_MAX_ID 240 +#define SPRAID_DEFAULT_MAX_LUN_PER_HOST 8 +#define MAX_SECTORS 2048 + +#define IO_SQE_SIZE sizeof(struct spraid_ioq_command) +#define ADMIN_SQE_SIZE sizeof(struct spraid_admin_command) +#define SQE_SIZE(qid) (((qid) > 0) ? IO_SQE_SIZE : ADMIN_SQE_SIZE) +#define CQ_SIZE(depth) ((depth) * sizeof(struct spraid_completion)) +#define SQ_SIZE(qid, depth) ((depth) * SQE_SIZE(qid)) + +#define SENSE_SIZE(depth) ((depth) * SCSI_SENSE_BUFFERSIZE) + +#define SPRAID_AQ_DEPTH 128 +#define SPRAID_NR_AEN_COMMANDS 16 +#define SPRAID_AQ_BLK_MQ_DEPTH (SPRAID_AQ_DEPTH - SPRAID_NR_AEN_COMMANDS) +#define SPRAID_AQ_MQ_TAG_DEPTH (SPRAID_AQ_BLK_MQ_DEPTH - 1) + +#define SPRAID_ADMIN_QUEUE_NUM 1 +#define SPRAID_PTCMDS_PERQ 1 +#define SPRAID_IO_BLK_MQ_DEPTH (hdev->shost->can_queue) +#define SPRAID_NR_IOQ_PTCMDS (SPRAID_PTCMDS_PERQ * hdev->shost->nr_hw_queues) + +#define FUA_MASK 0x08 +#define SPRAID_MINORS BIT(MINORBITS) + +#define COMMAND_IS_WRITE(cmd) ((cmd)->common.opcode & 1) + +#define SPRAID_IO_IOSQES 7 +#define SPRAID_IO_IOCQES 4 +#define PRP_ENTRY_SIZE 8 + +#define SMALL_POOL_SIZE 256 +#define MAX_SMALL_POOL_NUM 16 +#define MAX_CMD_PER_DEV 64 +#define MAX_CDB_LEN 32 + +#define SPRAID_UP_TO_MULTY4(x) (((x) + 4) & (~0x03)) + +#define CQE_STATUS_SUCCESS (0x0) + +#define PCI_VENDOR_ID_RAMAXEL_LOGIC 0x1E81 + +#define SPRAID_SERVER_DEVICE_HBA_DID 0x2100 +#define SPRAID_SERVER_DEVICE_RAID_DID 0x2200 + +#define IO_6_DEFAULT_TX_LEN 256 + +#define SPRAID_INT_PAGES 2 +#define SPRAID_INT_BYTES(hdev) (SPRAID_INT_PAGES * (hdev)->page_size) + +enum { + SPRAID_REQ_CANCELLED = (1 << 0), + SPRAID_REQ_USERCMD = (1 << 1), +}; + +enum { + SPRAID_SC_SUCCESS = 0x0, + SPRAID_SC_INVALID_OPCODE = 0x1, + SPRAID_SC_INVALID_FIELD = 0x2, + + SPRAID_SC_ABORT_LIMIT = 0x103, + SPRAID_SC_ABORT_MISSING = 0x104, + SPRAID_SC_ASYNC_LIMIT = 0x105, + + SPRAID_SC_DNR = 0x4000, +}; + +enum { + SPRAID_REG_CAP = 0x0000, + SPRAID_REG_CC = 0x0014, + SPRAID_REG_CSTS = 0x001c, + SPRAID_REG_AQA = 0x0024, + SPRAID_REG_ASQ = 0x0028, + SPRAID_REG_ACQ = 0x0030, + SPRAID_REG_DBS = 0x1000, +}; + +enum { + SPRAID_CC_ENABLE = 1 << 0, + SPRAID_CC_CSS_NVM = 0 << 4, + SPRAID_CC_MPS_SHIFT = 7, + SPRAID_CC_AMS_SHIFT = 11, + SPRAID_CC_SHN_SHIFT = 14, + SPRAID_CC_IOSQES_SHIFT = 16, + SPRAID_CC_IOCQES_SHIFT = 20, + SPRAID_CC_AMS_RR = 0 << SPRAID_CC_AMS_SHIFT, + SPRAID_CC_SHN_NONE = 0 << SPRAID_CC_SHN_SHIFT, + SPRAID_CC_IOSQES = SPRAID_IO_IOSQES << SPRAID_CC_IOSQES_SHIFT, + SPRAID_CC_IOCQES = SPRAID_IO_IOCQES << SPRAID_CC_IOCQES_SHIFT, + SPRAID_CC_SHN_NORMAL = 1 << SPRAID_CC_SHN_SHIFT, + SPRAID_CC_SHN_MASK = 3 << SPRAID_CC_SHN_SHIFT, + SPRAID_CSTS_CFS_SHIFT = 1, + SPRAID_CSTS_SHST_SHIFT = 2, + SPRAID_CSTS_PP_SHIFT = 5, + SPRAID_CSTS_RDY = 1 << 0, + SPRAID_CSTS_SHST_CMPLT = 2 << 2, + SPRAID_CSTS_SHST_MASK = 3 << 2, + SPRAID_CSTS_CFS_MASK = 1 << SPRAID_CSTS_CFS_SHIFT, + SPRAID_CSTS_PP_MASK = 1 << SPRAID_CSTS_PP_SHIFT, +}; + +enum { + SPRAID_ADMIN_DELETE_SQ = 0x00, + SPRAID_ADMIN_CREATE_SQ = 0x01, + SPRAID_ADMIN_DELETE_CQ = 0x04, + SPRAID_ADMIN_CREATE_CQ = 0x05, + SPRAID_ADMIN_ABORT_CMD = 0x08, + SPRAID_ADMIN_SET_FEATURES = 0x09, + SPRAID_ADMIN_ASYNC_EVENT = 0x0c, + SPRAID_ADMIN_GET_INFO = 0xc6, + SPRAID_ADMIN_RESET = 0xc8, +}; + +enum { + SPRAID_GET_INFO_CTRL = 0, + SPRAID_GET_INFO_DEV_LIST = 1, +}; + +enum { + SPRAID_RESET_TARGET = 0, + SPRAID_RESET_BUS = 1, +}; + +enum { + SPRAID_AEN_ERROR = 0, + SPRAID_AEN_NOTICE = 2, + SPRAID_AEN_VS = 7, +}; + +enum { + SPRAID_AEN_DEV_CHANGED = 0x00, + SPRAID_AEN_FW_ACT_START = 0x01, + SPRAID_AEN_HOST_PROBING = 0x10, +}; + +enum { + SPRAID_AEN_TIMESYN = 0x00, + SPRAID_AEN_FW_ACT_FINISH = 0x02, + SPRAID_AEN_EVENT_MIN = 0x80, + SPRAID_AEN_EVENT_MAX = 0xff, +}; + +enum { + SPRAID_CMD_WRITE = 0x01, + SPRAID_CMD_READ = 0x02, + + SPRAID_CMD_NONIO_NONE = 0x80, + SPRAID_CMD_NONIO_TODEV = 0x81, + SPRAID_CMD_NONIO_FROMDEV = 0x82, +}; + +enum { + SPRAID_QUEUE_PHYS_CONTIG = (1 << 0), + SPRAID_CQ_IRQ_ENABLED = (1 << 1), + + SPRAID_FEAT_NUM_QUEUES = 0x07, + SPRAID_FEAT_ASYNC_EVENT = 0x0b, + SPRAID_FEAT_TIMESTAMP = 0x0e, +}; + +enum spraid_state { + SPRAID_NEW, + SPRAID_LIVE, + SPRAID_RESETTING, + SPRAID_DELETING, + SPRAID_DEAD, +}; + +enum { + SPRAID_CARD_HBA, + SPRAID_CARD_RAID, +}; + +enum spraid_cmd_type { + SPRAID_CMD_ADM, + SPRAID_CMD_IOPT, +}; + +struct spraid_completion { + __le32 result; + union { + struct { + __u8 sense_len; + __u8 resv[3]; + }; + __le32 result1; + }; + __le16 sq_head; + __le16 sq_id; + __u16 cmd_id; + __le16 status; +}; + +struct spraid_ctrl_info { + __le32 nd; + __le16 max_cmds; + __le16 max_channel; + __le32 max_tgt_id; + __le16 max_lun; + __le16 max_num_sge; + __le16 lun_num_in_boot; + __u8 mdts; + __u8 acl; + __u8 aerl; + __u8 card_type; + __u16 rsvd; + __u32 rtd3e; + __u8 sn[32]; + __u8 fr[16]; + __u8 rsvd1[4020]; +}; + +struct spraid_dev { + struct pci_dev *pdev; + struct device *dev; + struct Scsi_Host *shost; + struct spraid_queue *queues; + struct dma_pool *prp_page_pool; + struct dma_pool *prp_small_pool[MAX_SMALL_POOL_NUM]; + mempool_t *iod_mempool; + void __iomem *bar; + u32 max_qid; + u32 num_vecs; + u32 queue_count; + u32 ioq_depth; + int db_stride; + u32 __iomem *dbs; + struct rw_semaphore devices_rwsem; + int numa_node; + u32 page_size; + u32 ctrl_config; + u32 online_queues; + u64 cap; + int instance; + struct spraid_ctrl_info *ctrl_info; + struct spraid_dev_info *devices; + + struct spraid_cmd *adm_cmds; + struct list_head adm_cmd_list; + spinlock_t adm_cmd_lock; + + struct spraid_cmd *ioq_ptcmds; + struct list_head ioq_pt_list; + spinlock_t ioq_pt_lock; + + struct work_struct scan_work; + struct work_struct timesyn_work; + struct work_struct reset_work; + struct work_struct fw_act_work; + + enum spraid_state state; + spinlock_t state_lock; + + struct request_queue *bsg_queue; +}; + +struct spraid_sgl_desc { + __le64 addr; + __le32 length; + __u8 rsvd[3]; + __u8 type; +}; + +union spraid_data_ptr { + struct { + __le64 prp1; + __le64 prp2; + }; + struct spraid_sgl_desc sgl; +}; + +struct spraid_admin_common_command { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + __le32 cdw2[4]; + union spraid_data_ptr dptr; + __le32 cdw10; + __le32 cdw11; + __le32 cdw12; + __le32 cdw13; + __le32 cdw14; + __le32 cdw15; +}; + +struct spraid_features { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + __u64 rsvd2[2]; + union spraid_data_ptr dptr; + __le32 fid; + __le32 dword11; + __le32 dword12; + __le32 dword13; + __le32 dword14; + __le32 dword15; +}; + +struct spraid_create_cq { + __u8 opcode; + __u8 flags; + __u16 command_id; + __u32 rsvd1[5]; + __le64 prp1; + __u64 rsvd8; + __le16 cqid; + __le16 qsize; + __le16 cq_flags; + __le16 irq_vector; + __u32 rsvd12[4]; +}; + +struct spraid_create_sq { + __u8 opcode; + __u8 flags; + __u16 command_id; + __u32 rsvd1[5]; + __le64 prp1; + __u64 rsvd8; + __le16 sqid; + __le16 qsize; + __le16 sq_flags; + __le16 cqid; + __u32 rsvd12[4]; +}; + +struct spraid_delete_queue { + __u8 opcode; + __u8 flags; + __u16 command_id; + __u32 rsvd1[9]; + __le16 qid; + __u16 rsvd10; + __u32 rsvd11[5]; +}; + +struct spraid_get_info { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + __u32 rsvd2[4]; + union spraid_data_ptr dptr; + __u8 type; + __u8 rsvd10[3]; + __le32 cdw11; + __u32 rsvd12[4]; +}; + +struct spraid_usr_cmd { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + union { + struct { + __le16 subopcode; + __le16 rsvd1; + } info_0; + __le32 cdw2; + }; + union { + struct { + __le16 data_len; + __le16 param_len; + } info_1; + __le32 cdw3; + }; + __u64 metadata; + union spraid_data_ptr dptr; + __le32 cdw10; + __le32 cdw11; + __le32 cdw12; + __le32 cdw13; + __le32 cdw14; + __le32 cdw15; +}; + +enum { + SPRAID_CMD_FLAG_SGL_METABUF = (1 << 6), + SPRAID_CMD_FLAG_SGL_METASEG = (1 << 7), + SPRAID_CMD_FLAG_SGL_ALL = SPRAID_CMD_FLAG_SGL_METABUF | + SPRAID_CMD_FLAG_SGL_METASEG, +}; + +enum spraid_cmd_state { + SPRAID_CMD_IDLE = 0, + SPRAID_CMD_IN_FLIGHT = 1, + SPRAID_CMD_COMPLETE = 2, + SPRAID_CMD_TIMEOUT = 3, + SPRAID_CMD_TMO_COMPLETE = 4, +}; + +struct spraid_abort_cmd { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + __u64 rsvd2[4]; + __le16 sqid; + __le16 cid; + __u32 rsvd11[5]; +}; + +struct spraid_reset_cmd { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + __u64 rsvd2[4]; + __u8 type; + __u8 rsvd10[3]; + __u32 rsvd11[5]; +}; + +struct spraid_admin_command { + union { + struct spraid_admin_common_command common; + struct spraid_features features; + struct spraid_create_cq create_cq; + struct spraid_create_sq create_sq; + struct spraid_delete_queue delete_queue; + struct spraid_get_info get_info; + struct spraid_abort_cmd abort; + struct spraid_reset_cmd reset; + struct spraid_usr_cmd usr_cmd; + }; +}; + +struct spraid_ioq_common_command { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + __le16 sense_len; + __u8 cdb_len; + __u8 rsvd2; + __le32 cdw3[3]; + union spraid_data_ptr dptr; + __le32 cdw10[6]; + __u8 cdb[32]; + __le64 sense_addr; + __le32 cdw26[6]; +}; + +struct spraid_rw_command { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + __le16 sense_len; + __u8 cdb_len; + __u8 rsvd2; + __u32 rsvd3[3]; + union spraid_data_ptr dptr; + __le64 slba; + __le16 nlb; + __le16 control; + __u32 rsvd13[3]; + __u8 cdb[32]; + __le64 sense_addr; + __u32 rsvd26[6]; +}; + +struct spraid_scsi_nonio { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + __le16 sense_len; + __u8 cdb_length; + __u8 rsvd2; + __u32 rsvd3[3]; + union spraid_data_ptr dptr; + __u32 rsvd10[5]; + __le32 buffer_len; + __u8 cdb[32]; + __le64 sense_addr; + __u32 rsvd26[6]; +}; + +struct spraid_ioq_command { + union { + struct spraid_ioq_common_command common; + struct spraid_rw_command rw; + struct spraid_scsi_nonio scsi_nonio; + }; +}; + +struct spraid_passthru_common_cmd { + __u8 opcode; + __u8 flags; + __u16 rsvd0; + __u32 nsid; + union { + struct { + __u16 subopcode; + __u16 rsvd1; + } info_0; + __u32 cdw2; + }; + union { + struct { + __u16 data_len; + __u16 param_len; + } info_1; + __u32 cdw3; + }; + __u64 metadata; + + __u64 addr; + __u64 prp2; + + __u32 cdw10; + __u32 cdw11; + __u32 cdw12; + __u32 cdw13; + __u32 cdw14; + __u32 cdw15; + __u32 timeout_ms; + __u32 result0; + __u32 result1; +}; + +struct spraid_ioq_passthru_cmd { + __u8 opcode; + __u8 flags; + __u16 rsvd0; + __u32 nsid; + union { + struct { + __u16 res_sense_len; + __u8 cdb_len; + __u8 rsvd0; + } info_0; + __u32 cdw2; + }; + union { + struct { + __u16 subopcode; + __u16 rsvd1; + } info_1; + __u32 cdw3; + }; + union { + struct { + __u16 rsvd; + __u16 param_len; + } info_2; + __u32 cdw4; + }; + __u32 cdw5; + __u64 addr; + __u64 prp2; + union { + struct { + __u16 eid; + __u16 sid; + } info_3; + __u32 cdw10; + }; + union { + struct { + __u16 did; + __u8 did_flag; + __u8 rsvd2; + } info_4; + __u32 cdw11; + }; + __u32 cdw12; + __u32 cdw13; + __u32 cdw14; + __u32 data_len; + __u32 cdw16; + __u32 cdw17; + __u32 cdw18; + __u32 cdw19; + __u32 cdw20; + __u32 cdw21; + __u32 cdw22; + __u32 cdw23; + __u64 sense_addr; + __u32 cdw26[4]; + __u32 timeout_ms; + __u32 result0; + __u32 result1; +}; + +struct spraid_bsg_request { + u32 msgcode; + u32 control; + union { + struct spraid_passthru_common_cmd admcmd; + struct spraid_ioq_passthru_cmd ioqcmd; + }; +}; + +enum { + SPRAID_BSG_ADM, + SPRAID_BSG_IOQ, +}; + +struct spraid_cmd { + int qid; + int cid; + u32 result0; + u32 result1; + u16 status; + void *priv; + enum spraid_cmd_state state; + struct completion cmd_done; + struct list_head list; +}; + +struct spraid_queue { + struct spraid_dev *hdev; + spinlock_t sq_lock; + + spinlock_t cq_lock ____cacheline_aligned_in_smp; + + void *sq_cmds; + + struct spraid_completion *cqes; + + dma_addr_t sq_dma_addr; + dma_addr_t cq_dma_addr; + u32 __iomem *q_db; + u8 cq_phase; + u8 sqes; + u16 qid; + u16 sq_tail; + u16 cq_head; + u16 last_cq_head; + u16 q_depth; + s16 cq_vector; + void *sense; + dma_addr_t sense_dma_addr; + struct dma_pool *prp_small_pool; +}; + +struct spraid_iod { + struct spraid_queue *spraidq; + enum spraid_cmd_state state; + int npages; + u32 nsge; + u32 length; + bool use_sgl; + bool sg_drv_mgmt; + dma_addr_t first_dma; + void *sense; + dma_addr_t sense_dma; + struct scatterlist *sg; + struct scatterlist inline_sg[0]; +}; + +#define SPRAID_DEV_INFO_ATTR_BOOT(attr) ((attr) & 0x01) +#define SPRAID_DEV_INFO_ATTR_VD(attr) (((attr) & 0x02) == 0x0) +#define SPRAID_DEV_INFO_ATTR_PT(attr) (((attr) & 0x22) == 0x02) +#define SPRAID_DEV_INFO_ATTR_RAWDISK(attr) ((attr) & 0x20) + +#define SPRAID_DEV_INFO_FLAG_VALID(flag) ((flag) & 0x01) +#define SPRAID_DEV_INFO_FLAG_CHANGE(flag) ((flag) & 0x02) + +#define BGTASK_TYPE_REBUILD 4 +#define USR_CMD_READ 0xc2 +#define USR_CMD_RDLEN 0x1000 +#define USR_CMD_VDINFO 0x704 +#define USR_CMD_BGTASK 0x504 +#define VDINFO_PARAM_LEN 0x04 + +struct spraid_vd_info { + __u8 name[32]; + __le16 id; + __u8 rg_id; + __u8 rg_level; + __u8 sg_num; + __u8 sg_disk_num; + __u8 vd_status; + __u8 vd_type; + __u8 rsvd1[4056]; +}; + +#define MAX_REALTIME_BGTASK_NUM 32 + +struct bgtask_info { + __u8 type; + __u8 progress; + __u8 rate; + __u8 rsvd0; + __le16 vd_id; + __le16 time_left; + __u8 rsvd1[4]; +}; + +struct spraid_bgtask { + __u8 sw; + __u8 task_num; + __u8 rsvd[6]; + struct bgtask_info bgtask[MAX_REALTIME_BGTASK_NUM]; +}; + +struct spraid_dev_info { + __le32 hdid; + __le16 target; + __u8 channel; + __u8 lun; + __u8 attr; + __u8 flag; + __le16 max_io_kb; +}; + +#define MAX_DEV_ENTRY_PER_PAGE_4K 340 +struct spraid_dev_list { + __le32 dev_num; + __u32 rsvd0[3]; + struct spraid_dev_info devices[MAX_DEV_ENTRY_PER_PAGE_4K]; +}; + +struct spraid_sdev_hostdata { + u32 hdid; + u16 max_io_kb; + u8 attr; + u8 flag; + u8 rg_id; + u8 rsvd[3]; +}; + +#endif + diff --git a/drivers/scsi/spraid/spraid_main.c b/drivers/scsi/spraid/spraid_main.c new file mode 100644 index 000000000000..519b39f44e91 --- /dev/null +++ b/drivers/scsi/spraid/spraid_main.c @@ -0,0 +1,3875 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2021 Ramaxel Memory Technology, Ltd */ + +/* Ramaxel Raid SPXXX Series Linux Driver */ + +#define pr_fmt(fmt) "spraid: " fmt + +#include <linux/sched/signal.h> +#include <linux/version.h> +#include <linux/pci.h> +#include <linux/aer.h> +#include <linux/module.h> +#include <linux/ioport.h> +#include <linux/device.h> +#include <linux/delay.h> +#include <linux/interrupt.h> +#include <linux/cdev.h> +#include <linux/sysfs.h> +#include <linux/gfp.h> +#include <linux/types.h> +#include <linux/ratelimit.h> +#include <linux/once.h> +#include <linux/debugfs.h> +#include <linux/io-64-nonatomic-lo-hi.h> +#include <linux/blkdev.h> +#include <linux/bsg-lib.h> +#include <asm/unaligned.h> +#include <linux/sort.h> +#include <target/target_core_backend.h> + +#include <scsi/scsi.h> +#include <scsi/scsi_cmnd.h> +#include <scsi/scsi_device.h> +#include <scsi/scsi_host.h> +#include <scsi/scsi_transport.h> +#include <scsi/scsi_dbg.h> + + +#include "spraid.h" + +static u32 admin_tmout = 60; +module_param(admin_tmout, uint, 0644); +MODULE_PARM_DESC(admin_tmout, "admin commands timeout (seconds)"); + +static u32 scmd_tmout_nonpt = 180; +module_param(scmd_tmout_nonpt, uint, 0644); +MODULE_PARM_DESC(scmd_tmout_nonpt, + "scsi commands timeout for rawdisk&raid(seconds)"); + +static int ioq_depth_set(const char *val, const struct kernel_param *kp); +static const struct kernel_param_ops ioq_depth_ops = { + .set = ioq_depth_set, + .get = param_get_uint, +}; + +static u32 io_queue_depth = 1024; +module_param_cb(io_queue_depth, &ioq_depth_ops, &io_queue_depth, 0644); +MODULE_PARM_DESC(io_queue_depth, "set io queue depth, should >= 2"); + +static int log_debug_switch_set(const char *val, const struct kernel_param *kp) +{ + u8 n = 0; + int ret; + + ret = kstrtou8(val, 10, &n); + if (ret != 0) + return -EINVAL; + + return param_set_byte(val, kp); +} + +static const struct kernel_param_ops log_debug_switch_ops = { + .set = log_debug_switch_set, + .get = param_get_byte, +}; + +static unsigned char log_debug_switch; +module_param_cb(log_debug_switch, &log_debug_switch_ops, + &log_debug_switch, 0644); +MODULE_PARM_DESC(log_debug_switch, + "set log state, default non-zero for switch on"); + +static int small_pool_num_set(const char *val, const struct kernel_param *kp) +{ + u8 n = 0; + int ret; + + ret = kstrtou8(val, 10, &n); + if (ret != 0) + return -EINVAL; + if (n > MAX_SMALL_POOL_NUM) + n = MAX_SMALL_POOL_NUM; + if (n < 1) + n = 1; + *((u8 *)kp->arg) = n; + + return 0; +} + +static const struct kernel_param_ops small_pool_num_ops = { + .set = small_pool_num_set, + .get = param_get_byte, +}; + +/* It was found that the spindlock of a single pool conflicts + * a lot with multiple CPUs.So multiple pools are introduced + * to reduce the conflictions. + */ +static unsigned char small_pool_num = 4; +module_param_cb(small_pool_num, &small_pool_num_ops, &small_pool_num, 0644); +MODULE_PARM_DESC(small_pool_num, "set prp small pool num, default 4, MAX 16"); + +static void spraid_free_queue(struct spraid_queue *spraidq); +static void spraid_handle_aen_notice(struct spraid_dev *hdev, u32 result); +static void spraid_handle_aen_vs(struct spraid_dev *hdev, + u32 result, u32 result1); + +static DEFINE_IDA(spraid_instance_ida); + +static struct class *spraid_class; + +#define SPRAID_CAP_TIMEOUT_UNIT_MS (HZ / 2) + +static struct workqueue_struct *spraid_wq; + +#define dev_log_dbg(dev, fmt, ...) do { \ + if (unlikely(log_debug_switch)) \ + dev_info(dev, "[%s] [%d] " fmt, \ + __func__, __LINE__, ##__VA_ARGS__); \ +} while (0) + +#define SPRAID_DRV_VERSION "1.0.0.0" + +#define ADMIN_TIMEOUT (admin_tmout * HZ) +#define ADMIN_ERR_TIMEOUT 32757 + +#define SPRAID_WAIT_ABNL_CMD_TIMEOUT (3 * 2) + +#define SPRAID_DMA_MSK_BIT_MAX 64 + +enum FW_STAT_CODE { + FW_STAT_OK = 0, + FW_STAT_NEED_CHECK, + FW_STAT_ERROR, + FW_STAT_EP_PCIE_ERROR, + FW_STAT_NAC_DMA_ERROR, + FW_STAT_ABORTED, + FW_STAT_NEED_RETRY +}; + +static const char * const raid_levels[] = {"0", "1", "5", "6", "10", "50", "60", + "NA"}; + +static const char * const raid_states[] = { + "NA", "NORMAL", "FAULT", "DEGRADE", "NOT_FORMATTED", + "FORMATTING", "SANITIZING", "INITIALIZING", "INITIALIZE_FAIL", + "DELETING", "DELETE_FAIL", "WRITE_PROTECT" +}; + +static int ioq_depth_set(const char *val, const struct kernel_param *kp) +{ + int n = 0; + int ret; + + ret = kstrtoint(val, 10, &n); + if (ret != 0 || n < 2) + return -EINVAL; + + return param_set_int(val, kp); +} + +static int spraid_remap_bar(struct spraid_dev *hdev, u32 size) +{ + struct pci_dev *pdev = hdev->pdev; + + if (size > pci_resource_len(pdev, 0)) { + dev_err(hdev->dev, "Input size[%u] exceed bar0 length[%llu]\n", + size, pci_resource_len(pdev, 0)); + return -ENOMEM; + } + + if (hdev->bar) + iounmap(hdev->bar); + + hdev->bar = ioremap(pci_resource_start(pdev, 0), size); + if (!hdev->bar) { + dev_err(hdev->dev, "ioremap for bar0 failed\n"); + return -ENOMEM; + } + hdev->dbs = hdev->bar + SPRAID_REG_DBS; + + return 0; +} + +static int spraid_dev_map(struct spraid_dev *hdev) +{ + struct pci_dev *pdev = hdev->pdev; + int ret; + + ret = pci_request_mem_regions(pdev, "spraid"); + if (ret) { + dev_err(hdev->dev, "fail to request memory regions\n"); + return ret; + } + + ret = spraid_remap_bar(hdev, SPRAID_REG_DBS + 4096); + if (ret) { + pci_release_mem_regions(pdev); + return ret; + } + + return 0; +} + +static void spraid_dev_unmap(struct spraid_dev *hdev) +{ + struct pci_dev *pdev = hdev->pdev; + + if (hdev->bar) { + iounmap(hdev->bar); + hdev->bar = NULL; + } + pci_release_mem_regions(pdev); +} + +static int spraid_pci_enable(struct spraid_dev *hdev) +{ + struct pci_dev *pdev = hdev->pdev; + int ret = -ENOMEM; + u64 maskbit = SPRAID_DMA_MSK_BIT_MAX; + + if (pci_enable_device_mem(pdev)) { + dev_err(hdev->dev, + "Enable pci device memory resources failed\n"); + return ret; + } + pci_set_master(pdev); + + if (readl(hdev->bar + SPRAID_REG_CSTS) == U32_MAX) { + ret = -ENODEV; + dev_err(hdev->dev, "Read csts register failed\n"); + goto disable; + } + + ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES); + if (ret < 0) { + dev_err(hdev->dev, + "Allocate one IRQ for setup admin channel failed\n"); + goto disable; + } + + hdev->cap = lo_hi_readq(hdev->bar + SPRAID_REG_CAP); + hdev->ioq_depth = min_t(u32, SPRAID_CAP_MQES(hdev->cap) + 1, + io_queue_depth); + hdev->db_stride = 1 << SPRAID_CAP_STRIDE(hdev->cap); + + maskbit = SPRAID_CAP_DMAMASK(hdev->cap); + if (maskbit < 32 || maskbit > SPRAID_DMA_MSK_BIT_MAX) { + dev_err(hdev->dev, + "err, dma mask invalid[%llu], set to default\n", + maskbit); + maskbit = SPRAID_DMA_MSK_BIT_MAX; + } + if (dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(maskbit))) { + dev_err(hdev->dev, "set dma mask and coherent failed\n"); + goto disable; + } + + dev_info(hdev->dev, "set dma mask[%llu] success\n", maskbit); + + pci_enable_pcie_error_reporting(pdev); + pci_save_state(pdev); + + return 0; + +disable: + pci_disable_device(pdev); + return ret; +} + +static int spraid_npages_prp(u32 size, struct spraid_dev *hdev) +{ + u32 nprps = DIV_ROUND_UP(size + hdev->page_size, hdev->page_size); + + return DIV_ROUND_UP(PRP_ENTRY_SIZE * nprps, PAGE_SIZE - PRP_ENTRY_SIZE); +} + +static int spraid_npages_sgl(u32 nseg) +{ + return DIV_ROUND_UP(nseg * sizeof(struct spraid_sgl_desc), PAGE_SIZE); +} + +static void **spraid_iod_list(struct spraid_iod *iod) +{ + return (void **)(iod->inline_sg + (iod->sg_drv_mgmt ? iod->nsge : 0)); +} + +static u32 spraid_iod_ext_size(struct spraid_dev *hdev, u32 size, u32 nsge, + bool sg_drv_mgmt, bool use_sgl) +{ + size_t alloc_size, sg_size; + + if (use_sgl) + alloc_size = sizeof(__le64 *) * spraid_npages_sgl(nsge); + else + alloc_size = sizeof(__le64 *) * spraid_npages_prp(size, hdev); + + sg_size = sg_drv_mgmt ? (sizeof(struct scatterlist) * nsge) : 0; + return sg_size + alloc_size; +} + +static u32 spraid_cmd_size(struct spraid_dev *hdev, + bool sg_drv_mgmt, bool use_sgl) +{ + u32 alloc_size = spraid_iod_ext_size(hdev, SPRAID_INT_BYTES(hdev), + SPRAID_INT_PAGES, sg_drv_mgmt, use_sgl); + + dev_info(hdev->dev, "sg_drv_mgmt: %s, use_sgl: %s, iod size: %lu;" + " alloc_size: %u\n", sg_drv_mgmt ? "true" : "false", + use_sgl ? "true" : "false", + sizeof(struct spraid_iod), alloc_size); + + return sizeof(struct spraid_iod) + alloc_size; +} + +static int spraid_setup_prps(struct spraid_dev *hdev, struct spraid_iod *iod) +{ + struct scatterlist *sg = iod->sg; + u64 dma_addr = sg_dma_address(sg); + int dma_len = sg_dma_len(sg); + __le64 *prp_list, *old_prp_list; + u32 page_size = hdev->page_size; + int offset = dma_addr & (page_size - 1); + void **list = spraid_iod_list(iod); + int length = iod->length; + struct dma_pool *pool; + dma_addr_t prp_dma; + int nprps, i; + + length -= (page_size - offset); + if (length <= 0) { + iod->first_dma = 0; + return 0; + } + + dma_len -= (page_size - offset); + if (dma_len) { + dma_addr += (page_size - offset); + } else { + sg = sg_next(sg); + dma_addr = sg_dma_address(sg); + dma_len = sg_dma_len(sg); + } + + if (length <= page_size) { + iod->first_dma = dma_addr; + return 0; + } + + nprps = DIV_ROUND_UP(length, page_size); + if (nprps <= (SMALL_POOL_SIZE / PRP_ENTRY_SIZE)) { + pool = iod->spraidq->prp_small_pool; + iod->npages = 0; + } else { + pool = hdev->prp_page_pool; + iod->npages = 1; + } + + prp_list = dma_pool_alloc(pool, GFP_ATOMIC, &prp_dma); + if (!prp_list) { + dev_err_ratelimited(hdev->dev, + "Allocate first prp_list memory failed\n"); + iod->first_dma = dma_addr; + iod->npages = -1; + return -ENOMEM; + } + list[0] = prp_list; + iod->first_dma = prp_dma; + i = 0; + for (;;) { + if (i == page_size / PRP_ENTRY_SIZE) { + old_prp_list = prp_list; + + prp_list = dma_pool_alloc(pool, GFP_ATOMIC, &prp_dma); + if (!prp_list) { + dev_err_ratelimited(hdev->dev, "Allocate %dth;" + " prp_list memory failed\n", + iod->npages + 1); + return -ENOMEM; + } + list[iod->npages++] = prp_list; + prp_list[0] = old_prp_list[i - 1]; + old_prp_list[i - 1] = cpu_to_le64(prp_dma); + i = 1; + } + prp_list[i++] = cpu_to_le64(dma_addr); + dma_len -= page_size; + dma_addr += page_size; + length -= page_size; + if (length <= 0) + break; + if (dma_len > 0) + continue; + if (unlikely(dma_len < 0)) + goto bad_sgl; + sg = sg_next(sg); + dma_addr = sg_dma_address(sg); + dma_len = sg_dma_len(sg); + } + + return 0; + +bad_sgl: + dev_err(hdev->dev, + "Setup prps, invalid SGL for payload: %d nents: %d\n", + iod->length, iod->nsge); + return -EIO; +} + +#define SGES_PER_PAGE (PAGE_SIZE / sizeof(struct spraid_sgl_desc)) + +static void spraid_submit_cmd(struct spraid_queue *spraidq, const void *cmd) +{ + u32 sqes = SQE_SIZE(spraidq->qid); + unsigned long flags; + struct spraid_admin_common_command *acd = + (struct spraid_admin_common_command *)cmd; + + spin_lock_irqsave(&spraidq->sq_lock, flags); + memcpy((spraidq->sq_cmds + sqes * spraidq->sq_tail), cmd, sqes); + if (++spraidq->sq_tail == spraidq->q_depth) + spraidq->sq_tail = 0; + + writel(spraidq->sq_tail, spraidq->q_db); + spin_unlock_irqrestore(&spraidq->sq_lock, flags); + + dev_log_dbg(spraidq->hdev->dev, + "cid[%d] qid[%d], opcode[0x%x], flags[0x%x], hdid[%u]\n", + acd->command_id, spraidq->qid, acd->opcode, + acd->flags, le32_to_cpu(acd->hdid)); +} + +static u32 spraid_mod64(u64 dividend, u32 divisor) +{ + u64 d; + u32 remainder; + + if (!divisor) + pr_err("DIVISOR is zero, in div fn\n"); + + d = dividend; + remainder = do_div(d, divisor); + return remainder; +} + +static inline bool spraid_is_rw_scmd(struct scsi_cmnd *scmd) +{ + switch (scmd->cmnd[0]) { + case READ_6: + case READ_10: + case READ_12: + case READ_16: + case READ_32: + case WRITE_6: + case WRITE_10: + case WRITE_12: + case WRITE_16: + case WRITE_32: + return true; + default: + return false; + } +} + +static bool spraid_is_prp(struct spraid_dev *hdev, + struct scsi_cmnd *scmd, u32 nsge) +{ + struct scatterlist *sg = scsi_sglist(scmd); + u32 page_size = hdev->page_size; + bool is_prp = true; + int i = 0; + + scsi_for_each_sg(scmd, sg, nsge, i) { + if (i != 0 && i != nsge - 1) { + if (spraid_mod64(sg_dma_len(sg), page_size) || + spraid_mod64(sg_dma_address(sg), page_size)) { + is_prp = false; + break; + } + } + + if (nsge > 1 && i == 0) { + if ((spraid_mod64((sg_dma_address(sg) + sg_dma_len(sg)), + page_size))) { + is_prp = false; + break; + } + } + + if (nsge > 1 && i == (nsge - 1)) { + if (spraid_mod64(sg_dma_address(sg), page_size)) { + is_prp = false; + break; + } + } + } + + return is_prp; +} + +enum { + SPRAID_SGL_FMT_DATA_DESC = 0x00, + SPRAID_SGL_FMT_SEG_DESC = 0x02, + SPRAID_SGL_FMT_LAST_SEG_DESC = 0x03, + SPRAID_KEY_SGL_FMT_DATA_DESC = 0x04, + SPRAID_TRANSPORT_SGL_DATA_DESC = 0x05 +}; + +static void spraid_sgl_set_data(struct spraid_sgl_desc *sge, + struct scatterlist *sg) +{ + sge->addr = cpu_to_le64(sg_dma_address(sg)); + sge->length = cpu_to_le32(sg_dma_len(sg)); + sge->type = SPRAID_SGL_FMT_DATA_DESC << 4; +} + +static void spraid_sgl_set_seg(struct spraid_sgl_desc *sge, + dma_addr_t dma_addr, int entries) +{ + sge->addr = cpu_to_le64(dma_addr); + if (entries <= SGES_PER_PAGE) { + sge->length = cpu_to_le32(entries * sizeof(*sge)); + sge->type = SPRAID_SGL_FMT_LAST_SEG_DESC << 4; + } else { + sge->length = cpu_to_le32(PAGE_SIZE); + sge->type = SPRAID_SGL_FMT_SEG_DESC << 4; + } +} + +static int spraid_setup_ioq_cmd_sgl(struct spraid_dev *hdev, + struct scsi_cmnd *scmd, + struct spraid_ioq_command *ioq_cmd, + struct spraid_iod *iod) +{ + struct spraid_sgl_desc *sg_list, *link, *old_sg_list; + struct scatterlist *sg = scsi_sglist(scmd); + void **list = spraid_iod_list(iod); + struct dma_pool *pool; + int nsge = iod->nsge; + dma_addr_t sgl_dma; + int i = 0; + + ioq_cmd->common.flags |= SPRAID_CMD_FLAG_SGL_METABUF; + + if (nsge == 1) { + spraid_sgl_set_data(&ioq_cmd->common.dptr.sgl, sg); + return 0; + } + + if (nsge <= (SMALL_POOL_SIZE / sizeof(struct spraid_sgl_desc))) { + pool = iod->spraidq->prp_small_pool; + iod->npages = 0; + } else { + pool = hdev->prp_page_pool; + iod->npages = 1; + } + + sg_list = dma_pool_alloc(pool, GFP_ATOMIC, &sgl_dma); + if (!sg_list) { + dev_err_ratelimited(hdev->dev, + "Allocate first sgl_list failed\n"); + iod->npages = -1; + return -ENOMEM; + } + + list[0] = sg_list; + iod->first_dma = sgl_dma; + spraid_sgl_set_seg(&ioq_cmd->common.dptr.sgl, sgl_dma, nsge); + do { + if (i == SGES_PER_PAGE) { + old_sg_list = sg_list; + link = &old_sg_list[SGES_PER_PAGE - 1]; + + sg_list = dma_pool_alloc(pool, GFP_ATOMIC, &sgl_dma); + if (!sg_list) { + dev_err_ratelimited(hdev->dev, + "Allocate %dth sgl_list;" + " failed\n", + iod->npages + 1); + return -ENOMEM; + } + list[iod->npages++] = sg_list; + + i = 0; + memcpy(&sg_list[i++], link, sizeof(*link)); + spraid_sgl_set_seg(link, sgl_dma, nsge); + } + + spraid_sgl_set_data(&sg_list[i++], sg); + sg = sg_next(sg); + } while (--nsge > 0); + + return 0; +} + +#define SPRAID_RW_FUA BIT(14) + +static void spraid_setup_rw_cmd(struct spraid_dev *hdev, + struct spraid_rw_command *rw, + struct scsi_cmnd *scmd) +{ + u32 start_lba_lo, start_lba_hi; + u32 datalength = 0; + u16 control = 0; + + start_lba_lo = 0; + start_lba_hi = 0; + + if (scmd->sc_data_direction == DMA_TO_DEVICE) { + rw->opcode = SPRAID_CMD_WRITE; + } else if (scmd->sc_data_direction == DMA_FROM_DEVICE) { + rw->opcode = SPRAID_CMD_READ; + } else { + dev_err(hdev->dev, + "Invalid IO for unsupported data direction: %d\n", + scmd->sc_data_direction); + WARN_ON(1); + } + + /* 6-byte READ(0x08) or WRITE(0x0A) cdb */ + if (scmd->cmd_len == 6) { + datalength = (u32)(scmd->cmnd[4] == 0 ? + IO_6_DEFAULT_TX_LEN : scmd->cmnd[4]); + start_lba_lo = (u32)get_unaligned_be24(&scmd->cmnd[1]); + + start_lba_lo &= 0x1FFFFF; + } + + /* 10-byte READ(0x28) or WRITE(0x2A) cdb */ + else if (scmd->cmd_len == 10) { + datalength = (u32)get_unaligned_be16(&scmd->cmnd[7]); + start_lba_lo = get_unaligned_be32(&scmd->cmnd[2]); + + if (scmd->cmnd[1] & FUA_MASK) + control |= SPRAID_RW_FUA; + } + + /* 12-byte READ(0xA8) or WRITE(0xAA) cdb */ + else if (scmd->cmd_len == 12) { + datalength = get_unaligned_be32(&scmd->cmnd[6]); + start_lba_lo = get_unaligned_be32(&scmd->cmnd[2]); + + if (scmd->cmnd[1] & FUA_MASK) + control |= SPRAID_RW_FUA; + } + /* 16-byte READ(0x88) or WRITE(0x8A) cdb */ + else if (scmd->cmd_len == 16) { + datalength = get_unaligned_be32(&scmd->cmnd[10]); + start_lba_lo = get_unaligned_be32(&scmd->cmnd[6]); + start_lba_hi = get_unaligned_be32(&scmd->cmnd[2]); + + if (scmd->cmnd[1] & FUA_MASK) + control |= SPRAID_RW_FUA; + } + /* 32-byte READ(0x88) or WRITE(0x8A) cdb */ + else if (scmd->cmd_len == 32) { + datalength = get_unaligned_be32(&scmd->cmnd[28]); + start_lba_lo = get_unaligned_be32(&scmd->cmnd[16]); + start_lba_hi = get_unaligned_be32(&scmd->cmnd[12]); + + if (scmd->cmnd[10] & FUA_MASK) + control |= SPRAID_RW_FUA; + } + + if (unlikely(datalength > U16_MAX || datalength == 0)) { + dev_err(hdev->dev, + "Invalid IO for illegal transfer data length: %u\n", + datalength); + WARN_ON(1); + } + + rw->slba = cpu_to_le64(((u64)start_lba_hi << 32) | start_lba_lo); + /* 0base for nlb */ + rw->nlb = cpu_to_le16((u16)(datalength - 1)); + rw->control = cpu_to_le16(control); +} + +static void spraid_setup_nonio_cmd(struct spraid_dev *hdev, + struct spraid_scsi_nonio *scsi_nonio, + struct scsi_cmnd *scmd) +{ + scsi_nonio->buffer_len = cpu_to_le32(scsi_bufflen(scmd)); + + switch (scmd->sc_data_direction) { + case DMA_NONE: + scsi_nonio->opcode = SPRAID_CMD_NONIO_NONE; + break; + case DMA_TO_DEVICE: + scsi_nonio->opcode = SPRAID_CMD_NONIO_TODEV; + break; + case DMA_FROM_DEVICE: + scsi_nonio->opcode = SPRAID_CMD_NONIO_FROMDEV; + break; + default: + dev_err(hdev->dev, + "Invalid IO for unsupported data direction: %d\n", + scmd->sc_data_direction); + WARN_ON(1); + } +} + +static void spraid_setup_ioq_cmd(struct spraid_dev *hdev, + struct spraid_ioq_command *ioq_cmd, + struct scsi_cmnd *scmd) +{ + memcpy(ioq_cmd->common.cdb, scmd->cmnd, scmd->cmd_len); + ioq_cmd->common.cdb_len = scmd->cmd_len; + + if (spraid_is_rw_scmd(scmd)) + spraid_setup_rw_cmd(hdev, &ioq_cmd->rw, scmd); + else + spraid_setup_nonio_cmd(hdev, &ioq_cmd->scsi_nonio, scmd); +} + +static int spraid_init_iod(struct spraid_dev *hdev, struct spraid_iod *iod, + struct spraid_ioq_command *ioq_cmd, + struct scsi_cmnd *scmd) +{ + if (unlikely(!iod->sense)) { + dev_err(hdev->dev, "Allocate sense data buffer failed\n"); + return -ENOMEM; + } + ioq_cmd->common.sense_addr = cpu_to_le64(iod->sense_dma); + ioq_cmd->common.sense_len = cpu_to_le16(SCSI_SENSE_BUFFERSIZE); + + iod->nsge = 0; + iod->npages = -1; + iod->use_sgl = 0; + iod->sg_drv_mgmt = false; + WRITE_ONCE(iod->state, SPRAID_CMD_IDLE); + + return 0; +} + +static void spraid_free_iod_res(struct spraid_dev *hdev, struct spraid_iod *iod) +{ + const int last_prp = hdev->page_size / sizeof(__le64) - 1; + dma_addr_t dma_addr, next_dma_addr; + struct spraid_sgl_desc *sg_list; + __le64 *prp_list; + void *addr; + int i; + + dma_addr = iod->first_dma; + if (iod->npages == 0) + dma_pool_free(iod->spraidq->prp_small_pool, + spraid_iod_list(iod)[0], dma_addr); + + for (i = 0; i < iod->npages; i++) { + addr = spraid_iod_list(iod)[i]; + + if (iod->use_sgl) { + sg_list = addr; + next_dma_addr = + le64_to_cpu((sg_list[SGES_PER_PAGE - 1]).addr); + } else { + prp_list = addr; + next_dma_addr = le64_to_cpu(prp_list[last_prp]); + } + + dma_pool_free(hdev->prp_page_pool, addr, dma_addr); + dma_addr = next_dma_addr; + } + + if (iod->sg_drv_mgmt && iod->sg != iod->inline_sg) { + iod->sg_drv_mgmt = false; + mempool_free(iod->sg, hdev->iod_mempool); + } + + iod->sense = NULL; + iod->npages = -1; +} + +static int spraid_io_map_data(struct spraid_dev *hdev, struct spraid_iod *iod, + struct scsi_cmnd *scmd, + struct spraid_ioq_command *ioq_cmd) +{ + int ret; + + iod->nsge = scsi_dma_map(scmd); + + /* No data to DMA, it may be scsi no-rw command */ + if (unlikely(iod->nsge == 0)) + return 0; + + iod->length = scsi_bufflen(scmd); + iod->sg = scsi_sglist(scmd); + iod->use_sgl = !spraid_is_prp(hdev, scmd, iod->nsge); + + if (iod->use_sgl) { + ret = spraid_setup_ioq_cmd_sgl(hdev, scmd, ioq_cmd, iod); + } else { + ret = spraid_setup_prps(hdev, iod); + ioq_cmd->common.dptr.prp1 = + cpu_to_le64(sg_dma_address(iod->sg)); + ioq_cmd->common.dptr.prp2 = cpu_to_le64(iod->first_dma); + } + + if (ret) + scsi_dma_unmap(scmd); + + return ret; +} + +static void spraid_map_status(struct spraid_iod *iod, struct scsi_cmnd *scmd, + struct spraid_completion *cqe) +{ + scsi_set_resid(scmd, 0); + + switch ((le16_to_cpu(cqe->status) >> 1) & 0x7f) { + case FW_STAT_OK: + set_host_byte(scmd, DID_OK); + break; + case FW_STAT_NEED_CHECK: + set_host_byte(scmd, DID_OK); + scmd->result |= le16_to_cpu(cqe->status) >> 8; + if (scmd->result & SAM_STAT_CHECK_CONDITION) { + memset(scmd->sense_buffer, 0, SCSI_SENSE_BUFFERSIZE); + memcpy(scmd->sense_buffer, iod->sense, + SCSI_SENSE_BUFFERSIZE); + scmd->result = + (scmd->result & 0x00ffffff) | (DRIVER_SENSE << 24); + } + break; + case FW_STAT_ABORTED: + set_host_byte(scmd, DID_ABORT); + break; + case FW_STAT_NEED_RETRY: + set_host_byte(scmd, DID_REQUEUE); + break; + default: + set_host_byte(scmd, DID_BAD_TARGET); + break; + } +} + +static inline void spraid_get_tag_from_scmd(struct scsi_cmnd *scmd, + u16 *qid, u16 *cid) +{ + u32 tag = blk_mq_unique_tag(scmd->request); + + *qid = blk_mq_unique_tag_to_hwq(tag) + 1; + *cid = blk_mq_unique_tag_to_tag(tag); +} + +static int spraid_queue_command(struct Scsi_Host *shost, struct scsi_cmnd *scmd) +{ + struct spraid_iod *iod = scsi_cmd_priv(scmd); + struct spraid_dev *hdev = shost_priv(shost); + struct scsi_device *sdev = scmd->device; + struct spraid_sdev_hostdata *hostdata; + struct spraid_ioq_command ioq_cmd; + struct spraid_queue *ioq; + unsigned long elapsed; + u16 hwq, cid; + int ret; + + if (unlikely(!scmd)) { + dev_err(hdev->dev, "err, scmd is null\n"); + return 0; + } + + if (unlikely(hdev->state != SPRAID_LIVE)) { + set_host_byte(scmd, DID_NO_CONNECT); + scmd->scsi_done(scmd); + return 0; + } + + if (log_debug_switch) + scsi_print_command(scmd); + + spraid_get_tag_from_scmd(scmd, &hwq, &cid); + hostdata = sdev->hostdata; + ioq = &hdev->queues[hwq]; + memset(&ioq_cmd, 0, sizeof(ioq_cmd)); + ioq_cmd.rw.hdid = cpu_to_le32(hostdata->hdid); + ioq_cmd.rw.command_id = cid; + + spraid_setup_ioq_cmd(hdev, &ioq_cmd, scmd); + + ret = cid * SCSI_SENSE_BUFFERSIZE; + iod->sense = ioq->sense + ret; + iod->sense_dma = ioq->sense_dma_addr + ret; + + ret = spraid_init_iod(hdev, iod, &ioq_cmd, scmd); + if (unlikely(ret)) + return SCSI_MLQUEUE_HOST_BUSY; + + iod->spraidq = ioq; + ret = spraid_io_map_data(hdev, iod, scmd, &ioq_cmd); + if (unlikely(ret)) { + dev_err(hdev->dev, "spraid_io_map_data Err.\n"); + set_host_byte(scmd, DID_ERROR); + scmd->scsi_done(scmd); + ret = 0; + goto deinit_iod; + } + + WRITE_ONCE(iod->state, SPRAID_CMD_IN_FLIGHT); + spraid_submit_cmd(ioq, &ioq_cmd); + elapsed = jiffies - scmd->jiffies_at_alloc; + dev_log_dbg(hdev->dev, + "cid[%d] qid[%d] submit IO cost %3ld.%3ld seconds\n", + cid, hwq, elapsed / HZ, elapsed % HZ); + return 0; + +deinit_iod: + spraid_free_iod_res(hdev, iod); + return ret; +} + +static int spraid_match_dev(struct spraid_dev *hdev, u16 idx, + struct scsi_device *sdev) +{ + if (SPRAID_DEV_INFO_FLAG_VALID(hdev->devices[idx].flag)) { + if (sdev->channel == hdev->devices[idx].channel && + sdev->id == le16_to_cpu(hdev->devices[idx].target) && + sdev->lun < hdev->devices[idx].lun) { + dev_info(hdev->dev, + "Match device success, channel;" + "target:lun[%d:%d:%d]\n", + hdev->devices[idx].channel, + hdev->devices[idx].target, + hdev->devices[idx].lun); + return 1; + } + } + + return 0; +} + +static int spraid_slave_alloc(struct scsi_device *sdev) +{ + struct spraid_sdev_hostdata *hostdata; + struct spraid_dev *hdev; + u16 idx; + + hdev = shost_priv(sdev->host); + hostdata = kzalloc(sizeof(*hostdata), GFP_KERNEL); + if (!hostdata) { + dev_err(hdev->dev, "Alloc scsi host data memory failed\n"); + return -ENOMEM; + } + + down_read(&hdev->devices_rwsem); + for (idx = 0; idx < le32_to_cpu(hdev->ctrl_info->nd); idx++) { + if (spraid_match_dev(hdev, idx, sdev)) + goto scan_host; + } + up_read(&hdev->devices_rwsem); + + kfree(hostdata); + return -ENXIO; + +scan_host: + hostdata->hdid = le32_to_cpu(hdev->devices[idx].hdid); + hostdata->max_io_kb = le16_to_cpu(hdev->devices[idx].max_io_kb); + hostdata->attr = hdev->devices[idx].attr; + hostdata->flag = hdev->devices[idx].flag; + hostdata->rg_id = 0xff; + sdev->hostdata = hostdata; + up_read(&hdev->devices_rwsem); + return 0; +} + +static void spraid_slave_destroy(struct scsi_device *sdev) +{ + kfree(sdev->hostdata); + sdev->hostdata = NULL; +} + +static int spraid_slave_configure(struct scsi_device *sdev) +{ + u16 idx; + unsigned int timeout = scmd_tmout_nonpt * HZ; + struct spraid_dev *hdev = shost_priv(sdev->host); + struct spraid_sdev_hostdata *hostdata = sdev->hostdata; + u32 max_sec = sdev->host->max_sectors; + + if (hostdata) { + idx = hostdata->hdid - 1; + if (sdev->channel == hdev->devices[idx].channel && + sdev->id == le16_to_cpu(hdev->devices[idx].target) && + sdev->lun < hdev->devices[idx].lun) { + if (SPRAID_DEV_INFO_ATTR_PT(hdev->devices[idx].attr)) + timeout = 30 * HZ; + else + timeout = scmd_tmout_nonpt * HZ; + max_sec = le16_to_cpu(hdev->devices[idx].max_io_kb) + << 1; + } else { + dev_err(hdev->dev, + "[%s] err, sdev->channel:id:lun[%d:%d:%lld];" + "devices[%d], channel:target:lun[%d:%d:%d]\n", + __func__, sdev->channel, sdev->id, sdev->lun, + idx, hdev->devices[idx].channel, + hdev->devices[idx].target, + hdev->devices[idx].lun); + } + } else { + dev_err(hdev->dev, "[%s] err, sdev->hostdata is null\n", + __func__); + } + + blk_queue_rq_timeout(sdev->request_queue, timeout); + sdev->eh_timeout = timeout; + + if ((max_sec == 0) || (max_sec > sdev->host->max_sectors)) + max_sec = sdev->host->max_sectors; + + dev_info(hdev->dev, + "[%s] sdev->channel:id:lun[%d:%d:%lld];" + " scmd_timeout[%d]s, maxsec[%d]\n", + __func__, sdev->channel, sdev->id, + sdev->lun, timeout / HZ, max_sec); + + return 0; +} + +static void spraid_shost_init(struct spraid_dev *hdev) +{ + struct pci_dev *pdev = hdev->pdev; + u8 domain, bus; + u32 dev_func; + + domain = pci_domain_nr(pdev->bus); + bus = pdev->bus->number; + dev_func = pdev->devfn; + + hdev->shost->nr_hw_queues = hdev->online_queues - 1; + hdev->shost->can_queue = (hdev->ioq_depth - SPRAID_PTCMDS_PERQ); + + hdev->shost->sg_tablesize = le16_to_cpu(hdev->ctrl_info->max_num_sge); + /* 512B per sector */ + hdev->shost->max_sectors = + (1U << ((hdev->ctrl_info->mdts) * 1U) << 12) / 512; + hdev->shost->cmd_per_lun = MAX_CMD_PER_DEV; + hdev->shost->max_channel = + le16_to_cpu(hdev->ctrl_info->max_channel) - 1; + hdev->shost->max_id = le32_to_cpu(hdev->ctrl_info->max_tgt_id); + hdev->shost->max_lun = le16_to_cpu(hdev->ctrl_info->max_lun); + + hdev->shost->this_id = -1; + hdev->shost->unique_id = (domain << 16) | (bus << 8) | dev_func; + hdev->shost->max_cmd_len = MAX_CDB_LEN; + hdev->shost->hostt->cmd_size = max(spraid_cmd_size(hdev, false, true), + spraid_cmd_size(hdev, false, false)); +} + +static inline void spraid_host_deinit(struct spraid_dev *hdev) +{ + ida_free(&spraid_instance_ida, hdev->instance); +} + +static int spraid_alloc_queue(struct spraid_dev *hdev, u16 qid, u16 depth) +{ + struct spraid_queue *spraidq = &hdev->queues[qid]; + int ret = 0; + + if (hdev->queue_count > qid) { + dev_info(hdev->dev, "[%s] warn: queue[%d] is exist\n", + __func__, qid); + return 0; + } + + spraidq->cqes = dma_alloc_coherent(hdev->dev, CQ_SIZE(depth), + &spraidq->cq_dma_addr, + GFP_KERNEL | __GFP_ZERO); + if (!spraidq->cqes) + return -ENOMEM; + + spraidq->sq_cmds = dma_alloc_coherent(hdev->dev, SQ_SIZE(qid, depth), + &spraidq->sq_dma_addr, + GFP_KERNEL); + if (!spraidq->sq_cmds) { + ret = -ENOMEM; + goto free_cqes; + } + + spin_lock_init(&spraidq->sq_lock); + spin_lock_init(&spraidq->cq_lock); + spraidq->hdev = hdev; + spraidq->q_depth = depth; + spraidq->qid = qid; + spraidq->cq_vector = -1; + hdev->queue_count++; + + /* alloc sense buffer */ + spraidq->sense = dma_alloc_coherent(hdev->dev, SENSE_SIZE(depth), + &spraidq->sense_dma_addr, + GFP_KERNEL | __GFP_ZERO); + if (!spraidq->sense) { + ret = -ENOMEM; + goto free_sq_cmds; + } + + return 0; + +free_sq_cmds: + dma_free_coherent(hdev->dev, SQ_SIZE(qid, depth), + (void *)spraidq->sq_cmds, spraidq->sq_dma_addr); +free_cqes: + dma_free_coherent(hdev->dev, CQ_SIZE(depth), (void *)spraidq->cqes, + spraidq->cq_dma_addr); + return ret; +} + +static int spraid_wait_ready(struct spraid_dev *hdev, u64 cap, bool enabled) +{ + unsigned long timeout = + ((SPRAID_CAP_TIMEOUT(cap) + 1) * SPRAID_CAP_TIMEOUT_UNIT_MS) + jiffies; + u32 bit = enabled ? SPRAID_CSTS_RDY : 0; + + while ((readl(hdev->bar + SPRAID_REG_CSTS) & SPRAID_CSTS_RDY) != bit) { + usleep_range(1000, 2000); + if (fatal_signal_pending(current)) + return -EINTR; + + if (time_after(jiffies, timeout)) { + dev_err(hdev->dev, "Device not ready; aborting %s\n", + enabled ? "initialisation" : "reset"); + return -ENODEV; + } + } + return 0; +} + +static int spraid_shutdown_ctrl(struct spraid_dev *hdev) +{ + unsigned long timeout = hdev->ctrl_info->rtd3e + jiffies; + + hdev->ctrl_config &= ~SPRAID_CC_SHN_MASK; + hdev->ctrl_config |= SPRAID_CC_SHN_NORMAL; + writel(hdev->ctrl_config, hdev->bar + SPRAID_REG_CC); + + while ((readl(hdev->bar + SPRAID_REG_CSTS) & SPRAID_CSTS_SHST_MASK) != + SPRAID_CSTS_SHST_CMPLT) { + msleep(100); + if (fatal_signal_pending(current)) + return -EINTR; + if (time_after(jiffies, timeout)) { + dev_err(hdev->dev, + "Device shutdown incomplete; abort shutdown\n"); + return -ENODEV; + } + } + return 0; +} + +static int spraid_disable_ctrl(struct spraid_dev *hdev) +{ + hdev->ctrl_config &= ~SPRAID_CC_SHN_MASK; + hdev->ctrl_config &= ~SPRAID_CC_ENABLE; + writel(hdev->ctrl_config, hdev->bar + SPRAID_REG_CC); + + return spraid_wait_ready(hdev, hdev->cap, false); +} + +static int spraid_enable_ctrl(struct spraid_dev *hdev) +{ + u64 cap = hdev->cap; + u32 dev_page_min = SPRAID_CAP_MPSMIN(cap) + 12; + u32 page_shift = PAGE_SHIFT; + + if (page_shift < dev_page_min) { + dev_err(hdev->dev, + "Minimum device page size[%u], too large for host[%u]\n", + 1U << dev_page_min, 1U << page_shift); + return -ENODEV; + } + + page_shift = min_t(unsigned int, SPRAID_CAP_MPSMAX(cap) + 12, + PAGE_SHIFT); + hdev->page_size = 1U << page_shift; + + hdev->ctrl_config = SPRAID_CC_CSS_NVM; + hdev->ctrl_config |= (page_shift - 12) << SPRAID_CC_MPS_SHIFT; + hdev->ctrl_config |= SPRAID_CC_AMS_RR | SPRAID_CC_SHN_NONE; + hdev->ctrl_config |= SPRAID_CC_IOSQES | SPRAID_CC_IOCQES; + hdev->ctrl_config |= SPRAID_CC_ENABLE; + writel(hdev->ctrl_config, hdev->bar + SPRAID_REG_CC); + + return spraid_wait_ready(hdev, cap, true); +} + +static void spraid_init_queue(struct spraid_queue *spraidq, u16 qid) +{ + struct spraid_dev *hdev = spraidq->hdev; + + memset((void *)spraidq->cqes, 0, CQ_SIZE(spraidq->q_depth)); + + spraidq->sq_tail = 0; + spraidq->cq_head = 0; + spraidq->cq_phase = 1; + spraidq->q_db = &hdev->dbs[qid * 2 * hdev->db_stride]; + spraidq->prp_small_pool = hdev->prp_small_pool[qid % small_pool_num]; + hdev->online_queues++; +} + +static inline bool spraid_cqe_pending(struct spraid_queue *spraidq) +{ + return (le16_to_cpu(spraidq->cqes[spraidq->cq_head].status) & 1) == + spraidq->cq_phase; +} + +static void spraid_sata_report_zone_handle(struct scsi_cmnd *scmd, + struct spraid_iod *iod) +{ + int i = 0; + unsigned int bytes = 0; + struct scatterlist *sg = scsi_sglist(scmd); + + scsi_for_each_sg(scmd, sg, iod->nsge, i) { + unsigned int offset = 0; + + if (bytes == 0) { + char *hdr; + u32 list_length; + u64 max_lba, opt_lba; + u16 same; + + hdr = sg_virt(sg); + + list_length = get_unaligned_le32(&hdr[0]); + same = get_unaligned_le16(&hdr[4]); + max_lba = get_unaligned_le64(&hdr[8]); + opt_lba = get_unaligned_le64(&hdr[16]); + put_unaligned_be32(list_length, &hdr[0]); + hdr[4] = same & 0xf; + put_unaligned_be64(max_lba, &hdr[8]); + put_unaligned_be64(opt_lba, &hdr[16]); + offset += 64; + bytes += 64; + } + while (offset < sg_dma_len(sg)) { + char *rec; + u8 cond, type, non_seq, reset; + u64 size, start, wp; + + rec = sg_virt(sg) + offset; + type = rec[0] & 0xf; + cond = (rec[1] >> 4) & 0xf; + non_seq = (rec[1] & 2); + reset = (rec[1] & 1); + size = get_unaligned_le64(&rec[8]); + start = get_unaligned_le64(&rec[16]); + wp = get_unaligned_le64(&rec[24]); + rec[0] = type; + rec[1] = (cond << 4) | non_seq | reset; + put_unaligned_be64(size, &rec[8]); + put_unaligned_be64(start, &rec[16]); + put_unaligned_be64(wp, &rec[24]); + WARN_ON(offset + 64 > sg_dma_len(sg)); + offset += 64; + bytes += 64; + } + } +} + +static inline void spraid_handle_ata_cmd(struct spraid_dev *hdev, + struct scsi_cmnd *scmd, + struct spraid_iod *iod) +{ + if (hdev->ctrl_info->card_type != SPRAID_CARD_HBA) + return; + + switch (scmd->cmnd[0]) { + case ZBC_IN: + dev_info(hdev->dev, "[%s] process report zone\n", __func__); + spraid_sata_report_zone_handle(scmd, iod); + break; + default: + break; + } +} + +static void spraid_complete_ioq_cmnd(struct spraid_queue *ioq, + struct spraid_completion *cqe) +{ + struct spraid_dev *hdev = ioq->hdev; + struct blk_mq_tags *tags; + struct scsi_cmnd *scmd; + struct spraid_iod *iod; + struct request *req; + unsigned long elapsed; + + tags = hdev->shost->tag_set.tags[ioq->qid - 1]; + req = blk_mq_tag_to_rq(tags, cqe->cmd_id); + if (unlikely(!req || !blk_mq_request_started(req))) { + dev_warn(hdev->dev, "Invalid id %d completed on queue %d\n", + cqe->cmd_id, ioq->qid); + return; + } + + scmd = blk_mq_rq_to_pdu(req); + iod = scsi_cmd_priv(scmd); + + elapsed = jiffies - scmd->jiffies_at_alloc; + dev_log_dbg(hdev->dev, + "cid[%d] qid[%d] finish IO cost %3ld.%3ld seconds\n", + cqe->cmd_id, ioq->qid, elapsed / HZ, elapsed % HZ); + + if (cmpxchg(&iod->state, SPRAID_CMD_IN_FLIGHT, SPRAID_CMD_COMPLETE) != + SPRAID_CMD_IN_FLIGHT) { + dev_warn(hdev->dev, + "cid[%d] qid[%d] enters abnormal handler;" + " cost %3ld.%3ld seconds\n", + cqe->cmd_id, ioq->qid, elapsed / HZ, elapsed % HZ); + WRITE_ONCE(iod->state, SPRAID_CMD_TMO_COMPLETE); + + if (iod->nsge) { + iod->nsge = 0; + scsi_dma_unmap(scmd); + } + spraid_free_iod_res(hdev, iod); + + return; + } + + spraid_handle_ata_cmd(hdev, scmd, iod); + + spraid_map_status(iod, scmd, cqe); + if (iod->nsge) { + iod->nsge = 0; + scsi_dma_unmap(scmd); + } + spraid_free_iod_res(hdev, iod); + scmd->scsi_done(scmd); +} + +static void spraid_complete_adminq_cmnd(struct spraid_queue *adminq, + struct spraid_completion *cqe) +{ + struct spraid_dev *hdev = adminq->hdev; + struct spraid_cmd *adm_cmd; + + adm_cmd = hdev->adm_cmds + cqe->cmd_id; + if (unlikely(adm_cmd->state == SPRAID_CMD_IDLE)) { + dev_warn(adminq->hdev->dev, + "Invalid id %d completed on queue %d\n", + cqe->cmd_id, le16_to_cpu(cqe->sq_id)); + return; + } + + adm_cmd->status = le16_to_cpu(cqe->status) >> 1; + adm_cmd->result0 = le32_to_cpu(cqe->result); + adm_cmd->result1 = le32_to_cpu(cqe->result1); + + complete(&adm_cmd->cmd_done); +} + +static void spraid_send_aen(struct spraid_dev *hdev, u16 cid); + +static void spraid_complete_aen(struct spraid_queue *spraidq, + struct spraid_completion *cqe) +{ + struct spraid_dev *hdev = spraidq->hdev; + u32 result = le32_to_cpu(cqe->result); + + dev_info(hdev->dev, "rcv aen, cid[%d], status[0x%x], result[0x%x]\n", + cqe->cmd_id, le16_to_cpu(cqe->status) >> 1, result); + + spraid_send_aen(hdev, cqe->cmd_id); + + if ((le16_to_cpu(cqe->status) >> 1) != SPRAID_SC_SUCCESS) + return; + switch (result & 0x7) { + case SPRAID_AEN_NOTICE: + spraid_handle_aen_notice(hdev, result); + break; + case SPRAID_AEN_VS: + spraid_handle_aen_vs(hdev, result, le32_to_cpu(cqe->result1)); + break; + default: + dev_warn(hdev->dev, "Unsupported async event type: %u\n", + result & 0x7); + break; + } +} + +static void spraid_complete_ioq_sync_cmnd(struct spraid_queue *ioq, + struct spraid_completion *cqe) +{ + struct spraid_dev *hdev = ioq->hdev; + struct spraid_cmd *ptcmd; + + ptcmd = hdev->ioq_ptcmds + (ioq->qid - 1) * SPRAID_PTCMDS_PERQ + + cqe->cmd_id - SPRAID_IO_BLK_MQ_DEPTH; + + ptcmd->status = le16_to_cpu(cqe->status) >> 1; + ptcmd->result0 = le32_to_cpu(cqe->result); + ptcmd->result1 = le32_to_cpu(cqe->result1); + + complete(&ptcmd->cmd_done); +} + +static inline void spraid_handle_cqe(struct spraid_queue *spraidq, u16 idx) +{ + struct spraid_completion *cqe = &spraidq->cqes[idx]; + struct spraid_dev *hdev = spraidq->hdev; + + if (unlikely(cqe->cmd_id >= spraidq->q_depth)) { + dev_err(hdev->dev, + "Invalid command id[%d] completed on queue %d\n", + cqe->cmd_id, cqe->sq_id); + return; + } + + dev_log_dbg(hdev->dev, "cid[%d] qid[%d];" + " result[0x%x], sq_id[%d], status[0x%x]\n", + cqe->cmd_id, spraidq->qid, le32_to_cpu(cqe->result), + le16_to_cpu(cqe->sq_id), le16_to_cpu(cqe->status)); + + if (unlikely(spraidq->qid == 0 + && cqe->cmd_id >= SPRAID_AQ_BLK_MQ_DEPTH)) { + spraid_complete_aen(spraidq, cqe); + return; + } + + if (unlikely(spraidq->qid && cqe->cmd_id >= SPRAID_IO_BLK_MQ_DEPTH)) { + spraid_complete_ioq_sync_cmnd(spraidq, cqe); + return; + } + + if (spraidq->qid) + spraid_complete_ioq_cmnd(spraidq, cqe); + else + spraid_complete_adminq_cmnd(spraidq, cqe); +} + +static void spraid_complete_cqes(struct spraid_queue *spraidq, + u16 start, u16 end) +{ + while (start != end) { + spraid_handle_cqe(spraidq, start); + if (++start == spraidq->q_depth) + start = 0; + } +} + +static inline void spraid_update_cq_head(struct spraid_queue *spraidq) +{ + if (++spraidq->cq_head == spraidq->q_depth) { + spraidq->cq_head = 0; + spraidq->cq_phase = !spraidq->cq_phase; + } +} + +static inline bool spraid_process_cq(struct spraid_queue *spraidq, + u16 *start, u16 *end, int tag) +{ + bool found = false; + + *start = spraidq->cq_head; + while (!found && spraid_cqe_pending(spraidq)) { + if (spraidq->cqes[spraidq->cq_head].cmd_id == tag) + found = true; + spraid_update_cq_head(spraidq); + } + *end = spraidq->cq_head; + + if (*start != *end) + writel(spraidq->cq_head, + spraidq->q_db + spraidq->hdev->db_stride); + + return found; +} + +static bool spraid_poll_cq(struct spraid_queue *spraidq, int cid) +{ + u16 start, end; + bool found; + + if (!spraid_cqe_pending(spraidq)) + return 0; + + spin_lock_irq(&spraidq->cq_lock); + found = spraid_process_cq(spraidq, &start, &end, cid); + spin_unlock_irq(&spraidq->cq_lock); + + spraid_complete_cqes(spraidq, start, end); + return found; +} + +static irqreturn_t spraid_irq(int irq, void *data) +{ + struct spraid_queue *spraidq = data; + irqreturn_t ret = IRQ_NONE; + u16 start, end; + + spin_lock(&spraidq->cq_lock); + if (spraidq->cq_head != spraidq->last_cq_head) + ret = IRQ_HANDLED; + + spraid_process_cq(spraidq, &start, &end, -1); + spraidq->last_cq_head = spraidq->cq_head; + spin_unlock(&spraidq->cq_lock); + + if (start != end) { + spraid_complete_cqes(spraidq, start, end); + ret = IRQ_HANDLED; + } + return ret; +} + +static int spraid_setup_admin_queue(struct spraid_dev *hdev) +{ + struct spraid_queue *adminq = &hdev->queues[0]; + u32 aqa; + int ret; + + dev_info(hdev->dev, "[%s] start disable ctrl\n", __func__); + + ret = spraid_disable_ctrl(hdev); + if (ret) + return ret; + + ret = spraid_alloc_queue(hdev, 0, SPRAID_AQ_DEPTH); + if (ret) + return ret; + + aqa = adminq->q_depth - 1; + aqa |= aqa << 16; + writel(aqa, hdev->bar + SPRAID_REG_AQA); + lo_hi_writeq(adminq->sq_dma_addr, hdev->bar + SPRAID_REG_ASQ); + lo_hi_writeq(adminq->cq_dma_addr, hdev->bar + SPRAID_REG_ACQ); + + dev_info(hdev->dev, "[%s] start enable ctrl\n", __func__); + + ret = spraid_enable_ctrl(hdev); + if (ret) { + ret = -ENODEV; + goto free_queue; + } + + adminq->cq_vector = 0; + spraid_init_queue(adminq, 0); + ret = pci_request_irq(hdev->pdev, adminq->cq_vector, spraid_irq, NULL, + adminq, "spraid%d_q%d", + hdev->instance, adminq->qid); + + if (ret) { + adminq->cq_vector = -1; + hdev->online_queues--; + goto free_queue; + } + + dev_info(hdev->dev, "[%s] success, queuecount:[%d], onlinequeue:[%d]\n", + __func__, hdev->queue_count, hdev->online_queues); + + return 0; + +free_queue: + spraid_free_queue(adminq); + return ret; +} + +static u32 spraid_bar_size(struct spraid_dev *hdev, u32 nr_ioqs) +{ + return (SPRAID_REG_DBS + ((nr_ioqs + 1) * 8 * hdev->db_stride)); +} + +static int spraid_alloc_admin_cmds(struct spraid_dev *hdev) +{ + int i; + + INIT_LIST_HEAD(&hdev->adm_cmd_list); + spin_lock_init(&hdev->adm_cmd_lock); + + hdev->adm_cmds = kcalloc_node(SPRAID_AQ_BLK_MQ_DEPTH, + sizeof(struct spraid_cmd), + GFP_KERNEL, hdev->numa_node); + + if (!hdev->adm_cmds) { + dev_err(hdev->dev, "Alloc admin cmds failed\n"); + return -ENOMEM; + } + + for (i = 0; i < SPRAID_AQ_BLK_MQ_DEPTH; i++) { + hdev->adm_cmds[i].qid = 0; + hdev->adm_cmds[i].cid = i; + list_add_tail(&(hdev->adm_cmds[i].list), &hdev->adm_cmd_list); + } + + dev_info(hdev->dev, "Alloc admin cmds success, num[%d]\n", + SPRAID_AQ_BLK_MQ_DEPTH); + + return 0; +} + +static void spraid_free_admin_cmds(struct spraid_dev *hdev) +{ + kfree(hdev->adm_cmds); + hdev->adm_cmds = NULL; + INIT_LIST_HEAD(&hdev->adm_cmd_list); +} + +static struct spraid_cmd *spraid_get_cmd(struct spraid_dev *hdev, + enum spraid_cmd_type type) +{ + struct spraid_cmd *cmd = NULL; + unsigned long flags; + struct list_head *head = &hdev->adm_cmd_list; + spinlock_t *slock = &hdev->adm_cmd_lock; + + if (type == SPRAID_CMD_IOPT) { + head = &hdev->ioq_pt_list; + slock = &hdev->ioq_pt_lock; + } + + spin_lock_irqsave(slock, flags); + if (list_empty(head)) { + spin_unlock_irqrestore(slock, flags); + dev_err(hdev->dev, "err, cmd[%d] list empty\n", type); + return NULL; + } + cmd = list_entry(head->next, struct spraid_cmd, list); + list_del_init(&cmd->list); + spin_unlock_irqrestore(slock, flags); + + WRITE_ONCE(cmd->state, SPRAID_CMD_IN_FLIGHT); + + return cmd; +} + +static void spraid_put_cmd(struct spraid_dev *hdev, struct spraid_cmd *cmd, + enum spraid_cmd_type type) +{ + unsigned long flags; + struct list_head *head = &hdev->adm_cmd_list; + spinlock_t *slock = &hdev->adm_cmd_lock; + + if (type == SPRAID_CMD_IOPT) { + head = &hdev->ioq_pt_list; + slock = &hdev->ioq_pt_lock; + } + + spin_lock_irqsave(slock, flags); + WRITE_ONCE(cmd->state, SPRAID_CMD_IDLE); + list_add_tail(&cmd->list, head); + spin_unlock_irqrestore(slock, flags); +} + + +static int spraid_submit_admin_sync_cmd(struct spraid_dev *hdev, + struct spraid_admin_command *cmd, + u32 *result0, u32 *result1, u32 timeout) +{ + struct spraid_cmd *adm_cmd = spraid_get_cmd(hdev, SPRAID_CMD_ADM); + + if (!adm_cmd) { + dev_err(hdev->dev, "err, get admin cmd failed\n"); + return -EFAULT; + } + + timeout = timeout ? timeout : ADMIN_TIMEOUT; + + init_completion(&adm_cmd->cmd_done); + + cmd->common.command_id = adm_cmd->cid; + spraid_submit_cmd(&hdev->queues[0], cmd); + + if (!wait_for_completion_timeout(&adm_cmd->cmd_done, timeout)) { + dev_err(hdev->dev, "[%s] cid[%d] qid[%d] timeout;" + " opcode[0x%x] subopcode[0x%x]\n", + __func__, adm_cmd->cid, adm_cmd->qid, + cmd->usr_cmd.opcode, cmd->usr_cmd.info_0.subopcode); + WRITE_ONCE(adm_cmd->state, SPRAID_CMD_TIMEOUT); + spraid_put_cmd(hdev, adm_cmd, SPRAID_CMD_ADM); + return -EINVAL; + } + + if (result0) + *result0 = adm_cmd->result0; + if (result1) + *result1 = adm_cmd->result1; + + spraid_put_cmd(hdev, adm_cmd, SPRAID_CMD_ADM); + + return adm_cmd->status; +} + +static int spraid_create_cq(struct spraid_dev *hdev, u16 qid, + struct spraid_queue *spraidq, u16 cq_vector) +{ + struct spraid_admin_command admin_cmd; + int flags = SPRAID_QUEUE_PHYS_CONTIG | SPRAID_CQ_IRQ_ENABLED; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.create_cq.opcode = SPRAID_ADMIN_CREATE_CQ; + admin_cmd.create_cq.prp1 = cpu_to_le64(spraidq->cq_dma_addr); + admin_cmd.create_cq.cqid = cpu_to_le16(qid); + admin_cmd.create_cq.qsize = cpu_to_le16(spraidq->q_depth - 1); + admin_cmd.create_cq.cq_flags = cpu_to_le16(flags); + admin_cmd.create_cq.irq_vector = cpu_to_le16(cq_vector); + + return spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); +} + +static int spraid_create_sq(struct spraid_dev *hdev, u16 qid, + struct spraid_queue *spraidq) +{ + struct spraid_admin_command admin_cmd; + int flags = SPRAID_QUEUE_PHYS_CONTIG; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.create_sq.opcode = SPRAID_ADMIN_CREATE_SQ; + admin_cmd.create_sq.prp1 = cpu_to_le64(spraidq->sq_dma_addr); + admin_cmd.create_sq.sqid = cpu_to_le16(qid); + admin_cmd.create_sq.qsize = cpu_to_le16(spraidq->q_depth - 1); + admin_cmd.create_sq.sq_flags = cpu_to_le16(flags); + admin_cmd.create_sq.cqid = cpu_to_le16(qid); + + return spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); +} + +static void spraid_free_queue(struct spraid_queue *spraidq) +{ + struct spraid_dev *hdev = spraidq->hdev; + + hdev->queue_count--; + dma_free_coherent(hdev->dev, CQ_SIZE(spraidq->q_depth), + (void *)spraidq->cqes, spraidq->cq_dma_addr); + dma_free_coherent(hdev->dev, SQ_SIZE(spraidq->qid, spraidq->q_depth), + spraidq->sq_cmds, spraidq->sq_dma_addr); + dma_free_coherent(hdev->dev, SENSE_SIZE(spraidq->q_depth), + spraidq->sense, spraidq->sense_dma_addr); +} + +static void spraid_free_admin_queue(struct spraid_dev *hdev) +{ + spraid_free_queue(&hdev->queues[0]); +} + +static void spraid_free_io_queues(struct spraid_dev *hdev) +{ + int i; + + for (i = hdev->queue_count - 1; i >= 1; i--) + spraid_free_queue(&hdev->queues[i]); +} + +static int spraid_delete_queue(struct spraid_dev *hdev, u8 op, u16 id) +{ + struct spraid_admin_command admin_cmd; + int ret; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.delete_queue.opcode = op; + admin_cmd.delete_queue.qid = cpu_to_le16(id); + + ret = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); + + if (ret) + dev_err(hdev->dev, "Delete %s:[%d] failed\n", + (op == SPRAID_ADMIN_DELETE_CQ) ? "cq" : "sq", id); + + return ret; +} + +static int spraid_delete_cq(struct spraid_dev *hdev, u16 cqid) +{ + return spraid_delete_queue(hdev, SPRAID_ADMIN_DELETE_CQ, cqid); +} + +static int spraid_delete_sq(struct spraid_dev *hdev, u16 sqid) +{ + return spraid_delete_queue(hdev, SPRAID_ADMIN_DELETE_SQ, sqid); +} + +static int spraid_create_queue(struct spraid_queue *spraidq, u16 qid) +{ + struct spraid_dev *hdev = spraidq->hdev; + u16 cq_vector; + int ret; + + cq_vector = (hdev->num_vecs == 1) ? 0 : qid; + ret = spraid_create_cq(hdev, qid, spraidq, cq_vector); + if (ret) + return ret; + + ret = spraid_create_sq(hdev, qid, spraidq); + if (ret) + goto delete_cq; + + spraid_init_queue(spraidq, qid); + spraidq->cq_vector = cq_vector; + + ret = pci_request_irq(hdev->pdev, cq_vector, spraid_irq, NULL, + spraidq, "spraid%d_q%d", hdev->instance, qid); + + if (ret) { + dev_err(hdev->dev, "Request queue[%d] irq failed\n", qid); + goto delete_sq; + } + + return 0; + +delete_sq: + spraidq->cq_vector = -1; + hdev->online_queues--; + spraid_delete_sq(hdev, qid); +delete_cq: + spraid_delete_cq(hdev, qid); + + return ret; +} + +static int spraid_create_io_queues(struct spraid_dev *hdev) +{ + u32 i, max; + int ret = 0; + + max = min(hdev->max_qid, hdev->queue_count - 1); + for (i = hdev->online_queues; i <= max; i++) { + ret = spraid_create_queue(&hdev->queues[i], i); + if (ret) { + dev_err(hdev->dev, "Create queue[%d] failed\n", i); + break; + } + } + + dev_info(hdev->dev, "[%s] queue_count[%d], online_queue[%d]", + __func__, hdev->queue_count, hdev->online_queues); + + return ret >= 0 ? 0 : ret; +} + +static int spraid_set_features(struct spraid_dev *hdev, u32 fid, + u32 dword11, void *buffer, + size_t buflen, u32 *result) +{ + struct spraid_admin_command admin_cmd; + int ret; + u8 *data_ptr = NULL; + dma_addr_t data_dma = 0; + + if (buffer && buflen) { + data_ptr = dma_alloc_coherent(hdev->dev, buflen, + &data_dma, GFP_KERNEL); + if (!data_ptr) + return -ENOMEM; + + memcpy(data_ptr, buffer, buflen); + } + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.features.opcode = SPRAID_ADMIN_SET_FEATURES; + admin_cmd.features.fid = cpu_to_le32(fid); + admin_cmd.features.dword11 = cpu_to_le32(dword11); + admin_cmd.common.dptr.prp1 = cpu_to_le64(data_dma); + + ret = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, result, NULL, 0); + + if (data_ptr) + dma_free_coherent(hdev->dev, buflen, data_ptr, data_dma); + + return ret; +} + +static int spraid_configure_timestamp(struct spraid_dev *hdev) +{ + __le64 ts; + int ret; + + ts = cpu_to_le64(ktime_to_ms(ktime_get_real())); + ret = spraid_set_features(hdev, SPRAID_FEAT_TIMESTAMP, + 0, &ts, sizeof(ts), NULL); + + if (ret) + dev_err(hdev->dev, "set timestamp failed: %d\n", ret); + return ret; +} + +static int spraid_set_queue_cnt(struct spraid_dev *hdev, u32 *cnt) +{ + u32 q_cnt = (*cnt - 1) | ((*cnt - 1) << 16); + u32 nr_ioqs, result; + int status; + + status = spraid_set_features(hdev, SPRAID_FEAT_NUM_QUEUES, + q_cnt, NULL, 0, &result); + if (status) { + dev_err(hdev->dev, "Set queue count failed, status: %d\n", + status); + return -EIO; + } + + nr_ioqs = min(result & 0xffff, result >> 16) + 1; + *cnt = min(*cnt, nr_ioqs); + if (*cnt == 0) { + dev_err(hdev->dev, "Illegal queue count: zero\n"); + return -EIO; + } + return 0; +} + +static int spraid_setup_io_queues(struct spraid_dev *hdev) +{ + struct spraid_queue *adminq = &hdev->queues[0]; + struct pci_dev *pdev = hdev->pdev; + u32 nr_ioqs = num_online_cpus(); + u32 i, size; + int ret; + + struct irq_affinity affd = { + .pre_vectors = 1 + }; + + ret = spraid_set_queue_cnt(hdev, &nr_ioqs); + if (ret < 0) + return ret; + + size = spraid_bar_size(hdev, nr_ioqs); + ret = spraid_remap_bar(hdev, size); + if (ret) + return -ENOMEM; + + adminq->q_db = hdev->dbs; + + pci_free_irq(pdev, 0, adminq); + pci_free_irq_vectors(pdev); + + ret = pci_alloc_irq_vectors_affinity(pdev, 1, (nr_ioqs + 1), + PCI_IRQ_ALL_TYPES | PCI_IRQ_AFFINITY, &affd); + if (ret <= 0) + return -EIO; + + hdev->num_vecs = ret; + + hdev->max_qid = max(ret - 1, 1); + + ret = pci_request_irq(pdev, adminq->cq_vector, spraid_irq, NULL, + adminq, "spraid%d_q%d", + hdev->instance, adminq->qid); + if (ret) { + dev_err(hdev->dev, "Request admin irq failed\n"); + adminq->cq_vector = -1; + return ret; + } + + for (i = hdev->queue_count; i <= hdev->max_qid; i++) { + ret = spraid_alloc_queue(hdev, i, hdev->ioq_depth); + if (ret) + break; + } + dev_info(hdev->dev, "[%s] max_qid: %d, queue_count: %d;" + " online_queue: %d, ioq_depth: %d\n", + __func__, hdev->max_qid, hdev->queue_count, + hdev->online_queues, hdev->ioq_depth); + + return spraid_create_io_queues(hdev); +} + +static void spraid_delete_io_queues(struct spraid_dev *hdev) +{ + u16 queues = hdev->online_queues - 1; + u8 opcode = SPRAID_ADMIN_DELETE_SQ; + u16 i, pass; + + if (!pci_device_is_present(hdev->pdev)) { + dev_err(hdev->dev, + "pci_device is not present, skip disable io queues\n"); + return; + } + + if (hdev->online_queues < 2) { + dev_err(hdev->dev, "[%s] err, io queue has been delete\n", + __func__); + return; + } + + for (pass = 0; pass < 2; pass++) { + for (i = queues; i > 0; i--) + if (spraid_delete_queue(hdev, opcode, i)) + break; + + opcode = SPRAID_ADMIN_DELETE_CQ; + } +} + +static void spraid_remove_io_queues(struct spraid_dev *hdev) +{ + spraid_delete_io_queues(hdev); + spraid_free_io_queues(hdev); +} + +static void spraid_pci_disable(struct spraid_dev *hdev) +{ + struct pci_dev *pdev = hdev->pdev; + u32 i; + + for (i = 0; i < hdev->online_queues; i++) + pci_free_irq(pdev, hdev->queues[i].cq_vector, &hdev->queues[i]); + pci_free_irq_vectors(pdev); + if (pci_is_enabled(pdev)) { + pci_disable_pcie_error_reporting(pdev); + pci_disable_device(pdev); + } + hdev->online_queues = 0; +} + +static void spraid_disable_admin_queue(struct spraid_dev *hdev, bool shutdown) +{ + struct spraid_queue *adminq = &hdev->queues[0]; + u16 start, end; + + if (pci_device_is_present(hdev->pdev)) { + if (shutdown) + spraid_shutdown_ctrl(hdev); + else + spraid_disable_ctrl(hdev); + } + + if (hdev->queue_count == 0) { + dev_err(hdev->dev, "[%s] err, admin queue has been delete\n", + __func__); + return; + } + + spin_lock_irq(&adminq->cq_lock); + spraid_process_cq(adminq, &start, &end, -1); + spin_unlock_irq(&adminq->cq_lock); + + spraid_complete_cqes(adminq, start, end); + spraid_free_admin_queue(hdev); +} + +static int spraid_create_dma_pools(struct spraid_dev *hdev) +{ + int i; + char poolname[20] = { 0 }; + + hdev->prp_page_pool = dma_pool_create("prp list page", hdev->dev, + PAGE_SIZE, PAGE_SIZE, 0); + + if (!hdev->prp_page_pool) { + dev_err(hdev->dev, "create prp_page_pool failed\n"); + return -ENOMEM; + } + + for (i = 0; i < small_pool_num; i++) { + sprintf(poolname, "prp_list_256_%d", i); + hdev->prp_small_pool[i] = + dma_pool_create(poolname, hdev->dev, SMALL_POOL_SIZE, + SMALL_POOL_SIZE, 0); + + if (!hdev->prp_small_pool[i]) { + dev_err(hdev->dev, "create prp_small_pool %d failed\n", + i); + goto destroy_prp_small_pool; + } + } + + return 0; + +destroy_prp_small_pool: + while (i > 0) + dma_pool_destroy(hdev->prp_small_pool[--i]); + dma_pool_destroy(hdev->prp_page_pool); + + return -ENOMEM; +} + +static void spraid_destroy_dma_pools(struct spraid_dev *hdev) +{ + int i; + + for (i = 0; i < small_pool_num; i++) + dma_pool_destroy(hdev->prp_small_pool[i]); + dma_pool_destroy(hdev->prp_page_pool); +} + +static int spraid_get_dev_list(struct spraid_dev *hdev, + struct spraid_dev_info *devices) +{ + u32 nd = le32_to_cpu(hdev->ctrl_info->nd); + struct spraid_admin_command admin_cmd; + struct spraid_dev_list *list_buf; + dma_addr_t data_dma = 0; + u32 i, idx, hdid, ndev; + int ret = 0; + + list_buf = dma_alloc_coherent(hdev->dev, PAGE_SIZE, + &data_dma, GFP_KERNEL); + if (!list_buf) + return -ENOMEM; + + for (idx = 0; idx < nd;) { + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.get_info.opcode = SPRAID_ADMIN_GET_INFO; + admin_cmd.get_info.type = SPRAID_GET_INFO_DEV_LIST; + admin_cmd.get_info.cdw11 = cpu_to_le32(idx); + admin_cmd.common.dptr.prp1 = cpu_to_le64(data_dma); + + ret = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, + NULL, NULL, 0); + + if (ret) { + dev_err(hdev->dev, "Get device list failed, nd: %u;" + "idx: %u, ret: %d\n", + nd, idx, ret); + goto out; + } + ndev = le32_to_cpu(list_buf->dev_num); + + dev_info(hdev->dev, "ndev numbers: %u\n", ndev); + + for (i = 0; i < ndev; i++) { + hdid = le32_to_cpu(list_buf->devices[i].hdid); + dev_info(hdev->dev, "list_buf->devices[%d], hdid: %u;" + "target: %d, channel: %d, lun: %d, attr[0x%x]\n", + i, hdid, + le16_to_cpu(list_buf->devices[i].target), + list_buf->devices[i].channel, + list_buf->devices[i].lun, + list_buf->devices[i].attr); + if (hdid > nd || hdid == 0) { + dev_err(hdev->dev, "err, hdid[%d] invalid\n", + hdid); + continue; + } + memcpy(&devices[hdid - 1], &list_buf->devices[i], + sizeof(struct spraid_dev_info)); + } + idx += ndev; + + if (idx < MAX_DEV_ENTRY_PER_PAGE_4K) + break; + } + +out: + dma_free_coherent(hdev->dev, PAGE_SIZE, list_buf, data_dma); + return ret; +} + +static void spraid_send_aen(struct spraid_dev *hdev, u16 cid) +{ + struct spraid_queue *adminq = &hdev->queues[0]; + struct spraid_admin_command admin_cmd; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.common.opcode = SPRAID_ADMIN_ASYNC_EVENT; + admin_cmd.common.command_id = cid; + + spraid_submit_cmd(adminq, &admin_cmd); + dev_info(hdev->dev, "send aen, cid[%d]\n", cid); +} + +static inline void spraid_send_all_aen(struct spraid_dev *hdev) +{ + u16 i; + + for (i = 0; i < hdev->ctrl_info->aerl; i++) + spraid_send_aen(hdev, i + SPRAID_AQ_BLK_MQ_DEPTH); +} + +static int spraid_add_device(struct spraid_dev *hdev, + struct spraid_dev_info *device) +{ + struct Scsi_Host *shost = hdev->shost; + struct scsi_device *sdev; + + dev_info(hdev->dev, "add device, hdid: %u target: %d, channel: %d;" + " lun: %d, attr[0x%x]\n", + le32_to_cpu(device->hdid), le16_to_cpu(device->target), + device->channel, device->lun, device->attr); + + sdev = scsi_device_lookup(shost, device->channel, + le16_to_cpu(device->target), 0); + if (sdev) { + dev_warn(hdev->dev, "Device is already exist, channel: %d;" + " target_id: %d, lun: %d\n", + device->channel, le16_to_cpu(device->target), 0); + scsi_device_put(sdev); + return -EEXIST; + } + scsi_add_device(shost, device->channel, le16_to_cpu(device->target), 0); + return 0; +} + +static int spraid_rescan_device(struct spraid_dev *hdev, + struct spraid_dev_info *device) +{ + struct Scsi_Host *shost = hdev->shost; + struct scsi_device *sdev; + + dev_info(hdev->dev, "rescan device, hdid: %u target: %d, channel: %d;" + " lun: %d, attr[0x%x]\n", + le32_to_cpu(device->hdid), le16_to_cpu(device->target), + device->channel, device->lun, device->attr); + + sdev = scsi_device_lookup(shost, device->channel, + le16_to_cpu(device->target), 0); + if (!sdev) { + dev_warn(hdev->dev, "device is not exit rescan it, channel: %d;" + " target_id: %d, lun: %d\n", + device->channel, le16_to_cpu(device->target), 0); + return -ENODEV; + } + + scsi_rescan_device(&sdev->sdev_gendev); + scsi_device_put(sdev); + return 0; +} + +static int spraid_remove_device(struct spraid_dev *hdev, + struct spraid_dev_info *org_device) +{ + struct Scsi_Host *shost = hdev->shost; + struct scsi_device *sdev; + + dev_info(hdev->dev, "remove device, hdid: %u target: %d, channel: %d;" + " lun: %d, attr[0x%x]\n", + le32_to_cpu(org_device->hdid), le16_to_cpu(org_device->target), + org_device->channel, org_device->lun, org_device->attr); + + sdev = scsi_device_lookup(shost, org_device->channel, + le16_to_cpu(org_device->target), 0); + if (!sdev) { + dev_warn(hdev->dev, "device is not exit remove it, channel: %d;" + " target_id: %d, lun: %d\n", + org_device->channel, + le16_to_cpu(org_device->target), 0); + return -ENODEV; + } + + scsi_remove_device(sdev); + scsi_device_put(sdev); + return 0; +} + +static int spraid_dev_list_init(struct spraid_dev *hdev) +{ + u32 nd = le32_to_cpu(hdev->ctrl_info->nd); + int i, ret; + + hdev->devices = kzalloc_node(nd * sizeof(struct spraid_dev_info), + GFP_KERNEL, hdev->numa_node); + if (!hdev->devices) + return -ENOMEM; + + ret = spraid_get_dev_list(hdev, hdev->devices); + if (ret) { + dev_err(hdev->dev, + "Ignore failure of getting device list;" + " within initialization\n"); + return 0; + } + + for (i = 0; i < nd; i++) { + if (SPRAID_DEV_INFO_FLAG_VALID(hdev->devices[i].flag) && + SPRAID_DEV_INFO_ATTR_BOOT(hdev->devices[i].attr)) { + spraid_add_device(hdev, &hdev->devices[i]); + break; + } + } + return 0; +} + +static int luntarget_cmp_func(const void *l, const void *r) +{ + const struct spraid_dev_info *ln = l; + const struct spraid_dev_info *rn = r; + + if (ln->channel == rn->channel) + return le16_to_cpu(ln->target) - le16_to_cpu(rn->target); + + return ln->channel - rn->channel; +} + +static void spraid_scan_work(struct work_struct *work) +{ + struct spraid_dev *hdev = + container_of(work, struct spraid_dev, scan_work); + struct spraid_dev_info *devices, *org_devices; + struct spraid_dev_info *sortdevice; + u32 nd = le32_to_cpu(hdev->ctrl_info->nd); + u8 flag, org_flag; + int i, ret; + int count = 0; + + devices = kcalloc(nd, sizeof(struct spraid_dev_info), GFP_KERNEL); + if (!devices) + return; + + sortdevice = kcalloc(nd, sizeof(struct spraid_dev_info), GFP_KERNEL); + if (!sortdevice) + goto free_list; + + ret = spraid_get_dev_list(hdev, devices); + if (ret) + goto free_all; + org_devices = hdev->devices; + for (i = 0; i < nd; i++) { + org_flag = org_devices[i].flag; + flag = devices[i].flag; + + dev_log_dbg(hdev->dev, "i: %d, org_flag: 0x%x, flag: 0x%x\n", + i, org_flag, flag); + + if (SPRAID_DEV_INFO_FLAG_VALID(flag)) { + if (!SPRAID_DEV_INFO_FLAG_VALID(org_flag)) { + down_write(&hdev->devices_rwsem); + memcpy(&org_devices[i], &devices[i], + sizeof(struct spraid_dev_info)); + memcpy(&sortdevice[count++], &devices[i], + sizeof(struct spraid_dev_info)); + up_write(&hdev->devices_rwsem); + } else if (SPRAID_DEV_INFO_FLAG_CHANGE(flag)) { + spraid_rescan_device(hdev, &devices[i]); + } + } else { + if (SPRAID_DEV_INFO_FLAG_VALID(org_flag)) { + down_write(&hdev->devices_rwsem); + org_devices[i].flag &= 0xfe; + up_write(&hdev->devices_rwsem); + spraid_remove_device(hdev, &org_devices[i]); + } + } + } + + dev_info(hdev->dev, "scan work add device count = %d\n", count); + + sort(sortdevice, count, sizeof(sortdevice[0]), + luntarget_cmp_func, NULL); + + for (i = 0; i < count; i++) + spraid_add_device(hdev, &sortdevice[i]); + +free_all: + kfree(sortdevice); +free_list: + kfree(devices); +} + +static void spraid_timesyn_work(struct work_struct *work) +{ + struct spraid_dev *hdev = + container_of(work, struct spraid_dev, timesyn_work); + + spraid_configure_timestamp(hdev); +} + +static int spraid_init_ctrl_info(struct spraid_dev *hdev); +static void spraid_fw_act_work(struct work_struct *work) +{ + struct spraid_dev *hdev = + container_of(work, struct spraid_dev, fw_act_work); + + if (spraid_init_ctrl_info(hdev)) + dev_err(hdev->dev, "get ctrl info failed after fw act\n"); +} + +static void spraid_queue_scan(struct spraid_dev *hdev) +{ + queue_work(spraid_wq, &hdev->scan_work); +} + +static void spraid_handle_aen_notice(struct spraid_dev *hdev, u32 result) +{ + switch ((result & 0xff00) >> 8) { + case SPRAID_AEN_DEV_CHANGED: + spraid_queue_scan(hdev); + break; + case SPRAID_AEN_FW_ACT_START: + dev_info(hdev->dev, "fw activation starting\n"); + break; + case SPRAID_AEN_HOST_PROBING: + break; + default: + dev_warn(hdev->dev, "async event result %08x\n", result); + } +} + +static void spraid_handle_aen_vs(struct spraid_dev *hdev, + u32 result, u32 result1) +{ + switch ((result & 0xff00) >> 8) { + case SPRAID_AEN_TIMESYN: + queue_work(spraid_wq, &hdev->timesyn_work); + break; + case SPRAID_AEN_FW_ACT_FINISH: + dev_info(hdev->dev, "fw activation finish\n"); + queue_work(spraid_wq, &hdev->fw_act_work); + break; + case SPRAID_AEN_EVENT_MIN ... SPRAID_AEN_EVENT_MAX: + dev_info(hdev->dev, "rcv card event[%d];" + " param1[0x%x] param2[0x%x]\n", + (result & 0xff00) >> 8, result, result1); + break; + default: + dev_warn(hdev->dev, "async event result: 0x%x\n", result); + } +} + +static int spraid_alloc_resources(struct spraid_dev *hdev) +{ + int ret, nqueue; + + ret = ida_alloc(&spraid_instance_ida, GFP_KERNEL); + if (ret < 0) { + dev_err(hdev->dev, "Get instance id failed\n"); + return ret; + } + hdev->instance = ret; + + hdev->ctrl_info = kzalloc_node(sizeof(*hdev->ctrl_info), + GFP_KERNEL, hdev->numa_node); + if (!hdev->ctrl_info) { + ret = -ENOMEM; + goto release_instance; + } + + ret = spraid_create_dma_pools(hdev); + if (ret) + goto free_ctrl_info; + nqueue = num_possible_cpus() + 1; + hdev->queues = kcalloc_node(nqueue, sizeof(struct spraid_queue), + GFP_KERNEL, hdev->numa_node); + if (!hdev->queues) { + ret = -ENOMEM; + goto destroy_dma_pools; + } + + ret = spraid_alloc_admin_cmds(hdev); + if (ret) + goto free_queues; + + dev_info(hdev->dev, "[%s] queues num: %d\n", __func__, nqueue); + + return 0; + +free_queues: + kfree(hdev->queues); +destroy_dma_pools: + spraid_destroy_dma_pools(hdev); +free_ctrl_info: + kfree(hdev->ctrl_info); +release_instance: + ida_free(&spraid_instance_ida, hdev->instance); + return ret; +} + +static void spraid_free_resources(struct spraid_dev *hdev) +{ + spraid_free_admin_cmds(hdev); + kfree(hdev->queues); + spraid_destroy_dma_pools(hdev); + kfree(hdev->ctrl_info); + ida_free(&spraid_instance_ida, hdev->instance); +} + +static void spraid_bsg_unmap_data(struct spraid_dev *hdev, struct bsg_job *job) +{ + struct request *rq = blk_mq_rq_from_pdu(job); + struct spraid_iod *iod = job->dd_data; + enum dma_data_direction dma_dir = + rq_data_dir(rq) ? DMA_TO_DEVICE : DMA_FROM_DEVICE; + + if (iod->nsge) + dma_unmap_sg(hdev->dev, iod->sg, iod->nsge, dma_dir); + + spraid_free_iod_res(hdev, iod); +} + +static int spraid_bsg_map_data(struct spraid_dev *hdev, struct bsg_job *job, + struct spraid_admin_command *cmd) +{ + struct request *rq = blk_mq_rq_from_pdu(job); + struct spraid_iod *iod = job->dd_data; + enum dma_data_direction dma_dir = + rq_data_dir(rq) ? DMA_TO_DEVICE : DMA_FROM_DEVICE; + int ret = 0; + + iod->sg = job->request_payload.sg_list; + iod->nsge = job->request_payload.sg_cnt; + iod->length = job->request_payload.payload_len; + iod->use_sgl = false; + iod->npages = -1; + iod->sg_drv_mgmt = false; + + if (!iod->nsge) + goto out; + + ret = dma_map_sg_attrs(hdev->dev, iod->sg, iod->nsge, + dma_dir, DMA_ATTR_NO_WARN); + if (!ret) + goto out; + + ret = spraid_setup_prps(hdev, iod); + if (ret) + goto unmap; + + cmd->common.dptr.prp1 = cpu_to_le64(sg_dma_address(iod->sg)); + cmd->common.dptr.prp2 = cpu_to_le64(iod->first_dma); + + return 0; + +unmap: + dma_unmap_sg(hdev->dev, iod->sg, iod->nsge, dma_dir); +out: + return ret; +} + +static int spraid_get_ctrl_info(struct spraid_dev *hdev, + struct spraid_ctrl_info *ctrl_info) +{ + struct spraid_admin_command admin_cmd; + u8 *data_ptr = NULL; + dma_addr_t data_dma = 0; + int ret; + + data_ptr = dma_alloc_coherent(hdev->dev, PAGE_SIZE, + &data_dma, GFP_KERNEL); + if (!data_ptr) + return -ENOMEM; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.get_info.opcode = SPRAID_ADMIN_GET_INFO; + admin_cmd.get_info.type = SPRAID_GET_INFO_CTRL; + admin_cmd.common.dptr.prp1 = cpu_to_le64(data_dma); + + ret = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); + if (!ret) + memcpy(ctrl_info, data_ptr, sizeof(struct spraid_ctrl_info)); + + dma_free_coherent(hdev->dev, PAGE_SIZE, data_ptr, data_dma); + + return ret; +} + +static int spraid_init_ctrl_info(struct spraid_dev *hdev) +{ + int ret; + + hdev->ctrl_info->nd = cpu_to_le32(240); + hdev->ctrl_info->mdts = 8; + hdev->ctrl_info->max_cmds = cpu_to_le16(4096); + hdev->ctrl_info->max_num_sge = cpu_to_le16(128); + hdev->ctrl_info->max_channel = cpu_to_le16(4); + hdev->ctrl_info->max_tgt_id = cpu_to_le32(3239); + hdev->ctrl_info->max_lun = cpu_to_le16(2); + + ret = spraid_get_ctrl_info(hdev, hdev->ctrl_info); + if (ret) + dev_err(hdev->dev, "get controller info failed: %d\n", ret); + + dev_info(hdev->dev, "[%s]nd = %d\n", __func__, hdev->ctrl_info->nd); + dev_info(hdev->dev, "[%s]max_cmd = %d\n", + __func__, hdev->ctrl_info->max_cmds); + dev_info(hdev->dev, "[%s]max_channel = %d\n", + __func__, hdev->ctrl_info->max_channel); + dev_info(hdev->dev, "[%s]max_tgt_id = %d\n", + __func__, hdev->ctrl_info->max_tgt_id); + dev_info(hdev->dev, "[%s]max_lun = %d\n", + __func__, hdev->ctrl_info->max_lun); + dev_info(hdev->dev, "[%s]max_num_sge = %d\n", + __func__, hdev->ctrl_info->max_num_sge); + dev_info(hdev->dev, "[%s]lun_num_boot = %d\n", + __func__, hdev->ctrl_info->lun_num_in_boot); + dev_info(hdev->dev, "[%s]mdts = %d\n", __func__, hdev->ctrl_info->mdts); + dev_info(hdev->dev, "[%s]acl = %d\n", __func__, hdev->ctrl_info->acl); + dev_info(hdev->dev, "[%s]aer1 = %d\n", __func__, hdev->ctrl_info->aerl); + dev_info(hdev->dev, "[%s]card_type = %d\n", + __func__, hdev->ctrl_info->card_type); + dev_info(hdev->dev, "[%s]rtd3e = %d\n", + __func__, hdev->ctrl_info->rtd3e); + dev_info(hdev->dev, "[%s]sn = %s\n", __func__, hdev->ctrl_info->sn); + dev_info(hdev->dev, "[%s]fr = %s\n", __func__, hdev->ctrl_info->fr); + + if (!hdev->ctrl_info->aerl) + hdev->ctrl_info->aerl = 1; + if (hdev->ctrl_info->aerl > SPRAID_NR_AEN_COMMANDS) + hdev->ctrl_info->aerl = SPRAID_NR_AEN_COMMANDS; + + return 0; +} + +#define SPRAID_MAX_ADMIN_PAYLOAD_SIZE BIT(16) +static int spraid_alloc_iod_ext_mem_pool(struct spraid_dev *hdev) +{ + u16 max_sge = le16_to_cpu(hdev->ctrl_info->max_num_sge); + size_t alloc_size; + + alloc_size = spraid_iod_ext_size(hdev, SPRAID_MAX_ADMIN_PAYLOAD_SIZE, + max_sge, true, false); + if (alloc_size > PAGE_SIZE) + dev_warn(hdev->dev, "It is unreasonable ;" + " sg allocation more than one page\n"); + hdev->iod_mempool = mempool_create_node(1, mempool_kmalloc, + mempool_kfree, + (void *)alloc_size, GFP_KERNEL, + hdev->numa_node); + if (!hdev->iod_mempool) { + dev_err(hdev->dev, "Create iod extension memory pool failed\n"); + return -ENOMEM; + } + + return 0; +} + +static void spraid_free_iod_ext_mem_pool(struct spraid_dev *hdev) +{ + mempool_destroy(hdev->iod_mempool); +} + +static int spraid_user_admin_cmd(struct spraid_dev *hdev, struct bsg_job *job) +{ + struct spraid_bsg_request *bsg_req = job->request; + struct spraid_passthru_common_cmd *cmd = &(bsg_req->admcmd); + struct spraid_admin_command admin_cmd; + u32 timeout = msecs_to_jiffies(cmd->timeout_ms); + u32 result[2] = {0}; + int status; + + if (hdev->state >= SPRAID_RESETTING) { + dev_err(hdev->dev, "[%s] err, host state:[%d] is not right\n", + __func__, hdev->state); + return -EBUSY; + } + + dev_info(hdev->dev, "[%s] opcode[0x%x] subopcode[0x%x] init\n", + __func__, cmd->opcode, cmd->info_0.subopcode); + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.common.opcode = cmd->opcode; + admin_cmd.common.flags = cmd->flags; + admin_cmd.common.hdid = cpu_to_le32(cmd->nsid); + admin_cmd.common.cdw2[0] = cpu_to_le32(cmd->cdw2); + admin_cmd.common.cdw2[1] = cpu_to_le32(cmd->cdw3); + admin_cmd.common.cdw10 = cpu_to_le32(cmd->cdw10); + admin_cmd.common.cdw11 = cpu_to_le32(cmd->cdw11); + admin_cmd.common.cdw12 = cpu_to_le32(cmd->cdw12); + admin_cmd.common.cdw13 = cpu_to_le32(cmd->cdw13); + admin_cmd.common.cdw14 = cpu_to_le32(cmd->cdw14); + admin_cmd.common.cdw15 = cpu_to_le32(cmd->cdw15); + + status = spraid_bsg_map_data(hdev, job, &admin_cmd); + if (status) { + dev_err(hdev->dev, "[%s] err, map data failed\n", __func__); + return status; + } + + status = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, &result[0], + &result[1], timeout); + if (status >= 0) { + job->reply_len = sizeof(result); + memcpy(job->reply, result, sizeof(result)); + } + + dev_info(hdev->dev, "[%s] opcode[0x%x] subopcode[0x%x];" + " status[0x%x] result0[0x%x] result1[0x%x]\n", + __func__, cmd->opcode, cmd->info_0.subopcode, + status, result[0], result[1]); + + spraid_bsg_unmap_data(hdev, job); + + return status; +} + +static int spraid_alloc_ioq_ptcmds(struct spraid_dev *hdev) +{ + int i; + int ptnum = SPRAID_NR_IOQ_PTCMDS; + + INIT_LIST_HEAD(&hdev->ioq_pt_list); + spin_lock_init(&hdev->ioq_pt_lock); + + hdev->ioq_ptcmds = kcalloc_node(ptnum, sizeof(struct spraid_cmd), + GFP_KERNEL, hdev->numa_node); + + if (!hdev->ioq_ptcmds) { + dev_err(hdev->dev, "Alloc ioq_ptcmds failed\n"); + return -ENOMEM; + } + + for (i = 0; i < ptnum; i++) { + hdev->ioq_ptcmds[i].qid = i / SPRAID_PTCMDS_PERQ + 1; + hdev->ioq_ptcmds[i].cid = i % SPRAID_PTCMDS_PERQ + + SPRAID_IO_BLK_MQ_DEPTH; + list_add_tail(&(hdev->ioq_ptcmds[i].list), &hdev->ioq_pt_list); + } + + dev_info(hdev->dev, "Alloc ioq_ptcmds success, ptnum[%d]\n", ptnum); + + return 0; +} + +static void spraid_free_ioq_ptcmds(struct spraid_dev *hdev) +{ + kfree(hdev->ioq_ptcmds); + hdev->ioq_ptcmds = NULL; + + INIT_LIST_HEAD(&hdev->ioq_pt_list); +} + +static int spraid_submit_ioq_sync_cmd(struct spraid_dev *hdev, + struct spraid_ioq_command *cmd, + u32 *result, u32 *reslen, u32 timeout) +{ + int ret; + dma_addr_t sense_dma; + struct spraid_queue *ioq; + void *sense_addr = NULL; + struct spraid_cmd *pt_cmd = spraid_get_cmd(hdev, SPRAID_CMD_IOPT); + + if (!pt_cmd) { + dev_err(hdev->dev, "err, get ioq cmd failed\n"); + return -EFAULT; + } + + timeout = timeout ? timeout : ADMIN_TIMEOUT; + + init_completion(&pt_cmd->cmd_done); + + ioq = &hdev->queues[pt_cmd->qid]; + ret = pt_cmd->cid * SCSI_SENSE_BUFFERSIZE; + sense_addr = ioq->sense + ret; + sense_dma = ioq->sense_dma_addr + ret; + + cmd->common.sense_addr = cpu_to_le64(sense_dma); + cmd->common.sense_len = cpu_to_le16(SCSI_SENSE_BUFFERSIZE); + cmd->common.command_id = pt_cmd->cid; + + spraid_submit_cmd(ioq, cmd); + + if (!wait_for_completion_timeout(&pt_cmd->cmd_done, timeout)) { + dev_err(hdev->dev, "[%s] cid[%d] qid[%d] timeout;" + " opcode[0x%x] subopcode[0x%x]\n", + __func__, pt_cmd->cid, pt_cmd->qid, cmd->common.opcode, + (le32_to_cpu(cmd->common.cdw3[0]) & 0xffff)); + WRITE_ONCE(pt_cmd->state, SPRAID_CMD_TIMEOUT); + spraid_put_cmd(hdev, pt_cmd, SPRAID_CMD_IOPT); + return -EINVAL; + } + + if (result && reslen) { + if ((pt_cmd->status & 0x17f) == 0x101) { + memcpy(result, sense_addr, SCSI_SENSE_BUFFERSIZE); + *reslen = SCSI_SENSE_BUFFERSIZE; + } + } + + spraid_put_cmd(hdev, pt_cmd, SPRAID_CMD_IOPT); + + return pt_cmd->status; +} + +static int spraid_user_ioq_cmd(struct spraid_dev *hdev, struct bsg_job *job) +{ + struct spraid_bsg_request *bsg_req = + (struct spraid_bsg_request *)(job->request); + struct spraid_ioq_passthru_cmd *cmd = &(bsg_req->ioqcmd); + struct spraid_ioq_command ioq_cmd; + int status = 0; + u32 timeout = msecs_to_jiffies(cmd->timeout_ms); + + if (cmd->data_len > PAGE_SIZE) { + dev_err(hdev->dev, "[%s] data len bigger than 4k\n", __func__); + return -EFAULT; + } + + if (hdev->state != SPRAID_LIVE) { + dev_err(hdev->dev, "[%s] err, host state:[%d] is not live\n", + __func__, hdev->state); + return -EBUSY; + } + + dev_info(hdev->dev, "[%s] opcode[0x%x] subopcode[0x%x] init;" + " datalen[%d]\n", + __func__, cmd->opcode, cmd->info_1.subopcode, cmd->data_len); + + memset(&ioq_cmd, 0, sizeof(ioq_cmd)); + ioq_cmd.common.opcode = cmd->opcode; + ioq_cmd.common.flags = cmd->flags; + ioq_cmd.common.hdid = cpu_to_le32(cmd->nsid); + ioq_cmd.common.sense_len = cpu_to_le16(cmd->info_0.res_sense_len); + ioq_cmd.common.cdb_len = cmd->info_0.cdb_len; + ioq_cmd.common.rsvd2 = cmd->info_0.rsvd0; + ioq_cmd.common.cdw3[0] = cpu_to_le32(cmd->cdw3); + ioq_cmd.common.cdw3[1] = cpu_to_le32(cmd->cdw4); + ioq_cmd.common.cdw3[2] = cpu_to_le32(cmd->cdw5); + + ioq_cmd.common.cdw10[0] = cpu_to_le32(cmd->cdw10); + ioq_cmd.common.cdw10[1] = cpu_to_le32(cmd->cdw11); + ioq_cmd.common.cdw10[2] = cpu_to_le32(cmd->cdw12); + ioq_cmd.common.cdw10[3] = cpu_to_le32(cmd->cdw13); + ioq_cmd.common.cdw10[4] = cpu_to_le32(cmd->cdw14); + ioq_cmd.common.cdw10[5] = cpu_to_le32(cmd->data_len); + + memcpy(ioq_cmd.common.cdb, &cmd->cdw16, cmd->info_0.cdb_len); + + ioq_cmd.common.cdw26[0] = cpu_to_le32(cmd->cdw26[0]); + ioq_cmd.common.cdw26[1] = cpu_to_le32(cmd->cdw26[1]); + ioq_cmd.common.cdw26[2] = cpu_to_le32(cmd->cdw26[2]); + ioq_cmd.common.cdw26[3] = cpu_to_le32(cmd->cdw26[3]); + + status = spraid_bsg_map_data(hdev, job, + (struct spraid_admin_command *)&ioq_cmd); + if (status) { + dev_err(hdev->dev, "[%s] err, map data failed\n", __func__); + return status; + } + + status = spraid_submit_ioq_sync_cmd(hdev, &ioq_cmd, job->reply, + &job->reply_len, timeout); + + dev_info(hdev->dev, "[%s] opcode[0x%x] subopcode[0x%x], status[0x%x];" + " reply_len[%d]\n", + __func__, cmd->opcode, cmd->info_1.subopcode, + status, job->reply_len); + + spraid_bsg_unmap_data(hdev, job); + + return status; +} + +static bool spraid_check_scmd_completed(struct scsi_cmnd *scmd) +{ + struct spraid_dev *hdev = shost_priv(scmd->device->host); + struct spraid_iod *iod = scsi_cmd_priv(scmd); + struct spraid_queue *spraidq; + u16 hwq, cid; + + spraid_get_tag_from_scmd(scmd, &hwq, &cid); + spraidq = &hdev->queues[hwq]; + if (READ_ONCE(iod->state) == SPRAID_CMD_COMPLETE + || spraid_poll_cq(spraidq, cid)) { + dev_warn(hdev->dev, "cid[%d] qid[%d] has been completed\n", + cid, spraidq->qid); + return true; + } + return false; +} + +static enum blk_eh_timer_return spraid_scmd_timeout(struct scsi_cmnd *scmd) +{ + struct spraid_iod *iod = scsi_cmd_priv(scmd); + unsigned int timeout = scmd->device->request_queue->rq_timeout; + + if (spraid_check_scmd_completed(scmd)) + goto out; + + if (time_after(jiffies, scmd->jiffies_at_alloc + timeout)) { + if (cmpxchg(&iod->state, + SPRAID_CMD_IN_FLIGHT, + SPRAID_CMD_TIMEOUT) == SPRAID_CMD_IN_FLIGHT) { + return BLK_EH_DONE; + } + } +out: + return BLK_EH_RESET_TIMER; +} + +/* send abort command by admin queue temporary */ +static int spraid_send_abort_cmd(struct spraid_dev *hdev, + u32 hdid, u16 qid, u16 cid) +{ + struct spraid_admin_command admin_cmd; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.abort.opcode = SPRAID_ADMIN_ABORT_CMD; + admin_cmd.abort.hdid = cpu_to_le32(hdid); + admin_cmd.abort.sqid = cpu_to_le16(qid); + admin_cmd.abort.cid = cpu_to_le16(cid); + + return spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); +} + +/* send reset command by admin quueue temporary */ +static int spraid_send_reset_cmd(struct spraid_dev *hdev, int type, u32 hdid) +{ + struct spraid_admin_command admin_cmd; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.reset.opcode = SPRAID_ADMIN_RESET; + admin_cmd.reset.hdid = cpu_to_le32(hdid); + admin_cmd.reset.type = type; + + return spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); +} + +static bool spraid_change_host_state(struct spraid_dev *hdev, + enum spraid_state newstate) +{ + unsigned long flags; + enum spraid_state oldstate; + bool change = false; + + spin_lock_irqsave(&hdev->state_lock, flags); + + oldstate = hdev->state; + switch (newstate) { + case SPRAID_LIVE: + switch (oldstate) { + case SPRAID_NEW: + case SPRAID_RESETTING: + change = true; + break; + default: + break; + } + break; + case SPRAID_RESETTING: + switch (oldstate) { + case SPRAID_LIVE: + change = true; + break; + default: + break; + } + break; + case SPRAID_DELETING: + if (oldstate != SPRAID_DELETING) + change = true; + break; + case SPRAID_DEAD: + switch (oldstate) { + case SPRAID_NEW: + case SPRAID_LIVE: + case SPRAID_RESETTING: + change = true; + break; + default: + break; + } + break; + default: + break; + } + if (change) + hdev->state = newstate; + spin_unlock_irqrestore(&hdev->state_lock, flags); + + dev_info(hdev->dev, "[%s][%d]->[%d], change[%d]\n", + __func__, oldstate, newstate, change); + + return change; +} + +static void spraid_back_fault_cqe(struct spraid_queue *ioq, + struct spraid_completion *cqe) +{ + struct spraid_dev *hdev = ioq->hdev; + struct blk_mq_tags *tags; + struct scsi_cmnd *scmd; + struct spraid_iod *iod; + struct request *req; + + tags = hdev->shost->tag_set.tags[ioq->qid - 1]; + req = blk_mq_tag_to_rq(tags, cqe->cmd_id); + if (unlikely(!req || !blk_mq_request_started(req))) + return; + + scmd = blk_mq_rq_to_pdu(req); + iod = scsi_cmd_priv(scmd); + + set_host_byte(scmd, DID_NO_CONNECT); + if (iod->nsge) + scsi_dma_unmap(scmd); + spraid_free_iod_res(hdev, iod); + scmd->scsi_done(scmd); + dev_warn(hdev->dev, "Back fault CQE, cid[%d] qid[%d]\n", + cqe->cmd_id, ioq->qid); +} + +static void spraid_back_all_io(struct spraid_dev *hdev) +{ + int i, j; + struct spraid_queue *ioq; + struct spraid_completion cqe = { 0 }; + + scsi_block_requests(hdev->shost); + + for (i = 1; i <= hdev->shost->nr_hw_queues; i++) { + ioq = &hdev->queues[i]; + for (j = 0; j < hdev->shost->can_queue; j++) { + cqe.cmd_id = j; + spraid_back_fault_cqe(ioq, &cqe); + } + } + + scsi_unblock_requests(hdev->shost); +} + +static void spraid_dev_disable(struct spraid_dev *hdev, bool shutdown) +{ + struct spraid_queue *adminq = &hdev->queues[0]; + u16 start, end; + unsigned long timeout = jiffies + 600 * HZ; + + if (pci_device_is_present(hdev->pdev)) { + if (shutdown) + spraid_shutdown_ctrl(hdev); + else + spraid_disable_ctrl(hdev); + } + + while (!time_after(jiffies, timeout)) { + if (!pci_device_is_present(hdev->pdev)) { + dev_info(hdev->dev, "[%s] pci_device not present;" + " skip wait\n", __func__); + break; + } + if (!spraid_wait_ready(hdev, hdev->cap, false)) { + dev_info(hdev->dev, + "[%s] wait ready success after reset\n", + __func__); + break; + } + dev_info(hdev->dev, "[%s] waiting csts_rdy ready\n", __func__); + } + + if (hdev->queue_count == 0) { + dev_err(hdev->dev, "[%s] warn, queue has been delete\n", + __func__); + return; + } + + spin_lock_irq(&adminq->cq_lock); + spraid_process_cq(adminq, &start, &end, -1); + spin_unlock_irq(&adminq->cq_lock); + spraid_complete_cqes(adminq, start, end); + + spraid_pci_disable(hdev); + + spraid_back_all_io(hdev); +} + +static void spraid_reset_work(struct work_struct *work) +{ + int ret; + struct spraid_dev *hdev = + container_of(work, struct spraid_dev, reset_work); + + if (hdev->state != SPRAID_RESETTING) { + dev_err(hdev->dev, "[%s] err, host is not reset state\n", + __func__); + return; + } + + dev_info(hdev->dev, "[%s] enter host reset\n", __func__); + + if (hdev->ctrl_config & SPRAID_CC_ENABLE) { + dev_info(hdev->dev, "[%s] start dev_disable\n", __func__); + spraid_dev_disable(hdev, false); + } + + ret = spraid_pci_enable(hdev); + if (ret) + goto out; + + ret = spraid_setup_admin_queue(hdev); + if (ret) + goto pci_disable; + + ret = spraid_setup_io_queues(hdev); + if (ret || hdev->online_queues <= hdev->shost->nr_hw_queues) + goto pci_disable; + + spraid_change_host_state(hdev, SPRAID_LIVE); + + spraid_send_all_aen(hdev); + + return; + +pci_disable: + spraid_pci_disable(hdev); +out: + spraid_change_host_state(hdev, SPRAID_DEAD); + dev_err(hdev->dev, "[%s] err, host reset failed\n", __func__); +} + +static int spraid_reset_work_sync(struct spraid_dev *hdev) +{ + if (!spraid_change_host_state(hdev, SPRAID_RESETTING)) { + dev_info(hdev->dev, "[%s] can't change to reset state\n", + __func__); + return -EBUSY; + } + + if (!queue_work(spraid_wq, &hdev->reset_work)) { + dev_err(hdev->dev, "[%s] err, host is already in reset state\n", + __func__); + return -EBUSY; + } + + flush_work(&hdev->reset_work); + if (hdev->state != SPRAID_LIVE) + return -ENODEV; + + return 0; +} + +static int spraid_wait_abnl_cmd_done(struct spraid_iod *iod) +{ + u16 times = 0; + + do { + if (READ_ONCE(iod->state) == SPRAID_CMD_TMO_COMPLETE) + break; + msleep(500); + times++; + } while (times <= SPRAID_WAIT_ABNL_CMD_TIMEOUT); + + /* wait command completion timeout after abort/reset success */ + if (times >= SPRAID_WAIT_ABNL_CMD_TIMEOUT) + return -ETIMEDOUT; + + return 0; +} + +static int spraid_abort_handler(struct scsi_cmnd *scmd) +{ + struct spraid_dev *hdev = shost_priv(scmd->device->host); + struct spraid_iod *iod = scsi_cmd_priv(scmd); + struct spraid_sdev_hostdata *hostdata; + u16 hwq, cid; + int ret; + + scsi_print_command(scmd); + + if (hdev->state != SPRAID_LIVE || !spraid_wait_abnl_cmd_done(iod) || + spraid_check_scmd_completed(scmd)) + return SUCCESS; + + hostdata = scmd->device->hostdata; + spraid_get_tag_from_scmd(scmd, &hwq, &cid); + + dev_warn(hdev->dev, "cid[%d] qid[%d] timeout, aborting\n", cid, hwq); + ret = spraid_send_abort_cmd(hdev, hostdata->hdid, hwq, cid); + if (ret != ADMIN_ERR_TIMEOUT) { + ret = spraid_wait_abnl_cmd_done(iod); + if (ret) { + dev_warn(hdev->dev, "cid[%d] qid[%d] abort failed;" + " not found\n", cid, hwq); + return FAILED; + } + dev_warn(hdev->dev, "cid[%d] qid[%d] abort succ\n", cid, hwq); + return SUCCESS; + } + dev_warn(hdev->dev, "cid[%d] qid[%d] abort failed, timeout\n", + cid, hwq); + return FAILED; +} + +static int spraid_tgt_reset_handler(struct scsi_cmnd *scmd) +{ + struct spraid_dev *hdev = shost_priv(scmd->device->host); + struct spraid_iod *iod = scsi_cmd_priv(scmd); + struct spraid_sdev_hostdata *hostdata; + u16 hwq, cid; + int ret; + + scsi_print_command(scmd); + + if (hdev->state != SPRAID_LIVE || !spraid_wait_abnl_cmd_done(iod) || + spraid_check_scmd_completed(scmd)) + return SUCCESS; + + hostdata = scmd->device->hostdata; + spraid_get_tag_from_scmd(scmd, &hwq, &cid); + + dev_warn(hdev->dev, "cid[%d] qid[%d] timeout, target reset\n", + cid, hwq); + ret = spraid_send_reset_cmd(hdev, SPRAID_RESET_TARGET, hostdata->hdid); + if (ret == 0) { + ret = spraid_wait_abnl_cmd_done(iod); + if (ret) { + dev_warn(hdev->dev, + "cid[%d] qid[%d]target reset failed;" + " not found\n", cid, hwq); + return FAILED; + } + + dev_warn(hdev->dev, "cid[%d] qid[%d] target reset success\n", + cid, hwq); + return SUCCESS; + } + + dev_warn(hdev->dev, "cid[%d] qid[%d] ret[%d] target reset failed\n", + cid, hwq, ret); + return FAILED; +} + +static int spraid_bus_reset_handler(struct scsi_cmnd *scmd) +{ + struct spraid_dev *hdev = shost_priv(scmd->device->host); + struct spraid_iod *iod = scsi_cmd_priv(scmd); + struct spraid_sdev_hostdata *hostdata; + u16 hwq, cid; + int ret; + + scsi_print_command(scmd); + + if (hdev->state != SPRAID_LIVE || !spraid_wait_abnl_cmd_done(iod) || + spraid_check_scmd_completed(scmd)) + return SUCCESS; + + hostdata = scmd->device->hostdata; + spraid_get_tag_from_scmd(scmd, &hwq, &cid); + + dev_warn(hdev->dev, "cid[%d] qid[%d] timeout, bus reset\n", cid, hwq); + ret = spraid_send_reset_cmd(hdev, SPRAID_RESET_BUS, hostdata->hdid); + if (ret == 0) { + ret = spraid_wait_abnl_cmd_done(iod); + if (ret) { + dev_warn(hdev->dev, + "cid[%d] qid[%d] bus reset failed;" + " not found\n", cid, hwq); + return FAILED; + } + + dev_warn(hdev->dev, "cid[%d] qid[%d] bus reset succ\n", + cid, hwq); + return SUCCESS; + } + + dev_warn(hdev->dev, "cid[%d] qid[%d] ret[%d] bus reset failed\n", + cid, hwq, ret); + return FAILED; +} + +static int spraid_shost_reset_handler(struct scsi_cmnd *scmd) +{ + u16 hwq, cid; + struct spraid_dev *hdev = shost_priv(scmd->device->host); + + scsi_print_command(scmd); + if (hdev->state != SPRAID_LIVE || spraid_check_scmd_completed(scmd)) + return SUCCESS; + + spraid_get_tag_from_scmd(scmd, &hwq, &cid); + dev_warn(hdev->dev, "cid[%d] qid[%d] host reset\n", cid, hwq); + + if (spraid_reset_work_sync(hdev)) { + dev_warn(hdev->dev, "cid[%d] qid[%d] host reset failed\n", + cid, hwq); + return FAILED; + } + + dev_warn(hdev->dev, "cid[%d] qid[%d] host reset success\n", cid, hwq); + + return SUCCESS; +} + +static pci_ers_result_t spraid_pci_error_detected(struct pci_dev *pdev, + pci_channel_state_t state) +{ + struct spraid_dev *hdev = pci_get_drvdata(pdev); + + dev_info(hdev->dev, "enter pci error detect, state:%d\n", state); + + switch (state) { + case pci_channel_io_normal: + dev_warn(hdev->dev, "channel is normal, do nothing\n"); + + return PCI_ERS_RESULT_CAN_RECOVER; + case pci_channel_io_frozen: + dev_warn(hdev->dev, + "channel io frozen, need reset controller\n"); + + scsi_block_requests(hdev->shost); + + spraid_change_host_state(hdev, SPRAID_RESETTING); + + return PCI_ERS_RESULT_NEED_RESET; + case pci_channel_io_perm_failure: + dev_warn(hdev->dev, "channel io failure, request disconnect\n"); + + return PCI_ERS_RESULT_DISCONNECT; + } + + return PCI_ERS_RESULT_NEED_RESET; +} + +static pci_ers_result_t spraid_pci_slot_reset(struct pci_dev *pdev) +{ + struct spraid_dev *hdev = pci_get_drvdata(pdev); + + dev_info(hdev->dev, "restart after slot reset\n"); + + pci_restore_state(pdev); + + if (!queue_work(spraid_wq, &hdev->reset_work)) { + dev_err(hdev->dev, "[%s] err, the device is resetting state\n", + __func__); + return PCI_ERS_RESULT_NONE; + } + + flush_work(&hdev->reset_work); + + scsi_unblock_requests(hdev->shost); + + return PCI_ERS_RESULT_RECOVERED; +} + +static void spraid_reset_done(struct pci_dev *pdev) +{ + struct spraid_dev *hdev = pci_get_drvdata(pdev); + + dev_info(hdev->dev, "enter spraid reset done\n"); +} + +static ssize_t csts_pp_show(struct device *cdev, + struct device_attribute *attr, char *buf) +{ + struct Scsi_Host *shost = class_to_shost(cdev); + struct spraid_dev *hdev = shost_priv(shost); + int ret = -1; + + if (pci_device_is_present(hdev->pdev)) { + ret = (readl(hdev->bar + SPRAID_REG_CSTS) + & SPRAID_CSTS_PP_MASK); + ret >>= SPRAID_CSTS_PP_SHIFT; + } + + return snprintf(buf, PAGE_SIZE, "%d\n", ret); +} + +static ssize_t csts_shst_show(struct device *cdev, + struct device_attribute *attr, char *buf) +{ + struct Scsi_Host *shost = class_to_shost(cdev); + struct spraid_dev *hdev = shost_priv(shost); + int ret = -1; + + if (pci_device_is_present(hdev->pdev)) { + ret = (readl(hdev->bar + SPRAID_REG_CSTS) + & SPRAID_CSTS_SHST_MASK); + ret >>= SPRAID_CSTS_SHST_SHIFT; + } + + return snprintf(buf, PAGE_SIZE, "%d\n", ret); +} + +static ssize_t csts_cfs_show(struct device *cdev, + struct device_attribute *attr, char *buf) +{ + struct Scsi_Host *shost = class_to_shost(cdev); + struct spraid_dev *hdev = shost_priv(shost); + int ret = -1; + + if (pci_device_is_present(hdev->pdev)) { + ret = (readl(hdev->bar + SPRAID_REG_CSTS) + & SPRAID_CSTS_CFS_MASK); + ret >>= SPRAID_CSTS_CFS_SHIFT; + } + + return snprintf(buf, PAGE_SIZE, "%d\n", ret); +} + +static ssize_t csts_rdy_show(struct device *cdev, + struct device_attribute *attr, char *buf) +{ + struct Scsi_Host *shost = class_to_shost(cdev); + struct spraid_dev *hdev = shost_priv(shost); + int ret = -1; + + if (pci_device_is_present(hdev->pdev)) + ret = (readl(hdev->bar + SPRAID_REG_CSTS) & SPRAID_CSTS_RDY); + + return snprintf(buf, PAGE_SIZE, "%d\n", ret); +} + +static ssize_t fw_version_show(struct device *cdev, + struct device_attribute *attr, char *buf) +{ + struct Scsi_Host *shost = class_to_shost(cdev); + struct spraid_dev *hdev = shost_priv(shost); + + return snprintf(buf, PAGE_SIZE, "%s\n", hdev->ctrl_info->fr); +} + +static DEVICE_ATTR_RO(csts_pp); +static DEVICE_ATTR_RO(csts_shst); +static DEVICE_ATTR_RO(csts_cfs); +static DEVICE_ATTR_RO(csts_rdy); +static DEVICE_ATTR_RO(fw_version); + +static struct device_attribute *spraid_host_attrs[] = { + &dev_attr_csts_pp, + &dev_attr_csts_shst, + &dev_attr_csts_cfs, + &dev_attr_csts_rdy, + &dev_attr_fw_version, + NULL, +}; + +static int spraid_get_vd_info(struct spraid_dev *hdev, + struct spraid_vd_info *vd_info, u16 vid) +{ + struct spraid_admin_command admin_cmd; + u8 *data_ptr = NULL; + dma_addr_t data_dma = 0; + int ret; + + data_ptr = dma_alloc_coherent(hdev->dev, PAGE_SIZE, + &data_dma, GFP_KERNEL); + if (!data_ptr) + return -ENOMEM; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.usr_cmd.opcode = USR_CMD_READ; + admin_cmd.usr_cmd.info_0.subopcode = cpu_to_le16(USR_CMD_VDINFO); + admin_cmd.usr_cmd.info_1.data_len = cpu_to_le16(USR_CMD_RDLEN); + admin_cmd.usr_cmd.info_1.param_len = cpu_to_le16(VDINFO_PARAM_LEN); + admin_cmd.usr_cmd.cdw10 = cpu_to_le32(vid); + admin_cmd.common.dptr.prp1 = cpu_to_le64(data_dma); + + ret = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); + if (!ret) + memcpy(vd_info, data_ptr, sizeof(struct spraid_vd_info)); + + dma_free_coherent(hdev->dev, PAGE_SIZE, data_ptr, data_dma); + + return ret; +} + +static int spraid_get_bgtask(struct spraid_dev *hdev, + struct spraid_bgtask *bgtask) +{ + struct spraid_admin_command admin_cmd; + u8 *data_ptr = NULL; + dma_addr_t data_dma = 0; + int ret; + + data_ptr = dma_alloc_coherent(hdev->dev, PAGE_SIZE, + &data_dma, GFP_KERNEL); + if (!data_ptr) + return -ENOMEM; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.usr_cmd.opcode = USR_CMD_READ; + admin_cmd.usr_cmd.info_0.subopcode = cpu_to_le16(USR_CMD_BGTASK); + admin_cmd.usr_cmd.info_1.data_len = cpu_to_le16(USR_CMD_RDLEN); + admin_cmd.common.dptr.prp1 = cpu_to_le64(data_dma); + + ret = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); + if (!ret) + memcpy(bgtask, data_ptr, sizeof(struct spraid_bgtask)); + + dma_free_coherent(hdev->dev, PAGE_SIZE, data_ptr, data_dma); + + return ret; +} + +static ssize_t raid_level_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct scsi_device *sdev; + struct spraid_dev *hdev; + struct spraid_vd_info *vd_info; + struct spraid_sdev_hostdata *hostdata; + int ret; + + sdev = to_scsi_device(dev); + hdev = shost_priv(sdev->host); + hostdata = sdev->hostdata; + + vd_info = kmalloc(sizeof(*vd_info), GFP_KERNEL); + if (!vd_info || !SPRAID_DEV_INFO_ATTR_VD(hostdata->attr)) + return snprintf(buf, PAGE_SIZE, "NA\n"); + + ret = spraid_get_vd_info(hdev, vd_info, sdev->id); + if (ret) + vd_info->rg_level = ARRAY_SIZE(raid_levels) - 1; + + ret = (vd_info->rg_level < ARRAY_SIZE(raid_levels)) ? + vd_info->rg_level : (ARRAY_SIZE(raid_levels) - 1); + + kfree(vd_info); + + return snprintf(buf, PAGE_SIZE, "RAID-%s\n", raid_levels[ret]); +} + +static ssize_t raid_state_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct scsi_device *sdev; + struct spraid_dev *hdev; + struct spraid_vd_info *vd_info; + struct spraid_sdev_hostdata *hostdata; + int ret; + + sdev = to_scsi_device(dev); + hdev = shost_priv(sdev->host); + hostdata = sdev->hostdata; + + vd_info = kmalloc(sizeof(*vd_info), GFP_KERNEL); + if (!vd_info || !SPRAID_DEV_INFO_ATTR_VD(hostdata->attr)) + return snprintf(buf, PAGE_SIZE, "NA\n"); + + ret = spraid_get_vd_info(hdev, vd_info, sdev->id); + if (ret) { + vd_info->vd_status = 0; + vd_info->rg_id = 0xff; + } + + ret = (vd_info->vd_status < ARRAY_SIZE(raid_states)) ? + vd_info->vd_status : 0; + + kfree(vd_info); + + return snprintf(buf, PAGE_SIZE, "%s\n", raid_states[ret]); +} + +static ssize_t raid_resync_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct scsi_device *sdev; + struct spraid_dev *hdev; + struct spraid_vd_info *vd_info; + struct spraid_bgtask *bgtask; + struct spraid_sdev_hostdata *hostdata; + u8 rg_id, i, progress = 0; + int ret; + + sdev = to_scsi_device(dev); + hdev = shost_priv(sdev->host); + hostdata = sdev->hostdata; + + vd_info = kmalloc(sizeof(*vd_info), GFP_KERNEL); + if (!vd_info || !SPRAID_DEV_INFO_ATTR_VD(hostdata->attr)) + return snprintf(buf, PAGE_SIZE, "NA\n"); + + ret = spraid_get_vd_info(hdev, vd_info, sdev->id); + if (ret) + goto out; + + rg_id = vd_info->rg_id; + + bgtask = (struct spraid_bgtask *)vd_info; + ret = spraid_get_bgtask(hdev, bgtask); + if (ret) + goto out; + for (i = 0; i < bgtask->task_num; i++) { + if ((bgtask->bgtask[i].type == BGTASK_TYPE_REBUILD) && + (le16_to_cpu(bgtask->bgtask[i].vd_id) == rg_id)) + progress = bgtask->bgtask[i].progress; + } + +out: + kfree(vd_info); + return snprintf(buf, PAGE_SIZE, "%d\n", progress); +} + +static DEVICE_ATTR_RO(raid_level); +static DEVICE_ATTR_RO(raid_state); +static DEVICE_ATTR_RO(raid_resync); + +static struct device_attribute *spraid_dev_attrs[] = { + &dev_attr_raid_level, + &dev_attr_raid_state, + &dev_attr_raid_resync, + NULL, +}; + +static struct pci_error_handlers spraid_err_handler = { + .error_detected = spraid_pci_error_detected, + .slot_reset = spraid_pci_slot_reset, + .reset_done = spraid_reset_done, +}; + +static int spraid_sysfs_host_reset(struct Scsi_Host *shost, int reset_type) +{ + int ret; + struct spraid_dev *hdev = shost_priv(shost); + + dev_info(hdev->dev, "[%s] start sysfs host reset cmd\n", __func__); + ret = spraid_reset_work_sync(hdev); + dev_info(hdev->dev, "[%s] stop sysfs host reset cmd[%d]\n", + __func__, ret); + + return ret; +} + +static struct scsi_host_template spraid_driver_template = { + .module = THIS_MODULE, + .name = "Ramaxel Logic spraid driver", + .proc_name = "spraid", + .queuecommand = spraid_queue_command, + .slave_alloc = spraid_slave_alloc, + .slave_destroy = spraid_slave_destroy, + .slave_configure = spraid_slave_configure, + .eh_timed_out = spraid_scmd_timeout, + .eh_abort_handler = spraid_abort_handler, + .eh_target_reset_handler = spraid_tgt_reset_handler, + .eh_bus_reset_handler = spraid_bus_reset_handler, + .eh_host_reset_handler = spraid_shost_reset_handler, + .change_queue_depth = scsi_change_queue_depth, + .this_id = -1, + .shost_attrs = spraid_host_attrs, + .sdev_attrs = spraid_dev_attrs, + .host_reset = spraid_sysfs_host_reset, +}; + +static void spraid_shutdown(struct pci_dev *pdev) +{ + struct spraid_dev *hdev = pci_get_drvdata(pdev); + + spraid_remove_io_queues(hdev); + spraid_disable_admin_queue(hdev, true); +} + +/* bsg dispatch user command */ +static int spraid_bsg_host_dispatch(struct bsg_job *job) +{ + struct Scsi_Host *shost = dev_to_shost(job->dev); + struct spraid_dev *hdev = shost_priv(shost); + struct request *rq = blk_mq_rq_from_pdu(job); + struct spraid_bsg_request *bsg_req = job->request; + int ret = 0; + + dev_info(hdev->dev, "[%s] msgcode[%d], msglen[%d], timeout[%d];" + " req_nsge[%d], req_len[%d]\n", + __func__, bsg_req->msgcode, job->request_len, + rq->timeout, job->request_payload.sg_cnt, + job->request_payload.payload_len); + + job->reply_len = 0; + + switch (bsg_req->msgcode) { + case SPRAID_BSG_ADM: + ret = spraid_user_admin_cmd(hdev, job); + break; + case SPRAID_BSG_IOQ: + ret = spraid_user_ioq_cmd(hdev, job); + break; + default: + dev_info(hdev->dev, "[%s] unsupport msgcode[%d]\n", + __func__, bsg_req->msgcode); + break; + } + + if (ret > 0) + ret = ret | (ret << 8); + + bsg_job_done(job, ret, 0); + return 0; +} + +static inline void spraid_remove_bsg(struct spraid_dev *hdev) +{ + if (hdev->bsg_queue) { + bsg_unregister_queue(hdev->bsg_queue); + blk_cleanup_queue(hdev->bsg_queue); + } +} +static int spraid_probe(struct pci_dev *pdev, const struct pci_device_id *id) +{ + struct spraid_dev *hdev; + struct Scsi_Host *shost; + int node, ret; + char bsg_name[15]; + + shost = scsi_host_alloc(&spraid_driver_template, sizeof(*hdev)); + if (!shost) { + dev_err(&pdev->dev, "Failed to allocate scsi host\n"); + return -ENOMEM; + } + hdev = shost_priv(shost); + hdev->pdev = pdev; + hdev->dev = get_device(&pdev->dev); + + node = dev_to_node(hdev->dev); + if (node == NUMA_NO_NODE) { + node = first_memory_node; + set_dev_node(hdev->dev, node); + } + hdev->numa_node = node; + hdev->shost = shost; + pci_set_drvdata(pdev, hdev); + + ret = spraid_dev_map(hdev); + if (ret) + goto put_dev; + + init_rwsem(&hdev->devices_rwsem); + INIT_WORK(&hdev->scan_work, spraid_scan_work); + INIT_WORK(&hdev->timesyn_work, spraid_timesyn_work); + INIT_WORK(&hdev->reset_work, spraid_reset_work); + INIT_WORK(&hdev->fw_act_work, spraid_fw_act_work); + spin_lock_init(&hdev->state_lock); + + ret = spraid_alloc_resources(hdev); + if (ret) + goto dev_unmap; + + ret = spraid_pci_enable(hdev); + if (ret) + goto resources_free; + + ret = spraid_setup_admin_queue(hdev); + if (ret) + goto pci_disable; + + ret = spraid_init_ctrl_info(hdev); + if (ret) + goto disable_admin_q; + + ret = spraid_alloc_iod_ext_mem_pool(hdev); + if (ret) + goto disable_admin_q; + + ret = spraid_setup_io_queues(hdev); + if (ret) + goto free_iod_mempool; + + spraid_shost_init(hdev); + + ret = scsi_add_host(hdev->shost, hdev->dev); + if (ret) { + dev_err(hdev->dev, "Add shost to system failed, ret: %d\n", + ret); + goto remove_io_queues; + } + + snprintf(bsg_name, sizeof(bsg_name), "spraid%d", shost->host_no); + hdev->bsg_queue = bsg_setup_queue(&shost->shost_gendev, bsg_name, + spraid_bsg_host_dispatch, + spraid_cmd_size(hdev, true, false)); + if (IS_ERR(hdev->bsg_queue)) { + dev_err(hdev->dev, "err, setup bsg failed\n"); + hdev->bsg_queue = NULL; + goto remove_io_queues; + } + + if (hdev->online_queues == SPRAID_ADMIN_QUEUE_NUM) { + dev_warn(hdev->dev, "warn only admin queue can be used\n"); + return 0; + } + + hdev->state = SPRAID_LIVE; + + spraid_send_all_aen(hdev); + + ret = spraid_dev_list_init(hdev); + if (ret) + goto remove_bsg; + + ret = spraid_configure_timestamp(hdev); + if (ret) + dev_warn(hdev->dev, "init set timestamp failed\n"); + + ret = spraid_alloc_ioq_ptcmds(hdev); + if (ret) + goto remove_bsg; + + scsi_scan_host(hdev->shost); + + return 0; + +remove_bsg: + spraid_remove_bsg(hdev); +remove_io_queues: + spraid_remove_io_queues(hdev); +free_iod_mempool: + spraid_free_iod_ext_mem_pool(hdev); +disable_admin_q: + spraid_disable_admin_queue(hdev, false); +pci_disable: + spraid_pci_disable(hdev); +resources_free: + spraid_free_resources(hdev); +dev_unmap: + spraid_dev_unmap(hdev); +put_dev: + put_device(hdev->dev); + scsi_host_put(shost); + + return -ENODEV; +} + +static void spraid_remove(struct pci_dev *pdev) +{ + struct spraid_dev *hdev = pci_get_drvdata(pdev); + struct Scsi_Host *shost = hdev->shost; + + dev_info(hdev->dev, "enter spraid remove\n"); + + spraid_change_host_state(hdev, SPRAID_DELETING); + flush_work(&hdev->reset_work); + + if (!pci_device_is_present(pdev)) + spraid_back_all_io(hdev); + + spraid_remove_bsg(hdev); + scsi_remove_host(shost); + spraid_free_ioq_ptcmds(hdev); + kfree(hdev->devices); + spraid_remove_io_queues(hdev); + spraid_free_iod_ext_mem_pool(hdev); + spraid_disable_admin_queue(hdev, false); + spraid_pci_disable(hdev); + spraid_free_resources(hdev); + spraid_dev_unmap(hdev); + put_device(hdev->dev); + scsi_host_put(shost); + + dev_info(hdev->dev, "exit spraid remove\n"); +} + +static const struct pci_device_id spraid_id_table[] = { + { PCI_DEVICE(PCI_VENDOR_ID_RAMAXEL_LOGIC, + SPRAID_SERVER_DEVICE_HBA_DID) }, + { PCI_DEVICE(PCI_VENDOR_ID_RAMAXEL_LOGIC, + SPRAID_SERVER_DEVICE_RAID_DID) }, + { 0, } +}; +MODULE_DEVICE_TABLE(pci, spraid_id_table); + +static struct pci_driver spraid_driver = { + .name = "spraid", + .id_table = spraid_id_table, + .probe = spraid_probe, + .remove = spraid_remove, + .shutdown = spraid_shutdown, + .err_handler = &spraid_err_handler, +}; + +static int __init spraid_init(void) +{ + int ret; + + spraid_wq = alloc_workqueue("spraid-wq", WQ_UNBOUND | WQ_MEM_RECLAIM | + WQ_SYSFS, 0); + if (!spraid_wq) + return -ENOMEM; + + spraid_class = class_create(THIS_MODULE, "spraid"); + if (IS_ERR(spraid_class)) { + ret = PTR_ERR(spraid_class); + goto destroy_wq; + } + + ret = pci_register_driver(&spraid_driver); + if (ret < 0) + goto destroy_class; + + return 0; + +destroy_class: + class_destroy(spraid_class); +destroy_wq: + destroy_workqueue(spraid_wq); + + return ret; +} + +static void __exit spraid_exit(void) +{ + pci_unregister_driver(&spraid_driver); + class_destroy(spraid_class); + destroy_workqueue(spraid_wq); + ida_destroy(&spraid_instance_ida); +} + +MODULE_AUTHOR("songyl(a)ramaxel.com"); +MODULE_DESCRIPTION("Ramaxel Memory Technology SPraid Driver"); +MODULE_LICENSE("GPL"); +MODULE_VERSION(SPRAID_DRV_VERSION); +module_init(spraid_init); +module_exit(spraid_exit); -- 2.27.0

2 1

[PATCH openEuler-1.0-LTS] USB: gadget: bRequestType is a bitfield, not a enum
by Yang Yingliang 22 Dec '21

22 Dec '21

From: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> mainline inclusion from mainline-v5.16-rc6 commit f08adf5add9a071160c68bb2a61d697f39ab0758 category: bugfix bugzilla: NA CVE: CVE-2021-39685 -------------------------------- Szymon rightly pointed out that the previous check for the endpoint direction in bRequestType was not looking at only the bit involved, but rather the whole value. Normally this is ok, but for some request types, bits other than bit 8 could be set and the check for the endpoint length could not stall correctly. Fix that up by only checking the single bit. Fixes: 153a2d7e3350 ("USB: gadget: detect too-big endpoint 0 requests") Cc: Felipe Balbi <balbi(a)kernel.org> Reported-by: Szymon Heidrich <szymon.heidrich(a)gmail.com> Link: https://lore.kernel.org/r/20211214184621.385828-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/usb/gadget/composite.c | 6 +++--- drivers/usb/gadget/legacy/dbgp.c | 6 +++--- drivers/usb/gadget/legacy/inode.c | 6 +++--- 3 files changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index 3813249387b3d..d39ebf5bdbdd5 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -1570,14 +1570,14 @@ composite_setup(struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl) u8 endp; if (w_length > USB_COMP_EP0_BUFSIZ) { - if (ctrl->bRequestType == USB_DIR_OUT) { - goto done; - } else { + if (ctrl->bRequestType & USB_DIR_IN) { /* Cast away the const, we are going to overwrite on purpose. */ __le16 *temp = (__le16 *)&ctrl->wLength; *temp = cpu_to_le16(USB_COMP_EP0_BUFSIZ); w_length = USB_COMP_EP0_BUFSIZ; + } else { + goto done; } } diff --git a/drivers/usb/gadget/legacy/dbgp.c b/drivers/usb/gadget/legacy/dbgp.c index e567afcb2794c..ffe58d44b2cb1 100644 --- a/drivers/usb/gadget/legacy/dbgp.c +++ b/drivers/usb/gadget/legacy/dbgp.c @@ -346,14 +346,14 @@ static int dbgp_setup(struct usb_gadget *gadget, u16 len = 0; if (length > DBGP_REQ_LEN) { - if (ctrl->bRequestType == USB_DIR_OUT) { - return err; - } else { + if (ctrl->bRequestType & USB_DIR_IN) { /* Cast away the const, we are going to overwrite on purpose. */ __le16 *temp = (__le16 *)&ctrl->wLength; *temp = cpu_to_le16(DBGP_REQ_LEN); length = DBGP_REQ_LEN; + } else { + return err; } } diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c index 83fd1b55d497a..f91d403da3141 100644 --- a/drivers/usb/gadget/legacy/inode.c +++ b/drivers/usb/gadget/legacy/inode.c @@ -1335,14 +1335,14 @@ gadgetfs_setup (struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl) u16 w_length = le16_to_cpu(ctrl->wLength); if (w_length > RBUF_SIZE) { - if (ctrl->bRequestType == USB_DIR_OUT) { - return value; - } else { + if (ctrl->bRequestType & USB_DIR_IN) { /* Cast away the const, we are going to overwrite on purpose. */ __le16 *temp = (__le16 *)&ctrl->wLength; *temp = cpu_to_le16(RBUF_SIZE); w_length = RBUF_SIZE; + } else { + return value; } } -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS 1/2] scsi:spraid: support Ramaxel's spraid driver
by Yang Yingliang 22 Dec '21

22 Dec '21

From: Yanling Song <songyl(a)ramaxel.com> Ramaxel inclusion category: features bugzilla: https://gitee.com/openeuler/kernel/issues/I4NJIB CVE: NA Support Ramaxel's SPRxxx Raid controller Signed-off-by: Yanling Song <songyl(a)ramaxel.com> Reviewed-by: Jiang Yu<yujiang(a)ramaxel.com> Acked-by: Xie XiuQi <xiexiuqi(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/scsi/Kconfig | 1 + drivers/scsi/Makefile | 1 + drivers/scsi/spraid/Kconfig | 13 + drivers/scsi/spraid/Makefile | 7 + drivers/scsi/spraid/spraid.h | 746 ++++++ drivers/scsi/spraid/spraid_main.c | 3875 +++++++++++++++++++++++++++++ 6 files changed, 4643 insertions(+) create mode 100644 drivers/scsi/spraid/Kconfig create mode 100644 drivers/scsi/spraid/Makefile create mode 100644 drivers/scsi/spraid/spraid.h create mode 100644 drivers/scsi/spraid/spraid_main.c diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig index 8450484184e36..63d2aaa228349 100644 --- a/drivers/scsi/Kconfig +++ b/drivers/scsi/Kconfig @@ -522,6 +522,7 @@ source "drivers/scsi/megaraid/Kconfig.megaraid" source "drivers/scsi/mpt3sas/Kconfig" source "drivers/scsi/smartpqi/Kconfig" source "drivers/scsi/ufs/Kconfig" +source "drivers/scsi/spraid/Kconfig" config SCSI_HPTIOP tristate "HighPoint RocketRAID 3xxx/4xxx Controller support" diff --git a/drivers/scsi/Makefile b/drivers/scsi/Makefile index 2973693f6dcc7..4056cf26e09e6 100644 --- a/drivers/scsi/Makefile +++ b/drivers/scsi/Makefile @@ -94,6 +94,7 @@ obj-$(CONFIG_SCSI_ZALON) += zalon7xx.o obj-$(CONFIG_SCSI_DC395x) += dc395x.o obj-$(CONFIG_SCSI_AM53C974) += esp_scsi.o am53c974.o obj-$(CONFIG_CXLFLASH) += cxlflash/ +obj-$(CONFIG_RAMAXEL_SPRAID) += spraid/ obj-$(CONFIG_MEGARAID_LEGACY) += megaraid.o obj-$(CONFIG_MEGARAID_NEWGEN) += megaraid/ obj-$(CONFIG_MEGARAID_SAS) += megaraid/ diff --git a/drivers/scsi/spraid/Kconfig b/drivers/scsi/spraid/Kconfig new file mode 100644 index 0000000000000..bfbba3db8db03 --- /dev/null +++ b/drivers/scsi/spraid/Kconfig @@ -0,0 +1,13 @@ +# +# Ramaxel driver configuration +# + +config RAMAXEL_SPRAID + tristate "Ramaxel spraid Adapter" + depends on PCI && SCSI + select BLK_DEV_BSGLIB + depends on ARM64 || X86_64 + help + This driver supports Ramaxel SPRxxx serial + raid controller, which has PCIE Gen4 interface + with host and supports SAS/SATA Hdd/ssd. diff --git a/drivers/scsi/spraid/Makefile b/drivers/scsi/spraid/Makefile new file mode 100644 index 0000000000000..aadc2ffd37ebd --- /dev/null +++ b/drivers/scsi/spraid/Makefile @@ -0,0 +1,7 @@ +# +# Makefile for the Ramaxel device drivers. +# + +obj-$(CONFIG_RAMAXEL_SPRAID) += spraid.o + +spraid-objs := spraid_main.o \ No newline at end of file diff --git a/drivers/scsi/spraid/spraid.h b/drivers/scsi/spraid/spraid.h new file mode 100644 index 0000000000000..c1e4980e18e5d --- /dev/null +++ b/drivers/scsi/spraid/spraid.h @@ -0,0 +1,746 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2021 Ramaxel Memory Technology, Ltd */ + +#ifndef __SPRAID_H_ +#define __SPRAID_H_ + +#define SPRAID_CAP_MQES(cap) ((cap) & 0xffff) +#define SPRAID_CAP_STRIDE(cap) (((cap) >> 32) & 0xf) +#define SPRAID_CAP_MPSMIN(cap) (((cap) >> 48) & 0xf) +#define SPRAID_CAP_MPSMAX(cap) (((cap) >> 52) & 0xf) +#define SPRAID_CAP_TIMEOUT(cap) (((cap) >> 24) & 0xff) +#define SPRAID_CAP_DMAMASK(cap) (((cap) >> 37) & 0xff) + +#define SPRAID_DEFAULT_MAX_CHANNEL 4 +#define SPRAID_DEFAULT_MAX_ID 240 +#define SPRAID_DEFAULT_MAX_LUN_PER_HOST 8 +#define MAX_SECTORS 2048 + +#define IO_SQE_SIZE sizeof(struct spraid_ioq_command) +#define ADMIN_SQE_SIZE sizeof(struct spraid_admin_command) +#define SQE_SIZE(qid) (((qid) > 0) ? IO_SQE_SIZE : ADMIN_SQE_SIZE) +#define CQ_SIZE(depth) ((depth) * sizeof(struct spraid_completion)) +#define SQ_SIZE(qid, depth) ((depth) * SQE_SIZE(qid)) + +#define SENSE_SIZE(depth) ((depth) * SCSI_SENSE_BUFFERSIZE) + +#define SPRAID_AQ_DEPTH 128 +#define SPRAID_NR_AEN_COMMANDS 16 +#define SPRAID_AQ_BLK_MQ_DEPTH (SPRAID_AQ_DEPTH - SPRAID_NR_AEN_COMMANDS) +#define SPRAID_AQ_MQ_TAG_DEPTH (SPRAID_AQ_BLK_MQ_DEPTH - 1) + +#define SPRAID_ADMIN_QUEUE_NUM 1 +#define SPRAID_PTCMDS_PERQ 1 +#define SPRAID_IO_BLK_MQ_DEPTH (hdev->shost->can_queue) +#define SPRAID_NR_IOQ_PTCMDS (SPRAID_PTCMDS_PERQ * hdev->shost->nr_hw_queues) + +#define FUA_MASK 0x08 +#define SPRAID_MINORS BIT(MINORBITS) + +#define COMMAND_IS_WRITE(cmd) ((cmd)->common.opcode & 1) + +#define SPRAID_IO_IOSQES 7 +#define SPRAID_IO_IOCQES 4 +#define PRP_ENTRY_SIZE 8 + +#define SMALL_POOL_SIZE 256 +#define MAX_SMALL_POOL_NUM 16 +#define MAX_CMD_PER_DEV 64 +#define MAX_CDB_LEN 32 + +#define SPRAID_UP_TO_MULTY4(x) (((x) + 4) & (~0x03)) + +#define CQE_STATUS_SUCCESS (0x0) + +#define PCI_VENDOR_ID_RAMAXEL_LOGIC 0x1E81 + +#define SPRAID_SERVER_DEVICE_HBA_DID 0x2100 +#define SPRAID_SERVER_DEVICE_RAID_DID 0x2200 + +#define IO_6_DEFAULT_TX_LEN 256 + +#define SPRAID_INT_PAGES 2 +#define SPRAID_INT_BYTES(hdev) (SPRAID_INT_PAGES * (hdev)->page_size) + +enum { + SPRAID_REQ_CANCELLED = (1 << 0), + SPRAID_REQ_USERCMD = (1 << 1), +}; + +enum { + SPRAID_SC_SUCCESS = 0x0, + SPRAID_SC_INVALID_OPCODE = 0x1, + SPRAID_SC_INVALID_FIELD = 0x2, + + SPRAID_SC_ABORT_LIMIT = 0x103, + SPRAID_SC_ABORT_MISSING = 0x104, + SPRAID_SC_ASYNC_LIMIT = 0x105, + + SPRAID_SC_DNR = 0x4000, +}; + +enum { + SPRAID_REG_CAP = 0x0000, + SPRAID_REG_CC = 0x0014, + SPRAID_REG_CSTS = 0x001c, + SPRAID_REG_AQA = 0x0024, + SPRAID_REG_ASQ = 0x0028, + SPRAID_REG_ACQ = 0x0030, + SPRAID_REG_DBS = 0x1000, +}; + +enum { + SPRAID_CC_ENABLE = 1 << 0, + SPRAID_CC_CSS_NVM = 0 << 4, + SPRAID_CC_MPS_SHIFT = 7, + SPRAID_CC_AMS_SHIFT = 11, + SPRAID_CC_SHN_SHIFT = 14, + SPRAID_CC_IOSQES_SHIFT = 16, + SPRAID_CC_IOCQES_SHIFT = 20, + SPRAID_CC_AMS_RR = 0 << SPRAID_CC_AMS_SHIFT, + SPRAID_CC_SHN_NONE = 0 << SPRAID_CC_SHN_SHIFT, + SPRAID_CC_IOSQES = SPRAID_IO_IOSQES << SPRAID_CC_IOSQES_SHIFT, + SPRAID_CC_IOCQES = SPRAID_IO_IOCQES << SPRAID_CC_IOCQES_SHIFT, + SPRAID_CC_SHN_NORMAL = 1 << SPRAID_CC_SHN_SHIFT, + SPRAID_CC_SHN_MASK = 3 << SPRAID_CC_SHN_SHIFT, + SPRAID_CSTS_CFS_SHIFT = 1, + SPRAID_CSTS_SHST_SHIFT = 2, + SPRAID_CSTS_PP_SHIFT = 5, + SPRAID_CSTS_RDY = 1 << 0, + SPRAID_CSTS_SHST_CMPLT = 2 << 2, + SPRAID_CSTS_SHST_MASK = 3 << 2, + SPRAID_CSTS_CFS_MASK = 1 << SPRAID_CSTS_CFS_SHIFT, + SPRAID_CSTS_PP_MASK = 1 << SPRAID_CSTS_PP_SHIFT, +}; + +enum { + SPRAID_ADMIN_DELETE_SQ = 0x00, + SPRAID_ADMIN_CREATE_SQ = 0x01, + SPRAID_ADMIN_DELETE_CQ = 0x04, + SPRAID_ADMIN_CREATE_CQ = 0x05, + SPRAID_ADMIN_ABORT_CMD = 0x08, + SPRAID_ADMIN_SET_FEATURES = 0x09, + SPRAID_ADMIN_ASYNC_EVENT = 0x0c, + SPRAID_ADMIN_GET_INFO = 0xc6, + SPRAID_ADMIN_RESET = 0xc8, +}; + +enum { + SPRAID_GET_INFO_CTRL = 0, + SPRAID_GET_INFO_DEV_LIST = 1, +}; + +enum { + SPRAID_RESET_TARGET = 0, + SPRAID_RESET_BUS = 1, +}; + +enum { + SPRAID_AEN_ERROR = 0, + SPRAID_AEN_NOTICE = 2, + SPRAID_AEN_VS = 7, +}; + +enum { + SPRAID_AEN_DEV_CHANGED = 0x00, + SPRAID_AEN_FW_ACT_START = 0x01, + SPRAID_AEN_HOST_PROBING = 0x10, +}; + +enum { + SPRAID_AEN_TIMESYN = 0x00, + SPRAID_AEN_FW_ACT_FINISH = 0x02, + SPRAID_AEN_EVENT_MIN = 0x80, + SPRAID_AEN_EVENT_MAX = 0xff, +}; + +enum { + SPRAID_CMD_WRITE = 0x01, + SPRAID_CMD_READ = 0x02, + + SPRAID_CMD_NONIO_NONE = 0x80, + SPRAID_CMD_NONIO_TODEV = 0x81, + SPRAID_CMD_NONIO_FROMDEV = 0x82, +}; + +enum { + SPRAID_QUEUE_PHYS_CONTIG = (1 << 0), + SPRAID_CQ_IRQ_ENABLED = (1 << 1), + + SPRAID_FEAT_NUM_QUEUES = 0x07, + SPRAID_FEAT_ASYNC_EVENT = 0x0b, + SPRAID_FEAT_TIMESTAMP = 0x0e, +}; + +enum spraid_state { + SPRAID_NEW, + SPRAID_LIVE, + SPRAID_RESETTING, + SPRAID_DELETING, + SPRAID_DEAD, +}; + +enum { + SPRAID_CARD_HBA, + SPRAID_CARD_RAID, +}; + +enum spraid_cmd_type { + SPRAID_CMD_ADM, + SPRAID_CMD_IOPT, +}; + +struct spraid_completion { + __le32 result; + union { + struct { + __u8 sense_len; + __u8 resv[3]; + }; + __le32 result1; + }; + __le16 sq_head; + __le16 sq_id; + __u16 cmd_id; + __le16 status; +}; + +struct spraid_ctrl_info { + __le32 nd; + __le16 max_cmds; + __le16 max_channel; + __le32 max_tgt_id; + __le16 max_lun; + __le16 max_num_sge; + __le16 lun_num_in_boot; + __u8 mdts; + __u8 acl; + __u8 aerl; + __u8 card_type; + __u16 rsvd; + __u32 rtd3e; + __u8 sn[32]; + __u8 fr[16]; + __u8 rsvd1[4020]; +}; + +struct spraid_dev { + struct pci_dev *pdev; + struct device *dev; + struct Scsi_Host *shost; + struct spraid_queue *queues; + struct dma_pool *prp_page_pool; + struct dma_pool *prp_small_pool[MAX_SMALL_POOL_NUM]; + mempool_t *iod_mempool; + void __iomem *bar; + u32 max_qid; + u32 num_vecs; + u32 queue_count; + u32 ioq_depth; + int db_stride; + u32 __iomem *dbs; + struct rw_semaphore devices_rwsem; + int numa_node; + u32 page_size; + u32 ctrl_config; + u32 online_queues; + u64 cap; + int instance; + struct spraid_ctrl_info *ctrl_info; + struct spraid_dev_info *devices; + + struct spraid_cmd *adm_cmds; + struct list_head adm_cmd_list; + spinlock_t adm_cmd_lock; + + struct spraid_cmd *ioq_ptcmds; + struct list_head ioq_pt_list; + spinlock_t ioq_pt_lock; + + struct work_struct scan_work; + struct work_struct timesyn_work; + struct work_struct reset_work; + struct work_struct fw_act_work; + + enum spraid_state state; + spinlock_t state_lock; + + struct request_queue *bsg_queue; +}; + +struct spraid_sgl_desc { + __le64 addr; + __le32 length; + __u8 rsvd[3]; + __u8 type; +}; + +union spraid_data_ptr { + struct { + __le64 prp1; + __le64 prp2; + }; + struct spraid_sgl_desc sgl; +}; + +struct spraid_admin_common_command { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + __le32 cdw2[4]; + union spraid_data_ptr dptr; + __le32 cdw10; + __le32 cdw11; + __le32 cdw12; + __le32 cdw13; + __le32 cdw14; + __le32 cdw15; +}; + +struct spraid_features { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + __u64 rsvd2[2]; + union spraid_data_ptr dptr; + __le32 fid; + __le32 dword11; + __le32 dword12; + __le32 dword13; + __le32 dword14; + __le32 dword15; +}; + +struct spraid_create_cq { + __u8 opcode; + __u8 flags; + __u16 command_id; + __u32 rsvd1[5]; + __le64 prp1; + __u64 rsvd8; + __le16 cqid; + __le16 qsize; + __le16 cq_flags; + __le16 irq_vector; + __u32 rsvd12[4]; +}; + +struct spraid_create_sq { + __u8 opcode; + __u8 flags; + __u16 command_id; + __u32 rsvd1[5]; + __le64 prp1; + __u64 rsvd8; + __le16 sqid; + __le16 qsize; + __le16 sq_flags; + __le16 cqid; + __u32 rsvd12[4]; +}; + +struct spraid_delete_queue { + __u8 opcode; + __u8 flags; + __u16 command_id; + __u32 rsvd1[9]; + __le16 qid; + __u16 rsvd10; + __u32 rsvd11[5]; +}; + +struct spraid_get_info { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + __u32 rsvd2[4]; + union spraid_data_ptr dptr; + __u8 type; + __u8 rsvd10[3]; + __le32 cdw11; + __u32 rsvd12[4]; +}; + +struct spraid_usr_cmd { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + union { + struct { + __le16 subopcode; + __le16 rsvd1; + } info_0; + __le32 cdw2; + }; + union { + struct { + __le16 data_len; + __le16 param_len; + } info_1; + __le32 cdw3; + }; + __u64 metadata; + union spraid_data_ptr dptr; + __le32 cdw10; + __le32 cdw11; + __le32 cdw12; + __le32 cdw13; + __le32 cdw14; + __le32 cdw15; +}; + +enum { + SPRAID_CMD_FLAG_SGL_METABUF = (1 << 6), + SPRAID_CMD_FLAG_SGL_METASEG = (1 << 7), + SPRAID_CMD_FLAG_SGL_ALL = SPRAID_CMD_FLAG_SGL_METABUF | + SPRAID_CMD_FLAG_SGL_METASEG, +}; + +enum spraid_cmd_state { + SPRAID_CMD_IDLE = 0, + SPRAID_CMD_IN_FLIGHT = 1, + SPRAID_CMD_COMPLETE = 2, + SPRAID_CMD_TIMEOUT = 3, + SPRAID_CMD_TMO_COMPLETE = 4, +}; + +struct spraid_abort_cmd { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + __u64 rsvd2[4]; + __le16 sqid; + __le16 cid; + __u32 rsvd11[5]; +}; + +struct spraid_reset_cmd { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + __u64 rsvd2[4]; + __u8 type; + __u8 rsvd10[3]; + __u32 rsvd11[5]; +}; + +struct spraid_admin_command { + union { + struct spraid_admin_common_command common; + struct spraid_features features; + struct spraid_create_cq create_cq; + struct spraid_create_sq create_sq; + struct spraid_delete_queue delete_queue; + struct spraid_get_info get_info; + struct spraid_abort_cmd abort; + struct spraid_reset_cmd reset; + struct spraid_usr_cmd usr_cmd; + }; +}; + +struct spraid_ioq_common_command { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + __le16 sense_len; + __u8 cdb_len; + __u8 rsvd2; + __le32 cdw3[3]; + union spraid_data_ptr dptr; + __le32 cdw10[6]; + __u8 cdb[32]; + __le64 sense_addr; + __le32 cdw26[6]; +}; + +struct spraid_rw_command { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + __le16 sense_len; + __u8 cdb_len; + __u8 rsvd2; + __u32 rsvd3[3]; + union spraid_data_ptr dptr; + __le64 slba; + __le16 nlb; + __le16 control; + __u32 rsvd13[3]; + __u8 cdb[32]; + __le64 sense_addr; + __u32 rsvd26[6]; +}; + +struct spraid_scsi_nonio { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + __le16 sense_len; + __u8 cdb_length; + __u8 rsvd2; + __u32 rsvd3[3]; + union spraid_data_ptr dptr; + __u32 rsvd10[5]; + __le32 buffer_len; + __u8 cdb[32]; + __le64 sense_addr; + __u32 rsvd26[6]; +}; + +struct spraid_ioq_command { + union { + struct spraid_ioq_common_command common; + struct spraid_rw_command rw; + struct spraid_scsi_nonio scsi_nonio; + }; +}; + +struct spraid_passthru_common_cmd { + __u8 opcode; + __u8 flags; + __u16 rsvd0; + __u32 nsid; + union { + struct { + __u16 subopcode; + __u16 rsvd1; + } info_0; + __u32 cdw2; + }; + union { + struct { + __u16 data_len; + __u16 param_len; + } info_1; + __u32 cdw3; + }; + __u64 metadata; + + __u64 addr; + __u64 prp2; + + __u32 cdw10; + __u32 cdw11; + __u32 cdw12; + __u32 cdw13; + __u32 cdw14; + __u32 cdw15; + __u32 timeout_ms; + __u32 result0; + __u32 result1; +}; + +struct spraid_ioq_passthru_cmd { + __u8 opcode; + __u8 flags; + __u16 rsvd0; + __u32 nsid; + union { + struct { + __u16 res_sense_len; + __u8 cdb_len; + __u8 rsvd0; + } info_0; + __u32 cdw2; + }; + union { + struct { + __u16 subopcode; + __u16 rsvd1; + } info_1; + __u32 cdw3; + }; + union { + struct { + __u16 rsvd; + __u16 param_len; + } info_2; + __u32 cdw4; + }; + __u32 cdw5; + __u64 addr; + __u64 prp2; + union { + struct { + __u16 eid; + __u16 sid; + } info_3; + __u32 cdw10; + }; + union { + struct { + __u16 did; + __u8 did_flag; + __u8 rsvd2; + } info_4; + __u32 cdw11; + }; + __u32 cdw12; + __u32 cdw13; + __u32 cdw14; + __u32 data_len; + __u32 cdw16; + __u32 cdw17; + __u32 cdw18; + __u32 cdw19; + __u32 cdw20; + __u32 cdw21; + __u32 cdw22; + __u32 cdw23; + __u64 sense_addr; + __u32 cdw26[4]; + __u32 timeout_ms; + __u32 result0; + __u32 result1; +}; + +struct spraid_bsg_request { + u32 msgcode; + u32 control; + union { + struct spraid_passthru_common_cmd admcmd; + struct spraid_ioq_passthru_cmd ioqcmd; + }; +}; + +enum { + SPRAID_BSG_ADM, + SPRAID_BSG_IOQ, +}; + +struct spraid_cmd { + int qid; + int cid; + u32 result0; + u32 result1; + u16 status; + void *priv; + enum spraid_cmd_state state; + struct completion cmd_done; + struct list_head list; +}; + +struct spraid_queue { + struct spraid_dev *hdev; + spinlock_t sq_lock; + + spinlock_t cq_lock ____cacheline_aligned_in_smp; + + void *sq_cmds; + + struct spraid_completion *cqes; + + dma_addr_t sq_dma_addr; + dma_addr_t cq_dma_addr; + u32 __iomem *q_db; + u8 cq_phase; + u8 sqes; + u16 qid; + u16 sq_tail; + u16 cq_head; + u16 last_cq_head; + u16 q_depth; + s16 cq_vector; + void *sense; + dma_addr_t sense_dma_addr; + struct dma_pool *prp_small_pool; +}; + +struct spraid_iod { + struct spraid_queue *spraidq; + enum spraid_cmd_state state; + int npages; + u32 nsge; + u32 length; + bool use_sgl; + bool sg_drv_mgmt; + dma_addr_t first_dma; + void *sense; + dma_addr_t sense_dma; + struct scatterlist *sg; + struct scatterlist inline_sg[0]; +}; + +#define SPRAID_DEV_INFO_ATTR_BOOT(attr) ((attr) & 0x01) +#define SPRAID_DEV_INFO_ATTR_VD(attr) (((attr) & 0x02) == 0x0) +#define SPRAID_DEV_INFO_ATTR_PT(attr) (((attr) & 0x22) == 0x02) +#define SPRAID_DEV_INFO_ATTR_RAWDISK(attr) ((attr) & 0x20) + +#define SPRAID_DEV_INFO_FLAG_VALID(flag) ((flag) & 0x01) +#define SPRAID_DEV_INFO_FLAG_CHANGE(flag) ((flag) & 0x02) + +#define BGTASK_TYPE_REBUILD 4 +#define USR_CMD_READ 0xc2 +#define USR_CMD_RDLEN 0x1000 +#define USR_CMD_VDINFO 0x704 +#define USR_CMD_BGTASK 0x504 +#define VDINFO_PARAM_LEN 0x04 + +struct spraid_vd_info { + __u8 name[32]; + __le16 id; + __u8 rg_id; + __u8 rg_level; + __u8 sg_num; + __u8 sg_disk_num; + __u8 vd_status; + __u8 vd_type; + __u8 rsvd1[4056]; +}; + +#define MAX_REALTIME_BGTASK_NUM 32 + +struct bgtask_info { + __u8 type; + __u8 progress; + __u8 rate; + __u8 rsvd0; + __le16 vd_id; + __le16 time_left; + __u8 rsvd1[4]; +}; + +struct spraid_bgtask { + __u8 sw; + __u8 task_num; + __u8 rsvd[6]; + struct bgtask_info bgtask[MAX_REALTIME_BGTASK_NUM]; +}; + +struct spraid_dev_info { + __le32 hdid; + __le16 target; + __u8 channel; + __u8 lun; + __u8 attr; + __u8 flag; + __le16 max_io_kb; +}; + +#define MAX_DEV_ENTRY_PER_PAGE_4K 340 +struct spraid_dev_list { + __le32 dev_num; + __u32 rsvd0[3]; + struct spraid_dev_info devices[MAX_DEV_ENTRY_PER_PAGE_4K]; +}; + +struct spraid_sdev_hostdata { + u32 hdid; + u16 max_io_kb; + u8 attr; + u8 flag; + u8 rg_id; + u8 rsvd[3]; +}; + +#endif + diff --git a/drivers/scsi/spraid/spraid_main.c b/drivers/scsi/spraid/spraid_main.c new file mode 100644 index 0000000000000..519b39f44e914 --- /dev/null +++ b/drivers/scsi/spraid/spraid_main.c @@ -0,0 +1,3875 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2021 Ramaxel Memory Technology, Ltd */ + +/* Ramaxel Raid SPXXX Series Linux Driver */ + +#define pr_fmt(fmt) "spraid: " fmt + +#include <linux/sched/signal.h> +#include <linux/version.h> +#include <linux/pci.h> +#include <linux/aer.h> +#include <linux/module.h> +#include <linux/ioport.h> +#include <linux/device.h> +#include <linux/delay.h> +#include <linux/interrupt.h> +#include <linux/cdev.h> +#include <linux/sysfs.h> +#include <linux/gfp.h> +#include <linux/types.h> +#include <linux/ratelimit.h> +#include <linux/once.h> +#include <linux/debugfs.h> +#include <linux/io-64-nonatomic-lo-hi.h> +#include <linux/blkdev.h> +#include <linux/bsg-lib.h> +#include <asm/unaligned.h> +#include <linux/sort.h> +#include <target/target_core_backend.h> + +#include <scsi/scsi.h> +#include <scsi/scsi_cmnd.h> +#include <scsi/scsi_device.h> +#include <scsi/scsi_host.h> +#include <scsi/scsi_transport.h> +#include <scsi/scsi_dbg.h> + + +#include "spraid.h" + +static u32 admin_tmout = 60; +module_param(admin_tmout, uint, 0644); +MODULE_PARM_DESC(admin_tmout, "admin commands timeout (seconds)"); + +static u32 scmd_tmout_nonpt = 180; +module_param(scmd_tmout_nonpt, uint, 0644); +MODULE_PARM_DESC(scmd_tmout_nonpt, + "scsi commands timeout for rawdisk&raid(seconds)"); + +static int ioq_depth_set(const char *val, const struct kernel_param *kp); +static const struct kernel_param_ops ioq_depth_ops = { + .set = ioq_depth_set, + .get = param_get_uint, +}; + +static u32 io_queue_depth = 1024; +module_param_cb(io_queue_depth, &ioq_depth_ops, &io_queue_depth, 0644); +MODULE_PARM_DESC(io_queue_depth, "set io queue depth, should >= 2"); + +static int log_debug_switch_set(const char *val, const struct kernel_param *kp) +{ + u8 n = 0; + int ret; + + ret = kstrtou8(val, 10, &n); + if (ret != 0) + return -EINVAL; + + return param_set_byte(val, kp); +} + +static const struct kernel_param_ops log_debug_switch_ops = { + .set = log_debug_switch_set, + .get = param_get_byte, +}; + +static unsigned char log_debug_switch; +module_param_cb(log_debug_switch, &log_debug_switch_ops, + &log_debug_switch, 0644); +MODULE_PARM_DESC(log_debug_switch, + "set log state, default non-zero for switch on"); + +static int small_pool_num_set(const char *val, const struct kernel_param *kp) +{ + u8 n = 0; + int ret; + + ret = kstrtou8(val, 10, &n); + if (ret != 0) + return -EINVAL; + if (n > MAX_SMALL_POOL_NUM) + n = MAX_SMALL_POOL_NUM; + if (n < 1) + n = 1; + *((u8 *)kp->arg) = n; + + return 0; +} + +static const struct kernel_param_ops small_pool_num_ops = { + .set = small_pool_num_set, + .get = param_get_byte, +}; + +/* It was found that the spindlock of a single pool conflicts + * a lot with multiple CPUs.So multiple pools are introduced + * to reduce the conflictions. + */ +static unsigned char small_pool_num = 4; +module_param_cb(small_pool_num, &small_pool_num_ops, &small_pool_num, 0644); +MODULE_PARM_DESC(small_pool_num, "set prp small pool num, default 4, MAX 16"); + +static void spraid_free_queue(struct spraid_queue *spraidq); +static void spraid_handle_aen_notice(struct spraid_dev *hdev, u32 result); +static void spraid_handle_aen_vs(struct spraid_dev *hdev, + u32 result, u32 result1); + +static DEFINE_IDA(spraid_instance_ida); + +static struct class *spraid_class; + +#define SPRAID_CAP_TIMEOUT_UNIT_MS (HZ / 2) + +static struct workqueue_struct *spraid_wq; + +#define dev_log_dbg(dev, fmt, ...) do { \ + if (unlikely(log_debug_switch)) \ + dev_info(dev, "[%s] [%d] " fmt, \ + __func__, __LINE__, ##__VA_ARGS__); \ +} while (0) + +#define SPRAID_DRV_VERSION "1.0.0.0" + +#define ADMIN_TIMEOUT (admin_tmout * HZ) +#define ADMIN_ERR_TIMEOUT 32757 + +#define SPRAID_WAIT_ABNL_CMD_TIMEOUT (3 * 2) + +#define SPRAID_DMA_MSK_BIT_MAX 64 + +enum FW_STAT_CODE { + FW_STAT_OK = 0, + FW_STAT_NEED_CHECK, + FW_STAT_ERROR, + FW_STAT_EP_PCIE_ERROR, + FW_STAT_NAC_DMA_ERROR, + FW_STAT_ABORTED, + FW_STAT_NEED_RETRY +}; + +static const char * const raid_levels[] = {"0", "1", "5", "6", "10", "50", "60", + "NA"}; + +static const char * const raid_states[] = { + "NA", "NORMAL", "FAULT", "DEGRADE", "NOT_FORMATTED", + "FORMATTING", "SANITIZING", "INITIALIZING", "INITIALIZE_FAIL", + "DELETING", "DELETE_FAIL", "WRITE_PROTECT" +}; + +static int ioq_depth_set(const char *val, const struct kernel_param *kp) +{ + int n = 0; + int ret; + + ret = kstrtoint(val, 10, &n); + if (ret != 0 || n < 2) + return -EINVAL; + + return param_set_int(val, kp); +} + +static int spraid_remap_bar(struct spraid_dev *hdev, u32 size) +{ + struct pci_dev *pdev = hdev->pdev; + + if (size > pci_resource_len(pdev, 0)) { + dev_err(hdev->dev, "Input size[%u] exceed bar0 length[%llu]\n", + size, pci_resource_len(pdev, 0)); + return -ENOMEM; + } + + if (hdev->bar) + iounmap(hdev->bar); + + hdev->bar = ioremap(pci_resource_start(pdev, 0), size); + if (!hdev->bar) { + dev_err(hdev->dev, "ioremap for bar0 failed\n"); + return -ENOMEM; + } + hdev->dbs = hdev->bar + SPRAID_REG_DBS; + + return 0; +} + +static int spraid_dev_map(struct spraid_dev *hdev) +{ + struct pci_dev *pdev = hdev->pdev; + int ret; + + ret = pci_request_mem_regions(pdev, "spraid"); + if (ret) { + dev_err(hdev->dev, "fail to request memory regions\n"); + return ret; + } + + ret = spraid_remap_bar(hdev, SPRAID_REG_DBS + 4096); + if (ret) { + pci_release_mem_regions(pdev); + return ret; + } + + return 0; +} + +static void spraid_dev_unmap(struct spraid_dev *hdev) +{ + struct pci_dev *pdev = hdev->pdev; + + if (hdev->bar) { + iounmap(hdev->bar); + hdev->bar = NULL; + } + pci_release_mem_regions(pdev); +} + +static int spraid_pci_enable(struct spraid_dev *hdev) +{ + struct pci_dev *pdev = hdev->pdev; + int ret = -ENOMEM; + u64 maskbit = SPRAID_DMA_MSK_BIT_MAX; + + if (pci_enable_device_mem(pdev)) { + dev_err(hdev->dev, + "Enable pci device memory resources failed\n"); + return ret; + } + pci_set_master(pdev); + + if (readl(hdev->bar + SPRAID_REG_CSTS) == U32_MAX) { + ret = -ENODEV; + dev_err(hdev->dev, "Read csts register failed\n"); + goto disable; + } + + ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES); + if (ret < 0) { + dev_err(hdev->dev, + "Allocate one IRQ for setup admin channel failed\n"); + goto disable; + } + + hdev->cap = lo_hi_readq(hdev->bar + SPRAID_REG_CAP); + hdev->ioq_depth = min_t(u32, SPRAID_CAP_MQES(hdev->cap) + 1, + io_queue_depth); + hdev->db_stride = 1 << SPRAID_CAP_STRIDE(hdev->cap); + + maskbit = SPRAID_CAP_DMAMASK(hdev->cap); + if (maskbit < 32 || maskbit > SPRAID_DMA_MSK_BIT_MAX) { + dev_err(hdev->dev, + "err, dma mask invalid[%llu], set to default\n", + maskbit); + maskbit = SPRAID_DMA_MSK_BIT_MAX; + } + if (dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(maskbit))) { + dev_err(hdev->dev, "set dma mask and coherent failed\n"); + goto disable; + } + + dev_info(hdev->dev, "set dma mask[%llu] success\n", maskbit); + + pci_enable_pcie_error_reporting(pdev); + pci_save_state(pdev); + + return 0; + +disable: + pci_disable_device(pdev); + return ret; +} + +static int spraid_npages_prp(u32 size, struct spraid_dev *hdev) +{ + u32 nprps = DIV_ROUND_UP(size + hdev->page_size, hdev->page_size); + + return DIV_ROUND_UP(PRP_ENTRY_SIZE * nprps, PAGE_SIZE - PRP_ENTRY_SIZE); +} + +static int spraid_npages_sgl(u32 nseg) +{ + return DIV_ROUND_UP(nseg * sizeof(struct spraid_sgl_desc), PAGE_SIZE); +} + +static void **spraid_iod_list(struct spraid_iod *iod) +{ + return (void **)(iod->inline_sg + (iod->sg_drv_mgmt ? iod->nsge : 0)); +} + +static u32 spraid_iod_ext_size(struct spraid_dev *hdev, u32 size, u32 nsge, + bool sg_drv_mgmt, bool use_sgl) +{ + size_t alloc_size, sg_size; + + if (use_sgl) + alloc_size = sizeof(__le64 *) * spraid_npages_sgl(nsge); + else + alloc_size = sizeof(__le64 *) * spraid_npages_prp(size, hdev); + + sg_size = sg_drv_mgmt ? (sizeof(struct scatterlist) * nsge) : 0; + return sg_size + alloc_size; +} + +static u32 spraid_cmd_size(struct spraid_dev *hdev, + bool sg_drv_mgmt, bool use_sgl) +{ + u32 alloc_size = spraid_iod_ext_size(hdev, SPRAID_INT_BYTES(hdev), + SPRAID_INT_PAGES, sg_drv_mgmt, use_sgl); + + dev_info(hdev->dev, "sg_drv_mgmt: %s, use_sgl: %s, iod size: %lu;" + " alloc_size: %u\n", sg_drv_mgmt ? "true" : "false", + use_sgl ? "true" : "false", + sizeof(struct spraid_iod), alloc_size); + + return sizeof(struct spraid_iod) + alloc_size; +} + +static int spraid_setup_prps(struct spraid_dev *hdev, struct spraid_iod *iod) +{ + struct scatterlist *sg = iod->sg; + u64 dma_addr = sg_dma_address(sg); + int dma_len = sg_dma_len(sg); + __le64 *prp_list, *old_prp_list; + u32 page_size = hdev->page_size; + int offset = dma_addr & (page_size - 1); + void **list = spraid_iod_list(iod); + int length = iod->length; + struct dma_pool *pool; + dma_addr_t prp_dma; + int nprps, i; + + length -= (page_size - offset); + if (length <= 0) { + iod->first_dma = 0; + return 0; + } + + dma_len -= (page_size - offset); + if (dma_len) { + dma_addr += (page_size - offset); + } else { + sg = sg_next(sg); + dma_addr = sg_dma_address(sg); + dma_len = sg_dma_len(sg); + } + + if (length <= page_size) { + iod->first_dma = dma_addr; + return 0; + } + + nprps = DIV_ROUND_UP(length, page_size); + if (nprps <= (SMALL_POOL_SIZE / PRP_ENTRY_SIZE)) { + pool = iod->spraidq->prp_small_pool; + iod->npages = 0; + } else { + pool = hdev->prp_page_pool; + iod->npages = 1; + } + + prp_list = dma_pool_alloc(pool, GFP_ATOMIC, &prp_dma); + if (!prp_list) { + dev_err_ratelimited(hdev->dev, + "Allocate first prp_list memory failed\n"); + iod->first_dma = dma_addr; + iod->npages = -1; + return -ENOMEM; + } + list[0] = prp_list; + iod->first_dma = prp_dma; + i = 0; + for (;;) { + if (i == page_size / PRP_ENTRY_SIZE) { + old_prp_list = prp_list; + + prp_list = dma_pool_alloc(pool, GFP_ATOMIC, &prp_dma); + if (!prp_list) { + dev_err_ratelimited(hdev->dev, "Allocate %dth;" + " prp_list memory failed\n", + iod->npages + 1); + return -ENOMEM; + } + list[iod->npages++] = prp_list; + prp_list[0] = old_prp_list[i - 1]; + old_prp_list[i - 1] = cpu_to_le64(prp_dma); + i = 1; + } + prp_list[i++] = cpu_to_le64(dma_addr); + dma_len -= page_size; + dma_addr += page_size; + length -= page_size; + if (length <= 0) + break; + if (dma_len > 0) + continue; + if (unlikely(dma_len < 0)) + goto bad_sgl; + sg = sg_next(sg); + dma_addr = sg_dma_address(sg); + dma_len = sg_dma_len(sg); + } + + return 0; + +bad_sgl: + dev_err(hdev->dev, + "Setup prps, invalid SGL for payload: %d nents: %d\n", + iod->length, iod->nsge); + return -EIO; +} + +#define SGES_PER_PAGE (PAGE_SIZE / sizeof(struct spraid_sgl_desc)) + +static void spraid_submit_cmd(struct spraid_queue *spraidq, const void *cmd) +{ + u32 sqes = SQE_SIZE(spraidq->qid); + unsigned long flags; + struct spraid_admin_common_command *acd = + (struct spraid_admin_common_command *)cmd; + + spin_lock_irqsave(&spraidq->sq_lock, flags); + memcpy((spraidq->sq_cmds + sqes * spraidq->sq_tail), cmd, sqes); + if (++spraidq->sq_tail == spraidq->q_depth) + spraidq->sq_tail = 0; + + writel(spraidq->sq_tail, spraidq->q_db); + spin_unlock_irqrestore(&spraidq->sq_lock, flags); + + dev_log_dbg(spraidq->hdev->dev, + "cid[%d] qid[%d], opcode[0x%x], flags[0x%x], hdid[%u]\n", + acd->command_id, spraidq->qid, acd->opcode, + acd->flags, le32_to_cpu(acd->hdid)); +} + +static u32 spraid_mod64(u64 dividend, u32 divisor) +{ + u64 d; + u32 remainder; + + if (!divisor) + pr_err("DIVISOR is zero, in div fn\n"); + + d = dividend; + remainder = do_div(d, divisor); + return remainder; +} + +static inline bool spraid_is_rw_scmd(struct scsi_cmnd *scmd) +{ + switch (scmd->cmnd[0]) { + case READ_6: + case READ_10: + case READ_12: + case READ_16: + case READ_32: + case WRITE_6: + case WRITE_10: + case WRITE_12: + case WRITE_16: + case WRITE_32: + return true; + default: + return false; + } +} + +static bool spraid_is_prp(struct spraid_dev *hdev, + struct scsi_cmnd *scmd, u32 nsge) +{ + struct scatterlist *sg = scsi_sglist(scmd); + u32 page_size = hdev->page_size; + bool is_prp = true; + int i = 0; + + scsi_for_each_sg(scmd, sg, nsge, i) { + if (i != 0 && i != nsge - 1) { + if (spraid_mod64(sg_dma_len(sg), page_size) || + spraid_mod64(sg_dma_address(sg), page_size)) { + is_prp = false; + break; + } + } + + if (nsge > 1 && i == 0) { + if ((spraid_mod64((sg_dma_address(sg) + sg_dma_len(sg)), + page_size))) { + is_prp = false; + break; + } + } + + if (nsge > 1 && i == (nsge - 1)) { + if (spraid_mod64(sg_dma_address(sg), page_size)) { + is_prp = false; + break; + } + } + } + + return is_prp; +} + +enum { + SPRAID_SGL_FMT_DATA_DESC = 0x00, + SPRAID_SGL_FMT_SEG_DESC = 0x02, + SPRAID_SGL_FMT_LAST_SEG_DESC = 0x03, + SPRAID_KEY_SGL_FMT_DATA_DESC = 0x04, + SPRAID_TRANSPORT_SGL_DATA_DESC = 0x05 +}; + +static void spraid_sgl_set_data(struct spraid_sgl_desc *sge, + struct scatterlist *sg) +{ + sge->addr = cpu_to_le64(sg_dma_address(sg)); + sge->length = cpu_to_le32(sg_dma_len(sg)); + sge->type = SPRAID_SGL_FMT_DATA_DESC << 4; +} + +static void spraid_sgl_set_seg(struct spraid_sgl_desc *sge, + dma_addr_t dma_addr, int entries) +{ + sge->addr = cpu_to_le64(dma_addr); + if (entries <= SGES_PER_PAGE) { + sge->length = cpu_to_le32(entries * sizeof(*sge)); + sge->type = SPRAID_SGL_FMT_LAST_SEG_DESC << 4; + } else { + sge->length = cpu_to_le32(PAGE_SIZE); + sge->type = SPRAID_SGL_FMT_SEG_DESC << 4; + } +} + +static int spraid_setup_ioq_cmd_sgl(struct spraid_dev *hdev, + struct scsi_cmnd *scmd, + struct spraid_ioq_command *ioq_cmd, + struct spraid_iod *iod) +{ + struct spraid_sgl_desc *sg_list, *link, *old_sg_list; + struct scatterlist *sg = scsi_sglist(scmd); + void **list = spraid_iod_list(iod); + struct dma_pool *pool; + int nsge = iod->nsge; + dma_addr_t sgl_dma; + int i = 0; + + ioq_cmd->common.flags |= SPRAID_CMD_FLAG_SGL_METABUF; + + if (nsge == 1) { + spraid_sgl_set_data(&ioq_cmd->common.dptr.sgl, sg); + return 0; + } + + if (nsge <= (SMALL_POOL_SIZE / sizeof(struct spraid_sgl_desc))) { + pool = iod->spraidq->prp_small_pool; + iod->npages = 0; + } else { + pool = hdev->prp_page_pool; + iod->npages = 1; + } + + sg_list = dma_pool_alloc(pool, GFP_ATOMIC, &sgl_dma); + if (!sg_list) { + dev_err_ratelimited(hdev->dev, + "Allocate first sgl_list failed\n"); + iod->npages = -1; + return -ENOMEM; + } + + list[0] = sg_list; + iod->first_dma = sgl_dma; + spraid_sgl_set_seg(&ioq_cmd->common.dptr.sgl, sgl_dma, nsge); + do { + if (i == SGES_PER_PAGE) { + old_sg_list = sg_list; + link = &old_sg_list[SGES_PER_PAGE - 1]; + + sg_list = dma_pool_alloc(pool, GFP_ATOMIC, &sgl_dma); + if (!sg_list) { + dev_err_ratelimited(hdev->dev, + "Allocate %dth sgl_list;" + " failed\n", + iod->npages + 1); + return -ENOMEM; + } + list[iod->npages++] = sg_list; + + i = 0; + memcpy(&sg_list[i++], link, sizeof(*link)); + spraid_sgl_set_seg(link, sgl_dma, nsge); + } + + spraid_sgl_set_data(&sg_list[i++], sg); + sg = sg_next(sg); + } while (--nsge > 0); + + return 0; +} + +#define SPRAID_RW_FUA BIT(14) + +static void spraid_setup_rw_cmd(struct spraid_dev *hdev, + struct spraid_rw_command *rw, + struct scsi_cmnd *scmd) +{ + u32 start_lba_lo, start_lba_hi; + u32 datalength = 0; + u16 control = 0; + + start_lba_lo = 0; + start_lba_hi = 0; + + if (scmd->sc_data_direction == DMA_TO_DEVICE) { + rw->opcode = SPRAID_CMD_WRITE; + } else if (scmd->sc_data_direction == DMA_FROM_DEVICE) { + rw->opcode = SPRAID_CMD_READ; + } else { + dev_err(hdev->dev, + "Invalid IO for unsupported data direction: %d\n", + scmd->sc_data_direction); + WARN_ON(1); + } + + /* 6-byte READ(0x08) or WRITE(0x0A) cdb */ + if (scmd->cmd_len == 6) { + datalength = (u32)(scmd->cmnd[4] == 0 ? + IO_6_DEFAULT_TX_LEN : scmd->cmnd[4]); + start_lba_lo = (u32)get_unaligned_be24(&scmd->cmnd[1]); + + start_lba_lo &= 0x1FFFFF; + } + + /* 10-byte READ(0x28) or WRITE(0x2A) cdb */ + else if (scmd->cmd_len == 10) { + datalength = (u32)get_unaligned_be16(&scmd->cmnd[7]); + start_lba_lo = get_unaligned_be32(&scmd->cmnd[2]); + + if (scmd->cmnd[1] & FUA_MASK) + control |= SPRAID_RW_FUA; + } + + /* 12-byte READ(0xA8) or WRITE(0xAA) cdb */ + else if (scmd->cmd_len == 12) { + datalength = get_unaligned_be32(&scmd->cmnd[6]); + start_lba_lo = get_unaligned_be32(&scmd->cmnd[2]); + + if (scmd->cmnd[1] & FUA_MASK) + control |= SPRAID_RW_FUA; + } + /* 16-byte READ(0x88) or WRITE(0x8A) cdb */ + else if (scmd->cmd_len == 16) { + datalength = get_unaligned_be32(&scmd->cmnd[10]); + start_lba_lo = get_unaligned_be32(&scmd->cmnd[6]); + start_lba_hi = get_unaligned_be32(&scmd->cmnd[2]); + + if (scmd->cmnd[1] & FUA_MASK) + control |= SPRAID_RW_FUA; + } + /* 32-byte READ(0x88) or WRITE(0x8A) cdb */ + else if (scmd->cmd_len == 32) { + datalength = get_unaligned_be32(&scmd->cmnd[28]); + start_lba_lo = get_unaligned_be32(&scmd->cmnd[16]); + start_lba_hi = get_unaligned_be32(&scmd->cmnd[12]); + + if (scmd->cmnd[10] & FUA_MASK) + control |= SPRAID_RW_FUA; + } + + if (unlikely(datalength > U16_MAX || datalength == 0)) { + dev_err(hdev->dev, + "Invalid IO for illegal transfer data length: %u\n", + datalength); + WARN_ON(1); + } + + rw->slba = cpu_to_le64(((u64)start_lba_hi << 32) | start_lba_lo); + /* 0base for nlb */ + rw->nlb = cpu_to_le16((u16)(datalength - 1)); + rw->control = cpu_to_le16(control); +} + +static void spraid_setup_nonio_cmd(struct spraid_dev *hdev, + struct spraid_scsi_nonio *scsi_nonio, + struct scsi_cmnd *scmd) +{ + scsi_nonio->buffer_len = cpu_to_le32(scsi_bufflen(scmd)); + + switch (scmd->sc_data_direction) { + case DMA_NONE: + scsi_nonio->opcode = SPRAID_CMD_NONIO_NONE; + break; + case DMA_TO_DEVICE: + scsi_nonio->opcode = SPRAID_CMD_NONIO_TODEV; + break; + case DMA_FROM_DEVICE: + scsi_nonio->opcode = SPRAID_CMD_NONIO_FROMDEV; + break; + default: + dev_err(hdev->dev, + "Invalid IO for unsupported data direction: %d\n", + scmd->sc_data_direction); + WARN_ON(1); + } +} + +static void spraid_setup_ioq_cmd(struct spraid_dev *hdev, + struct spraid_ioq_command *ioq_cmd, + struct scsi_cmnd *scmd) +{ + memcpy(ioq_cmd->common.cdb, scmd->cmnd, scmd->cmd_len); + ioq_cmd->common.cdb_len = scmd->cmd_len; + + if (spraid_is_rw_scmd(scmd)) + spraid_setup_rw_cmd(hdev, &ioq_cmd->rw, scmd); + else + spraid_setup_nonio_cmd(hdev, &ioq_cmd->scsi_nonio, scmd); +} + +static int spraid_init_iod(struct spraid_dev *hdev, struct spraid_iod *iod, + struct spraid_ioq_command *ioq_cmd, + struct scsi_cmnd *scmd) +{ + if (unlikely(!iod->sense)) { + dev_err(hdev->dev, "Allocate sense data buffer failed\n"); + return -ENOMEM; + } + ioq_cmd->common.sense_addr = cpu_to_le64(iod->sense_dma); + ioq_cmd->common.sense_len = cpu_to_le16(SCSI_SENSE_BUFFERSIZE); + + iod->nsge = 0; + iod->npages = -1; + iod->use_sgl = 0; + iod->sg_drv_mgmt = false; + WRITE_ONCE(iod->state, SPRAID_CMD_IDLE); + + return 0; +} + +static void spraid_free_iod_res(struct spraid_dev *hdev, struct spraid_iod *iod) +{ + const int last_prp = hdev->page_size / sizeof(__le64) - 1; + dma_addr_t dma_addr, next_dma_addr; + struct spraid_sgl_desc *sg_list; + __le64 *prp_list; + void *addr; + int i; + + dma_addr = iod->first_dma; + if (iod->npages == 0) + dma_pool_free(iod->spraidq->prp_small_pool, + spraid_iod_list(iod)[0], dma_addr); + + for (i = 0; i < iod->npages; i++) { + addr = spraid_iod_list(iod)[i]; + + if (iod->use_sgl) { + sg_list = addr; + next_dma_addr = + le64_to_cpu((sg_list[SGES_PER_PAGE - 1]).addr); + } else { + prp_list = addr; + next_dma_addr = le64_to_cpu(prp_list[last_prp]); + } + + dma_pool_free(hdev->prp_page_pool, addr, dma_addr); + dma_addr = next_dma_addr; + } + + if (iod->sg_drv_mgmt && iod->sg != iod->inline_sg) { + iod->sg_drv_mgmt = false; + mempool_free(iod->sg, hdev->iod_mempool); + } + + iod->sense = NULL; + iod->npages = -1; +} + +static int spraid_io_map_data(struct spraid_dev *hdev, struct spraid_iod *iod, + struct scsi_cmnd *scmd, + struct spraid_ioq_command *ioq_cmd) +{ + int ret; + + iod->nsge = scsi_dma_map(scmd); + + /* No data to DMA, it may be scsi no-rw command */ + if (unlikely(iod->nsge == 0)) + return 0; + + iod->length = scsi_bufflen(scmd); + iod->sg = scsi_sglist(scmd); + iod->use_sgl = !spraid_is_prp(hdev, scmd, iod->nsge); + + if (iod->use_sgl) { + ret = spraid_setup_ioq_cmd_sgl(hdev, scmd, ioq_cmd, iod); + } else { + ret = spraid_setup_prps(hdev, iod); + ioq_cmd->common.dptr.prp1 = + cpu_to_le64(sg_dma_address(iod->sg)); + ioq_cmd->common.dptr.prp2 = cpu_to_le64(iod->first_dma); + } + + if (ret) + scsi_dma_unmap(scmd); + + return ret; +} + +static void spraid_map_status(struct spraid_iod *iod, struct scsi_cmnd *scmd, + struct spraid_completion *cqe) +{ + scsi_set_resid(scmd, 0); + + switch ((le16_to_cpu(cqe->status) >> 1) & 0x7f) { + case FW_STAT_OK: + set_host_byte(scmd, DID_OK); + break; + case FW_STAT_NEED_CHECK: + set_host_byte(scmd, DID_OK); + scmd->result |= le16_to_cpu(cqe->status) >> 8; + if (scmd->result & SAM_STAT_CHECK_CONDITION) { + memset(scmd->sense_buffer, 0, SCSI_SENSE_BUFFERSIZE); + memcpy(scmd->sense_buffer, iod->sense, + SCSI_SENSE_BUFFERSIZE); + scmd->result = + (scmd->result & 0x00ffffff) | (DRIVER_SENSE << 24); + } + break; + case FW_STAT_ABORTED: + set_host_byte(scmd, DID_ABORT); + break; + case FW_STAT_NEED_RETRY: + set_host_byte(scmd, DID_REQUEUE); + break; + default: + set_host_byte(scmd, DID_BAD_TARGET); + break; + } +} + +static inline void spraid_get_tag_from_scmd(struct scsi_cmnd *scmd, + u16 *qid, u16 *cid) +{ + u32 tag = blk_mq_unique_tag(scmd->request); + + *qid = blk_mq_unique_tag_to_hwq(tag) + 1; + *cid = blk_mq_unique_tag_to_tag(tag); +} + +static int spraid_queue_command(struct Scsi_Host *shost, struct scsi_cmnd *scmd) +{ + struct spraid_iod *iod = scsi_cmd_priv(scmd); + struct spraid_dev *hdev = shost_priv(shost); + struct scsi_device *sdev = scmd->device; + struct spraid_sdev_hostdata *hostdata; + struct spraid_ioq_command ioq_cmd; + struct spraid_queue *ioq; + unsigned long elapsed; + u16 hwq, cid; + int ret; + + if (unlikely(!scmd)) { + dev_err(hdev->dev, "err, scmd is null\n"); + return 0; + } + + if (unlikely(hdev->state != SPRAID_LIVE)) { + set_host_byte(scmd, DID_NO_CONNECT); + scmd->scsi_done(scmd); + return 0; + } + + if (log_debug_switch) + scsi_print_command(scmd); + + spraid_get_tag_from_scmd(scmd, &hwq, &cid); + hostdata = sdev->hostdata; + ioq = &hdev->queues[hwq]; + memset(&ioq_cmd, 0, sizeof(ioq_cmd)); + ioq_cmd.rw.hdid = cpu_to_le32(hostdata->hdid); + ioq_cmd.rw.command_id = cid; + + spraid_setup_ioq_cmd(hdev, &ioq_cmd, scmd); + + ret = cid * SCSI_SENSE_BUFFERSIZE; + iod->sense = ioq->sense + ret; + iod->sense_dma = ioq->sense_dma_addr + ret; + + ret = spraid_init_iod(hdev, iod, &ioq_cmd, scmd); + if (unlikely(ret)) + return SCSI_MLQUEUE_HOST_BUSY; + + iod->spraidq = ioq; + ret = spraid_io_map_data(hdev, iod, scmd, &ioq_cmd); + if (unlikely(ret)) { + dev_err(hdev->dev, "spraid_io_map_data Err.\n"); + set_host_byte(scmd, DID_ERROR); + scmd->scsi_done(scmd); + ret = 0; + goto deinit_iod; + } + + WRITE_ONCE(iod->state, SPRAID_CMD_IN_FLIGHT); + spraid_submit_cmd(ioq, &ioq_cmd); + elapsed = jiffies - scmd->jiffies_at_alloc; + dev_log_dbg(hdev->dev, + "cid[%d] qid[%d] submit IO cost %3ld.%3ld seconds\n", + cid, hwq, elapsed / HZ, elapsed % HZ); + return 0; + +deinit_iod: + spraid_free_iod_res(hdev, iod); + return ret; +} + +static int spraid_match_dev(struct spraid_dev *hdev, u16 idx, + struct scsi_device *sdev) +{ + if (SPRAID_DEV_INFO_FLAG_VALID(hdev->devices[idx].flag)) { + if (sdev->channel == hdev->devices[idx].channel && + sdev->id == le16_to_cpu(hdev->devices[idx].target) && + sdev->lun < hdev->devices[idx].lun) { + dev_info(hdev->dev, + "Match device success, channel;" + "target:lun[%d:%d:%d]\n", + hdev->devices[idx].channel, + hdev->devices[idx].target, + hdev->devices[idx].lun); + return 1; + } + } + + return 0; +} + +static int spraid_slave_alloc(struct scsi_device *sdev) +{ + struct spraid_sdev_hostdata *hostdata; + struct spraid_dev *hdev; + u16 idx; + + hdev = shost_priv(sdev->host); + hostdata = kzalloc(sizeof(*hostdata), GFP_KERNEL); + if (!hostdata) { + dev_err(hdev->dev, "Alloc scsi host data memory failed\n"); + return -ENOMEM; + } + + down_read(&hdev->devices_rwsem); + for (idx = 0; idx < le32_to_cpu(hdev->ctrl_info->nd); idx++) { + if (spraid_match_dev(hdev, idx, sdev)) + goto scan_host; + } + up_read(&hdev->devices_rwsem); + + kfree(hostdata); + return -ENXIO; + +scan_host: + hostdata->hdid = le32_to_cpu(hdev->devices[idx].hdid); + hostdata->max_io_kb = le16_to_cpu(hdev->devices[idx].max_io_kb); + hostdata->attr = hdev->devices[idx].attr; + hostdata->flag = hdev->devices[idx].flag; + hostdata->rg_id = 0xff; + sdev->hostdata = hostdata; + up_read(&hdev->devices_rwsem); + return 0; +} + +static void spraid_slave_destroy(struct scsi_device *sdev) +{ + kfree(sdev->hostdata); + sdev->hostdata = NULL; +} + +static int spraid_slave_configure(struct scsi_device *sdev) +{ + u16 idx; + unsigned int timeout = scmd_tmout_nonpt * HZ; + struct spraid_dev *hdev = shost_priv(sdev->host); + struct spraid_sdev_hostdata *hostdata = sdev->hostdata; + u32 max_sec = sdev->host->max_sectors; + + if (hostdata) { + idx = hostdata->hdid - 1; + if (sdev->channel == hdev->devices[idx].channel && + sdev->id == le16_to_cpu(hdev->devices[idx].target) && + sdev->lun < hdev->devices[idx].lun) { + if (SPRAID_DEV_INFO_ATTR_PT(hdev->devices[idx].attr)) + timeout = 30 * HZ; + else + timeout = scmd_tmout_nonpt * HZ; + max_sec = le16_to_cpu(hdev->devices[idx].max_io_kb) + << 1; + } else { + dev_err(hdev->dev, + "[%s] err, sdev->channel:id:lun[%d:%d:%lld];" + "devices[%d], channel:target:lun[%d:%d:%d]\n", + __func__, sdev->channel, sdev->id, sdev->lun, + idx, hdev->devices[idx].channel, + hdev->devices[idx].target, + hdev->devices[idx].lun); + } + } else { + dev_err(hdev->dev, "[%s] err, sdev->hostdata is null\n", + __func__); + } + + blk_queue_rq_timeout(sdev->request_queue, timeout); + sdev->eh_timeout = timeout; + + if ((max_sec == 0) || (max_sec > sdev->host->max_sectors)) + max_sec = sdev->host->max_sectors; + + dev_info(hdev->dev, + "[%s] sdev->channel:id:lun[%d:%d:%lld];" + " scmd_timeout[%d]s, maxsec[%d]\n", + __func__, sdev->channel, sdev->id, + sdev->lun, timeout / HZ, max_sec); + + return 0; +} + +static void spraid_shost_init(struct spraid_dev *hdev) +{ + struct pci_dev *pdev = hdev->pdev; + u8 domain, bus; + u32 dev_func; + + domain = pci_domain_nr(pdev->bus); + bus = pdev->bus->number; + dev_func = pdev->devfn; + + hdev->shost->nr_hw_queues = hdev->online_queues - 1; + hdev->shost->can_queue = (hdev->ioq_depth - SPRAID_PTCMDS_PERQ); + + hdev->shost->sg_tablesize = le16_to_cpu(hdev->ctrl_info->max_num_sge); + /* 512B per sector */ + hdev->shost->max_sectors = + (1U << ((hdev->ctrl_info->mdts) * 1U) << 12) / 512; + hdev->shost->cmd_per_lun = MAX_CMD_PER_DEV; + hdev->shost->max_channel = + le16_to_cpu(hdev->ctrl_info->max_channel) - 1; + hdev->shost->max_id = le32_to_cpu(hdev->ctrl_info->max_tgt_id); + hdev->shost->max_lun = le16_to_cpu(hdev->ctrl_info->max_lun); + + hdev->shost->this_id = -1; + hdev->shost->unique_id = (domain << 16) | (bus << 8) | dev_func; + hdev->shost->max_cmd_len = MAX_CDB_LEN; + hdev->shost->hostt->cmd_size = max(spraid_cmd_size(hdev, false, true), + spraid_cmd_size(hdev, false, false)); +} + +static inline void spraid_host_deinit(struct spraid_dev *hdev) +{ + ida_free(&spraid_instance_ida, hdev->instance); +} + +static int spraid_alloc_queue(struct spraid_dev *hdev, u16 qid, u16 depth) +{ + struct spraid_queue *spraidq = &hdev->queues[qid]; + int ret = 0; + + if (hdev->queue_count > qid) { + dev_info(hdev->dev, "[%s] warn: queue[%d] is exist\n", + __func__, qid); + return 0; + } + + spraidq->cqes = dma_alloc_coherent(hdev->dev, CQ_SIZE(depth), + &spraidq->cq_dma_addr, + GFP_KERNEL | __GFP_ZERO); + if (!spraidq->cqes) + return -ENOMEM; + + spraidq->sq_cmds = dma_alloc_coherent(hdev->dev, SQ_SIZE(qid, depth), + &spraidq->sq_dma_addr, + GFP_KERNEL); + if (!spraidq->sq_cmds) { + ret = -ENOMEM; + goto free_cqes; + } + + spin_lock_init(&spraidq->sq_lock); + spin_lock_init(&spraidq->cq_lock); + spraidq->hdev = hdev; + spraidq->q_depth = depth; + spraidq->qid = qid; + spraidq->cq_vector = -1; + hdev->queue_count++; + + /* alloc sense buffer */ + spraidq->sense = dma_alloc_coherent(hdev->dev, SENSE_SIZE(depth), + &spraidq->sense_dma_addr, + GFP_KERNEL | __GFP_ZERO); + if (!spraidq->sense) { + ret = -ENOMEM; + goto free_sq_cmds; + } + + return 0; + +free_sq_cmds: + dma_free_coherent(hdev->dev, SQ_SIZE(qid, depth), + (void *)spraidq->sq_cmds, spraidq->sq_dma_addr); +free_cqes: + dma_free_coherent(hdev->dev, CQ_SIZE(depth), (void *)spraidq->cqes, + spraidq->cq_dma_addr); + return ret; +} + +static int spraid_wait_ready(struct spraid_dev *hdev, u64 cap, bool enabled) +{ + unsigned long timeout = + ((SPRAID_CAP_TIMEOUT(cap) + 1) * SPRAID_CAP_TIMEOUT_UNIT_MS) + jiffies; + u32 bit = enabled ? SPRAID_CSTS_RDY : 0; + + while ((readl(hdev->bar + SPRAID_REG_CSTS) & SPRAID_CSTS_RDY) != bit) { + usleep_range(1000, 2000); + if (fatal_signal_pending(current)) + return -EINTR; + + if (time_after(jiffies, timeout)) { + dev_err(hdev->dev, "Device not ready; aborting %s\n", + enabled ? "initialisation" : "reset"); + return -ENODEV; + } + } + return 0; +} + +static int spraid_shutdown_ctrl(struct spraid_dev *hdev) +{ + unsigned long timeout = hdev->ctrl_info->rtd3e + jiffies; + + hdev->ctrl_config &= ~SPRAID_CC_SHN_MASK; + hdev->ctrl_config |= SPRAID_CC_SHN_NORMAL; + writel(hdev->ctrl_config, hdev->bar + SPRAID_REG_CC); + + while ((readl(hdev->bar + SPRAID_REG_CSTS) & SPRAID_CSTS_SHST_MASK) != + SPRAID_CSTS_SHST_CMPLT) { + msleep(100); + if (fatal_signal_pending(current)) + return -EINTR; + if (time_after(jiffies, timeout)) { + dev_err(hdev->dev, + "Device shutdown incomplete; abort shutdown\n"); + return -ENODEV; + } + } + return 0; +} + +static int spraid_disable_ctrl(struct spraid_dev *hdev) +{ + hdev->ctrl_config &= ~SPRAID_CC_SHN_MASK; + hdev->ctrl_config &= ~SPRAID_CC_ENABLE; + writel(hdev->ctrl_config, hdev->bar + SPRAID_REG_CC); + + return spraid_wait_ready(hdev, hdev->cap, false); +} + +static int spraid_enable_ctrl(struct spraid_dev *hdev) +{ + u64 cap = hdev->cap; + u32 dev_page_min = SPRAID_CAP_MPSMIN(cap) + 12; + u32 page_shift = PAGE_SHIFT; + + if (page_shift < dev_page_min) { + dev_err(hdev->dev, + "Minimum device page size[%u], too large for host[%u]\n", + 1U << dev_page_min, 1U << page_shift); + return -ENODEV; + } + + page_shift = min_t(unsigned int, SPRAID_CAP_MPSMAX(cap) + 12, + PAGE_SHIFT); + hdev->page_size = 1U << page_shift; + + hdev->ctrl_config = SPRAID_CC_CSS_NVM; + hdev->ctrl_config |= (page_shift - 12) << SPRAID_CC_MPS_SHIFT; + hdev->ctrl_config |= SPRAID_CC_AMS_RR | SPRAID_CC_SHN_NONE; + hdev->ctrl_config |= SPRAID_CC_IOSQES | SPRAID_CC_IOCQES; + hdev->ctrl_config |= SPRAID_CC_ENABLE; + writel(hdev->ctrl_config, hdev->bar + SPRAID_REG_CC); + + return spraid_wait_ready(hdev, cap, true); +} + +static void spraid_init_queue(struct spraid_queue *spraidq, u16 qid) +{ + struct spraid_dev *hdev = spraidq->hdev; + + memset((void *)spraidq->cqes, 0, CQ_SIZE(spraidq->q_depth)); + + spraidq->sq_tail = 0; + spraidq->cq_head = 0; + spraidq->cq_phase = 1; + spraidq->q_db = &hdev->dbs[qid * 2 * hdev->db_stride]; + spraidq->prp_small_pool = hdev->prp_small_pool[qid % small_pool_num]; + hdev->online_queues++; +} + +static inline bool spraid_cqe_pending(struct spraid_queue *spraidq) +{ + return (le16_to_cpu(spraidq->cqes[spraidq->cq_head].status) & 1) == + spraidq->cq_phase; +} + +static void spraid_sata_report_zone_handle(struct scsi_cmnd *scmd, + struct spraid_iod *iod) +{ + int i = 0; + unsigned int bytes = 0; + struct scatterlist *sg = scsi_sglist(scmd); + + scsi_for_each_sg(scmd, sg, iod->nsge, i) { + unsigned int offset = 0; + + if (bytes == 0) { + char *hdr; + u32 list_length; + u64 max_lba, opt_lba; + u16 same; + + hdr = sg_virt(sg); + + list_length = get_unaligned_le32(&hdr[0]); + same = get_unaligned_le16(&hdr[4]); + max_lba = get_unaligned_le64(&hdr[8]); + opt_lba = get_unaligned_le64(&hdr[16]); + put_unaligned_be32(list_length, &hdr[0]); + hdr[4] = same & 0xf; + put_unaligned_be64(max_lba, &hdr[8]); + put_unaligned_be64(opt_lba, &hdr[16]); + offset += 64; + bytes += 64; + } + while (offset < sg_dma_len(sg)) { + char *rec; + u8 cond, type, non_seq, reset; + u64 size, start, wp; + + rec = sg_virt(sg) + offset; + type = rec[0] & 0xf; + cond = (rec[1] >> 4) & 0xf; + non_seq = (rec[1] & 2); + reset = (rec[1] & 1); + size = get_unaligned_le64(&rec[8]); + start = get_unaligned_le64(&rec[16]); + wp = get_unaligned_le64(&rec[24]); + rec[0] = type; + rec[1] = (cond << 4) | non_seq | reset; + put_unaligned_be64(size, &rec[8]); + put_unaligned_be64(start, &rec[16]); + put_unaligned_be64(wp, &rec[24]); + WARN_ON(offset + 64 > sg_dma_len(sg)); + offset += 64; + bytes += 64; + } + } +} + +static inline void spraid_handle_ata_cmd(struct spraid_dev *hdev, + struct scsi_cmnd *scmd, + struct spraid_iod *iod) +{ + if (hdev->ctrl_info->card_type != SPRAID_CARD_HBA) + return; + + switch (scmd->cmnd[0]) { + case ZBC_IN: + dev_info(hdev->dev, "[%s] process report zone\n", __func__); + spraid_sata_report_zone_handle(scmd, iod); + break; + default: + break; + } +} + +static void spraid_complete_ioq_cmnd(struct spraid_queue *ioq, + struct spraid_completion *cqe) +{ + struct spraid_dev *hdev = ioq->hdev; + struct blk_mq_tags *tags; + struct scsi_cmnd *scmd; + struct spraid_iod *iod; + struct request *req; + unsigned long elapsed; + + tags = hdev->shost->tag_set.tags[ioq->qid - 1]; + req = blk_mq_tag_to_rq(tags, cqe->cmd_id); + if (unlikely(!req || !blk_mq_request_started(req))) { + dev_warn(hdev->dev, "Invalid id %d completed on queue %d\n", + cqe->cmd_id, ioq->qid); + return; + } + + scmd = blk_mq_rq_to_pdu(req); + iod = scsi_cmd_priv(scmd); + + elapsed = jiffies - scmd->jiffies_at_alloc; + dev_log_dbg(hdev->dev, + "cid[%d] qid[%d] finish IO cost %3ld.%3ld seconds\n", + cqe->cmd_id, ioq->qid, elapsed / HZ, elapsed % HZ); + + if (cmpxchg(&iod->state, SPRAID_CMD_IN_FLIGHT, SPRAID_CMD_COMPLETE) != + SPRAID_CMD_IN_FLIGHT) { + dev_warn(hdev->dev, + "cid[%d] qid[%d] enters abnormal handler;" + " cost %3ld.%3ld seconds\n", + cqe->cmd_id, ioq->qid, elapsed / HZ, elapsed % HZ); + WRITE_ONCE(iod->state, SPRAID_CMD_TMO_COMPLETE); + + if (iod->nsge) { + iod->nsge = 0; + scsi_dma_unmap(scmd); + } + spraid_free_iod_res(hdev, iod); + + return; + } + + spraid_handle_ata_cmd(hdev, scmd, iod); + + spraid_map_status(iod, scmd, cqe); + if (iod->nsge) { + iod->nsge = 0; + scsi_dma_unmap(scmd); + } + spraid_free_iod_res(hdev, iod); + scmd->scsi_done(scmd); +} + +static void spraid_complete_adminq_cmnd(struct spraid_queue *adminq, + struct spraid_completion *cqe) +{ + struct spraid_dev *hdev = adminq->hdev; + struct spraid_cmd *adm_cmd; + + adm_cmd = hdev->adm_cmds + cqe->cmd_id; + if (unlikely(adm_cmd->state == SPRAID_CMD_IDLE)) { + dev_warn(adminq->hdev->dev, + "Invalid id %d completed on queue %d\n", + cqe->cmd_id, le16_to_cpu(cqe->sq_id)); + return; + } + + adm_cmd->status = le16_to_cpu(cqe->status) >> 1; + adm_cmd->result0 = le32_to_cpu(cqe->result); + adm_cmd->result1 = le32_to_cpu(cqe->result1); + + complete(&adm_cmd->cmd_done); +} + +static void spraid_send_aen(struct spraid_dev *hdev, u16 cid); + +static void spraid_complete_aen(struct spraid_queue *spraidq, + struct spraid_completion *cqe) +{ + struct spraid_dev *hdev = spraidq->hdev; + u32 result = le32_to_cpu(cqe->result); + + dev_info(hdev->dev, "rcv aen, cid[%d], status[0x%x], result[0x%x]\n", + cqe->cmd_id, le16_to_cpu(cqe->status) >> 1, result); + + spraid_send_aen(hdev, cqe->cmd_id); + + if ((le16_to_cpu(cqe->status) >> 1) != SPRAID_SC_SUCCESS) + return; + switch (result & 0x7) { + case SPRAID_AEN_NOTICE: + spraid_handle_aen_notice(hdev, result); + break; + case SPRAID_AEN_VS: + spraid_handle_aen_vs(hdev, result, le32_to_cpu(cqe->result1)); + break; + default: + dev_warn(hdev->dev, "Unsupported async event type: %u\n", + result & 0x7); + break; + } +} + +static void spraid_complete_ioq_sync_cmnd(struct spraid_queue *ioq, + struct spraid_completion *cqe) +{ + struct spraid_dev *hdev = ioq->hdev; + struct spraid_cmd *ptcmd; + + ptcmd = hdev->ioq_ptcmds + (ioq->qid - 1) * SPRAID_PTCMDS_PERQ + + cqe->cmd_id - SPRAID_IO_BLK_MQ_DEPTH; + + ptcmd->status = le16_to_cpu(cqe->status) >> 1; + ptcmd->result0 = le32_to_cpu(cqe->result); + ptcmd->result1 = le32_to_cpu(cqe->result1); + + complete(&ptcmd->cmd_done); +} + +static inline void spraid_handle_cqe(struct spraid_queue *spraidq, u16 idx) +{ + struct spraid_completion *cqe = &spraidq->cqes[idx]; + struct spraid_dev *hdev = spraidq->hdev; + + if (unlikely(cqe->cmd_id >= spraidq->q_depth)) { + dev_err(hdev->dev, + "Invalid command id[%d] completed on queue %d\n", + cqe->cmd_id, cqe->sq_id); + return; + } + + dev_log_dbg(hdev->dev, "cid[%d] qid[%d];" + " result[0x%x], sq_id[%d], status[0x%x]\n", + cqe->cmd_id, spraidq->qid, le32_to_cpu(cqe->result), + le16_to_cpu(cqe->sq_id), le16_to_cpu(cqe->status)); + + if (unlikely(spraidq->qid == 0 + && cqe->cmd_id >= SPRAID_AQ_BLK_MQ_DEPTH)) { + spraid_complete_aen(spraidq, cqe); + return; + } + + if (unlikely(spraidq->qid && cqe->cmd_id >= SPRAID_IO_BLK_MQ_DEPTH)) { + spraid_complete_ioq_sync_cmnd(spraidq, cqe); + return; + } + + if (spraidq->qid) + spraid_complete_ioq_cmnd(spraidq, cqe); + else + spraid_complete_adminq_cmnd(spraidq, cqe); +} + +static void spraid_complete_cqes(struct spraid_queue *spraidq, + u16 start, u16 end) +{ + while (start != end) { + spraid_handle_cqe(spraidq, start); + if (++start == spraidq->q_depth) + start = 0; + } +} + +static inline void spraid_update_cq_head(struct spraid_queue *spraidq) +{ + if (++spraidq->cq_head == spraidq->q_depth) { + spraidq->cq_head = 0; + spraidq->cq_phase = !spraidq->cq_phase; + } +} + +static inline bool spraid_process_cq(struct spraid_queue *spraidq, + u16 *start, u16 *end, int tag) +{ + bool found = false; + + *start = spraidq->cq_head; + while (!found && spraid_cqe_pending(spraidq)) { + if (spraidq->cqes[spraidq->cq_head].cmd_id == tag) + found = true; + spraid_update_cq_head(spraidq); + } + *end = spraidq->cq_head; + + if (*start != *end) + writel(spraidq->cq_head, + spraidq->q_db + spraidq->hdev->db_stride); + + return found; +} + +static bool spraid_poll_cq(struct spraid_queue *spraidq, int cid) +{ + u16 start, end; + bool found; + + if (!spraid_cqe_pending(spraidq)) + return 0; + + spin_lock_irq(&spraidq->cq_lock); + found = spraid_process_cq(spraidq, &start, &end, cid); + spin_unlock_irq(&spraidq->cq_lock); + + spraid_complete_cqes(spraidq, start, end); + return found; +} + +static irqreturn_t spraid_irq(int irq, void *data) +{ + struct spraid_queue *spraidq = data; + irqreturn_t ret = IRQ_NONE; + u16 start, end; + + spin_lock(&spraidq->cq_lock); + if (spraidq->cq_head != spraidq->last_cq_head) + ret = IRQ_HANDLED; + + spraid_process_cq(spraidq, &start, &end, -1); + spraidq->last_cq_head = spraidq->cq_head; + spin_unlock(&spraidq->cq_lock); + + if (start != end) { + spraid_complete_cqes(spraidq, start, end); + ret = IRQ_HANDLED; + } + return ret; +} + +static int spraid_setup_admin_queue(struct spraid_dev *hdev) +{ + struct spraid_queue *adminq = &hdev->queues[0]; + u32 aqa; + int ret; + + dev_info(hdev->dev, "[%s] start disable ctrl\n", __func__); + + ret = spraid_disable_ctrl(hdev); + if (ret) + return ret; + + ret = spraid_alloc_queue(hdev, 0, SPRAID_AQ_DEPTH); + if (ret) + return ret; + + aqa = adminq->q_depth - 1; + aqa |= aqa << 16; + writel(aqa, hdev->bar + SPRAID_REG_AQA); + lo_hi_writeq(adminq->sq_dma_addr, hdev->bar + SPRAID_REG_ASQ); + lo_hi_writeq(adminq->cq_dma_addr, hdev->bar + SPRAID_REG_ACQ); + + dev_info(hdev->dev, "[%s] start enable ctrl\n", __func__); + + ret = spraid_enable_ctrl(hdev); + if (ret) { + ret = -ENODEV; + goto free_queue; + } + + adminq->cq_vector = 0; + spraid_init_queue(adminq, 0); + ret = pci_request_irq(hdev->pdev, adminq->cq_vector, spraid_irq, NULL, + adminq, "spraid%d_q%d", + hdev->instance, adminq->qid); + + if (ret) { + adminq->cq_vector = -1; + hdev->online_queues--; + goto free_queue; + } + + dev_info(hdev->dev, "[%s] success, queuecount:[%d], onlinequeue:[%d]\n", + __func__, hdev->queue_count, hdev->online_queues); + + return 0; + +free_queue: + spraid_free_queue(adminq); + return ret; +} + +static u32 spraid_bar_size(struct spraid_dev *hdev, u32 nr_ioqs) +{ + return (SPRAID_REG_DBS + ((nr_ioqs + 1) * 8 * hdev->db_stride)); +} + +static int spraid_alloc_admin_cmds(struct spraid_dev *hdev) +{ + int i; + + INIT_LIST_HEAD(&hdev->adm_cmd_list); + spin_lock_init(&hdev->adm_cmd_lock); + + hdev->adm_cmds = kcalloc_node(SPRAID_AQ_BLK_MQ_DEPTH, + sizeof(struct spraid_cmd), + GFP_KERNEL, hdev->numa_node); + + if (!hdev->adm_cmds) { + dev_err(hdev->dev, "Alloc admin cmds failed\n"); + return -ENOMEM; + } + + for (i = 0; i < SPRAID_AQ_BLK_MQ_DEPTH; i++) { + hdev->adm_cmds[i].qid = 0; + hdev->adm_cmds[i].cid = i; + list_add_tail(&(hdev->adm_cmds[i].list), &hdev->adm_cmd_list); + } + + dev_info(hdev->dev, "Alloc admin cmds success, num[%d]\n", + SPRAID_AQ_BLK_MQ_DEPTH); + + return 0; +} + +static void spraid_free_admin_cmds(struct spraid_dev *hdev) +{ + kfree(hdev->adm_cmds); + hdev->adm_cmds = NULL; + INIT_LIST_HEAD(&hdev->adm_cmd_list); +} + +static struct spraid_cmd *spraid_get_cmd(struct spraid_dev *hdev, + enum spraid_cmd_type type) +{ + struct spraid_cmd *cmd = NULL; + unsigned long flags; + struct list_head *head = &hdev->adm_cmd_list; + spinlock_t *slock = &hdev->adm_cmd_lock; + + if (type == SPRAID_CMD_IOPT) { + head = &hdev->ioq_pt_list; + slock = &hdev->ioq_pt_lock; + } + + spin_lock_irqsave(slock, flags); + if (list_empty(head)) { + spin_unlock_irqrestore(slock, flags); + dev_err(hdev->dev, "err, cmd[%d] list empty\n", type); + return NULL; + } + cmd = list_entry(head->next, struct spraid_cmd, list); + list_del_init(&cmd->list); + spin_unlock_irqrestore(slock, flags); + + WRITE_ONCE(cmd->state, SPRAID_CMD_IN_FLIGHT); + + return cmd; +} + +static void spraid_put_cmd(struct spraid_dev *hdev, struct spraid_cmd *cmd, + enum spraid_cmd_type type) +{ + unsigned long flags; + struct list_head *head = &hdev->adm_cmd_list; + spinlock_t *slock = &hdev->adm_cmd_lock; + + if (type == SPRAID_CMD_IOPT) { + head = &hdev->ioq_pt_list; + slock = &hdev->ioq_pt_lock; + } + + spin_lock_irqsave(slock, flags); + WRITE_ONCE(cmd->state, SPRAID_CMD_IDLE); + list_add_tail(&cmd->list, head); + spin_unlock_irqrestore(slock, flags); +} + + +static int spraid_submit_admin_sync_cmd(struct spraid_dev *hdev, + struct spraid_admin_command *cmd, + u32 *result0, u32 *result1, u32 timeout) +{ + struct spraid_cmd *adm_cmd = spraid_get_cmd(hdev, SPRAID_CMD_ADM); + + if (!adm_cmd) { + dev_err(hdev->dev, "err, get admin cmd failed\n"); + return -EFAULT; + } + + timeout = timeout ? timeout : ADMIN_TIMEOUT; + + init_completion(&adm_cmd->cmd_done); + + cmd->common.command_id = adm_cmd->cid; + spraid_submit_cmd(&hdev->queues[0], cmd); + + if (!wait_for_completion_timeout(&adm_cmd->cmd_done, timeout)) { + dev_err(hdev->dev, "[%s] cid[%d] qid[%d] timeout;" + " opcode[0x%x] subopcode[0x%x]\n", + __func__, adm_cmd->cid, adm_cmd->qid, + cmd->usr_cmd.opcode, cmd->usr_cmd.info_0.subopcode); + WRITE_ONCE(adm_cmd->state, SPRAID_CMD_TIMEOUT); + spraid_put_cmd(hdev, adm_cmd, SPRAID_CMD_ADM); + return -EINVAL; + } + + if (result0) + *result0 = adm_cmd->result0; + if (result1) + *result1 = adm_cmd->result1; + + spraid_put_cmd(hdev, adm_cmd, SPRAID_CMD_ADM); + + return adm_cmd->status; +} + +static int spraid_create_cq(struct spraid_dev *hdev, u16 qid, + struct spraid_queue *spraidq, u16 cq_vector) +{ + struct spraid_admin_command admin_cmd; + int flags = SPRAID_QUEUE_PHYS_CONTIG | SPRAID_CQ_IRQ_ENABLED; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.create_cq.opcode = SPRAID_ADMIN_CREATE_CQ; + admin_cmd.create_cq.prp1 = cpu_to_le64(spraidq->cq_dma_addr); + admin_cmd.create_cq.cqid = cpu_to_le16(qid); + admin_cmd.create_cq.qsize = cpu_to_le16(spraidq->q_depth - 1); + admin_cmd.create_cq.cq_flags = cpu_to_le16(flags); + admin_cmd.create_cq.irq_vector = cpu_to_le16(cq_vector); + + return spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); +} + +static int spraid_create_sq(struct spraid_dev *hdev, u16 qid, + struct spraid_queue *spraidq) +{ + struct spraid_admin_command admin_cmd; + int flags = SPRAID_QUEUE_PHYS_CONTIG; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.create_sq.opcode = SPRAID_ADMIN_CREATE_SQ; + admin_cmd.create_sq.prp1 = cpu_to_le64(spraidq->sq_dma_addr); + admin_cmd.create_sq.sqid = cpu_to_le16(qid); + admin_cmd.create_sq.qsize = cpu_to_le16(spraidq->q_depth - 1); + admin_cmd.create_sq.sq_flags = cpu_to_le16(flags); + admin_cmd.create_sq.cqid = cpu_to_le16(qid); + + return spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); +} + +static void spraid_free_queue(struct spraid_queue *spraidq) +{ + struct spraid_dev *hdev = spraidq->hdev; + + hdev->queue_count--; + dma_free_coherent(hdev->dev, CQ_SIZE(spraidq->q_depth), + (void *)spraidq->cqes, spraidq->cq_dma_addr); + dma_free_coherent(hdev->dev, SQ_SIZE(spraidq->qid, spraidq->q_depth), + spraidq->sq_cmds, spraidq->sq_dma_addr); + dma_free_coherent(hdev->dev, SENSE_SIZE(spraidq->q_depth), + spraidq->sense, spraidq->sense_dma_addr); +} + +static void spraid_free_admin_queue(struct spraid_dev *hdev) +{ + spraid_free_queue(&hdev->queues[0]); +} + +static void spraid_free_io_queues(struct spraid_dev *hdev) +{ + int i; + + for (i = hdev->queue_count - 1; i >= 1; i--) + spraid_free_queue(&hdev->queues[i]); +} + +static int spraid_delete_queue(struct spraid_dev *hdev, u8 op, u16 id) +{ + struct spraid_admin_command admin_cmd; + int ret; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.delete_queue.opcode = op; + admin_cmd.delete_queue.qid = cpu_to_le16(id); + + ret = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); + + if (ret) + dev_err(hdev->dev, "Delete %s:[%d] failed\n", + (op == SPRAID_ADMIN_DELETE_CQ) ? "cq" : "sq", id); + + return ret; +} + +static int spraid_delete_cq(struct spraid_dev *hdev, u16 cqid) +{ + return spraid_delete_queue(hdev, SPRAID_ADMIN_DELETE_CQ, cqid); +} + +static int spraid_delete_sq(struct spraid_dev *hdev, u16 sqid) +{ + return spraid_delete_queue(hdev, SPRAID_ADMIN_DELETE_SQ, sqid); +} + +static int spraid_create_queue(struct spraid_queue *spraidq, u16 qid) +{ + struct spraid_dev *hdev = spraidq->hdev; + u16 cq_vector; + int ret; + + cq_vector = (hdev->num_vecs == 1) ? 0 : qid; + ret = spraid_create_cq(hdev, qid, spraidq, cq_vector); + if (ret) + return ret; + + ret = spraid_create_sq(hdev, qid, spraidq); + if (ret) + goto delete_cq; + + spraid_init_queue(spraidq, qid); + spraidq->cq_vector = cq_vector; + + ret = pci_request_irq(hdev->pdev, cq_vector, spraid_irq, NULL, + spraidq, "spraid%d_q%d", hdev->instance, qid); + + if (ret) { + dev_err(hdev->dev, "Request queue[%d] irq failed\n", qid); + goto delete_sq; + } + + return 0; + +delete_sq: + spraidq->cq_vector = -1; + hdev->online_queues--; + spraid_delete_sq(hdev, qid); +delete_cq: + spraid_delete_cq(hdev, qid); + + return ret; +} + +static int spraid_create_io_queues(struct spraid_dev *hdev) +{ + u32 i, max; + int ret = 0; + + max = min(hdev->max_qid, hdev->queue_count - 1); + for (i = hdev->online_queues; i <= max; i++) { + ret = spraid_create_queue(&hdev->queues[i], i); + if (ret) { + dev_err(hdev->dev, "Create queue[%d] failed\n", i); + break; + } + } + + dev_info(hdev->dev, "[%s] queue_count[%d], online_queue[%d]", + __func__, hdev->queue_count, hdev->online_queues); + + return ret >= 0 ? 0 : ret; +} + +static int spraid_set_features(struct spraid_dev *hdev, u32 fid, + u32 dword11, void *buffer, + size_t buflen, u32 *result) +{ + struct spraid_admin_command admin_cmd; + int ret; + u8 *data_ptr = NULL; + dma_addr_t data_dma = 0; + + if (buffer && buflen) { + data_ptr = dma_alloc_coherent(hdev->dev, buflen, + &data_dma, GFP_KERNEL); + if (!data_ptr) + return -ENOMEM; + + memcpy(data_ptr, buffer, buflen); + } + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.features.opcode = SPRAID_ADMIN_SET_FEATURES; + admin_cmd.features.fid = cpu_to_le32(fid); + admin_cmd.features.dword11 = cpu_to_le32(dword11); + admin_cmd.common.dptr.prp1 = cpu_to_le64(data_dma); + + ret = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, result, NULL, 0); + + if (data_ptr) + dma_free_coherent(hdev->dev, buflen, data_ptr, data_dma); + + return ret; +} + +static int spraid_configure_timestamp(struct spraid_dev *hdev) +{ + __le64 ts; + int ret; + + ts = cpu_to_le64(ktime_to_ms(ktime_get_real())); + ret = spraid_set_features(hdev, SPRAID_FEAT_TIMESTAMP, + 0, &ts, sizeof(ts), NULL); + + if (ret) + dev_err(hdev->dev, "set timestamp failed: %d\n", ret); + return ret; +} + +static int spraid_set_queue_cnt(struct spraid_dev *hdev, u32 *cnt) +{ + u32 q_cnt = (*cnt - 1) | ((*cnt - 1) << 16); + u32 nr_ioqs, result; + int status; + + status = spraid_set_features(hdev, SPRAID_FEAT_NUM_QUEUES, + q_cnt, NULL, 0, &result); + if (status) { + dev_err(hdev->dev, "Set queue count failed, status: %d\n", + status); + return -EIO; + } + + nr_ioqs = min(result & 0xffff, result >> 16) + 1; + *cnt = min(*cnt, nr_ioqs); + if (*cnt == 0) { + dev_err(hdev->dev, "Illegal queue count: zero\n"); + return -EIO; + } + return 0; +} + +static int spraid_setup_io_queues(struct spraid_dev *hdev) +{ + struct spraid_queue *adminq = &hdev->queues[0]; + struct pci_dev *pdev = hdev->pdev; + u32 nr_ioqs = num_online_cpus(); + u32 i, size; + int ret; + + struct irq_affinity affd = { + .pre_vectors = 1 + }; + + ret = spraid_set_queue_cnt(hdev, &nr_ioqs); + if (ret < 0) + return ret; + + size = spraid_bar_size(hdev, nr_ioqs); + ret = spraid_remap_bar(hdev, size); + if (ret) + return -ENOMEM; + + adminq->q_db = hdev->dbs; + + pci_free_irq(pdev, 0, adminq); + pci_free_irq_vectors(pdev); + + ret = pci_alloc_irq_vectors_affinity(pdev, 1, (nr_ioqs + 1), + PCI_IRQ_ALL_TYPES | PCI_IRQ_AFFINITY, &affd); + if (ret <= 0) + return -EIO; + + hdev->num_vecs = ret; + + hdev->max_qid = max(ret - 1, 1); + + ret = pci_request_irq(pdev, adminq->cq_vector, spraid_irq, NULL, + adminq, "spraid%d_q%d", + hdev->instance, adminq->qid); + if (ret) { + dev_err(hdev->dev, "Request admin irq failed\n"); + adminq->cq_vector = -1; + return ret; + } + + for (i = hdev->queue_count; i <= hdev->max_qid; i++) { + ret = spraid_alloc_queue(hdev, i, hdev->ioq_depth); + if (ret) + break; + } + dev_info(hdev->dev, "[%s] max_qid: %d, queue_count: %d;" + " online_queue: %d, ioq_depth: %d\n", + __func__, hdev->max_qid, hdev->queue_count, + hdev->online_queues, hdev->ioq_depth); + + return spraid_create_io_queues(hdev); +} + +static void spraid_delete_io_queues(struct spraid_dev *hdev) +{ + u16 queues = hdev->online_queues - 1; + u8 opcode = SPRAID_ADMIN_DELETE_SQ; + u16 i, pass; + + if (!pci_device_is_present(hdev->pdev)) { + dev_err(hdev->dev, + "pci_device is not present, skip disable io queues\n"); + return; + } + + if (hdev->online_queues < 2) { + dev_err(hdev->dev, "[%s] err, io queue has been delete\n", + __func__); + return; + } + + for (pass = 0; pass < 2; pass++) { + for (i = queues; i > 0; i--) + if (spraid_delete_queue(hdev, opcode, i)) + break; + + opcode = SPRAID_ADMIN_DELETE_CQ; + } +} + +static void spraid_remove_io_queues(struct spraid_dev *hdev) +{ + spraid_delete_io_queues(hdev); + spraid_free_io_queues(hdev); +} + +static void spraid_pci_disable(struct spraid_dev *hdev) +{ + struct pci_dev *pdev = hdev->pdev; + u32 i; + + for (i = 0; i < hdev->online_queues; i++) + pci_free_irq(pdev, hdev->queues[i].cq_vector, &hdev->queues[i]); + pci_free_irq_vectors(pdev); + if (pci_is_enabled(pdev)) { + pci_disable_pcie_error_reporting(pdev); + pci_disable_device(pdev); + } + hdev->online_queues = 0; +} + +static void spraid_disable_admin_queue(struct spraid_dev *hdev, bool shutdown) +{ + struct spraid_queue *adminq = &hdev->queues[0]; + u16 start, end; + + if (pci_device_is_present(hdev->pdev)) { + if (shutdown) + spraid_shutdown_ctrl(hdev); + else + spraid_disable_ctrl(hdev); + } + + if (hdev->queue_count == 0) { + dev_err(hdev->dev, "[%s] err, admin queue has been delete\n", + __func__); + return; + } + + spin_lock_irq(&adminq->cq_lock); + spraid_process_cq(adminq, &start, &end, -1); + spin_unlock_irq(&adminq->cq_lock); + + spraid_complete_cqes(adminq, start, end); + spraid_free_admin_queue(hdev); +} + +static int spraid_create_dma_pools(struct spraid_dev *hdev) +{ + int i; + char poolname[20] = { 0 }; + + hdev->prp_page_pool = dma_pool_create("prp list page", hdev->dev, + PAGE_SIZE, PAGE_SIZE, 0); + + if (!hdev->prp_page_pool) { + dev_err(hdev->dev, "create prp_page_pool failed\n"); + return -ENOMEM; + } + + for (i = 0; i < small_pool_num; i++) { + sprintf(poolname, "prp_list_256_%d", i); + hdev->prp_small_pool[i] = + dma_pool_create(poolname, hdev->dev, SMALL_POOL_SIZE, + SMALL_POOL_SIZE, 0); + + if (!hdev->prp_small_pool[i]) { + dev_err(hdev->dev, "create prp_small_pool %d failed\n", + i); + goto destroy_prp_small_pool; + } + } + + return 0; + +destroy_prp_small_pool: + while (i > 0) + dma_pool_destroy(hdev->prp_small_pool[--i]); + dma_pool_destroy(hdev->prp_page_pool); + + return -ENOMEM; +} + +static void spraid_destroy_dma_pools(struct spraid_dev *hdev) +{ + int i; + + for (i = 0; i < small_pool_num; i++) + dma_pool_destroy(hdev->prp_small_pool[i]); + dma_pool_destroy(hdev->prp_page_pool); +} + +static int spraid_get_dev_list(struct spraid_dev *hdev, + struct spraid_dev_info *devices) +{ + u32 nd = le32_to_cpu(hdev->ctrl_info->nd); + struct spraid_admin_command admin_cmd; + struct spraid_dev_list *list_buf; + dma_addr_t data_dma = 0; + u32 i, idx, hdid, ndev; + int ret = 0; + + list_buf = dma_alloc_coherent(hdev->dev, PAGE_SIZE, + &data_dma, GFP_KERNEL); + if (!list_buf) + return -ENOMEM; + + for (idx = 0; idx < nd;) { + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.get_info.opcode = SPRAID_ADMIN_GET_INFO; + admin_cmd.get_info.type = SPRAID_GET_INFO_DEV_LIST; + admin_cmd.get_info.cdw11 = cpu_to_le32(idx); + admin_cmd.common.dptr.prp1 = cpu_to_le64(data_dma); + + ret = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, + NULL, NULL, 0); + + if (ret) { + dev_err(hdev->dev, "Get device list failed, nd: %u;" + "idx: %u, ret: %d\n", + nd, idx, ret); + goto out; + } + ndev = le32_to_cpu(list_buf->dev_num); + + dev_info(hdev->dev, "ndev numbers: %u\n", ndev); + + for (i = 0; i < ndev; i++) { + hdid = le32_to_cpu(list_buf->devices[i].hdid); + dev_info(hdev->dev, "list_buf->devices[%d], hdid: %u;" + "target: %d, channel: %d, lun: %d, attr[0x%x]\n", + i, hdid, + le16_to_cpu(list_buf->devices[i].target), + list_buf->devices[i].channel, + list_buf->devices[i].lun, + list_buf->devices[i].attr); + if (hdid > nd || hdid == 0) { + dev_err(hdev->dev, "err, hdid[%d] invalid\n", + hdid); + continue; + } + memcpy(&devices[hdid - 1], &list_buf->devices[i], + sizeof(struct spraid_dev_info)); + } + idx += ndev; + + if (idx < MAX_DEV_ENTRY_PER_PAGE_4K) + break; + } + +out: + dma_free_coherent(hdev->dev, PAGE_SIZE, list_buf, data_dma); + return ret; +} + +static void spraid_send_aen(struct spraid_dev *hdev, u16 cid) +{ + struct spraid_queue *adminq = &hdev->queues[0]; + struct spraid_admin_command admin_cmd; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.common.opcode = SPRAID_ADMIN_ASYNC_EVENT; + admin_cmd.common.command_id = cid; + + spraid_submit_cmd(adminq, &admin_cmd); + dev_info(hdev->dev, "send aen, cid[%d]\n", cid); +} + +static inline void spraid_send_all_aen(struct spraid_dev *hdev) +{ + u16 i; + + for (i = 0; i < hdev->ctrl_info->aerl; i++) + spraid_send_aen(hdev, i + SPRAID_AQ_BLK_MQ_DEPTH); +} + +static int spraid_add_device(struct spraid_dev *hdev, + struct spraid_dev_info *device) +{ + struct Scsi_Host *shost = hdev->shost; + struct scsi_device *sdev; + + dev_info(hdev->dev, "add device, hdid: %u target: %d, channel: %d;" + " lun: %d, attr[0x%x]\n", + le32_to_cpu(device->hdid), le16_to_cpu(device->target), + device->channel, device->lun, device->attr); + + sdev = scsi_device_lookup(shost, device->channel, + le16_to_cpu(device->target), 0); + if (sdev) { + dev_warn(hdev->dev, "Device is already exist, channel: %d;" + " target_id: %d, lun: %d\n", + device->channel, le16_to_cpu(device->target), 0); + scsi_device_put(sdev); + return -EEXIST; + } + scsi_add_device(shost, device->channel, le16_to_cpu(device->target), 0); + return 0; +} + +static int spraid_rescan_device(struct spraid_dev *hdev, + struct spraid_dev_info *device) +{ + struct Scsi_Host *shost = hdev->shost; + struct scsi_device *sdev; + + dev_info(hdev->dev, "rescan device, hdid: %u target: %d, channel: %d;" + " lun: %d, attr[0x%x]\n", + le32_to_cpu(device->hdid), le16_to_cpu(device->target), + device->channel, device->lun, device->attr); + + sdev = scsi_device_lookup(shost, device->channel, + le16_to_cpu(device->target), 0); + if (!sdev) { + dev_warn(hdev->dev, "device is not exit rescan it, channel: %d;" + " target_id: %d, lun: %d\n", + device->channel, le16_to_cpu(device->target), 0); + return -ENODEV; + } + + scsi_rescan_device(&sdev->sdev_gendev); + scsi_device_put(sdev); + return 0; +} + +static int spraid_remove_device(struct spraid_dev *hdev, + struct spraid_dev_info *org_device) +{ + struct Scsi_Host *shost = hdev->shost; + struct scsi_device *sdev; + + dev_info(hdev->dev, "remove device, hdid: %u target: %d, channel: %d;" + " lun: %d, attr[0x%x]\n", + le32_to_cpu(org_device->hdid), le16_to_cpu(org_device->target), + org_device->channel, org_device->lun, org_device->attr); + + sdev = scsi_device_lookup(shost, org_device->channel, + le16_to_cpu(org_device->target), 0); + if (!sdev) { + dev_warn(hdev->dev, "device is not exit remove it, channel: %d;" + " target_id: %d, lun: %d\n", + org_device->channel, + le16_to_cpu(org_device->target), 0); + return -ENODEV; + } + + scsi_remove_device(sdev); + scsi_device_put(sdev); + return 0; +} + +static int spraid_dev_list_init(struct spraid_dev *hdev) +{ + u32 nd = le32_to_cpu(hdev->ctrl_info->nd); + int i, ret; + + hdev->devices = kzalloc_node(nd * sizeof(struct spraid_dev_info), + GFP_KERNEL, hdev->numa_node); + if (!hdev->devices) + return -ENOMEM; + + ret = spraid_get_dev_list(hdev, hdev->devices); + if (ret) { + dev_err(hdev->dev, + "Ignore failure of getting device list;" + " within initialization\n"); + return 0; + } + + for (i = 0; i < nd; i++) { + if (SPRAID_DEV_INFO_FLAG_VALID(hdev->devices[i].flag) && + SPRAID_DEV_INFO_ATTR_BOOT(hdev->devices[i].attr)) { + spraid_add_device(hdev, &hdev->devices[i]); + break; + } + } + return 0; +} + +static int luntarget_cmp_func(const void *l, const void *r) +{ + const struct spraid_dev_info *ln = l; + const struct spraid_dev_info *rn = r; + + if (ln->channel == rn->channel) + return le16_to_cpu(ln->target) - le16_to_cpu(rn->target); + + return ln->channel - rn->channel; +} + +static void spraid_scan_work(struct work_struct *work) +{ + struct spraid_dev *hdev = + container_of(work, struct spraid_dev, scan_work); + struct spraid_dev_info *devices, *org_devices; + struct spraid_dev_info *sortdevice; + u32 nd = le32_to_cpu(hdev->ctrl_info->nd); + u8 flag, org_flag; + int i, ret; + int count = 0; + + devices = kcalloc(nd, sizeof(struct spraid_dev_info), GFP_KERNEL); + if (!devices) + return; + + sortdevice = kcalloc(nd, sizeof(struct spraid_dev_info), GFP_KERNEL); + if (!sortdevice) + goto free_list; + + ret = spraid_get_dev_list(hdev, devices); + if (ret) + goto free_all; + org_devices = hdev->devices; + for (i = 0; i < nd; i++) { + org_flag = org_devices[i].flag; + flag = devices[i].flag; + + dev_log_dbg(hdev->dev, "i: %d, org_flag: 0x%x, flag: 0x%x\n", + i, org_flag, flag); + + if (SPRAID_DEV_INFO_FLAG_VALID(flag)) { + if (!SPRAID_DEV_INFO_FLAG_VALID(org_flag)) { + down_write(&hdev->devices_rwsem); + memcpy(&org_devices[i], &devices[i], + sizeof(struct spraid_dev_info)); + memcpy(&sortdevice[count++], &devices[i], + sizeof(struct spraid_dev_info)); + up_write(&hdev->devices_rwsem); + } else if (SPRAID_DEV_INFO_FLAG_CHANGE(flag)) { + spraid_rescan_device(hdev, &devices[i]); + } + } else { + if (SPRAID_DEV_INFO_FLAG_VALID(org_flag)) { + down_write(&hdev->devices_rwsem); + org_devices[i].flag &= 0xfe; + up_write(&hdev->devices_rwsem); + spraid_remove_device(hdev, &org_devices[i]); + } + } + } + + dev_info(hdev->dev, "scan work add device count = %d\n", count); + + sort(sortdevice, count, sizeof(sortdevice[0]), + luntarget_cmp_func, NULL); + + for (i = 0; i < count; i++) + spraid_add_device(hdev, &sortdevice[i]); + +free_all: + kfree(sortdevice); +free_list: + kfree(devices); +} + +static void spraid_timesyn_work(struct work_struct *work) +{ + struct spraid_dev *hdev = + container_of(work, struct spraid_dev, timesyn_work); + + spraid_configure_timestamp(hdev); +} + +static int spraid_init_ctrl_info(struct spraid_dev *hdev); +static void spraid_fw_act_work(struct work_struct *work) +{ + struct spraid_dev *hdev = + container_of(work, struct spraid_dev, fw_act_work); + + if (spraid_init_ctrl_info(hdev)) + dev_err(hdev->dev, "get ctrl info failed after fw act\n"); +} + +static void spraid_queue_scan(struct spraid_dev *hdev) +{ + queue_work(spraid_wq, &hdev->scan_work); +} + +static void spraid_handle_aen_notice(struct spraid_dev *hdev, u32 result) +{ + switch ((result & 0xff00) >> 8) { + case SPRAID_AEN_DEV_CHANGED: + spraid_queue_scan(hdev); + break; + case SPRAID_AEN_FW_ACT_START: + dev_info(hdev->dev, "fw activation starting\n"); + break; + case SPRAID_AEN_HOST_PROBING: + break; + default: + dev_warn(hdev->dev, "async event result %08x\n", result); + } +} + +static void spraid_handle_aen_vs(struct spraid_dev *hdev, + u32 result, u32 result1) +{ + switch ((result & 0xff00) >> 8) { + case SPRAID_AEN_TIMESYN: + queue_work(spraid_wq, &hdev->timesyn_work); + break; + case SPRAID_AEN_FW_ACT_FINISH: + dev_info(hdev->dev, "fw activation finish\n"); + queue_work(spraid_wq, &hdev->fw_act_work); + break; + case SPRAID_AEN_EVENT_MIN ... SPRAID_AEN_EVENT_MAX: + dev_info(hdev->dev, "rcv card event[%d];" + " param1[0x%x] param2[0x%x]\n", + (result & 0xff00) >> 8, result, result1); + break; + default: + dev_warn(hdev->dev, "async event result: 0x%x\n", result); + } +} + +static int spraid_alloc_resources(struct spraid_dev *hdev) +{ + int ret, nqueue; + + ret = ida_alloc(&spraid_instance_ida, GFP_KERNEL); + if (ret < 0) { + dev_err(hdev->dev, "Get instance id failed\n"); + return ret; + } + hdev->instance = ret; + + hdev->ctrl_info = kzalloc_node(sizeof(*hdev->ctrl_info), + GFP_KERNEL, hdev->numa_node); + if (!hdev->ctrl_info) { + ret = -ENOMEM; + goto release_instance; + } + + ret = spraid_create_dma_pools(hdev); + if (ret) + goto free_ctrl_info; + nqueue = num_possible_cpus() + 1; + hdev->queues = kcalloc_node(nqueue, sizeof(struct spraid_queue), + GFP_KERNEL, hdev->numa_node); + if (!hdev->queues) { + ret = -ENOMEM; + goto destroy_dma_pools; + } + + ret = spraid_alloc_admin_cmds(hdev); + if (ret) + goto free_queues; + + dev_info(hdev->dev, "[%s] queues num: %d\n", __func__, nqueue); + + return 0; + +free_queues: + kfree(hdev->queues); +destroy_dma_pools: + spraid_destroy_dma_pools(hdev); +free_ctrl_info: + kfree(hdev->ctrl_info); +release_instance: + ida_free(&spraid_instance_ida, hdev->instance); + return ret; +} + +static void spraid_free_resources(struct spraid_dev *hdev) +{ + spraid_free_admin_cmds(hdev); + kfree(hdev->queues); + spraid_destroy_dma_pools(hdev); + kfree(hdev->ctrl_info); + ida_free(&spraid_instance_ida, hdev->instance); +} + +static void spraid_bsg_unmap_data(struct spraid_dev *hdev, struct bsg_job *job) +{ + struct request *rq = blk_mq_rq_from_pdu(job); + struct spraid_iod *iod = job->dd_data; + enum dma_data_direction dma_dir = + rq_data_dir(rq) ? DMA_TO_DEVICE : DMA_FROM_DEVICE; + + if (iod->nsge) + dma_unmap_sg(hdev->dev, iod->sg, iod->nsge, dma_dir); + + spraid_free_iod_res(hdev, iod); +} + +static int spraid_bsg_map_data(struct spraid_dev *hdev, struct bsg_job *job, + struct spraid_admin_command *cmd) +{ + struct request *rq = blk_mq_rq_from_pdu(job); + struct spraid_iod *iod = job->dd_data; + enum dma_data_direction dma_dir = + rq_data_dir(rq) ? DMA_TO_DEVICE : DMA_FROM_DEVICE; + int ret = 0; + + iod->sg = job->request_payload.sg_list; + iod->nsge = job->request_payload.sg_cnt; + iod->length = job->request_payload.payload_len; + iod->use_sgl = false; + iod->npages = -1; + iod->sg_drv_mgmt = false; + + if (!iod->nsge) + goto out; + + ret = dma_map_sg_attrs(hdev->dev, iod->sg, iod->nsge, + dma_dir, DMA_ATTR_NO_WARN); + if (!ret) + goto out; + + ret = spraid_setup_prps(hdev, iod); + if (ret) + goto unmap; + + cmd->common.dptr.prp1 = cpu_to_le64(sg_dma_address(iod->sg)); + cmd->common.dptr.prp2 = cpu_to_le64(iod->first_dma); + + return 0; + +unmap: + dma_unmap_sg(hdev->dev, iod->sg, iod->nsge, dma_dir); +out: + return ret; +} + +static int spraid_get_ctrl_info(struct spraid_dev *hdev, + struct spraid_ctrl_info *ctrl_info) +{ + struct spraid_admin_command admin_cmd; + u8 *data_ptr = NULL; + dma_addr_t data_dma = 0; + int ret; + + data_ptr = dma_alloc_coherent(hdev->dev, PAGE_SIZE, + &data_dma, GFP_KERNEL); + if (!data_ptr) + return -ENOMEM; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.get_info.opcode = SPRAID_ADMIN_GET_INFO; + admin_cmd.get_info.type = SPRAID_GET_INFO_CTRL; + admin_cmd.common.dptr.prp1 = cpu_to_le64(data_dma); + + ret = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); + if (!ret) + memcpy(ctrl_info, data_ptr, sizeof(struct spraid_ctrl_info)); + + dma_free_coherent(hdev->dev, PAGE_SIZE, data_ptr, data_dma); + + return ret; +} + +static int spraid_init_ctrl_info(struct spraid_dev *hdev) +{ + int ret; + + hdev->ctrl_info->nd = cpu_to_le32(240); + hdev->ctrl_info->mdts = 8; + hdev->ctrl_info->max_cmds = cpu_to_le16(4096); + hdev->ctrl_info->max_num_sge = cpu_to_le16(128); + hdev->ctrl_info->max_channel = cpu_to_le16(4); + hdev->ctrl_info->max_tgt_id = cpu_to_le32(3239); + hdev->ctrl_info->max_lun = cpu_to_le16(2); + + ret = spraid_get_ctrl_info(hdev, hdev->ctrl_info); + if (ret) + dev_err(hdev->dev, "get controller info failed: %d\n", ret); + + dev_info(hdev->dev, "[%s]nd = %d\n", __func__, hdev->ctrl_info->nd); + dev_info(hdev->dev, "[%s]max_cmd = %d\n", + __func__, hdev->ctrl_info->max_cmds); + dev_info(hdev->dev, "[%s]max_channel = %d\n", + __func__, hdev->ctrl_info->max_channel); + dev_info(hdev->dev, "[%s]max_tgt_id = %d\n", + __func__, hdev->ctrl_info->max_tgt_id); + dev_info(hdev->dev, "[%s]max_lun = %d\n", + __func__, hdev->ctrl_info->max_lun); + dev_info(hdev->dev, "[%s]max_num_sge = %d\n", + __func__, hdev->ctrl_info->max_num_sge); + dev_info(hdev->dev, "[%s]lun_num_boot = %d\n", + __func__, hdev->ctrl_info->lun_num_in_boot); + dev_info(hdev->dev, "[%s]mdts = %d\n", __func__, hdev->ctrl_info->mdts); + dev_info(hdev->dev, "[%s]acl = %d\n", __func__, hdev->ctrl_info->acl); + dev_info(hdev->dev, "[%s]aer1 = %d\n", __func__, hdev->ctrl_info->aerl); + dev_info(hdev->dev, "[%s]card_type = %d\n", + __func__, hdev->ctrl_info->card_type); + dev_info(hdev->dev, "[%s]rtd3e = %d\n", + __func__, hdev->ctrl_info->rtd3e); + dev_info(hdev->dev, "[%s]sn = %s\n", __func__, hdev->ctrl_info->sn); + dev_info(hdev->dev, "[%s]fr = %s\n", __func__, hdev->ctrl_info->fr); + + if (!hdev->ctrl_info->aerl) + hdev->ctrl_info->aerl = 1; + if (hdev->ctrl_info->aerl > SPRAID_NR_AEN_COMMANDS) + hdev->ctrl_info->aerl = SPRAID_NR_AEN_COMMANDS; + + return 0; +} + +#define SPRAID_MAX_ADMIN_PAYLOAD_SIZE BIT(16) +static int spraid_alloc_iod_ext_mem_pool(struct spraid_dev *hdev) +{ + u16 max_sge = le16_to_cpu(hdev->ctrl_info->max_num_sge); + size_t alloc_size; + + alloc_size = spraid_iod_ext_size(hdev, SPRAID_MAX_ADMIN_PAYLOAD_SIZE, + max_sge, true, false); + if (alloc_size > PAGE_SIZE) + dev_warn(hdev->dev, "It is unreasonable ;" + " sg allocation more than one page\n"); + hdev->iod_mempool = mempool_create_node(1, mempool_kmalloc, + mempool_kfree, + (void *)alloc_size, GFP_KERNEL, + hdev->numa_node); + if (!hdev->iod_mempool) { + dev_err(hdev->dev, "Create iod extension memory pool failed\n"); + return -ENOMEM; + } + + return 0; +} + +static void spraid_free_iod_ext_mem_pool(struct spraid_dev *hdev) +{ + mempool_destroy(hdev->iod_mempool); +} + +static int spraid_user_admin_cmd(struct spraid_dev *hdev, struct bsg_job *job) +{ + struct spraid_bsg_request *bsg_req = job->request; + struct spraid_passthru_common_cmd *cmd = &(bsg_req->admcmd); + struct spraid_admin_command admin_cmd; + u32 timeout = msecs_to_jiffies(cmd->timeout_ms); + u32 result[2] = {0}; + int status; + + if (hdev->state >= SPRAID_RESETTING) { + dev_err(hdev->dev, "[%s] err, host state:[%d] is not right\n", + __func__, hdev->state); + return -EBUSY; + } + + dev_info(hdev->dev, "[%s] opcode[0x%x] subopcode[0x%x] init\n", + __func__, cmd->opcode, cmd->info_0.subopcode); + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.common.opcode = cmd->opcode; + admin_cmd.common.flags = cmd->flags; + admin_cmd.common.hdid = cpu_to_le32(cmd->nsid); + admin_cmd.common.cdw2[0] = cpu_to_le32(cmd->cdw2); + admin_cmd.common.cdw2[1] = cpu_to_le32(cmd->cdw3); + admin_cmd.common.cdw10 = cpu_to_le32(cmd->cdw10); + admin_cmd.common.cdw11 = cpu_to_le32(cmd->cdw11); + admin_cmd.common.cdw12 = cpu_to_le32(cmd->cdw12); + admin_cmd.common.cdw13 = cpu_to_le32(cmd->cdw13); + admin_cmd.common.cdw14 = cpu_to_le32(cmd->cdw14); + admin_cmd.common.cdw15 = cpu_to_le32(cmd->cdw15); + + status = spraid_bsg_map_data(hdev, job, &admin_cmd); + if (status) { + dev_err(hdev->dev, "[%s] err, map data failed\n", __func__); + return status; + } + + status = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, &result[0], + &result[1], timeout); + if (status >= 0) { + job->reply_len = sizeof(result); + memcpy(job->reply, result, sizeof(result)); + } + + dev_info(hdev->dev, "[%s] opcode[0x%x] subopcode[0x%x];" + " status[0x%x] result0[0x%x] result1[0x%x]\n", + __func__, cmd->opcode, cmd->info_0.subopcode, + status, result[0], result[1]); + + spraid_bsg_unmap_data(hdev, job); + + return status; +} + +static int spraid_alloc_ioq_ptcmds(struct spraid_dev *hdev) +{ + int i; + int ptnum = SPRAID_NR_IOQ_PTCMDS; + + INIT_LIST_HEAD(&hdev->ioq_pt_list); + spin_lock_init(&hdev->ioq_pt_lock); + + hdev->ioq_ptcmds = kcalloc_node(ptnum, sizeof(struct spraid_cmd), + GFP_KERNEL, hdev->numa_node); + + if (!hdev->ioq_ptcmds) { + dev_err(hdev->dev, "Alloc ioq_ptcmds failed\n"); + return -ENOMEM; + } + + for (i = 0; i < ptnum; i++) { + hdev->ioq_ptcmds[i].qid = i / SPRAID_PTCMDS_PERQ + 1; + hdev->ioq_ptcmds[i].cid = i % SPRAID_PTCMDS_PERQ + + SPRAID_IO_BLK_MQ_DEPTH; + list_add_tail(&(hdev->ioq_ptcmds[i].list), &hdev->ioq_pt_list); + } + + dev_info(hdev->dev, "Alloc ioq_ptcmds success, ptnum[%d]\n", ptnum); + + return 0; +} + +static void spraid_free_ioq_ptcmds(struct spraid_dev *hdev) +{ + kfree(hdev->ioq_ptcmds); + hdev->ioq_ptcmds = NULL; + + INIT_LIST_HEAD(&hdev->ioq_pt_list); +} + +static int spraid_submit_ioq_sync_cmd(struct spraid_dev *hdev, + struct spraid_ioq_command *cmd, + u32 *result, u32 *reslen, u32 timeout) +{ + int ret; + dma_addr_t sense_dma; + struct spraid_queue *ioq; + void *sense_addr = NULL; + struct spraid_cmd *pt_cmd = spraid_get_cmd(hdev, SPRAID_CMD_IOPT); + + if (!pt_cmd) { + dev_err(hdev->dev, "err, get ioq cmd failed\n"); + return -EFAULT; + } + + timeout = timeout ? timeout : ADMIN_TIMEOUT; + + init_completion(&pt_cmd->cmd_done); + + ioq = &hdev->queues[pt_cmd->qid]; + ret = pt_cmd->cid * SCSI_SENSE_BUFFERSIZE; + sense_addr = ioq->sense + ret; + sense_dma = ioq->sense_dma_addr + ret; + + cmd->common.sense_addr = cpu_to_le64(sense_dma); + cmd->common.sense_len = cpu_to_le16(SCSI_SENSE_BUFFERSIZE); + cmd->common.command_id = pt_cmd->cid; + + spraid_submit_cmd(ioq, cmd); + + if (!wait_for_completion_timeout(&pt_cmd->cmd_done, timeout)) { + dev_err(hdev->dev, "[%s] cid[%d] qid[%d] timeout;" + " opcode[0x%x] subopcode[0x%x]\n", + __func__, pt_cmd->cid, pt_cmd->qid, cmd->common.opcode, + (le32_to_cpu(cmd->common.cdw3[0]) & 0xffff)); + WRITE_ONCE(pt_cmd->state, SPRAID_CMD_TIMEOUT); + spraid_put_cmd(hdev, pt_cmd, SPRAID_CMD_IOPT); + return -EINVAL; + } + + if (result && reslen) { + if ((pt_cmd->status & 0x17f) == 0x101) { + memcpy(result, sense_addr, SCSI_SENSE_BUFFERSIZE); + *reslen = SCSI_SENSE_BUFFERSIZE; + } + } + + spraid_put_cmd(hdev, pt_cmd, SPRAID_CMD_IOPT); + + return pt_cmd->status; +} + +static int spraid_user_ioq_cmd(struct spraid_dev *hdev, struct bsg_job *job) +{ + struct spraid_bsg_request *bsg_req = + (struct spraid_bsg_request *)(job->request); + struct spraid_ioq_passthru_cmd *cmd = &(bsg_req->ioqcmd); + struct spraid_ioq_command ioq_cmd; + int status = 0; + u32 timeout = msecs_to_jiffies(cmd->timeout_ms); + + if (cmd->data_len > PAGE_SIZE) { + dev_err(hdev->dev, "[%s] data len bigger than 4k\n", __func__); + return -EFAULT; + } + + if (hdev->state != SPRAID_LIVE) { + dev_err(hdev->dev, "[%s] err, host state:[%d] is not live\n", + __func__, hdev->state); + return -EBUSY; + } + + dev_info(hdev->dev, "[%s] opcode[0x%x] subopcode[0x%x] init;" + " datalen[%d]\n", + __func__, cmd->opcode, cmd->info_1.subopcode, cmd->data_len); + + memset(&ioq_cmd, 0, sizeof(ioq_cmd)); + ioq_cmd.common.opcode = cmd->opcode; + ioq_cmd.common.flags = cmd->flags; + ioq_cmd.common.hdid = cpu_to_le32(cmd->nsid); + ioq_cmd.common.sense_len = cpu_to_le16(cmd->info_0.res_sense_len); + ioq_cmd.common.cdb_len = cmd->info_0.cdb_len; + ioq_cmd.common.rsvd2 = cmd->info_0.rsvd0; + ioq_cmd.common.cdw3[0] = cpu_to_le32(cmd->cdw3); + ioq_cmd.common.cdw3[1] = cpu_to_le32(cmd->cdw4); + ioq_cmd.common.cdw3[2] = cpu_to_le32(cmd->cdw5); + + ioq_cmd.common.cdw10[0] = cpu_to_le32(cmd->cdw10); + ioq_cmd.common.cdw10[1] = cpu_to_le32(cmd->cdw11); + ioq_cmd.common.cdw10[2] = cpu_to_le32(cmd->cdw12); + ioq_cmd.common.cdw10[3] = cpu_to_le32(cmd->cdw13); + ioq_cmd.common.cdw10[4] = cpu_to_le32(cmd->cdw14); + ioq_cmd.common.cdw10[5] = cpu_to_le32(cmd->data_len); + + memcpy(ioq_cmd.common.cdb, &cmd->cdw16, cmd->info_0.cdb_len); + + ioq_cmd.common.cdw26[0] = cpu_to_le32(cmd->cdw26[0]); + ioq_cmd.common.cdw26[1] = cpu_to_le32(cmd->cdw26[1]); + ioq_cmd.common.cdw26[2] = cpu_to_le32(cmd->cdw26[2]); + ioq_cmd.common.cdw26[3] = cpu_to_le32(cmd->cdw26[3]); + + status = spraid_bsg_map_data(hdev, job, + (struct spraid_admin_command *)&ioq_cmd); + if (status) { + dev_err(hdev->dev, "[%s] err, map data failed\n", __func__); + return status; + } + + status = spraid_submit_ioq_sync_cmd(hdev, &ioq_cmd, job->reply, + &job->reply_len, timeout); + + dev_info(hdev->dev, "[%s] opcode[0x%x] subopcode[0x%x], status[0x%x];" + " reply_len[%d]\n", + __func__, cmd->opcode, cmd->info_1.subopcode, + status, job->reply_len); + + spraid_bsg_unmap_data(hdev, job); + + return status; +} + +static bool spraid_check_scmd_completed(struct scsi_cmnd *scmd) +{ + struct spraid_dev *hdev = shost_priv(scmd->device->host); + struct spraid_iod *iod = scsi_cmd_priv(scmd); + struct spraid_queue *spraidq; + u16 hwq, cid; + + spraid_get_tag_from_scmd(scmd, &hwq, &cid); + spraidq = &hdev->queues[hwq]; + if (READ_ONCE(iod->state) == SPRAID_CMD_COMPLETE + || spraid_poll_cq(spraidq, cid)) { + dev_warn(hdev->dev, "cid[%d] qid[%d] has been completed\n", + cid, spraidq->qid); + return true; + } + return false; +} + +static enum blk_eh_timer_return spraid_scmd_timeout(struct scsi_cmnd *scmd) +{ + struct spraid_iod *iod = scsi_cmd_priv(scmd); + unsigned int timeout = scmd->device->request_queue->rq_timeout; + + if (spraid_check_scmd_completed(scmd)) + goto out; + + if (time_after(jiffies, scmd->jiffies_at_alloc + timeout)) { + if (cmpxchg(&iod->state, + SPRAID_CMD_IN_FLIGHT, + SPRAID_CMD_TIMEOUT) == SPRAID_CMD_IN_FLIGHT) { + return BLK_EH_DONE; + } + } +out: + return BLK_EH_RESET_TIMER; +} + +/* send abort command by admin queue temporary */ +static int spraid_send_abort_cmd(struct spraid_dev *hdev, + u32 hdid, u16 qid, u16 cid) +{ + struct spraid_admin_command admin_cmd; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.abort.opcode = SPRAID_ADMIN_ABORT_CMD; + admin_cmd.abort.hdid = cpu_to_le32(hdid); + admin_cmd.abort.sqid = cpu_to_le16(qid); + admin_cmd.abort.cid = cpu_to_le16(cid); + + return spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); +} + +/* send reset command by admin quueue temporary */ +static int spraid_send_reset_cmd(struct spraid_dev *hdev, int type, u32 hdid) +{ + struct spraid_admin_command admin_cmd; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.reset.opcode = SPRAID_ADMIN_RESET; + admin_cmd.reset.hdid = cpu_to_le32(hdid); + admin_cmd.reset.type = type; + + return spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); +} + +static bool spraid_change_host_state(struct spraid_dev *hdev, + enum spraid_state newstate) +{ + unsigned long flags; + enum spraid_state oldstate; + bool change = false; + + spin_lock_irqsave(&hdev->state_lock, flags); + + oldstate = hdev->state; + switch (newstate) { + case SPRAID_LIVE: + switch (oldstate) { + case SPRAID_NEW: + case SPRAID_RESETTING: + change = true; + break; + default: + break; + } + break; + case SPRAID_RESETTING: + switch (oldstate) { + case SPRAID_LIVE: + change = true; + break; + default: + break; + } + break; + case SPRAID_DELETING: + if (oldstate != SPRAID_DELETING) + change = true; + break; + case SPRAID_DEAD: + switch (oldstate) { + case SPRAID_NEW: + case SPRAID_LIVE: + case SPRAID_RESETTING: + change = true; + break; + default: + break; + } + break; + default: + break; + } + if (change) + hdev->state = newstate; + spin_unlock_irqrestore(&hdev->state_lock, flags); + + dev_info(hdev->dev, "[%s][%d]->[%d], change[%d]\n", + __func__, oldstate, newstate, change); + + return change; +} + +static void spraid_back_fault_cqe(struct spraid_queue *ioq, + struct spraid_completion *cqe) +{ + struct spraid_dev *hdev = ioq->hdev; + struct blk_mq_tags *tags; + struct scsi_cmnd *scmd; + struct spraid_iod *iod; + struct request *req; + + tags = hdev->shost->tag_set.tags[ioq->qid - 1]; + req = blk_mq_tag_to_rq(tags, cqe->cmd_id); + if (unlikely(!req || !blk_mq_request_started(req))) + return; + + scmd = blk_mq_rq_to_pdu(req); + iod = scsi_cmd_priv(scmd); + + set_host_byte(scmd, DID_NO_CONNECT); + if (iod->nsge) + scsi_dma_unmap(scmd); + spraid_free_iod_res(hdev, iod); + scmd->scsi_done(scmd); + dev_warn(hdev->dev, "Back fault CQE, cid[%d] qid[%d]\n", + cqe->cmd_id, ioq->qid); +} + +static void spraid_back_all_io(struct spraid_dev *hdev) +{ + int i, j; + struct spraid_queue *ioq; + struct spraid_completion cqe = { 0 }; + + scsi_block_requests(hdev->shost); + + for (i = 1; i <= hdev->shost->nr_hw_queues; i++) { + ioq = &hdev->queues[i]; + for (j = 0; j < hdev->shost->can_queue; j++) { + cqe.cmd_id = j; + spraid_back_fault_cqe(ioq, &cqe); + } + } + + scsi_unblock_requests(hdev->shost); +} + +static void spraid_dev_disable(struct spraid_dev *hdev, bool shutdown) +{ + struct spraid_queue *adminq = &hdev->queues[0]; + u16 start, end; + unsigned long timeout = jiffies + 600 * HZ; + + if (pci_device_is_present(hdev->pdev)) { + if (shutdown) + spraid_shutdown_ctrl(hdev); + else + spraid_disable_ctrl(hdev); + } + + while (!time_after(jiffies, timeout)) { + if (!pci_device_is_present(hdev->pdev)) { + dev_info(hdev->dev, "[%s] pci_device not present;" + " skip wait\n", __func__); + break; + } + if (!spraid_wait_ready(hdev, hdev->cap, false)) { + dev_info(hdev->dev, + "[%s] wait ready success after reset\n", + __func__); + break; + } + dev_info(hdev->dev, "[%s] waiting csts_rdy ready\n", __func__); + } + + if (hdev->queue_count == 0) { + dev_err(hdev->dev, "[%s] warn, queue has been delete\n", + __func__); + return; + } + + spin_lock_irq(&adminq->cq_lock); + spraid_process_cq(adminq, &start, &end, -1); + spin_unlock_irq(&adminq->cq_lock); + spraid_complete_cqes(adminq, start, end); + + spraid_pci_disable(hdev); + + spraid_back_all_io(hdev); +} + +static void spraid_reset_work(struct work_struct *work) +{ + int ret; + struct spraid_dev *hdev = + container_of(work, struct spraid_dev, reset_work); + + if (hdev->state != SPRAID_RESETTING) { + dev_err(hdev->dev, "[%s] err, host is not reset state\n", + __func__); + return; + } + + dev_info(hdev->dev, "[%s] enter host reset\n", __func__); + + if (hdev->ctrl_config & SPRAID_CC_ENABLE) { + dev_info(hdev->dev, "[%s] start dev_disable\n", __func__); + spraid_dev_disable(hdev, false); + } + + ret = spraid_pci_enable(hdev); + if (ret) + goto out; + + ret = spraid_setup_admin_queue(hdev); + if (ret) + goto pci_disable; + + ret = spraid_setup_io_queues(hdev); + if (ret || hdev->online_queues <= hdev->shost->nr_hw_queues) + goto pci_disable; + + spraid_change_host_state(hdev, SPRAID_LIVE); + + spraid_send_all_aen(hdev); + + return; + +pci_disable: + spraid_pci_disable(hdev); +out: + spraid_change_host_state(hdev, SPRAID_DEAD); + dev_err(hdev->dev, "[%s] err, host reset failed\n", __func__); +} + +static int spraid_reset_work_sync(struct spraid_dev *hdev) +{ + if (!spraid_change_host_state(hdev, SPRAID_RESETTING)) { + dev_info(hdev->dev, "[%s] can't change to reset state\n", + __func__); + return -EBUSY; + } + + if (!queue_work(spraid_wq, &hdev->reset_work)) { + dev_err(hdev->dev, "[%s] err, host is already in reset state\n", + __func__); + return -EBUSY; + } + + flush_work(&hdev->reset_work); + if (hdev->state != SPRAID_LIVE) + return -ENODEV; + + return 0; +} + +static int spraid_wait_abnl_cmd_done(struct spraid_iod *iod) +{ + u16 times = 0; + + do { + if (READ_ONCE(iod->state) == SPRAID_CMD_TMO_COMPLETE) + break; + msleep(500); + times++; + } while (times <= SPRAID_WAIT_ABNL_CMD_TIMEOUT); + + /* wait command completion timeout after abort/reset success */ + if (times >= SPRAID_WAIT_ABNL_CMD_TIMEOUT) + return -ETIMEDOUT; + + return 0; +} + +static int spraid_abort_handler(struct scsi_cmnd *scmd) +{ + struct spraid_dev *hdev = shost_priv(scmd->device->host); + struct spraid_iod *iod = scsi_cmd_priv(scmd); + struct spraid_sdev_hostdata *hostdata; + u16 hwq, cid; + int ret; + + scsi_print_command(scmd); + + if (hdev->state != SPRAID_LIVE || !spraid_wait_abnl_cmd_done(iod) || + spraid_check_scmd_completed(scmd)) + return SUCCESS; + + hostdata = scmd->device->hostdata; + spraid_get_tag_from_scmd(scmd, &hwq, &cid); + + dev_warn(hdev->dev, "cid[%d] qid[%d] timeout, aborting\n", cid, hwq); + ret = spraid_send_abort_cmd(hdev, hostdata->hdid, hwq, cid); + if (ret != ADMIN_ERR_TIMEOUT) { + ret = spraid_wait_abnl_cmd_done(iod); + if (ret) { + dev_warn(hdev->dev, "cid[%d] qid[%d] abort failed;" + " not found\n", cid, hwq); + return FAILED; + } + dev_warn(hdev->dev, "cid[%d] qid[%d] abort succ\n", cid, hwq); + return SUCCESS; + } + dev_warn(hdev->dev, "cid[%d] qid[%d] abort failed, timeout\n", + cid, hwq); + return FAILED; +} + +static int spraid_tgt_reset_handler(struct scsi_cmnd *scmd) +{ + struct spraid_dev *hdev = shost_priv(scmd->device->host); + struct spraid_iod *iod = scsi_cmd_priv(scmd); + struct spraid_sdev_hostdata *hostdata; + u16 hwq, cid; + int ret; + + scsi_print_command(scmd); + + if (hdev->state != SPRAID_LIVE || !spraid_wait_abnl_cmd_done(iod) || + spraid_check_scmd_completed(scmd)) + return SUCCESS; + + hostdata = scmd->device->hostdata; + spraid_get_tag_from_scmd(scmd, &hwq, &cid); + + dev_warn(hdev->dev, "cid[%d] qid[%d] timeout, target reset\n", + cid, hwq); + ret = spraid_send_reset_cmd(hdev, SPRAID_RESET_TARGET, hostdata->hdid); + if (ret == 0) { + ret = spraid_wait_abnl_cmd_done(iod); + if (ret) { + dev_warn(hdev->dev, + "cid[%d] qid[%d]target reset failed;" + " not found\n", cid, hwq); + return FAILED; + } + + dev_warn(hdev->dev, "cid[%d] qid[%d] target reset success\n", + cid, hwq); + return SUCCESS; + } + + dev_warn(hdev->dev, "cid[%d] qid[%d] ret[%d] target reset failed\n", + cid, hwq, ret); + return FAILED; +} + +static int spraid_bus_reset_handler(struct scsi_cmnd *scmd) +{ + struct spraid_dev *hdev = shost_priv(scmd->device->host); + struct spraid_iod *iod = scsi_cmd_priv(scmd); + struct spraid_sdev_hostdata *hostdata; + u16 hwq, cid; + int ret; + + scsi_print_command(scmd); + + if (hdev->state != SPRAID_LIVE || !spraid_wait_abnl_cmd_done(iod) || + spraid_check_scmd_completed(scmd)) + return SUCCESS; + + hostdata = scmd->device->hostdata; + spraid_get_tag_from_scmd(scmd, &hwq, &cid); + + dev_warn(hdev->dev, "cid[%d] qid[%d] timeout, bus reset\n", cid, hwq); + ret = spraid_send_reset_cmd(hdev, SPRAID_RESET_BUS, hostdata->hdid); + if (ret == 0) { + ret = spraid_wait_abnl_cmd_done(iod); + if (ret) { + dev_warn(hdev->dev, + "cid[%d] qid[%d] bus reset failed;" + " not found\n", cid, hwq); + return FAILED; + } + + dev_warn(hdev->dev, "cid[%d] qid[%d] bus reset succ\n", + cid, hwq); + return SUCCESS; + } + + dev_warn(hdev->dev, "cid[%d] qid[%d] ret[%d] bus reset failed\n", + cid, hwq, ret); + return FAILED; +} + +static int spraid_shost_reset_handler(struct scsi_cmnd *scmd) +{ + u16 hwq, cid; + struct spraid_dev *hdev = shost_priv(scmd->device->host); + + scsi_print_command(scmd); + if (hdev->state != SPRAID_LIVE || spraid_check_scmd_completed(scmd)) + return SUCCESS; + + spraid_get_tag_from_scmd(scmd, &hwq, &cid); + dev_warn(hdev->dev, "cid[%d] qid[%d] host reset\n", cid, hwq); + + if (spraid_reset_work_sync(hdev)) { + dev_warn(hdev->dev, "cid[%d] qid[%d] host reset failed\n", + cid, hwq); + return FAILED; + } + + dev_warn(hdev->dev, "cid[%d] qid[%d] host reset success\n", cid, hwq); + + return SUCCESS; +} + +static pci_ers_result_t spraid_pci_error_detected(struct pci_dev *pdev, + pci_channel_state_t state) +{ + struct spraid_dev *hdev = pci_get_drvdata(pdev); + + dev_info(hdev->dev, "enter pci error detect, state:%d\n", state); + + switch (state) { + case pci_channel_io_normal: + dev_warn(hdev->dev, "channel is normal, do nothing\n"); + + return PCI_ERS_RESULT_CAN_RECOVER; + case pci_channel_io_frozen: + dev_warn(hdev->dev, + "channel io frozen, need reset controller\n"); + + scsi_block_requests(hdev->shost); + + spraid_change_host_state(hdev, SPRAID_RESETTING); + + return PCI_ERS_RESULT_NEED_RESET; + case pci_channel_io_perm_failure: + dev_warn(hdev->dev, "channel io failure, request disconnect\n"); + + return PCI_ERS_RESULT_DISCONNECT; + } + + return PCI_ERS_RESULT_NEED_RESET; +} + +static pci_ers_result_t spraid_pci_slot_reset(struct pci_dev *pdev) +{ + struct spraid_dev *hdev = pci_get_drvdata(pdev); + + dev_info(hdev->dev, "restart after slot reset\n"); + + pci_restore_state(pdev); + + if (!queue_work(spraid_wq, &hdev->reset_work)) { + dev_err(hdev->dev, "[%s] err, the device is resetting state\n", + __func__); + return PCI_ERS_RESULT_NONE; + } + + flush_work(&hdev->reset_work); + + scsi_unblock_requests(hdev->shost); + + return PCI_ERS_RESULT_RECOVERED; +} + +static void spraid_reset_done(struct pci_dev *pdev) +{ + struct spraid_dev *hdev = pci_get_drvdata(pdev); + + dev_info(hdev->dev, "enter spraid reset done\n"); +} + +static ssize_t csts_pp_show(struct device *cdev, + struct device_attribute *attr, char *buf) +{ + struct Scsi_Host *shost = class_to_shost(cdev); + struct spraid_dev *hdev = shost_priv(shost); + int ret = -1; + + if (pci_device_is_present(hdev->pdev)) { + ret = (readl(hdev->bar + SPRAID_REG_CSTS) + & SPRAID_CSTS_PP_MASK); + ret >>= SPRAID_CSTS_PP_SHIFT; + } + + return snprintf(buf, PAGE_SIZE, "%d\n", ret); +} + +static ssize_t csts_shst_show(struct device *cdev, + struct device_attribute *attr, char *buf) +{ + struct Scsi_Host *shost = class_to_shost(cdev); + struct spraid_dev *hdev = shost_priv(shost); + int ret = -1; + + if (pci_device_is_present(hdev->pdev)) { + ret = (readl(hdev->bar + SPRAID_REG_CSTS) + & SPRAID_CSTS_SHST_MASK); + ret >>= SPRAID_CSTS_SHST_SHIFT; + } + + return snprintf(buf, PAGE_SIZE, "%d\n", ret); +} + +static ssize_t csts_cfs_show(struct device *cdev, + struct device_attribute *attr, char *buf) +{ + struct Scsi_Host *shost = class_to_shost(cdev); + struct spraid_dev *hdev = shost_priv(shost); + int ret = -1; + + if (pci_device_is_present(hdev->pdev)) { + ret = (readl(hdev->bar + SPRAID_REG_CSTS) + & SPRAID_CSTS_CFS_MASK); + ret >>= SPRAID_CSTS_CFS_SHIFT; + } + + return snprintf(buf, PAGE_SIZE, "%d\n", ret); +} + +static ssize_t csts_rdy_show(struct device *cdev, + struct device_attribute *attr, char *buf) +{ + struct Scsi_Host *shost = class_to_shost(cdev); + struct spraid_dev *hdev = shost_priv(shost); + int ret = -1; + + if (pci_device_is_present(hdev->pdev)) + ret = (readl(hdev->bar + SPRAID_REG_CSTS) & SPRAID_CSTS_RDY); + + return snprintf(buf, PAGE_SIZE, "%d\n", ret); +} + +static ssize_t fw_version_show(struct device *cdev, + struct device_attribute *attr, char *buf) +{ + struct Scsi_Host *shost = class_to_shost(cdev); + struct spraid_dev *hdev = shost_priv(shost); + + return snprintf(buf, PAGE_SIZE, "%s\n", hdev->ctrl_info->fr); +} + +static DEVICE_ATTR_RO(csts_pp); +static DEVICE_ATTR_RO(csts_shst); +static DEVICE_ATTR_RO(csts_cfs); +static DEVICE_ATTR_RO(csts_rdy); +static DEVICE_ATTR_RO(fw_version); + +static struct device_attribute *spraid_host_attrs[] = { + &dev_attr_csts_pp, + &dev_attr_csts_shst, + &dev_attr_csts_cfs, + &dev_attr_csts_rdy, + &dev_attr_fw_version, + NULL, +}; + +static int spraid_get_vd_info(struct spraid_dev *hdev, + struct spraid_vd_info *vd_info, u16 vid) +{ + struct spraid_admin_command admin_cmd; + u8 *data_ptr = NULL; + dma_addr_t data_dma = 0; + int ret; + + data_ptr = dma_alloc_coherent(hdev->dev, PAGE_SIZE, + &data_dma, GFP_KERNEL); + if (!data_ptr) + return -ENOMEM; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.usr_cmd.opcode = USR_CMD_READ; + admin_cmd.usr_cmd.info_0.subopcode = cpu_to_le16(USR_CMD_VDINFO); + admin_cmd.usr_cmd.info_1.data_len = cpu_to_le16(USR_CMD_RDLEN); + admin_cmd.usr_cmd.info_1.param_len = cpu_to_le16(VDINFO_PARAM_LEN); + admin_cmd.usr_cmd.cdw10 = cpu_to_le32(vid); + admin_cmd.common.dptr.prp1 = cpu_to_le64(data_dma); + + ret = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); + if (!ret) + memcpy(vd_info, data_ptr, sizeof(struct spraid_vd_info)); + + dma_free_coherent(hdev->dev, PAGE_SIZE, data_ptr, data_dma); + + return ret; +} + +static int spraid_get_bgtask(struct spraid_dev *hdev, + struct spraid_bgtask *bgtask) +{ + struct spraid_admin_command admin_cmd; + u8 *data_ptr = NULL; + dma_addr_t data_dma = 0; + int ret; + + data_ptr = dma_alloc_coherent(hdev->dev, PAGE_SIZE, + &data_dma, GFP_KERNEL); + if (!data_ptr) + return -ENOMEM; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.usr_cmd.opcode = USR_CMD_READ; + admin_cmd.usr_cmd.info_0.subopcode = cpu_to_le16(USR_CMD_BGTASK); + admin_cmd.usr_cmd.info_1.data_len = cpu_to_le16(USR_CMD_RDLEN); + admin_cmd.common.dptr.prp1 = cpu_to_le64(data_dma); + + ret = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); + if (!ret) + memcpy(bgtask, data_ptr, sizeof(struct spraid_bgtask)); + + dma_free_coherent(hdev->dev, PAGE_SIZE, data_ptr, data_dma); + + return ret; +} + +static ssize_t raid_level_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct scsi_device *sdev; + struct spraid_dev *hdev; + struct spraid_vd_info *vd_info; + struct spraid_sdev_hostdata *hostdata; + int ret; + + sdev = to_scsi_device(dev); + hdev = shost_priv(sdev->host); + hostdata = sdev->hostdata; + + vd_info = kmalloc(sizeof(*vd_info), GFP_KERNEL); + if (!vd_info || !SPRAID_DEV_INFO_ATTR_VD(hostdata->attr)) + return snprintf(buf, PAGE_SIZE, "NA\n"); + + ret = spraid_get_vd_info(hdev, vd_info, sdev->id); + if (ret) + vd_info->rg_level = ARRAY_SIZE(raid_levels) - 1; + + ret = (vd_info->rg_level < ARRAY_SIZE(raid_levels)) ? + vd_info->rg_level : (ARRAY_SIZE(raid_levels) - 1); + + kfree(vd_info); + + return snprintf(buf, PAGE_SIZE, "RAID-%s\n", raid_levels[ret]); +} + +static ssize_t raid_state_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct scsi_device *sdev; + struct spraid_dev *hdev; + struct spraid_vd_info *vd_info; + struct spraid_sdev_hostdata *hostdata; + int ret; + + sdev = to_scsi_device(dev); + hdev = shost_priv(sdev->host); + hostdata = sdev->hostdata; + + vd_info = kmalloc(sizeof(*vd_info), GFP_KERNEL); + if (!vd_info || !SPRAID_DEV_INFO_ATTR_VD(hostdata->attr)) + return snprintf(buf, PAGE_SIZE, "NA\n"); + + ret = spraid_get_vd_info(hdev, vd_info, sdev->id); + if (ret) { + vd_info->vd_status = 0; + vd_info->rg_id = 0xff; + } + + ret = (vd_info->vd_status < ARRAY_SIZE(raid_states)) ? + vd_info->vd_status : 0; + + kfree(vd_info); + + return snprintf(buf, PAGE_SIZE, "%s\n", raid_states[ret]); +} + +static ssize_t raid_resync_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct scsi_device *sdev; + struct spraid_dev *hdev; + struct spraid_vd_info *vd_info; + struct spraid_bgtask *bgtask; + struct spraid_sdev_hostdata *hostdata; + u8 rg_id, i, progress = 0; + int ret; + + sdev = to_scsi_device(dev); + hdev = shost_priv(sdev->host); + hostdata = sdev->hostdata; + + vd_info = kmalloc(sizeof(*vd_info), GFP_KERNEL); + if (!vd_info || !SPRAID_DEV_INFO_ATTR_VD(hostdata->attr)) + return snprintf(buf, PAGE_SIZE, "NA\n"); + + ret = spraid_get_vd_info(hdev, vd_info, sdev->id); + if (ret) + goto out; + + rg_id = vd_info->rg_id; + + bgtask = (struct spraid_bgtask *)vd_info; + ret = spraid_get_bgtask(hdev, bgtask); + if (ret) + goto out; + for (i = 0; i < bgtask->task_num; i++) { + if ((bgtask->bgtask[i].type == BGTASK_TYPE_REBUILD) && + (le16_to_cpu(bgtask->bgtask[i].vd_id) == rg_id)) + progress = bgtask->bgtask[i].progress; + } + +out: + kfree(vd_info); + return snprintf(buf, PAGE_SIZE, "%d\n", progress); +} + +static DEVICE_ATTR_RO(raid_level); +static DEVICE_ATTR_RO(raid_state); +static DEVICE_ATTR_RO(raid_resync); + +static struct device_attribute *spraid_dev_attrs[] = { + &dev_attr_raid_level, + &dev_attr_raid_state, + &dev_attr_raid_resync, + NULL, +}; + +static struct pci_error_handlers spraid_err_handler = { + .error_detected = spraid_pci_error_detected, + .slot_reset = spraid_pci_slot_reset, + .reset_done = spraid_reset_done, +}; + +static int spraid_sysfs_host_reset(struct Scsi_Host *shost, int reset_type) +{ + int ret; + struct spraid_dev *hdev = shost_priv(shost); + + dev_info(hdev->dev, "[%s] start sysfs host reset cmd\n", __func__); + ret = spraid_reset_work_sync(hdev); + dev_info(hdev->dev, "[%s] stop sysfs host reset cmd[%d]\n", + __func__, ret); + + return ret; +} + +static struct scsi_host_template spraid_driver_template = { + .module = THIS_MODULE, + .name = "Ramaxel Logic spraid driver", + .proc_name = "spraid", + .queuecommand = spraid_queue_command, + .slave_alloc = spraid_slave_alloc, + .slave_destroy = spraid_slave_destroy, + .slave_configure = spraid_slave_configure, + .eh_timed_out = spraid_scmd_timeout, + .eh_abort_handler = spraid_abort_handler, + .eh_target_reset_handler = spraid_tgt_reset_handler, + .eh_bus_reset_handler = spraid_bus_reset_handler, + .eh_host_reset_handler = spraid_shost_reset_handler, + .change_queue_depth = scsi_change_queue_depth, + .this_id = -1, + .shost_attrs = spraid_host_attrs, + .sdev_attrs = spraid_dev_attrs, + .host_reset = spraid_sysfs_host_reset, +}; + +static void spraid_shutdown(struct pci_dev *pdev) +{ + struct spraid_dev *hdev = pci_get_drvdata(pdev); + + spraid_remove_io_queues(hdev); + spraid_disable_admin_queue(hdev, true); +} + +/* bsg dispatch user command */ +static int spraid_bsg_host_dispatch(struct bsg_job *job) +{ + struct Scsi_Host *shost = dev_to_shost(job->dev); + struct spraid_dev *hdev = shost_priv(shost); + struct request *rq = blk_mq_rq_from_pdu(job); + struct spraid_bsg_request *bsg_req = job->request; + int ret = 0; + + dev_info(hdev->dev, "[%s] msgcode[%d], msglen[%d], timeout[%d];" + " req_nsge[%d], req_len[%d]\n", + __func__, bsg_req->msgcode, job->request_len, + rq->timeout, job->request_payload.sg_cnt, + job->request_payload.payload_len); + + job->reply_len = 0; + + switch (bsg_req->msgcode) { + case SPRAID_BSG_ADM: + ret = spraid_user_admin_cmd(hdev, job); + break; + case SPRAID_BSG_IOQ: + ret = spraid_user_ioq_cmd(hdev, job); + break; + default: + dev_info(hdev->dev, "[%s] unsupport msgcode[%d]\n", + __func__, bsg_req->msgcode); + break; + } + + if (ret > 0) + ret = ret | (ret << 8); + + bsg_job_done(job, ret, 0); + return 0; +} + +static inline void spraid_remove_bsg(struct spraid_dev *hdev) +{ + if (hdev->bsg_queue) { + bsg_unregister_queue(hdev->bsg_queue); + blk_cleanup_queue(hdev->bsg_queue); + } +} +static int spraid_probe(struct pci_dev *pdev, const struct pci_device_id *id) +{ + struct spraid_dev *hdev; + struct Scsi_Host *shost; + int node, ret; + char bsg_name[15]; + + shost = scsi_host_alloc(&spraid_driver_template, sizeof(*hdev)); + if (!shost) { + dev_err(&pdev->dev, "Failed to allocate scsi host\n"); + return -ENOMEM; + } + hdev = shost_priv(shost); + hdev->pdev = pdev; + hdev->dev = get_device(&pdev->dev); + + node = dev_to_node(hdev->dev); + if (node == NUMA_NO_NODE) { + node = first_memory_node; + set_dev_node(hdev->dev, node); + } + hdev->numa_node = node; + hdev->shost = shost; + pci_set_drvdata(pdev, hdev); + + ret = spraid_dev_map(hdev); + if (ret) + goto put_dev; + + init_rwsem(&hdev->devices_rwsem); + INIT_WORK(&hdev->scan_work, spraid_scan_work); + INIT_WORK(&hdev->timesyn_work, spraid_timesyn_work); + INIT_WORK(&hdev->reset_work, spraid_reset_work); + INIT_WORK(&hdev->fw_act_work, spraid_fw_act_work); + spin_lock_init(&hdev->state_lock); + + ret = spraid_alloc_resources(hdev); + if (ret) + goto dev_unmap; + + ret = spraid_pci_enable(hdev); + if (ret) + goto resources_free; + + ret = spraid_setup_admin_queue(hdev); + if (ret) + goto pci_disable; + + ret = spraid_init_ctrl_info(hdev); + if (ret) + goto disable_admin_q; + + ret = spraid_alloc_iod_ext_mem_pool(hdev); + if (ret) + goto disable_admin_q; + + ret = spraid_setup_io_queues(hdev); + if (ret) + goto free_iod_mempool; + + spraid_shost_init(hdev); + + ret = scsi_add_host(hdev->shost, hdev->dev); + if (ret) { + dev_err(hdev->dev, "Add shost to system failed, ret: %d\n", + ret); + goto remove_io_queues; + } + + snprintf(bsg_name, sizeof(bsg_name), "spraid%d", shost->host_no); + hdev->bsg_queue = bsg_setup_queue(&shost->shost_gendev, bsg_name, + spraid_bsg_host_dispatch, + spraid_cmd_size(hdev, true, false)); + if (IS_ERR(hdev->bsg_queue)) { + dev_err(hdev->dev, "err, setup bsg failed\n"); + hdev->bsg_queue = NULL; + goto remove_io_queues; + } + + if (hdev->online_queues == SPRAID_ADMIN_QUEUE_NUM) { + dev_warn(hdev->dev, "warn only admin queue can be used\n"); + return 0; + } + + hdev->state = SPRAID_LIVE; + + spraid_send_all_aen(hdev); + + ret = spraid_dev_list_init(hdev); + if (ret) + goto remove_bsg; + + ret = spraid_configure_timestamp(hdev); + if (ret) + dev_warn(hdev->dev, "init set timestamp failed\n"); + + ret = spraid_alloc_ioq_ptcmds(hdev); + if (ret) + goto remove_bsg; + + scsi_scan_host(hdev->shost); + + return 0; + +remove_bsg: + spraid_remove_bsg(hdev); +remove_io_queues: + spraid_remove_io_queues(hdev); +free_iod_mempool: + spraid_free_iod_ext_mem_pool(hdev); +disable_admin_q: + spraid_disable_admin_queue(hdev, false); +pci_disable: + spraid_pci_disable(hdev); +resources_free: + spraid_free_resources(hdev); +dev_unmap: + spraid_dev_unmap(hdev); +put_dev: + put_device(hdev->dev); + scsi_host_put(shost); + + return -ENODEV; +} + +static void spraid_remove(struct pci_dev *pdev) +{ + struct spraid_dev *hdev = pci_get_drvdata(pdev); + struct Scsi_Host *shost = hdev->shost; + + dev_info(hdev->dev, "enter spraid remove\n"); + + spraid_change_host_state(hdev, SPRAID_DELETING); + flush_work(&hdev->reset_work); + + if (!pci_device_is_present(pdev)) + spraid_back_all_io(hdev); + + spraid_remove_bsg(hdev); + scsi_remove_host(shost); + spraid_free_ioq_ptcmds(hdev); + kfree(hdev->devices); + spraid_remove_io_queues(hdev); + spraid_free_iod_ext_mem_pool(hdev); + spraid_disable_admin_queue(hdev, false); + spraid_pci_disable(hdev); + spraid_free_resources(hdev); + spraid_dev_unmap(hdev); + put_device(hdev->dev); + scsi_host_put(shost); + + dev_info(hdev->dev, "exit spraid remove\n"); +} + +static const struct pci_device_id spraid_id_table[] = { + { PCI_DEVICE(PCI_VENDOR_ID_RAMAXEL_LOGIC, + SPRAID_SERVER_DEVICE_HBA_DID) }, + { PCI_DEVICE(PCI_VENDOR_ID_RAMAXEL_LOGIC, + SPRAID_SERVER_DEVICE_RAID_DID) }, + { 0, } +}; +MODULE_DEVICE_TABLE(pci, spraid_id_table); + +static struct pci_driver spraid_driver = { + .name = "spraid", + .id_table = spraid_id_table, + .probe = spraid_probe, + .remove = spraid_remove, + .shutdown = spraid_shutdown, + .err_handler = &spraid_err_handler, +}; + +static int __init spraid_init(void) +{ + int ret; + + spraid_wq = alloc_workqueue("spraid-wq", WQ_UNBOUND | WQ_MEM_RECLAIM | + WQ_SYSFS, 0); + if (!spraid_wq) + return -ENOMEM; + + spraid_class = class_create(THIS_MODULE, "spraid"); + if (IS_ERR(spraid_class)) { + ret = PTR_ERR(spraid_class); + goto destroy_wq; + } + + ret = pci_register_driver(&spraid_driver); + if (ret < 0) + goto destroy_class; + + return 0; + +destroy_class: + class_destroy(spraid_class); +destroy_wq: + destroy_workqueue(spraid_wq); + + return ret; +} + +static void __exit spraid_exit(void) +{ + pci_unregister_driver(&spraid_driver); + class_destroy(spraid_class); + destroy_workqueue(spraid_wq); + ida_destroy(&spraid_instance_ida); +} + +MODULE_AUTHOR("songyl(a)ramaxel.com"); +MODULE_DESCRIPTION("Ramaxel Memory Technology SPraid Driver"); +MODULE_LICENSE("GPL"); +MODULE_VERSION(SPRAID_DRV_VERSION); +module_init(spraid_init); +module_exit(spraid_exit); -- 2.25.1

1 1

[PATCH OLK-5.10 1/2] reboot: allow to specify reboot mode via
by Hongyu Li 22 Dec '21

22 Dec '21

From: Matteo Croce <mcroce(a)microsoft.com> maillist inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4BULZ CVE: NA Reference: https://lore.kernel.org/all/20201110202746.9690-1-mcroce@linux.microsoft.co… ---------------------------------------------------------------------- The kernel cmdline reboot= option offers some sort of control on how the reboot is issued. Add handles in sysfs to allow setting these reboot options, so they can be changed when the system is booted, other than at boot time. The handlers are under <sysfs>/kernel/reboot, can be read to get the current configuration and written to alter it. # cd /sys/kernel/reboot/ # grep . * cpu:0 force:0 mode:cold type:acpi # echo 2 >cpu # echo yes >force # echo soft >mode # echo bios >type # grep . * cpu:2 force:1 mode:soft type:bios Before setting anything, check for CAP_SYS_BOOT capability, so it's possible to allow an unpriviledged process to change these settings simply by relaxing the handles permissions, without opening them to the world. Signed-off-by: Matteo Croce <mcroce(a)microsoft.com> Signed-off-by: Hongyu Li <543306408(a)qq.com> --- Documentation/ABI/testing/sysfs-kernel-reboot | 32 +++ kernel/reboot.c | 206 ++++++++++++++++++ 2 files changed, 238 insertions(+) create mode 100644 Documentation/ABI/testing/sysfs-kernel-reboot diff --git a/Documentation/ABI/testing/sysfs-kernel-reboot b/Documentation/ABI/testing/sysfs-kernel-reboot new file mode 100644 index 000000000000..837330fb2511 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-kernel-reboot @@ -0,0 +1,32 @@ +What: /sys/kernel/reboot +Date: November 2020 +KernelVersion: 5.11 +Contact: Matteo Croce <mcroce(a)microsoft.com> +Description: Interface to set the kernel reboot behavior, similarly to + what can be done via the reboot= cmdline option. + (see Documentation/admin-guide/kernel-parameters.txt) + +What: /sys/kernel/reboot/mode +Date: November 2020 +KernelVersion: 5.11 +Contact: Matteo Croce <mcroce(a)microsoft.com> +Description: Reboot mode. Valid values are: cold warm hard soft gpio + +What: /sys/kernel/reboot/type +Date: November 2020 +KernelVersion: 5.11 +Contact: Matteo Croce <mcroce(a)microsoft.com> +Description: Reboot type. Valid values are: bios acpi kbd triple efi pci + +What: /sys/kernel/reboot/cpu +Date: November 2020 +KernelVersion: 5.11 +Contact: Matteo Croce <mcroce(a)microsoft.com> +Description: CPU number to use to reboot. + +What: /sys/kernel/reboot/force +Date: November 2020 +KernelVersion: 5.11 +Contact: Matteo Croce <mcroce(a)microsoft.com> +Description: Don't wait for any other CPUs on reboot and + avoid anything that could hang. diff --git a/kernel/reboot.c b/kernel/reboot.c index af6f23d8bea1..778979d92dc7 100644 --- a/kernel/reboot.c +++ b/kernel/reboot.c @@ -594,3 +594,209 @@ static int __init reboot_setup(char *str) return 1; } __setup("reboot=", reboot_setup); + +#ifdef CONFIG_SYSFS + +#define REBOOT_COLD_STR "cold" +#define REBOOT_WARM_STR "warm" +#define REBOOT_HARD_STR "hard" +#define REBOOT_SOFT_STR "soft" +#define REBOOT_GPIO_STR "gpio" +#define REBOOT_UNDEFINED_STR "undefined" + +#define BOOT_TRIPLE_STR "triple" +#define BOOT_KBD_STR "kbd" +#define BOOT_BIOS_STR "bios" +#define BOOT_ACPI_STR "acpi" +#define BOOT_EFI_STR "efi" +#define BOOT_CF9_FORCE_STR "cf9_force" +#define BOOT_CF9_SAFE_STR "cf9_safe" + +static ssize_t mode_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) +{ + const char *val; + + switch (reboot_mode) { + case REBOOT_COLD: + val = REBOOT_COLD_STR; + break; + case REBOOT_WARM: + val = REBOOT_WARM_STR; + break; + case REBOOT_HARD: + val = REBOOT_HARD_STR; + break; + case REBOOT_SOFT: + val = REBOOT_SOFT_STR; + break; + case REBOOT_GPIO: + val = REBOOT_GPIO_STR; + break; + default: + val = REBOOT_UNDEFINED_STR; + } + + return sprintf(buf, "%s\n", val); +} +static ssize_t mode_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t count) +{ + if (!capable(CAP_SYS_BOOT)) + return -EPERM; + + if (!strncmp(buf, REBOOT_COLD_STR, strlen(REBOOT_COLD_STR))) + reboot_mode = REBOOT_COLD; + else if (!strncmp(buf, REBOOT_WARM_STR, strlen(REBOOT_WARM_STR))) + reboot_mode = REBOOT_WARM; + else if (!strncmp(buf, REBOOT_HARD_STR, strlen(REBOOT_HARD_STR))) + reboot_mode = REBOOT_HARD; + else if (!strncmp(buf, REBOOT_SOFT_STR, strlen(REBOOT_SOFT_STR))) + reboot_mode = REBOOT_SOFT; + else if (!strncmp(buf, REBOOT_GPIO_STR, strlen(REBOOT_GPIO_STR))) + reboot_mode = REBOOT_GPIO; + else + return -EINVAL; + + return count; +} +static struct kobj_attribute reboot_mode_attr = __ATTR_RW(mode); + +static ssize_t type_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) +{ + const char *val; + + switch (reboot_type) { + case BOOT_TRIPLE: + val = BOOT_TRIPLE_STR; + break; + case BOOT_KBD: + val = BOOT_KBD_STR; + break; + case BOOT_BIOS: + val = BOOT_BIOS_STR; + break; + case BOOT_ACPI: + val = BOOT_ACPI_STR; + break; + case BOOT_EFI: + val = BOOT_EFI_STR; + break; + case BOOT_CF9_FORCE: + val = BOOT_CF9_FORCE_STR; + break; + case BOOT_CF9_SAFE: + val = BOOT_CF9_SAFE_STR; + break; + default: + val = REBOOT_UNDEFINED_STR; + } + + return sprintf(buf, "%s\n", val); +} +static ssize_t type_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t count) +{ + if (!capable(CAP_SYS_BOOT)) + return -EPERM; + + if (!strncmp(buf, BOOT_TRIPLE_STR, strlen(BOOT_TRIPLE_STR))) + reboot_mode = BOOT_TRIPLE; + else if (!strncmp(buf, BOOT_KBD_STR, strlen(BOOT_KBD_STR))) + reboot_mode = BOOT_KBD; + else if (!strncmp(buf, BOOT_BIOS_STR, strlen(BOOT_BIOS_STR))) + reboot_mode = BOOT_BIOS; + else if (!strncmp(buf, BOOT_ACPI_STR, strlen(BOOT_ACPI_STR))) + reboot_mode = BOOT_ACPI; + else if (!strncmp(buf, BOOT_EFI_STR, strlen(BOOT_EFI_STR))) + reboot_mode = BOOT_EFI; + else if (!strncmp(buf, BOOT_CF9_FORCE_STR, strlen(BOOT_CF9_FORCE_STR))) + reboot_mode = BOOT_CF9_FORCE; + else if (!strncmp(buf, BOOT_CF9_SAFE_STR, strlen(BOOT_CF9_SAFE_STR))) + reboot_mode = BOOT_CF9_SAFE; + else + return -EINVAL; + + return count; +} +static struct kobj_attribute reboot_type_attr = __ATTR_RW(type); + +static ssize_t cpu_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%d\n", reboot_cpu); +} +static ssize_t cpu_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t count) +{ + unsigned int cpunum; + int rc; + + if (!capable(CAP_SYS_BOOT)) + return -EPERM; + + rc = kstrtouint(buf, 0, &cpunum); + + if (rc) + return rc; + + if (cpunum >= num_possible_cpus()) + return -ERANGE; + + reboot_cpu = cpunum; + + return count; +} +static struct kobj_attribute reboot_cpu_attr = __ATTR_RW(cpu); + +static ssize_t force_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%d\n", reboot_force); +} +static ssize_t force_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t count) +{ + bool res; + + if (!capable(CAP_SYS_BOOT)) + return -EPERM; + + if (kstrtobool(buf, &res)) + return -EINVAL; + + reboot_force = res; + + return count; +} +static struct kobj_attribute reboot_force_attr = __ATTR_RW(force); + +static struct attribute *reboot_attrs[] = { + &reboot_mode_attr.attr, + &reboot_type_attr.attr, + &reboot_cpu_attr.attr, + &reboot_force_attr.attr, + NULL, +}; + +static const struct attribute_group reboot_attr_group = { + .attrs = reboot_attrs, +}; + +static int __init reboot_ksysfs_init(void) +{ + struct kobject *reboot_kobj; + int ret; + + reboot_kobj = kobject_create_and_add("reboot", kernel_kobj); + if (!reboot_kobj) + return -ENOMEM; + + ret = sysfs_create_group(reboot_kobj, &reboot_attr_group); + if (ret) { + kobject_put(reboot_kobj); + return ret; + } + + return 0; +} +late_initcall(reboot_ksysfs_init); + +#endif -- 2.17.1

3 2

[PATCH OLK-5.10 2/2] reboot: Fix variable assignments in
by Hongyu Li 22 Dec '21

22 Dec '21

From: Nathan Chancellor <natechancellor(a)gmail.com> maillist inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4BULZ CVE: NA Reference: https://lore.kernel.org/all/20201112035023.974748-1-natechancellor@gmail.co… ---------------------------------------------------------------------- Clang warns: kernel/reboot.c:707:17: warning: implicit conversion from enumeration type 'enum reboot_type' to different enumeration type 'enum reboot_mode' [-Wenum-conversion] reboot_mode = BOOT_TRIPLE; ~ ^~~~~~~~~~~ kernel/reboot.c:709:17: warning: implicit conversion from enumeration type 'enum reboot_type' to different enumeration type 'enum reboot_mode' [-Wenum-conversion] reboot_mode = BOOT_KBD; ~ ^~~~~~~~ kernel/reboot.c:711:17: warning: implicit conversion from enumeration type 'enum reboot_type' to different enumeration type 'enum reboot_mode' [-Wenum-conversion] reboot_mode = BOOT_BIOS; ~ ^~~~~~~~~ kernel/reboot.c:713:17: warning: implicit conversion from enumeration type 'enum reboot_type' to different enumeration type 'enum reboot_mode' [-Wenum-conversion] reboot_mode = BOOT_ACPI; ~ ^~~~~~~~~ kernel/reboot.c:715:17: warning: implicit conversion from enumeration type 'enum reboot_type' to different enumeration type 'enum reboot_mode' [-Wenum-conversion] reboot_mode = BOOT_EFI; ~ ^~~~~~~~ kernel/reboot.c:717:17: warning: implicit conversion from enumeration type 'enum reboot_type' to different enumeration type 'enum reboot_mode' [-Wenum-conversion] reboot_mode = BOOT_CF9_FORCE; ~ ^~~~~~~~~~~~~~ kernel/reboot.c:719:17: warning: implicit conversion from enumeration type 'enum reboot_type' to different enumeration type 'enum reboot_mode' [-Wenum-conversion] reboot_mode = BOOT_CF9_SAFE; ~ ^~~~~~~~~~~~~ 7 warnings generated. It seems that these assignment should be to reboot_type, not reboot_mode. Fix it so there are no more warnings and the code works properly. Fixes: eab8da48579d ("reboot: allow to specify reboot mode via sysfs") Link: https://github.com/ClangBuiltLinux/linux/issues/1197 Signed-off-by: Nathan Chancellor <natechancellor(a)gmail.com> Reviewed-and-tested-by: Matteo Croce <mcroce(a)microsoft.com> Reviewed-by: Petr Mladek <pmladek(a)suse.com> Signed-off-by: Hongyu Li <543306408(a)qq.com> --- kernel/reboot.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/kernel/reboot.c b/kernel/reboot.c index 778979d92dc7..7a445c710f9a 100644 --- a/kernel/reboot.c +++ b/kernel/reboot.c @@ -700,19 +700,19 @@ static ssize_t type_store(struct kobject *kobj, struct kobj_attribute *attr, return -EPERM; if (!strncmp(buf, BOOT_TRIPLE_STR, strlen(BOOT_TRIPLE_STR))) - reboot_mode = BOOT_TRIPLE; + reboot_type = BOOT_TRIPLE; else if (!strncmp(buf, BOOT_KBD_STR, strlen(BOOT_KBD_STR))) - reboot_mode = BOOT_KBD; + reboot_type = BOOT_KBD; else if (!strncmp(buf, BOOT_BIOS_STR, strlen(BOOT_BIOS_STR))) - reboot_mode = BOOT_BIOS; + reboot_type = BOOT_BIOS; else if (!strncmp(buf, BOOT_ACPI_STR, strlen(BOOT_ACPI_STR))) - reboot_mode = BOOT_ACPI; + reboot_type = BOOT_ACPI; else if (!strncmp(buf, BOOT_EFI_STR, strlen(BOOT_EFI_STR))) - reboot_mode = BOOT_EFI; + reboot_type = BOOT_EFI; else if (!strncmp(buf, BOOT_CF9_FORCE_STR, strlen(BOOT_CF9_FORCE_STR))) - reboot_mode = BOOT_CF9_FORCE; + reboot_type = BOOT_CF9_FORCE; else if (!strncmp(buf, BOOT_CF9_SAFE_STR, strlen(BOOT_CF9_SAFE_STR))) - reboot_mode = BOOT_CF9_SAFE; + reboot_type = BOOT_CF9_SAFE; else return -EINVAL; -- 2.17.1

2 1

[PATCH openEuler-1.0-LTS v2] scsi:spraid: support Ramaxel's spraid driver
by Yanling Song 22 Dec '21

22 Dec '21

Ramaxel inclusion category: features bugzilla: https://gitee.com/openeuler/kernel/issues/I4NJIB CVE: NA v1->v2: 1. Add deconfig for arm64 and x86 Support Ramaxel's SPRxxx Raid controller Signed-off-by: Yanling Song <songyl(a)ramaxel.com> Reviewed-by: Jiang Yu<yujiang(a)ramaxel.com> --- arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + drivers/scsi/Kconfig | 1 + drivers/scsi/Makefile | 1 + drivers/scsi/spraid/Kconfig | 13 + drivers/scsi/spraid/Makefile | 7 + drivers/scsi/spraid/spraid.h | 746 +++++ drivers/scsi/spraid/spraid_main.c | 3875 ++++++++++++++++++++++++ 8 files changed, 4645 insertions(+) create mode 100644 drivers/scsi/spraid/Kconfig create mode 100644 drivers/scsi/spraid/Makefile create mode 100644 drivers/scsi/spraid/spraid.h create mode 100644 drivers/scsi/spraid/spraid_main.c diff --git a/arch/arm64/configs/openeuler_defconfig b/arch/arm64/configs/openeuler_defconfig index d2167c80757f..47b0931b91bf 100644 --- a/arch/arm64/configs/openeuler_defconfig +++ b/arch/arm64/configs/openeuler_defconfig @@ -2143,6 +2143,7 @@ CONFIG_SCSI_MPT2SAS_MAX_SGE=128 CONFIG_SCSI_MPT3SAS_MAX_SGE=128 CONFIG_SCSI_MPT2SAS=m CONFIG_SCSI_SMARTPQI=m +CONFIG_RAMAXEL_SPRAID=m # CONFIG_SCSI_UFSHCD is not set # CONFIG_SCSI_HPTIOP is not set CONFIG_LIBFC=m diff --git a/arch/x86/configs/openeuler_defconfig b/arch/x86/configs/openeuler_defconfig index 7043426d9780..786186288fea 100644 --- a/arch/x86/configs/openeuler_defconfig +++ b/arch/x86/configs/openeuler_defconfig @@ -2182,6 +2182,7 @@ CONFIG_SCSI_MPT2SAS_MAX_SGE=128 CONFIG_SCSI_MPT3SAS_MAX_SGE=128 CONFIG_SCSI_MPT2SAS=m CONFIG_SCSI_SMARTPQI=m +CONFIG_RAMAXEL_SPRAID=m # CONFIG_SCSI_UFSHCD is not set # CONFIG_SCSI_HPTIOP is not set # CONFIG_SCSI_BUSLOGIC is not set diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig index 8450484184e3..63d2aaa22834 100644 --- a/drivers/scsi/Kconfig +++ b/drivers/scsi/Kconfig @@ -522,6 +522,7 @@ source "drivers/scsi/megaraid/Kconfig.megaraid" source "drivers/scsi/mpt3sas/Kconfig" source "drivers/scsi/smartpqi/Kconfig" source "drivers/scsi/ufs/Kconfig" +source "drivers/scsi/spraid/Kconfig" config SCSI_HPTIOP tristate "HighPoint RocketRAID 3xxx/4xxx Controller support" diff --git a/drivers/scsi/Makefile b/drivers/scsi/Makefile index 2973693f6dcc..4056cf26e09e 100644 --- a/drivers/scsi/Makefile +++ b/drivers/scsi/Makefile @@ -94,6 +94,7 @@ obj-$(CONFIG_SCSI_ZALON) += zalon7xx.o obj-$(CONFIG_SCSI_DC395x) += dc395x.o obj-$(CONFIG_SCSI_AM53C974) += esp_scsi.o am53c974.o obj-$(CONFIG_CXLFLASH) += cxlflash/ +obj-$(CONFIG_RAMAXEL_SPRAID) += spraid/ obj-$(CONFIG_MEGARAID_LEGACY) += megaraid.o obj-$(CONFIG_MEGARAID_NEWGEN) += megaraid/ obj-$(CONFIG_MEGARAID_SAS) += megaraid/ diff --git a/drivers/scsi/spraid/Kconfig b/drivers/scsi/spraid/Kconfig new file mode 100644 index 000000000000..bfbba3db8db0 --- /dev/null +++ b/drivers/scsi/spraid/Kconfig @@ -0,0 +1,13 @@ +# +# Ramaxel driver configuration +# + +config RAMAXEL_SPRAID + tristate "Ramaxel spraid Adapter" + depends on PCI && SCSI + select BLK_DEV_BSGLIB + depends on ARM64 || X86_64 + help + This driver supports Ramaxel SPRxxx serial + raid controller, which has PCIE Gen4 interface + with host and supports SAS/SATA Hdd/ssd. diff --git a/drivers/scsi/spraid/Makefile b/drivers/scsi/spraid/Makefile new file mode 100644 index 000000000000..aadc2ffd37eb --- /dev/null +++ b/drivers/scsi/spraid/Makefile @@ -0,0 +1,7 @@ +# +# Makefile for the Ramaxel device drivers. +# + +obj-$(CONFIG_RAMAXEL_SPRAID) += spraid.o + +spraid-objs := spraid_main.o \ No newline at end of file diff --git a/drivers/scsi/spraid/spraid.h b/drivers/scsi/spraid/spraid.h new file mode 100644 index 000000000000..c1e4980e18e5 --- /dev/null +++ b/drivers/scsi/spraid/spraid.h @@ -0,0 +1,746 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2021 Ramaxel Memory Technology, Ltd */ + +#ifndef __SPRAID_H_ +#define __SPRAID_H_ + +#define SPRAID_CAP_MQES(cap) ((cap) & 0xffff) +#define SPRAID_CAP_STRIDE(cap) (((cap) >> 32) & 0xf) +#define SPRAID_CAP_MPSMIN(cap) (((cap) >> 48) & 0xf) +#define SPRAID_CAP_MPSMAX(cap) (((cap) >> 52) & 0xf) +#define SPRAID_CAP_TIMEOUT(cap) (((cap) >> 24) & 0xff) +#define SPRAID_CAP_DMAMASK(cap) (((cap) >> 37) & 0xff) + +#define SPRAID_DEFAULT_MAX_CHANNEL 4 +#define SPRAID_DEFAULT_MAX_ID 240 +#define SPRAID_DEFAULT_MAX_LUN_PER_HOST 8 +#define MAX_SECTORS 2048 + +#define IO_SQE_SIZE sizeof(struct spraid_ioq_command) +#define ADMIN_SQE_SIZE sizeof(struct spraid_admin_command) +#define SQE_SIZE(qid) (((qid) > 0) ? IO_SQE_SIZE : ADMIN_SQE_SIZE) +#define CQ_SIZE(depth) ((depth) * sizeof(struct spraid_completion)) +#define SQ_SIZE(qid, depth) ((depth) * SQE_SIZE(qid)) + +#define SENSE_SIZE(depth) ((depth) * SCSI_SENSE_BUFFERSIZE) + +#define SPRAID_AQ_DEPTH 128 +#define SPRAID_NR_AEN_COMMANDS 16 +#define SPRAID_AQ_BLK_MQ_DEPTH (SPRAID_AQ_DEPTH - SPRAID_NR_AEN_COMMANDS) +#define SPRAID_AQ_MQ_TAG_DEPTH (SPRAID_AQ_BLK_MQ_DEPTH - 1) + +#define SPRAID_ADMIN_QUEUE_NUM 1 +#define SPRAID_PTCMDS_PERQ 1 +#define SPRAID_IO_BLK_MQ_DEPTH (hdev->shost->can_queue) +#define SPRAID_NR_IOQ_PTCMDS (SPRAID_PTCMDS_PERQ * hdev->shost->nr_hw_queues) + +#define FUA_MASK 0x08 +#define SPRAID_MINORS BIT(MINORBITS) + +#define COMMAND_IS_WRITE(cmd) ((cmd)->common.opcode & 1) + +#define SPRAID_IO_IOSQES 7 +#define SPRAID_IO_IOCQES 4 +#define PRP_ENTRY_SIZE 8 + +#define SMALL_POOL_SIZE 256 +#define MAX_SMALL_POOL_NUM 16 +#define MAX_CMD_PER_DEV 64 +#define MAX_CDB_LEN 32 + +#define SPRAID_UP_TO_MULTY4(x) (((x) + 4) & (~0x03)) + +#define CQE_STATUS_SUCCESS (0x0) + +#define PCI_VENDOR_ID_RAMAXEL_LOGIC 0x1E81 + +#define SPRAID_SERVER_DEVICE_HBA_DID 0x2100 +#define SPRAID_SERVER_DEVICE_RAID_DID 0x2200 + +#define IO_6_DEFAULT_TX_LEN 256 + +#define SPRAID_INT_PAGES 2 +#define SPRAID_INT_BYTES(hdev) (SPRAID_INT_PAGES * (hdev)->page_size) + +enum { + SPRAID_REQ_CANCELLED = (1 << 0), + SPRAID_REQ_USERCMD = (1 << 1), +}; + +enum { + SPRAID_SC_SUCCESS = 0x0, + SPRAID_SC_INVALID_OPCODE = 0x1, + SPRAID_SC_INVALID_FIELD = 0x2, + + SPRAID_SC_ABORT_LIMIT = 0x103, + SPRAID_SC_ABORT_MISSING = 0x104, + SPRAID_SC_ASYNC_LIMIT = 0x105, + + SPRAID_SC_DNR = 0x4000, +}; + +enum { + SPRAID_REG_CAP = 0x0000, + SPRAID_REG_CC = 0x0014, + SPRAID_REG_CSTS = 0x001c, + SPRAID_REG_AQA = 0x0024, + SPRAID_REG_ASQ = 0x0028, + SPRAID_REG_ACQ = 0x0030, + SPRAID_REG_DBS = 0x1000, +}; + +enum { + SPRAID_CC_ENABLE = 1 << 0, + SPRAID_CC_CSS_NVM = 0 << 4, + SPRAID_CC_MPS_SHIFT = 7, + SPRAID_CC_AMS_SHIFT = 11, + SPRAID_CC_SHN_SHIFT = 14, + SPRAID_CC_IOSQES_SHIFT = 16, + SPRAID_CC_IOCQES_SHIFT = 20, + SPRAID_CC_AMS_RR = 0 << SPRAID_CC_AMS_SHIFT, + SPRAID_CC_SHN_NONE = 0 << SPRAID_CC_SHN_SHIFT, + SPRAID_CC_IOSQES = SPRAID_IO_IOSQES << SPRAID_CC_IOSQES_SHIFT, + SPRAID_CC_IOCQES = SPRAID_IO_IOCQES << SPRAID_CC_IOCQES_SHIFT, + SPRAID_CC_SHN_NORMAL = 1 << SPRAID_CC_SHN_SHIFT, + SPRAID_CC_SHN_MASK = 3 << SPRAID_CC_SHN_SHIFT, + SPRAID_CSTS_CFS_SHIFT = 1, + SPRAID_CSTS_SHST_SHIFT = 2, + SPRAID_CSTS_PP_SHIFT = 5, + SPRAID_CSTS_RDY = 1 << 0, + SPRAID_CSTS_SHST_CMPLT = 2 << 2, + SPRAID_CSTS_SHST_MASK = 3 << 2, + SPRAID_CSTS_CFS_MASK = 1 << SPRAID_CSTS_CFS_SHIFT, + SPRAID_CSTS_PP_MASK = 1 << SPRAID_CSTS_PP_SHIFT, +}; + +enum { + SPRAID_ADMIN_DELETE_SQ = 0x00, + SPRAID_ADMIN_CREATE_SQ = 0x01, + SPRAID_ADMIN_DELETE_CQ = 0x04, + SPRAID_ADMIN_CREATE_CQ = 0x05, + SPRAID_ADMIN_ABORT_CMD = 0x08, + SPRAID_ADMIN_SET_FEATURES = 0x09, + SPRAID_ADMIN_ASYNC_EVENT = 0x0c, + SPRAID_ADMIN_GET_INFO = 0xc6, + SPRAID_ADMIN_RESET = 0xc8, +}; + +enum { + SPRAID_GET_INFO_CTRL = 0, + SPRAID_GET_INFO_DEV_LIST = 1, +}; + +enum { + SPRAID_RESET_TARGET = 0, + SPRAID_RESET_BUS = 1, +}; + +enum { + SPRAID_AEN_ERROR = 0, + SPRAID_AEN_NOTICE = 2, + SPRAID_AEN_VS = 7, +}; + +enum { + SPRAID_AEN_DEV_CHANGED = 0x00, + SPRAID_AEN_FW_ACT_START = 0x01, + SPRAID_AEN_HOST_PROBING = 0x10, +}; + +enum { + SPRAID_AEN_TIMESYN = 0x00, + SPRAID_AEN_FW_ACT_FINISH = 0x02, + SPRAID_AEN_EVENT_MIN = 0x80, + SPRAID_AEN_EVENT_MAX = 0xff, +}; + +enum { + SPRAID_CMD_WRITE = 0x01, + SPRAID_CMD_READ = 0x02, + + SPRAID_CMD_NONIO_NONE = 0x80, + SPRAID_CMD_NONIO_TODEV = 0x81, + SPRAID_CMD_NONIO_FROMDEV = 0x82, +}; + +enum { + SPRAID_QUEUE_PHYS_CONTIG = (1 << 0), + SPRAID_CQ_IRQ_ENABLED = (1 << 1), + + SPRAID_FEAT_NUM_QUEUES = 0x07, + SPRAID_FEAT_ASYNC_EVENT = 0x0b, + SPRAID_FEAT_TIMESTAMP = 0x0e, +}; + +enum spraid_state { + SPRAID_NEW, + SPRAID_LIVE, + SPRAID_RESETTING, + SPRAID_DELETING, + SPRAID_DEAD, +}; + +enum { + SPRAID_CARD_HBA, + SPRAID_CARD_RAID, +}; + +enum spraid_cmd_type { + SPRAID_CMD_ADM, + SPRAID_CMD_IOPT, +}; + +struct spraid_completion { + __le32 result; + union { + struct { + __u8 sense_len; + __u8 resv[3]; + }; + __le32 result1; + }; + __le16 sq_head; + __le16 sq_id; + __u16 cmd_id; + __le16 status; +}; + +struct spraid_ctrl_info { + __le32 nd; + __le16 max_cmds; + __le16 max_channel; + __le32 max_tgt_id; + __le16 max_lun; + __le16 max_num_sge; + __le16 lun_num_in_boot; + __u8 mdts; + __u8 acl; + __u8 aerl; + __u8 card_type; + __u16 rsvd; + __u32 rtd3e; + __u8 sn[32]; + __u8 fr[16]; + __u8 rsvd1[4020]; +}; + +struct spraid_dev { + struct pci_dev *pdev; + struct device *dev; + struct Scsi_Host *shost; + struct spraid_queue *queues; + struct dma_pool *prp_page_pool; + struct dma_pool *prp_small_pool[MAX_SMALL_POOL_NUM]; + mempool_t *iod_mempool; + void __iomem *bar; + u32 max_qid; + u32 num_vecs; + u32 queue_count; + u32 ioq_depth; + int db_stride; + u32 __iomem *dbs; + struct rw_semaphore devices_rwsem; + int numa_node; + u32 page_size; + u32 ctrl_config; + u32 online_queues; + u64 cap; + int instance; + struct spraid_ctrl_info *ctrl_info; + struct spraid_dev_info *devices; + + struct spraid_cmd *adm_cmds; + struct list_head adm_cmd_list; + spinlock_t adm_cmd_lock; + + struct spraid_cmd *ioq_ptcmds; + struct list_head ioq_pt_list; + spinlock_t ioq_pt_lock; + + struct work_struct scan_work; + struct work_struct timesyn_work; + struct work_struct reset_work; + struct work_struct fw_act_work; + + enum spraid_state state; + spinlock_t state_lock; + + struct request_queue *bsg_queue; +}; + +struct spraid_sgl_desc { + __le64 addr; + __le32 length; + __u8 rsvd[3]; + __u8 type; +}; + +union spraid_data_ptr { + struct { + __le64 prp1; + __le64 prp2; + }; + struct spraid_sgl_desc sgl; +}; + +struct spraid_admin_common_command { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + __le32 cdw2[4]; + union spraid_data_ptr dptr; + __le32 cdw10; + __le32 cdw11; + __le32 cdw12; + __le32 cdw13; + __le32 cdw14; + __le32 cdw15; +}; + +struct spraid_features { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + __u64 rsvd2[2]; + union spraid_data_ptr dptr; + __le32 fid; + __le32 dword11; + __le32 dword12; + __le32 dword13; + __le32 dword14; + __le32 dword15; +}; + +struct spraid_create_cq { + __u8 opcode; + __u8 flags; + __u16 command_id; + __u32 rsvd1[5]; + __le64 prp1; + __u64 rsvd8; + __le16 cqid; + __le16 qsize; + __le16 cq_flags; + __le16 irq_vector; + __u32 rsvd12[4]; +}; + +struct spraid_create_sq { + __u8 opcode; + __u8 flags; + __u16 command_id; + __u32 rsvd1[5]; + __le64 prp1; + __u64 rsvd8; + __le16 sqid; + __le16 qsize; + __le16 sq_flags; + __le16 cqid; + __u32 rsvd12[4]; +}; + +struct spraid_delete_queue { + __u8 opcode; + __u8 flags; + __u16 command_id; + __u32 rsvd1[9]; + __le16 qid; + __u16 rsvd10; + __u32 rsvd11[5]; +}; + +struct spraid_get_info { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + __u32 rsvd2[4]; + union spraid_data_ptr dptr; + __u8 type; + __u8 rsvd10[3]; + __le32 cdw11; + __u32 rsvd12[4]; +}; + +struct spraid_usr_cmd { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + union { + struct { + __le16 subopcode; + __le16 rsvd1; + } info_0; + __le32 cdw2; + }; + union { + struct { + __le16 data_len; + __le16 param_len; + } info_1; + __le32 cdw3; + }; + __u64 metadata; + union spraid_data_ptr dptr; + __le32 cdw10; + __le32 cdw11; + __le32 cdw12; + __le32 cdw13; + __le32 cdw14; + __le32 cdw15; +}; + +enum { + SPRAID_CMD_FLAG_SGL_METABUF = (1 << 6), + SPRAID_CMD_FLAG_SGL_METASEG = (1 << 7), + SPRAID_CMD_FLAG_SGL_ALL = SPRAID_CMD_FLAG_SGL_METABUF | + SPRAID_CMD_FLAG_SGL_METASEG, +}; + +enum spraid_cmd_state { + SPRAID_CMD_IDLE = 0, + SPRAID_CMD_IN_FLIGHT = 1, + SPRAID_CMD_COMPLETE = 2, + SPRAID_CMD_TIMEOUT = 3, + SPRAID_CMD_TMO_COMPLETE = 4, +}; + +struct spraid_abort_cmd { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + __u64 rsvd2[4]; + __le16 sqid; + __le16 cid; + __u32 rsvd11[5]; +}; + +struct spraid_reset_cmd { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + __u64 rsvd2[4]; + __u8 type; + __u8 rsvd10[3]; + __u32 rsvd11[5]; +}; + +struct spraid_admin_command { + union { + struct spraid_admin_common_command common; + struct spraid_features features; + struct spraid_create_cq create_cq; + struct spraid_create_sq create_sq; + struct spraid_delete_queue delete_queue; + struct spraid_get_info get_info; + struct spraid_abort_cmd abort; + struct spraid_reset_cmd reset; + struct spraid_usr_cmd usr_cmd; + }; +}; + +struct spraid_ioq_common_command { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + __le16 sense_len; + __u8 cdb_len; + __u8 rsvd2; + __le32 cdw3[3]; + union spraid_data_ptr dptr; + __le32 cdw10[6]; + __u8 cdb[32]; + __le64 sense_addr; + __le32 cdw26[6]; +}; + +struct spraid_rw_command { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + __le16 sense_len; + __u8 cdb_len; + __u8 rsvd2; + __u32 rsvd3[3]; + union spraid_data_ptr dptr; + __le64 slba; + __le16 nlb; + __le16 control; + __u32 rsvd13[3]; + __u8 cdb[32]; + __le64 sense_addr; + __u32 rsvd26[6]; +}; + +struct spraid_scsi_nonio { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + __le16 sense_len; + __u8 cdb_length; + __u8 rsvd2; + __u32 rsvd3[3]; + union spraid_data_ptr dptr; + __u32 rsvd10[5]; + __le32 buffer_len; + __u8 cdb[32]; + __le64 sense_addr; + __u32 rsvd26[6]; +}; + +struct spraid_ioq_command { + union { + struct spraid_ioq_common_command common; + struct spraid_rw_command rw; + struct spraid_scsi_nonio scsi_nonio; + }; +}; + +struct spraid_passthru_common_cmd { + __u8 opcode; + __u8 flags; + __u16 rsvd0; + __u32 nsid; + union { + struct { + __u16 subopcode; + __u16 rsvd1; + } info_0; + __u32 cdw2; + }; + union { + struct { + __u16 data_len; + __u16 param_len; + } info_1; + __u32 cdw3; + }; + __u64 metadata; + + __u64 addr; + __u64 prp2; + + __u32 cdw10; + __u32 cdw11; + __u32 cdw12; + __u32 cdw13; + __u32 cdw14; + __u32 cdw15; + __u32 timeout_ms; + __u32 result0; + __u32 result1; +}; + +struct spraid_ioq_passthru_cmd { + __u8 opcode; + __u8 flags; + __u16 rsvd0; + __u32 nsid; + union { + struct { + __u16 res_sense_len; + __u8 cdb_len; + __u8 rsvd0; + } info_0; + __u32 cdw2; + }; + union { + struct { + __u16 subopcode; + __u16 rsvd1; + } info_1; + __u32 cdw3; + }; + union { + struct { + __u16 rsvd; + __u16 param_len; + } info_2; + __u32 cdw4; + }; + __u32 cdw5; + __u64 addr; + __u64 prp2; + union { + struct { + __u16 eid; + __u16 sid; + } info_3; + __u32 cdw10; + }; + union { + struct { + __u16 did; + __u8 did_flag; + __u8 rsvd2; + } info_4; + __u32 cdw11; + }; + __u32 cdw12; + __u32 cdw13; + __u32 cdw14; + __u32 data_len; + __u32 cdw16; + __u32 cdw17; + __u32 cdw18; + __u32 cdw19; + __u32 cdw20; + __u32 cdw21; + __u32 cdw22; + __u32 cdw23; + __u64 sense_addr; + __u32 cdw26[4]; + __u32 timeout_ms; + __u32 result0; + __u32 result1; +}; + +struct spraid_bsg_request { + u32 msgcode; + u32 control; + union { + struct spraid_passthru_common_cmd admcmd; + struct spraid_ioq_passthru_cmd ioqcmd; + }; +}; + +enum { + SPRAID_BSG_ADM, + SPRAID_BSG_IOQ, +}; + +struct spraid_cmd { + int qid; + int cid; + u32 result0; + u32 result1; + u16 status; + void *priv; + enum spraid_cmd_state state; + struct completion cmd_done; + struct list_head list; +}; + +struct spraid_queue { + struct spraid_dev *hdev; + spinlock_t sq_lock; + + spinlock_t cq_lock ____cacheline_aligned_in_smp; + + void *sq_cmds; + + struct spraid_completion *cqes; + + dma_addr_t sq_dma_addr; + dma_addr_t cq_dma_addr; + u32 __iomem *q_db; + u8 cq_phase; + u8 sqes; + u16 qid; + u16 sq_tail; + u16 cq_head; + u16 last_cq_head; + u16 q_depth; + s16 cq_vector; + void *sense; + dma_addr_t sense_dma_addr; + struct dma_pool *prp_small_pool; +}; + +struct spraid_iod { + struct spraid_queue *spraidq; + enum spraid_cmd_state state; + int npages; + u32 nsge; + u32 length; + bool use_sgl; + bool sg_drv_mgmt; + dma_addr_t first_dma; + void *sense; + dma_addr_t sense_dma; + struct scatterlist *sg; + struct scatterlist inline_sg[0]; +}; + +#define SPRAID_DEV_INFO_ATTR_BOOT(attr) ((attr) & 0x01) +#define SPRAID_DEV_INFO_ATTR_VD(attr) (((attr) & 0x02) == 0x0) +#define SPRAID_DEV_INFO_ATTR_PT(attr) (((attr) & 0x22) == 0x02) +#define SPRAID_DEV_INFO_ATTR_RAWDISK(attr) ((attr) & 0x20) + +#define SPRAID_DEV_INFO_FLAG_VALID(flag) ((flag) & 0x01) +#define SPRAID_DEV_INFO_FLAG_CHANGE(flag) ((flag) & 0x02) + +#define BGTASK_TYPE_REBUILD 4 +#define USR_CMD_READ 0xc2 +#define USR_CMD_RDLEN 0x1000 +#define USR_CMD_VDINFO 0x704 +#define USR_CMD_BGTASK 0x504 +#define VDINFO_PARAM_LEN 0x04 + +struct spraid_vd_info { + __u8 name[32]; + __le16 id; + __u8 rg_id; + __u8 rg_level; + __u8 sg_num; + __u8 sg_disk_num; + __u8 vd_status; + __u8 vd_type; + __u8 rsvd1[4056]; +}; + +#define MAX_REALTIME_BGTASK_NUM 32 + +struct bgtask_info { + __u8 type; + __u8 progress; + __u8 rate; + __u8 rsvd0; + __le16 vd_id; + __le16 time_left; + __u8 rsvd1[4]; +}; + +struct spraid_bgtask { + __u8 sw; + __u8 task_num; + __u8 rsvd[6]; + struct bgtask_info bgtask[MAX_REALTIME_BGTASK_NUM]; +}; + +struct spraid_dev_info { + __le32 hdid; + __le16 target; + __u8 channel; + __u8 lun; + __u8 attr; + __u8 flag; + __le16 max_io_kb; +}; + +#define MAX_DEV_ENTRY_PER_PAGE_4K 340 +struct spraid_dev_list { + __le32 dev_num; + __u32 rsvd0[3]; + struct spraid_dev_info devices[MAX_DEV_ENTRY_PER_PAGE_4K]; +}; + +struct spraid_sdev_hostdata { + u32 hdid; + u16 max_io_kb; + u8 attr; + u8 flag; + u8 rg_id; + u8 rsvd[3]; +}; + +#endif + diff --git a/drivers/scsi/spraid/spraid_main.c b/drivers/scsi/spraid/spraid_main.c new file mode 100644 index 000000000000..519b39f44e91 --- /dev/null +++ b/drivers/scsi/spraid/spraid_main.c @@ -0,0 +1,3875 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2021 Ramaxel Memory Technology, Ltd */ + +/* Ramaxel Raid SPXXX Series Linux Driver */ + +#define pr_fmt(fmt) "spraid: " fmt + +#include <linux/sched/signal.h> +#include <linux/version.h> +#include <linux/pci.h> +#include <linux/aer.h> +#include <linux/module.h> +#include <linux/ioport.h> +#include <linux/device.h> +#include <linux/delay.h> +#include <linux/interrupt.h> +#include <linux/cdev.h> +#include <linux/sysfs.h> +#include <linux/gfp.h> +#include <linux/types.h> +#include <linux/ratelimit.h> +#include <linux/once.h> +#include <linux/debugfs.h> +#include <linux/io-64-nonatomic-lo-hi.h> +#include <linux/blkdev.h> +#include <linux/bsg-lib.h> +#include <asm/unaligned.h> +#include <linux/sort.h> +#include <target/target_core_backend.h> + +#include <scsi/scsi.h> +#include <scsi/scsi_cmnd.h> +#include <scsi/scsi_device.h> +#include <scsi/scsi_host.h> +#include <scsi/scsi_transport.h> +#include <scsi/scsi_dbg.h> + + +#include "spraid.h" + +static u32 admin_tmout = 60; +module_param(admin_tmout, uint, 0644); +MODULE_PARM_DESC(admin_tmout, "admin commands timeout (seconds)"); + +static u32 scmd_tmout_nonpt = 180; +module_param(scmd_tmout_nonpt, uint, 0644); +MODULE_PARM_DESC(scmd_tmout_nonpt, + "scsi commands timeout for rawdisk&raid(seconds)"); + +static int ioq_depth_set(const char *val, const struct kernel_param *kp); +static const struct kernel_param_ops ioq_depth_ops = { + .set = ioq_depth_set, + .get = param_get_uint, +}; + +static u32 io_queue_depth = 1024; +module_param_cb(io_queue_depth, &ioq_depth_ops, &io_queue_depth, 0644); +MODULE_PARM_DESC(io_queue_depth, "set io queue depth, should >= 2"); + +static int log_debug_switch_set(const char *val, const struct kernel_param *kp) +{ + u8 n = 0; + int ret; + + ret = kstrtou8(val, 10, &n); + if (ret != 0) + return -EINVAL; + + return param_set_byte(val, kp); +} + +static const struct kernel_param_ops log_debug_switch_ops = { + .set = log_debug_switch_set, + .get = param_get_byte, +}; + +static unsigned char log_debug_switch; +module_param_cb(log_debug_switch, &log_debug_switch_ops, + &log_debug_switch, 0644); +MODULE_PARM_DESC(log_debug_switch, + "set log state, default non-zero for switch on"); + +static int small_pool_num_set(const char *val, const struct kernel_param *kp) +{ + u8 n = 0; + int ret; + + ret = kstrtou8(val, 10, &n); + if (ret != 0) + return -EINVAL; + if (n > MAX_SMALL_POOL_NUM) + n = MAX_SMALL_POOL_NUM; + if (n < 1) + n = 1; + *((u8 *)kp->arg) = n; + + return 0; +} + +static const struct kernel_param_ops small_pool_num_ops = { + .set = small_pool_num_set, + .get = param_get_byte, +}; + +/* It was found that the spindlock of a single pool conflicts + * a lot with multiple CPUs.So multiple pools are introduced + * to reduce the conflictions. + */ +static unsigned char small_pool_num = 4; +module_param_cb(small_pool_num, &small_pool_num_ops, &small_pool_num, 0644); +MODULE_PARM_DESC(small_pool_num, "set prp small pool num, default 4, MAX 16"); + +static void spraid_free_queue(struct spraid_queue *spraidq); +static void spraid_handle_aen_notice(struct spraid_dev *hdev, u32 result); +static void spraid_handle_aen_vs(struct spraid_dev *hdev, + u32 result, u32 result1); + +static DEFINE_IDA(spraid_instance_ida); + +static struct class *spraid_class; + +#define SPRAID_CAP_TIMEOUT_UNIT_MS (HZ / 2) + +static struct workqueue_struct *spraid_wq; + +#define dev_log_dbg(dev, fmt, ...) do { \ + if (unlikely(log_debug_switch)) \ + dev_info(dev, "[%s] [%d] " fmt, \ + __func__, __LINE__, ##__VA_ARGS__); \ +} while (0) + +#define SPRAID_DRV_VERSION "1.0.0.0" + +#define ADMIN_TIMEOUT (admin_tmout * HZ) +#define ADMIN_ERR_TIMEOUT 32757 + +#define SPRAID_WAIT_ABNL_CMD_TIMEOUT (3 * 2) + +#define SPRAID_DMA_MSK_BIT_MAX 64 + +enum FW_STAT_CODE { + FW_STAT_OK = 0, + FW_STAT_NEED_CHECK, + FW_STAT_ERROR, + FW_STAT_EP_PCIE_ERROR, + FW_STAT_NAC_DMA_ERROR, + FW_STAT_ABORTED, + FW_STAT_NEED_RETRY +}; + +static const char * const raid_levels[] = {"0", "1", "5", "6", "10", "50", "60", + "NA"}; + +static const char * const raid_states[] = { + "NA", "NORMAL", "FAULT", "DEGRADE", "NOT_FORMATTED", + "FORMATTING", "SANITIZING", "INITIALIZING", "INITIALIZE_FAIL", + "DELETING", "DELETE_FAIL", "WRITE_PROTECT" +}; + +static int ioq_depth_set(const char *val, const struct kernel_param *kp) +{ + int n = 0; + int ret; + + ret = kstrtoint(val, 10, &n); + if (ret != 0 || n < 2) + return -EINVAL; + + return param_set_int(val, kp); +} + +static int spraid_remap_bar(struct spraid_dev *hdev, u32 size) +{ + struct pci_dev *pdev = hdev->pdev; + + if (size > pci_resource_len(pdev, 0)) { + dev_err(hdev->dev, "Input size[%u] exceed bar0 length[%llu]\n", + size, pci_resource_len(pdev, 0)); + return -ENOMEM; + } + + if (hdev->bar) + iounmap(hdev->bar); + + hdev->bar = ioremap(pci_resource_start(pdev, 0), size); + if (!hdev->bar) { + dev_err(hdev->dev, "ioremap for bar0 failed\n"); + return -ENOMEM; + } + hdev->dbs = hdev->bar + SPRAID_REG_DBS; + + return 0; +} + +static int spraid_dev_map(struct spraid_dev *hdev) +{ + struct pci_dev *pdev = hdev->pdev; + int ret; + + ret = pci_request_mem_regions(pdev, "spraid"); + if (ret) { + dev_err(hdev->dev, "fail to request memory regions\n"); + return ret; + } + + ret = spraid_remap_bar(hdev, SPRAID_REG_DBS + 4096); + if (ret) { + pci_release_mem_regions(pdev); + return ret; + } + + return 0; +} + +static void spraid_dev_unmap(struct spraid_dev *hdev) +{ + struct pci_dev *pdev = hdev->pdev; + + if (hdev->bar) { + iounmap(hdev->bar); + hdev->bar = NULL; + } + pci_release_mem_regions(pdev); +} + +static int spraid_pci_enable(struct spraid_dev *hdev) +{ + struct pci_dev *pdev = hdev->pdev; + int ret = -ENOMEM; + u64 maskbit = SPRAID_DMA_MSK_BIT_MAX; + + if (pci_enable_device_mem(pdev)) { + dev_err(hdev->dev, + "Enable pci device memory resources failed\n"); + return ret; + } + pci_set_master(pdev); + + if (readl(hdev->bar + SPRAID_REG_CSTS) == U32_MAX) { + ret = -ENODEV; + dev_err(hdev->dev, "Read csts register failed\n"); + goto disable; + } + + ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES); + if (ret < 0) { + dev_err(hdev->dev, + "Allocate one IRQ for setup admin channel failed\n"); + goto disable; + } + + hdev->cap = lo_hi_readq(hdev->bar + SPRAID_REG_CAP); + hdev->ioq_depth = min_t(u32, SPRAID_CAP_MQES(hdev->cap) + 1, + io_queue_depth); + hdev->db_stride = 1 << SPRAID_CAP_STRIDE(hdev->cap); + + maskbit = SPRAID_CAP_DMAMASK(hdev->cap); + if (maskbit < 32 || maskbit > SPRAID_DMA_MSK_BIT_MAX) { + dev_err(hdev->dev, + "err, dma mask invalid[%llu], set to default\n", + maskbit); + maskbit = SPRAID_DMA_MSK_BIT_MAX; + } + if (dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(maskbit))) { + dev_err(hdev->dev, "set dma mask and coherent failed\n"); + goto disable; + } + + dev_info(hdev->dev, "set dma mask[%llu] success\n", maskbit); + + pci_enable_pcie_error_reporting(pdev); + pci_save_state(pdev); + + return 0; + +disable: + pci_disable_device(pdev); + return ret; +} + +static int spraid_npages_prp(u32 size, struct spraid_dev *hdev) +{ + u32 nprps = DIV_ROUND_UP(size + hdev->page_size, hdev->page_size); + + return DIV_ROUND_UP(PRP_ENTRY_SIZE * nprps, PAGE_SIZE - PRP_ENTRY_SIZE); +} + +static int spraid_npages_sgl(u32 nseg) +{ + return DIV_ROUND_UP(nseg * sizeof(struct spraid_sgl_desc), PAGE_SIZE); +} + +static void **spraid_iod_list(struct spraid_iod *iod) +{ + return (void **)(iod->inline_sg + (iod->sg_drv_mgmt ? iod->nsge : 0)); +} + +static u32 spraid_iod_ext_size(struct spraid_dev *hdev, u32 size, u32 nsge, + bool sg_drv_mgmt, bool use_sgl) +{ + size_t alloc_size, sg_size; + + if (use_sgl) + alloc_size = sizeof(__le64 *) * spraid_npages_sgl(nsge); + else + alloc_size = sizeof(__le64 *) * spraid_npages_prp(size, hdev); + + sg_size = sg_drv_mgmt ? (sizeof(struct scatterlist) * nsge) : 0; + return sg_size + alloc_size; +} + +static u32 spraid_cmd_size(struct spraid_dev *hdev, + bool sg_drv_mgmt, bool use_sgl) +{ + u32 alloc_size = spraid_iod_ext_size(hdev, SPRAID_INT_BYTES(hdev), + SPRAID_INT_PAGES, sg_drv_mgmt, use_sgl); + + dev_info(hdev->dev, "sg_drv_mgmt: %s, use_sgl: %s, iod size: %lu;" + " alloc_size: %u\n", sg_drv_mgmt ? "true" : "false", + use_sgl ? "true" : "false", + sizeof(struct spraid_iod), alloc_size); + + return sizeof(struct spraid_iod) + alloc_size; +} + +static int spraid_setup_prps(struct spraid_dev *hdev, struct spraid_iod *iod) +{ + struct scatterlist *sg = iod->sg; + u64 dma_addr = sg_dma_address(sg); + int dma_len = sg_dma_len(sg); + __le64 *prp_list, *old_prp_list; + u32 page_size = hdev->page_size; + int offset = dma_addr & (page_size - 1); + void **list = spraid_iod_list(iod); + int length = iod->length; + struct dma_pool *pool; + dma_addr_t prp_dma; + int nprps, i; + + length -= (page_size - offset); + if (length <= 0) { + iod->first_dma = 0; + return 0; + } + + dma_len -= (page_size - offset); + if (dma_len) { + dma_addr += (page_size - offset); + } else { + sg = sg_next(sg); + dma_addr = sg_dma_address(sg); + dma_len = sg_dma_len(sg); + } + + if (length <= page_size) { + iod->first_dma = dma_addr; + return 0; + } + + nprps = DIV_ROUND_UP(length, page_size); + if (nprps <= (SMALL_POOL_SIZE / PRP_ENTRY_SIZE)) { + pool = iod->spraidq->prp_small_pool; + iod->npages = 0; + } else { + pool = hdev->prp_page_pool; + iod->npages = 1; + } + + prp_list = dma_pool_alloc(pool, GFP_ATOMIC, &prp_dma); + if (!prp_list) { + dev_err_ratelimited(hdev->dev, + "Allocate first prp_list memory failed\n"); + iod->first_dma = dma_addr; + iod->npages = -1; + return -ENOMEM; + } + list[0] = prp_list; + iod->first_dma = prp_dma; + i = 0; + for (;;) { + if (i == page_size / PRP_ENTRY_SIZE) { + old_prp_list = prp_list; + + prp_list = dma_pool_alloc(pool, GFP_ATOMIC, &prp_dma); + if (!prp_list) { + dev_err_ratelimited(hdev->dev, "Allocate %dth;" + " prp_list memory failed\n", + iod->npages + 1); + return -ENOMEM; + } + list[iod->npages++] = prp_list; + prp_list[0] = old_prp_list[i - 1]; + old_prp_list[i - 1] = cpu_to_le64(prp_dma); + i = 1; + } + prp_list[i++] = cpu_to_le64(dma_addr); + dma_len -= page_size; + dma_addr += page_size; + length -= page_size; + if (length <= 0) + break; + if (dma_len > 0) + continue; + if (unlikely(dma_len < 0)) + goto bad_sgl; + sg = sg_next(sg); + dma_addr = sg_dma_address(sg); + dma_len = sg_dma_len(sg); + } + + return 0; + +bad_sgl: + dev_err(hdev->dev, + "Setup prps, invalid SGL for payload: %d nents: %d\n", + iod->length, iod->nsge); + return -EIO; +} + +#define SGES_PER_PAGE (PAGE_SIZE / sizeof(struct spraid_sgl_desc)) + +static void spraid_submit_cmd(struct spraid_queue *spraidq, const void *cmd) +{ + u32 sqes = SQE_SIZE(spraidq->qid); + unsigned long flags; + struct spraid_admin_common_command *acd = + (struct spraid_admin_common_command *)cmd; + + spin_lock_irqsave(&spraidq->sq_lock, flags); + memcpy((spraidq->sq_cmds + sqes * spraidq->sq_tail), cmd, sqes); + if (++spraidq->sq_tail == spraidq->q_depth) + spraidq->sq_tail = 0; + + writel(spraidq->sq_tail, spraidq->q_db); + spin_unlock_irqrestore(&spraidq->sq_lock, flags); + + dev_log_dbg(spraidq->hdev->dev, + "cid[%d] qid[%d], opcode[0x%x], flags[0x%x], hdid[%u]\n", + acd->command_id, spraidq->qid, acd->opcode, + acd->flags, le32_to_cpu(acd->hdid)); +} + +static u32 spraid_mod64(u64 dividend, u32 divisor) +{ + u64 d; + u32 remainder; + + if (!divisor) + pr_err("DIVISOR is zero, in div fn\n"); + + d = dividend; + remainder = do_div(d, divisor); + return remainder; +} + +static inline bool spraid_is_rw_scmd(struct scsi_cmnd *scmd) +{ + switch (scmd->cmnd[0]) { + case READ_6: + case READ_10: + case READ_12: + case READ_16: + case READ_32: + case WRITE_6: + case WRITE_10: + case WRITE_12: + case WRITE_16: + case WRITE_32: + return true; + default: + return false; + } +} + +static bool spraid_is_prp(struct spraid_dev *hdev, + struct scsi_cmnd *scmd, u32 nsge) +{ + struct scatterlist *sg = scsi_sglist(scmd); + u32 page_size = hdev->page_size; + bool is_prp = true; + int i = 0; + + scsi_for_each_sg(scmd, sg, nsge, i) { + if (i != 0 && i != nsge - 1) { + if (spraid_mod64(sg_dma_len(sg), page_size) || + spraid_mod64(sg_dma_address(sg), page_size)) { + is_prp = false; + break; + } + } + + if (nsge > 1 && i == 0) { + if ((spraid_mod64((sg_dma_address(sg) + sg_dma_len(sg)), + page_size))) { + is_prp = false; + break; + } + } + + if (nsge > 1 && i == (nsge - 1)) { + if (spraid_mod64(sg_dma_address(sg), page_size)) { + is_prp = false; + break; + } + } + } + + return is_prp; +} + +enum { + SPRAID_SGL_FMT_DATA_DESC = 0x00, + SPRAID_SGL_FMT_SEG_DESC = 0x02, + SPRAID_SGL_FMT_LAST_SEG_DESC = 0x03, + SPRAID_KEY_SGL_FMT_DATA_DESC = 0x04, + SPRAID_TRANSPORT_SGL_DATA_DESC = 0x05 +}; + +static void spraid_sgl_set_data(struct spraid_sgl_desc *sge, + struct scatterlist *sg) +{ + sge->addr = cpu_to_le64(sg_dma_address(sg)); + sge->length = cpu_to_le32(sg_dma_len(sg)); + sge->type = SPRAID_SGL_FMT_DATA_DESC << 4; +} + +static void spraid_sgl_set_seg(struct spraid_sgl_desc *sge, + dma_addr_t dma_addr, int entries) +{ + sge->addr = cpu_to_le64(dma_addr); + if (entries <= SGES_PER_PAGE) { + sge->length = cpu_to_le32(entries * sizeof(*sge)); + sge->type = SPRAID_SGL_FMT_LAST_SEG_DESC << 4; + } else { + sge->length = cpu_to_le32(PAGE_SIZE); + sge->type = SPRAID_SGL_FMT_SEG_DESC << 4; + } +} + +static int spraid_setup_ioq_cmd_sgl(struct spraid_dev *hdev, + struct scsi_cmnd *scmd, + struct spraid_ioq_command *ioq_cmd, + struct spraid_iod *iod) +{ + struct spraid_sgl_desc *sg_list, *link, *old_sg_list; + struct scatterlist *sg = scsi_sglist(scmd); + void **list = spraid_iod_list(iod); + struct dma_pool *pool; + int nsge = iod->nsge; + dma_addr_t sgl_dma; + int i = 0; + + ioq_cmd->common.flags |= SPRAID_CMD_FLAG_SGL_METABUF; + + if (nsge == 1) { + spraid_sgl_set_data(&ioq_cmd->common.dptr.sgl, sg); + return 0; + } + + if (nsge <= (SMALL_POOL_SIZE / sizeof(struct spraid_sgl_desc))) { + pool = iod->spraidq->prp_small_pool; + iod->npages = 0; + } else { + pool = hdev->prp_page_pool; + iod->npages = 1; + } + + sg_list = dma_pool_alloc(pool, GFP_ATOMIC, &sgl_dma); + if (!sg_list) { + dev_err_ratelimited(hdev->dev, + "Allocate first sgl_list failed\n"); + iod->npages = -1; + return -ENOMEM; + } + + list[0] = sg_list; + iod->first_dma = sgl_dma; + spraid_sgl_set_seg(&ioq_cmd->common.dptr.sgl, sgl_dma, nsge); + do { + if (i == SGES_PER_PAGE) { + old_sg_list = sg_list; + link = &old_sg_list[SGES_PER_PAGE - 1]; + + sg_list = dma_pool_alloc(pool, GFP_ATOMIC, &sgl_dma); + if (!sg_list) { + dev_err_ratelimited(hdev->dev, + "Allocate %dth sgl_list;" + " failed\n", + iod->npages + 1); + return -ENOMEM; + } + list[iod->npages++] = sg_list; + + i = 0; + memcpy(&sg_list[i++], link, sizeof(*link)); + spraid_sgl_set_seg(link, sgl_dma, nsge); + } + + spraid_sgl_set_data(&sg_list[i++], sg); + sg = sg_next(sg); + } while (--nsge > 0); + + return 0; +} + +#define SPRAID_RW_FUA BIT(14) + +static void spraid_setup_rw_cmd(struct spraid_dev *hdev, + struct spraid_rw_command *rw, + struct scsi_cmnd *scmd) +{ + u32 start_lba_lo, start_lba_hi; + u32 datalength = 0; + u16 control = 0; + + start_lba_lo = 0; + start_lba_hi = 0; + + if (scmd->sc_data_direction == DMA_TO_DEVICE) { + rw->opcode = SPRAID_CMD_WRITE; + } else if (scmd->sc_data_direction == DMA_FROM_DEVICE) { + rw->opcode = SPRAID_CMD_READ; + } else { + dev_err(hdev->dev, + "Invalid IO for unsupported data direction: %d\n", + scmd->sc_data_direction); + WARN_ON(1); + } + + /* 6-byte READ(0x08) or WRITE(0x0A) cdb */ + if (scmd->cmd_len == 6) { + datalength = (u32)(scmd->cmnd[4] == 0 ? + IO_6_DEFAULT_TX_LEN : scmd->cmnd[4]); + start_lba_lo = (u32)get_unaligned_be24(&scmd->cmnd[1]); + + start_lba_lo &= 0x1FFFFF; + } + + /* 10-byte READ(0x28) or WRITE(0x2A) cdb */ + else if (scmd->cmd_len == 10) { + datalength = (u32)get_unaligned_be16(&scmd->cmnd[7]); + start_lba_lo = get_unaligned_be32(&scmd->cmnd[2]); + + if (scmd->cmnd[1] & FUA_MASK) + control |= SPRAID_RW_FUA; + } + + /* 12-byte READ(0xA8) or WRITE(0xAA) cdb */ + else if (scmd->cmd_len == 12) { + datalength = get_unaligned_be32(&scmd->cmnd[6]); + start_lba_lo = get_unaligned_be32(&scmd->cmnd[2]); + + if (scmd->cmnd[1] & FUA_MASK) + control |= SPRAID_RW_FUA; + } + /* 16-byte READ(0x88) or WRITE(0x8A) cdb */ + else if (scmd->cmd_len == 16) { + datalength = get_unaligned_be32(&scmd->cmnd[10]); + start_lba_lo = get_unaligned_be32(&scmd->cmnd[6]); + start_lba_hi = get_unaligned_be32(&scmd->cmnd[2]); + + if (scmd->cmnd[1] & FUA_MASK) + control |= SPRAID_RW_FUA; + } + /* 32-byte READ(0x88) or WRITE(0x8A) cdb */ + else if (scmd->cmd_len == 32) { + datalength = get_unaligned_be32(&scmd->cmnd[28]); + start_lba_lo = get_unaligned_be32(&scmd->cmnd[16]); + start_lba_hi = get_unaligned_be32(&scmd->cmnd[12]); + + if (scmd->cmnd[10] & FUA_MASK) + control |= SPRAID_RW_FUA; + } + + if (unlikely(datalength > U16_MAX || datalength == 0)) { + dev_err(hdev->dev, + "Invalid IO for illegal transfer data length: %u\n", + datalength); + WARN_ON(1); + } + + rw->slba = cpu_to_le64(((u64)start_lba_hi << 32) | start_lba_lo); + /* 0base for nlb */ + rw->nlb = cpu_to_le16((u16)(datalength - 1)); + rw->control = cpu_to_le16(control); +} + +static void spraid_setup_nonio_cmd(struct spraid_dev *hdev, + struct spraid_scsi_nonio *scsi_nonio, + struct scsi_cmnd *scmd) +{ + scsi_nonio->buffer_len = cpu_to_le32(scsi_bufflen(scmd)); + + switch (scmd->sc_data_direction) { + case DMA_NONE: + scsi_nonio->opcode = SPRAID_CMD_NONIO_NONE; + break; + case DMA_TO_DEVICE: + scsi_nonio->opcode = SPRAID_CMD_NONIO_TODEV; + break; + case DMA_FROM_DEVICE: + scsi_nonio->opcode = SPRAID_CMD_NONIO_FROMDEV; + break; + default: + dev_err(hdev->dev, + "Invalid IO for unsupported data direction: %d\n", + scmd->sc_data_direction); + WARN_ON(1); + } +} + +static void spraid_setup_ioq_cmd(struct spraid_dev *hdev, + struct spraid_ioq_command *ioq_cmd, + struct scsi_cmnd *scmd) +{ + memcpy(ioq_cmd->common.cdb, scmd->cmnd, scmd->cmd_len); + ioq_cmd->common.cdb_len = scmd->cmd_len; + + if (spraid_is_rw_scmd(scmd)) + spraid_setup_rw_cmd(hdev, &ioq_cmd->rw, scmd); + else + spraid_setup_nonio_cmd(hdev, &ioq_cmd->scsi_nonio, scmd); +} + +static int spraid_init_iod(struct spraid_dev *hdev, struct spraid_iod *iod, + struct spraid_ioq_command *ioq_cmd, + struct scsi_cmnd *scmd) +{ + if (unlikely(!iod->sense)) { + dev_err(hdev->dev, "Allocate sense data buffer failed\n"); + return -ENOMEM; + } + ioq_cmd->common.sense_addr = cpu_to_le64(iod->sense_dma); + ioq_cmd->common.sense_len = cpu_to_le16(SCSI_SENSE_BUFFERSIZE); + + iod->nsge = 0; + iod->npages = -1; + iod->use_sgl = 0; + iod->sg_drv_mgmt = false; + WRITE_ONCE(iod->state, SPRAID_CMD_IDLE); + + return 0; +} + +static void spraid_free_iod_res(struct spraid_dev *hdev, struct spraid_iod *iod) +{ + const int last_prp = hdev->page_size / sizeof(__le64) - 1; + dma_addr_t dma_addr, next_dma_addr; + struct spraid_sgl_desc *sg_list; + __le64 *prp_list; + void *addr; + int i; + + dma_addr = iod->first_dma; + if (iod->npages == 0) + dma_pool_free(iod->spraidq->prp_small_pool, + spraid_iod_list(iod)[0], dma_addr); + + for (i = 0; i < iod->npages; i++) { + addr = spraid_iod_list(iod)[i]; + + if (iod->use_sgl) { + sg_list = addr; + next_dma_addr = + le64_to_cpu((sg_list[SGES_PER_PAGE - 1]).addr); + } else { + prp_list = addr; + next_dma_addr = le64_to_cpu(prp_list[last_prp]); + } + + dma_pool_free(hdev->prp_page_pool, addr, dma_addr); + dma_addr = next_dma_addr; + } + + if (iod->sg_drv_mgmt && iod->sg != iod->inline_sg) { + iod->sg_drv_mgmt = false; + mempool_free(iod->sg, hdev->iod_mempool); + } + + iod->sense = NULL; + iod->npages = -1; +} + +static int spraid_io_map_data(struct spraid_dev *hdev, struct spraid_iod *iod, + struct scsi_cmnd *scmd, + struct spraid_ioq_command *ioq_cmd) +{ + int ret; + + iod->nsge = scsi_dma_map(scmd); + + /* No data to DMA, it may be scsi no-rw command */ + if (unlikely(iod->nsge == 0)) + return 0; + + iod->length = scsi_bufflen(scmd); + iod->sg = scsi_sglist(scmd); + iod->use_sgl = !spraid_is_prp(hdev, scmd, iod->nsge); + + if (iod->use_sgl) { + ret = spraid_setup_ioq_cmd_sgl(hdev, scmd, ioq_cmd, iod); + } else { + ret = spraid_setup_prps(hdev, iod); + ioq_cmd->common.dptr.prp1 = + cpu_to_le64(sg_dma_address(iod->sg)); + ioq_cmd->common.dptr.prp2 = cpu_to_le64(iod->first_dma); + } + + if (ret) + scsi_dma_unmap(scmd); + + return ret; +} + +static void spraid_map_status(struct spraid_iod *iod, struct scsi_cmnd *scmd, + struct spraid_completion *cqe) +{ + scsi_set_resid(scmd, 0); + + switch ((le16_to_cpu(cqe->status) >> 1) & 0x7f) { + case FW_STAT_OK: + set_host_byte(scmd, DID_OK); + break; + case FW_STAT_NEED_CHECK: + set_host_byte(scmd, DID_OK); + scmd->result |= le16_to_cpu(cqe->status) >> 8; + if (scmd->result & SAM_STAT_CHECK_CONDITION) { + memset(scmd->sense_buffer, 0, SCSI_SENSE_BUFFERSIZE); + memcpy(scmd->sense_buffer, iod->sense, + SCSI_SENSE_BUFFERSIZE); + scmd->result = + (scmd->result & 0x00ffffff) | (DRIVER_SENSE << 24); + } + break; + case FW_STAT_ABORTED: + set_host_byte(scmd, DID_ABORT); + break; + case FW_STAT_NEED_RETRY: + set_host_byte(scmd, DID_REQUEUE); + break; + default: + set_host_byte(scmd, DID_BAD_TARGET); + break; + } +} + +static inline void spraid_get_tag_from_scmd(struct scsi_cmnd *scmd, + u16 *qid, u16 *cid) +{ + u32 tag = blk_mq_unique_tag(scmd->request); + + *qid = blk_mq_unique_tag_to_hwq(tag) + 1; + *cid = blk_mq_unique_tag_to_tag(tag); +} + +static int spraid_queue_command(struct Scsi_Host *shost, struct scsi_cmnd *scmd) +{ + struct spraid_iod *iod = scsi_cmd_priv(scmd); + struct spraid_dev *hdev = shost_priv(shost); + struct scsi_device *sdev = scmd->device; + struct spraid_sdev_hostdata *hostdata; + struct spraid_ioq_command ioq_cmd; + struct spraid_queue *ioq; + unsigned long elapsed; + u16 hwq, cid; + int ret; + + if (unlikely(!scmd)) { + dev_err(hdev->dev, "err, scmd is null\n"); + return 0; + } + + if (unlikely(hdev->state != SPRAID_LIVE)) { + set_host_byte(scmd, DID_NO_CONNECT); + scmd->scsi_done(scmd); + return 0; + } + + if (log_debug_switch) + scsi_print_command(scmd); + + spraid_get_tag_from_scmd(scmd, &hwq, &cid); + hostdata = sdev->hostdata; + ioq = &hdev->queues[hwq]; + memset(&ioq_cmd, 0, sizeof(ioq_cmd)); + ioq_cmd.rw.hdid = cpu_to_le32(hostdata->hdid); + ioq_cmd.rw.command_id = cid; + + spraid_setup_ioq_cmd(hdev, &ioq_cmd, scmd); + + ret = cid * SCSI_SENSE_BUFFERSIZE; + iod->sense = ioq->sense + ret; + iod->sense_dma = ioq->sense_dma_addr + ret; + + ret = spraid_init_iod(hdev, iod, &ioq_cmd, scmd); + if (unlikely(ret)) + return SCSI_MLQUEUE_HOST_BUSY; + + iod->spraidq = ioq; + ret = spraid_io_map_data(hdev, iod, scmd, &ioq_cmd); + if (unlikely(ret)) { + dev_err(hdev->dev, "spraid_io_map_data Err.\n"); + set_host_byte(scmd, DID_ERROR); + scmd->scsi_done(scmd); + ret = 0; + goto deinit_iod; + } + + WRITE_ONCE(iod->state, SPRAID_CMD_IN_FLIGHT); + spraid_submit_cmd(ioq, &ioq_cmd); + elapsed = jiffies - scmd->jiffies_at_alloc; + dev_log_dbg(hdev->dev, + "cid[%d] qid[%d] submit IO cost %3ld.%3ld seconds\n", + cid, hwq, elapsed / HZ, elapsed % HZ); + return 0; + +deinit_iod: + spraid_free_iod_res(hdev, iod); + return ret; +} + +static int spraid_match_dev(struct spraid_dev *hdev, u16 idx, + struct scsi_device *sdev) +{ + if (SPRAID_DEV_INFO_FLAG_VALID(hdev->devices[idx].flag)) { + if (sdev->channel == hdev->devices[idx].channel && + sdev->id == le16_to_cpu(hdev->devices[idx].target) && + sdev->lun < hdev->devices[idx].lun) { + dev_info(hdev->dev, + "Match device success, channel;" + "target:lun[%d:%d:%d]\n", + hdev->devices[idx].channel, + hdev->devices[idx].target, + hdev->devices[idx].lun); + return 1; + } + } + + return 0; +} + +static int spraid_slave_alloc(struct scsi_device *sdev) +{ + struct spraid_sdev_hostdata *hostdata; + struct spraid_dev *hdev; + u16 idx; + + hdev = shost_priv(sdev->host); + hostdata = kzalloc(sizeof(*hostdata), GFP_KERNEL); + if (!hostdata) { + dev_err(hdev->dev, "Alloc scsi host data memory failed\n"); + return -ENOMEM; + } + + down_read(&hdev->devices_rwsem); + for (idx = 0; idx < le32_to_cpu(hdev->ctrl_info->nd); idx++) { + if (spraid_match_dev(hdev, idx, sdev)) + goto scan_host; + } + up_read(&hdev->devices_rwsem); + + kfree(hostdata); + return -ENXIO; + +scan_host: + hostdata->hdid = le32_to_cpu(hdev->devices[idx].hdid); + hostdata->max_io_kb = le16_to_cpu(hdev->devices[idx].max_io_kb); + hostdata->attr = hdev->devices[idx].attr; + hostdata->flag = hdev->devices[idx].flag; + hostdata->rg_id = 0xff; + sdev->hostdata = hostdata; + up_read(&hdev->devices_rwsem); + return 0; +} + +static void spraid_slave_destroy(struct scsi_device *sdev) +{ + kfree(sdev->hostdata); + sdev->hostdata = NULL; +} + +static int spraid_slave_configure(struct scsi_device *sdev) +{ + u16 idx; + unsigned int timeout = scmd_tmout_nonpt * HZ; + struct spraid_dev *hdev = shost_priv(sdev->host); + struct spraid_sdev_hostdata *hostdata = sdev->hostdata; + u32 max_sec = sdev->host->max_sectors; + + if (hostdata) { + idx = hostdata->hdid - 1; + if (sdev->channel == hdev->devices[idx].channel && + sdev->id == le16_to_cpu(hdev->devices[idx].target) && + sdev->lun < hdev->devices[idx].lun) { + if (SPRAID_DEV_INFO_ATTR_PT(hdev->devices[idx].attr)) + timeout = 30 * HZ; + else + timeout = scmd_tmout_nonpt * HZ; + max_sec = le16_to_cpu(hdev->devices[idx].max_io_kb) + << 1; + } else { + dev_err(hdev->dev, + "[%s] err, sdev->channel:id:lun[%d:%d:%lld];" + "devices[%d], channel:target:lun[%d:%d:%d]\n", + __func__, sdev->channel, sdev->id, sdev->lun, + idx, hdev->devices[idx].channel, + hdev->devices[idx].target, + hdev->devices[idx].lun); + } + } else { + dev_err(hdev->dev, "[%s] err, sdev->hostdata is null\n", + __func__); + } + + blk_queue_rq_timeout(sdev->request_queue, timeout); + sdev->eh_timeout = timeout; + + if ((max_sec == 0) || (max_sec > sdev->host->max_sectors)) + max_sec = sdev->host->max_sectors; + + dev_info(hdev->dev, + "[%s] sdev->channel:id:lun[%d:%d:%lld];" + " scmd_timeout[%d]s, maxsec[%d]\n", + __func__, sdev->channel, sdev->id, + sdev->lun, timeout / HZ, max_sec); + + return 0; +} + +static void spraid_shost_init(struct spraid_dev *hdev) +{ + struct pci_dev *pdev = hdev->pdev; + u8 domain, bus; + u32 dev_func; + + domain = pci_domain_nr(pdev->bus); + bus = pdev->bus->number; + dev_func = pdev->devfn; + + hdev->shost->nr_hw_queues = hdev->online_queues - 1; + hdev->shost->can_queue = (hdev->ioq_depth - SPRAID_PTCMDS_PERQ); + + hdev->shost->sg_tablesize = le16_to_cpu(hdev->ctrl_info->max_num_sge); + /* 512B per sector */ + hdev->shost->max_sectors = + (1U << ((hdev->ctrl_info->mdts) * 1U) << 12) / 512; + hdev->shost->cmd_per_lun = MAX_CMD_PER_DEV; + hdev->shost->max_channel = + le16_to_cpu(hdev->ctrl_info->max_channel) - 1; + hdev->shost->max_id = le32_to_cpu(hdev->ctrl_info->max_tgt_id); + hdev->shost->max_lun = le16_to_cpu(hdev->ctrl_info->max_lun); + + hdev->shost->this_id = -1; + hdev->shost->unique_id = (domain << 16) | (bus << 8) | dev_func; + hdev->shost->max_cmd_len = MAX_CDB_LEN; + hdev->shost->hostt->cmd_size = max(spraid_cmd_size(hdev, false, true), + spraid_cmd_size(hdev, false, false)); +} + +static inline void spraid_host_deinit(struct spraid_dev *hdev) +{ + ida_free(&spraid_instance_ida, hdev->instance); +} + +static int spraid_alloc_queue(struct spraid_dev *hdev, u16 qid, u16 depth) +{ + struct spraid_queue *spraidq = &hdev->queues[qid]; + int ret = 0; + + if (hdev->queue_count > qid) { + dev_info(hdev->dev, "[%s] warn: queue[%d] is exist\n", + __func__, qid); + return 0; + } + + spraidq->cqes = dma_alloc_coherent(hdev->dev, CQ_SIZE(depth), + &spraidq->cq_dma_addr, + GFP_KERNEL | __GFP_ZERO); + if (!spraidq->cqes) + return -ENOMEM; + + spraidq->sq_cmds = dma_alloc_coherent(hdev->dev, SQ_SIZE(qid, depth), + &spraidq->sq_dma_addr, + GFP_KERNEL); + if (!spraidq->sq_cmds) { + ret = -ENOMEM; + goto free_cqes; + } + + spin_lock_init(&spraidq->sq_lock); + spin_lock_init(&spraidq->cq_lock); + spraidq->hdev = hdev; + spraidq->q_depth = depth; + spraidq->qid = qid; + spraidq->cq_vector = -1; + hdev->queue_count++; + + /* alloc sense buffer */ + spraidq->sense = dma_alloc_coherent(hdev->dev, SENSE_SIZE(depth), + &spraidq->sense_dma_addr, + GFP_KERNEL | __GFP_ZERO); + if (!spraidq->sense) { + ret = -ENOMEM; + goto free_sq_cmds; + } + + return 0; + +free_sq_cmds: + dma_free_coherent(hdev->dev, SQ_SIZE(qid, depth), + (void *)spraidq->sq_cmds, spraidq->sq_dma_addr); +free_cqes: + dma_free_coherent(hdev->dev, CQ_SIZE(depth), (void *)spraidq->cqes, + spraidq->cq_dma_addr); + return ret; +} + +static int spraid_wait_ready(struct spraid_dev *hdev, u64 cap, bool enabled) +{ + unsigned long timeout = + ((SPRAID_CAP_TIMEOUT(cap) + 1) * SPRAID_CAP_TIMEOUT_UNIT_MS) + jiffies; + u32 bit = enabled ? SPRAID_CSTS_RDY : 0; + + while ((readl(hdev->bar + SPRAID_REG_CSTS) & SPRAID_CSTS_RDY) != bit) { + usleep_range(1000, 2000); + if (fatal_signal_pending(current)) + return -EINTR; + + if (time_after(jiffies, timeout)) { + dev_err(hdev->dev, "Device not ready; aborting %s\n", + enabled ? "initialisation" : "reset"); + return -ENODEV; + } + } + return 0; +} + +static int spraid_shutdown_ctrl(struct spraid_dev *hdev) +{ + unsigned long timeout = hdev->ctrl_info->rtd3e + jiffies; + + hdev->ctrl_config &= ~SPRAID_CC_SHN_MASK; + hdev->ctrl_config |= SPRAID_CC_SHN_NORMAL; + writel(hdev->ctrl_config, hdev->bar + SPRAID_REG_CC); + + while ((readl(hdev->bar + SPRAID_REG_CSTS) & SPRAID_CSTS_SHST_MASK) != + SPRAID_CSTS_SHST_CMPLT) { + msleep(100); + if (fatal_signal_pending(current)) + return -EINTR; + if (time_after(jiffies, timeout)) { + dev_err(hdev->dev, + "Device shutdown incomplete; abort shutdown\n"); + return -ENODEV; + } + } + return 0; +} + +static int spraid_disable_ctrl(struct spraid_dev *hdev) +{ + hdev->ctrl_config &= ~SPRAID_CC_SHN_MASK; + hdev->ctrl_config &= ~SPRAID_CC_ENABLE; + writel(hdev->ctrl_config, hdev->bar + SPRAID_REG_CC); + + return spraid_wait_ready(hdev, hdev->cap, false); +} + +static int spraid_enable_ctrl(struct spraid_dev *hdev) +{ + u64 cap = hdev->cap; + u32 dev_page_min = SPRAID_CAP_MPSMIN(cap) + 12; + u32 page_shift = PAGE_SHIFT; + + if (page_shift < dev_page_min) { + dev_err(hdev->dev, + "Minimum device page size[%u], too large for host[%u]\n", + 1U << dev_page_min, 1U << page_shift); + return -ENODEV; + } + + page_shift = min_t(unsigned int, SPRAID_CAP_MPSMAX(cap) + 12, + PAGE_SHIFT); + hdev->page_size = 1U << page_shift; + + hdev->ctrl_config = SPRAID_CC_CSS_NVM; + hdev->ctrl_config |= (page_shift - 12) << SPRAID_CC_MPS_SHIFT; + hdev->ctrl_config |= SPRAID_CC_AMS_RR | SPRAID_CC_SHN_NONE; + hdev->ctrl_config |= SPRAID_CC_IOSQES | SPRAID_CC_IOCQES; + hdev->ctrl_config |= SPRAID_CC_ENABLE; + writel(hdev->ctrl_config, hdev->bar + SPRAID_REG_CC); + + return spraid_wait_ready(hdev, cap, true); +} + +static void spraid_init_queue(struct spraid_queue *spraidq, u16 qid) +{ + struct spraid_dev *hdev = spraidq->hdev; + + memset((void *)spraidq->cqes, 0, CQ_SIZE(spraidq->q_depth)); + + spraidq->sq_tail = 0; + spraidq->cq_head = 0; + spraidq->cq_phase = 1; + spraidq->q_db = &hdev->dbs[qid * 2 * hdev->db_stride]; + spraidq->prp_small_pool = hdev->prp_small_pool[qid % small_pool_num]; + hdev->online_queues++; +} + +static inline bool spraid_cqe_pending(struct spraid_queue *spraidq) +{ + return (le16_to_cpu(spraidq->cqes[spraidq->cq_head].status) & 1) == + spraidq->cq_phase; +} + +static void spraid_sata_report_zone_handle(struct scsi_cmnd *scmd, + struct spraid_iod *iod) +{ + int i = 0; + unsigned int bytes = 0; + struct scatterlist *sg = scsi_sglist(scmd); + + scsi_for_each_sg(scmd, sg, iod->nsge, i) { + unsigned int offset = 0; + + if (bytes == 0) { + char *hdr; + u32 list_length; + u64 max_lba, opt_lba; + u16 same; + + hdr = sg_virt(sg); + + list_length = get_unaligned_le32(&hdr[0]); + same = get_unaligned_le16(&hdr[4]); + max_lba = get_unaligned_le64(&hdr[8]); + opt_lba = get_unaligned_le64(&hdr[16]); + put_unaligned_be32(list_length, &hdr[0]); + hdr[4] = same & 0xf; + put_unaligned_be64(max_lba, &hdr[8]); + put_unaligned_be64(opt_lba, &hdr[16]); + offset += 64; + bytes += 64; + } + while (offset < sg_dma_len(sg)) { + char *rec; + u8 cond, type, non_seq, reset; + u64 size, start, wp; + + rec = sg_virt(sg) + offset; + type = rec[0] & 0xf; + cond = (rec[1] >> 4) & 0xf; + non_seq = (rec[1] & 2); + reset = (rec[1] & 1); + size = get_unaligned_le64(&rec[8]); + start = get_unaligned_le64(&rec[16]); + wp = get_unaligned_le64(&rec[24]); + rec[0] = type; + rec[1] = (cond << 4) | non_seq | reset; + put_unaligned_be64(size, &rec[8]); + put_unaligned_be64(start, &rec[16]); + put_unaligned_be64(wp, &rec[24]); + WARN_ON(offset + 64 > sg_dma_len(sg)); + offset += 64; + bytes += 64; + } + } +} + +static inline void spraid_handle_ata_cmd(struct spraid_dev *hdev, + struct scsi_cmnd *scmd, + struct spraid_iod *iod) +{ + if (hdev->ctrl_info->card_type != SPRAID_CARD_HBA) + return; + + switch (scmd->cmnd[0]) { + case ZBC_IN: + dev_info(hdev->dev, "[%s] process report zone\n", __func__); + spraid_sata_report_zone_handle(scmd, iod); + break; + default: + break; + } +} + +static void spraid_complete_ioq_cmnd(struct spraid_queue *ioq, + struct spraid_completion *cqe) +{ + struct spraid_dev *hdev = ioq->hdev; + struct blk_mq_tags *tags; + struct scsi_cmnd *scmd; + struct spraid_iod *iod; + struct request *req; + unsigned long elapsed; + + tags = hdev->shost->tag_set.tags[ioq->qid - 1]; + req = blk_mq_tag_to_rq(tags, cqe->cmd_id); + if (unlikely(!req || !blk_mq_request_started(req))) { + dev_warn(hdev->dev, "Invalid id %d completed on queue %d\n", + cqe->cmd_id, ioq->qid); + return; + } + + scmd = blk_mq_rq_to_pdu(req); + iod = scsi_cmd_priv(scmd); + + elapsed = jiffies - scmd->jiffies_at_alloc; + dev_log_dbg(hdev->dev, + "cid[%d] qid[%d] finish IO cost %3ld.%3ld seconds\n", + cqe->cmd_id, ioq->qid, elapsed / HZ, elapsed % HZ); + + if (cmpxchg(&iod->state, SPRAID_CMD_IN_FLIGHT, SPRAID_CMD_COMPLETE) != + SPRAID_CMD_IN_FLIGHT) { + dev_warn(hdev->dev, + "cid[%d] qid[%d] enters abnormal handler;" + " cost %3ld.%3ld seconds\n", + cqe->cmd_id, ioq->qid, elapsed / HZ, elapsed % HZ); + WRITE_ONCE(iod->state, SPRAID_CMD_TMO_COMPLETE); + + if (iod->nsge) { + iod->nsge = 0; + scsi_dma_unmap(scmd); + } + spraid_free_iod_res(hdev, iod); + + return; + } + + spraid_handle_ata_cmd(hdev, scmd, iod); + + spraid_map_status(iod, scmd, cqe); + if (iod->nsge) { + iod->nsge = 0; + scsi_dma_unmap(scmd); + } + spraid_free_iod_res(hdev, iod); + scmd->scsi_done(scmd); +} + +static void spraid_complete_adminq_cmnd(struct spraid_queue *adminq, + struct spraid_completion *cqe) +{ + struct spraid_dev *hdev = adminq->hdev; + struct spraid_cmd *adm_cmd; + + adm_cmd = hdev->adm_cmds + cqe->cmd_id; + if (unlikely(adm_cmd->state == SPRAID_CMD_IDLE)) { + dev_warn(adminq->hdev->dev, + "Invalid id %d completed on queue %d\n", + cqe->cmd_id, le16_to_cpu(cqe->sq_id)); + return; + } + + adm_cmd->status = le16_to_cpu(cqe->status) >> 1; + adm_cmd->result0 = le32_to_cpu(cqe->result); + adm_cmd->result1 = le32_to_cpu(cqe->result1); + + complete(&adm_cmd->cmd_done); +} + +static void spraid_send_aen(struct spraid_dev *hdev, u16 cid); + +static void spraid_complete_aen(struct spraid_queue *spraidq, + struct spraid_completion *cqe) +{ + struct spraid_dev *hdev = spraidq->hdev; + u32 result = le32_to_cpu(cqe->result); + + dev_info(hdev->dev, "rcv aen, cid[%d], status[0x%x], result[0x%x]\n", + cqe->cmd_id, le16_to_cpu(cqe->status) >> 1, result); + + spraid_send_aen(hdev, cqe->cmd_id); + + if ((le16_to_cpu(cqe->status) >> 1) != SPRAID_SC_SUCCESS) + return; + switch (result & 0x7) { + case SPRAID_AEN_NOTICE: + spraid_handle_aen_notice(hdev, result); + break; + case SPRAID_AEN_VS: + spraid_handle_aen_vs(hdev, result, le32_to_cpu(cqe->result1)); + break; + default: + dev_warn(hdev->dev, "Unsupported async event type: %u\n", + result & 0x7); + break; + } +} + +static void spraid_complete_ioq_sync_cmnd(struct spraid_queue *ioq, + struct spraid_completion *cqe) +{ + struct spraid_dev *hdev = ioq->hdev; + struct spraid_cmd *ptcmd; + + ptcmd = hdev->ioq_ptcmds + (ioq->qid - 1) * SPRAID_PTCMDS_PERQ + + cqe->cmd_id - SPRAID_IO_BLK_MQ_DEPTH; + + ptcmd->status = le16_to_cpu(cqe->status) >> 1; + ptcmd->result0 = le32_to_cpu(cqe->result); + ptcmd->result1 = le32_to_cpu(cqe->result1); + + complete(&ptcmd->cmd_done); +} + +static inline void spraid_handle_cqe(struct spraid_queue *spraidq, u16 idx) +{ + struct spraid_completion *cqe = &spraidq->cqes[idx]; + struct spraid_dev *hdev = spraidq->hdev; + + if (unlikely(cqe->cmd_id >= spraidq->q_depth)) { + dev_err(hdev->dev, + "Invalid command id[%d] completed on queue %d\n", + cqe->cmd_id, cqe->sq_id); + return; + } + + dev_log_dbg(hdev->dev, "cid[%d] qid[%d];" + " result[0x%x], sq_id[%d], status[0x%x]\n", + cqe->cmd_id, spraidq->qid, le32_to_cpu(cqe->result), + le16_to_cpu(cqe->sq_id), le16_to_cpu(cqe->status)); + + if (unlikely(spraidq->qid == 0 + && cqe->cmd_id >= SPRAID_AQ_BLK_MQ_DEPTH)) { + spraid_complete_aen(spraidq, cqe); + return; + } + + if (unlikely(spraidq->qid && cqe->cmd_id >= SPRAID_IO_BLK_MQ_DEPTH)) { + spraid_complete_ioq_sync_cmnd(spraidq, cqe); + return; + } + + if (spraidq->qid) + spraid_complete_ioq_cmnd(spraidq, cqe); + else + spraid_complete_adminq_cmnd(spraidq, cqe); +} + +static void spraid_complete_cqes(struct spraid_queue *spraidq, + u16 start, u16 end) +{ + while (start != end) { + spraid_handle_cqe(spraidq, start); + if (++start == spraidq->q_depth) + start = 0; + } +} + +static inline void spraid_update_cq_head(struct spraid_queue *spraidq) +{ + if (++spraidq->cq_head == spraidq->q_depth) { + spraidq->cq_head = 0; + spraidq->cq_phase = !spraidq->cq_phase; + } +} + +static inline bool spraid_process_cq(struct spraid_queue *spraidq, + u16 *start, u16 *end, int tag) +{ + bool found = false; + + *start = spraidq->cq_head; + while (!found && spraid_cqe_pending(spraidq)) { + if (spraidq->cqes[spraidq->cq_head].cmd_id == tag) + found = true; + spraid_update_cq_head(spraidq); + } + *end = spraidq->cq_head; + + if (*start != *end) + writel(spraidq->cq_head, + spraidq->q_db + spraidq->hdev->db_stride); + + return found; +} + +static bool spraid_poll_cq(struct spraid_queue *spraidq, int cid) +{ + u16 start, end; + bool found; + + if (!spraid_cqe_pending(spraidq)) + return 0; + + spin_lock_irq(&spraidq->cq_lock); + found = spraid_process_cq(spraidq, &start, &end, cid); + spin_unlock_irq(&spraidq->cq_lock); + + spraid_complete_cqes(spraidq, start, end); + return found; +} + +static irqreturn_t spraid_irq(int irq, void *data) +{ + struct spraid_queue *spraidq = data; + irqreturn_t ret = IRQ_NONE; + u16 start, end; + + spin_lock(&spraidq->cq_lock); + if (spraidq->cq_head != spraidq->last_cq_head) + ret = IRQ_HANDLED; + + spraid_process_cq(spraidq, &start, &end, -1); + spraidq->last_cq_head = spraidq->cq_head; + spin_unlock(&spraidq->cq_lock); + + if (start != end) { + spraid_complete_cqes(spraidq, start, end); + ret = IRQ_HANDLED; + } + return ret; +} + +static int spraid_setup_admin_queue(struct spraid_dev *hdev) +{ + struct spraid_queue *adminq = &hdev->queues[0]; + u32 aqa; + int ret; + + dev_info(hdev->dev, "[%s] start disable ctrl\n", __func__); + + ret = spraid_disable_ctrl(hdev); + if (ret) + return ret; + + ret = spraid_alloc_queue(hdev, 0, SPRAID_AQ_DEPTH); + if (ret) + return ret; + + aqa = adminq->q_depth - 1; + aqa |= aqa << 16; + writel(aqa, hdev->bar + SPRAID_REG_AQA); + lo_hi_writeq(adminq->sq_dma_addr, hdev->bar + SPRAID_REG_ASQ); + lo_hi_writeq(adminq->cq_dma_addr, hdev->bar + SPRAID_REG_ACQ); + + dev_info(hdev->dev, "[%s] start enable ctrl\n", __func__); + + ret = spraid_enable_ctrl(hdev); + if (ret) { + ret = -ENODEV; + goto free_queue; + } + + adminq->cq_vector = 0; + spraid_init_queue(adminq, 0); + ret = pci_request_irq(hdev->pdev, adminq->cq_vector, spraid_irq, NULL, + adminq, "spraid%d_q%d", + hdev->instance, adminq->qid); + + if (ret) { + adminq->cq_vector = -1; + hdev->online_queues--; + goto free_queue; + } + + dev_info(hdev->dev, "[%s] success, queuecount:[%d], onlinequeue:[%d]\n", + __func__, hdev->queue_count, hdev->online_queues); + + return 0; + +free_queue: + spraid_free_queue(adminq); + return ret; +} + +static u32 spraid_bar_size(struct spraid_dev *hdev, u32 nr_ioqs) +{ + return (SPRAID_REG_DBS + ((nr_ioqs + 1) * 8 * hdev->db_stride)); +} + +static int spraid_alloc_admin_cmds(struct spraid_dev *hdev) +{ + int i; + + INIT_LIST_HEAD(&hdev->adm_cmd_list); + spin_lock_init(&hdev->adm_cmd_lock); + + hdev->adm_cmds = kcalloc_node(SPRAID_AQ_BLK_MQ_DEPTH, + sizeof(struct spraid_cmd), + GFP_KERNEL, hdev->numa_node); + + if (!hdev->adm_cmds) { + dev_err(hdev->dev, "Alloc admin cmds failed\n"); + return -ENOMEM; + } + + for (i = 0; i < SPRAID_AQ_BLK_MQ_DEPTH; i++) { + hdev->adm_cmds[i].qid = 0; + hdev->adm_cmds[i].cid = i; + list_add_tail(&(hdev->adm_cmds[i].list), &hdev->adm_cmd_list); + } + + dev_info(hdev->dev, "Alloc admin cmds success, num[%d]\n", + SPRAID_AQ_BLK_MQ_DEPTH); + + return 0; +} + +static void spraid_free_admin_cmds(struct spraid_dev *hdev) +{ + kfree(hdev->adm_cmds); + hdev->adm_cmds = NULL; + INIT_LIST_HEAD(&hdev->adm_cmd_list); +} + +static struct spraid_cmd *spraid_get_cmd(struct spraid_dev *hdev, + enum spraid_cmd_type type) +{ + struct spraid_cmd *cmd = NULL; + unsigned long flags; + struct list_head *head = &hdev->adm_cmd_list; + spinlock_t *slock = &hdev->adm_cmd_lock; + + if (type == SPRAID_CMD_IOPT) { + head = &hdev->ioq_pt_list; + slock = &hdev->ioq_pt_lock; + } + + spin_lock_irqsave(slock, flags); + if (list_empty(head)) { + spin_unlock_irqrestore(slock, flags); + dev_err(hdev->dev, "err, cmd[%d] list empty\n", type); + return NULL; + } + cmd = list_entry(head->next, struct spraid_cmd, list); + list_del_init(&cmd->list); + spin_unlock_irqrestore(slock, flags); + + WRITE_ONCE(cmd->state, SPRAID_CMD_IN_FLIGHT); + + return cmd; +} + +static void spraid_put_cmd(struct spraid_dev *hdev, struct spraid_cmd *cmd, + enum spraid_cmd_type type) +{ + unsigned long flags; + struct list_head *head = &hdev->adm_cmd_list; + spinlock_t *slock = &hdev->adm_cmd_lock; + + if (type == SPRAID_CMD_IOPT) { + head = &hdev->ioq_pt_list; + slock = &hdev->ioq_pt_lock; + } + + spin_lock_irqsave(slock, flags); + WRITE_ONCE(cmd->state, SPRAID_CMD_IDLE); + list_add_tail(&cmd->list, head); + spin_unlock_irqrestore(slock, flags); +} + + +static int spraid_submit_admin_sync_cmd(struct spraid_dev *hdev, + struct spraid_admin_command *cmd, + u32 *result0, u32 *result1, u32 timeout) +{ + struct spraid_cmd *adm_cmd = spraid_get_cmd(hdev, SPRAID_CMD_ADM); + + if (!adm_cmd) { + dev_err(hdev->dev, "err, get admin cmd failed\n"); + return -EFAULT; + } + + timeout = timeout ? timeout : ADMIN_TIMEOUT; + + init_completion(&adm_cmd->cmd_done); + + cmd->common.command_id = adm_cmd->cid; + spraid_submit_cmd(&hdev->queues[0], cmd); + + if (!wait_for_completion_timeout(&adm_cmd->cmd_done, timeout)) { + dev_err(hdev->dev, "[%s] cid[%d] qid[%d] timeout;" + " opcode[0x%x] subopcode[0x%x]\n", + __func__, adm_cmd->cid, adm_cmd->qid, + cmd->usr_cmd.opcode, cmd->usr_cmd.info_0.subopcode); + WRITE_ONCE(adm_cmd->state, SPRAID_CMD_TIMEOUT); + spraid_put_cmd(hdev, adm_cmd, SPRAID_CMD_ADM); + return -EINVAL; + } + + if (result0) + *result0 = adm_cmd->result0; + if (result1) + *result1 = adm_cmd->result1; + + spraid_put_cmd(hdev, adm_cmd, SPRAID_CMD_ADM); + + return adm_cmd->status; +} + +static int spraid_create_cq(struct spraid_dev *hdev, u16 qid, + struct spraid_queue *spraidq, u16 cq_vector) +{ + struct spraid_admin_command admin_cmd; + int flags = SPRAID_QUEUE_PHYS_CONTIG | SPRAID_CQ_IRQ_ENABLED; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.create_cq.opcode = SPRAID_ADMIN_CREATE_CQ; + admin_cmd.create_cq.prp1 = cpu_to_le64(spraidq->cq_dma_addr); + admin_cmd.create_cq.cqid = cpu_to_le16(qid); + admin_cmd.create_cq.qsize = cpu_to_le16(spraidq->q_depth - 1); + admin_cmd.create_cq.cq_flags = cpu_to_le16(flags); + admin_cmd.create_cq.irq_vector = cpu_to_le16(cq_vector); + + return spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); +} + +static int spraid_create_sq(struct spraid_dev *hdev, u16 qid, + struct spraid_queue *spraidq) +{ + struct spraid_admin_command admin_cmd; + int flags = SPRAID_QUEUE_PHYS_CONTIG; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.create_sq.opcode = SPRAID_ADMIN_CREATE_SQ; + admin_cmd.create_sq.prp1 = cpu_to_le64(spraidq->sq_dma_addr); + admin_cmd.create_sq.sqid = cpu_to_le16(qid); + admin_cmd.create_sq.qsize = cpu_to_le16(spraidq->q_depth - 1); + admin_cmd.create_sq.sq_flags = cpu_to_le16(flags); + admin_cmd.create_sq.cqid = cpu_to_le16(qid); + + return spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); +} + +static void spraid_free_queue(struct spraid_queue *spraidq) +{ + struct spraid_dev *hdev = spraidq->hdev; + + hdev->queue_count--; + dma_free_coherent(hdev->dev, CQ_SIZE(spraidq->q_depth), + (void *)spraidq->cqes, spraidq->cq_dma_addr); + dma_free_coherent(hdev->dev, SQ_SIZE(spraidq->qid, spraidq->q_depth), + spraidq->sq_cmds, spraidq->sq_dma_addr); + dma_free_coherent(hdev->dev, SENSE_SIZE(spraidq->q_depth), + spraidq->sense, spraidq->sense_dma_addr); +} + +static void spraid_free_admin_queue(struct spraid_dev *hdev) +{ + spraid_free_queue(&hdev->queues[0]); +} + +static void spraid_free_io_queues(struct spraid_dev *hdev) +{ + int i; + + for (i = hdev->queue_count - 1; i >= 1; i--) + spraid_free_queue(&hdev->queues[i]); +} + +static int spraid_delete_queue(struct spraid_dev *hdev, u8 op, u16 id) +{ + struct spraid_admin_command admin_cmd; + int ret; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.delete_queue.opcode = op; + admin_cmd.delete_queue.qid = cpu_to_le16(id); + + ret = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); + + if (ret) + dev_err(hdev->dev, "Delete %s:[%d] failed\n", + (op == SPRAID_ADMIN_DELETE_CQ) ? "cq" : "sq", id); + + return ret; +} + +static int spraid_delete_cq(struct spraid_dev *hdev, u16 cqid) +{ + return spraid_delete_queue(hdev, SPRAID_ADMIN_DELETE_CQ, cqid); +} + +static int spraid_delete_sq(struct spraid_dev *hdev, u16 sqid) +{ + return spraid_delete_queue(hdev, SPRAID_ADMIN_DELETE_SQ, sqid); +} + +static int spraid_create_queue(struct spraid_queue *spraidq, u16 qid) +{ + struct spraid_dev *hdev = spraidq->hdev; + u16 cq_vector; + int ret; + + cq_vector = (hdev->num_vecs == 1) ? 0 : qid; + ret = spraid_create_cq(hdev, qid, spraidq, cq_vector); + if (ret) + return ret; + + ret = spraid_create_sq(hdev, qid, spraidq); + if (ret) + goto delete_cq; + + spraid_init_queue(spraidq, qid); + spraidq->cq_vector = cq_vector; + + ret = pci_request_irq(hdev->pdev, cq_vector, spraid_irq, NULL, + spraidq, "spraid%d_q%d", hdev->instance, qid); + + if (ret) { + dev_err(hdev->dev, "Request queue[%d] irq failed\n", qid); + goto delete_sq; + } + + return 0; + +delete_sq: + spraidq->cq_vector = -1; + hdev->online_queues--; + spraid_delete_sq(hdev, qid); +delete_cq: + spraid_delete_cq(hdev, qid); + + return ret; +} + +static int spraid_create_io_queues(struct spraid_dev *hdev) +{ + u32 i, max; + int ret = 0; + + max = min(hdev->max_qid, hdev->queue_count - 1); + for (i = hdev->online_queues; i <= max; i++) { + ret = spraid_create_queue(&hdev->queues[i], i); + if (ret) { + dev_err(hdev->dev, "Create queue[%d] failed\n", i); + break; + } + } + + dev_info(hdev->dev, "[%s] queue_count[%d], online_queue[%d]", + __func__, hdev->queue_count, hdev->online_queues); + + return ret >= 0 ? 0 : ret; +} + +static int spraid_set_features(struct spraid_dev *hdev, u32 fid, + u32 dword11, void *buffer, + size_t buflen, u32 *result) +{ + struct spraid_admin_command admin_cmd; + int ret; + u8 *data_ptr = NULL; + dma_addr_t data_dma = 0; + + if (buffer && buflen) { + data_ptr = dma_alloc_coherent(hdev->dev, buflen, + &data_dma, GFP_KERNEL); + if (!data_ptr) + return -ENOMEM; + + memcpy(data_ptr, buffer, buflen); + } + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.features.opcode = SPRAID_ADMIN_SET_FEATURES; + admin_cmd.features.fid = cpu_to_le32(fid); + admin_cmd.features.dword11 = cpu_to_le32(dword11); + admin_cmd.common.dptr.prp1 = cpu_to_le64(data_dma); + + ret = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, result, NULL, 0); + + if (data_ptr) + dma_free_coherent(hdev->dev, buflen, data_ptr, data_dma); + + return ret; +} + +static int spraid_configure_timestamp(struct spraid_dev *hdev) +{ + __le64 ts; + int ret; + + ts = cpu_to_le64(ktime_to_ms(ktime_get_real())); + ret = spraid_set_features(hdev, SPRAID_FEAT_TIMESTAMP, + 0, &ts, sizeof(ts), NULL); + + if (ret) + dev_err(hdev->dev, "set timestamp failed: %d\n", ret); + return ret; +} + +static int spraid_set_queue_cnt(struct spraid_dev *hdev, u32 *cnt) +{ + u32 q_cnt = (*cnt - 1) | ((*cnt - 1) << 16); + u32 nr_ioqs, result; + int status; + + status = spraid_set_features(hdev, SPRAID_FEAT_NUM_QUEUES, + q_cnt, NULL, 0, &result); + if (status) { + dev_err(hdev->dev, "Set queue count failed, status: %d\n", + status); + return -EIO; + } + + nr_ioqs = min(result & 0xffff, result >> 16) + 1; + *cnt = min(*cnt, nr_ioqs); + if (*cnt == 0) { + dev_err(hdev->dev, "Illegal queue count: zero\n"); + return -EIO; + } + return 0; +} + +static int spraid_setup_io_queues(struct spraid_dev *hdev) +{ + struct spraid_queue *adminq = &hdev->queues[0]; + struct pci_dev *pdev = hdev->pdev; + u32 nr_ioqs = num_online_cpus(); + u32 i, size; + int ret; + + struct irq_affinity affd = { + .pre_vectors = 1 + }; + + ret = spraid_set_queue_cnt(hdev, &nr_ioqs); + if (ret < 0) + return ret; + + size = spraid_bar_size(hdev, nr_ioqs); + ret = spraid_remap_bar(hdev, size); + if (ret) + return -ENOMEM; + + adminq->q_db = hdev->dbs; + + pci_free_irq(pdev, 0, adminq); + pci_free_irq_vectors(pdev); + + ret = pci_alloc_irq_vectors_affinity(pdev, 1, (nr_ioqs + 1), + PCI_IRQ_ALL_TYPES | PCI_IRQ_AFFINITY, &affd); + if (ret <= 0) + return -EIO; + + hdev->num_vecs = ret; + + hdev->max_qid = max(ret - 1, 1); + + ret = pci_request_irq(pdev, adminq->cq_vector, spraid_irq, NULL, + adminq, "spraid%d_q%d", + hdev->instance, adminq->qid); + if (ret) { + dev_err(hdev->dev, "Request admin irq failed\n"); + adminq->cq_vector = -1; + return ret; + } + + for (i = hdev->queue_count; i <= hdev->max_qid; i++) { + ret = spraid_alloc_queue(hdev, i, hdev->ioq_depth); + if (ret) + break; + } + dev_info(hdev->dev, "[%s] max_qid: %d, queue_count: %d;" + " online_queue: %d, ioq_depth: %d\n", + __func__, hdev->max_qid, hdev->queue_count, + hdev->online_queues, hdev->ioq_depth); + + return spraid_create_io_queues(hdev); +} + +static void spraid_delete_io_queues(struct spraid_dev *hdev) +{ + u16 queues = hdev->online_queues - 1; + u8 opcode = SPRAID_ADMIN_DELETE_SQ; + u16 i, pass; + + if (!pci_device_is_present(hdev->pdev)) { + dev_err(hdev->dev, + "pci_device is not present, skip disable io queues\n"); + return; + } + + if (hdev->online_queues < 2) { + dev_err(hdev->dev, "[%s] err, io queue has been delete\n", + __func__); + return; + } + + for (pass = 0; pass < 2; pass++) { + for (i = queues; i > 0; i--) + if (spraid_delete_queue(hdev, opcode, i)) + break; + + opcode = SPRAID_ADMIN_DELETE_CQ; + } +} + +static void spraid_remove_io_queues(struct spraid_dev *hdev) +{ + spraid_delete_io_queues(hdev); + spraid_free_io_queues(hdev); +} + +static void spraid_pci_disable(struct spraid_dev *hdev) +{ + struct pci_dev *pdev = hdev->pdev; + u32 i; + + for (i = 0; i < hdev->online_queues; i++) + pci_free_irq(pdev, hdev->queues[i].cq_vector, &hdev->queues[i]); + pci_free_irq_vectors(pdev); + if (pci_is_enabled(pdev)) { + pci_disable_pcie_error_reporting(pdev); + pci_disable_device(pdev); + } + hdev->online_queues = 0; +} + +static void spraid_disable_admin_queue(struct spraid_dev *hdev, bool shutdown) +{ + struct spraid_queue *adminq = &hdev->queues[0]; + u16 start, end; + + if (pci_device_is_present(hdev->pdev)) { + if (shutdown) + spraid_shutdown_ctrl(hdev); + else + spraid_disable_ctrl(hdev); + } + + if (hdev->queue_count == 0) { + dev_err(hdev->dev, "[%s] err, admin queue has been delete\n", + __func__); + return; + } + + spin_lock_irq(&adminq->cq_lock); + spraid_process_cq(adminq, &start, &end, -1); + spin_unlock_irq(&adminq->cq_lock); + + spraid_complete_cqes(adminq, start, end); + spraid_free_admin_queue(hdev); +} + +static int spraid_create_dma_pools(struct spraid_dev *hdev) +{ + int i; + char poolname[20] = { 0 }; + + hdev->prp_page_pool = dma_pool_create("prp list page", hdev->dev, + PAGE_SIZE, PAGE_SIZE, 0); + + if (!hdev->prp_page_pool) { + dev_err(hdev->dev, "create prp_page_pool failed\n"); + return -ENOMEM; + } + + for (i = 0; i < small_pool_num; i++) { + sprintf(poolname, "prp_list_256_%d", i); + hdev->prp_small_pool[i] = + dma_pool_create(poolname, hdev->dev, SMALL_POOL_SIZE, + SMALL_POOL_SIZE, 0); + + if (!hdev->prp_small_pool[i]) { + dev_err(hdev->dev, "create prp_small_pool %d failed\n", + i); + goto destroy_prp_small_pool; + } + } + + return 0; + +destroy_prp_small_pool: + while (i > 0) + dma_pool_destroy(hdev->prp_small_pool[--i]); + dma_pool_destroy(hdev->prp_page_pool); + + return -ENOMEM; +} + +static void spraid_destroy_dma_pools(struct spraid_dev *hdev) +{ + int i; + + for (i = 0; i < small_pool_num; i++) + dma_pool_destroy(hdev->prp_small_pool[i]); + dma_pool_destroy(hdev->prp_page_pool); +} + +static int spraid_get_dev_list(struct spraid_dev *hdev, + struct spraid_dev_info *devices) +{ + u32 nd = le32_to_cpu(hdev->ctrl_info->nd); + struct spraid_admin_command admin_cmd; + struct spraid_dev_list *list_buf; + dma_addr_t data_dma = 0; + u32 i, idx, hdid, ndev; + int ret = 0; + + list_buf = dma_alloc_coherent(hdev->dev, PAGE_SIZE, + &data_dma, GFP_KERNEL); + if (!list_buf) + return -ENOMEM; + + for (idx = 0; idx < nd;) { + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.get_info.opcode = SPRAID_ADMIN_GET_INFO; + admin_cmd.get_info.type = SPRAID_GET_INFO_DEV_LIST; + admin_cmd.get_info.cdw11 = cpu_to_le32(idx); + admin_cmd.common.dptr.prp1 = cpu_to_le64(data_dma); + + ret = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, + NULL, NULL, 0); + + if (ret) { + dev_err(hdev->dev, "Get device list failed, nd: %u;" + "idx: %u, ret: %d\n", + nd, idx, ret); + goto out; + } + ndev = le32_to_cpu(list_buf->dev_num); + + dev_info(hdev->dev, "ndev numbers: %u\n", ndev); + + for (i = 0; i < ndev; i++) { + hdid = le32_to_cpu(list_buf->devices[i].hdid); + dev_info(hdev->dev, "list_buf->devices[%d], hdid: %u;" + "target: %d, channel: %d, lun: %d, attr[0x%x]\n", + i, hdid, + le16_to_cpu(list_buf->devices[i].target), + list_buf->devices[i].channel, + list_buf->devices[i].lun, + list_buf->devices[i].attr); + if (hdid > nd || hdid == 0) { + dev_err(hdev->dev, "err, hdid[%d] invalid\n", + hdid); + continue; + } + memcpy(&devices[hdid - 1], &list_buf->devices[i], + sizeof(struct spraid_dev_info)); + } + idx += ndev; + + if (idx < MAX_DEV_ENTRY_PER_PAGE_4K) + break; + } + +out: + dma_free_coherent(hdev->dev, PAGE_SIZE, list_buf, data_dma); + return ret; +} + +static void spraid_send_aen(struct spraid_dev *hdev, u16 cid) +{ + struct spraid_queue *adminq = &hdev->queues[0]; + struct spraid_admin_command admin_cmd; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.common.opcode = SPRAID_ADMIN_ASYNC_EVENT; + admin_cmd.common.command_id = cid; + + spraid_submit_cmd(adminq, &admin_cmd); + dev_info(hdev->dev, "send aen, cid[%d]\n", cid); +} + +static inline void spraid_send_all_aen(struct spraid_dev *hdev) +{ + u16 i; + + for (i = 0; i < hdev->ctrl_info->aerl; i++) + spraid_send_aen(hdev, i + SPRAID_AQ_BLK_MQ_DEPTH); +} + +static int spraid_add_device(struct spraid_dev *hdev, + struct spraid_dev_info *device) +{ + struct Scsi_Host *shost = hdev->shost; + struct scsi_device *sdev; + + dev_info(hdev->dev, "add device, hdid: %u target: %d, channel: %d;" + " lun: %d, attr[0x%x]\n", + le32_to_cpu(device->hdid), le16_to_cpu(device->target), + device->channel, device->lun, device->attr); + + sdev = scsi_device_lookup(shost, device->channel, + le16_to_cpu(device->target), 0); + if (sdev) { + dev_warn(hdev->dev, "Device is already exist, channel: %d;" + " target_id: %d, lun: %d\n", + device->channel, le16_to_cpu(device->target), 0); + scsi_device_put(sdev); + return -EEXIST; + } + scsi_add_device(shost, device->channel, le16_to_cpu(device->target), 0); + return 0; +} + +static int spraid_rescan_device(struct spraid_dev *hdev, + struct spraid_dev_info *device) +{ + struct Scsi_Host *shost = hdev->shost; + struct scsi_device *sdev; + + dev_info(hdev->dev, "rescan device, hdid: %u target: %d, channel: %d;" + " lun: %d, attr[0x%x]\n", + le32_to_cpu(device->hdid), le16_to_cpu(device->target), + device->channel, device->lun, device->attr); + + sdev = scsi_device_lookup(shost, device->channel, + le16_to_cpu(device->target), 0); + if (!sdev) { + dev_warn(hdev->dev, "device is not exit rescan it, channel: %d;" + " target_id: %d, lun: %d\n", + device->channel, le16_to_cpu(device->target), 0); + return -ENODEV; + } + + scsi_rescan_device(&sdev->sdev_gendev); + scsi_device_put(sdev); + return 0; +} + +static int spraid_remove_device(struct spraid_dev *hdev, + struct spraid_dev_info *org_device) +{ + struct Scsi_Host *shost = hdev->shost; + struct scsi_device *sdev; + + dev_info(hdev->dev, "remove device, hdid: %u target: %d, channel: %d;" + " lun: %d, attr[0x%x]\n", + le32_to_cpu(org_device->hdid), le16_to_cpu(org_device->target), + org_device->channel, org_device->lun, org_device->attr); + + sdev = scsi_device_lookup(shost, org_device->channel, + le16_to_cpu(org_device->target), 0); + if (!sdev) { + dev_warn(hdev->dev, "device is not exit remove it, channel: %d;" + " target_id: %d, lun: %d\n", + org_device->channel, + le16_to_cpu(org_device->target), 0); + return -ENODEV; + } + + scsi_remove_device(sdev); + scsi_device_put(sdev); + return 0; +} + +static int spraid_dev_list_init(struct spraid_dev *hdev) +{ + u32 nd = le32_to_cpu(hdev->ctrl_info->nd); + int i, ret; + + hdev->devices = kzalloc_node(nd * sizeof(struct spraid_dev_info), + GFP_KERNEL, hdev->numa_node); + if (!hdev->devices) + return -ENOMEM; + + ret = spraid_get_dev_list(hdev, hdev->devices); + if (ret) { + dev_err(hdev->dev, + "Ignore failure of getting device list;" + " within initialization\n"); + return 0; + } + + for (i = 0; i < nd; i++) { + if (SPRAID_DEV_INFO_FLAG_VALID(hdev->devices[i].flag) && + SPRAID_DEV_INFO_ATTR_BOOT(hdev->devices[i].attr)) { + spraid_add_device(hdev, &hdev->devices[i]); + break; + } + } + return 0; +} + +static int luntarget_cmp_func(const void *l, const void *r) +{ + const struct spraid_dev_info *ln = l; + const struct spraid_dev_info *rn = r; + + if (ln->channel == rn->channel) + return le16_to_cpu(ln->target) - le16_to_cpu(rn->target); + + return ln->channel - rn->channel; +} + +static void spraid_scan_work(struct work_struct *work) +{ + struct spraid_dev *hdev = + container_of(work, struct spraid_dev, scan_work); + struct spraid_dev_info *devices, *org_devices; + struct spraid_dev_info *sortdevice; + u32 nd = le32_to_cpu(hdev->ctrl_info->nd); + u8 flag, org_flag; + int i, ret; + int count = 0; + + devices = kcalloc(nd, sizeof(struct spraid_dev_info), GFP_KERNEL); + if (!devices) + return; + + sortdevice = kcalloc(nd, sizeof(struct spraid_dev_info), GFP_KERNEL); + if (!sortdevice) + goto free_list; + + ret = spraid_get_dev_list(hdev, devices); + if (ret) + goto free_all; + org_devices = hdev->devices; + for (i = 0; i < nd; i++) { + org_flag = org_devices[i].flag; + flag = devices[i].flag; + + dev_log_dbg(hdev->dev, "i: %d, org_flag: 0x%x, flag: 0x%x\n", + i, org_flag, flag); + + if (SPRAID_DEV_INFO_FLAG_VALID(flag)) { + if (!SPRAID_DEV_INFO_FLAG_VALID(org_flag)) { + down_write(&hdev->devices_rwsem); + memcpy(&org_devices[i], &devices[i], + sizeof(struct spraid_dev_info)); + memcpy(&sortdevice[count++], &devices[i], + sizeof(struct spraid_dev_info)); + up_write(&hdev->devices_rwsem); + } else if (SPRAID_DEV_INFO_FLAG_CHANGE(flag)) { + spraid_rescan_device(hdev, &devices[i]); + } + } else { + if (SPRAID_DEV_INFO_FLAG_VALID(org_flag)) { + down_write(&hdev->devices_rwsem); + org_devices[i].flag &= 0xfe; + up_write(&hdev->devices_rwsem); + spraid_remove_device(hdev, &org_devices[i]); + } + } + } + + dev_info(hdev->dev, "scan work add device count = %d\n", count); + + sort(sortdevice, count, sizeof(sortdevice[0]), + luntarget_cmp_func, NULL); + + for (i = 0; i < count; i++) + spraid_add_device(hdev, &sortdevice[i]); + +free_all: + kfree(sortdevice); +free_list: + kfree(devices); +} + +static void spraid_timesyn_work(struct work_struct *work) +{ + struct spraid_dev *hdev = + container_of(work, struct spraid_dev, timesyn_work); + + spraid_configure_timestamp(hdev); +} + +static int spraid_init_ctrl_info(struct spraid_dev *hdev); +static void spraid_fw_act_work(struct work_struct *work) +{ + struct spraid_dev *hdev = + container_of(work, struct spraid_dev, fw_act_work); + + if (spraid_init_ctrl_info(hdev)) + dev_err(hdev->dev, "get ctrl info failed after fw act\n"); +} + +static void spraid_queue_scan(struct spraid_dev *hdev) +{ + queue_work(spraid_wq, &hdev->scan_work); +} + +static void spraid_handle_aen_notice(struct spraid_dev *hdev, u32 result) +{ + switch ((result & 0xff00) >> 8) { + case SPRAID_AEN_DEV_CHANGED: + spraid_queue_scan(hdev); + break; + case SPRAID_AEN_FW_ACT_START: + dev_info(hdev->dev, "fw activation starting\n"); + break; + case SPRAID_AEN_HOST_PROBING: + break; + default: + dev_warn(hdev->dev, "async event result %08x\n", result); + } +} + +static void spraid_handle_aen_vs(struct spraid_dev *hdev, + u32 result, u32 result1) +{ + switch ((result & 0xff00) >> 8) { + case SPRAID_AEN_TIMESYN: + queue_work(spraid_wq, &hdev->timesyn_work); + break; + case SPRAID_AEN_FW_ACT_FINISH: + dev_info(hdev->dev, "fw activation finish\n"); + queue_work(spraid_wq, &hdev->fw_act_work); + break; + case SPRAID_AEN_EVENT_MIN ... SPRAID_AEN_EVENT_MAX: + dev_info(hdev->dev, "rcv card event[%d];" + " param1[0x%x] param2[0x%x]\n", + (result & 0xff00) >> 8, result, result1); + break; + default: + dev_warn(hdev->dev, "async event result: 0x%x\n", result); + } +} + +static int spraid_alloc_resources(struct spraid_dev *hdev) +{ + int ret, nqueue; + + ret = ida_alloc(&spraid_instance_ida, GFP_KERNEL); + if (ret < 0) { + dev_err(hdev->dev, "Get instance id failed\n"); + return ret; + } + hdev->instance = ret; + + hdev->ctrl_info = kzalloc_node(sizeof(*hdev->ctrl_info), + GFP_KERNEL, hdev->numa_node); + if (!hdev->ctrl_info) { + ret = -ENOMEM; + goto release_instance; + } + + ret = spraid_create_dma_pools(hdev); + if (ret) + goto free_ctrl_info; + nqueue = num_possible_cpus() + 1; + hdev->queues = kcalloc_node(nqueue, sizeof(struct spraid_queue), + GFP_KERNEL, hdev->numa_node); + if (!hdev->queues) { + ret = -ENOMEM; + goto destroy_dma_pools; + } + + ret = spraid_alloc_admin_cmds(hdev); + if (ret) + goto free_queues; + + dev_info(hdev->dev, "[%s] queues num: %d\n", __func__, nqueue); + + return 0; + +free_queues: + kfree(hdev->queues); +destroy_dma_pools: + spraid_destroy_dma_pools(hdev); +free_ctrl_info: + kfree(hdev->ctrl_info); +release_instance: + ida_free(&spraid_instance_ida, hdev->instance); + return ret; +} + +static void spraid_free_resources(struct spraid_dev *hdev) +{ + spraid_free_admin_cmds(hdev); + kfree(hdev->queues); + spraid_destroy_dma_pools(hdev); + kfree(hdev->ctrl_info); + ida_free(&spraid_instance_ida, hdev->instance); +} + +static void spraid_bsg_unmap_data(struct spraid_dev *hdev, struct bsg_job *job) +{ + struct request *rq = blk_mq_rq_from_pdu(job); + struct spraid_iod *iod = job->dd_data; + enum dma_data_direction dma_dir = + rq_data_dir(rq) ? DMA_TO_DEVICE : DMA_FROM_DEVICE; + + if (iod->nsge) + dma_unmap_sg(hdev->dev, iod->sg, iod->nsge, dma_dir); + + spraid_free_iod_res(hdev, iod); +} + +static int spraid_bsg_map_data(struct spraid_dev *hdev, struct bsg_job *job, + struct spraid_admin_command *cmd) +{ + struct request *rq = blk_mq_rq_from_pdu(job); + struct spraid_iod *iod = job->dd_data; + enum dma_data_direction dma_dir = + rq_data_dir(rq) ? DMA_TO_DEVICE : DMA_FROM_DEVICE; + int ret = 0; + + iod->sg = job->request_payload.sg_list; + iod->nsge = job->request_payload.sg_cnt; + iod->length = job->request_payload.payload_len; + iod->use_sgl = false; + iod->npages = -1; + iod->sg_drv_mgmt = false; + + if (!iod->nsge) + goto out; + + ret = dma_map_sg_attrs(hdev->dev, iod->sg, iod->nsge, + dma_dir, DMA_ATTR_NO_WARN); + if (!ret) + goto out; + + ret = spraid_setup_prps(hdev, iod); + if (ret) + goto unmap; + + cmd->common.dptr.prp1 = cpu_to_le64(sg_dma_address(iod->sg)); + cmd->common.dptr.prp2 = cpu_to_le64(iod->first_dma); + + return 0; + +unmap: + dma_unmap_sg(hdev->dev, iod->sg, iod->nsge, dma_dir); +out: + return ret; +} + +static int spraid_get_ctrl_info(struct spraid_dev *hdev, + struct spraid_ctrl_info *ctrl_info) +{ + struct spraid_admin_command admin_cmd; + u8 *data_ptr = NULL; + dma_addr_t data_dma = 0; + int ret; + + data_ptr = dma_alloc_coherent(hdev->dev, PAGE_SIZE, + &data_dma, GFP_KERNEL); + if (!data_ptr) + return -ENOMEM; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.get_info.opcode = SPRAID_ADMIN_GET_INFO; + admin_cmd.get_info.type = SPRAID_GET_INFO_CTRL; + admin_cmd.common.dptr.prp1 = cpu_to_le64(data_dma); + + ret = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); + if (!ret) + memcpy(ctrl_info, data_ptr, sizeof(struct spraid_ctrl_info)); + + dma_free_coherent(hdev->dev, PAGE_SIZE, data_ptr, data_dma); + + return ret; +} + +static int spraid_init_ctrl_info(struct spraid_dev *hdev) +{ + int ret; + + hdev->ctrl_info->nd = cpu_to_le32(240); + hdev->ctrl_info->mdts = 8; + hdev->ctrl_info->max_cmds = cpu_to_le16(4096); + hdev->ctrl_info->max_num_sge = cpu_to_le16(128); + hdev->ctrl_info->max_channel = cpu_to_le16(4); + hdev->ctrl_info->max_tgt_id = cpu_to_le32(3239); + hdev->ctrl_info->max_lun = cpu_to_le16(2); + + ret = spraid_get_ctrl_info(hdev, hdev->ctrl_info); + if (ret) + dev_err(hdev->dev, "get controller info failed: %d\n", ret); + + dev_info(hdev->dev, "[%s]nd = %d\n", __func__, hdev->ctrl_info->nd); + dev_info(hdev->dev, "[%s]max_cmd = %d\n", + __func__, hdev->ctrl_info->max_cmds); + dev_info(hdev->dev, "[%s]max_channel = %d\n", + __func__, hdev->ctrl_info->max_channel); + dev_info(hdev->dev, "[%s]max_tgt_id = %d\n", + __func__, hdev->ctrl_info->max_tgt_id); + dev_info(hdev->dev, "[%s]max_lun = %d\n", + __func__, hdev->ctrl_info->max_lun); + dev_info(hdev->dev, "[%s]max_num_sge = %d\n", + __func__, hdev->ctrl_info->max_num_sge); + dev_info(hdev->dev, "[%s]lun_num_boot = %d\n", + __func__, hdev->ctrl_info->lun_num_in_boot); + dev_info(hdev->dev, "[%s]mdts = %d\n", __func__, hdev->ctrl_info->mdts); + dev_info(hdev->dev, "[%s]acl = %d\n", __func__, hdev->ctrl_info->acl); + dev_info(hdev->dev, "[%s]aer1 = %d\n", __func__, hdev->ctrl_info->aerl); + dev_info(hdev->dev, "[%s]card_type = %d\n", + __func__, hdev->ctrl_info->card_type); + dev_info(hdev->dev, "[%s]rtd3e = %d\n", + __func__, hdev->ctrl_info->rtd3e); + dev_info(hdev->dev, "[%s]sn = %s\n", __func__, hdev->ctrl_info->sn); + dev_info(hdev->dev, "[%s]fr = %s\n", __func__, hdev->ctrl_info->fr); + + if (!hdev->ctrl_info->aerl) + hdev->ctrl_info->aerl = 1; + if (hdev->ctrl_info->aerl > SPRAID_NR_AEN_COMMANDS) + hdev->ctrl_info->aerl = SPRAID_NR_AEN_COMMANDS; + + return 0; +} + +#define SPRAID_MAX_ADMIN_PAYLOAD_SIZE BIT(16) +static int spraid_alloc_iod_ext_mem_pool(struct spraid_dev *hdev) +{ + u16 max_sge = le16_to_cpu(hdev->ctrl_info->max_num_sge); + size_t alloc_size; + + alloc_size = spraid_iod_ext_size(hdev, SPRAID_MAX_ADMIN_PAYLOAD_SIZE, + max_sge, true, false); + if (alloc_size > PAGE_SIZE) + dev_warn(hdev->dev, "It is unreasonable ;" + " sg allocation more than one page\n"); + hdev->iod_mempool = mempool_create_node(1, mempool_kmalloc, + mempool_kfree, + (void *)alloc_size, GFP_KERNEL, + hdev->numa_node); + if (!hdev->iod_mempool) { + dev_err(hdev->dev, "Create iod extension memory pool failed\n"); + return -ENOMEM; + } + + return 0; +} + +static void spraid_free_iod_ext_mem_pool(struct spraid_dev *hdev) +{ + mempool_destroy(hdev->iod_mempool); +} + +static int spraid_user_admin_cmd(struct spraid_dev *hdev, struct bsg_job *job) +{ + struct spraid_bsg_request *bsg_req = job->request; + struct spraid_passthru_common_cmd *cmd = &(bsg_req->admcmd); + struct spraid_admin_command admin_cmd; + u32 timeout = msecs_to_jiffies(cmd->timeout_ms); + u32 result[2] = {0}; + int status; + + if (hdev->state >= SPRAID_RESETTING) { + dev_err(hdev->dev, "[%s] err, host state:[%d] is not right\n", + __func__, hdev->state); + return -EBUSY; + } + + dev_info(hdev->dev, "[%s] opcode[0x%x] subopcode[0x%x] init\n", + __func__, cmd->opcode, cmd->info_0.subopcode); + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.common.opcode = cmd->opcode; + admin_cmd.common.flags = cmd->flags; + admin_cmd.common.hdid = cpu_to_le32(cmd->nsid); + admin_cmd.common.cdw2[0] = cpu_to_le32(cmd->cdw2); + admin_cmd.common.cdw2[1] = cpu_to_le32(cmd->cdw3); + admin_cmd.common.cdw10 = cpu_to_le32(cmd->cdw10); + admin_cmd.common.cdw11 = cpu_to_le32(cmd->cdw11); + admin_cmd.common.cdw12 = cpu_to_le32(cmd->cdw12); + admin_cmd.common.cdw13 = cpu_to_le32(cmd->cdw13); + admin_cmd.common.cdw14 = cpu_to_le32(cmd->cdw14); + admin_cmd.common.cdw15 = cpu_to_le32(cmd->cdw15); + + status = spraid_bsg_map_data(hdev, job, &admin_cmd); + if (status) { + dev_err(hdev->dev, "[%s] err, map data failed\n", __func__); + return status; + } + + status = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, &result[0], + &result[1], timeout); + if (status >= 0) { + job->reply_len = sizeof(result); + memcpy(job->reply, result, sizeof(result)); + } + + dev_info(hdev->dev, "[%s] opcode[0x%x] subopcode[0x%x];" + " status[0x%x] result0[0x%x] result1[0x%x]\n", + __func__, cmd->opcode, cmd->info_0.subopcode, + status, result[0], result[1]); + + spraid_bsg_unmap_data(hdev, job); + + return status; +} + +static int spraid_alloc_ioq_ptcmds(struct spraid_dev *hdev) +{ + int i; + int ptnum = SPRAID_NR_IOQ_PTCMDS; + + INIT_LIST_HEAD(&hdev->ioq_pt_list); + spin_lock_init(&hdev->ioq_pt_lock); + + hdev->ioq_ptcmds = kcalloc_node(ptnum, sizeof(struct spraid_cmd), + GFP_KERNEL, hdev->numa_node); + + if (!hdev->ioq_ptcmds) { + dev_err(hdev->dev, "Alloc ioq_ptcmds failed\n"); + return -ENOMEM; + } + + for (i = 0; i < ptnum; i++) { + hdev->ioq_ptcmds[i].qid = i / SPRAID_PTCMDS_PERQ + 1; + hdev->ioq_ptcmds[i].cid = i % SPRAID_PTCMDS_PERQ + + SPRAID_IO_BLK_MQ_DEPTH; + list_add_tail(&(hdev->ioq_ptcmds[i].list), &hdev->ioq_pt_list); + } + + dev_info(hdev->dev, "Alloc ioq_ptcmds success, ptnum[%d]\n", ptnum); + + return 0; +} + +static void spraid_free_ioq_ptcmds(struct spraid_dev *hdev) +{ + kfree(hdev->ioq_ptcmds); + hdev->ioq_ptcmds = NULL; + + INIT_LIST_HEAD(&hdev->ioq_pt_list); +} + +static int spraid_submit_ioq_sync_cmd(struct spraid_dev *hdev, + struct spraid_ioq_command *cmd, + u32 *result, u32 *reslen, u32 timeout) +{ + int ret; + dma_addr_t sense_dma; + struct spraid_queue *ioq; + void *sense_addr = NULL; + struct spraid_cmd *pt_cmd = spraid_get_cmd(hdev, SPRAID_CMD_IOPT); + + if (!pt_cmd) { + dev_err(hdev->dev, "err, get ioq cmd failed\n"); + return -EFAULT; + } + + timeout = timeout ? timeout : ADMIN_TIMEOUT; + + init_completion(&pt_cmd->cmd_done); + + ioq = &hdev->queues[pt_cmd->qid]; + ret = pt_cmd->cid * SCSI_SENSE_BUFFERSIZE; + sense_addr = ioq->sense + ret; + sense_dma = ioq->sense_dma_addr + ret; + + cmd->common.sense_addr = cpu_to_le64(sense_dma); + cmd->common.sense_len = cpu_to_le16(SCSI_SENSE_BUFFERSIZE); + cmd->common.command_id = pt_cmd->cid; + + spraid_submit_cmd(ioq, cmd); + + if (!wait_for_completion_timeout(&pt_cmd->cmd_done, timeout)) { + dev_err(hdev->dev, "[%s] cid[%d] qid[%d] timeout;" + " opcode[0x%x] subopcode[0x%x]\n", + __func__, pt_cmd->cid, pt_cmd->qid, cmd->common.opcode, + (le32_to_cpu(cmd->common.cdw3[0]) & 0xffff)); + WRITE_ONCE(pt_cmd->state, SPRAID_CMD_TIMEOUT); + spraid_put_cmd(hdev, pt_cmd, SPRAID_CMD_IOPT); + return -EINVAL; + } + + if (result && reslen) { + if ((pt_cmd->status & 0x17f) == 0x101) { + memcpy(result, sense_addr, SCSI_SENSE_BUFFERSIZE); + *reslen = SCSI_SENSE_BUFFERSIZE; + } + } + + spraid_put_cmd(hdev, pt_cmd, SPRAID_CMD_IOPT); + + return pt_cmd->status; +} + +static int spraid_user_ioq_cmd(struct spraid_dev *hdev, struct bsg_job *job) +{ + struct spraid_bsg_request *bsg_req = + (struct spraid_bsg_request *)(job->request); + struct spraid_ioq_passthru_cmd *cmd = &(bsg_req->ioqcmd); + struct spraid_ioq_command ioq_cmd; + int status = 0; + u32 timeout = msecs_to_jiffies(cmd->timeout_ms); + + if (cmd->data_len > PAGE_SIZE) { + dev_err(hdev->dev, "[%s] data len bigger than 4k\n", __func__); + return -EFAULT; + } + + if (hdev->state != SPRAID_LIVE) { + dev_err(hdev->dev, "[%s] err, host state:[%d] is not live\n", + __func__, hdev->state); + return -EBUSY; + } + + dev_info(hdev->dev, "[%s] opcode[0x%x] subopcode[0x%x] init;" + " datalen[%d]\n", + __func__, cmd->opcode, cmd->info_1.subopcode, cmd->data_len); + + memset(&ioq_cmd, 0, sizeof(ioq_cmd)); + ioq_cmd.common.opcode = cmd->opcode; + ioq_cmd.common.flags = cmd->flags; + ioq_cmd.common.hdid = cpu_to_le32(cmd->nsid); + ioq_cmd.common.sense_len = cpu_to_le16(cmd->info_0.res_sense_len); + ioq_cmd.common.cdb_len = cmd->info_0.cdb_len; + ioq_cmd.common.rsvd2 = cmd->info_0.rsvd0; + ioq_cmd.common.cdw3[0] = cpu_to_le32(cmd->cdw3); + ioq_cmd.common.cdw3[1] = cpu_to_le32(cmd->cdw4); + ioq_cmd.common.cdw3[2] = cpu_to_le32(cmd->cdw5); + + ioq_cmd.common.cdw10[0] = cpu_to_le32(cmd->cdw10); + ioq_cmd.common.cdw10[1] = cpu_to_le32(cmd->cdw11); + ioq_cmd.common.cdw10[2] = cpu_to_le32(cmd->cdw12); + ioq_cmd.common.cdw10[3] = cpu_to_le32(cmd->cdw13); + ioq_cmd.common.cdw10[4] = cpu_to_le32(cmd->cdw14); + ioq_cmd.common.cdw10[5] = cpu_to_le32(cmd->data_len); + + memcpy(ioq_cmd.common.cdb, &cmd->cdw16, cmd->info_0.cdb_len); + + ioq_cmd.common.cdw26[0] = cpu_to_le32(cmd->cdw26[0]); + ioq_cmd.common.cdw26[1] = cpu_to_le32(cmd->cdw26[1]); + ioq_cmd.common.cdw26[2] = cpu_to_le32(cmd->cdw26[2]); + ioq_cmd.common.cdw26[3] = cpu_to_le32(cmd->cdw26[3]); + + status = spraid_bsg_map_data(hdev, job, + (struct spraid_admin_command *)&ioq_cmd); + if (status) { + dev_err(hdev->dev, "[%s] err, map data failed\n", __func__); + return status; + } + + status = spraid_submit_ioq_sync_cmd(hdev, &ioq_cmd, job->reply, + &job->reply_len, timeout); + + dev_info(hdev->dev, "[%s] opcode[0x%x] subopcode[0x%x], status[0x%x];" + " reply_len[%d]\n", + __func__, cmd->opcode, cmd->info_1.subopcode, + status, job->reply_len); + + spraid_bsg_unmap_data(hdev, job); + + return status; +} + +static bool spraid_check_scmd_completed(struct scsi_cmnd *scmd) +{ + struct spraid_dev *hdev = shost_priv(scmd->device->host); + struct spraid_iod *iod = scsi_cmd_priv(scmd); + struct spraid_queue *spraidq; + u16 hwq, cid; + + spraid_get_tag_from_scmd(scmd, &hwq, &cid); + spraidq = &hdev->queues[hwq]; + if (READ_ONCE(iod->state) == SPRAID_CMD_COMPLETE + || spraid_poll_cq(spraidq, cid)) { + dev_warn(hdev->dev, "cid[%d] qid[%d] has been completed\n", + cid, spraidq->qid); + return true; + } + return false; +} + +static enum blk_eh_timer_return spraid_scmd_timeout(struct scsi_cmnd *scmd) +{ + struct spraid_iod *iod = scsi_cmd_priv(scmd); + unsigned int timeout = scmd->device->request_queue->rq_timeout; + + if (spraid_check_scmd_completed(scmd)) + goto out; + + if (time_after(jiffies, scmd->jiffies_at_alloc + timeout)) { + if (cmpxchg(&iod->state, + SPRAID_CMD_IN_FLIGHT, + SPRAID_CMD_TIMEOUT) == SPRAID_CMD_IN_FLIGHT) { + return BLK_EH_DONE; + } + } +out: + return BLK_EH_RESET_TIMER; +} + +/* send abort command by admin queue temporary */ +static int spraid_send_abort_cmd(struct spraid_dev *hdev, + u32 hdid, u16 qid, u16 cid) +{ + struct spraid_admin_command admin_cmd; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.abort.opcode = SPRAID_ADMIN_ABORT_CMD; + admin_cmd.abort.hdid = cpu_to_le32(hdid); + admin_cmd.abort.sqid = cpu_to_le16(qid); + admin_cmd.abort.cid = cpu_to_le16(cid); + + return spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); +} + +/* send reset command by admin quueue temporary */ +static int spraid_send_reset_cmd(struct spraid_dev *hdev, int type, u32 hdid) +{ + struct spraid_admin_command admin_cmd; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.reset.opcode = SPRAID_ADMIN_RESET; + admin_cmd.reset.hdid = cpu_to_le32(hdid); + admin_cmd.reset.type = type; + + return spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); +} + +static bool spraid_change_host_state(struct spraid_dev *hdev, + enum spraid_state newstate) +{ + unsigned long flags; + enum spraid_state oldstate; + bool change = false; + + spin_lock_irqsave(&hdev->state_lock, flags); + + oldstate = hdev->state; + switch (newstate) { + case SPRAID_LIVE: + switch (oldstate) { + case SPRAID_NEW: + case SPRAID_RESETTING: + change = true; + break; + default: + break; + } + break; + case SPRAID_RESETTING: + switch (oldstate) { + case SPRAID_LIVE: + change = true; + break; + default: + break; + } + break; + case SPRAID_DELETING: + if (oldstate != SPRAID_DELETING) + change = true; + break; + case SPRAID_DEAD: + switch (oldstate) { + case SPRAID_NEW: + case SPRAID_LIVE: + case SPRAID_RESETTING: + change = true; + break; + default: + break; + } + break; + default: + break; + } + if (change) + hdev->state = newstate; + spin_unlock_irqrestore(&hdev->state_lock, flags); + + dev_info(hdev->dev, "[%s][%d]->[%d], change[%d]\n", + __func__, oldstate, newstate, change); + + return change; +} + +static void spraid_back_fault_cqe(struct spraid_queue *ioq, + struct spraid_completion *cqe) +{ + struct spraid_dev *hdev = ioq->hdev; + struct blk_mq_tags *tags; + struct scsi_cmnd *scmd; + struct spraid_iod *iod; + struct request *req; + + tags = hdev->shost->tag_set.tags[ioq->qid - 1]; + req = blk_mq_tag_to_rq(tags, cqe->cmd_id); + if (unlikely(!req || !blk_mq_request_started(req))) + return; + + scmd = blk_mq_rq_to_pdu(req); + iod = scsi_cmd_priv(scmd); + + set_host_byte(scmd, DID_NO_CONNECT); + if (iod->nsge) + scsi_dma_unmap(scmd); + spraid_free_iod_res(hdev, iod); + scmd->scsi_done(scmd); + dev_warn(hdev->dev, "Back fault CQE, cid[%d] qid[%d]\n", + cqe->cmd_id, ioq->qid); +} + +static void spraid_back_all_io(struct spraid_dev *hdev) +{ + int i, j; + struct spraid_queue *ioq; + struct spraid_completion cqe = { 0 }; + + scsi_block_requests(hdev->shost); + + for (i = 1; i <= hdev->shost->nr_hw_queues; i++) { + ioq = &hdev->queues[i]; + for (j = 0; j < hdev->shost->can_queue; j++) { + cqe.cmd_id = j; + spraid_back_fault_cqe(ioq, &cqe); + } + } + + scsi_unblock_requests(hdev->shost); +} + +static void spraid_dev_disable(struct spraid_dev *hdev, bool shutdown) +{ + struct spraid_queue *adminq = &hdev->queues[0]; + u16 start, end; + unsigned long timeout = jiffies + 600 * HZ; + + if (pci_device_is_present(hdev->pdev)) { + if (shutdown) + spraid_shutdown_ctrl(hdev); + else + spraid_disable_ctrl(hdev); + } + + while (!time_after(jiffies, timeout)) { + if (!pci_device_is_present(hdev->pdev)) { + dev_info(hdev->dev, "[%s] pci_device not present;" + " skip wait\n", __func__); + break; + } + if (!spraid_wait_ready(hdev, hdev->cap, false)) { + dev_info(hdev->dev, + "[%s] wait ready success after reset\n", + __func__); + break; + } + dev_info(hdev->dev, "[%s] waiting csts_rdy ready\n", __func__); + } + + if (hdev->queue_count == 0) { + dev_err(hdev->dev, "[%s] warn, queue has been delete\n", + __func__); + return; + } + + spin_lock_irq(&adminq->cq_lock); + spraid_process_cq(adminq, &start, &end, -1); + spin_unlock_irq(&adminq->cq_lock); + spraid_complete_cqes(adminq, start, end); + + spraid_pci_disable(hdev); + + spraid_back_all_io(hdev); +} + +static void spraid_reset_work(struct work_struct *work) +{ + int ret; + struct spraid_dev *hdev = + container_of(work, struct spraid_dev, reset_work); + + if (hdev->state != SPRAID_RESETTING) { + dev_err(hdev->dev, "[%s] err, host is not reset state\n", + __func__); + return; + } + + dev_info(hdev->dev, "[%s] enter host reset\n", __func__); + + if (hdev->ctrl_config & SPRAID_CC_ENABLE) { + dev_info(hdev->dev, "[%s] start dev_disable\n", __func__); + spraid_dev_disable(hdev, false); + } + + ret = spraid_pci_enable(hdev); + if (ret) + goto out; + + ret = spraid_setup_admin_queue(hdev); + if (ret) + goto pci_disable; + + ret = spraid_setup_io_queues(hdev); + if (ret || hdev->online_queues <= hdev->shost->nr_hw_queues) + goto pci_disable; + + spraid_change_host_state(hdev, SPRAID_LIVE); + + spraid_send_all_aen(hdev); + + return; + +pci_disable: + spraid_pci_disable(hdev); +out: + spraid_change_host_state(hdev, SPRAID_DEAD); + dev_err(hdev->dev, "[%s] err, host reset failed\n", __func__); +} + +static int spraid_reset_work_sync(struct spraid_dev *hdev) +{ + if (!spraid_change_host_state(hdev, SPRAID_RESETTING)) { + dev_info(hdev->dev, "[%s] can't change to reset state\n", + __func__); + return -EBUSY; + } + + if (!queue_work(spraid_wq, &hdev->reset_work)) { + dev_err(hdev->dev, "[%s] err, host is already in reset state\n", + __func__); + return -EBUSY; + } + + flush_work(&hdev->reset_work); + if (hdev->state != SPRAID_LIVE) + return -ENODEV; + + return 0; +} + +static int spraid_wait_abnl_cmd_done(struct spraid_iod *iod) +{ + u16 times = 0; + + do { + if (READ_ONCE(iod->state) == SPRAID_CMD_TMO_COMPLETE) + break; + msleep(500); + times++; + } while (times <= SPRAID_WAIT_ABNL_CMD_TIMEOUT); + + /* wait command completion timeout after abort/reset success */ + if (times >= SPRAID_WAIT_ABNL_CMD_TIMEOUT) + return -ETIMEDOUT; + + return 0; +} + +static int spraid_abort_handler(struct scsi_cmnd *scmd) +{ + struct spraid_dev *hdev = shost_priv(scmd->device->host); + struct spraid_iod *iod = scsi_cmd_priv(scmd); + struct spraid_sdev_hostdata *hostdata; + u16 hwq, cid; + int ret; + + scsi_print_command(scmd); + + if (hdev->state != SPRAID_LIVE || !spraid_wait_abnl_cmd_done(iod) || + spraid_check_scmd_completed(scmd)) + return SUCCESS; + + hostdata = scmd->device->hostdata; + spraid_get_tag_from_scmd(scmd, &hwq, &cid); + + dev_warn(hdev->dev, "cid[%d] qid[%d] timeout, aborting\n", cid, hwq); + ret = spraid_send_abort_cmd(hdev, hostdata->hdid, hwq, cid); + if (ret != ADMIN_ERR_TIMEOUT) { + ret = spraid_wait_abnl_cmd_done(iod); + if (ret) { + dev_warn(hdev->dev, "cid[%d] qid[%d] abort failed;" + " not found\n", cid, hwq); + return FAILED; + } + dev_warn(hdev->dev, "cid[%d] qid[%d] abort succ\n", cid, hwq); + return SUCCESS; + } + dev_warn(hdev->dev, "cid[%d] qid[%d] abort failed, timeout\n", + cid, hwq); + return FAILED; +} + +static int spraid_tgt_reset_handler(struct scsi_cmnd *scmd) +{ + struct spraid_dev *hdev = shost_priv(scmd->device->host); + struct spraid_iod *iod = scsi_cmd_priv(scmd); + struct spraid_sdev_hostdata *hostdata; + u16 hwq, cid; + int ret; + + scsi_print_command(scmd); + + if (hdev->state != SPRAID_LIVE || !spraid_wait_abnl_cmd_done(iod) || + spraid_check_scmd_completed(scmd)) + return SUCCESS; + + hostdata = scmd->device->hostdata; + spraid_get_tag_from_scmd(scmd, &hwq, &cid); + + dev_warn(hdev->dev, "cid[%d] qid[%d] timeout, target reset\n", + cid, hwq); + ret = spraid_send_reset_cmd(hdev, SPRAID_RESET_TARGET, hostdata->hdid); + if (ret == 0) { + ret = spraid_wait_abnl_cmd_done(iod); + if (ret) { + dev_warn(hdev->dev, + "cid[%d] qid[%d]target reset failed;" + " not found\n", cid, hwq); + return FAILED; + } + + dev_warn(hdev->dev, "cid[%d] qid[%d] target reset success\n", + cid, hwq); + return SUCCESS; + } + + dev_warn(hdev->dev, "cid[%d] qid[%d] ret[%d] target reset failed\n", + cid, hwq, ret); + return FAILED; +} + +static int spraid_bus_reset_handler(struct scsi_cmnd *scmd) +{ + struct spraid_dev *hdev = shost_priv(scmd->device->host); + struct spraid_iod *iod = scsi_cmd_priv(scmd); + struct spraid_sdev_hostdata *hostdata; + u16 hwq, cid; + int ret; + + scsi_print_command(scmd); + + if (hdev->state != SPRAID_LIVE || !spraid_wait_abnl_cmd_done(iod) || + spraid_check_scmd_completed(scmd)) + return SUCCESS; + + hostdata = scmd->device->hostdata; + spraid_get_tag_from_scmd(scmd, &hwq, &cid); + + dev_warn(hdev->dev, "cid[%d] qid[%d] timeout, bus reset\n", cid, hwq); + ret = spraid_send_reset_cmd(hdev, SPRAID_RESET_BUS, hostdata->hdid); + if (ret == 0) { + ret = spraid_wait_abnl_cmd_done(iod); + if (ret) { + dev_warn(hdev->dev, + "cid[%d] qid[%d] bus reset failed;" + " not found\n", cid, hwq); + return FAILED; + } + + dev_warn(hdev->dev, "cid[%d] qid[%d] bus reset succ\n", + cid, hwq); + return SUCCESS; + } + + dev_warn(hdev->dev, "cid[%d] qid[%d] ret[%d] bus reset failed\n", + cid, hwq, ret); + return FAILED; +} + +static int spraid_shost_reset_handler(struct scsi_cmnd *scmd) +{ + u16 hwq, cid; + struct spraid_dev *hdev = shost_priv(scmd->device->host); + + scsi_print_command(scmd); + if (hdev->state != SPRAID_LIVE || spraid_check_scmd_completed(scmd)) + return SUCCESS; + + spraid_get_tag_from_scmd(scmd, &hwq, &cid); + dev_warn(hdev->dev, "cid[%d] qid[%d] host reset\n", cid, hwq); + + if (spraid_reset_work_sync(hdev)) { + dev_warn(hdev->dev, "cid[%d] qid[%d] host reset failed\n", + cid, hwq); + return FAILED; + } + + dev_warn(hdev->dev, "cid[%d] qid[%d] host reset success\n", cid, hwq); + + return SUCCESS; +} + +static pci_ers_result_t spraid_pci_error_detected(struct pci_dev *pdev, + pci_channel_state_t state) +{ + struct spraid_dev *hdev = pci_get_drvdata(pdev); + + dev_info(hdev->dev, "enter pci error detect, state:%d\n", state); + + switch (state) { + case pci_channel_io_normal: + dev_warn(hdev->dev, "channel is normal, do nothing\n"); + + return PCI_ERS_RESULT_CAN_RECOVER; + case pci_channel_io_frozen: + dev_warn(hdev->dev, + "channel io frozen, need reset controller\n"); + + scsi_block_requests(hdev->shost); + + spraid_change_host_state(hdev, SPRAID_RESETTING); + + return PCI_ERS_RESULT_NEED_RESET; + case pci_channel_io_perm_failure: + dev_warn(hdev->dev, "channel io failure, request disconnect\n"); + + return PCI_ERS_RESULT_DISCONNECT; + } + + return PCI_ERS_RESULT_NEED_RESET; +} + +static pci_ers_result_t spraid_pci_slot_reset(struct pci_dev *pdev) +{ + struct spraid_dev *hdev = pci_get_drvdata(pdev); + + dev_info(hdev->dev, "restart after slot reset\n"); + + pci_restore_state(pdev); + + if (!queue_work(spraid_wq, &hdev->reset_work)) { + dev_err(hdev->dev, "[%s] err, the device is resetting state\n", + __func__); + return PCI_ERS_RESULT_NONE; + } + + flush_work(&hdev->reset_work); + + scsi_unblock_requests(hdev->shost); + + return PCI_ERS_RESULT_RECOVERED; +} + +static void spraid_reset_done(struct pci_dev *pdev) +{ + struct spraid_dev *hdev = pci_get_drvdata(pdev); + + dev_info(hdev->dev, "enter spraid reset done\n"); +} + +static ssize_t csts_pp_show(struct device *cdev, + struct device_attribute *attr, char *buf) +{ + struct Scsi_Host *shost = class_to_shost(cdev); + struct spraid_dev *hdev = shost_priv(shost); + int ret = -1; + + if (pci_device_is_present(hdev->pdev)) { + ret = (readl(hdev->bar + SPRAID_REG_CSTS) + & SPRAID_CSTS_PP_MASK); + ret >>= SPRAID_CSTS_PP_SHIFT; + } + + return snprintf(buf, PAGE_SIZE, "%d\n", ret); +} + +static ssize_t csts_shst_show(struct device *cdev, + struct device_attribute *attr, char *buf) +{ + struct Scsi_Host *shost = class_to_shost(cdev); + struct spraid_dev *hdev = shost_priv(shost); + int ret = -1; + + if (pci_device_is_present(hdev->pdev)) { + ret = (readl(hdev->bar + SPRAID_REG_CSTS) + & SPRAID_CSTS_SHST_MASK); + ret >>= SPRAID_CSTS_SHST_SHIFT; + } + + return snprintf(buf, PAGE_SIZE, "%d\n", ret); +} + +static ssize_t csts_cfs_show(struct device *cdev, + struct device_attribute *attr, char *buf) +{ + struct Scsi_Host *shost = class_to_shost(cdev); + struct spraid_dev *hdev = shost_priv(shost); + int ret = -1; + + if (pci_device_is_present(hdev->pdev)) { + ret = (readl(hdev->bar + SPRAID_REG_CSTS) + & SPRAID_CSTS_CFS_MASK); + ret >>= SPRAID_CSTS_CFS_SHIFT; + } + + return snprintf(buf, PAGE_SIZE, "%d\n", ret); +} + +static ssize_t csts_rdy_show(struct device *cdev, + struct device_attribute *attr, char *buf) +{ + struct Scsi_Host *shost = class_to_shost(cdev); + struct spraid_dev *hdev = shost_priv(shost); + int ret = -1; + + if (pci_device_is_present(hdev->pdev)) + ret = (readl(hdev->bar + SPRAID_REG_CSTS) & SPRAID_CSTS_RDY); + + return snprintf(buf, PAGE_SIZE, "%d\n", ret); +} + +static ssize_t fw_version_show(struct device *cdev, + struct device_attribute *attr, char *buf) +{ + struct Scsi_Host *shost = class_to_shost(cdev); + struct spraid_dev *hdev = shost_priv(shost); + + return snprintf(buf, PAGE_SIZE, "%s\n", hdev->ctrl_info->fr); +} + +static DEVICE_ATTR_RO(csts_pp); +static DEVICE_ATTR_RO(csts_shst); +static DEVICE_ATTR_RO(csts_cfs); +static DEVICE_ATTR_RO(csts_rdy); +static DEVICE_ATTR_RO(fw_version); + +static struct device_attribute *spraid_host_attrs[] = { + &dev_attr_csts_pp, + &dev_attr_csts_shst, + &dev_attr_csts_cfs, + &dev_attr_csts_rdy, + &dev_attr_fw_version, + NULL, +}; + +static int spraid_get_vd_info(struct spraid_dev *hdev, + struct spraid_vd_info *vd_info, u16 vid) +{ + struct spraid_admin_command admin_cmd; + u8 *data_ptr = NULL; + dma_addr_t data_dma = 0; + int ret; + + data_ptr = dma_alloc_coherent(hdev->dev, PAGE_SIZE, + &data_dma, GFP_KERNEL); + if (!data_ptr) + return -ENOMEM; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.usr_cmd.opcode = USR_CMD_READ; + admin_cmd.usr_cmd.info_0.subopcode = cpu_to_le16(USR_CMD_VDINFO); + admin_cmd.usr_cmd.info_1.data_len = cpu_to_le16(USR_CMD_RDLEN); + admin_cmd.usr_cmd.info_1.param_len = cpu_to_le16(VDINFO_PARAM_LEN); + admin_cmd.usr_cmd.cdw10 = cpu_to_le32(vid); + admin_cmd.common.dptr.prp1 = cpu_to_le64(data_dma); + + ret = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); + if (!ret) + memcpy(vd_info, data_ptr, sizeof(struct spraid_vd_info)); + + dma_free_coherent(hdev->dev, PAGE_SIZE, data_ptr, data_dma); + + return ret; +} + +static int spraid_get_bgtask(struct spraid_dev *hdev, + struct spraid_bgtask *bgtask) +{ + struct spraid_admin_command admin_cmd; + u8 *data_ptr = NULL; + dma_addr_t data_dma = 0; + int ret; + + data_ptr = dma_alloc_coherent(hdev->dev, PAGE_SIZE, + &data_dma, GFP_KERNEL); + if (!data_ptr) + return -ENOMEM; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.usr_cmd.opcode = USR_CMD_READ; + admin_cmd.usr_cmd.info_0.subopcode = cpu_to_le16(USR_CMD_BGTASK); + admin_cmd.usr_cmd.info_1.data_len = cpu_to_le16(USR_CMD_RDLEN); + admin_cmd.common.dptr.prp1 = cpu_to_le64(data_dma); + + ret = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); + if (!ret) + memcpy(bgtask, data_ptr, sizeof(struct spraid_bgtask)); + + dma_free_coherent(hdev->dev, PAGE_SIZE, data_ptr, data_dma); + + return ret; +} + +static ssize_t raid_level_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct scsi_device *sdev; + struct spraid_dev *hdev; + struct spraid_vd_info *vd_info; + struct spraid_sdev_hostdata *hostdata; + int ret; + + sdev = to_scsi_device(dev); + hdev = shost_priv(sdev->host); + hostdata = sdev->hostdata; + + vd_info = kmalloc(sizeof(*vd_info), GFP_KERNEL); + if (!vd_info || !SPRAID_DEV_INFO_ATTR_VD(hostdata->attr)) + return snprintf(buf, PAGE_SIZE, "NA\n"); + + ret = spraid_get_vd_info(hdev, vd_info, sdev->id); + if (ret) + vd_info->rg_level = ARRAY_SIZE(raid_levels) - 1; + + ret = (vd_info->rg_level < ARRAY_SIZE(raid_levels)) ? + vd_info->rg_level : (ARRAY_SIZE(raid_levels) - 1); + + kfree(vd_info); + + return snprintf(buf, PAGE_SIZE, "RAID-%s\n", raid_levels[ret]); +} + +static ssize_t raid_state_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct scsi_device *sdev; + struct spraid_dev *hdev; + struct spraid_vd_info *vd_info; + struct spraid_sdev_hostdata *hostdata; + int ret; + + sdev = to_scsi_device(dev); + hdev = shost_priv(sdev->host); + hostdata = sdev->hostdata; + + vd_info = kmalloc(sizeof(*vd_info), GFP_KERNEL); + if (!vd_info || !SPRAID_DEV_INFO_ATTR_VD(hostdata->attr)) + return snprintf(buf, PAGE_SIZE, "NA\n"); + + ret = spraid_get_vd_info(hdev, vd_info, sdev->id); + if (ret) { + vd_info->vd_status = 0; + vd_info->rg_id = 0xff; + } + + ret = (vd_info->vd_status < ARRAY_SIZE(raid_states)) ? + vd_info->vd_status : 0; + + kfree(vd_info); + + return snprintf(buf, PAGE_SIZE, "%s\n", raid_states[ret]); +} + +static ssize_t raid_resync_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct scsi_device *sdev; + struct spraid_dev *hdev; + struct spraid_vd_info *vd_info; + struct spraid_bgtask *bgtask; + struct spraid_sdev_hostdata *hostdata; + u8 rg_id, i, progress = 0; + int ret; + + sdev = to_scsi_device(dev); + hdev = shost_priv(sdev->host); + hostdata = sdev->hostdata; + + vd_info = kmalloc(sizeof(*vd_info), GFP_KERNEL); + if (!vd_info || !SPRAID_DEV_INFO_ATTR_VD(hostdata->attr)) + return snprintf(buf, PAGE_SIZE, "NA\n"); + + ret = spraid_get_vd_info(hdev, vd_info, sdev->id); + if (ret) + goto out; + + rg_id = vd_info->rg_id; + + bgtask = (struct spraid_bgtask *)vd_info; + ret = spraid_get_bgtask(hdev, bgtask); + if (ret) + goto out; + for (i = 0; i < bgtask->task_num; i++) { + if ((bgtask->bgtask[i].type == BGTASK_TYPE_REBUILD) && + (le16_to_cpu(bgtask->bgtask[i].vd_id) == rg_id)) + progress = bgtask->bgtask[i].progress; + } + +out: + kfree(vd_info); + return snprintf(buf, PAGE_SIZE, "%d\n", progress); +} + +static DEVICE_ATTR_RO(raid_level); +static DEVICE_ATTR_RO(raid_state); +static DEVICE_ATTR_RO(raid_resync); + +static struct device_attribute *spraid_dev_attrs[] = { + &dev_attr_raid_level, + &dev_attr_raid_state, + &dev_attr_raid_resync, + NULL, +}; + +static struct pci_error_handlers spraid_err_handler = { + .error_detected = spraid_pci_error_detected, + .slot_reset = spraid_pci_slot_reset, + .reset_done = spraid_reset_done, +}; + +static int spraid_sysfs_host_reset(struct Scsi_Host *shost, int reset_type) +{ + int ret; + struct spraid_dev *hdev = shost_priv(shost); + + dev_info(hdev->dev, "[%s] start sysfs host reset cmd\n", __func__); + ret = spraid_reset_work_sync(hdev); + dev_info(hdev->dev, "[%s] stop sysfs host reset cmd[%d]\n", + __func__, ret); + + return ret; +} + +static struct scsi_host_template spraid_driver_template = { + .module = THIS_MODULE, + .name = "Ramaxel Logic spraid driver", + .proc_name = "spraid", + .queuecommand = spraid_queue_command, + .slave_alloc = spraid_slave_alloc, + .slave_destroy = spraid_slave_destroy, + .slave_configure = spraid_slave_configure, + .eh_timed_out = spraid_scmd_timeout, + .eh_abort_handler = spraid_abort_handler, + .eh_target_reset_handler = spraid_tgt_reset_handler, + .eh_bus_reset_handler = spraid_bus_reset_handler, + .eh_host_reset_handler = spraid_shost_reset_handler, + .change_queue_depth = scsi_change_queue_depth, + .this_id = -1, + .shost_attrs = spraid_host_attrs, + .sdev_attrs = spraid_dev_attrs, + .host_reset = spraid_sysfs_host_reset, +}; + +static void spraid_shutdown(struct pci_dev *pdev) +{ + struct spraid_dev *hdev = pci_get_drvdata(pdev); + + spraid_remove_io_queues(hdev); + spraid_disable_admin_queue(hdev, true); +} + +/* bsg dispatch user command */ +static int spraid_bsg_host_dispatch(struct bsg_job *job) +{ + struct Scsi_Host *shost = dev_to_shost(job->dev); + struct spraid_dev *hdev = shost_priv(shost); + struct request *rq = blk_mq_rq_from_pdu(job); + struct spraid_bsg_request *bsg_req = job->request; + int ret = 0; + + dev_info(hdev->dev, "[%s] msgcode[%d], msglen[%d], timeout[%d];" + " req_nsge[%d], req_len[%d]\n", + __func__, bsg_req->msgcode, job->request_len, + rq->timeout, job->request_payload.sg_cnt, + job->request_payload.payload_len); + + job->reply_len = 0; + + switch (bsg_req->msgcode) { + case SPRAID_BSG_ADM: + ret = spraid_user_admin_cmd(hdev, job); + break; + case SPRAID_BSG_IOQ: + ret = spraid_user_ioq_cmd(hdev, job); + break; + default: + dev_info(hdev->dev, "[%s] unsupport msgcode[%d]\n", + __func__, bsg_req->msgcode); + break; + } + + if (ret > 0) + ret = ret | (ret << 8); + + bsg_job_done(job, ret, 0); + return 0; +} + +static inline void spraid_remove_bsg(struct spraid_dev *hdev) +{ + if (hdev->bsg_queue) { + bsg_unregister_queue(hdev->bsg_queue); + blk_cleanup_queue(hdev->bsg_queue); + } +} +static int spraid_probe(struct pci_dev *pdev, const struct pci_device_id *id) +{ + struct spraid_dev *hdev; + struct Scsi_Host *shost; + int node, ret; + char bsg_name[15]; + + shost = scsi_host_alloc(&spraid_driver_template, sizeof(*hdev)); + if (!shost) { + dev_err(&pdev->dev, "Failed to allocate scsi host\n"); + return -ENOMEM; + } + hdev = shost_priv(shost); + hdev->pdev = pdev; + hdev->dev = get_device(&pdev->dev); + + node = dev_to_node(hdev->dev); + if (node == NUMA_NO_NODE) { + node = first_memory_node; + set_dev_node(hdev->dev, node); + } + hdev->numa_node = node; + hdev->shost = shost; + pci_set_drvdata(pdev, hdev); + + ret = spraid_dev_map(hdev); + if (ret) + goto put_dev; + + init_rwsem(&hdev->devices_rwsem); + INIT_WORK(&hdev->scan_work, spraid_scan_work); + INIT_WORK(&hdev->timesyn_work, spraid_timesyn_work); + INIT_WORK(&hdev->reset_work, spraid_reset_work); + INIT_WORK(&hdev->fw_act_work, spraid_fw_act_work); + spin_lock_init(&hdev->state_lock); + + ret = spraid_alloc_resources(hdev); + if (ret) + goto dev_unmap; + + ret = spraid_pci_enable(hdev); + if (ret) + goto resources_free; + + ret = spraid_setup_admin_queue(hdev); + if (ret) + goto pci_disable; + + ret = spraid_init_ctrl_info(hdev); + if (ret) + goto disable_admin_q; + + ret = spraid_alloc_iod_ext_mem_pool(hdev); + if (ret) + goto disable_admin_q; + + ret = spraid_setup_io_queues(hdev); + if (ret) + goto free_iod_mempool; + + spraid_shost_init(hdev); + + ret = scsi_add_host(hdev->shost, hdev->dev); + if (ret) { + dev_err(hdev->dev, "Add shost to system failed, ret: %d\n", + ret); + goto remove_io_queues; + } + + snprintf(bsg_name, sizeof(bsg_name), "spraid%d", shost->host_no); + hdev->bsg_queue = bsg_setup_queue(&shost->shost_gendev, bsg_name, + spraid_bsg_host_dispatch, + spraid_cmd_size(hdev, true, false)); + if (IS_ERR(hdev->bsg_queue)) { + dev_err(hdev->dev, "err, setup bsg failed\n"); + hdev->bsg_queue = NULL; + goto remove_io_queues; + } + + if (hdev->online_queues == SPRAID_ADMIN_QUEUE_NUM) { + dev_warn(hdev->dev, "warn only admin queue can be used\n"); + return 0; + } + + hdev->state = SPRAID_LIVE; + + spraid_send_all_aen(hdev); + + ret = spraid_dev_list_init(hdev); + if (ret) + goto remove_bsg; + + ret = spraid_configure_timestamp(hdev); + if (ret) + dev_warn(hdev->dev, "init set timestamp failed\n"); + + ret = spraid_alloc_ioq_ptcmds(hdev); + if (ret) + goto remove_bsg; + + scsi_scan_host(hdev->shost); + + return 0; + +remove_bsg: + spraid_remove_bsg(hdev); +remove_io_queues: + spraid_remove_io_queues(hdev); +free_iod_mempool: + spraid_free_iod_ext_mem_pool(hdev); +disable_admin_q: + spraid_disable_admin_queue(hdev, false); +pci_disable: + spraid_pci_disable(hdev); +resources_free: + spraid_free_resources(hdev); +dev_unmap: + spraid_dev_unmap(hdev); +put_dev: + put_device(hdev->dev); + scsi_host_put(shost); + + return -ENODEV; +} + +static void spraid_remove(struct pci_dev *pdev) +{ + struct spraid_dev *hdev = pci_get_drvdata(pdev); + struct Scsi_Host *shost = hdev->shost; + + dev_info(hdev->dev, "enter spraid remove\n"); + + spraid_change_host_state(hdev, SPRAID_DELETING); + flush_work(&hdev->reset_work); + + if (!pci_device_is_present(pdev)) + spraid_back_all_io(hdev); + + spraid_remove_bsg(hdev); + scsi_remove_host(shost); + spraid_free_ioq_ptcmds(hdev); + kfree(hdev->devices); + spraid_remove_io_queues(hdev); + spraid_free_iod_ext_mem_pool(hdev); + spraid_disable_admin_queue(hdev, false); + spraid_pci_disable(hdev); + spraid_free_resources(hdev); + spraid_dev_unmap(hdev); + put_device(hdev->dev); + scsi_host_put(shost); + + dev_info(hdev->dev, "exit spraid remove\n"); +} + +static const struct pci_device_id spraid_id_table[] = { + { PCI_DEVICE(PCI_VENDOR_ID_RAMAXEL_LOGIC, + SPRAID_SERVER_DEVICE_HBA_DID) }, + { PCI_DEVICE(PCI_VENDOR_ID_RAMAXEL_LOGIC, + SPRAID_SERVER_DEVICE_RAID_DID) }, + { 0, } +}; +MODULE_DEVICE_TABLE(pci, spraid_id_table); + +static struct pci_driver spraid_driver = { + .name = "spraid", + .id_table = spraid_id_table, + .probe = spraid_probe, + .remove = spraid_remove, + .shutdown = spraid_shutdown, + .err_handler = &spraid_err_handler, +}; + +static int __init spraid_init(void) +{ + int ret; + + spraid_wq = alloc_workqueue("spraid-wq", WQ_UNBOUND | WQ_MEM_RECLAIM | + WQ_SYSFS, 0); + if (!spraid_wq) + return -ENOMEM; + + spraid_class = class_create(THIS_MODULE, "spraid"); + if (IS_ERR(spraid_class)) { + ret = PTR_ERR(spraid_class); + goto destroy_wq; + } + + ret = pci_register_driver(&spraid_driver); + if (ret < 0) + goto destroy_class; + + return 0; + +destroy_class: + class_destroy(spraid_class); +destroy_wq: + destroy_workqueue(spraid_wq); + + return ret; +} + +static void __exit spraid_exit(void) +{ + pci_unregister_driver(&spraid_driver); + class_destroy(spraid_class); + destroy_workqueue(spraid_wq); + ida_destroy(&spraid_instance_ida); +} + +MODULE_AUTHOR("songyl(a)ramaxel.com"); +MODULE_DESCRIPTION("Ramaxel Memory Technology SPraid Driver"); +MODULE_LICENSE("GPL"); +MODULE_VERSION(SPRAID_DRV_VERSION); +module_init(spraid_init); +module_exit(spraid_exit); -- 2.27.0

1 0

[PATCH openEuler-1.0-LTS 1/2] USB: gadget: detect too-big endpoint 0 requests
by Yang Yingliang 22 Dec '21

22 Dec '21

From: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> mainline inclusion from mainline-v5.16-rc5 commit 153a2d7e3350cc89d406ba2d35be8793a64c2038 category: bugfix bugzilla: NA CVE: CVE-2021-39685 -------------------------------- Sometimes USB hosts can ask for buffers that are too large from endpoint 0, which should not be allowed. If this happens for OUT requests, stall the endpoint, but for IN requests, trim the request size to the endpoint buffer size. Co-developed-by: Szymon Heidrich <szymon.heidrich(a)gmail.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/usb/gadget/composite.c | 12 ++++++++++++ drivers/usb/gadget/legacy/dbgp.c | 13 +++++++++++++ drivers/usb/gadget/legacy/inode.c | 16 +++++++++++++++- 3 files changed, 40 insertions(+), 1 deletion(-) diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index af0702cfa92ff..3813249387b3d 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -1569,6 +1569,18 @@ composite_setup(struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl) struct usb_function *f = NULL; u8 endp; + if (w_length > USB_COMP_EP0_BUFSIZ) { + if (ctrl->bRequestType == USB_DIR_OUT) { + goto done; + } else { + /* Cast away the const, we are going to overwrite on purpose. */ + __le16 *temp = (__le16 *)&ctrl->wLength; + + *temp = cpu_to_le16(USB_COMP_EP0_BUFSIZ); + w_length = USB_COMP_EP0_BUFSIZ; + } + } + /* partial re-init of the response message; the function or the * gadget might need to intercept e.g. a control-OUT completion * when we delegate to it. diff --git a/drivers/usb/gadget/legacy/dbgp.c b/drivers/usb/gadget/legacy/dbgp.c index e1d566c9918ae..e567afcb2794c 100644 --- a/drivers/usb/gadget/legacy/dbgp.c +++ b/drivers/usb/gadget/legacy/dbgp.c @@ -345,6 +345,19 @@ static int dbgp_setup(struct usb_gadget *gadget, void *data = NULL; u16 len = 0; + if (length > DBGP_REQ_LEN) { + if (ctrl->bRequestType == USB_DIR_OUT) { + return err; + } else { + /* Cast away the const, we are going to overwrite on purpose. */ + __le16 *temp = (__le16 *)&ctrl->wLength; + + *temp = cpu_to_le16(DBGP_REQ_LEN); + length = DBGP_REQ_LEN; + } + } + + if (request == USB_REQ_GET_DESCRIPTOR) { switch (value>>8) { case USB_DT_DEVICE: diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c index 37ca0e669bd85..83fd1b55d497a 100644 --- a/drivers/usb/gadget/legacy/inode.c +++ b/drivers/usb/gadget/legacy/inode.c @@ -109,6 +109,8 @@ enum ep0_state { /* enough for the whole queue: most events invalidate others */ #define N_EVENT 5 +#define RBUF_SIZE 256 + struct dev_data { spinlock_t lock; refcount_t count; @@ -143,7 +145,7 @@ struct dev_data { struct dentry *dentry; /* except this scratch i/o buffer for ep0 */ - u8 rbuf [256]; + u8 rbuf[RBUF_SIZE]; }; static inline void get_dev (struct dev_data *data) @@ -1332,6 +1334,18 @@ gadgetfs_setup (struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl) u16 w_value = le16_to_cpu(ctrl->wValue); u16 w_length = le16_to_cpu(ctrl->wLength); + if (w_length > RBUF_SIZE) { + if (ctrl->bRequestType == USB_DIR_OUT) { + return value; + } else { + /* Cast away the const, we are going to overwrite on purpose. */ + __le16 *temp = (__le16 *)&ctrl->wLength; + + *temp = cpu_to_le16(RBUF_SIZE); + w_length = RBUF_SIZE; + } + } + spin_lock (&dev->lock); dev->setup_abort = 0; if (dev->state == STATE_DEV_UNCONNECTED) { -- 2.25.1

1 1

[PATCH openEuler-1.0-LTS] scsi:spraid: support Ramaxel's spraid driver
by Yanling Song 21 Dec '21

21 Dec '21

Ramaxel inclusion category: features bugzilla: https://gitee.com/openeuler/kernel/issues/I4NJIB CVE: NA Support Ramaxel's SPRxxx Raid controller Signed-off-by: Yanling Song <songyl(a)ramaxel.com> Reviewed-by: Jiang Yu<yujiang(a)ramaxel.com> --- drivers/scsi/Kconfig | 1 + drivers/scsi/Makefile | 1 + drivers/scsi/spraid/Kconfig | 13 + drivers/scsi/spraid/Makefile | 7 + drivers/scsi/spraid/spraid.h | 746 ++++++ drivers/scsi/spraid/spraid_main.c | 3875 +++++++++++++++++++++++++++++ 6 files changed, 4643 insertions(+) create mode 100644 drivers/scsi/spraid/Kconfig create mode 100644 drivers/scsi/spraid/Makefile create mode 100644 drivers/scsi/spraid/spraid.h create mode 100644 drivers/scsi/spraid/spraid_main.c diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig index 8450484184e3..63d2aaa22834 100644 --- a/drivers/scsi/Kconfig +++ b/drivers/scsi/Kconfig @@ -522,6 +522,7 @@ source "drivers/scsi/megaraid/Kconfig.megaraid" source "drivers/scsi/mpt3sas/Kconfig" source "drivers/scsi/smartpqi/Kconfig" source "drivers/scsi/ufs/Kconfig" +source "drivers/scsi/spraid/Kconfig" config SCSI_HPTIOP tristate "HighPoint RocketRAID 3xxx/4xxx Controller support" diff --git a/drivers/scsi/Makefile b/drivers/scsi/Makefile index 2973693f6dcc..4056cf26e09e 100644 --- a/drivers/scsi/Makefile +++ b/drivers/scsi/Makefile @@ -94,6 +94,7 @@ obj-$(CONFIG_SCSI_ZALON) += zalon7xx.o obj-$(CONFIG_SCSI_DC395x) += dc395x.o obj-$(CONFIG_SCSI_AM53C974) += esp_scsi.o am53c974.o obj-$(CONFIG_CXLFLASH) += cxlflash/ +obj-$(CONFIG_RAMAXEL_SPRAID) += spraid/ obj-$(CONFIG_MEGARAID_LEGACY) += megaraid.o obj-$(CONFIG_MEGARAID_NEWGEN) += megaraid/ obj-$(CONFIG_MEGARAID_SAS) += megaraid/ diff --git a/drivers/scsi/spraid/Kconfig b/drivers/scsi/spraid/Kconfig new file mode 100644 index 000000000000..bfbba3db8db0 --- /dev/null +++ b/drivers/scsi/spraid/Kconfig @@ -0,0 +1,13 @@ +# +# Ramaxel driver configuration +# + +config RAMAXEL_SPRAID + tristate "Ramaxel spraid Adapter" + depends on PCI && SCSI + select BLK_DEV_BSGLIB + depends on ARM64 || X86_64 + help + This driver supports Ramaxel SPRxxx serial + raid controller, which has PCIE Gen4 interface + with host and supports SAS/SATA Hdd/ssd. diff --git a/drivers/scsi/spraid/Makefile b/drivers/scsi/spraid/Makefile new file mode 100644 index 000000000000..aadc2ffd37eb --- /dev/null +++ b/drivers/scsi/spraid/Makefile @@ -0,0 +1,7 @@ +# +# Makefile for the Ramaxel device drivers. +# + +obj-$(CONFIG_RAMAXEL_SPRAID) += spraid.o + +spraid-objs := spraid_main.o \ No newline at end of file diff --git a/drivers/scsi/spraid/spraid.h b/drivers/scsi/spraid/spraid.h new file mode 100644 index 000000000000..c1e4980e18e5 --- /dev/null +++ b/drivers/scsi/spraid/spraid.h @@ -0,0 +1,746 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2021 Ramaxel Memory Technology, Ltd */ + +#ifndef __SPRAID_H_ +#define __SPRAID_H_ + +#define SPRAID_CAP_MQES(cap) ((cap) & 0xffff) +#define SPRAID_CAP_STRIDE(cap) (((cap) >> 32) & 0xf) +#define SPRAID_CAP_MPSMIN(cap) (((cap) >> 48) & 0xf) +#define SPRAID_CAP_MPSMAX(cap) (((cap) >> 52) & 0xf) +#define SPRAID_CAP_TIMEOUT(cap) (((cap) >> 24) & 0xff) +#define SPRAID_CAP_DMAMASK(cap) (((cap) >> 37) & 0xff) + +#define SPRAID_DEFAULT_MAX_CHANNEL 4 +#define SPRAID_DEFAULT_MAX_ID 240 +#define SPRAID_DEFAULT_MAX_LUN_PER_HOST 8 +#define MAX_SECTORS 2048 + +#define IO_SQE_SIZE sizeof(struct spraid_ioq_command) +#define ADMIN_SQE_SIZE sizeof(struct spraid_admin_command) +#define SQE_SIZE(qid) (((qid) > 0) ? IO_SQE_SIZE : ADMIN_SQE_SIZE) +#define CQ_SIZE(depth) ((depth) * sizeof(struct spraid_completion)) +#define SQ_SIZE(qid, depth) ((depth) * SQE_SIZE(qid)) + +#define SENSE_SIZE(depth) ((depth) * SCSI_SENSE_BUFFERSIZE) + +#define SPRAID_AQ_DEPTH 128 +#define SPRAID_NR_AEN_COMMANDS 16 +#define SPRAID_AQ_BLK_MQ_DEPTH (SPRAID_AQ_DEPTH - SPRAID_NR_AEN_COMMANDS) +#define SPRAID_AQ_MQ_TAG_DEPTH (SPRAID_AQ_BLK_MQ_DEPTH - 1) + +#define SPRAID_ADMIN_QUEUE_NUM 1 +#define SPRAID_PTCMDS_PERQ 1 +#define SPRAID_IO_BLK_MQ_DEPTH (hdev->shost->can_queue) +#define SPRAID_NR_IOQ_PTCMDS (SPRAID_PTCMDS_PERQ * hdev->shost->nr_hw_queues) + +#define FUA_MASK 0x08 +#define SPRAID_MINORS BIT(MINORBITS) + +#define COMMAND_IS_WRITE(cmd) ((cmd)->common.opcode & 1) + +#define SPRAID_IO_IOSQES 7 +#define SPRAID_IO_IOCQES 4 +#define PRP_ENTRY_SIZE 8 + +#define SMALL_POOL_SIZE 256 +#define MAX_SMALL_POOL_NUM 16 +#define MAX_CMD_PER_DEV 64 +#define MAX_CDB_LEN 32 + +#define SPRAID_UP_TO_MULTY4(x) (((x) + 4) & (~0x03)) + +#define CQE_STATUS_SUCCESS (0x0) + +#define PCI_VENDOR_ID_RAMAXEL_LOGIC 0x1E81 + +#define SPRAID_SERVER_DEVICE_HBA_DID 0x2100 +#define SPRAID_SERVER_DEVICE_RAID_DID 0x2200 + +#define IO_6_DEFAULT_TX_LEN 256 + +#define SPRAID_INT_PAGES 2 +#define SPRAID_INT_BYTES(hdev) (SPRAID_INT_PAGES * (hdev)->page_size) + +enum { + SPRAID_REQ_CANCELLED = (1 << 0), + SPRAID_REQ_USERCMD = (1 << 1), +}; + +enum { + SPRAID_SC_SUCCESS = 0x0, + SPRAID_SC_INVALID_OPCODE = 0x1, + SPRAID_SC_INVALID_FIELD = 0x2, + + SPRAID_SC_ABORT_LIMIT = 0x103, + SPRAID_SC_ABORT_MISSING = 0x104, + SPRAID_SC_ASYNC_LIMIT = 0x105, + + SPRAID_SC_DNR = 0x4000, +}; + +enum { + SPRAID_REG_CAP = 0x0000, + SPRAID_REG_CC = 0x0014, + SPRAID_REG_CSTS = 0x001c, + SPRAID_REG_AQA = 0x0024, + SPRAID_REG_ASQ = 0x0028, + SPRAID_REG_ACQ = 0x0030, + SPRAID_REG_DBS = 0x1000, +}; + +enum { + SPRAID_CC_ENABLE = 1 << 0, + SPRAID_CC_CSS_NVM = 0 << 4, + SPRAID_CC_MPS_SHIFT = 7, + SPRAID_CC_AMS_SHIFT = 11, + SPRAID_CC_SHN_SHIFT = 14, + SPRAID_CC_IOSQES_SHIFT = 16, + SPRAID_CC_IOCQES_SHIFT = 20, + SPRAID_CC_AMS_RR = 0 << SPRAID_CC_AMS_SHIFT, + SPRAID_CC_SHN_NONE = 0 << SPRAID_CC_SHN_SHIFT, + SPRAID_CC_IOSQES = SPRAID_IO_IOSQES << SPRAID_CC_IOSQES_SHIFT, + SPRAID_CC_IOCQES = SPRAID_IO_IOCQES << SPRAID_CC_IOCQES_SHIFT, + SPRAID_CC_SHN_NORMAL = 1 << SPRAID_CC_SHN_SHIFT, + SPRAID_CC_SHN_MASK = 3 << SPRAID_CC_SHN_SHIFT, + SPRAID_CSTS_CFS_SHIFT = 1, + SPRAID_CSTS_SHST_SHIFT = 2, + SPRAID_CSTS_PP_SHIFT = 5, + SPRAID_CSTS_RDY = 1 << 0, + SPRAID_CSTS_SHST_CMPLT = 2 << 2, + SPRAID_CSTS_SHST_MASK = 3 << 2, + SPRAID_CSTS_CFS_MASK = 1 << SPRAID_CSTS_CFS_SHIFT, + SPRAID_CSTS_PP_MASK = 1 << SPRAID_CSTS_PP_SHIFT, +}; + +enum { + SPRAID_ADMIN_DELETE_SQ = 0x00, + SPRAID_ADMIN_CREATE_SQ = 0x01, + SPRAID_ADMIN_DELETE_CQ = 0x04, + SPRAID_ADMIN_CREATE_CQ = 0x05, + SPRAID_ADMIN_ABORT_CMD = 0x08, + SPRAID_ADMIN_SET_FEATURES = 0x09, + SPRAID_ADMIN_ASYNC_EVENT = 0x0c, + SPRAID_ADMIN_GET_INFO = 0xc6, + SPRAID_ADMIN_RESET = 0xc8, +}; + +enum { + SPRAID_GET_INFO_CTRL = 0, + SPRAID_GET_INFO_DEV_LIST = 1, +}; + +enum { + SPRAID_RESET_TARGET = 0, + SPRAID_RESET_BUS = 1, +}; + +enum { + SPRAID_AEN_ERROR = 0, + SPRAID_AEN_NOTICE = 2, + SPRAID_AEN_VS = 7, +}; + +enum { + SPRAID_AEN_DEV_CHANGED = 0x00, + SPRAID_AEN_FW_ACT_START = 0x01, + SPRAID_AEN_HOST_PROBING = 0x10, +}; + +enum { + SPRAID_AEN_TIMESYN = 0x00, + SPRAID_AEN_FW_ACT_FINISH = 0x02, + SPRAID_AEN_EVENT_MIN = 0x80, + SPRAID_AEN_EVENT_MAX = 0xff, +}; + +enum { + SPRAID_CMD_WRITE = 0x01, + SPRAID_CMD_READ = 0x02, + + SPRAID_CMD_NONIO_NONE = 0x80, + SPRAID_CMD_NONIO_TODEV = 0x81, + SPRAID_CMD_NONIO_FROMDEV = 0x82, +}; + +enum { + SPRAID_QUEUE_PHYS_CONTIG = (1 << 0), + SPRAID_CQ_IRQ_ENABLED = (1 << 1), + + SPRAID_FEAT_NUM_QUEUES = 0x07, + SPRAID_FEAT_ASYNC_EVENT = 0x0b, + SPRAID_FEAT_TIMESTAMP = 0x0e, +}; + +enum spraid_state { + SPRAID_NEW, + SPRAID_LIVE, + SPRAID_RESETTING, + SPRAID_DELETING, + SPRAID_DEAD, +}; + +enum { + SPRAID_CARD_HBA, + SPRAID_CARD_RAID, +}; + +enum spraid_cmd_type { + SPRAID_CMD_ADM, + SPRAID_CMD_IOPT, +}; + +struct spraid_completion { + __le32 result; + union { + struct { + __u8 sense_len; + __u8 resv[3]; + }; + __le32 result1; + }; + __le16 sq_head; + __le16 sq_id; + __u16 cmd_id; + __le16 status; +}; + +struct spraid_ctrl_info { + __le32 nd; + __le16 max_cmds; + __le16 max_channel; + __le32 max_tgt_id; + __le16 max_lun; + __le16 max_num_sge; + __le16 lun_num_in_boot; + __u8 mdts; + __u8 acl; + __u8 aerl; + __u8 card_type; + __u16 rsvd; + __u32 rtd3e; + __u8 sn[32]; + __u8 fr[16]; + __u8 rsvd1[4020]; +}; + +struct spraid_dev { + struct pci_dev *pdev; + struct device *dev; + struct Scsi_Host *shost; + struct spraid_queue *queues; + struct dma_pool *prp_page_pool; + struct dma_pool *prp_small_pool[MAX_SMALL_POOL_NUM]; + mempool_t *iod_mempool; + void __iomem *bar; + u32 max_qid; + u32 num_vecs; + u32 queue_count; + u32 ioq_depth; + int db_stride; + u32 __iomem *dbs; + struct rw_semaphore devices_rwsem; + int numa_node; + u32 page_size; + u32 ctrl_config; + u32 online_queues; + u64 cap; + int instance; + struct spraid_ctrl_info *ctrl_info; + struct spraid_dev_info *devices; + + struct spraid_cmd *adm_cmds; + struct list_head adm_cmd_list; + spinlock_t adm_cmd_lock; + + struct spraid_cmd *ioq_ptcmds; + struct list_head ioq_pt_list; + spinlock_t ioq_pt_lock; + + struct work_struct scan_work; + struct work_struct timesyn_work; + struct work_struct reset_work; + struct work_struct fw_act_work; + + enum spraid_state state; + spinlock_t state_lock; + + struct request_queue *bsg_queue; +}; + +struct spraid_sgl_desc { + __le64 addr; + __le32 length; + __u8 rsvd[3]; + __u8 type; +}; + +union spraid_data_ptr { + struct { + __le64 prp1; + __le64 prp2; + }; + struct spraid_sgl_desc sgl; +}; + +struct spraid_admin_common_command { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + __le32 cdw2[4]; + union spraid_data_ptr dptr; + __le32 cdw10; + __le32 cdw11; + __le32 cdw12; + __le32 cdw13; + __le32 cdw14; + __le32 cdw15; +}; + +struct spraid_features { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + __u64 rsvd2[2]; + union spraid_data_ptr dptr; + __le32 fid; + __le32 dword11; + __le32 dword12; + __le32 dword13; + __le32 dword14; + __le32 dword15; +}; + +struct spraid_create_cq { + __u8 opcode; + __u8 flags; + __u16 command_id; + __u32 rsvd1[5]; + __le64 prp1; + __u64 rsvd8; + __le16 cqid; + __le16 qsize; + __le16 cq_flags; + __le16 irq_vector; + __u32 rsvd12[4]; +}; + +struct spraid_create_sq { + __u8 opcode; + __u8 flags; + __u16 command_id; + __u32 rsvd1[5]; + __le64 prp1; + __u64 rsvd8; + __le16 sqid; + __le16 qsize; + __le16 sq_flags; + __le16 cqid; + __u32 rsvd12[4]; +}; + +struct spraid_delete_queue { + __u8 opcode; + __u8 flags; + __u16 command_id; + __u32 rsvd1[9]; + __le16 qid; + __u16 rsvd10; + __u32 rsvd11[5]; +}; + +struct spraid_get_info { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + __u32 rsvd2[4]; + union spraid_data_ptr dptr; + __u8 type; + __u8 rsvd10[3]; + __le32 cdw11; + __u32 rsvd12[4]; +}; + +struct spraid_usr_cmd { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + union { + struct { + __le16 subopcode; + __le16 rsvd1; + } info_0; + __le32 cdw2; + }; + union { + struct { + __le16 data_len; + __le16 param_len; + } info_1; + __le32 cdw3; + }; + __u64 metadata; + union spraid_data_ptr dptr; + __le32 cdw10; + __le32 cdw11; + __le32 cdw12; + __le32 cdw13; + __le32 cdw14; + __le32 cdw15; +}; + +enum { + SPRAID_CMD_FLAG_SGL_METABUF = (1 << 6), + SPRAID_CMD_FLAG_SGL_METASEG = (1 << 7), + SPRAID_CMD_FLAG_SGL_ALL = SPRAID_CMD_FLAG_SGL_METABUF | + SPRAID_CMD_FLAG_SGL_METASEG, +}; + +enum spraid_cmd_state { + SPRAID_CMD_IDLE = 0, + SPRAID_CMD_IN_FLIGHT = 1, + SPRAID_CMD_COMPLETE = 2, + SPRAID_CMD_TIMEOUT = 3, + SPRAID_CMD_TMO_COMPLETE = 4, +}; + +struct spraid_abort_cmd { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + __u64 rsvd2[4]; + __le16 sqid; + __le16 cid; + __u32 rsvd11[5]; +}; + +struct spraid_reset_cmd { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + __u64 rsvd2[4]; + __u8 type; + __u8 rsvd10[3]; + __u32 rsvd11[5]; +}; + +struct spraid_admin_command { + union { + struct spraid_admin_common_command common; + struct spraid_features features; + struct spraid_create_cq create_cq; + struct spraid_create_sq create_sq; + struct spraid_delete_queue delete_queue; + struct spraid_get_info get_info; + struct spraid_abort_cmd abort; + struct spraid_reset_cmd reset; + struct spraid_usr_cmd usr_cmd; + }; +}; + +struct spraid_ioq_common_command { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + __le16 sense_len; + __u8 cdb_len; + __u8 rsvd2; + __le32 cdw3[3]; + union spraid_data_ptr dptr; + __le32 cdw10[6]; + __u8 cdb[32]; + __le64 sense_addr; + __le32 cdw26[6]; +}; + +struct spraid_rw_command { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + __le16 sense_len; + __u8 cdb_len; + __u8 rsvd2; + __u32 rsvd3[3]; + union spraid_data_ptr dptr; + __le64 slba; + __le16 nlb; + __le16 control; + __u32 rsvd13[3]; + __u8 cdb[32]; + __le64 sense_addr; + __u32 rsvd26[6]; +}; + +struct spraid_scsi_nonio { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + __le16 sense_len; + __u8 cdb_length; + __u8 rsvd2; + __u32 rsvd3[3]; + union spraid_data_ptr dptr; + __u32 rsvd10[5]; + __le32 buffer_len; + __u8 cdb[32]; + __le64 sense_addr; + __u32 rsvd26[6]; +}; + +struct spraid_ioq_command { + union { + struct spraid_ioq_common_command common; + struct spraid_rw_command rw; + struct spraid_scsi_nonio scsi_nonio; + }; +}; + +struct spraid_passthru_common_cmd { + __u8 opcode; + __u8 flags; + __u16 rsvd0; + __u32 nsid; + union { + struct { + __u16 subopcode; + __u16 rsvd1; + } info_0; + __u32 cdw2; + }; + union { + struct { + __u16 data_len; + __u16 param_len; + } info_1; + __u32 cdw3; + }; + __u64 metadata; + + __u64 addr; + __u64 prp2; + + __u32 cdw10; + __u32 cdw11; + __u32 cdw12; + __u32 cdw13; + __u32 cdw14; + __u32 cdw15; + __u32 timeout_ms; + __u32 result0; + __u32 result1; +}; + +struct spraid_ioq_passthru_cmd { + __u8 opcode; + __u8 flags; + __u16 rsvd0; + __u32 nsid; + union { + struct { + __u16 res_sense_len; + __u8 cdb_len; + __u8 rsvd0; + } info_0; + __u32 cdw2; + }; + union { + struct { + __u16 subopcode; + __u16 rsvd1; + } info_1; + __u32 cdw3; + }; + union { + struct { + __u16 rsvd; + __u16 param_len; + } info_2; + __u32 cdw4; + }; + __u32 cdw5; + __u64 addr; + __u64 prp2; + union { + struct { + __u16 eid; + __u16 sid; + } info_3; + __u32 cdw10; + }; + union { + struct { + __u16 did; + __u8 did_flag; + __u8 rsvd2; + } info_4; + __u32 cdw11; + }; + __u32 cdw12; + __u32 cdw13; + __u32 cdw14; + __u32 data_len; + __u32 cdw16; + __u32 cdw17; + __u32 cdw18; + __u32 cdw19; + __u32 cdw20; + __u32 cdw21; + __u32 cdw22; + __u32 cdw23; + __u64 sense_addr; + __u32 cdw26[4]; + __u32 timeout_ms; + __u32 result0; + __u32 result1; +}; + +struct spraid_bsg_request { + u32 msgcode; + u32 control; + union { + struct spraid_passthru_common_cmd admcmd; + struct spraid_ioq_passthru_cmd ioqcmd; + }; +}; + +enum { + SPRAID_BSG_ADM, + SPRAID_BSG_IOQ, +}; + +struct spraid_cmd { + int qid; + int cid; + u32 result0; + u32 result1; + u16 status; + void *priv; + enum spraid_cmd_state state; + struct completion cmd_done; + struct list_head list; +}; + +struct spraid_queue { + struct spraid_dev *hdev; + spinlock_t sq_lock; + + spinlock_t cq_lock ____cacheline_aligned_in_smp; + + void *sq_cmds; + + struct spraid_completion *cqes; + + dma_addr_t sq_dma_addr; + dma_addr_t cq_dma_addr; + u32 __iomem *q_db; + u8 cq_phase; + u8 sqes; + u16 qid; + u16 sq_tail; + u16 cq_head; + u16 last_cq_head; + u16 q_depth; + s16 cq_vector; + void *sense; + dma_addr_t sense_dma_addr; + struct dma_pool *prp_small_pool; +}; + +struct spraid_iod { + struct spraid_queue *spraidq; + enum spraid_cmd_state state; + int npages; + u32 nsge; + u32 length; + bool use_sgl; + bool sg_drv_mgmt; + dma_addr_t first_dma; + void *sense; + dma_addr_t sense_dma; + struct scatterlist *sg; + struct scatterlist inline_sg[0]; +}; + +#define SPRAID_DEV_INFO_ATTR_BOOT(attr) ((attr) & 0x01) +#define SPRAID_DEV_INFO_ATTR_VD(attr) (((attr) & 0x02) == 0x0) +#define SPRAID_DEV_INFO_ATTR_PT(attr) (((attr) & 0x22) == 0x02) +#define SPRAID_DEV_INFO_ATTR_RAWDISK(attr) ((attr) & 0x20) + +#define SPRAID_DEV_INFO_FLAG_VALID(flag) ((flag) & 0x01) +#define SPRAID_DEV_INFO_FLAG_CHANGE(flag) ((flag) & 0x02) + +#define BGTASK_TYPE_REBUILD 4 +#define USR_CMD_READ 0xc2 +#define USR_CMD_RDLEN 0x1000 +#define USR_CMD_VDINFO 0x704 +#define USR_CMD_BGTASK 0x504 +#define VDINFO_PARAM_LEN 0x04 + +struct spraid_vd_info { + __u8 name[32]; + __le16 id; + __u8 rg_id; + __u8 rg_level; + __u8 sg_num; + __u8 sg_disk_num; + __u8 vd_status; + __u8 vd_type; + __u8 rsvd1[4056]; +}; + +#define MAX_REALTIME_BGTASK_NUM 32 + +struct bgtask_info { + __u8 type; + __u8 progress; + __u8 rate; + __u8 rsvd0; + __le16 vd_id; + __le16 time_left; + __u8 rsvd1[4]; +}; + +struct spraid_bgtask { + __u8 sw; + __u8 task_num; + __u8 rsvd[6]; + struct bgtask_info bgtask[MAX_REALTIME_BGTASK_NUM]; +}; + +struct spraid_dev_info { + __le32 hdid; + __le16 target; + __u8 channel; + __u8 lun; + __u8 attr; + __u8 flag; + __le16 max_io_kb; +}; + +#define MAX_DEV_ENTRY_PER_PAGE_4K 340 +struct spraid_dev_list { + __le32 dev_num; + __u32 rsvd0[3]; + struct spraid_dev_info devices[MAX_DEV_ENTRY_PER_PAGE_4K]; +}; + +struct spraid_sdev_hostdata { + u32 hdid; + u16 max_io_kb; + u8 attr; + u8 flag; + u8 rg_id; + u8 rsvd[3]; +}; + +#endif + diff --git a/drivers/scsi/spraid/spraid_main.c b/drivers/scsi/spraid/spraid_main.c new file mode 100644 index 000000000000..519b39f44e91 --- /dev/null +++ b/drivers/scsi/spraid/spraid_main.c @@ -0,0 +1,3875 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2021 Ramaxel Memory Technology, Ltd */ + +/* Ramaxel Raid SPXXX Series Linux Driver */ + +#define pr_fmt(fmt) "spraid: " fmt + +#include <linux/sched/signal.h> +#include <linux/version.h> +#include <linux/pci.h> +#include <linux/aer.h> +#include <linux/module.h> +#include <linux/ioport.h> +#include <linux/device.h> +#include <linux/delay.h> +#include <linux/interrupt.h> +#include <linux/cdev.h> +#include <linux/sysfs.h> +#include <linux/gfp.h> +#include <linux/types.h> +#include <linux/ratelimit.h> +#include <linux/once.h> +#include <linux/debugfs.h> +#include <linux/io-64-nonatomic-lo-hi.h> +#include <linux/blkdev.h> +#include <linux/bsg-lib.h> +#include <asm/unaligned.h> +#include <linux/sort.h> +#include <target/target_core_backend.h> + +#include <scsi/scsi.h> +#include <scsi/scsi_cmnd.h> +#include <scsi/scsi_device.h> +#include <scsi/scsi_host.h> +#include <scsi/scsi_transport.h> +#include <scsi/scsi_dbg.h> + + +#include "spraid.h" + +static u32 admin_tmout = 60; +module_param(admin_tmout, uint, 0644); +MODULE_PARM_DESC(admin_tmout, "admin commands timeout (seconds)"); + +static u32 scmd_tmout_nonpt = 180; +module_param(scmd_tmout_nonpt, uint, 0644); +MODULE_PARM_DESC(scmd_tmout_nonpt, + "scsi commands timeout for rawdisk&raid(seconds)"); + +static int ioq_depth_set(const char *val, const struct kernel_param *kp); +static const struct kernel_param_ops ioq_depth_ops = { + .set = ioq_depth_set, + .get = param_get_uint, +}; + +static u32 io_queue_depth = 1024; +module_param_cb(io_queue_depth, &ioq_depth_ops, &io_queue_depth, 0644); +MODULE_PARM_DESC(io_queue_depth, "set io queue depth, should >= 2"); + +static int log_debug_switch_set(const char *val, const struct kernel_param *kp) +{ + u8 n = 0; + int ret; + + ret = kstrtou8(val, 10, &n); + if (ret != 0) + return -EINVAL; + + return param_set_byte(val, kp); +} + +static const struct kernel_param_ops log_debug_switch_ops = { + .set = log_debug_switch_set, + .get = param_get_byte, +}; + +static unsigned char log_debug_switch; +module_param_cb(log_debug_switch, &log_debug_switch_ops, + &log_debug_switch, 0644); +MODULE_PARM_DESC(log_debug_switch, + "set log state, default non-zero for switch on"); + +static int small_pool_num_set(const char *val, const struct kernel_param *kp) +{ + u8 n = 0; + int ret; + + ret = kstrtou8(val, 10, &n); + if (ret != 0) + return -EINVAL; + if (n > MAX_SMALL_POOL_NUM) + n = MAX_SMALL_POOL_NUM; + if (n < 1) + n = 1; + *((u8 *)kp->arg) = n; + + return 0; +} + +static const struct kernel_param_ops small_pool_num_ops = { + .set = small_pool_num_set, + .get = param_get_byte, +}; + +/* It was found that the spindlock of a single pool conflicts + * a lot with multiple CPUs.So multiple pools are introduced + * to reduce the conflictions. + */ +static unsigned char small_pool_num = 4; +module_param_cb(small_pool_num, &small_pool_num_ops, &small_pool_num, 0644); +MODULE_PARM_DESC(small_pool_num, "set prp small pool num, default 4, MAX 16"); + +static void spraid_free_queue(struct spraid_queue *spraidq); +static void spraid_handle_aen_notice(struct spraid_dev *hdev, u32 result); +static void spraid_handle_aen_vs(struct spraid_dev *hdev, + u32 result, u32 result1); + +static DEFINE_IDA(spraid_instance_ida); + +static struct class *spraid_class; + +#define SPRAID_CAP_TIMEOUT_UNIT_MS (HZ / 2) + +static struct workqueue_struct *spraid_wq; + +#define dev_log_dbg(dev, fmt, ...) do { \ + if (unlikely(log_debug_switch)) \ + dev_info(dev, "[%s] [%d] " fmt, \ + __func__, __LINE__, ##__VA_ARGS__); \ +} while (0) + +#define SPRAID_DRV_VERSION "1.0.0.0" + +#define ADMIN_TIMEOUT (admin_tmout * HZ) +#define ADMIN_ERR_TIMEOUT 32757 + +#define SPRAID_WAIT_ABNL_CMD_TIMEOUT (3 * 2) + +#define SPRAID_DMA_MSK_BIT_MAX 64 + +enum FW_STAT_CODE { + FW_STAT_OK = 0, + FW_STAT_NEED_CHECK, + FW_STAT_ERROR, + FW_STAT_EP_PCIE_ERROR, + FW_STAT_NAC_DMA_ERROR, + FW_STAT_ABORTED, + FW_STAT_NEED_RETRY +}; + +static const char * const raid_levels[] = {"0", "1", "5", "6", "10", "50", "60", + "NA"}; + +static const char * const raid_states[] = { + "NA", "NORMAL", "FAULT", "DEGRADE", "NOT_FORMATTED", + "FORMATTING", "SANITIZING", "INITIALIZING", "INITIALIZE_FAIL", + "DELETING", "DELETE_FAIL", "WRITE_PROTECT" +}; + +static int ioq_depth_set(const char *val, const struct kernel_param *kp) +{ + int n = 0; + int ret; + + ret = kstrtoint(val, 10, &n); + if (ret != 0 || n < 2) + return -EINVAL; + + return param_set_int(val, kp); +} + +static int spraid_remap_bar(struct spraid_dev *hdev, u32 size) +{ + struct pci_dev *pdev = hdev->pdev; + + if (size > pci_resource_len(pdev, 0)) { + dev_err(hdev->dev, "Input size[%u] exceed bar0 length[%llu]\n", + size, pci_resource_len(pdev, 0)); + return -ENOMEM; + } + + if (hdev->bar) + iounmap(hdev->bar); + + hdev->bar = ioremap(pci_resource_start(pdev, 0), size); + if (!hdev->bar) { + dev_err(hdev->dev, "ioremap for bar0 failed\n"); + return -ENOMEM; + } + hdev->dbs = hdev->bar + SPRAID_REG_DBS; + + return 0; +} + +static int spraid_dev_map(struct spraid_dev *hdev) +{ + struct pci_dev *pdev = hdev->pdev; + int ret; + + ret = pci_request_mem_regions(pdev, "spraid"); + if (ret) { + dev_err(hdev->dev, "fail to request memory regions\n"); + return ret; + } + + ret = spraid_remap_bar(hdev, SPRAID_REG_DBS + 4096); + if (ret) { + pci_release_mem_regions(pdev); + return ret; + } + + return 0; +} + +static void spraid_dev_unmap(struct spraid_dev *hdev) +{ + struct pci_dev *pdev = hdev->pdev; + + if (hdev->bar) { + iounmap(hdev->bar); + hdev->bar = NULL; + } + pci_release_mem_regions(pdev); +} + +static int spraid_pci_enable(struct spraid_dev *hdev) +{ + struct pci_dev *pdev = hdev->pdev; + int ret = -ENOMEM; + u64 maskbit = SPRAID_DMA_MSK_BIT_MAX; + + if (pci_enable_device_mem(pdev)) { + dev_err(hdev->dev, + "Enable pci device memory resources failed\n"); + return ret; + } + pci_set_master(pdev); + + if (readl(hdev->bar + SPRAID_REG_CSTS) == U32_MAX) { + ret = -ENODEV; + dev_err(hdev->dev, "Read csts register failed\n"); + goto disable; + } + + ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES); + if (ret < 0) { + dev_err(hdev->dev, + "Allocate one IRQ for setup admin channel failed\n"); + goto disable; + } + + hdev->cap = lo_hi_readq(hdev->bar + SPRAID_REG_CAP); + hdev->ioq_depth = min_t(u32, SPRAID_CAP_MQES(hdev->cap) + 1, + io_queue_depth); + hdev->db_stride = 1 << SPRAID_CAP_STRIDE(hdev->cap); + + maskbit = SPRAID_CAP_DMAMASK(hdev->cap); + if (maskbit < 32 || maskbit > SPRAID_DMA_MSK_BIT_MAX) { + dev_err(hdev->dev, + "err, dma mask invalid[%llu], set to default\n", + maskbit); + maskbit = SPRAID_DMA_MSK_BIT_MAX; + } + if (dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(maskbit))) { + dev_err(hdev->dev, "set dma mask and coherent failed\n"); + goto disable; + } + + dev_info(hdev->dev, "set dma mask[%llu] success\n", maskbit); + + pci_enable_pcie_error_reporting(pdev); + pci_save_state(pdev); + + return 0; + +disable: + pci_disable_device(pdev); + return ret; +} + +static int spraid_npages_prp(u32 size, struct spraid_dev *hdev) +{ + u32 nprps = DIV_ROUND_UP(size + hdev->page_size, hdev->page_size); + + return DIV_ROUND_UP(PRP_ENTRY_SIZE * nprps, PAGE_SIZE - PRP_ENTRY_SIZE); +} + +static int spraid_npages_sgl(u32 nseg) +{ + return DIV_ROUND_UP(nseg * sizeof(struct spraid_sgl_desc), PAGE_SIZE); +} + +static void **spraid_iod_list(struct spraid_iod *iod) +{ + return (void **)(iod->inline_sg + (iod->sg_drv_mgmt ? iod->nsge : 0)); +} + +static u32 spraid_iod_ext_size(struct spraid_dev *hdev, u32 size, u32 nsge, + bool sg_drv_mgmt, bool use_sgl) +{ + size_t alloc_size, sg_size; + + if (use_sgl) + alloc_size = sizeof(__le64 *) * spraid_npages_sgl(nsge); + else + alloc_size = sizeof(__le64 *) * spraid_npages_prp(size, hdev); + + sg_size = sg_drv_mgmt ? (sizeof(struct scatterlist) * nsge) : 0; + return sg_size + alloc_size; +} + +static u32 spraid_cmd_size(struct spraid_dev *hdev, + bool sg_drv_mgmt, bool use_sgl) +{ + u32 alloc_size = spraid_iod_ext_size(hdev, SPRAID_INT_BYTES(hdev), + SPRAID_INT_PAGES, sg_drv_mgmt, use_sgl); + + dev_info(hdev->dev, "sg_drv_mgmt: %s, use_sgl: %s, iod size: %lu;" + " alloc_size: %u\n", sg_drv_mgmt ? "true" : "false", + use_sgl ? "true" : "false", + sizeof(struct spraid_iod), alloc_size); + + return sizeof(struct spraid_iod) + alloc_size; +} + +static int spraid_setup_prps(struct spraid_dev *hdev, struct spraid_iod *iod) +{ + struct scatterlist *sg = iod->sg; + u64 dma_addr = sg_dma_address(sg); + int dma_len = sg_dma_len(sg); + __le64 *prp_list, *old_prp_list; + u32 page_size = hdev->page_size; + int offset = dma_addr & (page_size - 1); + void **list = spraid_iod_list(iod); + int length = iod->length; + struct dma_pool *pool; + dma_addr_t prp_dma; + int nprps, i; + + length -= (page_size - offset); + if (length <= 0) { + iod->first_dma = 0; + return 0; + } + + dma_len -= (page_size - offset); + if (dma_len) { + dma_addr += (page_size - offset); + } else { + sg = sg_next(sg); + dma_addr = sg_dma_address(sg); + dma_len = sg_dma_len(sg); + } + + if (length <= page_size) { + iod->first_dma = dma_addr; + return 0; + } + + nprps = DIV_ROUND_UP(length, page_size); + if (nprps <= (SMALL_POOL_SIZE / PRP_ENTRY_SIZE)) { + pool = iod->spraidq->prp_small_pool; + iod->npages = 0; + } else { + pool = hdev->prp_page_pool; + iod->npages = 1; + } + + prp_list = dma_pool_alloc(pool, GFP_ATOMIC, &prp_dma); + if (!prp_list) { + dev_err_ratelimited(hdev->dev, + "Allocate first prp_list memory failed\n"); + iod->first_dma = dma_addr; + iod->npages = -1; + return -ENOMEM; + } + list[0] = prp_list; + iod->first_dma = prp_dma; + i = 0; + for (;;) { + if (i == page_size / PRP_ENTRY_SIZE) { + old_prp_list = prp_list; + + prp_list = dma_pool_alloc(pool, GFP_ATOMIC, &prp_dma); + if (!prp_list) { + dev_err_ratelimited(hdev->dev, "Allocate %dth;" + " prp_list memory failed\n", + iod->npages + 1); + return -ENOMEM; + } + list[iod->npages++] = prp_list; + prp_list[0] = old_prp_list[i - 1]; + old_prp_list[i - 1] = cpu_to_le64(prp_dma); + i = 1; + } + prp_list[i++] = cpu_to_le64(dma_addr); + dma_len -= page_size; + dma_addr += page_size; + length -= page_size; + if (length <= 0) + break; + if (dma_len > 0) + continue; + if (unlikely(dma_len < 0)) + goto bad_sgl; + sg = sg_next(sg); + dma_addr = sg_dma_address(sg); + dma_len = sg_dma_len(sg); + } + + return 0; + +bad_sgl: + dev_err(hdev->dev, + "Setup prps, invalid SGL for payload: %d nents: %d\n", + iod->length, iod->nsge); + return -EIO; +} + +#define SGES_PER_PAGE (PAGE_SIZE / sizeof(struct spraid_sgl_desc)) + +static void spraid_submit_cmd(struct spraid_queue *spraidq, const void *cmd) +{ + u32 sqes = SQE_SIZE(spraidq->qid); + unsigned long flags; + struct spraid_admin_common_command *acd = + (struct spraid_admin_common_command *)cmd; + + spin_lock_irqsave(&spraidq->sq_lock, flags); + memcpy((spraidq->sq_cmds + sqes * spraidq->sq_tail), cmd, sqes); + if (++spraidq->sq_tail == spraidq->q_depth) + spraidq->sq_tail = 0; + + writel(spraidq->sq_tail, spraidq->q_db); + spin_unlock_irqrestore(&spraidq->sq_lock, flags); + + dev_log_dbg(spraidq->hdev->dev, + "cid[%d] qid[%d], opcode[0x%x], flags[0x%x], hdid[%u]\n", + acd->command_id, spraidq->qid, acd->opcode, + acd->flags, le32_to_cpu(acd->hdid)); +} + +static u32 spraid_mod64(u64 dividend, u32 divisor) +{ + u64 d; + u32 remainder; + + if (!divisor) + pr_err("DIVISOR is zero, in div fn\n"); + + d = dividend; + remainder = do_div(d, divisor); + return remainder; +} + +static inline bool spraid_is_rw_scmd(struct scsi_cmnd *scmd) +{ + switch (scmd->cmnd[0]) { + case READ_6: + case READ_10: + case READ_12: + case READ_16: + case READ_32: + case WRITE_6: + case WRITE_10: + case WRITE_12: + case WRITE_16: + case WRITE_32: + return true; + default: + return false; + } +} + +static bool spraid_is_prp(struct spraid_dev *hdev, + struct scsi_cmnd *scmd, u32 nsge) +{ + struct scatterlist *sg = scsi_sglist(scmd); + u32 page_size = hdev->page_size; + bool is_prp = true; + int i = 0; + + scsi_for_each_sg(scmd, sg, nsge, i) { + if (i != 0 && i != nsge - 1) { + if (spraid_mod64(sg_dma_len(sg), page_size) || + spraid_mod64(sg_dma_address(sg), page_size)) { + is_prp = false; + break; + } + } + + if (nsge > 1 && i == 0) { + if ((spraid_mod64((sg_dma_address(sg) + sg_dma_len(sg)), + page_size))) { + is_prp = false; + break; + } + } + + if (nsge > 1 && i == (nsge - 1)) { + if (spraid_mod64(sg_dma_address(sg), page_size)) { + is_prp = false; + break; + } + } + } + + return is_prp; +} + +enum { + SPRAID_SGL_FMT_DATA_DESC = 0x00, + SPRAID_SGL_FMT_SEG_DESC = 0x02, + SPRAID_SGL_FMT_LAST_SEG_DESC = 0x03, + SPRAID_KEY_SGL_FMT_DATA_DESC = 0x04, + SPRAID_TRANSPORT_SGL_DATA_DESC = 0x05 +}; + +static void spraid_sgl_set_data(struct spraid_sgl_desc *sge, + struct scatterlist *sg) +{ + sge->addr = cpu_to_le64(sg_dma_address(sg)); + sge->length = cpu_to_le32(sg_dma_len(sg)); + sge->type = SPRAID_SGL_FMT_DATA_DESC << 4; +} + +static void spraid_sgl_set_seg(struct spraid_sgl_desc *sge, + dma_addr_t dma_addr, int entries) +{ + sge->addr = cpu_to_le64(dma_addr); + if (entries <= SGES_PER_PAGE) { + sge->length = cpu_to_le32(entries * sizeof(*sge)); + sge->type = SPRAID_SGL_FMT_LAST_SEG_DESC << 4; + } else { + sge->length = cpu_to_le32(PAGE_SIZE); + sge->type = SPRAID_SGL_FMT_SEG_DESC << 4; + } +} + +static int spraid_setup_ioq_cmd_sgl(struct spraid_dev *hdev, + struct scsi_cmnd *scmd, + struct spraid_ioq_command *ioq_cmd, + struct spraid_iod *iod) +{ + struct spraid_sgl_desc *sg_list, *link, *old_sg_list; + struct scatterlist *sg = scsi_sglist(scmd); + void **list = spraid_iod_list(iod); + struct dma_pool *pool; + int nsge = iod->nsge; + dma_addr_t sgl_dma; + int i = 0; + + ioq_cmd->common.flags |= SPRAID_CMD_FLAG_SGL_METABUF; + + if (nsge == 1) { + spraid_sgl_set_data(&ioq_cmd->common.dptr.sgl, sg); + return 0; + } + + if (nsge <= (SMALL_POOL_SIZE / sizeof(struct spraid_sgl_desc))) { + pool = iod->spraidq->prp_small_pool; + iod->npages = 0; + } else { + pool = hdev->prp_page_pool; + iod->npages = 1; + } + + sg_list = dma_pool_alloc(pool, GFP_ATOMIC, &sgl_dma); + if (!sg_list) { + dev_err_ratelimited(hdev->dev, + "Allocate first sgl_list failed\n"); + iod->npages = -1; + return -ENOMEM; + } + + list[0] = sg_list; + iod->first_dma = sgl_dma; + spraid_sgl_set_seg(&ioq_cmd->common.dptr.sgl, sgl_dma, nsge); + do { + if (i == SGES_PER_PAGE) { + old_sg_list = sg_list; + link = &old_sg_list[SGES_PER_PAGE - 1]; + + sg_list = dma_pool_alloc(pool, GFP_ATOMIC, &sgl_dma); + if (!sg_list) { + dev_err_ratelimited(hdev->dev, + "Allocate %dth sgl_list;" + " failed\n", + iod->npages + 1); + return -ENOMEM; + } + list[iod->npages++] = sg_list; + + i = 0; + memcpy(&sg_list[i++], link, sizeof(*link)); + spraid_sgl_set_seg(link, sgl_dma, nsge); + } + + spraid_sgl_set_data(&sg_list[i++], sg); + sg = sg_next(sg); + } while (--nsge > 0); + + return 0; +} + +#define SPRAID_RW_FUA BIT(14) + +static void spraid_setup_rw_cmd(struct spraid_dev *hdev, + struct spraid_rw_command *rw, + struct scsi_cmnd *scmd) +{ + u32 start_lba_lo, start_lba_hi; + u32 datalength = 0; + u16 control = 0; + + start_lba_lo = 0; + start_lba_hi = 0; + + if (scmd->sc_data_direction == DMA_TO_DEVICE) { + rw->opcode = SPRAID_CMD_WRITE; + } else if (scmd->sc_data_direction == DMA_FROM_DEVICE) { + rw->opcode = SPRAID_CMD_READ; + } else { + dev_err(hdev->dev, + "Invalid IO for unsupported data direction: %d\n", + scmd->sc_data_direction); + WARN_ON(1); + } + + /* 6-byte READ(0x08) or WRITE(0x0A) cdb */ + if (scmd->cmd_len == 6) { + datalength = (u32)(scmd->cmnd[4] == 0 ? + IO_6_DEFAULT_TX_LEN : scmd->cmnd[4]); + start_lba_lo = (u32)get_unaligned_be24(&scmd->cmnd[1]); + + start_lba_lo &= 0x1FFFFF; + } + + /* 10-byte READ(0x28) or WRITE(0x2A) cdb */ + else if (scmd->cmd_len == 10) { + datalength = (u32)get_unaligned_be16(&scmd->cmnd[7]); + start_lba_lo = get_unaligned_be32(&scmd->cmnd[2]); + + if (scmd->cmnd[1] & FUA_MASK) + control |= SPRAID_RW_FUA; + } + + /* 12-byte READ(0xA8) or WRITE(0xAA) cdb */ + else if (scmd->cmd_len == 12) { + datalength = get_unaligned_be32(&scmd->cmnd[6]); + start_lba_lo = get_unaligned_be32(&scmd->cmnd[2]); + + if (scmd->cmnd[1] & FUA_MASK) + control |= SPRAID_RW_FUA; + } + /* 16-byte READ(0x88) or WRITE(0x8A) cdb */ + else if (scmd->cmd_len == 16) { + datalength = get_unaligned_be32(&scmd->cmnd[10]); + start_lba_lo = get_unaligned_be32(&scmd->cmnd[6]); + start_lba_hi = get_unaligned_be32(&scmd->cmnd[2]); + + if (scmd->cmnd[1] & FUA_MASK) + control |= SPRAID_RW_FUA; + } + /* 32-byte READ(0x88) or WRITE(0x8A) cdb */ + else if (scmd->cmd_len == 32) { + datalength = get_unaligned_be32(&scmd->cmnd[28]); + start_lba_lo = get_unaligned_be32(&scmd->cmnd[16]); + start_lba_hi = get_unaligned_be32(&scmd->cmnd[12]); + + if (scmd->cmnd[10] & FUA_MASK) + control |= SPRAID_RW_FUA; + } + + if (unlikely(datalength > U16_MAX || datalength == 0)) { + dev_err(hdev->dev, + "Invalid IO for illegal transfer data length: %u\n", + datalength); + WARN_ON(1); + } + + rw->slba = cpu_to_le64(((u64)start_lba_hi << 32) | start_lba_lo); + /* 0base for nlb */ + rw->nlb = cpu_to_le16((u16)(datalength - 1)); + rw->control = cpu_to_le16(control); +} + +static void spraid_setup_nonio_cmd(struct spraid_dev *hdev, + struct spraid_scsi_nonio *scsi_nonio, + struct scsi_cmnd *scmd) +{ + scsi_nonio->buffer_len = cpu_to_le32(scsi_bufflen(scmd)); + + switch (scmd->sc_data_direction) { + case DMA_NONE: + scsi_nonio->opcode = SPRAID_CMD_NONIO_NONE; + break; + case DMA_TO_DEVICE: + scsi_nonio->opcode = SPRAID_CMD_NONIO_TODEV; + break; + case DMA_FROM_DEVICE: + scsi_nonio->opcode = SPRAID_CMD_NONIO_FROMDEV; + break; + default: + dev_err(hdev->dev, + "Invalid IO for unsupported data direction: %d\n", + scmd->sc_data_direction); + WARN_ON(1); + } +} + +static void spraid_setup_ioq_cmd(struct spraid_dev *hdev, + struct spraid_ioq_command *ioq_cmd, + struct scsi_cmnd *scmd) +{ + memcpy(ioq_cmd->common.cdb, scmd->cmnd, scmd->cmd_len); + ioq_cmd->common.cdb_len = scmd->cmd_len; + + if (spraid_is_rw_scmd(scmd)) + spraid_setup_rw_cmd(hdev, &ioq_cmd->rw, scmd); + else + spraid_setup_nonio_cmd(hdev, &ioq_cmd->scsi_nonio, scmd); +} + +static int spraid_init_iod(struct spraid_dev *hdev, struct spraid_iod *iod, + struct spraid_ioq_command *ioq_cmd, + struct scsi_cmnd *scmd) +{ + if (unlikely(!iod->sense)) { + dev_err(hdev->dev, "Allocate sense data buffer failed\n"); + return -ENOMEM; + } + ioq_cmd->common.sense_addr = cpu_to_le64(iod->sense_dma); + ioq_cmd->common.sense_len = cpu_to_le16(SCSI_SENSE_BUFFERSIZE); + + iod->nsge = 0; + iod->npages = -1; + iod->use_sgl = 0; + iod->sg_drv_mgmt = false; + WRITE_ONCE(iod->state, SPRAID_CMD_IDLE); + + return 0; +} + +static void spraid_free_iod_res(struct spraid_dev *hdev, struct spraid_iod *iod) +{ + const int last_prp = hdev->page_size / sizeof(__le64) - 1; + dma_addr_t dma_addr, next_dma_addr; + struct spraid_sgl_desc *sg_list; + __le64 *prp_list; + void *addr; + int i; + + dma_addr = iod->first_dma; + if (iod->npages == 0) + dma_pool_free(iod->spraidq->prp_small_pool, + spraid_iod_list(iod)[0], dma_addr); + + for (i = 0; i < iod->npages; i++) { + addr = spraid_iod_list(iod)[i]; + + if (iod->use_sgl) { + sg_list = addr; + next_dma_addr = + le64_to_cpu((sg_list[SGES_PER_PAGE - 1]).addr); + } else { + prp_list = addr; + next_dma_addr = le64_to_cpu(prp_list[last_prp]); + } + + dma_pool_free(hdev->prp_page_pool, addr, dma_addr); + dma_addr = next_dma_addr; + } + + if (iod->sg_drv_mgmt && iod->sg != iod->inline_sg) { + iod->sg_drv_mgmt = false; + mempool_free(iod->sg, hdev->iod_mempool); + } + + iod->sense = NULL; + iod->npages = -1; +} + +static int spraid_io_map_data(struct spraid_dev *hdev, struct spraid_iod *iod, + struct scsi_cmnd *scmd, + struct spraid_ioq_command *ioq_cmd) +{ + int ret; + + iod->nsge = scsi_dma_map(scmd); + + /* No data to DMA, it may be scsi no-rw command */ + if (unlikely(iod->nsge == 0)) + return 0; + + iod->length = scsi_bufflen(scmd); + iod->sg = scsi_sglist(scmd); + iod->use_sgl = !spraid_is_prp(hdev, scmd, iod->nsge); + + if (iod->use_sgl) { + ret = spraid_setup_ioq_cmd_sgl(hdev, scmd, ioq_cmd, iod); + } else { + ret = spraid_setup_prps(hdev, iod); + ioq_cmd->common.dptr.prp1 = + cpu_to_le64(sg_dma_address(iod->sg)); + ioq_cmd->common.dptr.prp2 = cpu_to_le64(iod->first_dma); + } + + if (ret) + scsi_dma_unmap(scmd); + + return ret; +} + +static void spraid_map_status(struct spraid_iod *iod, struct scsi_cmnd *scmd, + struct spraid_completion *cqe) +{ + scsi_set_resid(scmd, 0); + + switch ((le16_to_cpu(cqe->status) >> 1) & 0x7f) { + case FW_STAT_OK: + set_host_byte(scmd, DID_OK); + break; + case FW_STAT_NEED_CHECK: + set_host_byte(scmd, DID_OK); + scmd->result |= le16_to_cpu(cqe->status) >> 8; + if (scmd->result & SAM_STAT_CHECK_CONDITION) { + memset(scmd->sense_buffer, 0, SCSI_SENSE_BUFFERSIZE); + memcpy(scmd->sense_buffer, iod->sense, + SCSI_SENSE_BUFFERSIZE); + scmd->result = + (scmd->result & 0x00ffffff) | (DRIVER_SENSE << 24); + } + break; + case FW_STAT_ABORTED: + set_host_byte(scmd, DID_ABORT); + break; + case FW_STAT_NEED_RETRY: + set_host_byte(scmd, DID_REQUEUE); + break; + default: + set_host_byte(scmd, DID_BAD_TARGET); + break; + } +} + +static inline void spraid_get_tag_from_scmd(struct scsi_cmnd *scmd, + u16 *qid, u16 *cid) +{ + u32 tag = blk_mq_unique_tag(scmd->request); + + *qid = blk_mq_unique_tag_to_hwq(tag) + 1; + *cid = blk_mq_unique_tag_to_tag(tag); +} + +static int spraid_queue_command(struct Scsi_Host *shost, struct scsi_cmnd *scmd) +{ + struct spraid_iod *iod = scsi_cmd_priv(scmd); + struct spraid_dev *hdev = shost_priv(shost); + struct scsi_device *sdev = scmd->device; + struct spraid_sdev_hostdata *hostdata; + struct spraid_ioq_command ioq_cmd; + struct spraid_queue *ioq; + unsigned long elapsed; + u16 hwq, cid; + int ret; + + if (unlikely(!scmd)) { + dev_err(hdev->dev, "err, scmd is null\n"); + return 0; + } + + if (unlikely(hdev->state != SPRAID_LIVE)) { + set_host_byte(scmd, DID_NO_CONNECT); + scmd->scsi_done(scmd); + return 0; + } + + if (log_debug_switch) + scsi_print_command(scmd); + + spraid_get_tag_from_scmd(scmd, &hwq, &cid); + hostdata = sdev->hostdata; + ioq = &hdev->queues[hwq]; + memset(&ioq_cmd, 0, sizeof(ioq_cmd)); + ioq_cmd.rw.hdid = cpu_to_le32(hostdata->hdid); + ioq_cmd.rw.command_id = cid; + + spraid_setup_ioq_cmd(hdev, &ioq_cmd, scmd); + + ret = cid * SCSI_SENSE_BUFFERSIZE; + iod->sense = ioq->sense + ret; + iod->sense_dma = ioq->sense_dma_addr + ret; + + ret = spraid_init_iod(hdev, iod, &ioq_cmd, scmd); + if (unlikely(ret)) + return SCSI_MLQUEUE_HOST_BUSY; + + iod->spraidq = ioq; + ret = spraid_io_map_data(hdev, iod, scmd, &ioq_cmd); + if (unlikely(ret)) { + dev_err(hdev->dev, "spraid_io_map_data Err.\n"); + set_host_byte(scmd, DID_ERROR); + scmd->scsi_done(scmd); + ret = 0; + goto deinit_iod; + } + + WRITE_ONCE(iod->state, SPRAID_CMD_IN_FLIGHT); + spraid_submit_cmd(ioq, &ioq_cmd); + elapsed = jiffies - scmd->jiffies_at_alloc; + dev_log_dbg(hdev->dev, + "cid[%d] qid[%d] submit IO cost %3ld.%3ld seconds\n", + cid, hwq, elapsed / HZ, elapsed % HZ); + return 0; + +deinit_iod: + spraid_free_iod_res(hdev, iod); + return ret; +} + +static int spraid_match_dev(struct spraid_dev *hdev, u16 idx, + struct scsi_device *sdev) +{ + if (SPRAID_DEV_INFO_FLAG_VALID(hdev->devices[idx].flag)) { + if (sdev->channel == hdev->devices[idx].channel && + sdev->id == le16_to_cpu(hdev->devices[idx].target) && + sdev->lun < hdev->devices[idx].lun) { + dev_info(hdev->dev, + "Match device success, channel;" + "target:lun[%d:%d:%d]\n", + hdev->devices[idx].channel, + hdev->devices[idx].target, + hdev->devices[idx].lun); + return 1; + } + } + + return 0; +} + +static int spraid_slave_alloc(struct scsi_device *sdev) +{ + struct spraid_sdev_hostdata *hostdata; + struct spraid_dev *hdev; + u16 idx; + + hdev = shost_priv(sdev->host); + hostdata = kzalloc(sizeof(*hostdata), GFP_KERNEL); + if (!hostdata) { + dev_err(hdev->dev, "Alloc scsi host data memory failed\n"); + return -ENOMEM; + } + + down_read(&hdev->devices_rwsem); + for (idx = 0; idx < le32_to_cpu(hdev->ctrl_info->nd); idx++) { + if (spraid_match_dev(hdev, idx, sdev)) + goto scan_host; + } + up_read(&hdev->devices_rwsem); + + kfree(hostdata); + return -ENXIO; + +scan_host: + hostdata->hdid = le32_to_cpu(hdev->devices[idx].hdid); + hostdata->max_io_kb = le16_to_cpu(hdev->devices[idx].max_io_kb); + hostdata->attr = hdev->devices[idx].attr; + hostdata->flag = hdev->devices[idx].flag; + hostdata->rg_id = 0xff; + sdev->hostdata = hostdata; + up_read(&hdev->devices_rwsem); + return 0; +} + +static void spraid_slave_destroy(struct scsi_device *sdev) +{ + kfree(sdev->hostdata); + sdev->hostdata = NULL; +} + +static int spraid_slave_configure(struct scsi_device *sdev) +{ + u16 idx; + unsigned int timeout = scmd_tmout_nonpt * HZ; + struct spraid_dev *hdev = shost_priv(sdev->host); + struct spraid_sdev_hostdata *hostdata = sdev->hostdata; + u32 max_sec = sdev->host->max_sectors; + + if (hostdata) { + idx = hostdata->hdid - 1; + if (sdev->channel == hdev->devices[idx].channel && + sdev->id == le16_to_cpu(hdev->devices[idx].target) && + sdev->lun < hdev->devices[idx].lun) { + if (SPRAID_DEV_INFO_ATTR_PT(hdev->devices[idx].attr)) + timeout = 30 * HZ; + else + timeout = scmd_tmout_nonpt * HZ; + max_sec = le16_to_cpu(hdev->devices[idx].max_io_kb) + << 1; + } else { + dev_err(hdev->dev, + "[%s] err, sdev->channel:id:lun[%d:%d:%lld];" + "devices[%d], channel:target:lun[%d:%d:%d]\n", + __func__, sdev->channel, sdev->id, sdev->lun, + idx, hdev->devices[idx].channel, + hdev->devices[idx].target, + hdev->devices[idx].lun); + } + } else { + dev_err(hdev->dev, "[%s] err, sdev->hostdata is null\n", + __func__); + } + + blk_queue_rq_timeout(sdev->request_queue, timeout); + sdev->eh_timeout = timeout; + + if ((max_sec == 0) || (max_sec > sdev->host->max_sectors)) + max_sec = sdev->host->max_sectors; + + dev_info(hdev->dev, + "[%s] sdev->channel:id:lun[%d:%d:%lld];" + " scmd_timeout[%d]s, maxsec[%d]\n", + __func__, sdev->channel, sdev->id, + sdev->lun, timeout / HZ, max_sec); + + return 0; +} + +static void spraid_shost_init(struct spraid_dev *hdev) +{ + struct pci_dev *pdev = hdev->pdev; + u8 domain, bus; + u32 dev_func; + + domain = pci_domain_nr(pdev->bus); + bus = pdev->bus->number; + dev_func = pdev->devfn; + + hdev->shost->nr_hw_queues = hdev->online_queues - 1; + hdev->shost->can_queue = (hdev->ioq_depth - SPRAID_PTCMDS_PERQ); + + hdev->shost->sg_tablesize = le16_to_cpu(hdev->ctrl_info->max_num_sge); + /* 512B per sector */ + hdev->shost->max_sectors = + (1U << ((hdev->ctrl_info->mdts) * 1U) << 12) / 512; + hdev->shost->cmd_per_lun = MAX_CMD_PER_DEV; + hdev->shost->max_channel = + le16_to_cpu(hdev->ctrl_info->max_channel) - 1; + hdev->shost->max_id = le32_to_cpu(hdev->ctrl_info->max_tgt_id); + hdev->shost->max_lun = le16_to_cpu(hdev->ctrl_info->max_lun); + + hdev->shost->this_id = -1; + hdev->shost->unique_id = (domain << 16) | (bus << 8) | dev_func; + hdev->shost->max_cmd_len = MAX_CDB_LEN; + hdev->shost->hostt->cmd_size = max(spraid_cmd_size(hdev, false, true), + spraid_cmd_size(hdev, false, false)); +} + +static inline void spraid_host_deinit(struct spraid_dev *hdev) +{ + ida_free(&spraid_instance_ida, hdev->instance); +} + +static int spraid_alloc_queue(struct spraid_dev *hdev, u16 qid, u16 depth) +{ + struct spraid_queue *spraidq = &hdev->queues[qid]; + int ret = 0; + + if (hdev->queue_count > qid) { + dev_info(hdev->dev, "[%s] warn: queue[%d] is exist\n", + __func__, qid); + return 0; + } + + spraidq->cqes = dma_alloc_coherent(hdev->dev, CQ_SIZE(depth), + &spraidq->cq_dma_addr, + GFP_KERNEL | __GFP_ZERO); + if (!spraidq->cqes) + return -ENOMEM; + + spraidq->sq_cmds = dma_alloc_coherent(hdev->dev, SQ_SIZE(qid, depth), + &spraidq->sq_dma_addr, + GFP_KERNEL); + if (!spraidq->sq_cmds) { + ret = -ENOMEM; + goto free_cqes; + } + + spin_lock_init(&spraidq->sq_lock); + spin_lock_init(&spraidq->cq_lock); + spraidq->hdev = hdev; + spraidq->q_depth = depth; + spraidq->qid = qid; + spraidq->cq_vector = -1; + hdev->queue_count++; + + /* alloc sense buffer */ + spraidq->sense = dma_alloc_coherent(hdev->dev, SENSE_SIZE(depth), + &spraidq->sense_dma_addr, + GFP_KERNEL | __GFP_ZERO); + if (!spraidq->sense) { + ret = -ENOMEM; + goto free_sq_cmds; + } + + return 0; + +free_sq_cmds: + dma_free_coherent(hdev->dev, SQ_SIZE(qid, depth), + (void *)spraidq->sq_cmds, spraidq->sq_dma_addr); +free_cqes: + dma_free_coherent(hdev->dev, CQ_SIZE(depth), (void *)spraidq->cqes, + spraidq->cq_dma_addr); + return ret; +} + +static int spraid_wait_ready(struct spraid_dev *hdev, u64 cap, bool enabled) +{ + unsigned long timeout = + ((SPRAID_CAP_TIMEOUT(cap) + 1) * SPRAID_CAP_TIMEOUT_UNIT_MS) + jiffies; + u32 bit = enabled ? SPRAID_CSTS_RDY : 0; + + while ((readl(hdev->bar + SPRAID_REG_CSTS) & SPRAID_CSTS_RDY) != bit) { + usleep_range(1000, 2000); + if (fatal_signal_pending(current)) + return -EINTR; + + if (time_after(jiffies, timeout)) { + dev_err(hdev->dev, "Device not ready; aborting %s\n", + enabled ? "initialisation" : "reset"); + return -ENODEV; + } + } + return 0; +} + +static int spraid_shutdown_ctrl(struct spraid_dev *hdev) +{ + unsigned long timeout = hdev->ctrl_info->rtd3e + jiffies; + + hdev->ctrl_config &= ~SPRAID_CC_SHN_MASK; + hdev->ctrl_config |= SPRAID_CC_SHN_NORMAL; + writel(hdev->ctrl_config, hdev->bar + SPRAID_REG_CC); + + while ((readl(hdev->bar + SPRAID_REG_CSTS) & SPRAID_CSTS_SHST_MASK) != + SPRAID_CSTS_SHST_CMPLT) { + msleep(100); + if (fatal_signal_pending(current)) + return -EINTR; + if (time_after(jiffies, timeout)) { + dev_err(hdev->dev, + "Device shutdown incomplete; abort shutdown\n"); + return -ENODEV; + } + } + return 0; +} + +static int spraid_disable_ctrl(struct spraid_dev *hdev) +{ + hdev->ctrl_config &= ~SPRAID_CC_SHN_MASK; + hdev->ctrl_config &= ~SPRAID_CC_ENABLE; + writel(hdev->ctrl_config, hdev->bar + SPRAID_REG_CC); + + return spraid_wait_ready(hdev, hdev->cap, false); +} + +static int spraid_enable_ctrl(struct spraid_dev *hdev) +{ + u64 cap = hdev->cap; + u32 dev_page_min = SPRAID_CAP_MPSMIN(cap) + 12; + u32 page_shift = PAGE_SHIFT; + + if (page_shift < dev_page_min) { + dev_err(hdev->dev, + "Minimum device page size[%u], too large for host[%u]\n", + 1U << dev_page_min, 1U << page_shift); + return -ENODEV; + } + + page_shift = min_t(unsigned int, SPRAID_CAP_MPSMAX(cap) + 12, + PAGE_SHIFT); + hdev->page_size = 1U << page_shift; + + hdev->ctrl_config = SPRAID_CC_CSS_NVM; + hdev->ctrl_config |= (page_shift - 12) << SPRAID_CC_MPS_SHIFT; + hdev->ctrl_config |= SPRAID_CC_AMS_RR | SPRAID_CC_SHN_NONE; + hdev->ctrl_config |= SPRAID_CC_IOSQES | SPRAID_CC_IOCQES; + hdev->ctrl_config |= SPRAID_CC_ENABLE; + writel(hdev->ctrl_config, hdev->bar + SPRAID_REG_CC); + + return spraid_wait_ready(hdev, cap, true); +} + +static void spraid_init_queue(struct spraid_queue *spraidq, u16 qid) +{ + struct spraid_dev *hdev = spraidq->hdev; + + memset((void *)spraidq->cqes, 0, CQ_SIZE(spraidq->q_depth)); + + spraidq->sq_tail = 0; + spraidq->cq_head = 0; + spraidq->cq_phase = 1; + spraidq->q_db = &hdev->dbs[qid * 2 * hdev->db_stride]; + spraidq->prp_small_pool = hdev->prp_small_pool[qid % small_pool_num]; + hdev->online_queues++; +} + +static inline bool spraid_cqe_pending(struct spraid_queue *spraidq) +{ + return (le16_to_cpu(spraidq->cqes[spraidq->cq_head].status) & 1) == + spraidq->cq_phase; +} + +static void spraid_sata_report_zone_handle(struct scsi_cmnd *scmd, + struct spraid_iod *iod) +{ + int i = 0; + unsigned int bytes = 0; + struct scatterlist *sg = scsi_sglist(scmd); + + scsi_for_each_sg(scmd, sg, iod->nsge, i) { + unsigned int offset = 0; + + if (bytes == 0) { + char *hdr; + u32 list_length; + u64 max_lba, opt_lba; + u16 same; + + hdr = sg_virt(sg); + + list_length = get_unaligned_le32(&hdr[0]); + same = get_unaligned_le16(&hdr[4]); + max_lba = get_unaligned_le64(&hdr[8]); + opt_lba = get_unaligned_le64(&hdr[16]); + put_unaligned_be32(list_length, &hdr[0]); + hdr[4] = same & 0xf; + put_unaligned_be64(max_lba, &hdr[8]); + put_unaligned_be64(opt_lba, &hdr[16]); + offset += 64; + bytes += 64; + } + while (offset < sg_dma_len(sg)) { + char *rec; + u8 cond, type, non_seq, reset; + u64 size, start, wp; + + rec = sg_virt(sg) + offset; + type = rec[0] & 0xf; + cond = (rec[1] >> 4) & 0xf; + non_seq = (rec[1] & 2); + reset = (rec[1] & 1); + size = get_unaligned_le64(&rec[8]); + start = get_unaligned_le64(&rec[16]); + wp = get_unaligned_le64(&rec[24]); + rec[0] = type; + rec[1] = (cond << 4) | non_seq | reset; + put_unaligned_be64(size, &rec[8]); + put_unaligned_be64(start, &rec[16]); + put_unaligned_be64(wp, &rec[24]); + WARN_ON(offset + 64 > sg_dma_len(sg)); + offset += 64; + bytes += 64; + } + } +} + +static inline void spraid_handle_ata_cmd(struct spraid_dev *hdev, + struct scsi_cmnd *scmd, + struct spraid_iod *iod) +{ + if (hdev->ctrl_info->card_type != SPRAID_CARD_HBA) + return; + + switch (scmd->cmnd[0]) { + case ZBC_IN: + dev_info(hdev->dev, "[%s] process report zone\n", __func__); + spraid_sata_report_zone_handle(scmd, iod); + break; + default: + break; + } +} + +static void spraid_complete_ioq_cmnd(struct spraid_queue *ioq, + struct spraid_completion *cqe) +{ + struct spraid_dev *hdev = ioq->hdev; + struct blk_mq_tags *tags; + struct scsi_cmnd *scmd; + struct spraid_iod *iod; + struct request *req; + unsigned long elapsed; + + tags = hdev->shost->tag_set.tags[ioq->qid - 1]; + req = blk_mq_tag_to_rq(tags, cqe->cmd_id); + if (unlikely(!req || !blk_mq_request_started(req))) { + dev_warn(hdev->dev, "Invalid id %d completed on queue %d\n", + cqe->cmd_id, ioq->qid); + return; + } + + scmd = blk_mq_rq_to_pdu(req); + iod = scsi_cmd_priv(scmd); + + elapsed = jiffies - scmd->jiffies_at_alloc; + dev_log_dbg(hdev->dev, + "cid[%d] qid[%d] finish IO cost %3ld.%3ld seconds\n", + cqe->cmd_id, ioq->qid, elapsed / HZ, elapsed % HZ); + + if (cmpxchg(&iod->state, SPRAID_CMD_IN_FLIGHT, SPRAID_CMD_COMPLETE) != + SPRAID_CMD_IN_FLIGHT) { + dev_warn(hdev->dev, + "cid[%d] qid[%d] enters abnormal handler;" + " cost %3ld.%3ld seconds\n", + cqe->cmd_id, ioq->qid, elapsed / HZ, elapsed % HZ); + WRITE_ONCE(iod->state, SPRAID_CMD_TMO_COMPLETE); + + if (iod->nsge) { + iod->nsge = 0; + scsi_dma_unmap(scmd); + } + spraid_free_iod_res(hdev, iod); + + return; + } + + spraid_handle_ata_cmd(hdev, scmd, iod); + + spraid_map_status(iod, scmd, cqe); + if (iod->nsge) { + iod->nsge = 0; + scsi_dma_unmap(scmd); + } + spraid_free_iod_res(hdev, iod); + scmd->scsi_done(scmd); +} + +static void spraid_complete_adminq_cmnd(struct spraid_queue *adminq, + struct spraid_completion *cqe) +{ + struct spraid_dev *hdev = adminq->hdev; + struct spraid_cmd *adm_cmd; + + adm_cmd = hdev->adm_cmds + cqe->cmd_id; + if (unlikely(adm_cmd->state == SPRAID_CMD_IDLE)) { + dev_warn(adminq->hdev->dev, + "Invalid id %d completed on queue %d\n", + cqe->cmd_id, le16_to_cpu(cqe->sq_id)); + return; + } + + adm_cmd->status = le16_to_cpu(cqe->status) >> 1; + adm_cmd->result0 = le32_to_cpu(cqe->result); + adm_cmd->result1 = le32_to_cpu(cqe->result1); + + complete(&adm_cmd->cmd_done); +} + +static void spraid_send_aen(struct spraid_dev *hdev, u16 cid); + +static void spraid_complete_aen(struct spraid_queue *spraidq, + struct spraid_completion *cqe) +{ + struct spraid_dev *hdev = spraidq->hdev; + u32 result = le32_to_cpu(cqe->result); + + dev_info(hdev->dev, "rcv aen, cid[%d], status[0x%x], result[0x%x]\n", + cqe->cmd_id, le16_to_cpu(cqe->status) >> 1, result); + + spraid_send_aen(hdev, cqe->cmd_id); + + if ((le16_to_cpu(cqe->status) >> 1) != SPRAID_SC_SUCCESS) + return; + switch (result & 0x7) { + case SPRAID_AEN_NOTICE: + spraid_handle_aen_notice(hdev, result); + break; + case SPRAID_AEN_VS: + spraid_handle_aen_vs(hdev, result, le32_to_cpu(cqe->result1)); + break; + default: + dev_warn(hdev->dev, "Unsupported async event type: %u\n", + result & 0x7); + break; + } +} + +static void spraid_complete_ioq_sync_cmnd(struct spraid_queue *ioq, + struct spraid_completion *cqe) +{ + struct spraid_dev *hdev = ioq->hdev; + struct spraid_cmd *ptcmd; + + ptcmd = hdev->ioq_ptcmds + (ioq->qid - 1) * SPRAID_PTCMDS_PERQ + + cqe->cmd_id - SPRAID_IO_BLK_MQ_DEPTH; + + ptcmd->status = le16_to_cpu(cqe->status) >> 1; + ptcmd->result0 = le32_to_cpu(cqe->result); + ptcmd->result1 = le32_to_cpu(cqe->result1); + + complete(&ptcmd->cmd_done); +} + +static inline void spraid_handle_cqe(struct spraid_queue *spraidq, u16 idx) +{ + struct spraid_completion *cqe = &spraidq->cqes[idx]; + struct spraid_dev *hdev = spraidq->hdev; + + if (unlikely(cqe->cmd_id >= spraidq->q_depth)) { + dev_err(hdev->dev, + "Invalid command id[%d] completed on queue %d\n", + cqe->cmd_id, cqe->sq_id); + return; + } + + dev_log_dbg(hdev->dev, "cid[%d] qid[%d];" + " result[0x%x], sq_id[%d], status[0x%x]\n", + cqe->cmd_id, spraidq->qid, le32_to_cpu(cqe->result), + le16_to_cpu(cqe->sq_id), le16_to_cpu(cqe->status)); + + if (unlikely(spraidq->qid == 0 + && cqe->cmd_id >= SPRAID_AQ_BLK_MQ_DEPTH)) { + spraid_complete_aen(spraidq, cqe); + return; + } + + if (unlikely(spraidq->qid && cqe->cmd_id >= SPRAID_IO_BLK_MQ_DEPTH)) { + spraid_complete_ioq_sync_cmnd(spraidq, cqe); + return; + } + + if (spraidq->qid) + spraid_complete_ioq_cmnd(spraidq, cqe); + else + spraid_complete_adminq_cmnd(spraidq, cqe); +} + +static void spraid_complete_cqes(struct spraid_queue *spraidq, + u16 start, u16 end) +{ + while (start != end) { + spraid_handle_cqe(spraidq, start); + if (++start == spraidq->q_depth) + start = 0; + } +} + +static inline void spraid_update_cq_head(struct spraid_queue *spraidq) +{ + if (++spraidq->cq_head == spraidq->q_depth) { + spraidq->cq_head = 0; + spraidq->cq_phase = !spraidq->cq_phase; + } +} + +static inline bool spraid_process_cq(struct spraid_queue *spraidq, + u16 *start, u16 *end, int tag) +{ + bool found = false; + + *start = spraidq->cq_head; + while (!found && spraid_cqe_pending(spraidq)) { + if (spraidq->cqes[spraidq->cq_head].cmd_id == tag) + found = true; + spraid_update_cq_head(spraidq); + } + *end = spraidq->cq_head; + + if (*start != *end) + writel(spraidq->cq_head, + spraidq->q_db + spraidq->hdev->db_stride); + + return found; +} + +static bool spraid_poll_cq(struct spraid_queue *spraidq, int cid) +{ + u16 start, end; + bool found; + + if (!spraid_cqe_pending(spraidq)) + return 0; + + spin_lock_irq(&spraidq->cq_lock); + found = spraid_process_cq(spraidq, &start, &end, cid); + spin_unlock_irq(&spraidq->cq_lock); + + spraid_complete_cqes(spraidq, start, end); + return found; +} + +static irqreturn_t spraid_irq(int irq, void *data) +{ + struct spraid_queue *spraidq = data; + irqreturn_t ret = IRQ_NONE; + u16 start, end; + + spin_lock(&spraidq->cq_lock); + if (spraidq->cq_head != spraidq->last_cq_head) + ret = IRQ_HANDLED; + + spraid_process_cq(spraidq, &start, &end, -1); + spraidq->last_cq_head = spraidq->cq_head; + spin_unlock(&spraidq->cq_lock); + + if (start != end) { + spraid_complete_cqes(spraidq, start, end); + ret = IRQ_HANDLED; + } + return ret; +} + +static int spraid_setup_admin_queue(struct spraid_dev *hdev) +{ + struct spraid_queue *adminq = &hdev->queues[0]; + u32 aqa; + int ret; + + dev_info(hdev->dev, "[%s] start disable ctrl\n", __func__); + + ret = spraid_disable_ctrl(hdev); + if (ret) + return ret; + + ret = spraid_alloc_queue(hdev, 0, SPRAID_AQ_DEPTH); + if (ret) + return ret; + + aqa = adminq->q_depth - 1; + aqa |= aqa << 16; + writel(aqa, hdev->bar + SPRAID_REG_AQA); + lo_hi_writeq(adminq->sq_dma_addr, hdev->bar + SPRAID_REG_ASQ); + lo_hi_writeq(adminq->cq_dma_addr, hdev->bar + SPRAID_REG_ACQ); + + dev_info(hdev->dev, "[%s] start enable ctrl\n", __func__); + + ret = spraid_enable_ctrl(hdev); + if (ret) { + ret = -ENODEV; + goto free_queue; + } + + adminq->cq_vector = 0; + spraid_init_queue(adminq, 0); + ret = pci_request_irq(hdev->pdev, adminq->cq_vector, spraid_irq, NULL, + adminq, "spraid%d_q%d", + hdev->instance, adminq->qid); + + if (ret) { + adminq->cq_vector = -1; + hdev->online_queues--; + goto free_queue; + } + + dev_info(hdev->dev, "[%s] success, queuecount:[%d], onlinequeue:[%d]\n", + __func__, hdev->queue_count, hdev->online_queues); + + return 0; + +free_queue: + spraid_free_queue(adminq); + return ret; +} + +static u32 spraid_bar_size(struct spraid_dev *hdev, u32 nr_ioqs) +{ + return (SPRAID_REG_DBS + ((nr_ioqs + 1) * 8 * hdev->db_stride)); +} + +static int spraid_alloc_admin_cmds(struct spraid_dev *hdev) +{ + int i; + + INIT_LIST_HEAD(&hdev->adm_cmd_list); + spin_lock_init(&hdev->adm_cmd_lock); + + hdev->adm_cmds = kcalloc_node(SPRAID_AQ_BLK_MQ_DEPTH, + sizeof(struct spraid_cmd), + GFP_KERNEL, hdev->numa_node); + + if (!hdev->adm_cmds) { + dev_err(hdev->dev, "Alloc admin cmds failed\n"); + return -ENOMEM; + } + + for (i = 0; i < SPRAID_AQ_BLK_MQ_DEPTH; i++) { + hdev->adm_cmds[i].qid = 0; + hdev->adm_cmds[i].cid = i; + list_add_tail(&(hdev->adm_cmds[i].list), &hdev->adm_cmd_list); + } + + dev_info(hdev->dev, "Alloc admin cmds success, num[%d]\n", + SPRAID_AQ_BLK_MQ_DEPTH); + + return 0; +} + +static void spraid_free_admin_cmds(struct spraid_dev *hdev) +{ + kfree(hdev->adm_cmds); + hdev->adm_cmds = NULL; + INIT_LIST_HEAD(&hdev->adm_cmd_list); +} + +static struct spraid_cmd *spraid_get_cmd(struct spraid_dev *hdev, + enum spraid_cmd_type type) +{ + struct spraid_cmd *cmd = NULL; + unsigned long flags; + struct list_head *head = &hdev->adm_cmd_list; + spinlock_t *slock = &hdev->adm_cmd_lock; + + if (type == SPRAID_CMD_IOPT) { + head = &hdev->ioq_pt_list; + slock = &hdev->ioq_pt_lock; + } + + spin_lock_irqsave(slock, flags); + if (list_empty(head)) { + spin_unlock_irqrestore(slock, flags); + dev_err(hdev->dev, "err, cmd[%d] list empty\n", type); + return NULL; + } + cmd = list_entry(head->next, struct spraid_cmd, list); + list_del_init(&cmd->list); + spin_unlock_irqrestore(slock, flags); + + WRITE_ONCE(cmd->state, SPRAID_CMD_IN_FLIGHT); + + return cmd; +} + +static void spraid_put_cmd(struct spraid_dev *hdev, struct spraid_cmd *cmd, + enum spraid_cmd_type type) +{ + unsigned long flags; + struct list_head *head = &hdev->adm_cmd_list; + spinlock_t *slock = &hdev->adm_cmd_lock; + + if (type == SPRAID_CMD_IOPT) { + head = &hdev->ioq_pt_list; + slock = &hdev->ioq_pt_lock; + } + + spin_lock_irqsave(slock, flags); + WRITE_ONCE(cmd->state, SPRAID_CMD_IDLE); + list_add_tail(&cmd->list, head); + spin_unlock_irqrestore(slock, flags); +} + + +static int spraid_submit_admin_sync_cmd(struct spraid_dev *hdev, + struct spraid_admin_command *cmd, + u32 *result0, u32 *result1, u32 timeout) +{ + struct spraid_cmd *adm_cmd = spraid_get_cmd(hdev, SPRAID_CMD_ADM); + + if (!adm_cmd) { + dev_err(hdev->dev, "err, get admin cmd failed\n"); + return -EFAULT; + } + + timeout = timeout ? timeout : ADMIN_TIMEOUT; + + init_completion(&adm_cmd->cmd_done); + + cmd->common.command_id = adm_cmd->cid; + spraid_submit_cmd(&hdev->queues[0], cmd); + + if (!wait_for_completion_timeout(&adm_cmd->cmd_done, timeout)) { + dev_err(hdev->dev, "[%s] cid[%d] qid[%d] timeout;" + " opcode[0x%x] subopcode[0x%x]\n", + __func__, adm_cmd->cid, adm_cmd->qid, + cmd->usr_cmd.opcode, cmd->usr_cmd.info_0.subopcode); + WRITE_ONCE(adm_cmd->state, SPRAID_CMD_TIMEOUT); + spraid_put_cmd(hdev, adm_cmd, SPRAID_CMD_ADM); + return -EINVAL; + } + + if (result0) + *result0 = adm_cmd->result0; + if (result1) + *result1 = adm_cmd->result1; + + spraid_put_cmd(hdev, adm_cmd, SPRAID_CMD_ADM); + + return adm_cmd->status; +} + +static int spraid_create_cq(struct spraid_dev *hdev, u16 qid, + struct spraid_queue *spraidq, u16 cq_vector) +{ + struct spraid_admin_command admin_cmd; + int flags = SPRAID_QUEUE_PHYS_CONTIG | SPRAID_CQ_IRQ_ENABLED; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.create_cq.opcode = SPRAID_ADMIN_CREATE_CQ; + admin_cmd.create_cq.prp1 = cpu_to_le64(spraidq->cq_dma_addr); + admin_cmd.create_cq.cqid = cpu_to_le16(qid); + admin_cmd.create_cq.qsize = cpu_to_le16(spraidq->q_depth - 1); + admin_cmd.create_cq.cq_flags = cpu_to_le16(flags); + admin_cmd.create_cq.irq_vector = cpu_to_le16(cq_vector); + + return spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); +} + +static int spraid_create_sq(struct spraid_dev *hdev, u16 qid, + struct spraid_queue *spraidq) +{ + struct spraid_admin_command admin_cmd; + int flags = SPRAID_QUEUE_PHYS_CONTIG; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.create_sq.opcode = SPRAID_ADMIN_CREATE_SQ; + admin_cmd.create_sq.prp1 = cpu_to_le64(spraidq->sq_dma_addr); + admin_cmd.create_sq.sqid = cpu_to_le16(qid); + admin_cmd.create_sq.qsize = cpu_to_le16(spraidq->q_depth - 1); + admin_cmd.create_sq.sq_flags = cpu_to_le16(flags); + admin_cmd.create_sq.cqid = cpu_to_le16(qid); + + return spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); +} + +static void spraid_free_queue(struct spraid_queue *spraidq) +{ + struct spraid_dev *hdev = spraidq->hdev; + + hdev->queue_count--; + dma_free_coherent(hdev->dev, CQ_SIZE(spraidq->q_depth), + (void *)spraidq->cqes, spraidq->cq_dma_addr); + dma_free_coherent(hdev->dev, SQ_SIZE(spraidq->qid, spraidq->q_depth), + spraidq->sq_cmds, spraidq->sq_dma_addr); + dma_free_coherent(hdev->dev, SENSE_SIZE(spraidq->q_depth), + spraidq->sense, spraidq->sense_dma_addr); +} + +static void spraid_free_admin_queue(struct spraid_dev *hdev) +{ + spraid_free_queue(&hdev->queues[0]); +} + +static void spraid_free_io_queues(struct spraid_dev *hdev) +{ + int i; + + for (i = hdev->queue_count - 1; i >= 1; i--) + spraid_free_queue(&hdev->queues[i]); +} + +static int spraid_delete_queue(struct spraid_dev *hdev, u8 op, u16 id) +{ + struct spraid_admin_command admin_cmd; + int ret; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.delete_queue.opcode = op; + admin_cmd.delete_queue.qid = cpu_to_le16(id); + + ret = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); + + if (ret) + dev_err(hdev->dev, "Delete %s:[%d] failed\n", + (op == SPRAID_ADMIN_DELETE_CQ) ? "cq" : "sq", id); + + return ret; +} + +static int spraid_delete_cq(struct spraid_dev *hdev, u16 cqid) +{ + return spraid_delete_queue(hdev, SPRAID_ADMIN_DELETE_CQ, cqid); +} + +static int spraid_delete_sq(struct spraid_dev *hdev, u16 sqid) +{ + return spraid_delete_queue(hdev, SPRAID_ADMIN_DELETE_SQ, sqid); +} + +static int spraid_create_queue(struct spraid_queue *spraidq, u16 qid) +{ + struct spraid_dev *hdev = spraidq->hdev; + u16 cq_vector; + int ret; + + cq_vector = (hdev->num_vecs == 1) ? 0 : qid; + ret = spraid_create_cq(hdev, qid, spraidq, cq_vector); + if (ret) + return ret; + + ret = spraid_create_sq(hdev, qid, spraidq); + if (ret) + goto delete_cq; + + spraid_init_queue(spraidq, qid); + spraidq->cq_vector = cq_vector; + + ret = pci_request_irq(hdev->pdev, cq_vector, spraid_irq, NULL, + spraidq, "spraid%d_q%d", hdev->instance, qid); + + if (ret) { + dev_err(hdev->dev, "Request queue[%d] irq failed\n", qid); + goto delete_sq; + } + + return 0; + +delete_sq: + spraidq->cq_vector = -1; + hdev->online_queues--; + spraid_delete_sq(hdev, qid); +delete_cq: + spraid_delete_cq(hdev, qid); + + return ret; +} + +static int spraid_create_io_queues(struct spraid_dev *hdev) +{ + u32 i, max; + int ret = 0; + + max = min(hdev->max_qid, hdev->queue_count - 1); + for (i = hdev->online_queues; i <= max; i++) { + ret = spraid_create_queue(&hdev->queues[i], i); + if (ret) { + dev_err(hdev->dev, "Create queue[%d] failed\n", i); + break; + } + } + + dev_info(hdev->dev, "[%s] queue_count[%d], online_queue[%d]", + __func__, hdev->queue_count, hdev->online_queues); + + return ret >= 0 ? 0 : ret; +} + +static int spraid_set_features(struct spraid_dev *hdev, u32 fid, + u32 dword11, void *buffer, + size_t buflen, u32 *result) +{ + struct spraid_admin_command admin_cmd; + int ret; + u8 *data_ptr = NULL; + dma_addr_t data_dma = 0; + + if (buffer && buflen) { + data_ptr = dma_alloc_coherent(hdev->dev, buflen, + &data_dma, GFP_KERNEL); + if (!data_ptr) + return -ENOMEM; + + memcpy(data_ptr, buffer, buflen); + } + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.features.opcode = SPRAID_ADMIN_SET_FEATURES; + admin_cmd.features.fid = cpu_to_le32(fid); + admin_cmd.features.dword11 = cpu_to_le32(dword11); + admin_cmd.common.dptr.prp1 = cpu_to_le64(data_dma); + + ret = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, result, NULL, 0); + + if (data_ptr) + dma_free_coherent(hdev->dev, buflen, data_ptr, data_dma); + + return ret; +} + +static int spraid_configure_timestamp(struct spraid_dev *hdev) +{ + __le64 ts; + int ret; + + ts = cpu_to_le64(ktime_to_ms(ktime_get_real())); + ret = spraid_set_features(hdev, SPRAID_FEAT_TIMESTAMP, + 0, &ts, sizeof(ts), NULL); + + if (ret) + dev_err(hdev->dev, "set timestamp failed: %d\n", ret); + return ret; +} + +static int spraid_set_queue_cnt(struct spraid_dev *hdev, u32 *cnt) +{ + u32 q_cnt = (*cnt - 1) | ((*cnt - 1) << 16); + u32 nr_ioqs, result; + int status; + + status = spraid_set_features(hdev, SPRAID_FEAT_NUM_QUEUES, + q_cnt, NULL, 0, &result); + if (status) { + dev_err(hdev->dev, "Set queue count failed, status: %d\n", + status); + return -EIO; + } + + nr_ioqs = min(result & 0xffff, result >> 16) + 1; + *cnt = min(*cnt, nr_ioqs); + if (*cnt == 0) { + dev_err(hdev->dev, "Illegal queue count: zero\n"); + return -EIO; + } + return 0; +} + +static int spraid_setup_io_queues(struct spraid_dev *hdev) +{ + struct spraid_queue *adminq = &hdev->queues[0]; + struct pci_dev *pdev = hdev->pdev; + u32 nr_ioqs = num_online_cpus(); + u32 i, size; + int ret; + + struct irq_affinity affd = { + .pre_vectors = 1 + }; + + ret = spraid_set_queue_cnt(hdev, &nr_ioqs); + if (ret < 0) + return ret; + + size = spraid_bar_size(hdev, nr_ioqs); + ret = spraid_remap_bar(hdev, size); + if (ret) + return -ENOMEM; + + adminq->q_db = hdev->dbs; + + pci_free_irq(pdev, 0, adminq); + pci_free_irq_vectors(pdev); + + ret = pci_alloc_irq_vectors_affinity(pdev, 1, (nr_ioqs + 1), + PCI_IRQ_ALL_TYPES | PCI_IRQ_AFFINITY, &affd); + if (ret <= 0) + return -EIO; + + hdev->num_vecs = ret; + + hdev->max_qid = max(ret - 1, 1); + + ret = pci_request_irq(pdev, adminq->cq_vector, spraid_irq, NULL, + adminq, "spraid%d_q%d", + hdev->instance, adminq->qid); + if (ret) { + dev_err(hdev->dev, "Request admin irq failed\n"); + adminq->cq_vector = -1; + return ret; + } + + for (i = hdev->queue_count; i <= hdev->max_qid; i++) { + ret = spraid_alloc_queue(hdev, i, hdev->ioq_depth); + if (ret) + break; + } + dev_info(hdev->dev, "[%s] max_qid: %d, queue_count: %d;" + " online_queue: %d, ioq_depth: %d\n", + __func__, hdev->max_qid, hdev->queue_count, + hdev->online_queues, hdev->ioq_depth); + + return spraid_create_io_queues(hdev); +} + +static void spraid_delete_io_queues(struct spraid_dev *hdev) +{ + u16 queues = hdev->online_queues - 1; + u8 opcode = SPRAID_ADMIN_DELETE_SQ; + u16 i, pass; + + if (!pci_device_is_present(hdev->pdev)) { + dev_err(hdev->dev, + "pci_device is not present, skip disable io queues\n"); + return; + } + + if (hdev->online_queues < 2) { + dev_err(hdev->dev, "[%s] err, io queue has been delete\n", + __func__); + return; + } + + for (pass = 0; pass < 2; pass++) { + for (i = queues; i > 0; i--) + if (spraid_delete_queue(hdev, opcode, i)) + break; + + opcode = SPRAID_ADMIN_DELETE_CQ; + } +} + +static void spraid_remove_io_queues(struct spraid_dev *hdev) +{ + spraid_delete_io_queues(hdev); + spraid_free_io_queues(hdev); +} + +static void spraid_pci_disable(struct spraid_dev *hdev) +{ + struct pci_dev *pdev = hdev->pdev; + u32 i; + + for (i = 0; i < hdev->online_queues; i++) + pci_free_irq(pdev, hdev->queues[i].cq_vector, &hdev->queues[i]); + pci_free_irq_vectors(pdev); + if (pci_is_enabled(pdev)) { + pci_disable_pcie_error_reporting(pdev); + pci_disable_device(pdev); + } + hdev->online_queues = 0; +} + +static void spraid_disable_admin_queue(struct spraid_dev *hdev, bool shutdown) +{ + struct spraid_queue *adminq = &hdev->queues[0]; + u16 start, end; + + if (pci_device_is_present(hdev->pdev)) { + if (shutdown) + spraid_shutdown_ctrl(hdev); + else + spraid_disable_ctrl(hdev); + } + + if (hdev->queue_count == 0) { + dev_err(hdev->dev, "[%s] err, admin queue has been delete\n", + __func__); + return; + } + + spin_lock_irq(&adminq->cq_lock); + spraid_process_cq(adminq, &start, &end, -1); + spin_unlock_irq(&adminq->cq_lock); + + spraid_complete_cqes(adminq, start, end); + spraid_free_admin_queue(hdev); +} + +static int spraid_create_dma_pools(struct spraid_dev *hdev) +{ + int i; + char poolname[20] = { 0 }; + + hdev->prp_page_pool = dma_pool_create("prp list page", hdev->dev, + PAGE_SIZE, PAGE_SIZE, 0); + + if (!hdev->prp_page_pool) { + dev_err(hdev->dev, "create prp_page_pool failed\n"); + return -ENOMEM; + } + + for (i = 0; i < small_pool_num; i++) { + sprintf(poolname, "prp_list_256_%d", i); + hdev->prp_small_pool[i] = + dma_pool_create(poolname, hdev->dev, SMALL_POOL_SIZE, + SMALL_POOL_SIZE, 0); + + if (!hdev->prp_small_pool[i]) { + dev_err(hdev->dev, "create prp_small_pool %d failed\n", + i); + goto destroy_prp_small_pool; + } + } + + return 0; + +destroy_prp_small_pool: + while (i > 0) + dma_pool_destroy(hdev->prp_small_pool[--i]); + dma_pool_destroy(hdev->prp_page_pool); + + return -ENOMEM; +} + +static void spraid_destroy_dma_pools(struct spraid_dev *hdev) +{ + int i; + + for (i = 0; i < small_pool_num; i++) + dma_pool_destroy(hdev->prp_small_pool[i]); + dma_pool_destroy(hdev->prp_page_pool); +} + +static int spraid_get_dev_list(struct spraid_dev *hdev, + struct spraid_dev_info *devices) +{ + u32 nd = le32_to_cpu(hdev->ctrl_info->nd); + struct spraid_admin_command admin_cmd; + struct spraid_dev_list *list_buf; + dma_addr_t data_dma = 0; + u32 i, idx, hdid, ndev; + int ret = 0; + + list_buf = dma_alloc_coherent(hdev->dev, PAGE_SIZE, + &data_dma, GFP_KERNEL); + if (!list_buf) + return -ENOMEM; + + for (idx = 0; idx < nd;) { + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.get_info.opcode = SPRAID_ADMIN_GET_INFO; + admin_cmd.get_info.type = SPRAID_GET_INFO_DEV_LIST; + admin_cmd.get_info.cdw11 = cpu_to_le32(idx); + admin_cmd.common.dptr.prp1 = cpu_to_le64(data_dma); + + ret = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, + NULL, NULL, 0); + + if (ret) { + dev_err(hdev->dev, "Get device list failed, nd: %u;" + "idx: %u, ret: %d\n", + nd, idx, ret); + goto out; + } + ndev = le32_to_cpu(list_buf->dev_num); + + dev_info(hdev->dev, "ndev numbers: %u\n", ndev); + + for (i = 0; i < ndev; i++) { + hdid = le32_to_cpu(list_buf->devices[i].hdid); + dev_info(hdev->dev, "list_buf->devices[%d], hdid: %u;" + "target: %d, channel: %d, lun: %d, attr[0x%x]\n", + i, hdid, + le16_to_cpu(list_buf->devices[i].target), + list_buf->devices[i].channel, + list_buf->devices[i].lun, + list_buf->devices[i].attr); + if (hdid > nd || hdid == 0) { + dev_err(hdev->dev, "err, hdid[%d] invalid\n", + hdid); + continue; + } + memcpy(&devices[hdid - 1], &list_buf->devices[i], + sizeof(struct spraid_dev_info)); + } + idx += ndev; + + if (idx < MAX_DEV_ENTRY_PER_PAGE_4K) + break; + } + +out: + dma_free_coherent(hdev->dev, PAGE_SIZE, list_buf, data_dma); + return ret; +} + +static void spraid_send_aen(struct spraid_dev *hdev, u16 cid) +{ + struct spraid_queue *adminq = &hdev->queues[0]; + struct spraid_admin_command admin_cmd; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.common.opcode = SPRAID_ADMIN_ASYNC_EVENT; + admin_cmd.common.command_id = cid; + + spraid_submit_cmd(adminq, &admin_cmd); + dev_info(hdev->dev, "send aen, cid[%d]\n", cid); +} + +static inline void spraid_send_all_aen(struct spraid_dev *hdev) +{ + u16 i; + + for (i = 0; i < hdev->ctrl_info->aerl; i++) + spraid_send_aen(hdev, i + SPRAID_AQ_BLK_MQ_DEPTH); +} + +static int spraid_add_device(struct spraid_dev *hdev, + struct spraid_dev_info *device) +{ + struct Scsi_Host *shost = hdev->shost; + struct scsi_device *sdev; + + dev_info(hdev->dev, "add device, hdid: %u target: %d, channel: %d;" + " lun: %d, attr[0x%x]\n", + le32_to_cpu(device->hdid), le16_to_cpu(device->target), + device->channel, device->lun, device->attr); + + sdev = scsi_device_lookup(shost, device->channel, + le16_to_cpu(device->target), 0); + if (sdev) { + dev_warn(hdev->dev, "Device is already exist, channel: %d;" + " target_id: %d, lun: %d\n", + device->channel, le16_to_cpu(device->target), 0); + scsi_device_put(sdev); + return -EEXIST; + } + scsi_add_device(shost, device->channel, le16_to_cpu(device->target), 0); + return 0; +} + +static int spraid_rescan_device(struct spraid_dev *hdev, + struct spraid_dev_info *device) +{ + struct Scsi_Host *shost = hdev->shost; + struct scsi_device *sdev; + + dev_info(hdev->dev, "rescan device, hdid: %u target: %d, channel: %d;" + " lun: %d, attr[0x%x]\n", + le32_to_cpu(device->hdid), le16_to_cpu(device->target), + device->channel, device->lun, device->attr); + + sdev = scsi_device_lookup(shost, device->channel, + le16_to_cpu(device->target), 0); + if (!sdev) { + dev_warn(hdev->dev, "device is not exit rescan it, channel: %d;" + " target_id: %d, lun: %d\n", + device->channel, le16_to_cpu(device->target), 0); + return -ENODEV; + } + + scsi_rescan_device(&sdev->sdev_gendev); + scsi_device_put(sdev); + return 0; +} + +static int spraid_remove_device(struct spraid_dev *hdev, + struct spraid_dev_info *org_device) +{ + struct Scsi_Host *shost = hdev->shost; + struct scsi_device *sdev; + + dev_info(hdev->dev, "remove device, hdid: %u target: %d, channel: %d;" + " lun: %d, attr[0x%x]\n", + le32_to_cpu(org_device->hdid), le16_to_cpu(org_device->target), + org_device->channel, org_device->lun, org_device->attr); + + sdev = scsi_device_lookup(shost, org_device->channel, + le16_to_cpu(org_device->target), 0); + if (!sdev) { + dev_warn(hdev->dev, "device is not exit remove it, channel: %d;" + " target_id: %d, lun: %d\n", + org_device->channel, + le16_to_cpu(org_device->target), 0); + return -ENODEV; + } + + scsi_remove_device(sdev); + scsi_device_put(sdev); + return 0; +} + +static int spraid_dev_list_init(struct spraid_dev *hdev) +{ + u32 nd = le32_to_cpu(hdev->ctrl_info->nd); + int i, ret; + + hdev->devices = kzalloc_node(nd * sizeof(struct spraid_dev_info), + GFP_KERNEL, hdev->numa_node); + if (!hdev->devices) + return -ENOMEM; + + ret = spraid_get_dev_list(hdev, hdev->devices); + if (ret) { + dev_err(hdev->dev, + "Ignore failure of getting device list;" + " within initialization\n"); + return 0; + } + + for (i = 0; i < nd; i++) { + if (SPRAID_DEV_INFO_FLAG_VALID(hdev->devices[i].flag) && + SPRAID_DEV_INFO_ATTR_BOOT(hdev->devices[i].attr)) { + spraid_add_device(hdev, &hdev->devices[i]); + break; + } + } + return 0; +} + +static int luntarget_cmp_func(const void *l, const void *r) +{ + const struct spraid_dev_info *ln = l; + const struct spraid_dev_info *rn = r; + + if (ln->channel == rn->channel) + return le16_to_cpu(ln->target) - le16_to_cpu(rn->target); + + return ln->channel - rn->channel; +} + +static void spraid_scan_work(struct work_struct *work) +{ + struct spraid_dev *hdev = + container_of(work, struct spraid_dev, scan_work); + struct spraid_dev_info *devices, *org_devices; + struct spraid_dev_info *sortdevice; + u32 nd = le32_to_cpu(hdev->ctrl_info->nd); + u8 flag, org_flag; + int i, ret; + int count = 0; + + devices = kcalloc(nd, sizeof(struct spraid_dev_info), GFP_KERNEL); + if (!devices) + return; + + sortdevice = kcalloc(nd, sizeof(struct spraid_dev_info), GFP_KERNEL); + if (!sortdevice) + goto free_list; + + ret = spraid_get_dev_list(hdev, devices); + if (ret) + goto free_all; + org_devices = hdev->devices; + for (i = 0; i < nd; i++) { + org_flag = org_devices[i].flag; + flag = devices[i].flag; + + dev_log_dbg(hdev->dev, "i: %d, org_flag: 0x%x, flag: 0x%x\n", + i, org_flag, flag); + + if (SPRAID_DEV_INFO_FLAG_VALID(flag)) { + if (!SPRAID_DEV_INFO_FLAG_VALID(org_flag)) { + down_write(&hdev->devices_rwsem); + memcpy(&org_devices[i], &devices[i], + sizeof(struct spraid_dev_info)); + memcpy(&sortdevice[count++], &devices[i], + sizeof(struct spraid_dev_info)); + up_write(&hdev->devices_rwsem); + } else if (SPRAID_DEV_INFO_FLAG_CHANGE(flag)) { + spraid_rescan_device(hdev, &devices[i]); + } + } else { + if (SPRAID_DEV_INFO_FLAG_VALID(org_flag)) { + down_write(&hdev->devices_rwsem); + org_devices[i].flag &= 0xfe; + up_write(&hdev->devices_rwsem); + spraid_remove_device(hdev, &org_devices[i]); + } + } + } + + dev_info(hdev->dev, "scan work add device count = %d\n", count); + + sort(sortdevice, count, sizeof(sortdevice[0]), + luntarget_cmp_func, NULL); + + for (i = 0; i < count; i++) + spraid_add_device(hdev, &sortdevice[i]); + +free_all: + kfree(sortdevice); +free_list: + kfree(devices); +} + +static void spraid_timesyn_work(struct work_struct *work) +{ + struct spraid_dev *hdev = + container_of(work, struct spraid_dev, timesyn_work); + + spraid_configure_timestamp(hdev); +} + +static int spraid_init_ctrl_info(struct spraid_dev *hdev); +static void spraid_fw_act_work(struct work_struct *work) +{ + struct spraid_dev *hdev = + container_of(work, struct spraid_dev, fw_act_work); + + if (spraid_init_ctrl_info(hdev)) + dev_err(hdev->dev, "get ctrl info failed after fw act\n"); +} + +static void spraid_queue_scan(struct spraid_dev *hdev) +{ + queue_work(spraid_wq, &hdev->scan_work); +} + +static void spraid_handle_aen_notice(struct spraid_dev *hdev, u32 result) +{ + switch ((result & 0xff00) >> 8) { + case SPRAID_AEN_DEV_CHANGED: + spraid_queue_scan(hdev); + break; + case SPRAID_AEN_FW_ACT_START: + dev_info(hdev->dev, "fw activation starting\n"); + break; + case SPRAID_AEN_HOST_PROBING: + break; + default: + dev_warn(hdev->dev, "async event result %08x\n", result); + } +} + +static void spraid_handle_aen_vs(struct spraid_dev *hdev, + u32 result, u32 result1) +{ + switch ((result & 0xff00) >> 8) { + case SPRAID_AEN_TIMESYN: + queue_work(spraid_wq, &hdev->timesyn_work); + break; + case SPRAID_AEN_FW_ACT_FINISH: + dev_info(hdev->dev, "fw activation finish\n"); + queue_work(spraid_wq, &hdev->fw_act_work); + break; + case SPRAID_AEN_EVENT_MIN ... SPRAID_AEN_EVENT_MAX: + dev_info(hdev->dev, "rcv card event[%d];" + " param1[0x%x] param2[0x%x]\n", + (result & 0xff00) >> 8, result, result1); + break; + default: + dev_warn(hdev->dev, "async event result: 0x%x\n", result); + } +} + +static int spraid_alloc_resources(struct spraid_dev *hdev) +{ + int ret, nqueue; + + ret = ida_alloc(&spraid_instance_ida, GFP_KERNEL); + if (ret < 0) { + dev_err(hdev->dev, "Get instance id failed\n"); + return ret; + } + hdev->instance = ret; + + hdev->ctrl_info = kzalloc_node(sizeof(*hdev->ctrl_info), + GFP_KERNEL, hdev->numa_node); + if (!hdev->ctrl_info) { + ret = -ENOMEM; + goto release_instance; + } + + ret = spraid_create_dma_pools(hdev); + if (ret) + goto free_ctrl_info; + nqueue = num_possible_cpus() + 1; + hdev->queues = kcalloc_node(nqueue, sizeof(struct spraid_queue), + GFP_KERNEL, hdev->numa_node); + if (!hdev->queues) { + ret = -ENOMEM; + goto destroy_dma_pools; + } + + ret = spraid_alloc_admin_cmds(hdev); + if (ret) + goto free_queues; + + dev_info(hdev->dev, "[%s] queues num: %d\n", __func__, nqueue); + + return 0; + +free_queues: + kfree(hdev->queues); +destroy_dma_pools: + spraid_destroy_dma_pools(hdev); +free_ctrl_info: + kfree(hdev->ctrl_info); +release_instance: + ida_free(&spraid_instance_ida, hdev->instance); + return ret; +} + +static void spraid_free_resources(struct spraid_dev *hdev) +{ + spraid_free_admin_cmds(hdev); + kfree(hdev->queues); + spraid_destroy_dma_pools(hdev); + kfree(hdev->ctrl_info); + ida_free(&spraid_instance_ida, hdev->instance); +} + +static void spraid_bsg_unmap_data(struct spraid_dev *hdev, struct bsg_job *job) +{ + struct request *rq = blk_mq_rq_from_pdu(job); + struct spraid_iod *iod = job->dd_data; + enum dma_data_direction dma_dir = + rq_data_dir(rq) ? DMA_TO_DEVICE : DMA_FROM_DEVICE; + + if (iod->nsge) + dma_unmap_sg(hdev->dev, iod->sg, iod->nsge, dma_dir); + + spraid_free_iod_res(hdev, iod); +} + +static int spraid_bsg_map_data(struct spraid_dev *hdev, struct bsg_job *job, + struct spraid_admin_command *cmd) +{ + struct request *rq = blk_mq_rq_from_pdu(job); + struct spraid_iod *iod = job->dd_data; + enum dma_data_direction dma_dir = + rq_data_dir(rq) ? DMA_TO_DEVICE : DMA_FROM_DEVICE; + int ret = 0; + + iod->sg = job->request_payload.sg_list; + iod->nsge = job->request_payload.sg_cnt; + iod->length = job->request_payload.payload_len; + iod->use_sgl = false; + iod->npages = -1; + iod->sg_drv_mgmt = false; + + if (!iod->nsge) + goto out; + + ret = dma_map_sg_attrs(hdev->dev, iod->sg, iod->nsge, + dma_dir, DMA_ATTR_NO_WARN); + if (!ret) + goto out; + + ret = spraid_setup_prps(hdev, iod); + if (ret) + goto unmap; + + cmd->common.dptr.prp1 = cpu_to_le64(sg_dma_address(iod->sg)); + cmd->common.dptr.prp2 = cpu_to_le64(iod->first_dma); + + return 0; + +unmap: + dma_unmap_sg(hdev->dev, iod->sg, iod->nsge, dma_dir); +out: + return ret; +} + +static int spraid_get_ctrl_info(struct spraid_dev *hdev, + struct spraid_ctrl_info *ctrl_info) +{ + struct spraid_admin_command admin_cmd; + u8 *data_ptr = NULL; + dma_addr_t data_dma = 0; + int ret; + + data_ptr = dma_alloc_coherent(hdev->dev, PAGE_SIZE, + &data_dma, GFP_KERNEL); + if (!data_ptr) + return -ENOMEM; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.get_info.opcode = SPRAID_ADMIN_GET_INFO; + admin_cmd.get_info.type = SPRAID_GET_INFO_CTRL; + admin_cmd.common.dptr.prp1 = cpu_to_le64(data_dma); + + ret = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); + if (!ret) + memcpy(ctrl_info, data_ptr, sizeof(struct spraid_ctrl_info)); + + dma_free_coherent(hdev->dev, PAGE_SIZE, data_ptr, data_dma); + + return ret; +} + +static int spraid_init_ctrl_info(struct spraid_dev *hdev) +{ + int ret; + + hdev->ctrl_info->nd = cpu_to_le32(240); + hdev->ctrl_info->mdts = 8; + hdev->ctrl_info->max_cmds = cpu_to_le16(4096); + hdev->ctrl_info->max_num_sge = cpu_to_le16(128); + hdev->ctrl_info->max_channel = cpu_to_le16(4); + hdev->ctrl_info->max_tgt_id = cpu_to_le32(3239); + hdev->ctrl_info->max_lun = cpu_to_le16(2); + + ret = spraid_get_ctrl_info(hdev, hdev->ctrl_info); + if (ret) + dev_err(hdev->dev, "get controller info failed: %d\n", ret); + + dev_info(hdev->dev, "[%s]nd = %d\n", __func__, hdev->ctrl_info->nd); + dev_info(hdev->dev, "[%s]max_cmd = %d\n", + __func__, hdev->ctrl_info->max_cmds); + dev_info(hdev->dev, "[%s]max_channel = %d\n", + __func__, hdev->ctrl_info->max_channel); + dev_info(hdev->dev, "[%s]max_tgt_id = %d\n", + __func__, hdev->ctrl_info->max_tgt_id); + dev_info(hdev->dev, "[%s]max_lun = %d\n", + __func__, hdev->ctrl_info->max_lun); + dev_info(hdev->dev, "[%s]max_num_sge = %d\n", + __func__, hdev->ctrl_info->max_num_sge); + dev_info(hdev->dev, "[%s]lun_num_boot = %d\n", + __func__, hdev->ctrl_info->lun_num_in_boot); + dev_info(hdev->dev, "[%s]mdts = %d\n", __func__, hdev->ctrl_info->mdts); + dev_info(hdev->dev, "[%s]acl = %d\n", __func__, hdev->ctrl_info->acl); + dev_info(hdev->dev, "[%s]aer1 = %d\n", __func__, hdev->ctrl_info->aerl); + dev_info(hdev->dev, "[%s]card_type = %d\n", + __func__, hdev->ctrl_info->card_type); + dev_info(hdev->dev, "[%s]rtd3e = %d\n", + __func__, hdev->ctrl_info->rtd3e); + dev_info(hdev->dev, "[%s]sn = %s\n", __func__, hdev->ctrl_info->sn); + dev_info(hdev->dev, "[%s]fr = %s\n", __func__, hdev->ctrl_info->fr); + + if (!hdev->ctrl_info->aerl) + hdev->ctrl_info->aerl = 1; + if (hdev->ctrl_info->aerl > SPRAID_NR_AEN_COMMANDS) + hdev->ctrl_info->aerl = SPRAID_NR_AEN_COMMANDS; + + return 0; +} + +#define SPRAID_MAX_ADMIN_PAYLOAD_SIZE BIT(16) +static int spraid_alloc_iod_ext_mem_pool(struct spraid_dev *hdev) +{ + u16 max_sge = le16_to_cpu(hdev->ctrl_info->max_num_sge); + size_t alloc_size; + + alloc_size = spraid_iod_ext_size(hdev, SPRAID_MAX_ADMIN_PAYLOAD_SIZE, + max_sge, true, false); + if (alloc_size > PAGE_SIZE) + dev_warn(hdev->dev, "It is unreasonable ;" + " sg allocation more than one page\n"); + hdev->iod_mempool = mempool_create_node(1, mempool_kmalloc, + mempool_kfree, + (void *)alloc_size, GFP_KERNEL, + hdev->numa_node); + if (!hdev->iod_mempool) { + dev_err(hdev->dev, "Create iod extension memory pool failed\n"); + return -ENOMEM; + } + + return 0; +} + +static void spraid_free_iod_ext_mem_pool(struct spraid_dev *hdev) +{ + mempool_destroy(hdev->iod_mempool); +} + +static int spraid_user_admin_cmd(struct spraid_dev *hdev, struct bsg_job *job) +{ + struct spraid_bsg_request *bsg_req = job->request; + struct spraid_passthru_common_cmd *cmd = &(bsg_req->admcmd); + struct spraid_admin_command admin_cmd; + u32 timeout = msecs_to_jiffies(cmd->timeout_ms); + u32 result[2] = {0}; + int status; + + if (hdev->state >= SPRAID_RESETTING) { + dev_err(hdev->dev, "[%s] err, host state:[%d] is not right\n", + __func__, hdev->state); + return -EBUSY; + } + + dev_info(hdev->dev, "[%s] opcode[0x%x] subopcode[0x%x] init\n", + __func__, cmd->opcode, cmd->info_0.subopcode); + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.common.opcode = cmd->opcode; + admin_cmd.common.flags = cmd->flags; + admin_cmd.common.hdid = cpu_to_le32(cmd->nsid); + admin_cmd.common.cdw2[0] = cpu_to_le32(cmd->cdw2); + admin_cmd.common.cdw2[1] = cpu_to_le32(cmd->cdw3); + admin_cmd.common.cdw10 = cpu_to_le32(cmd->cdw10); + admin_cmd.common.cdw11 = cpu_to_le32(cmd->cdw11); + admin_cmd.common.cdw12 = cpu_to_le32(cmd->cdw12); + admin_cmd.common.cdw13 = cpu_to_le32(cmd->cdw13); + admin_cmd.common.cdw14 = cpu_to_le32(cmd->cdw14); + admin_cmd.common.cdw15 = cpu_to_le32(cmd->cdw15); + + status = spraid_bsg_map_data(hdev, job, &admin_cmd); + if (status) { + dev_err(hdev->dev, "[%s] err, map data failed\n", __func__); + return status; + } + + status = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, &result[0], + &result[1], timeout); + if (status >= 0) { + job->reply_len = sizeof(result); + memcpy(job->reply, result, sizeof(result)); + } + + dev_info(hdev->dev, "[%s] opcode[0x%x] subopcode[0x%x];" + " status[0x%x] result0[0x%x] result1[0x%x]\n", + __func__, cmd->opcode, cmd->info_0.subopcode, + status, result[0], result[1]); + + spraid_bsg_unmap_data(hdev, job); + + return status; +} + +static int spraid_alloc_ioq_ptcmds(struct spraid_dev *hdev) +{ + int i; + int ptnum = SPRAID_NR_IOQ_PTCMDS; + + INIT_LIST_HEAD(&hdev->ioq_pt_list); + spin_lock_init(&hdev->ioq_pt_lock); + + hdev->ioq_ptcmds = kcalloc_node(ptnum, sizeof(struct spraid_cmd), + GFP_KERNEL, hdev->numa_node); + + if (!hdev->ioq_ptcmds) { + dev_err(hdev->dev, "Alloc ioq_ptcmds failed\n"); + return -ENOMEM; + } + + for (i = 0; i < ptnum; i++) { + hdev->ioq_ptcmds[i].qid = i / SPRAID_PTCMDS_PERQ + 1; + hdev->ioq_ptcmds[i].cid = i % SPRAID_PTCMDS_PERQ + + SPRAID_IO_BLK_MQ_DEPTH; + list_add_tail(&(hdev->ioq_ptcmds[i].list), &hdev->ioq_pt_list); + } + + dev_info(hdev->dev, "Alloc ioq_ptcmds success, ptnum[%d]\n", ptnum); + + return 0; +} + +static void spraid_free_ioq_ptcmds(struct spraid_dev *hdev) +{ + kfree(hdev->ioq_ptcmds); + hdev->ioq_ptcmds = NULL; + + INIT_LIST_HEAD(&hdev->ioq_pt_list); +} + +static int spraid_submit_ioq_sync_cmd(struct spraid_dev *hdev, + struct spraid_ioq_command *cmd, + u32 *result, u32 *reslen, u32 timeout) +{ + int ret; + dma_addr_t sense_dma; + struct spraid_queue *ioq; + void *sense_addr = NULL; + struct spraid_cmd *pt_cmd = spraid_get_cmd(hdev, SPRAID_CMD_IOPT); + + if (!pt_cmd) { + dev_err(hdev->dev, "err, get ioq cmd failed\n"); + return -EFAULT; + } + + timeout = timeout ? timeout : ADMIN_TIMEOUT; + + init_completion(&pt_cmd->cmd_done); + + ioq = &hdev->queues[pt_cmd->qid]; + ret = pt_cmd->cid * SCSI_SENSE_BUFFERSIZE; + sense_addr = ioq->sense + ret; + sense_dma = ioq->sense_dma_addr + ret; + + cmd->common.sense_addr = cpu_to_le64(sense_dma); + cmd->common.sense_len = cpu_to_le16(SCSI_SENSE_BUFFERSIZE); + cmd->common.command_id = pt_cmd->cid; + + spraid_submit_cmd(ioq, cmd); + + if (!wait_for_completion_timeout(&pt_cmd->cmd_done, timeout)) { + dev_err(hdev->dev, "[%s] cid[%d] qid[%d] timeout;" + " opcode[0x%x] subopcode[0x%x]\n", + __func__, pt_cmd->cid, pt_cmd->qid, cmd->common.opcode, + (le32_to_cpu(cmd->common.cdw3[0]) & 0xffff)); + WRITE_ONCE(pt_cmd->state, SPRAID_CMD_TIMEOUT); + spraid_put_cmd(hdev, pt_cmd, SPRAID_CMD_IOPT); + return -EINVAL; + } + + if (result && reslen) { + if ((pt_cmd->status & 0x17f) == 0x101) { + memcpy(result, sense_addr, SCSI_SENSE_BUFFERSIZE); + *reslen = SCSI_SENSE_BUFFERSIZE; + } + } + + spraid_put_cmd(hdev, pt_cmd, SPRAID_CMD_IOPT); + + return pt_cmd->status; +} + +static int spraid_user_ioq_cmd(struct spraid_dev *hdev, struct bsg_job *job) +{ + struct spraid_bsg_request *bsg_req = + (struct spraid_bsg_request *)(job->request); + struct spraid_ioq_passthru_cmd *cmd = &(bsg_req->ioqcmd); + struct spraid_ioq_command ioq_cmd; + int status = 0; + u32 timeout = msecs_to_jiffies(cmd->timeout_ms); + + if (cmd->data_len > PAGE_SIZE) { + dev_err(hdev->dev, "[%s] data len bigger than 4k\n", __func__); + return -EFAULT; + } + + if (hdev->state != SPRAID_LIVE) { + dev_err(hdev->dev, "[%s] err, host state:[%d] is not live\n", + __func__, hdev->state); + return -EBUSY; + } + + dev_info(hdev->dev, "[%s] opcode[0x%x] subopcode[0x%x] init;" + " datalen[%d]\n", + __func__, cmd->opcode, cmd->info_1.subopcode, cmd->data_len); + + memset(&ioq_cmd, 0, sizeof(ioq_cmd)); + ioq_cmd.common.opcode = cmd->opcode; + ioq_cmd.common.flags = cmd->flags; + ioq_cmd.common.hdid = cpu_to_le32(cmd->nsid); + ioq_cmd.common.sense_len = cpu_to_le16(cmd->info_0.res_sense_len); + ioq_cmd.common.cdb_len = cmd->info_0.cdb_len; + ioq_cmd.common.rsvd2 = cmd->info_0.rsvd0; + ioq_cmd.common.cdw3[0] = cpu_to_le32(cmd->cdw3); + ioq_cmd.common.cdw3[1] = cpu_to_le32(cmd->cdw4); + ioq_cmd.common.cdw3[2] = cpu_to_le32(cmd->cdw5); + + ioq_cmd.common.cdw10[0] = cpu_to_le32(cmd->cdw10); + ioq_cmd.common.cdw10[1] = cpu_to_le32(cmd->cdw11); + ioq_cmd.common.cdw10[2] = cpu_to_le32(cmd->cdw12); + ioq_cmd.common.cdw10[3] = cpu_to_le32(cmd->cdw13); + ioq_cmd.common.cdw10[4] = cpu_to_le32(cmd->cdw14); + ioq_cmd.common.cdw10[5] = cpu_to_le32(cmd->data_len); + + memcpy(ioq_cmd.common.cdb, &cmd->cdw16, cmd->info_0.cdb_len); + + ioq_cmd.common.cdw26[0] = cpu_to_le32(cmd->cdw26[0]); + ioq_cmd.common.cdw26[1] = cpu_to_le32(cmd->cdw26[1]); + ioq_cmd.common.cdw26[2] = cpu_to_le32(cmd->cdw26[2]); + ioq_cmd.common.cdw26[3] = cpu_to_le32(cmd->cdw26[3]); + + status = spraid_bsg_map_data(hdev, job, + (struct spraid_admin_command *)&ioq_cmd); + if (status) { + dev_err(hdev->dev, "[%s] err, map data failed\n", __func__); + return status; + } + + status = spraid_submit_ioq_sync_cmd(hdev, &ioq_cmd, job->reply, + &job->reply_len, timeout); + + dev_info(hdev->dev, "[%s] opcode[0x%x] subopcode[0x%x], status[0x%x];" + " reply_len[%d]\n", + __func__, cmd->opcode, cmd->info_1.subopcode, + status, job->reply_len); + + spraid_bsg_unmap_data(hdev, job); + + return status; +} + +static bool spraid_check_scmd_completed(struct scsi_cmnd *scmd) +{ + struct spraid_dev *hdev = shost_priv(scmd->device->host); + struct spraid_iod *iod = scsi_cmd_priv(scmd); + struct spraid_queue *spraidq; + u16 hwq, cid; + + spraid_get_tag_from_scmd(scmd, &hwq, &cid); + spraidq = &hdev->queues[hwq]; + if (READ_ONCE(iod->state) == SPRAID_CMD_COMPLETE + || spraid_poll_cq(spraidq, cid)) { + dev_warn(hdev->dev, "cid[%d] qid[%d] has been completed\n", + cid, spraidq->qid); + return true; + } + return false; +} + +static enum blk_eh_timer_return spraid_scmd_timeout(struct scsi_cmnd *scmd) +{ + struct spraid_iod *iod = scsi_cmd_priv(scmd); + unsigned int timeout = scmd->device->request_queue->rq_timeout; + + if (spraid_check_scmd_completed(scmd)) + goto out; + + if (time_after(jiffies, scmd->jiffies_at_alloc + timeout)) { + if (cmpxchg(&iod->state, + SPRAID_CMD_IN_FLIGHT, + SPRAID_CMD_TIMEOUT) == SPRAID_CMD_IN_FLIGHT) { + return BLK_EH_DONE; + } + } +out: + return BLK_EH_RESET_TIMER; +} + +/* send abort command by admin queue temporary */ +static int spraid_send_abort_cmd(struct spraid_dev *hdev, + u32 hdid, u16 qid, u16 cid) +{ + struct spraid_admin_command admin_cmd; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.abort.opcode = SPRAID_ADMIN_ABORT_CMD; + admin_cmd.abort.hdid = cpu_to_le32(hdid); + admin_cmd.abort.sqid = cpu_to_le16(qid); + admin_cmd.abort.cid = cpu_to_le16(cid); + + return spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); +} + +/* send reset command by admin quueue temporary */ +static int spraid_send_reset_cmd(struct spraid_dev *hdev, int type, u32 hdid) +{ + struct spraid_admin_command admin_cmd; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.reset.opcode = SPRAID_ADMIN_RESET; + admin_cmd.reset.hdid = cpu_to_le32(hdid); + admin_cmd.reset.type = type; + + return spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); +} + +static bool spraid_change_host_state(struct spraid_dev *hdev, + enum spraid_state newstate) +{ + unsigned long flags; + enum spraid_state oldstate; + bool change = false; + + spin_lock_irqsave(&hdev->state_lock, flags); + + oldstate = hdev->state; + switch (newstate) { + case SPRAID_LIVE: + switch (oldstate) { + case SPRAID_NEW: + case SPRAID_RESETTING: + change = true; + break; + default: + break; + } + break; + case SPRAID_RESETTING: + switch (oldstate) { + case SPRAID_LIVE: + change = true; + break; + default: + break; + } + break; + case SPRAID_DELETING: + if (oldstate != SPRAID_DELETING) + change = true; + break; + case SPRAID_DEAD: + switch (oldstate) { + case SPRAID_NEW: + case SPRAID_LIVE: + case SPRAID_RESETTING: + change = true; + break; + default: + break; + } + break; + default: + break; + } + if (change) + hdev->state = newstate; + spin_unlock_irqrestore(&hdev->state_lock, flags); + + dev_info(hdev->dev, "[%s][%d]->[%d], change[%d]\n", + __func__, oldstate, newstate, change); + + return change; +} + +static void spraid_back_fault_cqe(struct spraid_queue *ioq, + struct spraid_completion *cqe) +{ + struct spraid_dev *hdev = ioq->hdev; + struct blk_mq_tags *tags; + struct scsi_cmnd *scmd; + struct spraid_iod *iod; + struct request *req; + + tags = hdev->shost->tag_set.tags[ioq->qid - 1]; + req = blk_mq_tag_to_rq(tags, cqe->cmd_id); + if (unlikely(!req || !blk_mq_request_started(req))) + return; + + scmd = blk_mq_rq_to_pdu(req); + iod = scsi_cmd_priv(scmd); + + set_host_byte(scmd, DID_NO_CONNECT); + if (iod->nsge) + scsi_dma_unmap(scmd); + spraid_free_iod_res(hdev, iod); + scmd->scsi_done(scmd); + dev_warn(hdev->dev, "Back fault CQE, cid[%d] qid[%d]\n", + cqe->cmd_id, ioq->qid); +} + +static void spraid_back_all_io(struct spraid_dev *hdev) +{ + int i, j; + struct spraid_queue *ioq; + struct spraid_completion cqe = { 0 }; + + scsi_block_requests(hdev->shost); + + for (i = 1; i <= hdev->shost->nr_hw_queues; i++) { + ioq = &hdev->queues[i]; + for (j = 0; j < hdev->shost->can_queue; j++) { + cqe.cmd_id = j; + spraid_back_fault_cqe(ioq, &cqe); + } + } + + scsi_unblock_requests(hdev->shost); +} + +static void spraid_dev_disable(struct spraid_dev *hdev, bool shutdown) +{ + struct spraid_queue *adminq = &hdev->queues[0]; + u16 start, end; + unsigned long timeout = jiffies + 600 * HZ; + + if (pci_device_is_present(hdev->pdev)) { + if (shutdown) + spraid_shutdown_ctrl(hdev); + else + spraid_disable_ctrl(hdev); + } + + while (!time_after(jiffies, timeout)) { + if (!pci_device_is_present(hdev->pdev)) { + dev_info(hdev->dev, "[%s] pci_device not present;" + " skip wait\n", __func__); + break; + } + if (!spraid_wait_ready(hdev, hdev->cap, false)) { + dev_info(hdev->dev, + "[%s] wait ready success after reset\n", + __func__); + break; + } + dev_info(hdev->dev, "[%s] waiting csts_rdy ready\n", __func__); + } + + if (hdev->queue_count == 0) { + dev_err(hdev->dev, "[%s] warn, queue has been delete\n", + __func__); + return; + } + + spin_lock_irq(&adminq->cq_lock); + spraid_process_cq(adminq, &start, &end, -1); + spin_unlock_irq(&adminq->cq_lock); + spraid_complete_cqes(adminq, start, end); + + spraid_pci_disable(hdev); + + spraid_back_all_io(hdev); +} + +static void spraid_reset_work(struct work_struct *work) +{ + int ret; + struct spraid_dev *hdev = + container_of(work, struct spraid_dev, reset_work); + + if (hdev->state != SPRAID_RESETTING) { + dev_err(hdev->dev, "[%s] err, host is not reset state\n", + __func__); + return; + } + + dev_info(hdev->dev, "[%s] enter host reset\n", __func__); + + if (hdev->ctrl_config & SPRAID_CC_ENABLE) { + dev_info(hdev->dev, "[%s] start dev_disable\n", __func__); + spraid_dev_disable(hdev, false); + } + + ret = spraid_pci_enable(hdev); + if (ret) + goto out; + + ret = spraid_setup_admin_queue(hdev); + if (ret) + goto pci_disable; + + ret = spraid_setup_io_queues(hdev); + if (ret || hdev->online_queues <= hdev->shost->nr_hw_queues) + goto pci_disable; + + spraid_change_host_state(hdev, SPRAID_LIVE); + + spraid_send_all_aen(hdev); + + return; + +pci_disable: + spraid_pci_disable(hdev); +out: + spraid_change_host_state(hdev, SPRAID_DEAD); + dev_err(hdev->dev, "[%s] err, host reset failed\n", __func__); +} + +static int spraid_reset_work_sync(struct spraid_dev *hdev) +{ + if (!spraid_change_host_state(hdev, SPRAID_RESETTING)) { + dev_info(hdev->dev, "[%s] can't change to reset state\n", + __func__); + return -EBUSY; + } + + if (!queue_work(spraid_wq, &hdev->reset_work)) { + dev_err(hdev->dev, "[%s] err, host is already in reset state\n", + __func__); + return -EBUSY; + } + + flush_work(&hdev->reset_work); + if (hdev->state != SPRAID_LIVE) + return -ENODEV; + + return 0; +} + +static int spraid_wait_abnl_cmd_done(struct spraid_iod *iod) +{ + u16 times = 0; + + do { + if (READ_ONCE(iod->state) == SPRAID_CMD_TMO_COMPLETE) + break; + msleep(500); + times++; + } while (times <= SPRAID_WAIT_ABNL_CMD_TIMEOUT); + + /* wait command completion timeout after abort/reset success */ + if (times >= SPRAID_WAIT_ABNL_CMD_TIMEOUT) + return -ETIMEDOUT; + + return 0; +} + +static int spraid_abort_handler(struct scsi_cmnd *scmd) +{ + struct spraid_dev *hdev = shost_priv(scmd->device->host); + struct spraid_iod *iod = scsi_cmd_priv(scmd); + struct spraid_sdev_hostdata *hostdata; + u16 hwq, cid; + int ret; + + scsi_print_command(scmd); + + if (hdev->state != SPRAID_LIVE || !spraid_wait_abnl_cmd_done(iod) || + spraid_check_scmd_completed(scmd)) + return SUCCESS; + + hostdata = scmd->device->hostdata; + spraid_get_tag_from_scmd(scmd, &hwq, &cid); + + dev_warn(hdev->dev, "cid[%d] qid[%d] timeout, aborting\n", cid, hwq); + ret = spraid_send_abort_cmd(hdev, hostdata->hdid, hwq, cid); + if (ret != ADMIN_ERR_TIMEOUT) { + ret = spraid_wait_abnl_cmd_done(iod); + if (ret) { + dev_warn(hdev->dev, "cid[%d] qid[%d] abort failed;" + " not found\n", cid, hwq); + return FAILED; + } + dev_warn(hdev->dev, "cid[%d] qid[%d] abort succ\n", cid, hwq); + return SUCCESS; + } + dev_warn(hdev->dev, "cid[%d] qid[%d] abort failed, timeout\n", + cid, hwq); + return FAILED; +} + +static int spraid_tgt_reset_handler(struct scsi_cmnd *scmd) +{ + struct spraid_dev *hdev = shost_priv(scmd->device->host); + struct spraid_iod *iod = scsi_cmd_priv(scmd); + struct spraid_sdev_hostdata *hostdata; + u16 hwq, cid; + int ret; + + scsi_print_command(scmd); + + if (hdev->state != SPRAID_LIVE || !spraid_wait_abnl_cmd_done(iod) || + spraid_check_scmd_completed(scmd)) + return SUCCESS; + + hostdata = scmd->device->hostdata; + spraid_get_tag_from_scmd(scmd, &hwq, &cid); + + dev_warn(hdev->dev, "cid[%d] qid[%d] timeout, target reset\n", + cid, hwq); + ret = spraid_send_reset_cmd(hdev, SPRAID_RESET_TARGET, hostdata->hdid); + if (ret == 0) { + ret = spraid_wait_abnl_cmd_done(iod); + if (ret) { + dev_warn(hdev->dev, + "cid[%d] qid[%d]target reset failed;" + " not found\n", cid, hwq); + return FAILED; + } + + dev_warn(hdev->dev, "cid[%d] qid[%d] target reset success\n", + cid, hwq); + return SUCCESS; + } + + dev_warn(hdev->dev, "cid[%d] qid[%d] ret[%d] target reset failed\n", + cid, hwq, ret); + return FAILED; +} + +static int spraid_bus_reset_handler(struct scsi_cmnd *scmd) +{ + struct spraid_dev *hdev = shost_priv(scmd->device->host); + struct spraid_iod *iod = scsi_cmd_priv(scmd); + struct spraid_sdev_hostdata *hostdata; + u16 hwq, cid; + int ret; + + scsi_print_command(scmd); + + if (hdev->state != SPRAID_LIVE || !spraid_wait_abnl_cmd_done(iod) || + spraid_check_scmd_completed(scmd)) + return SUCCESS; + + hostdata = scmd->device->hostdata; + spraid_get_tag_from_scmd(scmd, &hwq, &cid); + + dev_warn(hdev->dev, "cid[%d] qid[%d] timeout, bus reset\n", cid, hwq); + ret = spraid_send_reset_cmd(hdev, SPRAID_RESET_BUS, hostdata->hdid); + if (ret == 0) { + ret = spraid_wait_abnl_cmd_done(iod); + if (ret) { + dev_warn(hdev->dev, + "cid[%d] qid[%d] bus reset failed;" + " not found\n", cid, hwq); + return FAILED; + } + + dev_warn(hdev->dev, "cid[%d] qid[%d] bus reset succ\n", + cid, hwq); + return SUCCESS; + } + + dev_warn(hdev->dev, "cid[%d] qid[%d] ret[%d] bus reset failed\n", + cid, hwq, ret); + return FAILED; +} + +static int spraid_shost_reset_handler(struct scsi_cmnd *scmd) +{ + u16 hwq, cid; + struct spraid_dev *hdev = shost_priv(scmd->device->host); + + scsi_print_command(scmd); + if (hdev->state != SPRAID_LIVE || spraid_check_scmd_completed(scmd)) + return SUCCESS; + + spraid_get_tag_from_scmd(scmd, &hwq, &cid); + dev_warn(hdev->dev, "cid[%d] qid[%d] host reset\n", cid, hwq); + + if (spraid_reset_work_sync(hdev)) { + dev_warn(hdev->dev, "cid[%d] qid[%d] host reset failed\n", + cid, hwq); + return FAILED; + } + + dev_warn(hdev->dev, "cid[%d] qid[%d] host reset success\n", cid, hwq); + + return SUCCESS; +} + +static pci_ers_result_t spraid_pci_error_detected(struct pci_dev *pdev, + pci_channel_state_t state) +{ + struct spraid_dev *hdev = pci_get_drvdata(pdev); + + dev_info(hdev->dev, "enter pci error detect, state:%d\n", state); + + switch (state) { + case pci_channel_io_normal: + dev_warn(hdev->dev, "channel is normal, do nothing\n"); + + return PCI_ERS_RESULT_CAN_RECOVER; + case pci_channel_io_frozen: + dev_warn(hdev->dev, + "channel io frozen, need reset controller\n"); + + scsi_block_requests(hdev->shost); + + spraid_change_host_state(hdev, SPRAID_RESETTING); + + return PCI_ERS_RESULT_NEED_RESET; + case pci_channel_io_perm_failure: + dev_warn(hdev->dev, "channel io failure, request disconnect\n"); + + return PCI_ERS_RESULT_DISCONNECT; + } + + return PCI_ERS_RESULT_NEED_RESET; +} + +static pci_ers_result_t spraid_pci_slot_reset(struct pci_dev *pdev) +{ + struct spraid_dev *hdev = pci_get_drvdata(pdev); + + dev_info(hdev->dev, "restart after slot reset\n"); + + pci_restore_state(pdev); + + if (!queue_work(spraid_wq, &hdev->reset_work)) { + dev_err(hdev->dev, "[%s] err, the device is resetting state\n", + __func__); + return PCI_ERS_RESULT_NONE; + } + + flush_work(&hdev->reset_work); + + scsi_unblock_requests(hdev->shost); + + return PCI_ERS_RESULT_RECOVERED; +} + +static void spraid_reset_done(struct pci_dev *pdev) +{ + struct spraid_dev *hdev = pci_get_drvdata(pdev); + + dev_info(hdev->dev, "enter spraid reset done\n"); +} + +static ssize_t csts_pp_show(struct device *cdev, + struct device_attribute *attr, char *buf) +{ + struct Scsi_Host *shost = class_to_shost(cdev); + struct spraid_dev *hdev = shost_priv(shost); + int ret = -1; + + if (pci_device_is_present(hdev->pdev)) { + ret = (readl(hdev->bar + SPRAID_REG_CSTS) + & SPRAID_CSTS_PP_MASK); + ret >>= SPRAID_CSTS_PP_SHIFT; + } + + return snprintf(buf, PAGE_SIZE, "%d\n", ret); +} + +static ssize_t csts_shst_show(struct device *cdev, + struct device_attribute *attr, char *buf) +{ + struct Scsi_Host *shost = class_to_shost(cdev); + struct spraid_dev *hdev = shost_priv(shost); + int ret = -1; + + if (pci_device_is_present(hdev->pdev)) { + ret = (readl(hdev->bar + SPRAID_REG_CSTS) + & SPRAID_CSTS_SHST_MASK); + ret >>= SPRAID_CSTS_SHST_SHIFT; + } + + return snprintf(buf, PAGE_SIZE, "%d\n", ret); +} + +static ssize_t csts_cfs_show(struct device *cdev, + struct device_attribute *attr, char *buf) +{ + struct Scsi_Host *shost = class_to_shost(cdev); + struct spraid_dev *hdev = shost_priv(shost); + int ret = -1; + + if (pci_device_is_present(hdev->pdev)) { + ret = (readl(hdev->bar + SPRAID_REG_CSTS) + & SPRAID_CSTS_CFS_MASK); + ret >>= SPRAID_CSTS_CFS_SHIFT; + } + + return snprintf(buf, PAGE_SIZE, "%d\n", ret); +} + +static ssize_t csts_rdy_show(struct device *cdev, + struct device_attribute *attr, char *buf) +{ + struct Scsi_Host *shost = class_to_shost(cdev); + struct spraid_dev *hdev = shost_priv(shost); + int ret = -1; + + if (pci_device_is_present(hdev->pdev)) + ret = (readl(hdev->bar + SPRAID_REG_CSTS) & SPRAID_CSTS_RDY); + + return snprintf(buf, PAGE_SIZE, "%d\n", ret); +} + +static ssize_t fw_version_show(struct device *cdev, + struct device_attribute *attr, char *buf) +{ + struct Scsi_Host *shost = class_to_shost(cdev); + struct spraid_dev *hdev = shost_priv(shost); + + return snprintf(buf, PAGE_SIZE, "%s\n", hdev->ctrl_info->fr); +} + +static DEVICE_ATTR_RO(csts_pp); +static DEVICE_ATTR_RO(csts_shst); +static DEVICE_ATTR_RO(csts_cfs); +static DEVICE_ATTR_RO(csts_rdy); +static DEVICE_ATTR_RO(fw_version); + +static struct device_attribute *spraid_host_attrs[] = { + &dev_attr_csts_pp, + &dev_attr_csts_shst, + &dev_attr_csts_cfs, + &dev_attr_csts_rdy, + &dev_attr_fw_version, + NULL, +}; + +static int spraid_get_vd_info(struct spraid_dev *hdev, + struct spraid_vd_info *vd_info, u16 vid) +{ + struct spraid_admin_command admin_cmd; + u8 *data_ptr = NULL; + dma_addr_t data_dma = 0; + int ret; + + data_ptr = dma_alloc_coherent(hdev->dev, PAGE_SIZE, + &data_dma, GFP_KERNEL); + if (!data_ptr) + return -ENOMEM; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.usr_cmd.opcode = USR_CMD_READ; + admin_cmd.usr_cmd.info_0.subopcode = cpu_to_le16(USR_CMD_VDINFO); + admin_cmd.usr_cmd.info_1.data_len = cpu_to_le16(USR_CMD_RDLEN); + admin_cmd.usr_cmd.info_1.param_len = cpu_to_le16(VDINFO_PARAM_LEN); + admin_cmd.usr_cmd.cdw10 = cpu_to_le32(vid); + admin_cmd.common.dptr.prp1 = cpu_to_le64(data_dma); + + ret = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); + if (!ret) + memcpy(vd_info, data_ptr, sizeof(struct spraid_vd_info)); + + dma_free_coherent(hdev->dev, PAGE_SIZE, data_ptr, data_dma); + + return ret; +} + +static int spraid_get_bgtask(struct spraid_dev *hdev, + struct spraid_bgtask *bgtask) +{ + struct spraid_admin_command admin_cmd; + u8 *data_ptr = NULL; + dma_addr_t data_dma = 0; + int ret; + + data_ptr = dma_alloc_coherent(hdev->dev, PAGE_SIZE, + &data_dma, GFP_KERNEL); + if (!data_ptr) + return -ENOMEM; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.usr_cmd.opcode = USR_CMD_READ; + admin_cmd.usr_cmd.info_0.subopcode = cpu_to_le16(USR_CMD_BGTASK); + admin_cmd.usr_cmd.info_1.data_len = cpu_to_le16(USR_CMD_RDLEN); + admin_cmd.common.dptr.prp1 = cpu_to_le64(data_dma); + + ret = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); + if (!ret) + memcpy(bgtask, data_ptr, sizeof(struct spraid_bgtask)); + + dma_free_coherent(hdev->dev, PAGE_SIZE, data_ptr, data_dma); + + return ret; +} + +static ssize_t raid_level_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct scsi_device *sdev; + struct spraid_dev *hdev; + struct spraid_vd_info *vd_info; + struct spraid_sdev_hostdata *hostdata; + int ret; + + sdev = to_scsi_device(dev); + hdev = shost_priv(sdev->host); + hostdata = sdev->hostdata; + + vd_info = kmalloc(sizeof(*vd_info), GFP_KERNEL); + if (!vd_info || !SPRAID_DEV_INFO_ATTR_VD(hostdata->attr)) + return snprintf(buf, PAGE_SIZE, "NA\n"); + + ret = spraid_get_vd_info(hdev, vd_info, sdev->id); + if (ret) + vd_info->rg_level = ARRAY_SIZE(raid_levels) - 1; + + ret = (vd_info->rg_level < ARRAY_SIZE(raid_levels)) ? + vd_info->rg_level : (ARRAY_SIZE(raid_levels) - 1); + + kfree(vd_info); + + return snprintf(buf, PAGE_SIZE, "RAID-%s\n", raid_levels[ret]); +} + +static ssize_t raid_state_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct scsi_device *sdev; + struct spraid_dev *hdev; + struct spraid_vd_info *vd_info; + struct spraid_sdev_hostdata *hostdata; + int ret; + + sdev = to_scsi_device(dev); + hdev = shost_priv(sdev->host); + hostdata = sdev->hostdata; + + vd_info = kmalloc(sizeof(*vd_info), GFP_KERNEL); + if (!vd_info || !SPRAID_DEV_INFO_ATTR_VD(hostdata->attr)) + return snprintf(buf, PAGE_SIZE, "NA\n"); + + ret = spraid_get_vd_info(hdev, vd_info, sdev->id); + if (ret) { + vd_info->vd_status = 0; + vd_info->rg_id = 0xff; + } + + ret = (vd_info->vd_status < ARRAY_SIZE(raid_states)) ? + vd_info->vd_status : 0; + + kfree(vd_info); + + return snprintf(buf, PAGE_SIZE, "%s\n", raid_states[ret]); +} + +static ssize_t raid_resync_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct scsi_device *sdev; + struct spraid_dev *hdev; + struct spraid_vd_info *vd_info; + struct spraid_bgtask *bgtask; + struct spraid_sdev_hostdata *hostdata; + u8 rg_id, i, progress = 0; + int ret; + + sdev = to_scsi_device(dev); + hdev = shost_priv(sdev->host); + hostdata = sdev->hostdata; + + vd_info = kmalloc(sizeof(*vd_info), GFP_KERNEL); + if (!vd_info || !SPRAID_DEV_INFO_ATTR_VD(hostdata->attr)) + return snprintf(buf, PAGE_SIZE, "NA\n"); + + ret = spraid_get_vd_info(hdev, vd_info, sdev->id); + if (ret) + goto out; + + rg_id = vd_info->rg_id; + + bgtask = (struct spraid_bgtask *)vd_info; + ret = spraid_get_bgtask(hdev, bgtask); + if (ret) + goto out; + for (i = 0; i < bgtask->task_num; i++) { + if ((bgtask->bgtask[i].type == BGTASK_TYPE_REBUILD) && + (le16_to_cpu(bgtask->bgtask[i].vd_id) == rg_id)) + progress = bgtask->bgtask[i].progress; + } + +out: + kfree(vd_info); + return snprintf(buf, PAGE_SIZE, "%d\n", progress); +} + +static DEVICE_ATTR_RO(raid_level); +static DEVICE_ATTR_RO(raid_state); +static DEVICE_ATTR_RO(raid_resync); + +static struct device_attribute *spraid_dev_attrs[] = { + &dev_attr_raid_level, + &dev_attr_raid_state, + &dev_attr_raid_resync, + NULL, +}; + +static struct pci_error_handlers spraid_err_handler = { + .error_detected = spraid_pci_error_detected, + .slot_reset = spraid_pci_slot_reset, + .reset_done = spraid_reset_done, +}; + +static int spraid_sysfs_host_reset(struct Scsi_Host *shost, int reset_type) +{ + int ret; + struct spraid_dev *hdev = shost_priv(shost); + + dev_info(hdev->dev, "[%s] start sysfs host reset cmd\n", __func__); + ret = spraid_reset_work_sync(hdev); + dev_info(hdev->dev, "[%s] stop sysfs host reset cmd[%d]\n", + __func__, ret); + + return ret; +} + +static struct scsi_host_template spraid_driver_template = { + .module = THIS_MODULE, + .name = "Ramaxel Logic spraid driver", + .proc_name = "spraid", + .queuecommand = spraid_queue_command, + .slave_alloc = spraid_slave_alloc, + .slave_destroy = spraid_slave_destroy, + .slave_configure = spraid_slave_configure, + .eh_timed_out = spraid_scmd_timeout, + .eh_abort_handler = spraid_abort_handler, + .eh_target_reset_handler = spraid_tgt_reset_handler, + .eh_bus_reset_handler = spraid_bus_reset_handler, + .eh_host_reset_handler = spraid_shost_reset_handler, + .change_queue_depth = scsi_change_queue_depth, + .this_id = -1, + .shost_attrs = spraid_host_attrs, + .sdev_attrs = spraid_dev_attrs, + .host_reset = spraid_sysfs_host_reset, +}; + +static void spraid_shutdown(struct pci_dev *pdev) +{ + struct spraid_dev *hdev = pci_get_drvdata(pdev); + + spraid_remove_io_queues(hdev); + spraid_disable_admin_queue(hdev, true); +} + +/* bsg dispatch user command */ +static int spraid_bsg_host_dispatch(struct bsg_job *job) +{ + struct Scsi_Host *shost = dev_to_shost(job->dev); + struct spraid_dev *hdev = shost_priv(shost); + struct request *rq = blk_mq_rq_from_pdu(job); + struct spraid_bsg_request *bsg_req = job->request; + int ret = 0; + + dev_info(hdev->dev, "[%s] msgcode[%d], msglen[%d], timeout[%d];" + " req_nsge[%d], req_len[%d]\n", + __func__, bsg_req->msgcode, job->request_len, + rq->timeout, job->request_payload.sg_cnt, + job->request_payload.payload_len); + + job->reply_len = 0; + + switch (bsg_req->msgcode) { + case SPRAID_BSG_ADM: + ret = spraid_user_admin_cmd(hdev, job); + break; + case SPRAID_BSG_IOQ: + ret = spraid_user_ioq_cmd(hdev, job); + break; + default: + dev_info(hdev->dev, "[%s] unsupport msgcode[%d]\n", + __func__, bsg_req->msgcode); + break; + } + + if (ret > 0) + ret = ret | (ret << 8); + + bsg_job_done(job, ret, 0); + return 0; +} + +static inline void spraid_remove_bsg(struct spraid_dev *hdev) +{ + if (hdev->bsg_queue) { + bsg_unregister_queue(hdev->bsg_queue); + blk_cleanup_queue(hdev->bsg_queue); + } +} +static int spraid_probe(struct pci_dev *pdev, const struct pci_device_id *id) +{ + struct spraid_dev *hdev; + struct Scsi_Host *shost; + int node, ret; + char bsg_name[15]; + + shost = scsi_host_alloc(&spraid_driver_template, sizeof(*hdev)); + if (!shost) { + dev_err(&pdev->dev, "Failed to allocate scsi host\n"); + return -ENOMEM; + } + hdev = shost_priv(shost); + hdev->pdev = pdev; + hdev->dev = get_device(&pdev->dev); + + node = dev_to_node(hdev->dev); + if (node == NUMA_NO_NODE) { + node = first_memory_node; + set_dev_node(hdev->dev, node); + } + hdev->numa_node = node; + hdev->shost = shost; + pci_set_drvdata(pdev, hdev); + + ret = spraid_dev_map(hdev); + if (ret) + goto put_dev; + + init_rwsem(&hdev->devices_rwsem); + INIT_WORK(&hdev->scan_work, spraid_scan_work); + INIT_WORK(&hdev->timesyn_work, spraid_timesyn_work); + INIT_WORK(&hdev->reset_work, spraid_reset_work); + INIT_WORK(&hdev->fw_act_work, spraid_fw_act_work); + spin_lock_init(&hdev->state_lock); + + ret = spraid_alloc_resources(hdev); + if (ret) + goto dev_unmap; + + ret = spraid_pci_enable(hdev); + if (ret) + goto resources_free; + + ret = spraid_setup_admin_queue(hdev); + if (ret) + goto pci_disable; + + ret = spraid_init_ctrl_info(hdev); + if (ret) + goto disable_admin_q; + + ret = spraid_alloc_iod_ext_mem_pool(hdev); + if (ret) + goto disable_admin_q; + + ret = spraid_setup_io_queues(hdev); + if (ret) + goto free_iod_mempool; + + spraid_shost_init(hdev); + + ret = scsi_add_host(hdev->shost, hdev->dev); + if (ret) { + dev_err(hdev->dev, "Add shost to system failed, ret: %d\n", + ret); + goto remove_io_queues; + } + + snprintf(bsg_name, sizeof(bsg_name), "spraid%d", shost->host_no); + hdev->bsg_queue = bsg_setup_queue(&shost->shost_gendev, bsg_name, + spraid_bsg_host_dispatch, + spraid_cmd_size(hdev, true, false)); + if (IS_ERR(hdev->bsg_queue)) { + dev_err(hdev->dev, "err, setup bsg failed\n"); + hdev->bsg_queue = NULL; + goto remove_io_queues; + } + + if (hdev->online_queues == SPRAID_ADMIN_QUEUE_NUM) { + dev_warn(hdev->dev, "warn only admin queue can be used\n"); + return 0; + } + + hdev->state = SPRAID_LIVE; + + spraid_send_all_aen(hdev); + + ret = spraid_dev_list_init(hdev); + if (ret) + goto remove_bsg; + + ret = spraid_configure_timestamp(hdev); + if (ret) + dev_warn(hdev->dev, "init set timestamp failed\n"); + + ret = spraid_alloc_ioq_ptcmds(hdev); + if (ret) + goto remove_bsg; + + scsi_scan_host(hdev->shost); + + return 0; + +remove_bsg: + spraid_remove_bsg(hdev); +remove_io_queues: + spraid_remove_io_queues(hdev); +free_iod_mempool: + spraid_free_iod_ext_mem_pool(hdev); +disable_admin_q: + spraid_disable_admin_queue(hdev, false); +pci_disable: + spraid_pci_disable(hdev); +resources_free: + spraid_free_resources(hdev); +dev_unmap: + spraid_dev_unmap(hdev); +put_dev: + put_device(hdev->dev); + scsi_host_put(shost); + + return -ENODEV; +} + +static void spraid_remove(struct pci_dev *pdev) +{ + struct spraid_dev *hdev = pci_get_drvdata(pdev); + struct Scsi_Host *shost = hdev->shost; + + dev_info(hdev->dev, "enter spraid remove\n"); + + spraid_change_host_state(hdev, SPRAID_DELETING); + flush_work(&hdev->reset_work); + + if (!pci_device_is_present(pdev)) + spraid_back_all_io(hdev); + + spraid_remove_bsg(hdev); + scsi_remove_host(shost); + spraid_free_ioq_ptcmds(hdev); + kfree(hdev->devices); + spraid_remove_io_queues(hdev); + spraid_free_iod_ext_mem_pool(hdev); + spraid_disable_admin_queue(hdev, false); + spraid_pci_disable(hdev); + spraid_free_resources(hdev); + spraid_dev_unmap(hdev); + put_device(hdev->dev); + scsi_host_put(shost); + + dev_info(hdev->dev, "exit spraid remove\n"); +} + +static const struct pci_device_id spraid_id_table[] = { + { PCI_DEVICE(PCI_VENDOR_ID_RAMAXEL_LOGIC, + SPRAID_SERVER_DEVICE_HBA_DID) }, + { PCI_DEVICE(PCI_VENDOR_ID_RAMAXEL_LOGIC, + SPRAID_SERVER_DEVICE_RAID_DID) }, + { 0, } +}; +MODULE_DEVICE_TABLE(pci, spraid_id_table); + +static struct pci_driver spraid_driver = { + .name = "spraid", + .id_table = spraid_id_table, + .probe = spraid_probe, + .remove = spraid_remove, + .shutdown = spraid_shutdown, + .err_handler = &spraid_err_handler, +}; + +static int __init spraid_init(void) +{ + int ret; + + spraid_wq = alloc_workqueue("spraid-wq", WQ_UNBOUND | WQ_MEM_RECLAIM | + WQ_SYSFS, 0); + if (!spraid_wq) + return -ENOMEM; + + spraid_class = class_create(THIS_MODULE, "spraid"); + if (IS_ERR(spraid_class)) { + ret = PTR_ERR(spraid_class); + goto destroy_wq; + } + + ret = pci_register_driver(&spraid_driver); + if (ret < 0) + goto destroy_class; + + return 0; + +destroy_class: + class_destroy(spraid_class); +destroy_wq: + destroy_workqueue(spraid_wq); + + return ret; +} + +static void __exit spraid_exit(void) +{ + pci_unregister_driver(&spraid_driver); + class_destroy(spraid_class); + destroy_workqueue(spraid_wq); + ida_destroy(&spraid_instance_ida); +} + +MODULE_AUTHOR("songyl(a)ramaxel.com"); +MODULE_DESCRIPTION("Ramaxel Memory Technology SPraid Driver"); +MODULE_LICENSE("GPL"); +MODULE_VERSION(SPRAID_DRV_VERSION); +module_init(spraid_init); +module_exit(spraid_exit); -- 2.27.0

1 0

[PATCH openEuler-1.0-LTS 1/2] blk-mq: fix abnormal free in single queue process
by Yang Yingliang 20 Dec '21

20 Dec '21

From: Zhang Wensheng <zhangwensheng5(a)huawei.com> hulk inclusion category: bugfix bugzilla: 185922, https://gitee.com/openeuler/kernel/issues/I4NDPF CVE: NA -------------------------------- fix the problem introduced by commit 80086651acbd ("blk: Fix lock inversion between ioc lock and bfqd lock"), which lead to blk_queue_bio using blk_mq_free_request to free abnormally. fix the problem using __blk_put_request to replace it. Fixes: 80086651acbdb ("blk: Fix lock inversion between ioc lock and bfqd lock") Signed-off-by: Zhang Wensheng <zhangwensheng5(a)huawei.com> Reviewed-by: Laibin Qiu <qiulaibin(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- block/blk-mq.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/blk-mq.h b/block/blk-mq.h index bb8aabbc5c579..b3540d62c541e 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -228,7 +228,7 @@ static inline void blk_mq_free_requests(struct list_head *list) struct request *rq = list_entry_rq(list->next); list_del_init(&rq->queuelist); - blk_mq_free_request(rq); + __blk_put_request(rq->q, rq); } } -- 2.25.1

1 1

[PATCH openEuler-1.0-LTS] scsi: hisi_sas: Add support for sata disk I/O errors report to libsas
by Yang Yingliang 20 Dec '21

20 Dec '21

From: Xingui Yang <yangxingui(a)huawei.com> driver inclusion category: feature bugzilla: NA CVE: NA --------------------------- If the response frame has been written back to the memory and carries the disk error and status when sata I/O completion abnormally, then set task stat to SAS_PROTO_RESPONSE and let libsas to handle it. Signed-off-by: Xingui Yang <yangxingui(a)huawei.com> Reviewed-by: Kangfenglong <kangfenglong(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c index 4508c4a2f02fc..3c662fa5f6c0c 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c @@ -470,6 +470,9 @@ struct hisi_sas_err_record_v3 { #define RX_DATA_LEN_UNDERFLOW_OFF 6 #define RX_DATA_LEN_UNDERFLOW_MSK (1 << RX_DATA_LEN_UNDERFLOW_OFF) +#define RX_FIS_STATUS_ERR_OFF 0 +#define RX_FIS_STATUS_ERR_MSK (1 << RX_FIS_STATUS_ERR_OFF) + #define HISI_SAS_COMMAND_ENTRIES_V3_HW 4096 #define HISI_SAS_MSI_COUNT_V3_HW 32 @@ -2241,17 +2244,20 @@ slot_err_v3_hw(struct hisi_hba *hisi_hba, struct sas_task *task, hisi_sas_status_buf_addr_mem(slot); u32 dma_rx_err_type = record->dma_rx_err_type; u32 trans_tx_fail_type = record->trans_tx_fail_type; + u16 sipc_rx_err_type = le16_to_cpu(record->sipc_rx_err_type); + u32 dw0 = le32_to_cpu(complete_hdr->dw0); + u32 dw3 = le32_to_cpu(complete_hdr->dw3); switch (task->task_proto) { case SAS_PROTOCOL_SSP: if (dma_rx_err_type & RX_DATA_LEN_UNDERFLOW_MSK) { ts->residual = trans_tx_fail_type; ts->stat = SAS_DATA_UNDERRUN; - if ((!(complete_hdr->dw0 & CMPLT_HDR_RSPNS_GOOD_MSK)) && - (complete_hdr->dw0 & CMPLT_HDR_RSPNS_XFRD_MSK)) { + if (!(dw0 & CMPLT_HDR_RSPNS_GOOD_MSK) && + (dw0 & CMPLT_HDR_RSPNS_XFRD_MSK)) { hisi_sas_set_sense_data(task, slot); } - } else if (complete_hdr->dw3 & CMPLT_HDR_IO_IN_TARGET_MSK) { + } else if (dw3 & CMPLT_HDR_IO_IN_TARGET_MSK) { ts->stat = SAS_QUEUE_FULL; slot->abort = 1; } else { @@ -2262,7 +2268,10 @@ slot_err_v3_hw(struct hisi_hba *hisi_hba, struct sas_task *task, case SAS_PROTOCOL_SATA: case SAS_PROTOCOL_STP: case SAS_PROTOCOL_SATA | SAS_PROTOCOL_STP: - if (complete_hdr->dw3 & CMPLT_HDR_IO_IN_TARGET_MSK) { + if ((dw0 & CMPLT_HDR_RSPNS_XFRD_MSK) && + (sipc_rx_err_type & RX_FIS_STATUS_ERR_MSK)) { + ts->stat = SAS_PROTO_RESPONSE; + } else if (dw3 & CMPLT_HDR_IO_IN_TARGET_MSK) { ts->stat = SAS_PHY_DOWN; slot->abort = 1; } else if (dma_rx_err_type & RX_DATA_LEN_UNDERFLOW_MSK) { -- 2.25.1

1 0

[PATCH OLK5.10 v2 ] scsi:spraid: use bsg module to replace with ioctrl
by Yanling Song 20 Dec '21

20 Dec '21

Ramaxel inclusion category: features bugzilla: https://gitee.com/openeuler/kernel/issues/I4JXCG CVE: NA Changes from v1: 1. Add more debug infor. 2. Remove some unnecessary module parameters. 3. Report disks by the order of channel/target id. 4. Add host_reset handler. 5. Use get_unaligned_be24. Signed-off-by: Yanling Song <songyl(a)ramaxel.com> Reviewed-by: Jiang Yu<yujiang(a)ramaxel.com> --- drivers/scsi/spraid/Kconfig | 6 +- drivers/scsi/spraid/spraid.h | 142 ++- drivers/scsi/spraid/spraid_main.c | 1571 +++++++++++++++-------------- 3 files changed, 938 insertions(+), 781 deletions(-) diff --git a/drivers/scsi/spraid/Kconfig b/drivers/scsi/spraid/Kconfig index 83962efaab07..bfbba3db8db0 100644 --- a/drivers/scsi/spraid/Kconfig +++ b/drivers/scsi/spraid/Kconfig @@ -5,7 +5,9 @@ config RAMAXEL_SPRAID tristate "Ramaxel spraid Adapter" depends on PCI && SCSI + select BLK_DEV_BSGLIB depends on ARM64 || X86_64 - default m help - This driver supports Ramaxel spraid driver. + This driver supports Ramaxel SPRxxx serial + raid controller, which has PCIE Gen4 interface + with host and supports SAS/SATA Hdd/ssd. diff --git a/drivers/scsi/spraid/spraid.h b/drivers/scsi/spraid/spraid.h index da46d8e1b4b6..983d7af2faa8 100644 --- a/drivers/scsi/spraid/spraid.h +++ b/drivers/scsi/spraid/spraid.h @@ -1,4 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2021 Ramaxel Memory Technology, Ltd */ #ifndef __SPRAID_H_ #define __SPRAID_H_ @@ -24,7 +25,7 @@ #define SENSE_SIZE(depth) ((depth) * SCSI_SENSE_BUFFERSIZE) #define SPRAID_AQ_DEPTH 128 -#define SPRAID_NR_AEN_COMMANDS 1 +#define SPRAID_NR_AEN_COMMANDS 16 #define SPRAID_AQ_BLK_MQ_DEPTH (SPRAID_AQ_DEPTH - SPRAID_NR_AEN_COMMANDS) #define SPRAID_AQ_MQ_TAG_DEPTH (SPRAID_AQ_BLK_MQ_DEPTH - 1) @@ -44,7 +45,7 @@ #define SMALL_POOL_SIZE 256 #define MAX_SMALL_POOL_NUM 16 -#define MAX_CMD_PER_DEV 32 +#define MAX_CMD_PER_DEV 64 #define MAX_CDB_LEN 32 #define SPRAID_UP_TO_MULTY4(x) (((x) + 4) & (~0x03)) @@ -53,7 +54,7 @@ #define PCI_VENDOR_ID_RAMAXEL_LOGIC 0x1E81 -#define SPRAID_SERVER_DEVICE_HAB_DID 0x2100 +#define SPRAID_SERVER_DEVICE_HBA_DID 0x2100 #define SPRAID_SERVER_DEVICE_RAID_DID 0x2200 #define IO_6_DEFAULT_TX_LEN 256 @@ -142,11 +143,15 @@ enum { enum { SPRAID_AEN_DEV_CHANGED = 0x00, + SPRAID_AEN_FW_ACT_START = 0x01, SPRAID_AEN_HOST_PROBING = 0x10, }; enum { - SPRAID_AEN_TIMESYN = 0x07 + SPRAID_AEN_TIMESYN = 0x00, + SPRAID_AEN_FW_ACT_FINISH = 0x02, + SPRAID_AEN_EVENT_MIN = 0x80, + SPRAID_AEN_EVENT_MAX = 0xff, }; enum { @@ -175,6 +180,16 @@ enum spraid_state { SPRAID_DEAD, }; +enum { + SPRAID_CARD_HBA, + SPRAID_CARD_RAID, +}; + +enum spraid_cmd_type { + SPRAID_CMD_ADM, + SPRAID_CMD_IOPT, +}; + struct spraid_completion { __le32 result; union { @@ -217,8 +232,6 @@ struct spraid_dev { struct dma_pool *prp_page_pool; struct dma_pool *prp_small_pool[MAX_SMALL_POOL_NUM]; mempool_t *iod_mempool; - struct blk_mq_tag_set admin_tagset; - struct request_queue *admin_q; void __iomem *bar; u32 max_qid; u32 num_vecs; @@ -232,23 +245,27 @@ struct spraid_dev { u32 ctrl_config; u32 online_queues; u64 cap; - struct device ctrl_device; - struct cdev cdev; int instance; struct spraid_ctrl_info *ctrl_info; struct spraid_dev_info *devices; - struct spraid_ioq_ptcmd *ioq_ptcmds; + struct spraid_cmd *adm_cmds; + struct list_head adm_cmd_list; + spinlock_t adm_cmd_lock; + + struct spraid_cmd *ioq_ptcmds; struct list_head ioq_pt_list; spinlock_t ioq_pt_lock; - struct work_struct aen_work; struct work_struct scan_work; struct work_struct timesyn_work; struct work_struct reset_work; + struct work_struct fw_act_work; enum spraid_state state; spinlock_t state_lock; + + struct request_queue *bsg_queue; }; struct spraid_sgl_desc { @@ -347,6 +364,35 @@ struct spraid_get_info { __u32 rsvd12[4]; }; +struct spraid_usr_cmd { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + union { + struct { + __le16 subopcode; + __le16 rsvd1; + } info_0; + __le32 cdw2; + }; + union { + struct { + __le16 data_len; + __le16 param_len; + } info_1; + __le32 cdw3; + }; + __u64 metadata; + union spraid_data_ptr dptr; + __le32 cdw10; + __le32 cdw11; + __le32 cdw12; + __le32 cdw13; + __le32 cdw14; + __le32 cdw15; +}; + enum { SPRAID_CMD_FLAG_SGL_METABUF = (1 << 6), SPRAID_CMD_FLAG_SGL_METASEG = (1 << 7), @@ -393,6 +439,7 @@ struct spraid_admin_command { struct spraid_get_info get_info; struct spraid_abort_cmd abort; struct spraid_reset_cmd reset; + struct spraid_usr_cmd usr_cmd; }; }; @@ -456,9 +503,6 @@ struct spraid_ioq_command { }; }; -#define SPRAID_IOCTL_RESET_CMD _IOWR('N', 0x80, struct spraid_passthru_common_cmd) -#define SPRAID_IOCTL_ADMIN_CMD _IOWR('N', 0x41, struct spraid_passthru_common_cmd) - struct spraid_passthru_common_cmd { __u8 opcode; __u8 flags; @@ -494,8 +538,6 @@ struct spraid_passthru_common_cmd { __u32 result1; }; -#define SPRAID_IOCTL_IOQ_CMD _IOWR('N', 0x42, struct spraid_ioq_passthru_cmd) - struct spraid_ioq_passthru_cmd { __u8 opcode; __u8 flags; @@ -560,7 +602,21 @@ struct spraid_ioq_passthru_cmd { __u32 result1; }; -struct spraid_ioq_ptcmd { +struct spraid_bsg_request { + u32 msgcode; + u32 control; + union { + struct spraid_passthru_common_cmd admcmd; + struct spraid_ioq_passthru_cmd ioqcmd; + }; +}; + +enum { + SPRAID_BSG_ADM, + SPRAID_BSG_IOQ, +}; + +struct spraid_cmd { int qid; int cid; u32 result0; @@ -572,14 +628,6 @@ struct spraid_ioq_ptcmd { struct list_head list; }; -struct spraid_admin_request { - struct spraid_admin_command *cmd; - u32 result0; - u32 result1; - u16 flags; - u16 status; -}; - struct spraid_queue { struct spraid_dev *hdev; spinlock_t sq_lock; /* spinlock for lock handling */ @@ -607,7 +655,6 @@ struct spraid_queue { }; struct spraid_iod { - struct spraid_admin_request req; struct spraid_queue *spraidq; enum spraid_cmd_state state; int npages; @@ -623,13 +670,51 @@ struct spraid_iod { }; #define SPRAID_DEV_INFO_ATTR_BOOT(attr) ((attr) & 0x01) -#define SPRAID_DEV_INFO_ATTR_HDD(attr) ((attr) & 0x02) +#define SPRAID_DEV_INFO_ATTR_VD(attr) (((attr) & 0x02) == 0x0) #define SPRAID_DEV_INFO_ATTR_PT(attr) (((attr) & 0x22) == 0x02) #define SPRAID_DEV_INFO_ATTR_RAWDISK(attr) ((attr) & 0x20) #define SPRAID_DEV_INFO_FLAG_VALID(flag) ((flag) & 0x01) #define SPRAID_DEV_INFO_FLAG_CHANGE(flag) ((flag) & 0x02) +#define BGTASK_TYPE_REBUILD 4 +#define USR_CMD_READ 0xc2 +#define USR_CMD_RDLEN 0x1000 +#define USR_CMD_VDINFO 0x704 +#define USR_CMD_BGTASK 0x504 +#define VDINFO_PARAM_LEN 0x04 + +struct spraid_vd_info { + __u8 name[32]; + __le16 id; + __u8 rg_id; + __u8 rg_level; + __u8 sg_num; + __u8 sg_disk_num; + __u8 vd_status; + __u8 vd_type; + __u8 rsvd1[4056]; +}; + +#define MAX_REALTIME_BGTASK_NUM 32 + +struct bgtask_info { + __u8 type; + __u8 progress; + __u8 rate; + __u8 rsvd0; + __le16 vd_id; + __le16 time_left; + __u8 rsvd1[4]; +}; + +struct spraid_bgtask { + __u8 sw; + __u8 task_num; + __u8 rsvd[6]; + struct bgtask_info bgtask[MAX_REALTIME_BGTASK_NUM]; +}; + struct spraid_dev_info { __le32 hdid; __le16 target; @@ -649,6 +734,11 @@ struct spraid_dev_list { struct spraid_sdev_hostdata { u32 hdid; + u16 max_io_kb; + u8 attr; + u8 flag; + u8 rg_id; + u8 rsvd[3]; }; #endif diff --git a/drivers/scsi/spraid/spraid_main.c b/drivers/scsi/spraid/spraid_main.c index a0a75ecb0027..976b7ded336a 100644 --- a/drivers/scsi/spraid/spraid_main.c +++ b/drivers/scsi/spraid/spraid_main.c @@ -1,8 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 -/* - * Linux spraid device driver - * Copyright(c) 2021 Ramaxel Memory Technology, Ltd - */ +/* Copyright(c) 2021 Ramaxel Memory Technology, Ltd */ + +/* Ramaxel Raid SPXXX Series Linux Driver */ + #define pr_fmt(fmt) "spraid: " fmt #include <linux/sched/signal.h> @@ -23,6 +23,9 @@ #include <linux/debugfs.h> #include <linux/io-64-nonatomic-lo-hi.h> #include <linux/blkdev.h> +#include <linux/bsg-lib.h> +#include <asm/unaligned.h> +#include <linux/sort.h> #include <scsi/scsi.h> #include <scsi/scsi_cmnd.h> @@ -31,28 +34,17 @@ #include <scsi/scsi_transport.h> #include <scsi/scsi_dbg.h> + #include "spraid.h" static u32 admin_tmout = 60; module_param(admin_tmout, uint, 0644); MODULE_PARM_DESC(admin_tmout, "admin commands timeout (seconds)"); -static u32 scmd_tmout_pt = 30; -module_param(scmd_tmout_pt, uint, 0644); -MODULE_PARM_DESC(scmd_tmout_pt, "scsi commands timeout for passthrough(seconds)"); - static u32 scmd_tmout_nonpt = 180; module_param(scmd_tmout_nonpt, uint, 0644); MODULE_PARM_DESC(scmd_tmout_nonpt, "scsi commands timeout for rawdisk&raid(seconds)"); -static u32 wait_abl_tmout = 3; -module_param(wait_abl_tmout, uint, 0644); -MODULE_PARM_DESC(wait_abl_tmout, "wait abnormal io timeout(seconds)"); - -static bool use_sgl_force; -module_param(use_sgl_force, bool, 0644); -MODULE_PARM_DESC(use_sgl_force, "force IO use sgl format, default false"); - static int ioq_depth_set(const char *val, const struct kernel_param *kp); static const struct kernel_param_ops ioq_depth_ops = { .set = ioq_depth_set, @@ -106,16 +98,20 @@ static const struct kernel_param_ops small_pool_num_ops = { .get = param_get_byte, }; +/* It was found that the spindlock of a single pool conflicts + * a lot with multiple CPUs.So multiple pools are introduced + * to reduce the conflictions. + */ static unsigned char small_pool_num = 4; module_param_cb(small_pool_num, &small_pool_num_ops, &small_pool_num, 0644); MODULE_PARM_DESC(small_pool_num, "set prp small pool num, default 4, MAX 16"); static void spraid_free_queue(struct spraid_queue *spraidq); static void spraid_handle_aen_notice(struct spraid_dev *hdev, u32 result); -static void spraid_handle_aen_vs(struct spraid_dev *hdev, u32 result); +static void spraid_handle_aen_vs(struct spraid_dev *hdev, u32 result, u32 result1); static DEFINE_IDA(spraid_instance_ida); -static dev_t spraid_chr_devt; + static struct class *spraid_class; #define SPRAID_CAP_TIMEOUT_UNIT_MS (HZ / 2) @@ -133,7 +129,7 @@ static struct workqueue_struct *spraid_wq; #define ADMIN_TIMEOUT (admin_tmout * HZ) #define ADMIN_ERR_TIMEOUT 32757 -#define SPRAID_WAIT_ABNL_CMD_TIMEOUT (wait_abl_tmout * 2) +#define SPRAID_WAIT_ABNL_CMD_TIMEOUT (3 * 2) #define SPRAID_DMA_MSK_BIT_MAX 64 @@ -147,6 +143,13 @@ enum FW_STAT_CODE { FW_STAT_NEED_RETRY }; +static const char * const raid_levels[] = {"0", "1", "5", "6", "10", "50", "60", "NA"}; + +static const char * const raid_states[] = { + "NA", "NORMAL", "FAULT", "DEGRADE", "NOT_FORMATTED", "FORMATTING", "SANITIZING", + "INITIALIZING", "INITIALIZE_FAIL", "DELETING", "DELETE_FAIL", "WRITE_PROTECT" +}; + static int ioq_depth_set(const char *val, const struct kernel_param *kp) { int n = 0; @@ -263,12 +266,6 @@ static int spraid_pci_enable(struct spraid_dev *hdev) return ret; } -static inline -struct spraid_admin_request *spraid_admin_req(struct request *req) -{ - return blk_mq_rq_to_pdu(req); -} - static int spraid_npages_prp(u32 size, struct spraid_dev *hdev) { u32 nprps = DIV_ROUND_UP(size + hdev->page_size, hdev->page_size); @@ -419,7 +416,7 @@ static void spraid_submit_cmd(struct spraid_queue *spraidq, const void *cmd) writel(spraidq->sq_tail, spraidq->q_db); spin_unlock_irqrestore(&spraidq->sq_lock, flags); - dev_log_dbg(spraidq->hdev->dev, "cid[%d], qid[%d], opcode[0x%x], flags[0x%x], hdid[%u]\n", + dev_log_dbg(spraidq->hdev->dev, "cid[%d] qid[%d], opcode[0x%x], flags[0x%x], hdid[%u]\n", acd->command_id, spraidq->qid, acd->opcode, acd->flags, le32_to_cpu(acd->hdid)); } @@ -605,18 +602,15 @@ static void spraid_setup_rw_cmd(struct spraid_dev *hdev, if (scmd->cmd_len == 6) { datalength = (u32)(scmd->cmnd[4] == 0 ? IO_6_DEFAULT_TX_LEN : scmd->cmnd[4]); - start_lba_lo = ((u32)scmd->cmnd[1] << 16) | - ((u32)scmd->cmnd[2] << 8) | (u32)scmd->cmnd[3]; + start_lba_lo = (u32)get_unaligned_be24(&scmd->cmnd[1]); start_lba_lo &= 0x1FFFFF; } /* 10-byte READ(0x28) or WRITE(0x2A) cdb */ else if (scmd->cmd_len == 10) { - datalength = (u32)scmd->cmnd[8] | ((u32)scmd->cmnd[7] << 8); - start_lba_lo = ((u32)scmd->cmnd[2] << 24) | - ((u32)scmd->cmnd[3] << 16) | - ((u32)scmd->cmnd[4] << 8) | (u32)scmd->cmnd[5]; + datalength = (u32)get_unaligned_be16(&scmd->cmnd[7]); + start_lba_lo = get_unaligned_be32(&scmd->cmnd[2]); if (scmd->cmnd[1] & FUA_MASK) control |= SPRAID_RW_FUA; @@ -624,42 +618,26 @@ static void spraid_setup_rw_cmd(struct spraid_dev *hdev, /* 12-byte READ(0xA8) or WRITE(0xAA) cdb */ else if (scmd->cmd_len == 12) { - datalength = ((u32)scmd->cmnd[6] << 24) | - ((u32)scmd->cmnd[7] << 16) | - ((u32)scmd->cmnd[8] << 8) | (u32)scmd->cmnd[9]; - start_lba_lo = ((u32)scmd->cmnd[2] << 24) | - ((u32)scmd->cmnd[3] << 16) | - ((u32)scmd->cmnd[4] << 8) | (u32)scmd->cmnd[5]; + datalength = get_unaligned_be32(&scmd->cmnd[6]); + start_lba_lo = get_unaligned_be32(&scmd->cmnd[2]); if (scmd->cmnd[1] & FUA_MASK) control |= SPRAID_RW_FUA; } /* 16-byte READ(0x88) or WRITE(0x8A) cdb */ else if (scmd->cmd_len == 16) { - datalength = ((u32)scmd->cmnd[10] << 24) | - ((u32)scmd->cmnd[11] << 16) | - ((u32)scmd->cmnd[12] << 8) | (u32)scmd->cmnd[13]; - start_lba_lo = ((u32)scmd->cmnd[6] << 24) | - ((u32)scmd->cmnd[7] << 16) | - ((u32)scmd->cmnd[8] << 8) | (u32)scmd->cmnd[9]; - start_lba_hi = ((u32)scmd->cmnd[2] << 24) | - ((u32)scmd->cmnd[3] << 16) | - ((u32)scmd->cmnd[4] << 8) | (u32)scmd->cmnd[5]; + datalength = get_unaligned_be32(&scmd->cmnd[10]); + start_lba_lo = get_unaligned_be32(&scmd->cmnd[6]); + start_lba_hi = get_unaligned_be32(&scmd->cmnd[2]); if (scmd->cmnd[1] & FUA_MASK) control |= SPRAID_RW_FUA; } /* 32-byte READ(0x88) or WRITE(0x8A) cdb */ else if (scmd->cmd_len == 32) { - datalength = ((u32)scmd->cmnd[28] << 24) | - ((u32)scmd->cmnd[29] << 16) | - ((u32)scmd->cmnd[30] << 8) | (u32)scmd->cmnd[31]; - start_lba_lo = ((u32)scmd->cmnd[16] << 24) | - ((u32)scmd->cmnd[17] << 16) | - ((u32)scmd->cmnd[18] << 8) | (u32)scmd->cmnd[19]; - start_lba_hi = ((u32)scmd->cmnd[12] << 24) | - ((u32)scmd->cmnd[13] << 16) | - ((u32)scmd->cmnd[14] << 8) | (u32)scmd->cmnd[15]; + datalength = get_unaligned_be32(&scmd->cmnd[28]); + start_lba_lo = get_unaligned_be32(&scmd->cmnd[16]); + start_lba_hi = get_unaligned_be32(&scmd->cmnd[12]); if (scmd->cmnd[10] & FUA_MASK) control |= SPRAID_RW_FUA; @@ -814,7 +792,7 @@ static void spraid_map_status(struct spraid_iod *iod, struct scsi_cmnd *scmd, if (scmd->result & SAM_STAT_CHECK_CONDITION) { memset(scmd->sense_buffer, 0, SCSI_SENSE_BUFFERSIZE); memcpy(scmd->sense_buffer, iod->sense, SCSI_SENSE_BUFFERSIZE); - set_driver_byte(scmd, DRIVER_SENSE); + scmd->result = (scmd->result & 0x00ffffff) | (DRIVER_SENSE << 24); } break; case FW_STAT_ABORTED: @@ -850,14 +828,13 @@ static int spraid_queue_command(struct Scsi_Host *shost, struct scsi_cmnd *scmd) int ret; if (unlikely(!scmd)) { - dev_err(hdev->dev, "err, scmd is null, return 0\n"); + dev_err(hdev->dev, "err, scmd is null\n"); return 0; } if (unlikely(hdev->state != SPRAID_LIVE)) { set_host_byte(scmd, DID_NO_CONNECT); scmd->scsi_done(scmd); - dev_err(hdev->dev, "[%s] err, hdev state is not live\n", __func__); return 0; } @@ -894,7 +871,7 @@ static int spraid_queue_command(struct Scsi_Host *shost, struct scsi_cmnd *scmd) WRITE_ONCE(iod->state, SPRAID_CMD_IN_FLIGHT); spraid_submit_cmd(ioq, &ioq_cmd); elapsed = jiffies - scmd->jiffies_at_alloc; - dev_log_dbg(hdev->dev, "cid[%d], qid[%d] submit IO cost %3ld.%3ld seconds\n", + dev_log_dbg(hdev->dev, "cid[%d] qid[%d] submit IO cost %3ld.%3ld seconds\n", cid, hwq, elapsed / HZ, elapsed % HZ); return 0; @@ -945,6 +922,10 @@ static int spraid_slave_alloc(struct scsi_device *sdev) scan_host: hostdata->hdid = le32_to_cpu(hdev->devices[idx].hdid); + hostdata->max_io_kb = le16_to_cpu(hdev->devices[idx].max_io_kb); + hostdata->attr = hdev->devices[idx].attr; + hostdata->flag = hdev->devices[idx].flag; + hostdata->rg_id = 0xff; sdev->hostdata = hostdata; up_read(&hdev->devices_rwsem); return 0; @@ -964,13 +945,13 @@ static int spraid_slave_configure(struct scsi_device *sdev) struct spraid_sdev_hostdata *hostdata = sdev->hostdata; u32 max_sec = sdev->host->max_sectors; - if (!hostdata) { + if (hostdata) { idx = hostdata->hdid - 1; if (sdev->channel == hdev->devices[idx].channel && sdev->id == le16_to_cpu(hdev->devices[idx].target) && sdev->lun < hdev->devices[idx].lun) { if (SPRAID_DEV_INFO_ATTR_PT(hdev->devices[idx].attr)) - timeout = scmd_tmout_pt * HZ; + timeout = 30 * HZ; else timeout = scmd_tmout_nonpt * HZ; max_sec = le16_to_cpu(hdev->devices[idx].max_io_kb) << 1; @@ -991,7 +972,6 @@ static int spraid_slave_configure(struct scsi_device *sdev) if ((max_sec == 0) || (max_sec > sdev->host->max_sectors)) max_sec = sdev->host->max_sectors; - blk_queue_max_hw_sectors(sdev->request_queue, max_sec); dev_info(hdev->dev, "[%s] sdev->channel:id:lun[%d:%d:%lld], scmd_timeout[%d]s, maxsec[%d]\n", __func__, sdev->channel, sdev->id, sdev->lun, timeout / HZ, max_sec); @@ -1176,6 +1156,75 @@ static inline bool spraid_cqe_pending(struct spraid_queue *spraidq) spraidq->cq_phase; } +static void spraid_sata_report_zone_handle(struct scsi_cmnd *scmd, struct spraid_iod *iod) +{ + int i = 0; + unsigned int bytes = 0; + struct scatterlist *sg = scsi_sglist(scmd); + + scsi_for_each_sg(scmd, sg, iod->nsge, i) { + unsigned int offset = 0; + + if (bytes == 0) { + char *hdr; + u32 list_length; + u64 max_lba, opt_lba; + u16 same; + + hdr = sg_virt(sg); + + list_length = get_unaligned_le32(&hdr[0]); + same = get_unaligned_le16(&hdr[4]); + max_lba = get_unaligned_le64(&hdr[8]); + opt_lba = get_unaligned_le64(&hdr[16]); + put_unaligned_be32(list_length, &hdr[0]); + hdr[4] = same & 0xf; + put_unaligned_be64(max_lba, &hdr[8]); + put_unaligned_be64(opt_lba, &hdr[16]); + offset += 64; + bytes += 64; + } + while (offset < sg_dma_len(sg)) { + char *rec; + u8 cond, type, non_seq, reset; + u64 size, start, wp; + + rec = sg_virt(sg) + offset; + type = rec[0] & 0xf; + cond = (rec[1] >> 4) & 0xf; + non_seq = (rec[1] & 2); + reset = (rec[1] & 1); + size = get_unaligned_le64(&rec[8]); + start = get_unaligned_le64(&rec[16]); + wp = get_unaligned_le64(&rec[24]); + rec[0] = type; + rec[1] = (cond << 4) | non_seq | reset; + put_unaligned_be64(size, &rec[8]); + put_unaligned_be64(start, &rec[16]); + put_unaligned_be64(wp, &rec[24]); + WARN_ON(offset + 64 > sg_dma_len(sg)); + offset += 64; + bytes += 64; + } + } +} + +static inline void spraid_handle_ata_cmd(struct spraid_dev *hdev, struct scsi_cmnd *scmd, + struct spraid_iod *iod) +{ + if (hdev->ctrl_info->card_type != SPRAID_CARD_HBA) + return; + + switch (scmd->cmnd[0]) { + case ZBC_IN: + dev_info(hdev->dev, "[%s] process report zone\n", __func__); + spraid_sata_report_zone_handle(scmd, iod); + break; + default: + break; + } +} + static void spraid_complete_ioq_cmnd(struct spraid_queue *ioq, struct spraid_completion *cqe) { struct spraid_dev *hdev = ioq->hdev; @@ -1197,12 +1246,12 @@ static void spraid_complete_ioq_cmnd(struct spraid_queue *ioq, struct spraid_com iod = scsi_cmd_priv(scmd); elapsed = jiffies - scmd->jiffies_at_alloc; - dev_log_dbg(hdev->dev, "cid[%d], qid[%d] finish IO cost %3ld.%3ld seconds\n", + dev_log_dbg(hdev->dev, "cid[%d] qid[%d] finish IO cost %3ld.%3ld seconds\n", cqe->cmd_id, ioq->qid, elapsed / HZ, elapsed % HZ); if (cmpxchg(&iod->state, SPRAID_CMD_IN_FLIGHT, SPRAID_CMD_COMPLETE) != SPRAID_CMD_IN_FLIGHT) { - dev_warn(hdev->dev, "cid[%d], qid[%d] enters abnormal handler, cost %3ld.%3ld seconds\n", + dev_warn(hdev->dev, "cid[%d] qid[%d] enters abnormal handler, cost %3ld.%3ld seconds\n", cqe->cmd_id, ioq->qid, elapsed / HZ, elapsed % HZ); WRITE_ONCE(iod->state, SPRAID_CMD_TMO_COMPLETE); @@ -1215,6 +1264,8 @@ static void spraid_complete_ioq_cmnd(struct spraid_queue *ioq, struct spraid_com return; } + spraid_handle_ata_cmd(hdev, scmd, iod); + spraid_map_status(iod, scmd, cqe); if (iod->nsge) { iod->nsge = 0; @@ -1224,38 +1275,36 @@ static void spraid_complete_ioq_cmnd(struct spraid_queue *ioq, struct spraid_com scmd->scsi_done(scmd); } -static inline void spraid_end_admin_request(struct request *req, __le16 status, - __le32 result0, __le32 result1) -{ - struct spraid_admin_request *rq = spraid_admin_req(req); - - rq->status = le16_to_cpu(status) >> 1; - rq->result0 = le32_to_cpu(result0); - rq->result1 = le32_to_cpu(result1); - blk_mq_complete_request(req); -} - static void spraid_complete_adminq_cmnd(struct spraid_queue *adminq, struct spraid_completion *cqe) { - struct blk_mq_tags *tags = adminq->hdev->admin_tagset.tags[0]; - struct request *req; + struct spraid_dev *hdev = adminq->hdev; + struct spraid_cmd *adm_cmd; - req = blk_mq_tag_to_rq(tags, cqe->cmd_id); - if (unlikely(!req)) { + adm_cmd = hdev->adm_cmds + cqe->cmd_id; + if (unlikely(adm_cmd->state == SPRAID_CMD_IDLE)) { dev_warn(adminq->hdev->dev, "Invalid id %d completed on queue %d\n", cqe->cmd_id, le16_to_cpu(cqe->sq_id)); return; } - spraid_end_admin_request(req, cqe->status, cqe->result, cqe->result1); + + adm_cmd->status = le16_to_cpu(cqe->status) >> 1; + adm_cmd->result0 = le32_to_cpu(cqe->result); + adm_cmd->result1 = le32_to_cpu(cqe->result1); + + complete(&adm_cmd->cmd_done); } +static void spraid_send_aen(struct spraid_dev *hdev, u16 cid); + static void spraid_complete_aen(struct spraid_queue *spraidq, struct spraid_completion *cqe) { struct spraid_dev *hdev = spraidq->hdev; u32 result = le32_to_cpu(cqe->result); - dev_info(hdev->dev, "rcv aen, status[%x], result[%x]\n", - le16_to_cpu(cqe->status) >> 1, result); + dev_info(hdev->dev, "rcv aen, cid[%d], status[0x%x], result[0x%x]\n", + cqe->cmd_id, le16_to_cpu(cqe->status) >> 1, result); + + spraid_send_aen(hdev, cqe->cmd_id); if ((le16_to_cpu(cqe->status) >> 1) != SPRAID_SC_SUCCESS) return; @@ -1264,22 +1313,19 @@ static void spraid_complete_aen(struct spraid_queue *spraidq, struct spraid_comp spraid_handle_aen_notice(hdev, result); break; case SPRAID_AEN_VS: - spraid_handle_aen_vs(hdev, result); + spraid_handle_aen_vs(hdev, result, le32_to_cpu(cqe->result1)); break; default: dev_warn(hdev->dev, "Unsupported async event type: %u\n", result & 0x7); break; } - queue_work(spraid_wq, &hdev->aen_work); } -static void spraid_put_ioq_ptcmd(struct spraid_dev *hdev, struct spraid_ioq_ptcmd *cmd); - static void spraid_complete_ioq_sync_cmnd(struct spraid_queue *ioq, struct spraid_completion *cqe) { struct spraid_dev *hdev = ioq->hdev; - struct spraid_ioq_ptcmd *ptcmd; + struct spraid_cmd *ptcmd; ptcmd = hdev->ioq_ptcmds + (ioq->qid - 1) * SPRAID_PTCMDS_PERQ + cqe->cmd_id - SPRAID_IO_BLK_MQ_DEPTH; @@ -1289,8 +1335,6 @@ static void spraid_complete_ioq_sync_cmnd(struct spraid_queue *ioq, struct sprai ptcmd->result1 = le32_to_cpu(cqe->result1); complete(&ptcmd->cmd_done); - - spraid_put_ioq_ptcmd(hdev, ptcmd); } static inline void spraid_handle_cqe(struct spraid_queue *spraidq, u16 idx) @@ -1304,7 +1348,7 @@ static inline void spraid_handle_cqe(struct spraid_queue *spraidq, u16 idx) return; } - dev_log_dbg(hdev->dev, "cid[%d], qid[%d], result[0x%x], sq_id[%d], status[0x%x]\n", + dev_log_dbg(hdev->dev, "cid[%d] qid[%d], result[0x%x], sq_id[%d], status[0x%x]\n", cqe->cmd_id, spraidq->qid, le32_to_cpu(cqe->result), le16_to_cpu(cqe->sq_id), le16_to_cpu(cqe->status)); @@ -1452,62 +1496,119 @@ static u32 spraid_bar_size(struct spraid_dev *hdev, u32 nr_ioqs) return (SPRAID_REG_DBS + ((nr_ioqs + 1) * 8 * hdev->db_stride)); } -static inline void spraid_clear_spraid_request(struct request *req) +static int spraid_alloc_admin_cmds(struct spraid_dev *hdev) { - if (!(req->rq_flags & RQF_DONTPREP)) { - spraid_admin_req(req)->flags = 0; - req->rq_flags |= RQF_DONTPREP; + int i; + + INIT_LIST_HEAD(&hdev->adm_cmd_list); + spin_lock_init(&hdev->adm_cmd_lock); + + hdev->adm_cmds = kcalloc_node(SPRAID_AQ_BLK_MQ_DEPTH, sizeof(struct spraid_cmd), + GFP_KERNEL, hdev->numa_node); + + if (!hdev->adm_cmds) { + dev_err(hdev->dev, "Alloc admin cmds failed\n"); + return -ENOMEM; + } + + for (i = 0; i < SPRAID_AQ_BLK_MQ_DEPTH; i++) { + hdev->adm_cmds[i].qid = 0; + hdev->adm_cmds[i].cid = i; + list_add_tail(&(hdev->adm_cmds[i].list), &hdev->adm_cmd_list); } + + dev_info(hdev->dev, "Alloc admin cmds success, num[%d]\n", SPRAID_AQ_BLK_MQ_DEPTH); + + return 0; } -static struct request *spraid_alloc_admin_request(struct request_queue *q, - struct spraid_admin_command *cmd, - blk_mq_req_flags_t flags) +static void spraid_free_admin_cmds(struct spraid_dev *hdev) { - u32 op = COMMAND_IS_WRITE(cmd) ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN; - struct request *req; + kfree(hdev->adm_cmds); + hdev->adm_cmds = NULL; + INIT_LIST_HEAD(&hdev->adm_cmd_list); +} + +static struct spraid_cmd *spraid_get_cmd(struct spraid_dev *hdev, enum spraid_cmd_type type) +{ + struct spraid_cmd *cmd = NULL; + unsigned long flags; + struct list_head *head = &hdev->adm_cmd_list; + spinlock_t *slock = &hdev->adm_cmd_lock; - req = blk_mq_alloc_request(q, op, flags); - if (IS_ERR(req)) - return req; - req->cmd_flags |= REQ_FAILFAST_DRIVER; - spraid_clear_spraid_request(req); - spraid_admin_req(req)->cmd = cmd; + if (type == SPRAID_CMD_IOPT) { + head = &hdev->ioq_pt_list; + slock = &hdev->ioq_pt_lock; + } + + spin_lock_irqsave(slock, flags); + if (list_empty(head)) { + spin_unlock_irqrestore(slock, flags); + dev_err(hdev->dev, "err, cmd[%d] list empty\n", type); + return NULL; + } + cmd = list_entry(head->next, struct spraid_cmd, list); + list_del_init(&cmd->list); + spin_unlock_irqrestore(slock, flags); + + WRITE_ONCE(cmd->state, SPRAID_CMD_IN_FLIGHT); - return req; + return cmd; } -static int spraid_submit_admin_sync_cmd(struct request_queue *q, - struct spraid_admin_command *cmd, - u32 *result, void *buffer, - u32 bufflen, u32 timeout, int at_head, blk_mq_req_flags_t flags) +static void spraid_put_cmd(struct spraid_dev *hdev, struct spraid_cmd *cmd, + enum spraid_cmd_type type) { - struct request *req; - int ret; + unsigned long flags; + struct list_head *head = &hdev->adm_cmd_list; + spinlock_t *slock = &hdev->adm_cmd_lock; - req = spraid_alloc_admin_request(q, cmd, flags); - if (IS_ERR(req)) - return PTR_ERR(req); + if (type == SPRAID_CMD_IOPT) { + head = &hdev->ioq_pt_list; + slock = &hdev->ioq_pt_lock; + } - req->timeout = timeout ? timeout : ADMIN_TIMEOUT; - if (buffer && bufflen) { - ret = blk_rq_map_kern(q, req, buffer, bufflen, GFP_KERNEL); - if (ret) - goto out; + spin_lock_irqsave(slock, flags); + WRITE_ONCE(cmd->state, SPRAID_CMD_IDLE); + list_add_tail(&cmd->list, head); + spin_unlock_irqrestore(slock, flags); +} + + +static int spraid_submit_admin_sync_cmd(struct spraid_dev *hdev, struct spraid_admin_command *cmd, + u32 *result0, u32 *result1, u32 timeout) +{ + struct spraid_cmd *adm_cmd = spraid_get_cmd(hdev, SPRAID_CMD_ADM); + + if (!adm_cmd) { + dev_err(hdev->dev, "err, get admin cmd failed\n"); + return -EFAULT; } - blk_execute_rq(req->q, NULL, req, at_head); - if (result) - *result = spraid_admin_req(req)->result0; + timeout = timeout ? timeout : ADMIN_TIMEOUT; - if (spraid_admin_req(req)->flags & SPRAID_REQ_CANCELLED) - ret = -EINTR; - else - ret = spraid_admin_req(req)->status; + init_completion(&adm_cmd->cmd_done); -out: - blk_mq_free_request(req); - return ret; + cmd->common.command_id = adm_cmd->cid; + spraid_submit_cmd(&hdev->queues[0], cmd); + + if (!wait_for_completion_timeout(&adm_cmd->cmd_done, timeout)) { + dev_err(hdev->dev, "[%s] cid[%d] qid[%d] timeout, opcode[0x%x] subopcode[0x%x]\n", + __func__, adm_cmd->cid, adm_cmd->qid, cmd->usr_cmd.opcode, + cmd->usr_cmd.info_0.subopcode); + WRITE_ONCE(adm_cmd->state, SPRAID_CMD_TIMEOUT); + spraid_put_cmd(hdev, adm_cmd, SPRAID_CMD_ADM); + return -EINVAL; + } + + if (result0) + *result0 = adm_cmd->result0; + if (result1) + *result1 = adm_cmd->result1; + + spraid_put_cmd(hdev, adm_cmd, SPRAID_CMD_ADM); + + return adm_cmd->status; } static int spraid_create_cq(struct spraid_dev *hdev, u16 qid, @@ -1524,8 +1625,7 @@ static int spraid_create_cq(struct spraid_dev *hdev, u16 qid, admin_cmd.create_cq.cq_flags = cpu_to_le16(flags); admin_cmd.create_cq.irq_vector = cpu_to_le16(cq_vector); - return spraid_submit_admin_sync_cmd(hdev->admin_q, &admin_cmd, NULL, - NULL, 0, 0, 0, 0); + return spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); } static int spraid_create_sq(struct spraid_dev *hdev, u16 qid, @@ -1542,8 +1642,7 @@ static int spraid_create_sq(struct spraid_dev *hdev, u16 qid, admin_cmd.create_sq.sq_flags = cpu_to_le16(flags); admin_cmd.create_sq.cqid = cpu_to_le16(qid); - return spraid_submit_admin_sync_cmd(hdev->admin_q, &admin_cmd, NULL, - NULL, 0, 0, 0, 0); + return spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); } static void spraid_free_queue(struct spraid_queue *spraidq) @@ -1581,8 +1680,7 @@ static int spraid_delete_queue(struct spraid_dev *hdev, u8 op, u16 id) admin_cmd.delete_queue.opcode = op; admin_cmd.delete_queue.qid = cpu_to_le16(id); - ret = spraid_submit_admin_sync_cmd(hdev->admin_q, &admin_cmd, NULL, - NULL, 0, 0, 0, 0); + ret = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); if (ret) dev_err(hdev->dev, "Delete %s:[%d] failed\n", @@ -1663,19 +1761,28 @@ static int spraid_set_features(struct spraid_dev *hdev, u32 fid, u32 dword11, vo size_t buflen, u32 *result) { struct spraid_admin_command admin_cmd; - u32 res; int ret; + u8 *data_ptr = NULL; + dma_addr_t data_dma = 0; + + if (buffer && buflen) { + data_ptr = dma_alloc_coherent(hdev->dev, buflen, &data_dma, GFP_KERNEL); + if (!data_ptr) + return -ENOMEM; + + memcpy(data_ptr, buffer, buflen); + } memset(&admin_cmd, 0, sizeof(admin_cmd)); admin_cmd.features.opcode = SPRAID_ADMIN_SET_FEATURES; admin_cmd.features.fid = cpu_to_le32(fid); admin_cmd.features.dword11 = cpu_to_le32(dword11); + admin_cmd.common.dptr.prp1 = cpu_to_le64(data_dma); - ret = spraid_submit_admin_sync_cmd(hdev->admin_q, &admin_cmd, &res, - buffer, buflen, 0, 0, 0); + ret = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, result, NULL, 0); - if (!ret && result) - *result = res; + if (data_ptr) + dma_free_coherent(hdev->dev, buflen, data_ptr, data_dma); return ret; } @@ -1764,8 +1871,7 @@ static int spraid_setup_io_queues(struct spraid_dev *hdev) break; } dev_info(hdev->dev, "[%s] max_qid: %d, queue_count: %d, online_queue: %d, ioq_depth: %d\n", - __func__, hdev->max_qid, hdev->queue_count, - hdev->online_queues, hdev->ioq_depth); + __func__, hdev->max_qid, hdev->queue_count, hdev->online_queues, hdev->ioq_depth); return spraid_create_io_queues(hdev); } @@ -1889,10 +1995,11 @@ static int spraid_get_dev_list(struct spraid_dev *hdev, struct spraid_dev_info * u32 nd = le32_to_cpu(hdev->ctrl_info->nd); struct spraid_admin_command admin_cmd; struct spraid_dev_list *list_buf; + dma_addr_t data_dma = 0; u32 i, idx, hdid, ndev; int ret = 0; - list_buf = kmalloc(sizeof(*list_buf), GFP_KERNEL); + list_buf = dma_alloc_coherent(hdev->dev, PAGE_SIZE, &data_dma, GFP_KERNEL); if (!list_buf) return -ENOMEM; @@ -1901,9 +2008,9 @@ static int spraid_get_dev_list(struct spraid_dev *hdev, struct spraid_dev_info * admin_cmd.get_info.opcode = SPRAID_ADMIN_GET_INFO; admin_cmd.get_info.type = SPRAID_GET_INFO_DEV_LIST; admin_cmd.get_info.cdw11 = cpu_to_le32(idx); + admin_cmd.common.dptr.prp1 = cpu_to_le64(data_dma); - ret = spraid_submit_admin_sync_cmd(hdev->admin_q, &admin_cmd, NULL, list_buf, - sizeof(*list_buf), 0, 0, 0); + ret = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); if (ret) { dev_err(hdev->dev, "Get device list failed, nd: %u, idx: %u, ret: %d\n", @@ -1916,12 +2023,11 @@ static int spraid_get_dev_list(struct spraid_dev *hdev, struct spraid_dev_info * for (i = 0; i < ndev; i++) { hdid = le32_to_cpu(list_buf->devices[i].hdid); - dev_info(hdev->dev, "list_buf->devices[%d], hdid: %u target: %d, channel: %d, lun: %d, attr[%x]\n", - i, hdid, - le16_to_cpu(list_buf->devices[i].target), - list_buf->devices[i].channel, - list_buf->devices[i].lun, - list_buf->devices[i].attr); + dev_info(hdev->dev, "list_buf->devices[%d], hdid: %u target: %d, channel: %d, lun: %d, attr[0x%x]\n", + i, hdid, le16_to_cpu(list_buf->devices[i].target), + list_buf->devices[i].channel, + list_buf->devices[i].lun, + list_buf->devices[i].attr); if (hdid > nd || hdid == 0) { dev_err(hdev->dev, "err, hdid[%d] invalid\n", hdid); continue; @@ -1936,21 +2042,29 @@ static int spraid_get_dev_list(struct spraid_dev *hdev, struct spraid_dev_info * } out: - kfree(list_buf); + dma_free_coherent(hdev->dev, PAGE_SIZE, list_buf, data_dma); return ret; } -static void spraid_send_aen(struct spraid_dev *hdev) +static void spraid_send_aen(struct spraid_dev *hdev, u16 cid) { struct spraid_queue *adminq = &hdev->queues[0]; struct spraid_admin_command admin_cmd; memset(&admin_cmd, 0, sizeof(admin_cmd)); admin_cmd.common.opcode = SPRAID_ADMIN_ASYNC_EVENT; - admin_cmd.common.command_id = SPRAID_AQ_BLK_MQ_DEPTH; + admin_cmd.common.command_id = cid; spraid_submit_cmd(adminq, &admin_cmd); - dev_info(hdev->dev, "send aen, cid[%d]\n", SPRAID_AQ_BLK_MQ_DEPTH); + dev_info(hdev->dev, "send aen, cid[%d]\n", cid); +} + +static inline void spraid_send_all_aen(struct spraid_dev *hdev) +{ + u16 i; + + for (i = 0; i < hdev->ctrl_info->aerl; i++) + spraid_send_aen(hdev, i + SPRAID_AQ_BLK_MQ_DEPTH); } static int spraid_add_device(struct spraid_dev *hdev, struct spraid_dev_info *device) @@ -1958,6 +2072,10 @@ static int spraid_add_device(struct spraid_dev *hdev, struct spraid_dev_info *de struct Scsi_Host *shost = hdev->shost; struct scsi_device *sdev; + dev_info(hdev->dev, "add device, hdid: %u target: %d, channel: %d, lun: %d, attr[0x%x]\n", + le32_to_cpu(device->hdid), le16_to_cpu(device->target), + device->channel, device->lun, device->attr); + sdev = scsi_device_lookup(shost, device->channel, le16_to_cpu(device->target), 0); if (sdev) { dev_warn(hdev->dev, "Device is already exist, channel: %d, target_id: %d, lun: %d\n", @@ -1974,9 +2092,13 @@ static int spraid_rescan_device(struct spraid_dev *hdev, struct spraid_dev_info struct Scsi_Host *shost = hdev->shost; struct scsi_device *sdev; + dev_info(hdev->dev, "rescan device, hdid: %u target: %d, channel: %d, lun: %d, attr[0x%x]\n", + le32_to_cpu(device->hdid), le16_to_cpu(device->target), + device->channel, device->lun, device->attr); + sdev = scsi_device_lookup(shost, device->channel, le16_to_cpu(device->target), 0); if (!sdev) { - dev_warn(hdev->dev, "Device is not exit, channel: %d, target_id: %d, lun: %d\n", + dev_warn(hdev->dev, "device is not exit rescan it, channel: %d, target_id: %d, lun: %d\n", device->channel, le16_to_cpu(device->target), 0); return -ENODEV; } @@ -1991,9 +2113,13 @@ static int spraid_remove_device(struct spraid_dev *hdev, struct spraid_dev_info struct Scsi_Host *shost = hdev->shost; struct scsi_device *sdev; + dev_info(hdev->dev, "remove device, hdid: %u target: %d, channel: %d, lun: %d, attr[0x%x]\n", + le32_to_cpu(org_device->hdid), le16_to_cpu(org_device->target), + org_device->channel, org_device->lun, org_device->attr); + sdev = scsi_device_lookup(shost, org_device->channel, le16_to_cpu(org_device->target), 0); if (!sdev) { - dev_warn(hdev->dev, "Device is not exit, channel: %d, target_id: %d, lun: %d\n", + dev_warn(hdev->dev, "device is not exit remove it, channel: %d, target_id: %d, lun: %d\n", org_device->channel, le16_to_cpu(org_device->target), 0); return -ENODEV; } @@ -2029,36 +2155,54 @@ static int spraid_dev_list_init(struct spraid_dev *hdev) return 0; } +static int luntarget_cmp_func(const void *l, const void *r) +{ + const struct spraid_dev_info *ln = l; + const struct spraid_dev_info *rn = r; + + if (ln->channel == rn->channel) + return ln->target - rn->target; + + return ln->channel - rn->channel; +} + static void spraid_scan_work(struct work_struct *work) { struct spraid_dev *hdev = container_of(work, struct spraid_dev, scan_work); struct spraid_dev_info *devices, *org_devices; + struct spraid_dev_info *sortdevice; u32 nd = le32_to_cpu(hdev->ctrl_info->nd); u8 flag, org_flag; int i, ret; + int count = 0; devices = kcalloc(nd, sizeof(struct spraid_dev_info), GFP_KERNEL); if (!devices) return; + + sortdevice = kcalloc(nd, sizeof(struct spraid_dev_info), GFP_KERNEL); + if (!sortdevice) + goto free_list; + ret = spraid_get_dev_list(hdev, devices); if (ret) - goto free_list; + goto free_all; org_devices = hdev->devices; for (i = 0; i < nd; i++) { org_flag = org_devices[i].flag; flag = devices[i].flag; - dev_log_dbg(hdev->dev, "i: %d, org_flag: 0x%x, flag: 0x%x\n", - i, org_flag, flag); + dev_log_dbg(hdev->dev, "i: %d, org_flag: 0x%x, flag: 0x%x\n", i, org_flag, flag); if (SPRAID_DEV_INFO_FLAG_VALID(flag)) { if (!SPRAID_DEV_INFO_FLAG_VALID(org_flag)) { down_write(&hdev->devices_rwsem); memcpy(&org_devices[i], &devices[i], - sizeof(struct spraid_dev_info)); + sizeof(struct spraid_dev_info)); + memcpy(&sortdevice[count++], &devices[i], + sizeof(struct spraid_dev_info)); up_write(&hdev->devices_rwsem); - spraid_add_device(hdev, &devices[i]); } else if (SPRAID_DEV_INFO_FLAG_CHANGE(flag)) { spraid_rescan_device(hdev, &devices[i]); } @@ -2071,6 +2215,16 @@ static void spraid_scan_work(struct work_struct *work) } } } + + dev_info(hdev->dev, "scan work add device count = %d\n", count); + + sort(sortdevice, count, sizeof(sortdevice[0]), luntarget_cmp_func, NULL); + + for (i = 0; i < count; i++) + spraid_add_device(hdev, &sortdevice[i]); + +free_all: + kfree(sortdevice); free_list: kfree(devices); } @@ -2083,6 +2237,15 @@ static void spraid_timesyn_work(struct work_struct *work) spraid_configure_timestamp(hdev); } +static int spraid_init_ctrl_info(struct spraid_dev *hdev); +static void spraid_fw_act_work(struct work_struct *work) +{ + struct spraid_dev *hdev = container_of(work, struct spraid_dev, fw_act_work); + + if (spraid_init_ctrl_info(hdev)) + dev_err(hdev->dev, "get ctrl info failed after fw act\n"); +} + static void spraid_queue_scan(struct spraid_dev *hdev) { queue_work(spraid_wq, &hdev->scan_work); @@ -2094,6 +2257,9 @@ static void spraid_handle_aen_notice(struct spraid_dev *hdev, u32 result) case SPRAID_AEN_DEV_CHANGED: spraid_queue_scan(hdev); break; + case SPRAID_AEN_FW_ACT_START: + dev_info(hdev->dev, "fw activation starting\n"); + break; case SPRAID_AEN_HOST_PROBING: break; default: @@ -2101,25 +2267,25 @@ static void spraid_handle_aen_notice(struct spraid_dev *hdev, u32 result) } } -static void spraid_handle_aen_vs(struct spraid_dev *hdev, u32 result) +static void spraid_handle_aen_vs(struct spraid_dev *hdev, u32 result, u32 result1) { - switch (result) { + switch ((result & 0xff00) >> 8) { case SPRAID_AEN_TIMESYN: queue_work(spraid_wq, &hdev->timesyn_work); break; + case SPRAID_AEN_FW_ACT_FINISH: + dev_info(hdev->dev, "fw activation finish\n"); + queue_work(spraid_wq, &hdev->fw_act_work); + break; + case SPRAID_AEN_EVENT_MIN ... SPRAID_AEN_EVENT_MAX: + dev_info(hdev->dev, "rcv card event[%d], param1[0x%x] param2[0x%x]\n", + (result & 0xff00) >> 8, result, result1); + break; default: - dev_warn(hdev->dev, "async event result: %x\n", result); + dev_warn(hdev->dev, "async event result: 0x%x\n", result); } } -static void spraid_async_event_work(struct work_struct *work) -{ - struct spraid_dev *hdev = - container_of(work, struct spraid_dev, aen_work); - - spraid_send_aen(hdev); -} - static int spraid_alloc_resources(struct spraid_dev *hdev) { int ret, nqueue; @@ -2149,10 +2315,16 @@ static int spraid_alloc_resources(struct spraid_dev *hdev) goto destroy_dma_pools; } + ret = spraid_alloc_admin_cmds(hdev); + if (ret) + goto free_queues; + dev_info(hdev->dev, "[%s] queues num: %d\n", __func__, nqueue); return 0; +free_queues: + kfree(hdev->queues); destroy_dma_pools: spraid_destroy_dma_pools(hdev); free_ctrl_info: @@ -2164,50 +2336,18 @@ static int spraid_alloc_resources(struct spraid_dev *hdev) static void spraid_free_resources(struct spraid_dev *hdev) { + spraid_free_admin_cmds(hdev); kfree(hdev->queues); spraid_destroy_dma_pools(hdev); kfree(hdev->ctrl_info); ida_free(&spraid_instance_ida, hdev->instance); } -static void spraid_setup_passthrough(struct request *req, struct spraid_admin_command *cmd) -{ - memcpy(cmd, spraid_admin_req(req)->cmd, sizeof(*cmd)); - cmd->common.flags &= ~SPRAID_CMD_FLAG_SGL_ALL; -} - -static inline void spraid_clear_hreq(struct request *req) -{ - if (!(req->rq_flags & RQF_DONTPREP)) { - spraid_admin_req(req)->flags = 0; - req->rq_flags |= RQF_DONTPREP; - } -} - -static blk_status_t spraid_setup_admin_cmd(struct request *req, struct spraid_admin_command *cmd) +static void spraid_bsg_unmap_data(struct spraid_dev *hdev, struct bsg_job *job) { - spraid_clear_hreq(req); - - memset(cmd, 0, sizeof(*cmd)); - switch (req_op(req)) { - case REQ_OP_DRV_IN: - case REQ_OP_DRV_OUT: - spraid_setup_passthrough(req, cmd); - break; - default: - WARN_ON_ONCE(1); - return BLK_STS_IOERR; - } - - cmd->common.command_id = req->tag; - return BLK_STS_OK; -} - -static void spraid_unmap_data(struct spraid_dev *hdev, struct request *req) -{ - struct spraid_iod *iod = blk_mq_rq_to_pdu(req); - enum dma_data_direction dma_dir = rq_data_dir(req) ? - DMA_TO_DEVICE : DMA_FROM_DEVICE; + struct request *rq = blk_mq_rq_from_pdu(job); + struct spraid_iod *iod = job->dd_data; + enum dma_data_direction dma_dir = rq_data_dir(rq) ? DMA_TO_DEVICE : DMA_FROM_DEVICE; if (iod->nsge) dma_unmap_sg(hdev->dev, iod->sg, iod->nsge, dma_dir); @@ -2215,36 +2355,36 @@ static void spraid_unmap_data(struct spraid_dev *hdev, struct request *req) spraid_free_iod_res(hdev, iod); } -static blk_status_t spraid_admin_map_data(struct spraid_dev *hdev, struct request *req, - struct spraid_admin_command *cmd) +static int spraid_bsg_map_data(struct spraid_dev *hdev, struct bsg_job *job, + struct spraid_admin_command *cmd) { - struct spraid_iod *iod = blk_mq_rq_to_pdu(req); - struct request_queue *admin_q = req->q; - enum dma_data_direction dma_dir = rq_data_dir(req) ? - DMA_TO_DEVICE : DMA_FROM_DEVICE; - blk_status_t ret = BLK_STS_IOERR; - int nr_mapped; - int res; + struct request *rq = blk_mq_rq_from_pdu(job); + struct spraid_iod *iod = job->dd_data; + enum dma_data_direction dma_dir = rq_data_dir(rq) ? DMA_TO_DEVICE : DMA_FROM_DEVICE; + int ret = 0; + + iod->sg = job->request_payload.sg_list; + iod->nsge = job->request_payload.sg_cnt; + iod->length = job->request_payload.payload_len; + iod->use_sgl = false; + iod->npages = -1; + iod->sg_drv_mgmt = false; - sg_init_table(iod->sg, blk_rq_nr_phys_segments(req)); - iod->nsge = blk_rq_map_sg(admin_q, req, iod->sg); if (!iod->nsge) goto out; - dev_info(hdev->dev, "nseg: %u, nsge: %u\n", - blk_rq_nr_phys_segments(req), iod->nsge); - - ret = BLK_STS_RESOURCE; - nr_mapped = dma_map_sg_attrs(hdev->dev, iod->sg, iod->nsge, dma_dir, DMA_ATTR_NO_WARN); - if (!nr_mapped) + ret = dma_map_sg_attrs(hdev->dev, iod->sg, iod->nsge, dma_dir, DMA_ATTR_NO_WARN); + if (!ret) goto out; - res = spraid_setup_prps(hdev, iod); - if (res) + ret = spraid_setup_prps(hdev, iod); + if (ret) goto unmap; + cmd->common.dptr.prp1 = cpu_to_le64(sg_dma_address(iod->sg)); cmd->common.dptr.prp2 = cpu_to_le64(iod->first_dma); - return BLK_STS_OK; + + return 0; unmap: dma_unmap_sg(hdev->dev, iod->sg, iod->nsge, dma_dir); @@ -2252,137 +2392,29 @@ static blk_status_t spraid_admin_map_data(struct spraid_dev *hdev, struct reques return ret; } -static blk_status_t spraid_init_admin_iod(struct request *rq, struct spraid_dev *hdev) -{ - struct spraid_iod *iod = blk_mq_rq_to_pdu(rq); - int nents = blk_rq_nr_phys_segments(rq); - unsigned int size = blk_rq_payload_bytes(rq); - - if (nents > SPRAID_INT_PAGES || size > SPRAID_INT_BYTES(hdev)) { - iod->sg = mempool_alloc(hdev->iod_mempool, GFP_ATOMIC); - if (!iod->sg) - return BLK_STS_RESOURCE; - } else { - iod->sg = iod->inline_sg; - } - - iod->nsge = 0; - iod->use_sgl = false; - iod->npages = -1; - iod->length = size; - iod->sg_drv_mgmt = true; - - return BLK_STS_OK; -} - -static blk_status_t spraid_queue_admin_rq(struct blk_mq_hw_ctx *hctx, - const struct blk_mq_queue_data *bd) -{ - struct spraid_queue *adminq = hctx->driver_data; - struct spraid_dev *hdev = adminq->hdev; - struct request *req = bd->rq; - struct spraid_iod *iod = blk_mq_rq_to_pdu(req); - struct spraid_admin_command cmd; - blk_status_t ret; - - ret = spraid_setup_admin_cmd(req, &cmd); - if (ret) - goto out; - - ret = spraid_init_admin_iod(req, hdev); - if (ret) - goto out; - - if (blk_rq_nr_phys_segments(req)) { - ret = spraid_admin_map_data(hdev, req, &cmd); - if (ret) - goto cleanup_iod; - } - - blk_mq_start_request(req); - spraid_submit_cmd(adminq, &cmd); - return BLK_STS_OK; - -cleanup_iod: - spraid_free_iod_res(hdev, iod); -out: - return ret; -} - -static blk_status_t spraid_error_status(struct request *req) -{ - switch (spraid_admin_req(req)->status & 0x7ff) { - case SPRAID_SC_SUCCESS: - return BLK_STS_OK; - default: - return BLK_STS_IOERR; - } -} - -static void spraid_complete_admin_rq(struct request *req) -{ - struct spraid_iod *iod = blk_mq_rq_to_pdu(req); - struct spraid_dev *hdev = iod->spraidq->hdev; - - if (blk_rq_nr_phys_segments(req)) - spraid_unmap_data(hdev, req); - blk_mq_end_request(req, spraid_error_status(req)); -} - -static int spraid_admin_init_hctx(struct blk_mq_hw_ctx *hctx, void *data, unsigned int hctx_idx) -{ - struct spraid_dev *hdev = data; - struct spraid_queue *adminq = &hdev->queues[0]; - - WARN_ON(hctx_idx != 0); - WARN_ON(hdev->admin_tagset.tags[0] != hctx->tags); - - hctx->driver_data = adminq; - return 0; -} - -static int spraid_admin_init_request(struct blk_mq_tag_set *set, struct request *req, - unsigned int hctx_idx, unsigned int numa_node) -{ - struct spraid_dev *hdev = set->driver_data; - struct spraid_iod *iod = blk_mq_rq_to_pdu(req); - struct spraid_queue *adminq = &hdev->queues[0]; - - WARN_ON(!adminq); - iod->spraidq = adminq; - return 0; -} - -static enum blk_eh_timer_return -spraid_admin_timeout(struct request *req, bool reserved) -{ - struct spraid_iod *iod = blk_mq_rq_to_pdu(req); - struct spraid_queue *spraidq = iod->spraidq; - struct spraid_dev *hdev = spraidq->hdev; - - dev_err(hdev->dev, "Admin cid[%d] qid[%d] timeout\n", - req->tag, spraidq->qid); - - if (spraid_poll_cq(spraidq, req->tag)) { - dev_warn(hdev->dev, "cid[%d] qid[%d] timeout, completion polled\n", - req->tag, spraidq->qid); - return BLK_EH_DONE; - } - - spraid_end_admin_request(req, cpu_to_le16(-EINVAL), 0, 0); - return BLK_EH_DONE; -} - static int spraid_get_ctrl_info(struct spraid_dev *hdev, struct spraid_ctrl_info *ctrl_info) { struct spraid_admin_command admin_cmd; + u8 *data_ptr = NULL; + dma_addr_t data_dma = 0; + int ret; + + data_ptr = dma_alloc_coherent(hdev->dev, PAGE_SIZE, &data_dma, GFP_KERNEL); + if (!data_ptr) + return -ENOMEM; memset(&admin_cmd, 0, sizeof(admin_cmd)); admin_cmd.get_info.opcode = SPRAID_ADMIN_GET_INFO; admin_cmd.get_info.type = SPRAID_GET_INFO_CTRL; + admin_cmd.common.dptr.prp1 = cpu_to_le64(data_dma); + + ret = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); + if (!ret) + memcpy(ctrl_info, data_ptr, sizeof(struct spraid_ctrl_info)); - return spraid_submit_admin_sync_cmd(hdev->admin_q, &admin_cmd, NULL, - ctrl_info, sizeof(struct spraid_ctrl_info), 0, 0, 0); + dma_free_coherent(hdev->dev, PAGE_SIZE, data_ptr, data_dma); + + return ret; } static int spraid_init_ctrl_info(struct spraid_dev *hdev) @@ -2416,6 +2448,11 @@ static int spraid_init_ctrl_info(struct spraid_dev *hdev) dev_info(hdev->dev, "[%s]sn = %s\n", __func__, hdev->ctrl_info->sn); dev_info(hdev->dev, "[%s]fr = %s\n", __func__, hdev->ctrl_info->fr); + if (!hdev->ctrl_info->aerl) + hdev->ctrl_info->aerl = 1; + if (hdev->ctrl_info->aerl > SPRAID_NR_AEN_COMMANDS) + hdev->ctrl_info->aerl = SPRAID_NR_AEN_COMMANDS; + return 0; } @@ -2444,99 +2481,54 @@ static void spraid_free_iod_ext_mem_pool(struct spraid_dev *hdev) mempool_destroy(hdev->iod_mempool); } -static int spraid_submit_user_cmd(struct request_queue *q, struct spraid_admin_command *cmd, - void __user *ubuffer, unsigned int bufflen, u32 *result, - unsigned int timeout) -{ - struct request *req; - struct bio *bio = NULL; - int ret; - - req = spraid_alloc_admin_request(q, cmd, 0); - if (IS_ERR(req)) - return PTR_ERR(req); - - req->timeout = timeout ? timeout : ADMIN_TIMEOUT; - spraid_admin_req(req)->flags |= SPRAID_REQ_USERCMD; - - if (ubuffer && bufflen) { - ret = blk_rq_map_user(q, req, NULL, ubuffer, bufflen, GFP_KERNEL); - if (ret) - goto out; - bio = req->bio; - } - blk_execute_rq(req->q, NULL, req, 0); - if (spraid_admin_req(req)->flags & SPRAID_REQ_CANCELLED) - ret = -EINTR; - else - ret = spraid_admin_req(req)->status; - if (result) { - result[0] = spraid_admin_req(req)->result0; - result[1] = spraid_admin_req(req)->result1; - } - if (bio) - blk_rq_unmap_user(bio); -out: - blk_mq_free_request(req); - return ret; -} - -static int spraid_user_admin_cmd(struct spraid_dev *hdev, - struct spraid_passthru_common_cmd __user *ucmd) +static int spraid_user_admin_cmd(struct spraid_dev *hdev, struct bsg_job *job) { - struct spraid_passthru_common_cmd cmd; + struct spraid_bsg_request *bsg_req = job->request; + struct spraid_passthru_common_cmd *cmd = &(bsg_req->admcmd); struct spraid_admin_command admin_cmd; - u32 timeout = 0; + u32 timeout = msecs_to_jiffies(cmd->timeout_ms); + u32 result[2] = {0}; int status; - if (!capable(CAP_SYS_ADMIN)) { - dev_err(hdev->dev, "Current user hasn't administrator right, reject service\n"); - return -EACCES; - } - - if (copy_from_user(&cmd, ucmd, sizeof(cmd))) { - dev_err(hdev->dev, "Copy command from user space to kernel space failed\n"); - return -EFAULT; - } - - if (cmd.flags) { - dev_err(hdev->dev, "Invalid flags in user command\n"); - return -EINVAL; + if (hdev->state >= SPRAID_RESETTING) { + dev_err(hdev->dev, "[%s] err, host state:[%d] is not right\n", + __func__, hdev->state); + return -EBUSY; } - dev_info(hdev->dev, "user_admin_cmd opcode: 0x%x, subopcode: 0x%x\n", - cmd.opcode, cmd.cdw2 & 0x7ff); + dev_info(hdev->dev, "[%s] opcode[0x%x] subopcode[0x%x] init\n", + __func__, cmd->opcode, cmd->info_0.subopcode); memset(&admin_cmd, 0, sizeof(admin_cmd)); - admin_cmd.common.opcode = cmd.opcode; - admin_cmd.common.flags = cmd.flags; - admin_cmd.common.hdid = cpu_to_le32(cmd.nsid); - admin_cmd.common.cdw2[0] = cpu_to_le32(cmd.cdw2); - admin_cmd.common.cdw2[1] = cpu_to_le32(cmd.cdw3); - admin_cmd.common.cdw10 = cpu_to_le32(cmd.cdw10); - admin_cmd.common.cdw11 = cpu_to_le32(cmd.cdw11); - admin_cmd.common.cdw12 = cpu_to_le32(cmd.cdw12); - admin_cmd.common.cdw13 = cpu_to_le32(cmd.cdw13); - admin_cmd.common.cdw14 = cpu_to_le32(cmd.cdw14); - admin_cmd.common.cdw15 = cpu_to_le32(cmd.cdw15); - - if (cmd.timeout_ms) - timeout = msecs_to_jiffies(cmd.timeout_ms); - - status = spraid_submit_user_cmd(hdev->admin_q, &admin_cmd, - (void __user *)(uintptr_t)cmd.addr, cmd.info_1.data_len, - &cmd.result0, timeout); - - dev_info(hdev->dev, "user_admin_cmd status: 0x%x, result0: 0x%x, result1: 0x%x\n", - status, cmd.result0, cmd.result1); + admin_cmd.common.opcode = cmd->opcode; + admin_cmd.common.flags = cmd->flags; + admin_cmd.common.hdid = cpu_to_le32(cmd->nsid); + admin_cmd.common.cdw2[0] = cpu_to_le32(cmd->cdw2); + admin_cmd.common.cdw2[1] = cpu_to_le32(cmd->cdw3); + admin_cmd.common.cdw10 = cpu_to_le32(cmd->cdw10); + admin_cmd.common.cdw11 = cpu_to_le32(cmd->cdw11); + admin_cmd.common.cdw12 = cpu_to_le32(cmd->cdw12); + admin_cmd.common.cdw13 = cpu_to_le32(cmd->cdw13); + admin_cmd.common.cdw14 = cpu_to_le32(cmd->cdw14); + admin_cmd.common.cdw15 = cpu_to_le32(cmd->cdw15); + + status = spraid_bsg_map_data(hdev, job, &admin_cmd); + if (status) { + dev_err(hdev->dev, "[%s] err, map data failed\n", __func__); + return status; + } + status = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, &result[0], &result[1], timeout); if (status >= 0) { - if (put_user(cmd.result0, &ucmd->result0)) - return -EFAULT; - if (put_user(cmd.result1, &ucmd->result1)) - return -EFAULT; + job->reply_len = sizeof(result); + memcpy(job->reply, result, sizeof(result)); } + dev_info(hdev->dev, "[%s] opcode[0x%x] subopcode[0x%x], status[0x%x] result0[0x%x] result1[0x%x]\n", + __func__, cmd->opcode, cmd->info_0.subopcode, status, result[0], result[1]); + + spraid_bsg_unmap_data(hdev, job); + return status; } @@ -2548,8 +2540,8 @@ static int spraid_alloc_ioq_ptcmds(struct spraid_dev *hdev) INIT_LIST_HEAD(&hdev->ioq_pt_list); spin_lock_init(&hdev->ioq_pt_lock); - hdev->ioq_ptcmds = kcalloc_node(ptnum, sizeof(struct spraid_ioq_ptcmd), - GFP_KERNEL, hdev->numa_node); + hdev->ioq_ptcmds = kcalloc_node(ptnum, sizeof(struct spraid_cmd), + GFP_KERNEL, hdev->numa_node); if (!hdev->ioq_ptcmds) { dev_err(hdev->dev, "Alloc ioq_ptcmds failed\n"); @@ -2567,55 +2559,35 @@ static int spraid_alloc_ioq_ptcmds(struct spraid_dev *hdev) return 0; } -static struct spraid_ioq_ptcmd *spraid_get_ioq_ptcmd(struct spraid_dev *hdev) +static void spraid_free_ioq_ptcmds(struct spraid_dev *hdev) { - struct spraid_ioq_ptcmd *cmd = NULL; - unsigned long flags; - - spin_lock_irqsave(&hdev->ioq_pt_lock, flags); - if (list_empty(&hdev->ioq_pt_list)) { - spin_unlock_irqrestore(&hdev->ioq_pt_lock, flags); - dev_err(hdev->dev, "err, ioq ptcmd list empty\n"); - return NULL; - } - cmd = list_entry((&hdev->ioq_pt_list)->next, struct spraid_ioq_ptcmd, list); - list_del_init(&cmd->list); - spin_unlock_irqrestore(&hdev->ioq_pt_lock, flags); - - WRITE_ONCE(cmd->state, SPRAID_CMD_IDLE); - - return cmd; -} - -static void spraid_put_ioq_ptcmd(struct spraid_dev *hdev, struct spraid_ioq_ptcmd *cmd) -{ - unsigned long flags; + kfree(hdev->ioq_ptcmds); + hdev->ioq_ptcmds = NULL; - spin_lock_irqsave(&hdev->ioq_pt_lock, flags); - list_add(&cmd->list, (&hdev->ioq_pt_list)->next); - spin_unlock_irqrestore(&hdev->ioq_pt_lock, flags); + INIT_LIST_HEAD(&hdev->ioq_pt_list); } static int spraid_submit_ioq_sync_cmd(struct spraid_dev *hdev, struct spraid_ioq_command *cmd, - u32 *result, void **sense, u32 timeout) + u32 *result, u32 *reslen, u32 timeout) { - struct spraid_queue *ioq; int ret; dma_addr_t sense_dma; - struct spraid_ioq_ptcmd *pt_cmd = spraid_get_ioq_ptcmd(hdev); - - *sense = NULL; + struct spraid_queue *ioq; + void *sense_addr = NULL; + struct spraid_cmd *pt_cmd = spraid_get_cmd(hdev, SPRAID_CMD_IOPT); - if (!pt_cmd) + if (!pt_cmd) { + dev_err(hdev->dev, "err, get ioq cmd failed\n"); return -EFAULT; + } - dev_info(hdev->dev, "[%s] ptcmd, cid[%d], qid[%d]\n", __func__, pt_cmd->cid, pt_cmd->qid); + timeout = timeout ? timeout : ADMIN_TIMEOUT; init_completion(&pt_cmd->cmd_done); ioq = &hdev->queues[pt_cmd->qid]; ret = pt_cmd->cid * SCSI_SENSE_BUFFERSIZE; - pt_cmd->priv = ioq->sense + ret; + sense_addr = ioq->sense + ret; sense_dma = ioq->sense_dma_addr + ret; cmd->common.sense_addr = cpu_to_le64(sense_dma); @@ -2625,260 +2597,87 @@ static int spraid_submit_ioq_sync_cmd(struct spraid_dev *hdev, struct spraid_ioq spraid_submit_cmd(ioq, cmd); if (!wait_for_completion_timeout(&pt_cmd->cmd_done, timeout)) { - dev_err(hdev->dev, "[%s] cid[%d], qid[%d] timeout\n", - __func__, pt_cmd->cid, pt_cmd->qid); + dev_err(hdev->dev, "[%s] cid[%d] qid[%d] timeout, opcode[0x%x] subopcode[0x%x]\n", + __func__, pt_cmd->cid, pt_cmd->qid, cmd->common.opcode, + (le32_to_cpu(cmd->common.cdw3[0]) & 0xffff)); WRITE_ONCE(pt_cmd->state, SPRAID_CMD_TIMEOUT); + spraid_put_cmd(hdev, pt_cmd, SPRAID_CMD_IOPT); return -EINVAL; } - if (result) { - result[0] = pt_cmd->result0; - result[1] = pt_cmd->result1; + if (result && reslen) { + if ((pt_cmd->status & 0x17f) == 0x101) { + memcpy(result, sense_addr, SCSI_SENSE_BUFFERSIZE); + *reslen = SCSI_SENSE_BUFFERSIZE; + } } - if ((pt_cmd->status & 0x17f) == 0x101) - *sense = pt_cmd->priv; + spraid_put_cmd(hdev, pt_cmd, SPRAID_CMD_IOPT); return pt_cmd->status; } -static int spraid_user_ioq_cmd(struct spraid_dev *hdev, - struct spraid_ioq_passthru_cmd __user *ucmd) +static int spraid_user_ioq_cmd(struct spraid_dev *hdev, struct bsg_job *job) { - struct spraid_ioq_passthru_cmd cmd; + struct spraid_bsg_request *bsg_req = (struct spraid_bsg_request *)(job->request); + struct spraid_ioq_passthru_cmd *cmd = &(bsg_req->ioqcmd); struct spraid_ioq_command ioq_cmd; - u32 timeout = 0; int status = 0; - u8 *data_ptr = NULL; - dma_addr_t data_dma; - enum dma_data_direction dma_dir = DMA_NONE; - void *sense = NULL; - - if (!capable(CAP_SYS_ADMIN)) { - dev_err(hdev->dev, "Current user hasn't administrator right, reject service\n"); - return -EACCES; - } - - if (copy_from_user(&cmd, ucmd, sizeof(cmd))) { - dev_err(hdev->dev, "Copy command from user space to kernel space failed\n"); - return -EFAULT; - } + u32 timeout = msecs_to_jiffies(cmd->timeout_ms); - if (cmd.data_len > PAGE_SIZE) { + if (cmd->data_len > PAGE_SIZE) { dev_err(hdev->dev, "[%s] data len bigger than 4k\n", __func__); return -EFAULT; } - dev_info(hdev->dev, "[%s] opcode: 0x%x, subopcode: 0x%x, datalen: %d\n", - __func__, cmd.opcode, cmd.info_1.subopcode, cmd.data_len); - - if (cmd.addr && cmd.data_len) { - data_ptr = dma_alloc_coherent(hdev->dev, PAGE_SIZE, &data_dma, GFP_KERNEL); - if (!data_ptr) - return -ENOMEM; - - dma_dir = (cmd.opcode & 1) ? DMA_TO_DEVICE : DMA_FROM_DEVICE; + if (hdev->state != SPRAID_LIVE) { + dev_err(hdev->dev, "[%s] err, host state:[%d] is not live\n", + __func__, hdev->state); + return -EBUSY; } - if (dma_dir == DMA_TO_DEVICE) { - if (copy_from_user(data_ptr, (void __user *)(uintptr_t)cmd.addr, cmd.data_len)) { - dev_err(hdev->dev, "[%s] copy user data failed\n", __func__); - status = -EFAULT; - goto free_dma_mem; - } - } + dev_info(hdev->dev, "[%s] opcode[0x%x] subopcode[0x%x] init, datalen[%d]\n", + __func__, cmd->opcode, cmd->info_1.subopcode, cmd->data_len); memset(&ioq_cmd, 0, sizeof(ioq_cmd)); - ioq_cmd.common.opcode = cmd.opcode; - ioq_cmd.common.flags = cmd.flags; - ioq_cmd.common.hdid = cpu_to_le32(cmd.nsid); - ioq_cmd.common.sense_len = cpu_to_le16(cmd.info_0.res_sense_len); - ioq_cmd.common.cdb_len = cmd.info_0.cdb_len; - ioq_cmd.common.rsvd2 = cmd.info_0.rsvd0; - ioq_cmd.common.cdw3[0] = cpu_to_le32(cmd.cdw3); - ioq_cmd.common.cdw3[1] = cpu_to_le32(cmd.cdw4); - ioq_cmd.common.cdw3[2] = cpu_to_le32(cmd.cdw5); - ioq_cmd.common.dptr.prp1 = cpu_to_le64(data_dma); - - ioq_cmd.common.cdw10[0] = cpu_to_le32(cmd.cdw10); - ioq_cmd.common.cdw10[1] = cpu_to_le32(cmd.cdw11); - ioq_cmd.common.cdw10[2] = cpu_to_le32(cmd.cdw12); - ioq_cmd.common.cdw10[3] = cpu_to_le32(cmd.cdw13); - ioq_cmd.common.cdw10[4] = cpu_to_le32(cmd.cdw14); - ioq_cmd.common.cdw10[5] = cpu_to_le32(cmd.data_len); - - memcpy(ioq_cmd.common.cdb, &cmd.cdw16, cmd.info_0.cdb_len); - - ioq_cmd.common.cdw26[0] = cpu_to_le32(cmd.cdw26[0]); - ioq_cmd.common.cdw26[1] = cpu_to_le32(cmd.cdw26[1]); - ioq_cmd.common.cdw26[2] = cpu_to_le32(cmd.cdw26[2]); - ioq_cmd.common.cdw26[3] = cpu_to_le32(cmd.cdw26[3]); - - if (cmd.timeout_ms) - timeout = msecs_to_jiffies(cmd.timeout_ms); - timeout = timeout ? timeout : ADMIN_TIMEOUT; - - status = spraid_submit_ioq_sync_cmd(hdev, &ioq_cmd, &cmd.result0, &sense, timeout); - - if (status >= 0) { - if (put_user(cmd.result0, &ucmd->result0)) { - status = -EFAULT; - goto free_dma_mem; - } - if (put_user(cmd.result1, &ucmd->result1)) { - status = -EFAULT; - goto free_dma_mem; - } - if (dma_dir == DMA_FROM_DEVICE && - copy_to_user((void __user *)(uintptr_t)cmd.addr, data_ptr, cmd.data_len)) { - status = -EFAULT; - goto free_dma_mem; - } - } - - if (sense) { - if (copy_to_user((void *__user *)(uintptr_t)cmd.sense_addr, - sense, cmd.info_0.res_sense_len)) { - status = -EFAULT; - goto free_dma_mem; - } - } - -free_dma_mem: - if (data_ptr) - dma_free_coherent(hdev->dev, PAGE_SIZE, data_ptr, data_dma); - - return status; - -} - -static int spraid_reset_work_sync(struct spraid_dev *hdev); - -static int spraid_user_reset_cmd(struct spraid_dev *hdev) -{ - int ret; - - dev_info(hdev->dev, "[%s] start user reset cmd\n", __func__); - ret = spraid_reset_work_sync(hdev); - dev_info(hdev->dev, "[%s] stop user reset cmd[%d]\n", __func__, ret); - - return ret; -} - -static int hdev_open(struct inode *inode, struct file *file) -{ - struct spraid_dev *hdev = - container_of(inode->i_cdev, struct spraid_dev, cdev); - file->private_data = hdev; - return 0; -} - -static long hdev_ioctl(struct file *file, u32 cmd, unsigned long arg) -{ - struct spraid_dev *hdev = file->private_data; - void __user *argp = (void __user *)arg; - - switch (cmd) { - case SPRAID_IOCTL_ADMIN_CMD: - return spraid_user_admin_cmd(hdev, argp); - case SPRAID_IOCTL_IOQ_CMD: - return spraid_user_ioq_cmd(hdev, argp); - case SPRAID_IOCTL_RESET_CMD: - return spraid_user_reset_cmd(hdev); - default: - return -ENOTTY; - } -} - -static const struct file_operations spraid_dev_fops = { - .owner = THIS_MODULE, - .open = hdev_open, - .unlocked_ioctl = hdev_ioctl, - .compat_ioctl = hdev_ioctl, -}; - -static int spraid_create_cdev(struct spraid_dev *hdev) -{ - int ret; - - device_initialize(&hdev->ctrl_device); - hdev->ctrl_device.devt = MKDEV(MAJOR(spraid_chr_devt), hdev->instance); - hdev->ctrl_device.class = spraid_class; - hdev->ctrl_device.parent = hdev->dev; - dev_set_drvdata(&hdev->ctrl_device, hdev); - ret = dev_set_name(&hdev->ctrl_device, "spraid%d", hdev->instance); - if (ret) - return ret; - cdev_init(&hdev->cdev, &spraid_dev_fops); - hdev->cdev.owner = THIS_MODULE; - ret = cdev_device_add(&hdev->cdev, &hdev->ctrl_device); - if (ret) { - dev_err(hdev->dev, "Add cdev failed, ret: %d", ret); - put_device(&hdev->ctrl_device); - kfree_const(hdev->ctrl_device.kobj.name); - return ret; - } - - return 0; -} - -static inline void spraid_remove_cdev(struct spraid_dev *hdev) -{ - cdev_device_del(&hdev->cdev, &hdev->ctrl_device); -} - -static const struct blk_mq_ops spraid_admin_mq_ops = { - .queue_rq = spraid_queue_admin_rq, - .complete = spraid_complete_admin_rq, - .init_hctx = spraid_admin_init_hctx, - .init_request = spraid_admin_init_request, - .timeout = spraid_admin_timeout, -}; - -static void spraid_remove_admin_tagset(struct spraid_dev *hdev) -{ - if (hdev->admin_q && !blk_queue_dying(hdev->admin_q)) { - blk_mq_unquiesce_queue(hdev->admin_q); - blk_cleanup_queue(hdev->admin_q); - blk_mq_free_tag_set(&hdev->admin_tagset); + ioq_cmd.common.opcode = cmd->opcode; + ioq_cmd.common.flags = cmd->flags; + ioq_cmd.common.hdid = cpu_to_le32(cmd->nsid); + ioq_cmd.common.sense_len = cpu_to_le16(cmd->info_0.res_sense_len); + ioq_cmd.common.cdb_len = cmd->info_0.cdb_len; + ioq_cmd.common.rsvd2 = cmd->info_0.rsvd0; + ioq_cmd.common.cdw3[0] = cpu_to_le32(cmd->cdw3); + ioq_cmd.common.cdw3[1] = cpu_to_le32(cmd->cdw4); + ioq_cmd.common.cdw3[2] = cpu_to_le32(cmd->cdw5); + + ioq_cmd.common.cdw10[0] = cpu_to_le32(cmd->cdw10); + ioq_cmd.common.cdw10[1] = cpu_to_le32(cmd->cdw11); + ioq_cmd.common.cdw10[2] = cpu_to_le32(cmd->cdw12); + ioq_cmd.common.cdw10[3] = cpu_to_le32(cmd->cdw13); + ioq_cmd.common.cdw10[4] = cpu_to_le32(cmd->cdw14); + ioq_cmd.common.cdw10[5] = cpu_to_le32(cmd->data_len); + + memcpy(ioq_cmd.common.cdb, &cmd->cdw16, cmd->info_0.cdb_len); + + ioq_cmd.common.cdw26[0] = cpu_to_le32(cmd->cdw26[0]); + ioq_cmd.common.cdw26[1] = cpu_to_le32(cmd->cdw26[1]); + ioq_cmd.common.cdw26[2] = cpu_to_le32(cmd->cdw26[2]); + ioq_cmd.common.cdw26[3] = cpu_to_le32(cmd->cdw26[3]); + + status = spraid_bsg_map_data(hdev, job, (struct spraid_admin_command *)&ioq_cmd); + if (status) { + dev_err(hdev->dev, "[%s] err, map data failed\n", __func__); + return status; } -} -static int spraid_alloc_admin_tags(struct spraid_dev *hdev) -{ - if (!hdev->admin_q) { - hdev->admin_tagset.ops = &spraid_admin_mq_ops; - hdev->admin_tagset.nr_hw_queues = 1; + status = spraid_submit_ioq_sync_cmd(hdev, &ioq_cmd, job->reply, &job->reply_len, timeout); - hdev->admin_tagset.queue_depth = SPRAID_AQ_MQ_TAG_DEPTH; - hdev->admin_tagset.timeout = ADMIN_TIMEOUT; - hdev->admin_tagset.numa_node = hdev->numa_node; - hdev->admin_tagset.cmd_size = - spraid_cmd_size(hdev, true, false); - hdev->admin_tagset.flags = BLK_MQ_F_NO_SCHED; - hdev->admin_tagset.driver_data = hdev; + dev_info(hdev->dev, "[%s] opcode[0x%x] subopcode[0x%x], status[0x%x], reply_len[%d]\n", + __func__, cmd->opcode, cmd->info_1.subopcode, status, job->reply_len); - if (blk_mq_alloc_tag_set(&hdev->admin_tagset)) { - dev_err(hdev->dev, "Allocate admin tagset failed\n"); - return -ENOMEM; - } + spraid_bsg_unmap_data(hdev, job); - hdev->admin_q = blk_mq_init_queue(&hdev->admin_tagset); - if (IS_ERR(hdev->admin_q)) { - dev_err(hdev->dev, "Initialize admin request queue failed\n"); - blk_mq_free_tag_set(&hdev->admin_tagset); - return -ENOMEM; - } - if (!blk_get_queue(hdev->admin_q)) { - dev_err(hdev->dev, "Get admin request queue failed\n"); - spraid_remove_admin_tagset(hdev); - hdev->admin_q = NULL; - return -ENODEV; - } - } else { - blk_mq_unquiesce_queue(hdev->admin_q); - } - return 0; + return status; } static bool spraid_check_scmd_completed(struct scsi_cmnd *scmd) @@ -2891,7 +2690,7 @@ static bool spraid_check_scmd_completed(struct scsi_cmnd *scmd) spraid_get_tag_from_scmd(scmd, &hwq, &cid); spraidq = &hdev->queues[hwq]; if (READ_ONCE(iod->state) == SPRAID_CMD_COMPLETE || spraid_poll_cq(spraidq, cid)) { - dev_warn(hdev->dev, "cid[%d], qid[%d] has been completed\n", + dev_warn(hdev->dev, "cid[%d] qid[%d] has been completed\n", cid, spraidq->qid); return true; } @@ -2927,8 +2726,7 @@ static int spraid_send_abort_cmd(struct spraid_dev *hdev, u32 hdid, u16 qid, u16 admin_cmd.abort.sqid = cpu_to_le16(qid); admin_cmd.abort.cid = cpu_to_le16(cid); - return spraid_submit_admin_sync_cmd(hdev->admin_q, &admin_cmd, NULL, - NULL, 0, 0, 0, 0); + return spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); } /* send reset command by admin quueue temporary */ @@ -2941,8 +2739,7 @@ static int spraid_send_reset_cmd(struct spraid_dev *hdev, int type, u32 hdid) admin_cmd.reset.hdid = cpu_to_le32(hdid); admin_cmd.reset.type = type; - return spraid_submit_admin_sync_cmd(hdev->admin_q, &admin_cmd, NULL, - NULL, 0, 0, 0, 0); + return spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); } static bool spraid_change_host_state(struct spraid_dev *hdev, enum spraid_state newstate) @@ -3022,7 +2819,7 @@ static void spraid_back_fault_cqe(struct spraid_queue *ioq, struct spraid_comple scsi_dma_unmap(scmd); spraid_free_iod_res(hdev, iod); scmd->scsi_done(scmd); - dev_warn(hdev->dev, "Back fault CQE, cid[%d], qid[%d]\n", + dev_warn(hdev->dev, "Back fault CQE, cid[%d] qid[%d]\n", cqe->cmd_id, ioq->qid); } @@ -3032,6 +2829,8 @@ static void spraid_back_all_io(struct spraid_dev *hdev) struct spraid_queue *ioq; struct spraid_completion cqe = { 0 }; + scsi_block_requests(hdev->shost); + for (i = 1; i <= hdev->shost->nr_hw_queues; i++) { ioq = &hdev->queues[i]; for (j = 0; j < hdev->shost->can_queue; j++) { @@ -3039,6 +2838,8 @@ static void spraid_back_all_io(struct spraid_dev *hdev) spraid_back_fault_cqe(ioq, &cqe); } } + + scsi_unblock_requests(hdev->shost); } static void spraid_dev_disable(struct spraid_dev *hdev, bool shutdown) @@ -3106,17 +2907,13 @@ static void spraid_reset_work(struct work_struct *work) if (ret) goto pci_disable; - ret = spraid_alloc_admin_tags(hdev); - if (ret) - goto pci_disable; - ret = spraid_setup_io_queues(hdev); if (ret || hdev->online_queues <= hdev->shost->nr_hw_queues) goto pci_disable; spraid_change_host_state(hdev, SPRAID_LIVE); - spraid_send_aen(hdev); + spraid_send_all_aen(hdev); return; @@ -3174,8 +2971,8 @@ static int spraid_abort_handler(struct scsi_cmnd *scmd) scsi_print_command(scmd); - if (!spraid_wait_abnl_cmd_done(iod) || spraid_check_scmd_completed(scmd) || - hdev->state != SPRAID_LIVE) + if (hdev->state != SPRAID_LIVE || !spraid_wait_abnl_cmd_done(iod) || + spraid_check_scmd_completed(scmd)) return SUCCESS; hostdata = scmd->device->hostdata; @@ -3206,8 +3003,8 @@ static int spraid_tgt_reset_handler(struct scsi_cmnd *scmd) scsi_print_command(scmd); - if (!spraid_wait_abnl_cmd_done(iod) || spraid_check_scmd_completed(scmd) || - hdev->state != SPRAID_LIVE) + if (hdev->state != SPRAID_LIVE || !spraid_wait_abnl_cmd_done(iod) || + spraid_check_scmd_completed(scmd)) return SUCCESS; hostdata = scmd->device->hostdata; @@ -3241,8 +3038,8 @@ static int spraid_bus_reset_handler(struct scsi_cmnd *scmd) scsi_print_command(scmd); - if (!spraid_wait_abnl_cmd_done(iod) || spraid_check_scmd_completed(scmd) || - hdev->state != SPRAID_LIVE) + if (hdev->state != SPRAID_LIVE || !spraid_wait_abnl_cmd_done(iod) || + spraid_check_scmd_completed(scmd)) return SUCCESS; hostdata = scmd->device->hostdata; @@ -3272,7 +3069,7 @@ static int spraid_shost_reset_handler(struct scsi_cmnd *scmd) struct spraid_dev *hdev = shost_priv(scmd->device->host); scsi_print_command(scmd); - if (spraid_check_scmd_completed(scmd) || hdev->state != SPRAID_LIVE) + if (hdev->state != SPRAID_LIVE || spraid_check_scmd_completed(scmd)) return SUCCESS; spraid_get_tag_from_scmd(scmd, &hwq, &cid); @@ -3288,6 +3085,62 @@ static int spraid_shost_reset_handler(struct scsi_cmnd *scmd) return SUCCESS; } +static pci_ers_result_t spraid_pci_error_detected(struct pci_dev *pdev, + pci_channel_state_t state) +{ + struct spraid_dev *hdev = pci_get_drvdata(pdev); + + dev_info(hdev->dev, "enter pci error detect, state:%d\n", state); + + switch (state) { + case pci_channel_io_normal: + dev_warn(hdev->dev, "channel is normal, do nothing\n"); + + return PCI_ERS_RESULT_CAN_RECOVER; + case pci_channel_io_frozen: + dev_warn(hdev->dev, "channel io frozen, need reset controller\n"); + + scsi_block_requests(hdev->shost); + + spraid_change_host_state(hdev, SPRAID_RESETTING); + + return PCI_ERS_RESULT_NEED_RESET; + case pci_channel_io_perm_failure: + dev_warn(hdev->dev, "channel io failure, request disconnect\n"); + + return PCI_ERS_RESULT_DISCONNECT; + } + + return PCI_ERS_RESULT_NEED_RESET; +} + +static pci_ers_result_t spraid_pci_slot_reset(struct pci_dev *pdev) +{ + struct spraid_dev *hdev = pci_get_drvdata(pdev); + + dev_info(hdev->dev, "restart after slot reset\n"); + + pci_restore_state(pdev); + + if (!queue_work(spraid_wq, &hdev->reset_work)) { + dev_err(hdev->dev, "[%s] err, the device is resetting state\n", __func__); + return PCI_ERS_RESULT_NONE; + } + + flush_work(&hdev->reset_work); + + scsi_unblock_requests(hdev->shost); + + return PCI_ERS_RESULT_RECOVERED; +} + +static void spraid_reset_done(struct pci_dev *pdev) +{ + struct spraid_dev *hdev = pci_get_drvdata(pdev); + + dev_info(hdev->dev, "enter spraid reset done\n"); +} + static ssize_t csts_pp_show(struct device *cdev, struct device_attribute *attr, char *buf) { struct Scsi_Host *shost = class_to_shost(cdev); @@ -3347,7 +3200,7 @@ static ssize_t fw_version_show(struct device *cdev, struct device_attribute *att struct Scsi_Host *shost = class_to_shost(cdev); struct spraid_dev *hdev = shost_priv(shost); - return snprintf(buf, sizeof(hdev->ctrl_info->fr), "%s\n", hdev->ctrl_info->fr); + return snprintf(buf, PAGE_SIZE, "%s\n", hdev->ctrl_info->fr); } static DEVICE_ATTR_RO(csts_pp); @@ -3365,6 +3218,185 @@ static struct device_attribute *spraid_host_attrs[] = { NULL, }; +static int spraid_get_vd_info(struct spraid_dev *hdev, struct spraid_vd_info *vd_info, u16 vid) +{ + struct spraid_admin_command admin_cmd; + u8 *data_ptr = NULL; + dma_addr_t data_dma = 0; + int ret; + + data_ptr = dma_alloc_coherent(hdev->dev, PAGE_SIZE, &data_dma, GFP_KERNEL); + if (!data_ptr) + return -ENOMEM; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.usr_cmd.opcode = USR_CMD_READ; + admin_cmd.usr_cmd.info_0.subopcode = cpu_to_le16(USR_CMD_VDINFO); + admin_cmd.usr_cmd.info_1.data_len = cpu_to_le16(USR_CMD_RDLEN); + admin_cmd.usr_cmd.info_1.param_len = cpu_to_le16(VDINFO_PARAM_LEN); + admin_cmd.usr_cmd.cdw10 = cpu_to_le32(vid); + admin_cmd.common.dptr.prp1 = cpu_to_le64(data_dma); + + ret = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); + if (!ret) + memcpy(vd_info, data_ptr, sizeof(struct spraid_vd_info)); + + dma_free_coherent(hdev->dev, PAGE_SIZE, data_ptr, data_dma); + + return ret; +} + +static int spraid_get_bgtask(struct spraid_dev *hdev, struct spraid_bgtask *bgtask) +{ + struct spraid_admin_command admin_cmd; + u8 *data_ptr = NULL; + dma_addr_t data_dma = 0; + int ret; + + data_ptr = dma_alloc_coherent(hdev->dev, PAGE_SIZE, &data_dma, GFP_KERNEL); + if (!data_ptr) + return -ENOMEM; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.usr_cmd.opcode = USR_CMD_READ; + admin_cmd.usr_cmd.info_0.subopcode = cpu_to_le16(USR_CMD_BGTASK); + admin_cmd.usr_cmd.info_1.data_len = cpu_to_le16(USR_CMD_RDLEN); + admin_cmd.common.dptr.prp1 = cpu_to_le64(data_dma); + + ret = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); + if (!ret) + memcpy(bgtask, data_ptr, sizeof(struct spraid_bgtask)); + + dma_free_coherent(hdev->dev, PAGE_SIZE, data_ptr, data_dma); + + return ret; +} + +static ssize_t raid_level_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct scsi_device *sdev; + struct spraid_dev *hdev; + struct spraid_vd_info *vd_info; + struct spraid_sdev_hostdata *hostdata; + int ret; + + sdev = to_scsi_device(dev); + hdev = shost_priv(sdev->host); + hostdata = sdev->hostdata; + + vd_info = kmalloc(sizeof(*vd_info), GFP_KERNEL); + if (!vd_info || !SPRAID_DEV_INFO_ATTR_VD(hostdata->attr)) + return snprintf(buf, PAGE_SIZE, "NA\n"); + + ret = spraid_get_vd_info(hdev, vd_info, sdev->id); + if (ret) + vd_info->rg_level = ARRAY_SIZE(raid_levels) - 1; + + ret = (vd_info->rg_level < ARRAY_SIZE(raid_levels)) ? + vd_info->rg_level : (ARRAY_SIZE(raid_levels) - 1); + + kfree(vd_info); + + return snprintf(buf, PAGE_SIZE, "RAID-%s\n", raid_levels[ret]); +} + +static ssize_t raid_state_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct scsi_device *sdev; + struct spraid_dev *hdev; + struct spraid_vd_info *vd_info; + struct spraid_sdev_hostdata *hostdata; + int ret; + + sdev = to_scsi_device(dev); + hdev = shost_priv(sdev->host); + hostdata = sdev->hostdata; + + vd_info = kmalloc(sizeof(*vd_info), GFP_KERNEL); + if (!vd_info || !SPRAID_DEV_INFO_ATTR_VD(hostdata->attr)) + return snprintf(buf, PAGE_SIZE, "NA\n"); + + ret = spraid_get_vd_info(hdev, vd_info, sdev->id); + if (ret) { + vd_info->vd_status = 0; + vd_info->rg_id = 0xff; + } + + ret = (vd_info->vd_status < ARRAY_SIZE(raid_states)) ? vd_info->vd_status : 0; + + kfree(vd_info); + + return snprintf(buf, PAGE_SIZE, "%s\n", raid_states[ret]); +} + +static ssize_t raid_resync_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct scsi_device *sdev; + struct spraid_dev *hdev; + struct spraid_vd_info *vd_info; + struct spraid_bgtask *bgtask; + struct spraid_sdev_hostdata *hostdata; + u8 rg_id, i, progress = 0; + int ret; + + sdev = to_scsi_device(dev); + hdev = shost_priv(sdev->host); + hostdata = sdev->hostdata; + + vd_info = kmalloc(sizeof(*vd_info), GFP_KERNEL); + if (!vd_info || !SPRAID_DEV_INFO_ATTR_VD(hostdata->attr)) + return snprintf(buf, PAGE_SIZE, "NA\n"); + + ret = spraid_get_vd_info(hdev, vd_info, sdev->id); + if (ret) + goto out; + + rg_id = vd_info->rg_id; + + bgtask = (struct spraid_bgtask *)vd_info; + ret = spraid_get_bgtask(hdev, bgtask); + if (ret) + goto out; + for (i = 0; i < bgtask->task_num; i++) { + if ((bgtask->bgtask[i].type == BGTASK_TYPE_REBUILD) && + (le16_to_cpu(bgtask->bgtask[i].vd_id) == rg_id)) + progress = bgtask->bgtask[i].progress; + } + +out: + kfree(vd_info); + return snprintf(buf, PAGE_SIZE, "%d\n", progress); +} + +static DEVICE_ATTR_RO(raid_level); +static DEVICE_ATTR_RO(raid_state); +static DEVICE_ATTR_RO(raid_resync); + +static struct device_attribute *spraid_dev_attrs[] = { + &dev_attr_raid_level, + &dev_attr_raid_state, + &dev_attr_raid_resync, + NULL, +}; + +static struct pci_error_handlers spraid_err_handler = { + .error_detected = spraid_pci_error_detected, + .slot_reset = spraid_pci_slot_reset, + .reset_done = spraid_reset_done, +}; + +static int spraid_sysfs_host_reset(struct Scsi_Host *shost, int reset_type) +{ + int ret; + struct spraid_dev *hdev = shost_priv(shost); + + dev_info(hdev->dev, "[%s] start sysfs host reset cmd\n", __func__); + ret = spraid_reset_work_sync(hdev); + dev_info(hdev->dev, "[%s] stop sysfs host reset cmd[%d]\n", __func__, ret); + + return ret; +} + static struct scsi_host_template spraid_driver_template = { .module = THIS_MODULE, .name = "Ramaxel Logic spraid driver", @@ -3379,9 +3411,11 @@ static struct scsi_host_template spraid_driver_template = { .eh_bus_reset_handler = spraid_bus_reset_handler, .eh_host_reset_handler = spraid_shost_reset_handler, .change_queue_depth = scsi_change_queue_depth, - .host_tagset = 1, + .host_tagset = 0, .this_id = -1, .shost_attrs = spraid_host_attrs, + .sdev_attrs = spraid_dev_attrs, + .host_reset = spraid_sysfs_host_reset, }; static void spraid_shutdown(struct pci_dev *pdev) @@ -3392,11 +3426,53 @@ static void spraid_shutdown(struct pci_dev *pdev) spraid_disable_admin_queue(hdev, true); } +/* bsg dispatch user command */ +static int spraid_bsg_host_dispatch(struct bsg_job *job) +{ + struct Scsi_Host *shost = dev_to_shost(job->dev); + struct spraid_dev *hdev = shost_priv(shost); + struct request *rq = blk_mq_rq_from_pdu(job); + struct spraid_bsg_request *bsg_req = job->request; + int ret = 0; + + dev_info(hdev->dev, "[%s] msgcode[%d], msglen[%d], timeout[%d], req_nsge[%d], req_len[%d]\n", + __func__, bsg_req->msgcode, job->request_len, rq->timeout, + job->request_payload.sg_cnt, job->request_payload.payload_len); + + job->reply_len = 0; + + switch (bsg_req->msgcode) { + case SPRAID_BSG_ADM: + ret = spraid_user_admin_cmd(hdev, job); + break; + case SPRAID_BSG_IOQ: + ret = spraid_user_ioq_cmd(hdev, job); + break; + default: + dev_info(hdev->dev, "[%s] unsupport msgcode[%d]\n", __func__, bsg_req->msgcode); + break; + } + + if (ret > 0) + ret = ret | (ret << 8); + + bsg_job_done(job, ret, 0); + return 0; +} + +static inline void spraid_remove_bsg(struct spraid_dev *hdev) +{ + if (hdev->bsg_queue) { + bsg_unregister_queue(hdev->bsg_queue); + blk_cleanup_queue(hdev->bsg_queue); + } +} static int spraid_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct spraid_dev *hdev; struct Scsi_Host *shost; int node, ret; + char bsg_name[15]; shost = scsi_host_alloc(&spraid_driver_template, sizeof(*hdev)); if (!shost) { @@ -3421,10 +3497,10 @@ static int spraid_probe(struct pci_dev *pdev, const struct pci_device_id *id) goto put_dev; init_rwsem(&hdev->devices_rwsem); - INIT_WORK(&hdev->aen_work, spraid_async_event_work); INIT_WORK(&hdev->scan_work, spraid_scan_work); INIT_WORK(&hdev->timesyn_work, spraid_timesyn_work); INIT_WORK(&hdev->reset_work, spraid_reset_work); + INIT_WORK(&hdev->fw_act_work, spraid_fw_act_work); spin_lock_init(&hdev->state_lock); ret = spraid_alloc_resources(hdev); @@ -3439,17 +3515,13 @@ static int spraid_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (ret) goto pci_disable; - ret = spraid_alloc_admin_tags(hdev); - if (ret) - goto disable_admin_q; - ret = spraid_init_ctrl_info(hdev); if (ret) - goto free_admin_tagset; + goto disable_admin_q; ret = spraid_alloc_iod_ext_mem_pool(hdev); if (ret) - goto free_admin_tagset; + goto disable_admin_q; ret = spraid_setup_io_queues(hdev); if (ret) @@ -3464,9 +3536,15 @@ static int spraid_probe(struct pci_dev *pdev, const struct pci_device_id *id) goto remove_io_queues; } - ret = spraid_create_cdev(hdev); - if (ret) + snprintf(bsg_name, sizeof(bsg_name), "spraid%d", shost->host_no); + hdev->bsg_queue = bsg_setup_queue(&shost->shost_gendev, bsg_name, + spraid_bsg_host_dispatch, NULL, + spraid_cmd_size(hdev, true, false)); + if (IS_ERR(hdev->bsg_queue)) { + dev_err(hdev->dev, "err, setup bsg failed\n"); + hdev->bsg_queue = NULL; goto remove_io_queues; + } if (hdev->online_queues == SPRAID_ADMIN_QUEUE_NUM) { dev_warn(hdev->dev, "warn only admin queue can be used\n"); @@ -3475,11 +3553,11 @@ static int spraid_probe(struct pci_dev *pdev, const struct pci_device_id *id) hdev->state = SPRAID_LIVE; - spraid_send_aen(hdev); + spraid_send_all_aen(hdev); ret = spraid_dev_list_init(hdev); if (ret) - goto remove_cdev; + goto remove_bsg; ret = spraid_configure_timestamp(hdev); if (ret) @@ -3487,20 +3565,18 @@ static int spraid_probe(struct pci_dev *pdev, const struct pci_device_id *id) ret = spraid_alloc_ioq_ptcmds(hdev); if (ret) - goto remove_cdev; + goto remove_bsg; scsi_scan_host(hdev->shost); return 0; -remove_cdev: - spraid_remove_cdev(hdev); +remove_bsg: + spraid_remove_bsg(hdev); remove_io_queues: spraid_remove_io_queues(hdev); free_iod_mempool: spraid_free_iod_ext_mem_pool(hdev); -free_admin_tagset: - spraid_remove_admin_tagset(hdev); disable_admin_q: spraid_disable_admin_queue(hdev, false); pci_disable: @@ -3524,22 +3600,17 @@ static void spraid_remove(struct pci_dev *pdev) dev_info(hdev->dev, "enter spraid remove\n"); spraid_change_host_state(hdev, SPRAID_DELETING); + flush_work(&hdev->reset_work); - if (!pci_device_is_present(pdev)) { - scsi_block_requests(shost); + if (!pci_device_is_present(pdev)) spraid_back_all_io(hdev); - scsi_unblock_requests(shost); - } - flush_work(&hdev->reset_work); + spraid_remove_bsg(hdev); scsi_remove_host(shost); - - kfree(hdev->ioq_ptcmds); + spraid_free_ioq_ptcmds(hdev); kfree(hdev->devices); - spraid_remove_cdev(hdev); spraid_remove_io_queues(hdev); spraid_free_iod_ext_mem_pool(hdev); - spraid_remove_admin_tagset(hdev); spraid_disable_admin_queue(hdev, false); spraid_pci_disable(hdev); spraid_free_resources(hdev); @@ -3551,7 +3622,7 @@ static void spraid_remove(struct pci_dev *pdev) } static const struct pci_device_id spraid_id_table[] = { - { PCI_DEVICE(PCI_VENDOR_ID_RAMAXEL_LOGIC, SPRAID_SERVER_DEVICE_HAB_DID) }, + { PCI_DEVICE(PCI_VENDOR_ID_RAMAXEL_LOGIC, SPRAID_SERVER_DEVICE_HBA_DID) }, { PCI_DEVICE(PCI_VENDOR_ID_RAMAXEL_LOGIC, SPRAID_SERVER_DEVICE_RAID_DID) }, { 0, } }; @@ -3563,6 +3634,7 @@ static struct pci_driver spraid_driver = { .probe = spraid_probe, .remove = spraid_remove, .shutdown = spraid_shutdown, + .err_handler = &spraid_err_handler, }; static int __init spraid_init(void) @@ -3573,14 +3645,10 @@ static int __init spraid_init(void) if (!spraid_wq) return -ENOMEM; - ret = alloc_chrdev_region(&spraid_chr_devt, 0, SPRAID_MINORS, "spraid"); - if (ret < 0) - goto destroy_wq; - spraid_class = class_create(THIS_MODULE, "spraid"); if (IS_ERR(spraid_class)) { ret = PTR_ERR(spraid_class); - goto unregister_chrdev; + goto destroy_wq; } ret = pci_register_driver(&spraid_driver); @@ -3591,8 +3659,6 @@ static int __init spraid_init(void) destroy_class: class_destroy(spraid_class); -unregister_chrdev: - unregister_chrdev_region(spraid_chr_devt, SPRAID_MINORS); destroy_wq: destroy_workqueue(spraid_wq); @@ -3603,12 +3669,11 @@ static void __exit spraid_exit(void) { pci_unregister_driver(&spraid_driver); class_destroy(spraid_class); - unregister_chrdev_region(spraid_chr_devt, SPRAID_MINORS); destroy_workqueue(spraid_wq); ida_destroy(&spraid_instance_ida); } -MODULE_AUTHOR("Ramaxel Memory Technology"); +MODULE_AUTHOR("songyl(a)ramaxel.com"); MODULE_DESCRIPTION("Ramaxel Memory Technology SPraid Driver"); MODULE_LICENSE("GPL"); MODULE_VERSION(SPRAID_DRV_VERSION); -- 2.27.0

1 0

[PATCH openEuler-1.0-LTS v2 01/10] arm64: mm: Restore mm_cpumask (revert commit 38d96287504a ("arm64: mm: kill mm_cpumask usage"))
by Yang Yingliang 20 Dec '21

20 Dec '21

From: Takao Indoh <indou.takao(a)fujitsu.com> hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4BLL0 CVE: NA --------------------------- mm_cpumask was deleted by the commit 38d96287504a ("arm64: mm: kill mm_cpumask usage") because it was not used at that time. Now this is needed to find appropriate CPUs for TLB flush, so this patch reverts this commit. Signed-off-by: QI Fuli <qi.fuli(a)fujitsu.com> Signed-off-by: Takao Indoh <indou.takao(a)fujitsu.com> Signed-off-by: Cheng Jian <cj.chengjian(a)huawei.com> Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/arm64/kernel/smp.c | 6 ++++++ arch/arm64/mm/context.c | 2 ++ 2 files changed, 8 insertions(+) diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index fe562778de352..e86940d353a3e 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -387,6 +387,7 @@ asmlinkage notrace void secondary_start_kernel(void) */ mmgrab(mm); current->active_mm = mm; + cpumask_set_cpu(cpu, mm_cpumask(mm)); /* * TTBR0 is only used for the identity mapping at this stage. Make it @@ -489,6 +490,11 @@ int __cpu_disable(void) */ irq_migrate_all_off_this_cpu(); + /* + * Remove this CPU from the vm mask set of all processes. + */ + clear_tasks_mm_cpumask(cpu); + return 0; } diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c index 2b80ceff5d6c2..27d1f3fec1cc9 100644 --- a/arch/arm64/mm/context.c +++ b/arch/arm64/mm/context.c @@ -207,6 +207,7 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu) set_asid: __set_bit(asid, asid_map); cur_idx = asid; + cpumask_clear(mm_cpumask(mm)); return idx2asid(asid) | generation; } @@ -254,6 +255,7 @@ void check_and_switch_context(struct mm_struct *mm, unsigned int cpu) switch_mm_fastpath: arm64_apply_bp_hardening(); + cpumask_set_cpu(cpu, mm_cpumask(mm)); /* * Defer TTBR0_EL1 setting for user threads to uaccess_enable() when -- 2.25.1

1 9

[PATCH openEuler-1.0-LTS 1/2] audit: improve robustness of the audit queue handling
by Yang Yingliang 20 Dec '21

20 Dec '21

From: Paul Moore <paul(a)paul-moore.com> hulk inclusion category: bugfix bugzilla: 185904, https://gitee.com/openeuler/kernel/issues/I4NAZN CVE: NA Reference: https://patchwork.kernel.org/project/linux-audit/patch/163942029335.62691.7… ------------------------------------------------------------------- If the audit daemon were ever to get stuck in a stopped state the kernel's kauditd_thread() could get blocked attempting to send audit records to the userspace audit daemon. With the kernel thread blocked it is possible that the audit queue could grow unbounded as certain audit record generating events must be exempt from the queue limits else the system enter a deadlock state. This patch resolves this problem by lowering the kernel thread's socket sending timeout from MAX_SCHEDULE_TIMEOUT to HZ/10 and tweaks the kauditd_send_queue() function to better manage the various audit queues when connection problems occur between the kernel and the audit daemon. With this patch, the backlog may temporarily grow beyond the defined limits when the audit daemon is stopped and the system is under heavy audit pressure, but kauditd_thread() will continue to make progress and drain the queues as it would for other connection problems. For example, with the audit daemon put into a stopped state and the system configured to audit every syscall it was still possible to shutdown the system without a kernel panic, deadlock, etc.; granted, the system was slow to shutdown but that is to be expected given the extreme pressure of recording every syscall. The timeout value of HZ/10 was chosen primarily through experimentation and this developer's "gut feeling". There is likely no one perfect value, but as this scenario is limited in scope (root privileges would be needed to send SIGSTOP to the audit daemon), it is likely not worth exposing this as a tunable at present. This can always be done at a later date if it proves necessary. Cc: stable(a)vger.kernel.org Fixes: 5b52330bbfe63 ("audit: fix auditd/kernel connection state tracking") Reported-by: Gaosheng Cui <cuigaosheng1(a)huawei.com> Tested-by: Gaosheng Cui <cuigaosheng1(a)huawei.com> Reviewed-by: Richard Guy Briggs <rgb(a)redhat.com> Signed-off-by: Paul Moore <paul(a)paul-moore.com> Signed-off-by: Cui GaoSheng <cuigaosheng1(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- kernel/audit.c | 21 ++++++++++----------- 1 file changed, 10 insertions(+), 11 deletions(-) diff --git a/kernel/audit.c b/kernel/audit.c index 45741c3c48a47..968921d376b98 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -726,7 +726,7 @@ static int kauditd_send_queue(struct sock *sk, u32 portid, { int rc = 0; struct sk_buff *skb; - static unsigned int failed = 0; + unsigned int failed = 0; /* NOTE: kauditd_thread takes care of all our locking, we just use * the netlink info passed to us (e.g. sk and portid) */ @@ -743,32 +743,30 @@ static int kauditd_send_queue(struct sock *sk, u32 portid, continue; } +retry: /* grab an extra skb reference in case of error */ skb_get(skb); rc = netlink_unicast(sk, skb, portid, 0); if (rc < 0) { - /* fatal failure for our queue flush attempt? */ + /* send failed - try a few times unless fatal error */ if (++failed >= retry_limit || rc == -ECONNREFUSED || rc == -EPERM) { - /* yes - error processing for the queue */ sk = NULL; if (err_hook) (*err_hook)(skb); - if (!skb_hook) - goto out; - /* keep processing with the skb_hook */ + if (rc == -EAGAIN) + rc = 0; + /* continue to drain the queue */ continue; } else - /* no - requeue to preserve ordering */ - skb_queue_head(queue, skb); + goto retry; } else { - /* it worked - drop the extra reference and continue */ + /* skb sent - drop the extra reference and continue */ consume_skb(skb); failed = 0; } } -out: return (rc >= 0 ? 0 : rc); } @@ -1557,7 +1555,8 @@ static int __net_init audit_net_init(struct net *net) audit_panic("cannot initialize netlink socket in namespace"); return -ENOMEM; } - aunet->sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT; + /* limit the timeout in case auditd is blocked/stopped */ + aunet->sk->sk_sndtimeo = HZ / 10; return 0; } -- 2.25.1

1 1

[PATCH openEuler-1.0-LTS v11 00/35] support psi feature
by Liu Xinpeng 19 Dec '21

19 Dec '21

backport psi feature and avoid kabi change bugzilla: https://gitee.com/openeuler/kernel/issues/I47QS2 Changes since v9: 1.Third-party kernel modules should not use struct cgroup, to avoid kabi changes by __GENKSYMS__, from Xie Xiuqi. Baruch Siach (1): psi: fix reference to kernel commandline enable Dan Schatzberg (1): kernel/sched/psi.c: expose pressure metrics on root cgroup Jason Xing (1): psi: get poll_work to run when calling poll syscall next time Johannes Weiner (14): mm: workingset: tell cache transitions from workingset thrashing sched: loadavg: consolidate LOAD_INT, LOAD_FRAC, CALC_LOAD sched: loadavg: make calc_load_n() public sched: sched.h: make rq locking and clock functions available in stats.h sched: introduce this_rq_lock_irq() psi: pressure stall information for CPU, memory, and IO psi: cgroup support psi: make disabling/enabling easier for vendor kernels psi: fix aggregation idle shut-off psi: avoid divide-by-zero crash inside virtual machines fs: kernfs: add poll file operation kernel: cgroup: add poll file operation sched/psi: Fix sampling error and rare div0 crashes with cgroups and high uptime psi: Fix a division error in psi poll() Josef Bacik (1): blk-iolatency: use a percentile approache for ssd's Liu Xinpeng (2): psi:enable psi in config psi:avoid kabi change Miklos Szeredi (1): fuse: ignore PG_workingset after stealing Miles Chen (1): sched/psi: Correct overly pessimistic size calculation Odin Ugedal (1): cgroup: fix psi monitor for root cgroup Olof Johansson (1): kernel/sched/psi.c: simplify cgroup_move_task() Peter Zijlstra (1): sched/psi: Reduce psimon FIFO priority Suren Baghdasaryan (9): psi: introduce state_mask to represent stalled psi states psi: make psi_enable static psi: rename psi fields in preparation for psi trigger addition psi: split update_stats into parts psi: track changed states include/: refactor headers to allow kthread.h inclusion in psi_types.h psi: introduce psi monitor sched/psi: Do not require setsched permission from the sched/psi: Fix OOB write when writing 0 bytes to PSI files Yafang Shao (1): mm, memcg: add workingset_restore in memory.stat Documentation/accounting/psi.txt | 180 ++++ Documentation/admin-guide/cgroup-v2.rst | 22 + Documentation/admin-guide/kernel-parameters.txt | 4 + arch/arm64/configs/openeuler_defconfig | 2 + arch/powerpc/platforms/cell/cpufreq_spudemand.c | 2 +- arch/powerpc/platforms/cell/spufs/sched.c | 9 +- arch/s390/appldata/appldata_os.c | 4 - arch/x86/configs/openeuler_defconfig | 2 + block/blk-iolatency.c | 183 +++- drivers/cpuidle/governors/menu.c | 4 - drivers/spi/spi-rockchip.c | 1 + fs/fuse/dev.c | 1 + fs/kernfs/file.c | 31 +- fs/proc/loadavg.c | 3 - include/linux/cgroup-defs.h | 11 + include/linux/cgroup.h | 15 + include/linux/kernfs.h | 8 + include/linux/kthread.h | 4 + include/linux/page-flags.h | 5 + include/linux/psi.h | 65 ++ include/linux/psi_types.h | 173 +++ include/linux/sched.h | 13 + include/linux/sched/loadavg.h | 24 +- include/linux/swap.h | 1 + include/trace/events/mmflags.h | 1 + init/Kconfig | 28 + kernel/cgroup/cgroup.c | 131 ++- kernel/debug/kdb/kdb_main.c | 7 +- kernel/fork.c | 4 + kernel/kthread.c | 1 + kernel/sched/Makefile | 1 + kernel/sched/core.c | 16 +- kernel/sched/loadavg.c | 139 ++- kernel/sched/psi.c | 1292 +++++++++++++++++++++++ kernel/sched/sched.h | 178 ++-- kernel/sched/stats.h | 86 ++ kernel/workqueue.c | 23 + kernel/workqueue_internal.h | 6 +- mm/compaction.c | 5 + mm/filemap.c | 20 +- mm/huge_memory.c | 1 + mm/migrate.c | 2 + mm/page_alloc.c | 9 + mm/swap_state.c | 1 + mm/vmscan.c | 10 + mm/workingset.c | 113 +- 46 files changed, 2562 insertions(+), 279 deletions(-) create mode 100644 Documentation/accounting/psi.txt create mode 100644 include/linux/psi.h create mode 100644 include/linux/psi_types.h create mode 100644 kernel/sched/psi.c -- 1.8.3.1

1 35

[PATCH openEuler-1.0-LTS] block/wbt: fix negative inflight counter when remove scsi device
by Yang Yingliang 18 Dec '21

18 Dec '21

From: Laibin Qiu <qiulaibin(a)huawei.com> hulk inclusion category: bugfix bugzilla: 185857 CVE: NA -------------------------------- Now that we disable wbt by set WBT_STATE_OFF_DEFAULT in wbt_disable_default() when switch elevator to bfq. And when we remove scsi device, wbt will be enabled by wbt_enable_default. If it become false positive between wbt_wait() and wbt_track() when submit write request. The following is the scenario that triggered the problem. T1 T2 T3 elevator_switch_mq bfq_init_queue wbt_disable_default <= Set rwb->enable_state (OFF) Submit_bio blk_mq_make_request rq_qos_throttle <= rwb->enable_state (OFF) scsi_remove_device sd_remove del_gendisk blk_unregister_queue elv_unregister_queue wbt_enable_default <= Set rwb->enable_state (ON) q_qos_track <= rwb->enable_state (ON) ^^^^^^ this request will mark WBT_TRACKED without inflight add and will lead to drop rqw->inflight to -1 in wbt_done() which will trigger IO hung. Fix this by move wbt_enable_default() from elv_unregister to bfq_exit_queue(). Only re-enable wbt when bfq exit. Fixes: 76a8040817b4b ("blk-wbt: make sure throttle is enabled properly") confilct: block/elevator.c Signed-off-by: Laibin Qiu <qiulaibin(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- block/bfq-iosched.c | 4 ++++ block/elevator.c | 2 -- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 9078299ffe3da..fe4255698d810 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -5381,6 +5381,7 @@ static void bfq_exit_queue(struct elevator_queue *e) { struct bfq_data *bfqd = e->elevator_data; struct bfq_queue *bfqq, *n; + struct request_queue *q = bfqd->queue; hrtimer_cancel(&bfqd->idle_slice_timer); @@ -5404,6 +5405,9 @@ static void bfq_exit_queue(struct elevator_queue *e) #endif kfree(bfqd); + + /* Re-enable throttling in case elevator disabled it */ + wbt_enable_default(q); } static void bfq_init_root_group(struct bfq_group *root_group, diff --git a/block/elevator.c b/block/elevator.c index 70ea9f3e64d7e..9621a812319e7 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -876,8 +876,6 @@ void elv_unregister_queue(struct request_queue *q) kobject_uevent(&e->kobj, KOBJ_REMOVE); kobject_del(&e->kobj); e->registered = 0; - /* Re-enable throttling in case elevator disabled it */ - wbt_enable_default(q); } } -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] nbd: Fix use-after-free in blk_mq_free_rqs
by Yang Yingliang 18 Dec '21

18 Dec '21

From: Ye Bin <yebin10(a)huawei.com> hulk inclusion category: bugfix bugzilla: 185875 CVE: NA ----------------------------------------------- We got issue as follows: [ 833.786542] nbd: failed to add new device [ 833.791613] ================================================================== [ 833.794918] BUG: KASAN: use-after-free in blk_mq_free_rqs+0x558/0x6c0 [ 833.798108] Read of size 8 at addr ffff800109b7c288 by task kworker/0:3/113 [ 833.804216] CPU: 0 PID: 113 Comm: kworker/0:3 Kdump: loaded Not tainted 4.19.90 #1 [ 833.807635] Hardware name: QEMU KVM Virtual Machine, BIOS 0.0.0 02/06/2015 [ 833.811798] Workqueue: events __blk_release_queue [ 833.815035] Call trace: [ 833.817964] dump_backtrace+0x0/0x3c0 [ 833.821070] show_stack+0x28/0x38 [ 833.824091] dump_stack+0xfc/0x154 [ 833.827042] print_address_description+0x68/0x278 [ 833.830147] kasan_report+0x204/0x330 [ 833.833121] __asan_report_load8_noabort+0x30/0x40 [ 833.836180] blk_mq_free_rqs+0x558/0x6c0 [ 833.839089] blk_mq_sched_tags_teardown+0xf4/0x1c0 [ 833.842035] blk_mq_exit_sched+0x1b8/0x260 [ 833.844878] elevator_exit+0x114/0x148 [ 833.847634] blk_exit_queue+0x68/0xe8 [ 833.850352] __blk_release_queue+0xd0/0x408 [ 833.853113] process_one_work+0x55c/0x10d0 [ 833.855864] worker_thread+0x3d4/0xe30 [ 833.858558] kthread+0x2c8/0x348 [ 833.861139] ret_from_fork+0x10/0x18 [ 833.863714] [ 833.866000] Allocated by task 186531: [ 833.868467] kasan_kmalloc+0xe0/0x190 [ 833.870936] kmem_cache_alloc_trace+0x104/0x218 [ 833.873483] nbd_dev_add+0x54/0x760 [nbd] [ 833.875988] nbd_genl_connect+0x3c4/0x1348 [nbd] [ 833.878591] genl_family_rcv_msg+0x798/0xa10 [ 833.881113] genl_rcv_msg+0xc0/0x170 [ 833.883489] netlink_rcv_skb+0x1b4/0x370 [ 833.885897] genl_rcv+0x40/0x58 [ 833.888225] netlink_unicast+0x4bc/0x660 [ 833.890661] netlink_sendmsg+0x880/0xa60 [ 833.893112] sock_sendmsg+0xb8/0x110 [ 833.895513] ____sys_sendmsg+0x570/0x698 [ 833.897927] ___sys_sendmsg+0x108/0x188 [ 833.900350] __sys_sendmsg+0xe8/0x198 [ 833.900360] __arm64_sys_sendmsg+0x78/0xa8 [ 833.906911] el0_svc_common+0x10c/0x330 [ 833.909289] el0_svc_handler+0x60/0xd0 [ 833.911660] el0_svc+0x8/0x1b0 [ 833.913963] [ 833.916117] Freed by task 186531: [ 833.918445] __kasan_slab_free+0x120/0x228 [ 833.920860] kasan_slab_free+0x10/0x18 [ 833.923193] kfree+0x80/0x1f0 [ 833.925392] nbd_dev_add+0xf0/0x760 [nbd] [ 833.927686] nbd_genl_connect+0x3c4/0x1348 [nbd] [ 833.929989] genl_family_rcv_msg+0x798/0xa10 [ 833.932231] genl_rcv_msg+0xc0/0x170 [ 833.934335] netlink_rcv_skb+0x1b4/0x370 [ 833.936444] genl_rcv+0x40/0x58 [ 833.938460] netlink_unicast+0x4bc/0x660 [ 833.940570] netlink_sendmsg+0x880/0xa60 [ 833.942682] sock_sendmsg+0xb8/0x110 [ 833.944745] ____sys_sendmsg+0x570/0x698 [ 833.946849] ___sys_sendmsg+0x108/0x188 [ 833.948924] __sys_sendmsg+0xe8/0x198 [ 833.950980] __arm64_sys_sendmsg+0x78/0xa8 [ 833.953059] el0_svc_common+0x10c/0x330 [ 833.955121] el0_svc_handler+0x60/0xd0 [ 833.957143] el0_svc+0x8/0x1b0 [ 833.959088] [ 833.960846] The buggy address belongs to the object at ffff800109b7c280 [ 833.960846] which belongs to the cache kmalloc-512 of size 512 [ 833.965502] The buggy address is located 8 bytes inside of [ 833.965502] 512-byte region [ffff800109b7c280, ffff800109b7c480) [ 833.970108] The buggy address belongs to the page: [ 833.972390] page:ffff7e000426df00 count:1 mapcount:0 mapping:ffff8000c0003800 index:0x0 compound_mapcount: 0 [ 833.975269] flags: 0x7ffff0000008100(slab|head) [ 833.977640] raw: 07ffff0000008100 ffff7e00035d1600 0000000200000002 ffff8000c0003800 [ 833.980426] raw: 0000000000000000 00000000000c000c 00000001ffffffff 0000000000000000 [ 833.983212] page dumped because: kasan: bad access detected [ 833.985778] [ 833.987935] Memory state around the buggy address: [ 833.990448] ffff800109b7c180: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 833.993265] ffff800109b7c200: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 833.996097] >ffff800109b7c280: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 833.998930] ^ [ 834.001384] ffff800109b7c300: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 834.004329] ffff800109b7c380: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 834.007264] ================================================================== As 98fd847a495f commit add check "disk->first_minor", if failed will free tags and finally call put_disk will free request_queue. blk_mq_free_tag_set blk_mq_free_map_and_requests blk_mq_free_rqs put_disk: __blk_release_queue blk_exit_queue elevator_exit blk_mq_exit_sched blk_mq_sched_tags_teardown blk_mq_free_rqs -->will trigger UAF To address this issue, just move 'disk->first_minor' check at the first in nbd_dev_add. Fixes:98fd847a495f("nbd: add sanity check for first_minor") Signed-off-by: Ye Bin <yebin10(a)huawei.com> Reviewed-by: Yu Kuai <yukuai3(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/block/nbd.c | 22 ++++++++++------------ 1 file changed, 10 insertions(+), 12 deletions(-) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 775cbb4c1bbcd..a35189098581b 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1702,6 +1702,15 @@ static int nbd_dev_add(int index) struct gendisk *disk; struct request_queue *q; int err = -ENOMEM; + int first_minor = index << part_shift; + + /* + * Too big index can cause duplicate creation of sysfs files/links, + * because MKDEV() expect that the max first minor is MINORMASK, or + * index << part_shift can overflow. + */ + if (first_minor < index || first_minor > MINORMASK) + return -EINVAL; nbd = kzalloc(sizeof(struct nbd_device), GFP_KERNEL); if (!nbd) @@ -1765,18 +1774,7 @@ static int nbd_dev_add(int index) refcount_set(&nbd->refs, 1); INIT_LIST_HEAD(&nbd->list); disk->major = NBD_MAJOR; - - /* - * Too big index can cause duplicate creation of sysfs files/links, - * because MKDEV() expect that the max first minor is MINORMASK, or - * index << part_shift can overflow. - */ - disk->first_minor = index << part_shift; - if (disk->first_minor < index || disk->first_minor > MINORMASK) { - err = -EINVAL; - goto out_free_tags; - } - + disk->first_minor = first_minor; disk->fops = &nbd_fops; disk->private_data = nbd; sprintf(disk->disk_name, "nbd%d", index); -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS 1/5] block, bfq: improve asymmetric scenarios detection
by Yang Yingliang 17 Dec '21

17 Dec '21

From: Federico Motta <federico(a)willer.it> mainline inclusion from mainline-v4.20-rc1 commit 2d29c9f89fcd9bf408fcdaaf515c90a169f22ecd category: bugfix bugzilla: 185905 CVE: NA --------------------------- bfq defines as asymmetric a scenario where an active entity, say E (representing either a single bfq_queue or a group of other entities), has a higher weight than some other entities. If the entity E does sync I/O in such a scenario, then bfq plugs the dispatch of the I/O of the other entities in the following situation: E is in service but temporarily has no pending I/O request. In fact, without this plugging, all the times that E stops being temporarily idle, it may find the internal queues of the storage device already filled with an out-of-control number of extra requests, from other entities. So E may have to wait for the service of these extra requests, before finally having its own requests served. This may easily break service guarantees, with E getting less than its fair share of the device throughput. Usually, the end result is that E gets the same fraction of the throughput as the other entities, instead of getting more, according to its higher weight. Yet there are two other more subtle cases where E, even if its weight is actually equal to or even lower than the weight of any other active entities, may get less than its fair share of the throughput in case the above I/O plugging is not performed: 1. other entities issue larger requests than E; 2. other entities contain more active child entities than E (or in general tend to have more backlog than E). In the first case, other entities may get more service than E because they get larger requests, than those of E, served during the temporary idle periods of E. In the second case, other entities get more service because, by having many child entities, they have many requests ready for dispatching while E is temporarily idle. This commit addresses this issue by extending the definition of asymmetric scenario: a scenario is asymmetric when - active entities representing bfq_queues have differentiated weights, as in the original definition or (inclusive) - one or more entities representing groups of entities are active. This broader definition makes sure that I/O plugging will be performed in all the above cases, provided that there is at least one active group. Of course, this definition is very coarse, so it will trigger I/O plugging also in cases where it is not needed, such as, e.g., multiple active entities with just one child each, and all with the same I/O-request size. The reason for this coarse definition is just that a finer-grained definition would be rather heavy to compute. On the opposite end, even this new definition does not trigger I/O plugging in all cases where there is no active group, and all bfq_queues have the same weight. So, in these cases some unfairness may occur if there are asymmetries in I/O-request sizes. We made this choice because I/O plugging may lower throughput, and probably a user that has not created any group cares more about throughput than about perfect fairness. At any rate, as for possible applications that may care about service guarantees, bfq already guarantees a high responsiveness and a low latency to soft real-time applications automatically. Signed-off-by: Federico Motta <federico(a)willer.it> Signed-off-by: Paolo Valente <paolo.valente(a)linaro.org> Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> Reviewed-by: Hou Tao <houtao1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- block/bfq-iosched.c | 223 ++++++++++++++++++++++++-------------------- block/bfq-iosched.h | 27 +++--- block/bfq-wf2q.c | 35 +++---- 3 files changed, 154 insertions(+), 131 deletions(-) diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 4686ca1e93afe..e2b5c3ccd5502 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -625,12 +625,13 @@ void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq) } /* - * Tell whether there are active queues or groups with differentiated weights. + * Tell whether there are active queues with different weights or + * active groups. */ -static bool bfq_differentiated_weights(struct bfq_data *bfqd) +static bool bfq_varied_queue_weights_or_active_groups(struct bfq_data *bfqd) { /* - * For weights to differ, at least one of the trees must contain + * For queue weights to differ, queue_weights_tree must contain * at least two nodes. */ return (!RB_EMPTY_ROOT(&bfqd->queue_weights_tree) && @@ -638,9 +639,7 @@ static bool bfq_differentiated_weights(struct bfq_data *bfqd) bfqd->queue_weights_tree.rb_node->rb_right) #ifdef CONFIG_BFQ_GROUP_IOSCHED ) || - (!RB_EMPTY_ROOT(&bfqd->group_weights_tree) && - (bfqd->group_weights_tree.rb_node->rb_left || - bfqd->group_weights_tree.rb_node->rb_right) + (bfqd->num_active_groups > 0 #endif ); } @@ -658,26 +657,25 @@ static bool bfq_differentiated_weights(struct bfq_data *bfqd) * 3) all active groups at the same level in the groups tree have the same * number of children. * - * Unfortunately, keeping the necessary state for evaluating exactly the - * above symmetry conditions would be quite complex and time-consuming. - * Therefore this function evaluates, instead, the following stronger - * sub-conditions, for which it is much easier to maintain the needed - * state: + * Unfortunately, keeping the necessary state for evaluating exactly + * the last two symmetry sub-conditions above would be quite complex + * and time consuming. Therefore this function evaluates, instead, + * only the following stronger two sub-conditions, for which it is + * much easier to maintain the needed state: * 1) all active queues have the same weight, - * 2) all active groups have the same weight, - * 3) all active groups have at most one active child each. - * In particular, the last two conditions are always true if hierarchical - * support and the cgroups interface are not enabled, thus no state needs - * to be maintained in this case. + * 2) there are no active groups. + * In particular, the last condition is always true if hierarchical + * support or the cgroups interface are not enabled, thus no state + * needs to be maintained in this case. */ static bool bfq_symmetric_scenario(struct bfq_data *bfqd) { - return !bfq_differentiated_weights(bfqd); + return !bfq_varied_queue_weights_or_active_groups(bfqd); } /* * If the weight-counter tree passed as input contains no counter for - * the weight of the input entity, then add that counter; otherwise just + * the weight of the input queue, then add that counter; otherwise just * increment the existing counter. * * Note that weight-counter trees contain few nodes in mostly symmetric @@ -688,25 +686,25 @@ static bool bfq_symmetric_scenario(struct bfq_data *bfqd) * In most scenarios, the rate at which nodes are created/destroyed * should be low too. */ -void bfq_weights_tree_add(struct bfq_data *bfqd, struct bfq_entity *entity, +void bfq_weights_tree_add(struct bfq_data *bfqd, struct bfq_queue *bfqq, struct rb_root *root) { + struct bfq_entity *entity = &bfqq->entity; struct rb_node **new = &(root->rb_node), *parent = NULL; /* - * Do not insert if the entity is already associated with a + * Do not insert if the queue is already associated with a * counter, which happens if: - * 1) the entity is associated with a queue, - * 2) a request arrival has caused the queue to become both + * 1) a request arrival has caused the queue to become both * non-weight-raised, and hence change its weight, and * backlogged; in this respect, each of the two events * causes an invocation of this function, - * 3) this is the invocation of this function caused by the + * 2) this is the invocation of this function caused by the * second event. This second invocation is actually useless, * and we handle this fact by exiting immediately. More * efficient or clearer solutions might possibly be adopted. */ - if (entity->weight_counter) + if (bfqq->weight_counter) return; while (*new) { @@ -716,7 +714,7 @@ void bfq_weights_tree_add(struct bfq_data *bfqd, struct bfq_entity *entity, parent = *new; if (entity->weight == __counter->weight) { - entity->weight_counter = __counter; + bfqq->weight_counter = __counter; goto inc_counter; } if (entity->weight < __counter->weight) @@ -725,66 +723,67 @@ void bfq_weights_tree_add(struct bfq_data *bfqd, struct bfq_entity *entity, new = &((*new)->rb_right); } - entity->weight_counter = kzalloc(sizeof(struct bfq_weight_counter), - GFP_ATOMIC); + bfqq->weight_counter = kzalloc(sizeof(struct bfq_weight_counter), + GFP_ATOMIC); /* * In the unlucky event of an allocation failure, we just - * exit. This will cause the weight of entity to not be - * considered in bfq_differentiated_weights, which, in its - * turn, causes the scenario to be deemed wrongly symmetric in - * case entity's weight would have been the only weight making - * the scenario asymmetric. On the bright side, no unbalance - * will however occur when entity becomes inactive again (the - * invocation of this function is triggered by an activation - * of entity). In fact, bfq_weights_tree_remove does nothing - * if !entity->weight_counter. + * exit. This will cause the weight of queue to not be + * considered in bfq_varied_queue_weights_or_active_groups, + * which, in its turn, causes the scenario to be deemed + * wrongly symmetric in case bfqq's weight would have been + * the only weight making the scenario asymmetric. On the + * bright side, no unbalance will however occur when bfqq + * becomes inactive again (the invocation of this function + * is triggered by an activation of queue). In fact, + * bfq_weights_tree_remove does nothing if + * !bfqq->weight_counter. */ - if (unlikely(!entity->weight_counter)) + if (unlikely(!bfqq->weight_counter)) return; - entity->weight_counter->weight = entity->weight; - rb_link_node(&entity->weight_counter->weights_node, parent, new); - rb_insert_color(&entity->weight_counter->weights_node, root); + bfqq->weight_counter->weight = entity->weight; + rb_link_node(&bfqq->weight_counter->weights_node, parent, new); + rb_insert_color(&bfqq->weight_counter->weights_node, root); inc_counter: - entity->weight_counter->num_active++; + bfqq->weight_counter->num_active++; } /* - * Decrement the weight counter associated with the entity, and, if the + * Decrement the weight counter associated with the queue, and, if the * counter reaches 0, remove the counter from the tree. * See the comments to the function bfq_weights_tree_add() for considerations * about overhead. */ void __bfq_weights_tree_remove(struct bfq_data *bfqd, - struct bfq_entity *entity, + struct bfq_queue *bfqq, struct rb_root *root) { - if (!entity->weight_counter) + if (!bfqq->weight_counter) return; - entity->weight_counter->num_active--; - if (entity->weight_counter->num_active > 0) + bfqq->weight_counter->num_active--; + if (bfqq->weight_counter->num_active > 0) goto reset_entity_pointer; - rb_erase(&entity->weight_counter->weights_node, root); - kfree(entity->weight_counter); + rb_erase(&bfqq->weight_counter->weights_node, root); + kfree(bfqq->weight_counter); reset_entity_pointer: - entity->weight_counter = NULL; + bfqq->weight_counter = NULL; } /* - * Invoke __bfq_weights_tree_remove on bfqq and all its inactive - * parent entities. + * Invoke __bfq_weights_tree_remove on bfqq and decrement the number + * of active groups for each queue's inactive parent entity. */ void bfq_weights_tree_remove(struct bfq_data *bfqd, struct bfq_queue *bfqq) { struct bfq_entity *entity = bfqq->entity.parent; - __bfq_weights_tree_remove(bfqd, &bfqq->entity, + __bfq_weights_tree_remove(bfqd, bfqq, &bfqd->queue_weights_tree); for_each_entity(entity) { @@ -798,17 +797,13 @@ void bfq_weights_tree_remove(struct bfq_data *bfqd, * next_in_service for details on why * in_service_entity must be checked too). * - * As a consequence, the weight of entity is - * not to be removed. In addition, if entity - * is active, then its parent entities are - * active as well, and thus their weights are - * not to be removed either. In the end, this - * loop must stop here. + * As a consequence, its parent entities are + * active as well, and thus this loop must + * stop here. */ break; } - __bfq_weights_tree_remove(bfqd, entity, - &bfqd->group_weights_tree); + bfqd->num_active_groups--; } } @@ -3539,9 +3534,11 @@ static bool bfq_better_to_idle(struct bfq_queue *bfqq) * symmetric scenario where: * (i) each of these processes must get the same throughput as * the others; - * (ii) all these processes have the same I/O pattern - (either sequential or random). - * In fact, in such a scenario, the drive will tend to treat + * (ii) the I/O of each process has the same properties, in + * terms of locality (sequential or random), direction + * (reads or writes), request sizes, greediness + * (from I/O-bound to sporadic), and so on. + * In fact, in such a scenario, the drive tends to treat * the requests of each of these processes in about the same * way as the requests of the others, and thus to provide * each of these processes with about the same throughput @@ -3550,18 +3547,50 @@ static bool bfq_better_to_idle(struct bfq_queue *bfqq) * certainly needed to guarantee that bfqq receives its * assigned fraction of the device throughput (see [1] for * details). + * The problem is that idling may significantly reduce + * throughput with certain combinations of types of I/O and + * devices. An important example is sync random I/O, on flash + * storage with command queueing. So, unless bfqq falls in the + * above cases where idling also boosts throughput, it would + * be important to check conditions (i) and (ii) accurately, + * so as to avoid idling when not strictly needed for service + * guarantees. + * + * Unfortunately, it is extremely difficult to thoroughly + * check condition (ii). And, in case there are active groups, + * it becomes very difficult to check condition (i) too. In + * fact, if there are active groups, then, for condition (i) + * to become false, it is enough that an active group contains + * more active processes or sub-groups than some other active + * group. We address this issue with the following bi-modal + * behavior, implemented in the function + * bfq_symmetric_scenario(). * - * We address this issue by controlling, actually, only the - * symmetry sub-condition (i), i.e., provided that - * sub-condition (i) holds, idling is not performed, - * regardless of whether sub-condition (ii) holds. In other - * words, only if sub-condition (i) holds, then idling is + * If there are active groups, then the scenario is tagged as + * asymmetric, conservatively, without checking any of the + * conditions (i) and (ii). So the device is idled for bfqq. + * This behavior matches also the fact that groups are created + * exactly if controlling I/O (to preserve bandwidth and + * latency guarantees) is a primary concern. + * + * On the opposite end, if there are no active groups, then + * only condition (i) is actually controlled, i.e., provided + * that condition (i) holds, idling is not performed, + * regardless of whether condition (ii) holds. In other words, + * only if condition (i) does not hold, then idling is * allowed, and the device tends to be prevented from queueing - * many requests, possibly of several processes. The reason - * for not controlling also sub-condition (ii) is that we - * exploit preemption to preserve guarantees in case of - * symmetric scenarios, even if (ii) does not hold, as - * explained in the next two paragraphs. + * many requests, possibly of several processes. Since there + * are no active groups, then, to control condition (i) it is + * enough to check whether all active queues have the same + * weight. + * + * Not checking condition (ii) evidently exposes bfqq to the + * risk of getting less throughput than its fair share. + * However, for queues with the same weight, a further + * mechanism, preemption, mitigates or even eliminates this + * problem. And it does so without consequences on overall + * throughput. This mechanism and its benefits are explained + * in the next three paragraphs. * * Even if a queue, say Q, is expired when it remains idle, Q * can still preempt the new in-service queue if the next @@ -3575,11 +3604,7 @@ static bool bfq_better_to_idle(struct bfq_queue *bfqq) * idling allows the internal queues of the device to contain * many requests, and thus to reorder requests, we can rather * safely assume that the internal scheduler still preserves a - * minimum of mid-term fairness. The motivation for using - * preemption instead of idling is that, by not idling, - * service guarantees are preserved without minimally - * sacrificing throughput. In other words, both a high - * throughput and its desired distribution are obtained. + * minimum of mid-term fairness. * * More precisely, this preemption-based, idleless approach * provides fairness in terms of IOPS, and not sectors per @@ -3598,27 +3623,27 @@ static bool bfq_better_to_idle(struct bfq_queue *bfqq) * 1024/8 times as high as the service received by the other * queue. * - * On the other hand, device idling is performed, and thus - * pure sector-domain guarantees are provided, for the - * following queues, which are likely to need stronger - * throughput guarantees: weight-raised queues, and queues - * with a higher weight than other queues. When such queues - * are active, sub-condition (i) is false, which triggers - * device idling. + * The motivation for using preemption instead of idling (for + * queues with the same weight) is that, by not idling, + * service guarantees are preserved (completely or at least in + * part) without minimally sacrificing throughput. And, if + * there is no active group, then the primary expectation for + * this device is probably a high throughput. * - * According to the above considerations, the next variable is - * true (only) if sub-condition (i) holds. To compute the - * value of this variable, we not only use the return value of - * the function bfq_symmetric_scenario(), but also check - * whether bfqq is being weight-raised, because - * bfq_symmetric_scenario() does not take into account also - * weight-raised queues (see comments on - * bfq_weights_tree_add()). In particular, if bfqq is being - * weight-raised, it is important to idle only if there are - * other, non-weight-raised queues that may steal throughput - * to bfqq. Actually, we should be even more precise, and - * differentiate between interactive weight raising and - * soft real-time weight raising. + * We are now left only with explaining the additional + * compound condition that is checked below for deciding + * whether the scenario is asymmetric. To explain this + * compound condition, we need to add that the function + * bfq_symmetric_scenario checks the weights of only + * non-weight-raised queues, for efficiency reasons (see + * comments on bfq_weights_tree_add()). Then the fact that + * bfqq is weight-raised is checked explicitly here. More + * precisely, the compound condition below takes into account + * also the fact that, even if bfqq is being weight-raised, + * the scenario is still symmetric if all active queues happen + * to be weight-raised. Actually, we should be even more + * precise here, and differentiate between interactive weight + * raising and soft real-time weight raising. * * As a side note, it is worth considering that the above * device-idling countermeasures may however fail in the @@ -5408,7 +5433,7 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e) bfqd->idle_slice_timer.function = bfq_idle_slice_timer; bfqd->queue_weights_tree = RB_ROOT; - bfqd->group_weights_tree = RB_ROOT; + bfqd->num_active_groups = 0; INIT_LIST_HEAD(&bfqd->active_list); INIT_LIST_HEAD(&bfqd->idle_list); diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h index a41e9884f2dd2..e9960727cb565 100644 --- a/block/bfq-iosched.h +++ b/block/bfq-iosched.h @@ -108,15 +108,14 @@ struct bfq_sched_data { }; /** - * struct bfq_weight_counter - counter of the number of all active entities + * struct bfq_weight_counter - counter of the number of all active queues * with a given weight. */ struct bfq_weight_counter { - unsigned int weight; /* weight of the entities this counter refers to */ - unsigned int num_active; /* nr of active entities with this weight */ + unsigned int weight; /* weight of the queues this counter refers to */ + unsigned int num_active; /* nr of active queues with this weight */ /* - * Weights tree member (see bfq_data's @queue_weights_tree and - * @group_weights_tree) + * Weights tree member (see bfq_data's @queue_weights_tree) */ struct rb_node weights_node; }; @@ -151,8 +150,6 @@ struct bfq_weight_counter { struct bfq_entity { /* service_tree member */ struct rb_node rb_node; - /* pointer to the weight counter associated with this entity */ - struct bfq_weight_counter *weight_counter; /* * Flag, true if the entity is on a tree (either the active or @@ -266,6 +263,9 @@ struct bfq_queue { /* entity representing this queue in the scheduler */ struct bfq_entity entity; + /* pointer to the weight counter associated with this entity */ + struct bfq_weight_counter *weight_counter; + /* maximum budget allowed from the feedback mechanism */ int max_budget; /* budget expiration (in jiffies) */ @@ -449,14 +449,9 @@ struct bfq_data { */ struct rb_root queue_weights_tree; /* - * rbtree of non-queue @bfq_entity weight counters, sorted by - * weight. Used to keep track of whether all @bfq_groups have - * the same weight. The tree contains one counter for each - * distinct weight associated to some active @bfq_group (see - * the comments to the functions bfq_weights_tree_[add|remove] - * for further details). + * number of groups with requests still waiting for completion */ - struct rb_root group_weights_tree; + unsigned int num_active_groups; /* * Number of bfq_queues containing requests (including the @@ -854,10 +849,10 @@ struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic, bool is_sync); void bic_set_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq, bool is_sync); struct bfq_data *bic_to_bfqd(struct bfq_io_cq *bic); void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq); -void bfq_weights_tree_add(struct bfq_data *bfqd, struct bfq_entity *entity, +void bfq_weights_tree_add(struct bfq_data *bfqd, struct bfq_queue *bfqq, struct rb_root *root); void __bfq_weights_tree_remove(struct bfq_data *bfqd, - struct bfq_entity *entity, + struct bfq_queue *bfqq, struct rb_root *root); void bfq_weights_tree_remove(struct bfq_data *bfqd, struct bfq_queue *bfqq); diff --git a/block/bfq-wf2q.c b/block/bfq-wf2q.c index e830715fe15d6..cdd164c82398a 100644 --- a/block/bfq-wf2q.c +++ b/block/bfq-wf2q.c @@ -788,25 +788,29 @@ __bfq_entity_update_weight_prio(struct bfq_service_tree *old_st, new_weight = entity->orig_weight * (bfqq ? bfqq->wr_coeff : 1); /* - * If the weight of the entity changes, remove the entity - * from its old weight counter (if there is a counter - * associated with the entity), and add it to the counter - * associated with its new weight. + * If the weight of the entity changes, and the entity is a + * queue, remove the entity from its old weight counter (if + * there is a counter associated with the entity). */ if (prev_weight != new_weight) { - root = bfqq ? &bfqd->queue_weights_tree : - &bfqd->group_weights_tree; - __bfq_weights_tree_remove(bfqd, entity, root); + if (bfqq) { + root = &bfqd->queue_weights_tree; + __bfq_weights_tree_remove(bfqd, bfqq, root); + } else + bfqd->num_active_groups--; } entity->weight = new_weight; /* - * Add the entity to its weights tree only if it is - * not associated with a weight-raised queue. + * Add the entity, if it is not a weight-raised queue, + * to the counter associated with its new weight. */ - if (prev_weight != new_weight && - (bfqq ? bfqq->wr_coeff == 1 : 1)) - /* If we get here, root has been initialized. */ - bfq_weights_tree_add(bfqd, entity, root); + if (prev_weight != new_weight) { + if (bfqq && bfqq->wr_coeff == 1) { + /* If we get here, root has been initialized. */ + bfq_weights_tree_add(bfqd, bfqq, root); + } else + bfqd->num_active_groups++; + } new_st->wsum += entity->weight; @@ -1014,8 +1018,7 @@ static void __bfq_activate_entity(struct bfq_entity *entity, container_of(entity, struct bfq_group, entity); struct bfq_data *bfqd = bfqg->bfqd; - bfq_weights_tree_add(bfqg->bfqd, entity, - &bfqd->group_weights_tree); + bfqd->num_active_groups++; } #endif @@ -1702,7 +1705,7 @@ void bfq_add_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq) if (!bfqq->dispatched) if (bfqq->wr_coeff == 1) - bfq_weights_tree_add(bfqd, &bfqq->entity, + bfq_weights_tree_add(bfqd, bfqq, &bfqd->queue_weights_tree); if (bfqq->wr_coeff > 1) -- 2.25.1

1 4

[PATCH openEuler-1.0-LTS 01/10] arm64: mm: Restore mm_cpumask (revert commit 38d96287504a ("arm64: mm: kill mm_cpumask usage"))
by Yang Yingliang 17 Dec '21

17 Dec '21

From: Takao Indoh <indou.takao(a)fujitsu.com> hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4BLL0 CVE: NA --------------------------- mm_cpumask was deleted by the commit 38d96287504a ("arm64: mm: kill mm_cpumask usage") because it was not used at that time. Now this is needed to find appropriate CPUs for TLB flush, so this patch reverts this commit. Signed-off-by: QI Fuli <qi.fuli(a)fujitsu.com> Signed-off-by: Takao Indoh <indou.takao(a)fujitsu.com> Signed-off-by: Cheng Jian <cj.chengjian(a)huawei.com> Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/arm64/kernel/smp.c | 6 ++++++ arch/arm64/mm/context.c | 2 ++ 2 files changed, 8 insertions(+) diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index fe562778de352..e86940d353a3e 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -387,6 +387,7 @@ asmlinkage notrace void secondary_start_kernel(void) */ mmgrab(mm); current->active_mm = mm; + cpumask_set_cpu(cpu, mm_cpumask(mm)); /* * TTBR0 is only used for the identity mapping at this stage. Make it @@ -489,6 +490,11 @@ int __cpu_disable(void) */ irq_migrate_all_off_this_cpu(); + /* + * Remove this CPU from the vm mask set of all processes. + */ + clear_tasks_mm_cpumask(cpu); + return 0; } diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c index 2b80ceff5d6c2..27d1f3fec1cc9 100644 --- a/arch/arm64/mm/context.c +++ b/arch/arm64/mm/context.c @@ -207,6 +207,7 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu) set_asid: __set_bit(asid, asid_map); cur_idx = asid; + cpumask_clear(mm_cpumask(mm)); return idx2asid(asid) | generation; } @@ -254,6 +255,7 @@ void check_and_switch_context(struct mm_struct *mm, unsigned int cpu) switch_mm_fastpath: arm64_apply_bp_hardening(); + cpumask_set_cpu(cpu, mm_cpumask(mm)); /* * Defer TTBR0_EL1 setting for user threads to uaccess_enable() when -- 2.25.1

1 9

[PATCH openEuler-1.0-LTS] fget: check that the fd still exists after getting a ref to it
by Yang Yingliang 17 Dec '21

17 Dec '21

From: Linus Torvalds <torvalds(a)linux-foundation.org> stable inclusion from stable-4.19.220 commit 8bf31f9d9395b71af3ed33166a057cd3ec0c59da category: bugfix bugzilla: 185907 CVE: CVE-2021-4083 ------------------------------------------------- commit 054aa8d439b9185d4f5eb9a90282d1ce74772969 upstream. Jann Horn points out that there is another possible race wrt Unix domain socket garbage collection, somewhat reminiscent of the one fixed in commit cbcf01128d0a ("af_unix: fix garbage collect vs MSG_PEEK"). See the extended comment about the garbage collection requirements added to unix_peek_fds() by that commit for details. The race comes from how we can locklessly look up a file descriptor just as it is in the process of being closed, and with the right artificial timing (Jann added a few strategic 'mdelay(500)' calls to do that), the Unix domain socket garbage collector could see the reference count decrement of the close() happen before fget() took its reference to the file and the file was attached onto a new file descriptor. This is all (intentionally) correct on the 'struct file *' side, with RCU lookups and lockless reference counting very much part of the design. Getting that reference count out of order isn't a problem per se. But the garbage collector can get confused by seeing this situation of having seen a file not having any remaining external references and then seeing it being attached to an fd. In commit cbcf01128d0a ("af_unix: fix garbage collect vs MSG_PEEK") the fix was to serialize the file descriptor install with the garbage collector by taking and releasing the unix_gc_lock. That's not really an option here, but since this all happens when we are in the process of looking up a file descriptor, we can instead simply just re-check that the file hasn't been closed in the meantime, and just re-do the lookup if we raced with a concurrent close() of the same file descriptor. Reported-and-tested-by: Jann Horn <jannh(a)google.com> Acked-by: Miklos Szeredi <mszeredi(a)redhat.com> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Baokun Li <libaokun1(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/file.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/file.c b/fs/file.c index 0caadedd3cc43..20a44d0ac400b 100644 --- a/fs/file.c +++ b/fs/file.c @@ -779,6 +779,10 @@ static struct file *__fget(unsigned int fd, fmode_t mask, unsigned int refs) file = NULL; else if (!get_file_rcu_many(file, refs)) goto loop; + else if (__fcheck_files(files, fd) != file) { + fput_many(file, refs); + goto loop; + } } rcu_read_unlock(); -- 2.25.1

1 0

the patches of ntfs3
by 尹秀江 17 Dec '21

17 Dec '21

1 0

[PATCH openEuler-1.0-LTS 1/4] Revert "Revert "ext4: Allow parallel DIO reads""
by Yang Yingliang 17 Dec '21

17 Dec '21

From: Zhang Xiaoxu <zhangxiaoxu5(a)huawei.com> hulk inclusion category: feature bugzilla: 185871, https://gitee.com/openeuler/kernel/issues/I4MIQ0 CVE: NA --------------------------- This reverts commit bb24e7e6309ae1bbc80062366b8f9bb2e8fcc025. In order to improve the dio reads performance, we enable the parallel dio reads. And make it configuratable Conflict: fs/ext4/Kconfig fs/ext4/inode.c Signed-off-by: Zhang Xiaoxu <zhangxiaoxu5(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/ext4/Kconfig | 5 +++++ fs/ext4/inode.c | 34 ++++++++++++++++++++++++++++------ 2 files changed, 33 insertions(+), 6 deletions(-) diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig index a453cc87082b5..de836b75c6f2b 100644 --- a/fs/ext4/Kconfig +++ b/fs/ext4/Kconfig @@ -120,3 +120,8 @@ config EXT4_DEBUG If you select Y here, then you will be able to turn on debugging with a command such as: echo 1 > /sys/module/ext4/parameters/mballoc_debug +config EXT4_PARALLEL_DIO_READ + bool "EXT4 parallel dio reads" + depends on EXT4_FS + help + Enable parallel dio read. diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index fb4de707cd9ad..2f5231899d342 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3795,15 +3795,31 @@ static ssize_t ext4_direct_IO_write(struct kiocb *iocb, struct iov_iter *iter) static ssize_t ext4_direct_IO_read(struct kiocb *iocb, struct iov_iter *iter) { + struct address_space *mapping = iocb->ki_filp->f_mapping; + struct inode *inode = mapping->host; +#ifdef CONFIG_EXT4_PARALLEL_DIO_READ + size_t count = iov_iter_count(iter); +#else int unlocked = 0; - struct inode *inode = iocb->ki_filp->f_mapping->host; +#endif ssize_t ret; loff_t offset = iocb->ki_pos; loff_t size = i_size_read(inode); if (offset >= size) return 0; - +#ifdef CONFIG_EXT4_PARALLEL_DIO_READ + /* + * Shared inode_lock is enough for us - it protects against concurrent + * writes & truncates and since we take care of writing back page cache, + * we are protected against page writeback as well. + */ + inode_lock_shared(inode); + ret = filemap_write_and_wait_range(mapping, iocb->ki_pos, + iocb->ki_pos + count - 1); + if (ret) + goto out_unlock; +#else if (ext4_should_dioread_nolock(inode)) { /* * Nolock dioread optimization may be dynamically disabled @@ -3813,18 +3829,24 @@ static ssize_t ext4_direct_IO_read(struct kiocb *iocb, struct iov_iter *iter) inode_dio_begin(inode); smp_mb(); if (unlikely(ext4_test_inode_state(inode, - EXT4_STATE_DIOREAD_LOCK))) + EXT4_STATE_DIOREAD_LOCK))) inode_dio_end(inode); else unlocked = 1; } +#endif + ret = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, - iter, ext4_dio_get_block, - NULL, NULL, + iter, ext4_dio_get_block, NULL, NULL, +#ifdef CONFIG_EXT4_PARALLEL_DIO_READ + 0); +out_unlock: + inode_unlock_shared(inode); +#else unlocked ? 0 : DIO_LOCKING); - if (unlocked) inode_dio_end(inode); +#endif return ret; } -- 2.25.1

1 3

[PATCH openEuler-1.0-LTS 1/4] Revert "Revert "ext4: Allow parallel DIO reads""
by Yang Yingliang 17 Dec '21

17 Dec '21

From: Zhang Xiaoxu <zhangxiaoxu5(a)huawei.com> hulk inclusion category: feature bugzilla: 185871, https://gitee.com/openeuler/kernel/issues/I4MIQ0 CVE: NA --------------------------- This reverts commit bb24e7e6309ae1bbc80062366b8f9bb2e8fcc025. In order to improve the dio reads performance, we enable the parallel dio reads. And make it configuratable Conflict: fs/ext4/Kconfig fs/ext4/inode.c Signed-off-by: Zhang Xiaoxu <zhangxiaoxu5(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/ext4/Kconfig | 5 +++++ fs/ext4/inode.c | 34 ++++++++++++++++++++++++++++------ 2 files changed, 33 insertions(+), 6 deletions(-) diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig index a453cc87082b5..de836b75c6f2b 100644 --- a/fs/ext4/Kconfig +++ b/fs/ext4/Kconfig @@ -120,3 +120,8 @@ config EXT4_DEBUG If you select Y here, then you will be able to turn on debugging with a command such as: echo 1 > /sys/module/ext4/parameters/mballoc_debug +config EXT4_PARALLEL_DIO_READ + bool "EXT4 parallel dio reads" + depends on EXT4_FS + help + Enable parallel dio read. diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index fb4de707cd9ad..2f5231899d342 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3795,15 +3795,31 @@ static ssize_t ext4_direct_IO_write(struct kiocb *iocb, struct iov_iter *iter) static ssize_t ext4_direct_IO_read(struct kiocb *iocb, struct iov_iter *iter) { + struct address_space *mapping = iocb->ki_filp->f_mapping; + struct inode *inode = mapping->host; +#ifdef CONFIG_EXT4_PARALLEL_DIO_READ + size_t count = iov_iter_count(iter); +#else int unlocked = 0; - struct inode *inode = iocb->ki_filp->f_mapping->host; +#endif ssize_t ret; loff_t offset = iocb->ki_pos; loff_t size = i_size_read(inode); if (offset >= size) return 0; - +#ifdef CONFIG_EXT4_PARALLEL_DIO_READ + /* + * Shared inode_lock is enough for us - it protects against concurrent + * writes & truncates and since we take care of writing back page cache, + * we are protected against page writeback as well. + */ + inode_lock_shared(inode); + ret = filemap_write_and_wait_range(mapping, iocb->ki_pos, + iocb->ki_pos + count - 1); + if (ret) + goto out_unlock; +#else if (ext4_should_dioread_nolock(inode)) { /* * Nolock dioread optimization may be dynamically disabled @@ -3813,18 +3829,24 @@ static ssize_t ext4_direct_IO_read(struct kiocb *iocb, struct iov_iter *iter) inode_dio_begin(inode); smp_mb(); if (unlikely(ext4_test_inode_state(inode, - EXT4_STATE_DIOREAD_LOCK))) + EXT4_STATE_DIOREAD_LOCK))) inode_dio_end(inode); else unlocked = 1; } +#endif + ret = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, - iter, ext4_dio_get_block, - NULL, NULL, + iter, ext4_dio_get_block, NULL, NULL, +#ifdef CONFIG_EXT4_PARALLEL_DIO_READ + 0); +out_unlock: + inode_unlock_shared(inode); +#else unlocked ? 0 : DIO_LOCKING); - if (unlocked) inode_dio_end(inode); +#endif return ret; } -- 2.25.1

1 3

[PATCH openEuler-1.0-LTS 1/4] net: hns3: fix VF RSS failed problem after PF enable multi-TCs
by Yang Yingliang 16 Dec '21

16 Dec '21

From: Guangbin Huang <huangguangbin2(a)huawei.com> mainline inclusion from mainline-v5.16-rc3 commit 8d2ad993aa05c0768f00c886c9d369cd97a337ac category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4MWF6 CVE: NA ---------------------------- When PF is set to multi-TCs and configured mapping relationship between priorities and TCs, the hardware will active these settings for this PF and its VFs. In this case when VF just uses one TC and its rx packets contain priority, and if the priority is not mapped to TC0, as other TCs of VF is not valid, hardware always put this kind of packets to the queue 0. It cause this kind of packets of VF can not be used RSS function. To fix this problem, set tc mode of all unused TCs of VF to the setting of TC0, then rx packet with priority which map to unused TC will be direct to TC0. Fixes: e2cb1dec9779 ("net: hns3: Add HNS3 VF HCL(Hardware Compatibility Layer) Support") Signed-off-by: Guangbin Huang <huangguangbin2(a)huawei.com> Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Yonglong Liu <liuyonglong(a)huawei.com> Reviewed-by: li yongxin <liyongxin1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 8e79818f149d2..ebe09a304aeda 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -686,9 +686,9 @@ static int hclgevf_set_rss_tc_mode(struct hclgevf_dev *hdev, u16 rss_size) roundup_size = ilog2(roundup_size); for (i = 0; i < HCLGEVF_MAX_TC_NUM; i++) { - tc_valid[i] = !!(hdev->hw_tc_map & BIT(i)); + tc_valid[i] = 1; tc_size[i] = roundup_size; - tc_offset[i] = rss_size * i; + tc_offset[i] = (hdev->hw_tc_map & BIT(i)) ? rss_size * i : 0; } hclgevf_cmd_setup_basic_desc(&desc, HCLGEVF_OPC_RSS_TC_MODE, false); -- 2.25.1

1 3

[PATCH openEuler-1.0-LTS 1/2] hugetlbfs: flush TLBs correctly after huge_pmd_unshare
by Yang Yingliang 16 Dec '21

16 Dec '21

From: Nadav Amit <namit(a)vmware.com> stable inclusion from linux-v4.19.219 commit b0313bc7f5fbb6beee327af39d818ffdc921821a category: bugfix bugzilla: 185854 CVE: CVE-2021-4002 ----------------------------------------------- commit a4a118f2eead1d6c49e00765de89878288d4b890 upstream. When __unmap_hugepage_range() calls to huge_pmd_unshare() succeed, a TLB flush is missing. This TLB flush must be performed before releasing the i_mmap_rwsem, in order to prevent an unshared PMDs page from being released and reused before the TLB flush took place. Arguably, a comprehensive solution would use mmu_gather interface to batch the TLB flushes and the PMDs page release, however it is not an easy solution: (1) try_to_unmap_one() and try_to_migrate_one() also call huge_pmd_unshare() and they cannot use the mmu_gather interface; and (2) deferring the release of the page reference for the PMDs page until after i_mmap_rwsem is dropeed can confuse huge_pmd_unshare() into thinking PMDs are shared when they are not. Fix __unmap_hugepage_range() by adding the missing TLB flush, and forcing a flush when unshare is successful. Fixes: 24669e58477e ("hugetlb: use mmu_gather instead of a temporary linked list for accumulating pages)" # 3.6 Signed-off-by: Nadav Amit <namit(a)vmware.com> Reviewed-by: Mike Kravetz <mike.kravetz(a)oracle.com> Cc: Aneesh Kumar K.V <aneesh.kumar(a)linux.vnet.ibm.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu(a)jp.fujitsu.com> Cc: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: include/asm-generic/tlb.h mm/mmu_gather.c Signed-off-by: Liu Shixin <liushixin2(a)huawei.com> Reviewed-by: tong tiangen <tongtiangen(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/arm/include/asm/tlb.h | 8 ++++++++ arch/ia64/include/asm/tlb.h | 10 ++++++++++ arch/s390/include/asm/tlb.h | 16 ++++++++++++++++ arch/sh/include/asm/tlb.h | 10 ++++++++++ arch/um/include/asm/tlb.h | 12 ++++++++++++ include/asm-generic/tlb.h | 2 ++ mm/hugetlb.c | 23 +++++++++++++++++++---- mm/mmu_gather.c | 10 ++++++++++ 8 files changed, 87 insertions(+), 4 deletions(-) diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h index f854148c8d7c2..00baa13c158d7 100644 --- a/arch/arm/include/asm/tlb.h +++ b/arch/arm/include/asm/tlb.h @@ -280,6 +280,14 @@ tlb_remove_pmd_tlb_entry(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr tlb_add_flush(tlb, addr); } +static inline void +tlb_flush_pmd_range(struct mmu_gather *tlb, unsigned long address, + unsigned long size) +{ + tlb_add_flush(tlb, address); + tlb_add_flush(tlb, address + size - PMD_SIZE); +} + #define pte_free_tlb(tlb, ptep, addr) __pte_free_tlb(tlb, ptep, addr) #define pmd_free_tlb(tlb, pmdp, addr) __pmd_free_tlb(tlb, pmdp, addr) #define pud_free_tlb(tlb, pudp, addr) pud_free((tlb)->mm, pudp) diff --git a/arch/ia64/include/asm/tlb.h b/arch/ia64/include/asm/tlb.h index 516355a774bfe..5d032d97c254e 100644 --- a/arch/ia64/include/asm/tlb.h +++ b/arch/ia64/include/asm/tlb.h @@ -268,6 +268,16 @@ __tlb_remove_tlb_entry (struct mmu_gather *tlb, pte_t *ptep, unsigned long addre tlb->end_addr = address + PAGE_SIZE; } +static inline void +tlb_flush_pmd_range(struct mmu_gather *tlb, unsigned long address, + unsigned long size) +{ + if (tlb->start_addr > address) + tlb->start_addr = address; + if (tlb->end_addr < address + size) + tlb->end_addr = address + size; +} + #define tlb_migrate_finish(mm) platform_tlb_migrate_finish(mm) #define tlb_start_vma(tlb, vma) do { } while (0) diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h index b31c779cf5817..1df28a8e2f19e 100644 --- a/arch/s390/include/asm/tlb.h +++ b/arch/s390/include/asm/tlb.h @@ -116,6 +116,20 @@ static inline void tlb_remove_page_size(struct mmu_gather *tlb, return tlb_remove_page(tlb, page); } +static inline void tlb_flush_pmd_range(struct mmu_gather *tlb, + unsigned long address, unsigned long size) +{ + /* + * the range might exceed the original range that was provided to + * tlb_gather_mmu(), so we need to update it despite the fact it is + * usually not updated. + */ + if (tlb->start > address) + tlb->start = address; + if (tlb->end < address + size) + tlb->end = address + size; +} + /* * pte_free_tlb frees a pte table and clears the CRSTE for the * page table from the tlb. @@ -177,6 +191,8 @@ static inline void pud_free_tlb(struct mmu_gather *tlb, pud_t *pud, #define tlb_remove_tlb_entry(tlb, ptep, addr) do { } while (0) #define tlb_remove_pmd_tlb_entry(tlb, pmdp, addr) do { } while (0) #define tlb_migrate_finish(mm) do { } while (0) +#define tlb_flush_pmd_range(tlb, addr, sz) do { } while (0) + #define tlb_remove_huge_tlb_entry(h, tlb, ptep, address) \ tlb_remove_tlb_entry(tlb, ptep, address) diff --git a/arch/sh/include/asm/tlb.h b/arch/sh/include/asm/tlb.h index 77abe192fb43d..adcb0bfe238e3 100644 --- a/arch/sh/include/asm/tlb.h +++ b/arch/sh/include/asm/tlb.h @@ -127,6 +127,16 @@ static inline void tlb_remove_page_size(struct mmu_gather *tlb, return tlb_remove_page(tlb, page); } +static inline void +tlb_flush_pmd_range(struct mmu_gather *tlb, unsigned long address, + unsigned long size) +{ + if (tlb->start > address) + tlb->start = address; + if (tlb->end < address + size) + tlb->end = address + size; +} + #define tlb_remove_check_page_size_change tlb_remove_check_page_size_change static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb, unsigned int page_size) diff --git a/arch/um/include/asm/tlb.h b/arch/um/include/asm/tlb.h index dce6db147f245..02e61f6abfcab 100644 --- a/arch/um/include/asm/tlb.h +++ b/arch/um/include/asm/tlb.h @@ -130,6 +130,18 @@ static inline void tlb_remove_page_size(struct mmu_gather *tlb, return tlb_remove_page(tlb, page); } +static inline void +tlb_flush_pmd_range(struct mmu_gather *tlb, unsigned long address, + unsigned long size) +{ + tlb->need_flush = 1; + + if (tlb->start > address) + tlb->start = address; + if (tlb->end < address + size) + tlb->end = address + size; +} + /** * tlb_remove_tlb_entry - remember a pte unmapping for later tlb invalidation. * diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index 6be86c1c5c583..cfc86e3ba4606 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -139,6 +139,8 @@ void tlb_flush_mmu(struct mmu_gather *tlb); void arch_tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end, bool force); void tlb_flush_mmu_free(struct mmu_gather *tlb); +void tlb_flush_pmd_range(struct mmu_gather *tlb, unsigned long address, + unsigned long size); extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 2f65dad443ab3..b2ed9174bfd73 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3595,6 +3595,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long sz = huge_page_size(h); unsigned long mmun_start = start; /* For mmu_notifiers */ unsigned long mmun_end = end; /* For mmu_notifiers */ + bool force_flush = false; WARN_ON(!is_vm_hugetlb_page(vma)); BUG_ON(start & ~huge_page_mask(h)); @@ -3621,10 +3622,8 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, ptl = huge_pte_lock(h, mm, ptep); if (huge_pmd_unshare(mm, &address, ptep)) { spin_unlock(ptl); - /* - * We just unmapped a page of PMDs by clearing a PUD. - * The caller's TLB flush range should cover this area. - */ + tlb_flush_pmd_range(tlb, address & PUD_MASK, PUD_SIZE); + force_flush = true; continue; } @@ -3688,6 +3687,22 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, } mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); tlb_end_vma(tlb, vma); + + /* + * If we unshared PMDs, the TLB flush was not recorded in mmu_gather. We + * could defer the flush until now, since by holding i_mmap_rwsem we + * guaranteed that the last refernece would not be dropped. But we must + * do the flushing before we return, as otherwise i_mmap_rwsem will be + * dropped and the last reference to the shared PMDs page might be + * dropped as well. + * + * In theory we could defer the freeing of the PMD pages as well, but + * huge_pmd_unshare() relies on the exact page_count for the PMD page to + * detect sharing, so we cannot defer the release of the page either. + * Instead, do flush now. + */ + if (force_flush) + tlb_flush_mmu_tlbonly(tlb); } void __unmap_hugepage_range_final(struct mmu_gather *tlb, diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c index 2a9fbc4a37d59..c147a5aacfa96 100644 --- a/mm/mmu_gather.c +++ b/mm/mmu_gather.c @@ -139,6 +139,16 @@ bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_ return false; } +void tlb_flush_pmd_range(struct mmu_gather *tlb, unsigned long address, + unsigned long size) +{ + if (tlb->page_size != 0 && tlb->page_size != PMD_SIZE) + tlb_flush_mmu(tlb); + + tlb->page_size = PMD_SIZE; + tlb->start = min(tlb->start, address); + tlb->end = max(tlb->end, address + size); +} #endif /* HAVE_GENERIC_MMU_GATHER */ #ifdef CONFIG_HAVE_RCU_TABLE_FREE -- 2.25.1

1 1

[PATCH openEuler-1.0-LTS 1/2] mm: share_pool: adjust sp_make_share_k2u behavior when coredump
by Yang Yingliang 16 Dec '21

16 Dec '21

From: Guo Mengqi <guomengqi3(a)huawei.com> ascend inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4MUV2 CVE: NA when k2u is being executed ont the whole sharepool group, and one process coredumps, k2u will skip the coredumped process and continue on the rest processes in the group. Signed-off-by: Guo Mengqi <guomengqi3(a)huawei.com> Reviewed-by: Weilong Chen <chenweilong(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- mm/share_pool.c | 50 +++++++++++++++++++++++++++++++------------------ 1 file changed, 32 insertions(+), 18 deletions(-) diff --git a/mm/share_pool.c b/mm/share_pool.c index c9079e6a40b1a..ac97a68a70264 100644 --- a/mm/share_pool.c +++ b/mm/share_pool.c @@ -678,8 +678,25 @@ static unsigned long sp_mmap(struct mm_struct *mm, struct file *file, struct sp_area *spa, unsigned long *populate, unsigned long prot); static void sp_munmap(struct mm_struct *mm, unsigned long addr, unsigned long size); + +#define K2U_NORMAL 0 +#define K2U_COREDUMP 1 + +struct sp_k2u_context { + unsigned long kva; + unsigned long kva_aligned; + unsigned long size; + unsigned long size_aligned; + unsigned long sp_flags; + int state; + int spg_id; + bool to_task; + struct timespec64 start; + struct timespec64 end; +}; + static unsigned long sp_remap_kva_to_vma(unsigned long kva, struct sp_area *spa, - struct mm_struct *mm, unsigned long prot); + struct mm_struct *mm, unsigned long prot, struct sp_k2u_context *kc); static void free_sp_group_id(int spg_id) { @@ -1334,7 +1351,7 @@ int mg_sp_group_add_task(int pid, unsigned long prot, int spg_id) spin_unlock(&sp_area_lock); if (spa->type == SPA_TYPE_K2SPG && spa->kva) { - addr = sp_remap_kva_to_vma(spa->kva, spa, mm, prot); + addr = sp_remap_kva_to_vma(spa->kva, spa, mm, prot, NULL); if (IS_ERR_VALUE(addr)) pr_warn("add group remap k2u failed %ld\n", addr); @@ -2606,7 +2623,7 @@ static unsigned long __sp_remap_get_pfn(unsigned long kva) /* when called by k2u to group, always make sure rw_lock of spg is down */ static unsigned long sp_remap_kva_to_vma(unsigned long kva, struct sp_area *spa, - struct mm_struct *mm, unsigned long prot) + struct mm_struct *mm, unsigned long prot, struct sp_k2u_context *kc) { struct vm_area_struct *vma; unsigned long ret_addr; @@ -2618,6 +2635,8 @@ static unsigned long sp_remap_kva_to_vma(unsigned long kva, struct sp_area *spa, if (unlikely(mm->core_state)) { pr_err("k2u mmap: encountered coredump, abort\n"); ret_addr = -EBUSY; + if (kc) + kc->state = K2U_COREDUMP; goto put_mm; } @@ -2703,7 +2722,7 @@ static void *sp_make_share_kva_to_task(unsigned long kva, unsigned long size, un spa->kva = kva; - uva = (void *)sp_remap_kva_to_vma(kva, spa, current->mm, prot); + uva = (void *)sp_remap_kva_to_vma(kva, spa, current->mm, prot, NULL); __sp_area_drop(spa); if (IS_ERR(uva)) pr_err("remap k2u to task failed %ld\n", PTR_ERR(uva)); @@ -2731,6 +2750,8 @@ static void *sp_make_share_kva_to_spg(unsigned long kva, unsigned long size, struct mm_struct *mm; struct sp_group_node *spg_node; void *uva = ERR_PTR(-ENODEV); + struct sp_k2u_context kc; + unsigned long ret_addr = -ENODEV; down_read(&spg->rw_lock); spa = sp_alloc_area(size, sp_flags, spg, SPA_TYPE_K2SPG, current->tgid); @@ -2745,12 +2766,17 @@ static void *sp_make_share_kva_to_spg(unsigned long kva, unsigned long size, list_for_each_entry(spg_node, &spg->procs, proc_node) { mm = spg_node->master->mm; - uva = (void *)sp_remap_kva_to_vma(kva, spa, mm, spg_node->prot); - if (IS_ERR(uva)) { + kc.state = K2U_NORMAL; + ret_addr = sp_remap_kva_to_vma(kva, spa, mm, spg_node->prot, &kc); + if (IS_ERR_VALUE(ret_addr)) { + if (kc.state == K2U_COREDUMP) + continue; + uva = (void *)ret_addr; pr_err("remap k2u to spg failed %ld\n", PTR_ERR(uva)); __sp_free(spg, spa->va_start, spa_size(spa), mm); goto out; } + uva = (void *)ret_addr; } out: @@ -2775,18 +2801,6 @@ static bool vmalloc_area_set_flag(unsigned long kva, unsigned long flags) return false; } -struct sp_k2u_context { - unsigned long kva; - unsigned long kva_aligned; - unsigned long size; - unsigned long size_aligned; - unsigned long sp_flags; - int spg_id; - bool to_task; - struct timespec64 start; - struct timespec64 end; -}; - static void trace_sp_k2u_begin(struct sp_k2u_context *kc) { if (!sysctl_sp_perf_k2u) -- 2.25.1

1 1

[PATCH OLK-5.10 0/2]drm/hisilicon: Support hibmc get EDID
by Gou Hao 16 Dec '21

16 Dec '21

bugzilla: https://gitee.com/openeuler/kernel/issues/I469VQ Tian Tao (2): drm/hisilicon: Support i2c driver algorithms for bit-shift adapters drm/hisilicon: Features to support reading resolutions from EDID drivers/gpu/drm/hisilicon/hibmc/Makefile | 2 +- .../gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h | 25 ++++- .../gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c | 99 +++++++++++++++++++ .../gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c | 38 ++++++- 4 files changed, 158 insertions(+), 6 deletions(-) create mode 100644 drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c -- 2.20.1

1 2

[PATCH OLK-5.10 0/2]drm/hisilicon: Support hibmc get EDID
by Gou Hao 16 Dec '21

16 Dec '21

bugzilla: https://gitee.com/openeuler/kernel/issues/I469VQ Tian Tao (2): drm/hisilicon: Support i2c driver algorithms for bit-shift adapters drm/hisilicon: Features to support reading resolutions from EDID drivers/gpu/drm/hisilicon/hibmc/Makefile | 2 +- .../gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h | 25 ++++- .../gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c | 99 +++++++++++++++++++ .../gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c | 38 ++++++- 4 files changed, 158 insertions(+), 6 deletions(-) create mode 100644 drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c -- 2.20.1

1 1

[PATCH openEuler-1.0-LTS v10 00/26] support psi feature
by Liu Xinpeng 16 Dec '21

16 Dec '21

backport psi feature and avoid kabi change bugzilla: https://gitee.com/openeuler/kernel/issues/I47QS2 Changes since v9: 1.There are some problems when allocating cgroups, from Cheng Jian. First. We use `sizeof(struct cgroup_psi)` to allocate more space. This is inappropriate. Second, variable length arrays isn't the last member of cgroups_psi, so the offset of the psi will not be a compile-determined value. It's dangerous to use cgroup_psi(). 2.free path should change too,from Xie Xiuqi. Baruch Siach (1): psi: fix reference to kernel commandline enable Dan Schatzberg (1): kernel/sched/psi.c: expose pressure metrics on root cgroup Johannes Weiner (12): mm: workingset: tell cache transitions from workingset thrashing sched: loadavg: consolidate LOAD_INT, LOAD_FRAC, CALC_LOAD sched: loadavg: make calc_load_n() public sched: sched.h: make rq locking and clock functions available in stats.h sched: introduce this_rq_lock_irq() psi: pressure stall information for CPU, memory, and IO psi: cgroup support psi: make disabling/enabling easier for vendor kernels psi: fix aggregation idle shut-off psi: avoid divide-by-zero crash inside virtual machines fs: kernfs: add poll file operation sched/psi: Fix sampling error and rare div0 crashes with cgroups and high uptime Josef Bacik (1): blk-iolatency: use a percentile approache for ssd's Liu Xinpeng (2): psi:enable psi in config psi:avoid kabi change Miklos Szeredi (1): fuse: ignore PG_workingset after stealing Olof Johansson (1): kernel/sched/psi.c: simplify cgroup_move_task() Suren Baghdasaryan (6): psi: introduce state_mask to represent stalled psi states psi: make psi_enable static psi: rename psi fields in preparation for psi trigger addition psi: split update_stats into parts psi: track changed states include/: refactor headers to allow kthread.h inclusion in psi_types.h Yafang Shao (1): mm, memcg: add workingset_restore in memory.stat Documentation/accounting/psi.txt | 73 +++ Documentation/admin-guide/cgroup-v2.rst | 22 + Documentation/admin-guide/kernel-parameters.txt | 4 + arch/arm64/configs/openeuler_defconfig | 2 + arch/powerpc/platforms/cell/cpufreq_spudemand.c | 2 +- arch/powerpc/platforms/cell/spufs/sched.c | 9 +- arch/s390/appldata/appldata_os.c | 4 - arch/x86/configs/openeuler_defconfig | 2 + block/blk-iolatency.c | 183 +++++- drivers/cpuidle/governors/menu.c | 4 - drivers/spi/spi-rockchip.c | 1 + fs/fuse/dev.c | 1 + fs/kernfs/file.c | 31 +- fs/proc/loadavg.c | 3 - include/linux/cgroup-defs.h | 12 + include/linux/cgroup.h | 17 + include/linux/kernfs.h | 8 + include/linux/kthread.h | 4 + include/linux/page-flags.h | 5 + include/linux/psi.h | 55 ++ include/linux/psi_types.h | 95 +++ include/linux/sched.h | 13 + include/linux/sched/loadavg.h | 24 +- include/linux/swap.h | 1 + include/trace/events/mmflags.h | 1 + init/Kconfig | 28 + kernel/cgroup/cgroup.c | 69 +- kernel/debug/kdb/kdb_main.c | 7 +- kernel/fork.c | 4 + kernel/kthread.c | 3 + kernel/sched/Makefile | 1 + kernel/sched/core.c | 16 +- kernel/sched/loadavg.c | 139 ++-- kernel/sched/psi.c | 823 ++++++++++++++++++++++++ kernel/sched/sched.h | 178 ++--- kernel/sched/stats.h | 86 +++ kernel/workqueue.c | 23 + kernel/workqueue_internal.h | 6 +- mm/compaction.c | 5 + mm/filemap.c | 20 +- mm/huge_memory.c | 1 + mm/migrate.c | 2 + mm/page_alloc.c | 9 + mm/swap_state.c | 1 + mm/vmscan.c | 10 + mm/workingset.c | 113 +++- 46 files changed, 1841 insertions(+), 279 deletions(-) create mode 100644 Documentation/accounting/psi.txt create mode 100644 include/linux/psi.h create mode 100644 include/linux/psi_types.h create mode 100644 kernel/sched/psi.c -- 1.8.3.1

3 28

[PATCH openEuler-1.0-LTS 1/4] time: Normalize timespec64 before timespec64_compare()
by Yang Yingliang 15 Dec '21

15 Dec '21

From: Yu Liao <liaoyu15(a)huawei.com> hulk inclusion category: bugfix bugzilla: 185831, https://gitee.com/openeuler/kernel/issues/I4MO2G CVE: NA ------------------------------------------------- Passing unnormalized timespec64 to timespec64_compare() may cause incorrect results. For example: wall_to_monotonic = {tv_sec = -10, tv_nsec = 900000000} ts_delta = {tv_sec = -9, tv_nsec = -900000000} timespec64_compare() returns -1, but actually wall_to_monotonic > ts_delta. This will cause wall_to_monotonic to become a positive number. Use timespec64_sub() instead of direct subtraction to avoid this. Signed-off-by: Yu Liao <liaoyu15(a)huawei.com> Reviewed-by: Xiongfeng Wang <wangxiongfeng2(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- include/linux/time64.h | 2 ++ kernel/time/timekeeping.c | 3 +-- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/include/linux/time64.h b/include/linux/time64.h index b58142aa0b1dd..e58f59674ad6d 100644 --- a/include/linux/time64.h +++ b/include/linux/time64.h @@ -62,6 +62,8 @@ static inline int timespec64_equal(const struct timespec64 *a, * lhs < rhs: return <0 * lhs == rhs: return 0 * lhs > rhs: return >0 + * + * Note: Both lhs and rhs must be normalized. */ static inline int timespec64_compare(const struct timespec64 *lhs, const struct timespec64 *rhs) { diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 64aa492f79422..17ba0a2f5f5d1 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1236,8 +1236,7 @@ int do_settimeofday64(const struct timespec64 *ts) timekeeping_forward_now(tk); xt = tk_xtime(tk); - ts_delta.tv_sec = ts->tv_sec - xt.tv_sec; - ts_delta.tv_nsec = ts->tv_nsec - xt.tv_nsec; + ts_delta = timespec64_sub(*ts, xt); if (timespec64_compare(&tk->wall_to_monotonic, &ts_delta) > 0) { ret = -EINVAL; -- 2.25.1

1 3

[PATCH] scsi: pm8001: Fix memory leak in pm8001_send_abort_all()
by Jianglei Nie 15 Dec '21

15 Dec '21

openEuler inclusion category: bugfix bugzilla: NA CVE: NA ------------------------ In line 1767, sas_alloc_slow_task() allocates and initializes a sas_task structure. When some errors occur, line 1778 and line 1795 forget to free this structure, which will lead to a memory leak. There is a similar snippet of code in the same file (in function pm8001_send_read_log) as allocating and initializing in line 1812 as well as releasing the memory in line 1822 and line 1867. We can fix it by calling sas_free_task() when the res and ret is true and before the function returns. Signed-off-by: Jianglei Nie <niejianglei2021(a)163.com> --- drivers/scsi/pm8001/pm8001_hwi.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/pm8001/pm8001_hwi.c b/drivers/scsi/pm8001/pm8001_hwi.c index 124cb69740c6..25045a91620e 100644 --- a/drivers/scsi/pm8001/pm8001_hwi.c +++ b/drivers/scsi/pm8001/pm8001_hwi.c @@ -1774,8 +1774,10 @@ static void pm8001_send_abort_all(struct pm8001_hba_info *pm8001_ha, task->task_done = pm8001_task_done; res = pm8001_tag_alloc(pm8001_ha, &ccb_tag); - if (res) + if (res) { + sas_free_task(task); return; + } ccb = &pm8001_ha->ccb_info[ccb_tag]; ccb->device = pm8001_ha_dev; @@ -1791,8 +1793,10 @@ static void pm8001_send_abort_all(struct pm8001_hba_info *pm8001_ha, ret = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &task_abort, sizeof(task_abort), 0); - if (ret) + if (ret) { + sas_free_task(task); pm8001_tag_free(pm8001_ha, ccb_tag); + } } -- 2.25.1

1 0

perf spe-c2c record失败的问题
by haoxin 15 Dec '21

15 Dec '21

您好，我采用最细的openEuler-1.0测试perf spe-c2c的功能，但是发现/sys/devices下没有arm_spe_0这个目录执行perf spe-c2c record时显示： event syntax error: 'arm_spe_0/ts_enable=1,pct_enable=1,pa_enable=1,load_filter=1,jitter=1,store_filter=1,min_latency=0/' \___ Cannot find PMU `arm_spe_0'. Missing kernel support? 想问下您这是为什么？需要哪里开启spe功能吗？

3 2

[PATCH openEuler-1.0-LTS] fix kabi effect by change in md_rdev
by Yang Yingliang 14 Dec '21

14 Dec '21

From: zhangwensheng <zhangwensheng5(a)huawei.com> hulk inclusion category: bugfix bugzilla: 185891 CVE: NA -------------------------------- because enlarge the last_events in md_rdev, to fix the kabi change; Signed-off-by: zhangwensheng <zhangwensheng5(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/md/md.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/md/md.h b/drivers/md/md.h index e745f701e1a82..422af63f1e1ee 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -47,8 +47,16 @@ struct md_rdev { sector_t sectors; /* Device size (in 512bytes sectors) */ struct mddev *mddev; /* RAID array if running */ - long long last_events; /* IO event timestamp */ + /* + * IO event timestamp, this pos has 64 bit space, + * can enlarge it solving its small size. + */ +#ifndef __GENKSYMS__ + long long last_events; +#else + int last_events; +#endif /* * If meta_bdev is non-NULL, it means that a separate device is * being used to store the metadata (superblock/bitmap) which -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] Revert "dm space maps: don't reset space map allocation cursor when committing"
by Yang Yingliang 14 Dec '21

14 Dec '21

From: Luo Meng <luomeng12(a)huawei.com> hulk inclusion category: bugfix bugzilla: 185894, https://gitee.com/openeuler/kernel/issues/I4MITL CVE: NA ----------------------------------------------- This reverts commit 38cb5d45845b9d8962eb26660c14b7f05abc602f. Signed-off-by: Luo Meng <luomeng12(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/md/persistent-data/dm-space-map-disk.c | 9 +-------- drivers/md/persistent-data/dm-space-map-metadata.c | 9 +-------- 2 files changed, 2 insertions(+), 16 deletions(-) diff --git a/drivers/md/persistent-data/dm-space-map-disk.c b/drivers/md/persistent-data/dm-space-map-disk.c index e0acae7a3815d..bf4c5e2ccb6ff 100644 --- a/drivers/md/persistent-data/dm-space-map-disk.c +++ b/drivers/md/persistent-data/dm-space-map-disk.c @@ -171,14 +171,6 @@ static int sm_disk_new_block(struct dm_space_map *sm, dm_block_t *b) * Any block we allocate has to be free in both the old and current ll. */ r = sm_ll_find_common_free_block(&smd->old_ll, &smd->ll, smd->begin, smd->ll.nr_blocks, b); - if (r == -ENOSPC) { - /* - * There's no free block between smd->begin and the end of the metadata device. - * We search before smd->begin in case something has been freed. - */ - r = sm_ll_find_common_free_block(&smd->old_ll, &smd->ll, 0, smd->begin, b); - } - if (r) return r; @@ -207,6 +199,7 @@ static int sm_disk_commit(struct dm_space_map *sm) return r; memcpy(&smd->old_ll, &smd->ll, sizeof(smd->old_ll)); + smd->begin = 0; smd->nr_allocated_this_transaction = 0; r = sm_disk_get_nr_free(sm, &nr_free); diff --git a/drivers/md/persistent-data/dm-space-map-metadata.c b/drivers/md/persistent-data/dm-space-map-metadata.c index da439ac857963..9e3c64ec2026f 100644 --- a/drivers/md/persistent-data/dm-space-map-metadata.c +++ b/drivers/md/persistent-data/dm-space-map-metadata.c @@ -452,14 +452,6 @@ static int sm_metadata_new_block_(struct dm_space_map *sm, dm_block_t *b) * Any block we allocate has to be free in both the old and current ll. */ r = sm_ll_find_common_free_block(&smm->old_ll, &smm->ll, smm->begin, smm->ll.nr_blocks, b); - if (r == -ENOSPC) { - /* - * There's no free block between smm->begin and the end of the metadata device. - * We search before smm->begin in case something has been freed. - */ - r = sm_ll_find_common_free_block(&smm->old_ll, &smm->ll, 0, smm->begin, b); - } - if (r) return r; @@ -511,6 +503,7 @@ static int sm_metadata_commit(struct dm_space_map *sm) return r; memcpy(&smm->old_ll, &smm->ll, sizeof(smm->old_ll)); + smm->begin = 0; smm->allocated_this_transaction = 0; return 0; -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS 1/4] nvme-fabrics: reject I/O to offline device
by Yang Yingliang 14 Dec '21

14 Dec '21

From: Victor Gladkov <victor.gladkov(a)kioxia.com> mainline inclusion from mainline-v5.11-rc1 commit 8c4dfea97f15b80097b3f882ca428fb2751ec30c category: bugfix bugzilla: NA CVE: NA Link: https://gitee.com/openeuler/kernel/issues/I4JFPM?from=project-issue ------------------------------------------------- Commands get stuck while Host NVMe-oF controller is in reconnect state. The controller enters into reconnect state when it loses connection with the target. It tries to reconnect every 10 seconds (default) until a successful reconnect or until the reconnect time-out is reached. The default reconnect time out is 10 minutes. Applications are expecting commands to complete with success or error within a certain timeout (30 seconds by default). The NVMe host is enforcing that timeout while it is connected, but during reconnect the timeout is not enforced and commands may get stuck for a long period or even forever. To fix this long delay due to the default timeout, introduce new "fast_io_fail_tmo" session parameter. The timeout is measured in seconds from the controller reconnect and any command beyond that timeout is rejected. The new parameter value may be passed during 'connect'. The default value of -1 means no timeout (similar to current behavior). Signed-off-by: Victor Gladkov <victor.gladkov(a)kioxia.com> Signed-off-by: Chaitanya Kulkarni <chaitanya.kulkarni(a)wdc.com> Reviewed-by: Hannes Reinecke <hare(a)suse.de> Reviewed-by: Sagi Grimberg <sagi(a)grimberg.me> Reviewed-by: Chao Leng <lengchao(a)huawei.com> Signed-off-by: Christoph Hellwig <hch(a)lst.de> conflicts:: drivers/nvme/host/core.c [adjust context] Signed-off-by: jiangtao <jiangtao62(a)huawei.com> Reviewed-by: chengjike <chengjike.cheng(a)huawei.com> Reviewed-by: Ao Sun <sunao.sun(a)huawei.com> Reviewed-by: Zhenwei Yang <yangzhenwei(a)huawei.com> Reviewed-by: Hou Tao <houtao1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/nvme/host/core.c | 51 +++++++++++++++++++++++++++++++++-- drivers/nvme/host/fabrics.c | 28 ++++++++++++++++--- drivers/nvme/host/fabrics.h | 5 ++++ drivers/nvme/host/multipath.c | 2 ++ drivers/nvme/host/nvme.h | 3 +++ 5 files changed, 83 insertions(+), 6 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index b45ae13aa5fe6..c9ca375a5ddb9 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -130,6 +130,37 @@ static void nvme_queue_scan(struct nvme_ctrl *ctrl) queue_work(nvme_wq, &ctrl->scan_work); } +static void nvme_failfast_work(struct work_struct *work) +{ + struct nvme_ctrl *ctrl = container_of(to_delayed_work(work), + struct nvme_ctrl, failfast_work); + + if (ctrl->state != NVME_CTRL_CONNECTING) + return; + + set_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags); + dev_info(ctrl->device, "failfast expired\n"); + nvme_kick_requeue_lists(ctrl); +} + +static inline void nvme_start_failfast_work(struct nvme_ctrl *ctrl) +{ + if (!ctrl->opts || ctrl->opts->fast_io_fail_tmo == -1) + return; + + schedule_delayed_work(&ctrl->failfast_work, + ctrl->opts->fast_io_fail_tmo * HZ); +} + +static inline void nvme_stop_failfast_work(struct nvme_ctrl *ctrl) +{ + if (!ctrl->opts) + return; + + cancel_delayed_work_sync(&ctrl->failfast_work); + clear_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags); +} + int nvme_reset_ctrl(struct nvme_ctrl *ctrl) { if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING)) @@ -385,8 +416,21 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, ctrl->state = new_state; spin_unlock_irqrestore(&ctrl->lock, flags); - if (changed && ctrl->state == NVME_CTRL_LIVE) - nvme_kick_requeue_lists(ctrl); + if (changed) { + switch (ctrl->state) { + case NVME_CTRL_LIVE: + if (old_state == NVME_CTRL_CONNECTING) + nvme_stop_failfast_work(ctrl); + nvme_kick_requeue_lists(ctrl); + break; + case NVME_CTRL_CONNECTING: + if (old_state == NVME_CTRL_RESETTING) + nvme_start_failfast_work(ctrl); + break; + default: + break; + } + } return changed; } EXPORT_SYMBOL_GPL(nvme_change_ctrl_state); @@ -3712,6 +3756,7 @@ void nvme_stop_ctrl(struct nvme_ctrl *ctrl) { nvme_mpath_stop(ctrl); nvme_stop_keep_alive(ctrl); + nvme_stop_failfast_work(ctrl); flush_work(&ctrl->async_event_work); cancel_work_sync(&ctrl->fw_act_work); if (ctrl->ops->stop_ctrl) @@ -3776,6 +3821,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, int ret; ctrl->state = NVME_CTRL_NEW; + clear_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags); spin_lock_init(&ctrl->lock); mutex_init(&ctrl->scan_lock); INIT_LIST_HEAD(&ctrl->namespaces); @@ -3791,6 +3837,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, INIT_DELAYED_WORK(&ctrl->ka_work, nvme_keep_alive_work); memset(&ctrl->ka_cmd, 0, sizeof(ctrl->ka_cmd)); ctrl->ka_cmd.common.opcode = nvme_admin_keep_alive; + INIT_DELAYED_WORK(&ctrl->failfast_work, nvme_failfast_work); BUILD_BUG_ON(NVME_DSM_MAX_RANGES * sizeof(struct nvme_dsm_range) > PAGE_SIZE); diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index 738794af3f389..650b3bd89968f 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -550,6 +550,7 @@ blk_status_t nvmf_fail_nonready_command(struct nvme_ctrl *ctrl, { if (ctrl->state != NVME_CTRL_DELETING && ctrl->state != NVME_CTRL_DEAD && + !test_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags) && !blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH)) return BLK_STS_RESOURCE; @@ -607,6 +608,7 @@ static const match_table_t opt_tokens = { { NVMF_OPT_HOST_TRADDR, "host_traddr=%s" }, { NVMF_OPT_HOST_ID, "hostid=%s" }, { NVMF_OPT_DUP_CONNECT, "duplicate_connect" }, + { NVMF_OPT_FAIL_FAST_TMO, "fast_io_fail_tmo=%d" }, { NVMF_OPT_ERR, NULL } }; @@ -626,6 +628,7 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, opts->reconnect_delay = NVMF_DEF_RECONNECT_DELAY; opts->kato = NVME_DEFAULT_KATO; opts->duplicate_connect = false; + opts->fast_io_fail_tmo = NVMF_DEF_FAIL_FAST_TMO; options = o = kstrdup(buf, GFP_KERNEL); if (!options) @@ -750,6 +753,17 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, pr_warn("ctrl_loss_tmo < 0 will reconnect forever\n"); ctrl_loss_tmo = token; break; + case NVMF_OPT_FAIL_FAST_TMO: + if (match_int(args, &token)) { + ret = -EINVAL; + goto out; + } + + if (token >= 0) + pr_warn("I/O will fail on after %d sec reconnect\n", + token); + opts->fast_io_fail_tmo = token; + break; case NVMF_OPT_HOSTNQN: if (opts->host) { pr_err("hostnqn already user-assigned: %s\n", @@ -830,11 +844,17 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, opts->nr_io_queues = 0; opts->duplicate_connect = true; } - if (ctrl_loss_tmo < 0) + + if (ctrl_loss_tmo < 0) { opts->max_reconnects = -1; - else + } else { opts->max_reconnects = DIV_ROUND_UP(ctrl_loss_tmo, opts->reconnect_delay); + if (ctrl_loss_tmo < opts->fast_io_fail_tmo) + pr_warn("failfast tmo (%d) > ctrl_loss_tmo (%d)\n", + opts->fast_io_fail_tmo, + ctrl_loss_tmo); + } if (!opts->host) { kref_get(&nvmf_default_host->ref); @@ -903,8 +923,8 @@ EXPORT_SYMBOL_GPL(nvmf_free_options); #define NVMF_REQUIRED_OPTS (NVMF_OPT_TRANSPORT | NVMF_OPT_NQN) #define NVMF_ALLOWED_OPTS (NVMF_OPT_QUEUE_SIZE | NVMF_OPT_NR_IO_QUEUES | \ NVMF_OPT_KATO | NVMF_OPT_HOSTNQN | \ - NVMF_OPT_HOST_ID | NVMF_OPT_DUP_CONNECT) - + NVMF_OPT_HOST_ID | NVMF_OPT_DUP_CONNECT |\ + NVMF_OPT_FAIL_FAST_TMO) static struct nvme_ctrl * nvmf_create_ctrl(struct device *dev, const char *buf, size_t count) { diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h index 188ebbeec32ce..645ed75f22980 100644 --- a/drivers/nvme/host/fabrics.h +++ b/drivers/nvme/host/fabrics.h @@ -24,6 +24,8 @@ /* default to 600 seconds of reconnect attempts before giving up */ #define NVMF_DEF_CTRL_LOSS_TMO 600 #define NVMF_DEF_RECONNECT_FOREVER -1 +/* default is -1: the fail fast mechanism is disabled */ +#define NVMF_DEF_FAIL_FAST_TMO -1 /* * Define a host as seen by the target. We allocate one at boot, but also @@ -59,6 +61,7 @@ enum { NVMF_OPT_CTRL_LOSS_TMO = 1 << 11, NVMF_OPT_HOST_ID = 1 << 12, NVMF_OPT_DUP_CONNECT = 1 << 13, + NVMF_OPT_FAIL_FAST_TMO = 1 << 20, }; /** @@ -86,6 +89,7 @@ enum { * @max_reconnects: maximum number of allowed reconnect attempts before removing * the controller, (-1) means reconnect forever, zero means remove * immediately; + * @fast_io_fail_tmo: Fast I/O fail timeout in seconds */ struct nvmf_ctrl_options { unsigned mask; @@ -102,6 +106,7 @@ struct nvmf_ctrl_options { unsigned int kato; struct nvmf_host *host; int max_reconnects; + int fast_io_fail_tmo; }; /* diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index f4616df1f7f15..9201946568630 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -198,6 +198,8 @@ static bool nvme_available_path(struct nvme_ns_head *head) struct nvme_ns *ns; list_for_each_entry_rcu(ns, &head->list, siblings) { + if (test_bit(NVME_CTRL_FAILFAST_EXPIRED, &ns->ctrl->flags)) + continue; switch (ns->ctrl->state) { case NVME_CTRL_LIVE: case NVME_CTRL_RESETTING: diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 85f814a91ce9c..cd66364eb5429 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -211,6 +211,7 @@ struct nvme_ctrl { struct work_struct scan_work; struct work_struct async_event_work; struct delayed_work ka_work; + struct delayed_work failfast_work; struct nvme_command ka_cmd; struct work_struct fw_act_work; unsigned long events; @@ -245,6 +246,8 @@ struct nvme_ctrl { u16 icdoff; u16 maxcmd; int nr_reconnects; + unsigned long flags; +#define NVME_CTRL_FAILFAST_EXPIRED 0 struct nvmf_ctrl_options *opts; struct page *discard_page; -- 2.25.1

1 3

[PATCH openEuler-1.0-LTS 01/12] nvme: add proper discard setup for the multipath device
by Yang Yingliang 14 Dec '21

14 Dec '21

From: Christoph Hellwig <hch(a)lst.de> mainline inclusion from mainline-v5.1-rc1 commit 2631857160ecbea04e54423f5053133fe2b6ea45 category: bugfix bugzilla: NA CVE: NA Link: https://gitee.com/openeuler/kernel/issues/I4JFBE?from=project-issue ------------------------------------------------- Add a gendisk argument to nvme_config_discard so that the call to nvme_update_disk_info for the multipath device node updates the proper request_queue. Signed-off-by: Christoph Hellwig <hch(a)lst.de> Reported-by: Sagi Grimberg <sagi(a)grimberg.me> Reviewed-by: Keith Busch <keith.busch(a)intel.com> Reviewed-by: Max Gurtovoy <maxg(a)mellanox.com> Tested-by: Sagi Grimberg <sagi(a)grimberg.me> Signed-off-by: Jens Axboe <axboe(a)kernel.dk> conflicts: drivers/nvme/host/core.c [adjust context] Signed-off-by: chengjike <chengjike.cheng(a)huawei.com> Reviewed-by: Ao Sun <sunao.sun(a)huawei.com> Reviewed-by: Zhenwei Yang <yangzhenwei(a)huawei.com> Reviewed-by: Hou Tao <houtao1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/nvme/host/core.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 522ab9c0133ca..7c4a97e2cd93a 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1558,10 +1558,10 @@ static void nvme_set_chunk_size(struct nvme_ns *ns) blk_queue_chunk_sectors(ns->queue, rounddown_pow_of_two(chunk_size)); } -static void nvme_config_discard(struct nvme_ns *ns) +static void nvme_config_discard(struct gendisk *disk, struct nvme_ns *ns) { struct nvme_ctrl *ctrl = ns->ctrl; - struct request_queue *queue = ns->queue; + struct request_queue *queue = disk->queue; u32 size = queue_logical_block_size(queue); if (!(ctrl->oncs & NVME_CTRL_ONCS_DSM)) { @@ -1647,7 +1647,7 @@ static void nvme_update_disk_info(struct gendisk *disk, capacity = 0; set_capacity(disk, capacity); - nvme_config_discard(ns); + nvme_config_discard(disk, ns); if (id->nsattr & (1 << 0)) set_disk_ro(disk, true); -- 2.25.1

1 11

[PATCH openEuler-1.0-LTS 1/2] md: Fix undefined behaviour in is_mddev_idle
by Yang Yingliang 14 Dec '21

14 Dec '21

From: zhangwensheng <zhangwensheng5(a)huawei.com> hulk inclusion category: bugfix bugzilla: 185891 CVE: NA -------------------------------- UBSAN reports this problem: [ 5984.281385] UBSAN: Undefined behaviour in drivers/md/md.c:8175:15 [ 5984.281390] signed integer overflow: [ 5984.281393] -2147483291 - 2072033152 cannot be represented in type 'int' [ 5984.281400] CPU: 25 PID: 1854 Comm: md101_resync Kdump: loaded Not tainted 4.19.90 [ 5984.281404] Hardware name: Huawei TaiShan 200 (Model 5280)/BC82AMDDA [ 5984.281406] Call trace: [ 5984.281415] dump_backtrace+0x0/0x310 [ 5984.281418] show_stack+0x28/0x38 [ 5984.281425] dump_stack+0xec/0x15c [ 5984.281430] ubsan_epilogue+0x18/0x84 [ 5984.281434] handle_overflow+0x14c/0x19c [ 5984.281439] __ubsan_handle_sub_overflow+0x34/0x44 [ 5984.281445] is_mddev_idle+0x338/0x3d8 [ 5984.281449] md_do_sync+0x1bb8/0x1cf8 [ 5984.281452] md_thread+0x220/0x288 [ 5984.281457] kthread+0x1d8/0x1e0 [ 5984.281461] ret_from_fork+0x10/0x18 When the stat aacum of the disk is greater than INT_MAX, its value becomes negative after casting to 'int', which may lead to overflow after subtracting a positive number. In the same way, when the value of sync_io is greater than INT_MAX,overflow may also occur. These situations will lead to undefined behavior. Otherwise, if the stat accum of the disk is close to INT_MAX when creating raid arrays, the initial value of last_events would be set close to INT_MAX when mddev initializes IO event counters. 'curr_events - rdev->last_events > 64' will always false during synchronization. If all the disks of mddev are in this case, is_mddev_idle() will always return 1, which may cause non-sync IO is very slow. To address these problems, need to use 64bit signed integer type for sync_io,last_events, and curr_events. Signed-off-by: zhangwensheng <zhangwensheng5(a)huawei.com> Reviewed-by: Hou Tao <houtao1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/md/md.c | 7 ++++--- drivers/md/md.h | 6 +++--- include/linux/genhd.h | 2 +- 3 files changed, 8 insertions(+), 7 deletions(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index 409ec5ffd28d3..8a68ff71fbbf8 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -8161,14 +8161,15 @@ static int is_mddev_idle(struct mddev *mddev, int init) { struct md_rdev *rdev; int idle; - int curr_events; + long long curr_events; idle = 1; rcu_read_lock(); rdev_for_each_rcu(rdev, mddev) { struct gendisk *disk = rdev->bdev->bd_contains->bd_disk; - curr_events = (int)part_stat_read_accum(&disk->part0, sectors) - - atomic_read(&disk->sync_io); + curr_events = + (long long)part_stat_read_accum(&disk->part0, sectors) - + atomic64_read(&disk->sync_io_sectors); /* sync IO will cause sync_io to increase before the disk_stats * as sync_io is counted when a request starts, and * disk_stats is counted when it completes. diff --git a/drivers/md/md.h b/drivers/md/md.h index ee3c9768ff9e7..e745f701e1a82 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -47,7 +47,7 @@ struct md_rdev { sector_t sectors; /* Device size (in 512bytes sectors) */ struct mddev *mddev; /* RAID array if running */ - int last_events; /* IO event timestamp */ + long long last_events; /* IO event timestamp */ /* * If meta_bdev is non-NULL, it means that a separate device is @@ -528,12 +528,12 @@ extern void mddev_unlock(struct mddev *mddev); static inline void md_sync_acct(struct block_device *bdev, unsigned long nr_sectors) { - atomic_add(nr_sectors, &bdev->bd_contains->bd_disk->sync_io); + atomic64_add(nr_sectors, &bdev->bd_contains->bd_disk->sync_io_sectors); } static inline void md_sync_acct_bio(struct bio *bio, unsigned long nr_sectors) { - atomic_add(nr_sectors, &bio->bi_disk->sync_io); + atomic64_add(nr_sectors, &bio->bi_disk->sync_io_sectors); } struct md_personality diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 9c398294b6279..38737c853b28d 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -212,7 +212,6 @@ struct gendisk { struct kobject *slave_dir; struct timer_rand_state *random; - atomic_t sync_io; /* RAID */ struct disk_events *ev; #ifdef CONFIG_BLK_DEV_INTEGRITY struct kobject integrity_kobj; @@ -220,6 +219,7 @@ struct gendisk { int node_id; struct badblocks *bb; struct lockdep_map lockdep_map; + atomic64_t sync_io_sectors; /* RAID */ #ifndef __GENKSYMS__ unsigned long *user_ro_bitmap; -- 2.25.1

1 1

[PATCH openEuler-1.0-LTS 1/4] xfs: ensure that the inode uid/gid match values match the icdinode ones
by Yang Yingliang 14 Dec '21

14 Dec '21

From: Christoph Hellwig <hch(a)lst.de> mainline inclusion from mainline-v5.6-rc4 commit 3d8f2821502d0b60bac2789d0bea951fda61de0c category: bugfix bugzilla: 185881 CVE: CVE-2021-4037 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ------------------------------------------------- Instead of only synchronizing the uid/gid values in xfs_setup_inode, ensure that they always match to prepare for removing the icdinode fields. Signed-off-by: Christoph Hellwig <hch(a)lst.de> Reviewed-by: Darrick J. Wong <darrick.wong(a)oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong(a)oracle.com> Signed-off-by: Guo Xuenan <guoxuenan(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/xfs/libxfs/xfs_inode_buf.c | 2 ++ fs/xfs/xfs_icache.c | 4 ++++ fs/xfs/xfs_inode.c | 8 ++++++-- fs/xfs/xfs_iops.c | 3 --- 4 files changed, 12 insertions(+), 5 deletions(-) diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index 82c4374acb4c6..ed58741e09ea8 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -225,7 +225,9 @@ xfs_inode_from_disk( to->di_format = from->di_format; to->di_uid = be32_to_cpu(from->di_uid); + inode->i_uid = xfs_uid_to_kuid(to->di_uid); to->di_gid = be32_to_cpu(from->di_gid); + inode->i_gid = xfs_gid_to_kgid(to->di_gid); to->di_flushiter = be16_to_cpu(from->di_flushiter); /* diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 56e9043bddc71..ceee27b703842 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -286,6 +286,8 @@ xfs_reinit_inode( uint64_t version = inode_peek_iversion(inode); umode_t mode = inode->i_mode; dev_t dev = inode->i_rdev; + kuid_t uid = inode->i_uid; + kgid_t gid = inode->i_gid; error = inode_init_always(mp->m_super, inode); @@ -294,6 +296,8 @@ xfs_reinit_inode( inode_set_iversion_queried(inode, version); inode->i_mode = mode; inode->i_rdev = dev; + inode->i_uid = uid; + inode->i_gid = gid; return error; } diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index c3226c48079da..70d5f0e2aa129 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -812,15 +812,19 @@ xfs_ialloc( inode->i_mode = mode; set_nlink(inode, nlink); - ip->i_d.di_uid = xfs_kuid_to_uid(current_fsuid()); - ip->i_d.di_gid = xfs_kgid_to_gid(current_fsgid()); + inode->i_uid = current_fsuid(); + ip->i_d.di_uid = xfs_kuid_to_uid(inode->i_uid); inode->i_rdev = rdev; xfs_set_projid(ip, prid); if (pip && XFS_INHERIT_GID(pip)) { + inode->i_gid = VFS_I(pip)->i_gid; ip->i_d.di_gid = pip->i_d.di_gid; if ((VFS_I(pip)->i_mode & S_ISGID) && S_ISDIR(mode)) inode->i_mode |= S_ISGID; + } else { + inode->i_gid = current_fsgid(); + ip->i_d.di_gid = xfs_kgid_to_gid(inode->i_gid); } /* diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 0ac63cafb32a1..2c9d2d2f92983 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -1305,9 +1305,6 @@ xfs_setup_inode( /* make the inode look hashed for the writeback code */ inode_fake_hash(inode); - inode->i_uid = xfs_uid_to_kuid(ip->i_d.di_uid); - inode->i_gid = xfs_gid_to_kgid(ip->i_d.di_gid); - i_size_write(inode, ip->i_d.di_size); xfs_diflags_to_iflags(inode, ip); -- 2.25.1

1 3

[PATCH openEuler-1.0-LTS] configfs: fix a use-after-free in __configfs_open_file
by Yang Yingliang 14 Dec '21

14 Dec '21

From: Daiyue Zhang <zhangdaiyue1(a)huawei.com> mainline inclusion from mainline-v5.12-rc3 commit 14fbbc8297728e880070f7b077b3301a8c698ef9 category: bugfix bugzilla: NA CVE: CVE-2021-39656 ----------------------------------------------- Commit b0841eefd969 ("configfs: provide exclusion between IO and removals") uses ->frag_dead to mark the fragment state, thus no bothering with extra refcount on config_item when opening a file. The configfs_get_config_item was removed in __configfs_open_file, but not with config_item_put. So the refcount on config_item will lost its balance, causing use-after-free issues in some occasions like this: Test: 1. Mount configfs on /config with read-only items: drwxrwx--- 289 root root 0 2021-04-01 11:55 /config drwxr-xr-x 2 root root 0 2021-04-01 11:54 /config/a --w--w--w- 1 root root 4096 2021-04-01 11:53 /config/a/1.txt ...... 2. Then run: for file in /config do echo $file grep -R 'key' $file done 3. __configfs_open_file will be called in parallel, the first one got called will do: if (file->f_mode & FMODE_READ) { if (!(inode->i_mode & S_IRUGO)) goto out_put_module; config_item_put(buffer->item); kref_put() package_details_release() kfree() the other one will run into use-after-free issues like this: BUG: KASAN: use-after-free in __configfs_open_file+0x1bc/0x3b0 Read of size 8 at addr fffffff155f02480 by task grep/13096 CPU: 0 PID: 13096 Comm: grep VIP: 00 Tainted: G W 4.14.116-kasan #1 TGID: 13096 Comm: grep Call trace: dump_stack+0x118/0x160 kasan_report+0x22c/0x294 __asan_load8+0x80/0x88 __configfs_open_file+0x1bc/0x3b0 configfs_open_file+0x28/0x34 do_dentry_open+0x2cc/0x5c0 vfs_open+0x80/0xe0 path_openat+0xd8c/0x2988 do_filp_open+0x1c4/0x2fc do_sys_open+0x23c/0x404 SyS_openat+0x38/0x48 Allocated by task 2138: kasan_kmalloc+0xe0/0x1ac kmem_cache_alloc_trace+0x334/0x394 packages_make_item+0x4c/0x180 configfs_mkdir+0x358/0x740 vfs_mkdir2+0x1bc/0x2e8 SyS_mkdirat+0x154/0x23c el0_svc_naked+0x34/0x38 Freed by task 13096: kasan_slab_free+0xb8/0x194 kfree+0x13c/0x910 package_details_release+0x524/0x56c kref_put+0xc4/0x104 config_item_put+0x24/0x34 __configfs_open_file+0x35c/0x3b0 configfs_open_file+0x28/0x34 do_dentry_open+0x2cc/0x5c0 vfs_open+0x80/0xe0 path_openat+0xd8c/0x2988 do_filp_open+0x1c4/0x2fc do_sys_open+0x23c/0x404 SyS_openat+0x38/0x48 el0_svc_naked+0x34/0x38 To fix this issue, remove the config_item_put in __configfs_open_file to balance the refcount of config_item. Fixes: b0841eefd969 ("configfs: provide exclusion between IO and removals") Signed-off-by: Daiyue Zhang <zhangdaiyue1(a)huawei.com> Signed-off-by: Yi Chen <chenyi77(a)huawei.com> Signed-off-by: Ge Qiu <qiuge(a)huawei.com> Reviewed-by: Chao Yu <yuchao0(a)huawei.com> Acked-by: Al Viro <viro(a)zeniv.linux.org.uk> Signed-off-by: Christoph Hellwig <hch(a)lst.de> Signed-off-by: Ye Bin <yebin10(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Reviewed-by: weiyang wang <wangweiyang2(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/configfs/file.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/fs/configfs/file.c b/fs/configfs/file.c index bb0a427517e92..50b7c4c4310e0 100644 --- a/fs/configfs/file.c +++ b/fs/configfs/file.c @@ -392,7 +392,7 @@ static int __configfs_open_file(struct inode *inode, struct file *file, int type attr = to_attr(dentry); if (!attr) - goto out_put_item; + goto out_free_buffer; if (type & CONFIGFS_ITEM_BIN_ATTR) { buffer->bin_attr = to_bin_attr(dentry); @@ -405,7 +405,7 @@ static int __configfs_open_file(struct inode *inode, struct file *file, int type /* Grab the module reference for this attribute if we have one */ error = -ENODEV; if (!try_module_get(buffer->owner)) - goto out_put_item; + goto out_free_buffer; error = -EACCES; if (!buffer->item->ci_type) @@ -449,8 +449,6 @@ static int __configfs_open_file(struct inode *inode, struct file *file, int type out_put_module: module_put(buffer->owner); -out_put_item: - config_item_put(buffer->item); out_free_buffer: up_read(&frag->frag_sem); kfree(buffer); -- 2.25.1

1 0

[PATCH] vfio/iommu_type1: replace kfree with kvfree
by Jiacheng Shi 13 Dec '21

13 Dec '21

Variables allocated by kvmalloc should not be freed by kfree. Because they may be allocated by vmalloc. So we replace kfree with kvfree here. Fixes: 738fe155f58b ("vfio/iommu_type1: Add support for manual dirty log clear") Signed-off-by: Jiacheng Shi <billsjc(a)sjtu.edu.cn> --- drivers/vfio/vfio_iommu_type1.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 5daceec48811..6811a85109aa 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -1150,7 +1150,7 @@ static int vfio_iova_dirty_log_clear(u64 __user *bitmap, } out: - kfree(bitmap_buffer); + kvfree(bitmap_buffer); return ret; } -- 2.17.1

3 4

[PATCH openEuler-1.0-LTS 1/2] share_pool: Remove the redundant warning message
by Yang Yingliang 13 Dec '21

13 Dec '21

From: Ding Tianhong <dingtianhong(a)huawei.com> ascend inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4M253 CVE: NA ------------------------------------------------- No need to record the redundant message for out of memory, the kernel already handle it when oom. Signed-off-by: Ding Tianhong <dingtianhong(a)huawei.com> Reviewed-by: Weilong Chen <chenweilong(a)huawei.com> Reviewed-by: Hanjun Guo <guohanjun(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- mm/share_pool.c | 20 +++++--------------- 1 file changed, 5 insertions(+), 15 deletions(-) diff --git a/mm/share_pool.c b/mm/share_pool.c index 2cc15f894cf84..ea61f69cdd6ad 100644 --- a/mm/share_pool.c +++ b/mm/share_pool.c @@ -137,10 +137,8 @@ static struct sp_group_master *sp_init_group_master_locked( } master = kmalloc(sizeof(struct sp_group_master), GFP_KERNEL); - if (master == NULL) { - pr_err_ratelimited("no memory for spg master\n"); + if (master == NULL) return ERR_PTR(-ENOMEM); - } INIT_LIST_HEAD(&master->node_list); master->count = 0; @@ -192,10 +190,8 @@ static struct sp_proc_stat *create_proc_stat(struct mm_struct *mm, struct sp_proc_stat *stat; stat = kmalloc(sizeof(*stat), GFP_KERNEL); - if (stat == NULL) { - pr_err_ratelimited("no memory for proc stat\n"); + if (stat == NULL) return ERR_PTR(-ENOMEM); - } atomic_set(&stat->use_count, 1); atomic64_set(&stat->alloc_size, 0); @@ -342,10 +338,8 @@ static struct spg_proc_stat *create_spg_proc_stat(int tgid, int spg_id) struct spg_proc_stat *stat; stat = kmalloc(sizeof(struct spg_proc_stat), GFP_KERNEL); - if (stat == NULL) { - pr_err_ratelimited("no memory for spg proc stat\n"); + if (stat == NULL) return ERR_PTR(-ENOMEM); - } stat->tgid = tgid; stat->spg_id = spg_id; @@ -413,10 +407,8 @@ static struct sp_spg_stat *create_spg_stat(int spg_id) struct sp_spg_stat *stat; stat = kmalloc(sizeof(*stat), GFP_KERNEL); - if (stat == NULL) { - pr_err_ratelimited("no memory for spg stat\n"); + if (stat == NULL) return ERR_PTR(-ENOMEM); - } stat->spg_id = spg_id; atomic_set(&stat->hugepage_failures, 0); @@ -1624,10 +1616,8 @@ static struct sp_area *sp_alloc_area(unsigned long size, unsigned long flags, } spa = __kmalloc_node(sizeof(struct sp_area), GFP_KERNEL, node_id); - if (unlikely(!spa)) { - pr_err_ratelimited("no memory for spa\n"); + if (unlikely(!spa)) return ERR_PTR(-ENOMEM); - } spin_lock(&sp_area_lock); -- 2.25.1

1 1

[PATCH OLK-5.10 000/107] NTFS read-write driver GPL implementation by Paragon Software
by Yin Xiujiang 13 Dec '21

13 Dec '21

This patch adds NTFS Read-Write driver to fs/ntfs3. Having decades of expertise in commercial file systems development and huge test coverage, we at Paragon Software GmbH want to make our contribution to the Open Source Community by providing implementation of NTFS Read-Write driver for the Linux Kernel. This is fully functional NTFS Read-Write driver. Current version works with NTFS(including v3.1) and normal/compressed/sparse files and supports journal replaying. We plan to support this version after the codebase once merged, and add new features and fix bugs. For example, full journaling support over JBD will be added in later updates. v2: - patch splitted to chunks (file-wise) - build issues fixed - sparse and checkpatch.pl errors fixed - NULL pointer dereference on mkfs.ntfs-formatted volume mount fixed - cosmetics + code cleanup v3: - added acl, noatime, no_acs_rules, prealloc mount options - added fiemap support - fixed encodings support - removed typedefs - adapted Kernel-way logging mechanisms - fixed typos and corner-case issues v4: - atomic_open() refactored - code style updated - bugfixes v5: - nls/nls_alt mount options added - Unicode conversion fixes - Improved very fragmented files operations - logging cosmetics v6: - Security Descriptors processing changed added system.ntfs_security xattr to set SD - atomic_open() optimized - cosmetics Christophe JAILLET (2): fs/ntfs3: Remove a useless test in 'indx_find()' fs/ntfs3: Remove a useless shadowing variable Colin Ian King (4): fs/ntfs3: Fix various spelling mistakes fs/ntfs3: Fix integer overflow in multiplication fs/ntfs3: Remove redundant initialization of variable err fs/ntfs3: Fix a memory leak on object opts Dan Carpenter (5): fs/ntfs3: add checks for allocation failure fs/ntfs3: fix an error code in ntfs_get_acl_ex() fs/ntfs3: Fix error code in indx_add_allocate() fs/ntfs3: Potential NULL dereference in hdr_find_split() fs/ntfs3: Fix error handling in indx_insert_into_root() Gustavo A. R. Silva (1): fs/ntfs3: Fix fall-through warnings for Clang Jiapeng Chong (1): fs/ntfs3: Remove unused including <linux/version.h> Kari Argillander (54): fs/ntfs3: Use linux/log2 is_power_of_2 function fs/ntfs3: Add ifndef + define to all header files fs/ntfs3: Fix one none utf8 char in source file fs/ntfs3: Restyle comment block in ni_parse_reparse() fs/ntfs3: Use kernel ALIGN macros over driver specific fs/ntfs3: Do not use driver own alloc wrappers fs/ntfs3: Use kcalloc/kmalloc_array over kzalloc/kmalloc fs/ntfs3: Restyle comments to better align with kernel-doc fs/ntfs3: Remove fat ioctl's from ntfs3 driver for now fs/ntfs3: Fix integer overflow in ni_fiemap with fiemap_prep() fs/ntfs3: Remove unnecessary condition checking from ntfs_file_read_iter fs/ntfs3: Remove GPL boilerplates from decompress lib files fs/ntfs3: Change how module init/info messages are displayed fs/ntfs3: Remove unnecesarry mount option noatime fs/ntfs3: Remove unnecesarry remount flag handling fs/ntfs3: Convert mount options to pointer in sbi fs/ntfs3: Use new api for mounting fs/ntfs3: Init spi more in init_fs_context than fill_super fs/ntfs3: Make mount option nohidden more universal fs/ntfs3: Add iocharset= mount option as alias for nls= fs/ntfs3: Rename mount option no_acs_rules > (no)acsrules fs/ntfs3: Show uid/gid always in show_options() fs/ntfs3. Add forward declarations for structs to debug.h fs/ntfs3: Add missing header files to ntfs.h fs/ntfs3: Add missing headers and forward declarations to ntfs_fs.h fs/ntfs3: Add missing header and guards to lib/ headers fs/ntfs3: Change right headers to bitfunc.c fs/ntfs3: Change right headers to upcase.c fs/ntfs3: Change right headers to lznt.c fs/ntfs3: Remove unneeded header files from c files fs/ntfs3: Limit binary search table size fs/ntfs3: Make binary search to search smaller chunks in beginning fs/ntfs3: Always use binary search with entry search fs/ntfs3: Remove '+' before constant in ni_insert_resident() fs/ntfs3: Place Comparisons constant right side of the test fs/ntfs3: Remove braces from single statment block fs/ntfs3: Remove tabs before spaces from comment fs/ntfs3: Fix ntfs_look_for_free_space() does only report -ENOSPC fs/ntfs3: Remove always false condition check fs/ntfs3: Use clamp/max macros instead of comparisons fs/ntfs3: Use min/max macros instated of ternary operators fs/ntfs3: Fix wrong error message $Logfile -> $UpCase fs/ntfs3: Change EINVAL to ENOMEM when d_make_root fails fs/ntfs3: Remove impossible fault condition in fill_super fs/ntfs3: Return straight without goto in fill_super fs/ntfs3: Remove unnecessary variable loading in fill_super fs/ntfs3: Use sb instead of sbi->sb in fill_super fs/ntfs3: Remove tmp var is_ro in ntfs_fill_super fs/ntfs3: Remove tmp pointer bd_inode in fill_super fs/ntfs3: Remove tmp pointer upcase in fill_super fs/ntfs3: Initialize pointer before use place in fill_super fs/ntfs3: Initiliaze sb blocksize only in one place + refactor Doc/fs/ntfs3: Fix rst format and make it cleaner fs/ntfs3: Remove deprecated mount options nls Konstantin Komarov (37): fs/ntfs3: Add headers and misc files fs/ntfs3: Add initialization of super block fs/ntfs3: Add bitmap fs/ntfs3: Add file operations and implementation fs/ntfs3: Add attrib operations fs/ntfs3: Add compression fs/ntfs3: Add NTFS journal fs/ntfs3: Add Kconfig, Makefile and doc fs/ntfs3: Add NTFS3 in fs/Kconfig and fs/Makefile fs/ntfs3: Rework file operations fs/ntfs3: Restyle comments to better align with kernel-doc fs/ntfs3: Fix insertion of attr in ni_ins_attr_ext fs/ntfs3: Change max hardlinks limit to 4000 fs/ntfs3: Add sync flag to ntfs_sb_write_run and al_update fs/ntfs3: Fix logical error in ntfs_create_inode fs/ntfs3: Move ni_lock_dir and ni_unlock into ntfs_create_inode fs/ntfs3: Refactor ntfs_get_acl_ex for better readability fs/ntfs3: Pass flags to ntfs_set_ea in ntfs_set_acl_ex fs/ntfs3: Change posix_acl_equiv_mode to posix_acl_update_mode fs/ntfs3: Refactoring lock in ntfs_init_acl fs/ntfs3: Reject mount if boot's cluster size < media sector size fs/ntfs3: Refactoring of ntfs_init_from_boot fs/ntfs3: Check for NULL if ATTR_EA_INFO is incorrect fs/ntfs3: Use available posix_acl_release instead of ntfs_posix_acl_release fs/ntfs3: Remove locked argument in ntfs_set_ea fs/ntfs3: Refactoring of ntfs_set_ea fs/ntfs3: Forbid FALLOC_FL_PUNCH_HOLE for normal files fs/ntfs3: Remove unnecessary functions fs/ntfs3: Keep prealloc for all types of files fs/ntfs3: Fix memory leak if fill_super failed fs/ntfs3: Rework ntfs_utf16_to_nls fs/ntfs3: Refactor ntfs_readlink_hlp fs/ntfs3: Refactor ntfs_create_inode fs/ntfs3: Refactor ni_parse_reparse fs/ntfs3: Refactor ntfs_read_mft fs/ntfs3: Check for NULL pointers in ni_try_remove_attr_list fs/ntfs3: Add MAINTAINERS Nathan Chancellor (1): fs/ntfs3: Remove unused variable cnt in ntfs_security_init() Yin Xiujiang (2): fs/ntfs3: Fix the issue from backport 5.15 to 5.10 fs/ntfs3: Add ntfs3 module in openeuler_defconfig Documentation/filesystems/index.rst | 1 + Documentation/filesystems/ntfs3.rst | 115 + MAINTAINERS | 9 + arch/arm64/configs/openeuler_defconfig | 4 + arch/x86/configs/openeuler_defconfig | 4 + fs/Kconfig | 1 + fs/Makefile | 1 + fs/ntfs3/Kconfig | 46 + fs/ntfs3/Makefile | 36 + fs/ntfs3/attrib.c | 2083 ++++++++++ fs/ntfs3/attrlist.c | 457 +++ fs/ntfs3/bitfunc.c | 128 + fs/ntfs3/bitmap.c | 1491 +++++++ fs/ntfs3/debug.h | 55 + fs/ntfs3/dir.c | 593 +++ fs/ntfs3/file.c | 1254 ++++++ fs/ntfs3/frecord.c | 3284 +++++++++++++++ fs/ntfs3/fslog.c | 5213 ++++++++++++++++++++++++ fs/ntfs3/fsntfs.c | 2506 ++++++++++++ fs/ntfs3/index.c | 2584 ++++++++++++ fs/ntfs3/inode.c | 1960 +++++++++ fs/ntfs3/lib/decompress_common.c | 319 ++ fs/ntfs3/lib/decompress_common.h | 343 ++ fs/ntfs3/lib/lib.h | 32 + fs/ntfs3/lib/lzx_decompress.c | 670 +++ fs/ntfs3/lib/xpress_decompress.c | 142 + fs/ntfs3/lznt.c | 453 ++ fs/ntfs3/namei.c | 387 ++ fs/ntfs3/ntfs.h | 1224 ++++++ fs/ntfs3/ntfs_fs.h | 1138 ++++++ fs/ntfs3/record.c | 602 +++ fs/ntfs3/run.c | 1111 +++++ fs/ntfs3/super.c | 1507 +++++++ fs/ntfs3/upcase.c | 104 + fs/ntfs3/xattr.c | 991 +++++ 35 files changed, 30848 insertions(+) create mode 100644 Documentation/filesystems/ntfs3.rst create mode 100644 fs/ntfs3/Kconfig create mode 100644 fs/ntfs3/Makefile create mode 100644 fs/ntfs3/attrib.c create mode 100644 fs/ntfs3/attrlist.c create mode 100644 fs/ntfs3/bitfunc.c create mode 100644 fs/ntfs3/bitmap.c create mode 100644 fs/ntfs3/debug.h create mode 100644 fs/ntfs3/dir.c create mode 100644 fs/ntfs3/file.c create mode 100644 fs/ntfs3/frecord.c create mode 100644 fs/ntfs3/fslog.c create mode 100644 fs/ntfs3/fsntfs.c create mode 100644 fs/ntfs3/index.c create mode 100644 fs/ntfs3/inode.c create mode 100644 fs/ntfs3/lib/decompress_common.c create mode 100644 fs/ntfs3/lib/decompress_common.h create mode 100644 fs/ntfs3/lib/lib.h create mode 100644 fs/ntfs3/lib/lzx_decompress.c create mode 100644 fs/ntfs3/lib/xpress_decompress.c create mode 100644 fs/ntfs3/lznt.c create mode 100644 fs/ntfs3/namei.c create mode 100644 fs/ntfs3/ntfs.h create mode 100644 fs/ntfs3/ntfs_fs.h create mode 100644 fs/ntfs3/record.c create mode 100644 fs/ntfs3/run.c create mode 100644 fs/ntfs3/super.c create mode 100644 fs/ntfs3/upcase.c create mode 100644 fs/ntfs3/xattr.c -- 2.30.0

1 34

[PATCH OLK-5.10 001/107] fs/ntfs3: Add headers and misc files
by Yin Xiujiang 13 Dec '21

13 Dec '21

From: Konstantin Komarov <almaz.alexandrovich(a)paragon-software.com> mainline inclusion from mainline-v5.15 commit 4534a70b7056fd4b9a1c6db5a4ce3c98546b291e category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4G67J?from=project-issue CVE: NA ---------------------------------------------------------------------- This adds headers and misc files Signed-off-by: Konstantin Komarov <almaz.alexandrovich(a)paragon-software.com> Signed-off-by: Yin Xiujiang <yinxiujiang(a)kylinos.cn> --- fs/ntfs3/debug.h | 64 +++ fs/ntfs3/ntfs.h | 1238 ++++++++++++++++++++++++++++++++++++++++++++ fs/ntfs3/ntfs_fs.h | 1092 ++++++++++++++++++++++++++++++++++++++ fs/ntfs3/upcase.c | 105 ++++ 4 files changed, 2499 insertions(+) create mode 100644 fs/ntfs3/debug.h create mode 100644 fs/ntfs3/ntfs.h create mode 100644 fs/ntfs3/ntfs_fs.h create mode 100644 fs/ntfs3/upcase.c diff --git a/fs/ntfs3/debug.h b/fs/ntfs3/debug.h new file mode 100644 index 000000000000..dfaa4c79dc6d --- /dev/null +++ b/fs/ntfs3/debug.h @@ -0,0 +1,64 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * + * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved. + * + * useful functions for debuging + */ + +// clang-format off +#ifndef Add2Ptr +#define Add2Ptr(P, I) ((void *)((u8 *)(P) + (I))) +#define PtrOffset(B, O) ((size_t)((size_t)(O) - (size_t)(B))) +#endif + +#define QuadAlign(n) (((n) + 7u) & (~7u)) +#define IsQuadAligned(n) (!((size_t)(n)&7u)) +#define Quad2Align(n) (((n) + 15u) & (~15u)) +#define IsQuad2Aligned(n) (!((size_t)(n)&15u)) +#define Quad4Align(n) (((n) + 31u) & (~31u)) +#define IsSizeTAligned(n) (!((size_t)(n) & (sizeof(size_t) - 1))) +#define DwordAlign(n) (((n) + 3u) & (~3u)) +#define IsDwordAligned(n) (!((size_t)(n)&3u)) +#define WordAlign(n) (((n) + 1u) & (~1u)) +#define IsWordAligned(n) (!((size_t)(n)&1u)) + +#ifdef CONFIG_PRINTK +__printf(2, 3) +void ntfs_printk(const struct super_block *sb, const char *fmt, ...); +__printf(2, 3) +void ntfs_inode_printk(struct inode *inode, const char *fmt, ...); +#else +static inline __printf(2, 3) +void ntfs_printk(const struct super_block *sb, const char *fmt, ...) +{ +} + +static inline __printf(2, 3) +void ntfs_inode_printk(struct inode *inode, const char *fmt, ...) +{ +} +#endif + +/* + * Logging macros ( thanks Joe Perches <joe(a)perches.com> for implementation ) + */ + +#define ntfs_err(sb, fmt, ...) ntfs_printk(sb, KERN_ERR fmt, ##__VA_ARGS__) +#define ntfs_warn(sb, fmt, ...) ntfs_printk(sb, KERN_WARNING fmt, ##__VA_ARGS__) +#define ntfs_info(sb, fmt, ...) ntfs_printk(sb, KERN_INFO fmt, ##__VA_ARGS__) +#define ntfs_notice(sb, fmt, ...) \ + ntfs_printk(sb, KERN_NOTICE fmt, ##__VA_ARGS__) + +#define ntfs_inode_err(inode, fmt, ...) \ + ntfs_inode_printk(inode, KERN_ERR fmt, ##__VA_ARGS__) +#define ntfs_inode_warn(inode, fmt, ...) \ + ntfs_inode_printk(inode, KERN_WARNING fmt, ##__VA_ARGS__) + +#define ntfs_malloc(s) kmalloc(s, GFP_NOFS) +#define ntfs_zalloc(s) kzalloc(s, GFP_NOFS) +#define ntfs_vmalloc(s) kvmalloc(s, GFP_KERNEL) +#define ntfs_free(p) kfree(p) +#define ntfs_vfree(p) kvfree(p) +#define ntfs_memdup(src, len) kmemdup(src, len, GFP_NOFS) +// clang-format on diff --git a/fs/ntfs3/ntfs.h b/fs/ntfs3/ntfs.h new file mode 100644 index 000000000000..40398e6c39c9 --- /dev/null +++ b/fs/ntfs3/ntfs.h @@ -0,0 +1,1238 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * + * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved. + * + * on-disk ntfs structs + */ + +// clang-format off + +/* TODO: + * - Check 4K mft record and 512 bytes cluster + */ + +/* + * Activate this define to use binary search in indexes + */ +#define NTFS3_INDEX_BINARY_SEARCH + +/* + * Check each run for marked clusters + */ +#define NTFS3_CHECK_FREE_CLST + +#define NTFS_NAME_LEN 255 + +/* + * ntfs.sys used 500 maximum links + * on-disk struct allows up to 0xffff + */ +#define NTFS_LINK_MAX 0x400 +//#define NTFS_LINK_MAX 0xffff + +/* + * Activate to use 64 bit clusters instead of 32 bits in ntfs.sys + * Logical and virtual cluster number + * If needed, may be redefined to use 64 bit value + */ +//#define CONFIG_NTFS3_64BIT_CLUSTER + +#define NTFS_LZNT_MAX_CLUSTER 4096 +#define NTFS_LZNT_CUNIT 4 +#define NTFS_LZNT_CLUSTERS (1u<<NTFS_LZNT_CUNIT) + +struct GUID { + __le32 Data1; + __le16 Data2; + __le16 Data3; + u8 Data4[8]; +}; + +/* + * this struct repeats layout of ATTR_FILE_NAME + * at offset 0x40 + * it used to store global constants NAME_MFT/NAME_MIRROR... + * most constant names are shorter than 10 + */ +struct cpu_str { + u8 len; + u8 unused; + u16 name[10]; +}; + +struct le_str { + u8 len; + u8 unused; + __le16 name[]; +}; + +static_assert(SECTOR_SHIFT == 9); + +#ifdef CONFIG_NTFS3_64BIT_CLUSTER +typedef u64 CLST; +static_assert(sizeof(size_t) == 8); +#else +typedef u32 CLST; +#endif + +#define SPARSE_LCN64 ((u64)-1) +#define SPARSE_LCN ((CLST)-1) +#define RESIDENT_LCN ((CLST)-2) +#define COMPRESSED_LCN ((CLST)-3) + +#define COMPRESSION_UNIT 4 +#define COMPRESS_MAX_CLUSTER 0x1000 +#define MFT_INCREASE_CHUNK 1024 + +enum RECORD_NUM { + MFT_REC_MFT = 0, + MFT_REC_MIRR = 1, + MFT_REC_LOG = 2, + MFT_REC_VOL = 3, + MFT_REC_ATTR = 4, + MFT_REC_ROOT = 5, + MFT_REC_BITMAP = 6, + MFT_REC_BOOT = 7, + MFT_REC_BADCLUST = 8, + //MFT_REC_QUOTA = 9, + MFT_REC_SECURE = 9, // NTFS 3.0 + MFT_REC_UPCASE = 10, + MFT_REC_EXTEND = 11, // NTFS 3.0 + MFT_REC_RESERVED = 11, + MFT_REC_FREE = 16, + MFT_REC_USER = 24, +}; + +enum ATTR_TYPE { + ATTR_ZERO = cpu_to_le32(0x00), + ATTR_STD = cpu_to_le32(0x10), + ATTR_LIST = cpu_to_le32(0x20), + ATTR_NAME = cpu_to_le32(0x30), + // ATTR_VOLUME_VERSION on Nt4 + ATTR_ID = cpu_to_le32(0x40), + ATTR_SECURE = cpu_to_le32(0x50), + ATTR_LABEL = cpu_to_le32(0x60), + ATTR_VOL_INFO = cpu_to_le32(0x70), + ATTR_DATA = cpu_to_le32(0x80), + ATTR_ROOT = cpu_to_le32(0x90), + ATTR_ALLOC = cpu_to_le32(0xA0), + ATTR_BITMAP = cpu_to_le32(0xB0), + // ATTR_SYMLINK on Nt4 + ATTR_REPARSE = cpu_to_le32(0xC0), + ATTR_EA_INFO = cpu_to_le32(0xD0), + ATTR_EA = cpu_to_le32(0xE0), + ATTR_PROPERTYSET = cpu_to_le32(0xF0), + ATTR_LOGGED_UTILITY_STREAM = cpu_to_le32(0x100), + ATTR_END = cpu_to_le32(0xFFFFFFFF) +}; + +static_assert(sizeof(enum ATTR_TYPE) == 4); + +enum FILE_ATTRIBUTE { + FILE_ATTRIBUTE_READONLY = cpu_to_le32(0x00000001), + FILE_ATTRIBUTE_HIDDEN = cpu_to_le32(0x00000002), + FILE_ATTRIBUTE_SYSTEM = cpu_to_le32(0x00000004), + FILE_ATTRIBUTE_ARCHIVE = cpu_to_le32(0x00000020), + FILE_ATTRIBUTE_DEVICE = cpu_to_le32(0x00000040), + FILE_ATTRIBUTE_TEMPORARY = cpu_to_le32(0x00000100), + FILE_ATTRIBUTE_SPARSE_FILE = cpu_to_le32(0x00000200), + FILE_ATTRIBUTE_REPARSE_POINT = cpu_to_le32(0x00000400), + FILE_ATTRIBUTE_COMPRESSED = cpu_to_le32(0x00000800), + FILE_ATTRIBUTE_OFFLINE = cpu_to_le32(0x00001000), + FILE_ATTRIBUTE_NOT_CONTENT_INDEXED = cpu_to_le32(0x00002000), + FILE_ATTRIBUTE_ENCRYPTED = cpu_to_le32(0x00004000), + FILE_ATTRIBUTE_VALID_FLAGS = cpu_to_le32(0x00007fb7), + FILE_ATTRIBUTE_DIRECTORY = cpu_to_le32(0x10000000), +}; + +static_assert(sizeof(enum FILE_ATTRIBUTE) == 4); + +extern const struct cpu_str NAME_MFT; +extern const struct cpu_str NAME_MIRROR; +extern const struct cpu_str NAME_LOGFILE; +extern const struct cpu_str NAME_VOLUME; +extern const struct cpu_str NAME_ATTRDEF; +extern const struct cpu_str NAME_ROOT; +extern const struct cpu_str NAME_BITMAP; +extern const struct cpu_str NAME_BOOT; +extern const struct cpu_str NAME_BADCLUS; +extern const struct cpu_str NAME_QUOTA; +extern const struct cpu_str NAME_SECURE; +extern const struct cpu_str NAME_UPCASE; +extern const struct cpu_str NAME_EXTEND; +extern const struct cpu_str NAME_OBJID; +extern const struct cpu_str NAME_REPARSE; +extern const struct cpu_str NAME_USNJRNL; + +extern const __le16 I30_NAME[4]; +extern const __le16 SII_NAME[4]; +extern const __le16 SDH_NAME[4]; +extern const __le16 SO_NAME[2]; +extern const __le16 SQ_NAME[2]; +extern const __le16 SR_NAME[2]; + +extern const __le16 BAD_NAME[4]; +extern const __le16 SDS_NAME[4]; +extern const __le16 WOF_NAME[17]; /* WofCompressedData */ + +/* MFT record number structure */ +struct MFT_REF { + __le32 low; // The low part of the number + __le16 high; // The high part of the number + __le16 seq; // The sequence number of MFT record +}; + +static_assert(sizeof(__le64) == sizeof(struct MFT_REF)); + +static inline CLST ino_get(const struct MFT_REF *ref) +{ +#ifdef CONFIG_NTFS3_64BIT_CLUSTER + return le32_to_cpu(ref->low) | ((u64)le16_to_cpu(ref->high) << 32); +#else + return le32_to_cpu(ref->low); +#endif +} + +struct NTFS_BOOT { + u8 jump_code[3]; // 0x00: Jump to boot code + u8 system_id[8]; // 0x03: System ID, equals "NTFS " + + // NOTE: this member is not aligned(!) + // bytes_per_sector[0] must be 0 + // bytes_per_sector[1] must be multiplied by 256 + u8 bytes_per_sector[2]; // 0x0B: Bytes per sector + + u8 sectors_per_clusters;// 0x0D: Sectors per cluster + u8 unused1[7]; + u8 media_type; // 0x15: Media type (0xF8 - harddisk) + u8 unused2[2]; + __le16 sct_per_track; // 0x18: number of sectors per track + __le16 heads; // 0x1A: number of heads per cylinder + __le32 hidden_sectors; // 0x1C: number of 'hidden' sectors + u8 unused3[4]; + u8 bios_drive_num; // 0x24: BIOS drive number =0x80 + u8 unused4; + u8 signature_ex; // 0x26: Extended BOOT signature =0x80 + u8 unused5; + __le64 sectors_per_volume;// 0x28: size of volume in sectors + __le64 mft_clst; // 0x30: first cluster of $MFT + __le64 mft2_clst; // 0x38: first cluster of $MFTMirr + s8 record_size; // 0x40: size of MFT record in clusters(sectors) + u8 unused6[3]; + s8 index_size; // 0x44: size of INDX record in clusters(sectors) + u8 unused7[3]; + __le64 serial_num; // 0x48: Volume serial number + __le32 check_sum; // 0x50: Simple additive checksum of all + // of the u32's which precede the 'check_sum' + + u8 boot_code[0x200 - 0x50 - 2 - 4]; // 0x54: + u8 boot_magic[2]; // 0x1FE: Boot signature =0x55 + 0xAA +}; + +static_assert(sizeof(struct NTFS_BOOT) == 0x200); + +enum NTFS_SIGNATURE { + NTFS_FILE_SIGNATURE = cpu_to_le32(0x454C4946), // 'FILE' + NTFS_INDX_SIGNATURE = cpu_to_le32(0x58444E49), // 'INDX' + NTFS_CHKD_SIGNATURE = cpu_to_le32(0x444B4843), // 'CHKD' + NTFS_RSTR_SIGNATURE = cpu_to_le32(0x52545352), // 'RSTR' + NTFS_RCRD_SIGNATURE = cpu_to_le32(0x44524352), // 'RCRD' + NTFS_BAAD_SIGNATURE = cpu_to_le32(0x44414142), // 'BAAD' + NTFS_HOLE_SIGNATURE = cpu_to_le32(0x454C4F48), // 'HOLE' + NTFS_FFFF_SIGNATURE = cpu_to_le32(0xffffffff), +}; + +static_assert(sizeof(enum NTFS_SIGNATURE) == 4); + +/* MFT Record header structure */ +struct NTFS_RECORD_HEADER { + /* Record magic number, equals 'FILE'/'INDX'/'RSTR'/'RCRD' */ + enum NTFS_SIGNATURE sign; // 0x00: + __le16 fix_off; // 0x04: + __le16 fix_num; // 0x06: + __le64 lsn; // 0x08: Log file sequence number +}; + +static_assert(sizeof(struct NTFS_RECORD_HEADER) == 0x10); + +static inline int is_baad(const struct NTFS_RECORD_HEADER *hdr) +{ + return hdr->sign == NTFS_BAAD_SIGNATURE; +} + +/* Possible bits in struct MFT_REC.flags */ +enum RECORD_FLAG { + RECORD_FLAG_IN_USE = cpu_to_le16(0x0001), + RECORD_FLAG_DIR = cpu_to_le16(0x0002), + RECORD_FLAG_SYSTEM = cpu_to_le16(0x0004), + RECORD_FLAG_UNKNOWN = cpu_to_le16(0x0008), +}; + +/* MFT Record structure */ +struct MFT_REC { + struct NTFS_RECORD_HEADER rhdr; // 'FILE' + + __le16 seq; // 0x10: Sequence number for this record + __le16 hard_links; // 0x12: The number of hard links to record + __le16 attr_off; // 0x14: Offset to attributes + __le16 flags; // 0x16: See RECORD_FLAG + __le32 used; // 0x18: The size of used part + __le32 total; // 0x1C: Total record size + + struct MFT_REF parent_ref; // 0x20: Parent MFT record + __le16 next_attr_id; // 0x28: The next attribute Id + + __le16 res; // 0x2A: High part of mft record? + __le32 mft_record; // 0x2C: Current mft record number + __le16 fixups[]; // 0x30: +}; + +#define MFTRECORD_FIXUP_OFFSET_1 offsetof(struct MFT_REC, res) +#define MFTRECORD_FIXUP_OFFSET_3 offsetof(struct MFT_REC, fixups) + +static_assert(MFTRECORD_FIXUP_OFFSET_1 == 0x2A); +static_assert(MFTRECORD_FIXUP_OFFSET_3 == 0x30); + +static inline bool is_rec_base(const struct MFT_REC *rec) +{ + const struct MFT_REF *r = &rec->parent_ref; + + return !r->low && !r->high && !r->seq; +} + +static inline bool is_mft_rec5(const struct MFT_REC *rec) +{ + return le16_to_cpu(rec->rhdr.fix_off) >= + offsetof(struct MFT_REC, fixups); +} + +static inline bool is_rec_inuse(const struct MFT_REC *rec) +{ + return rec->flags & RECORD_FLAG_IN_USE; +} + +static inline bool clear_rec_inuse(struct MFT_REC *rec) +{ + return rec->flags &= ~RECORD_FLAG_IN_USE; +} + +/* Possible values of ATTR_RESIDENT.flags */ +#define RESIDENT_FLAG_INDEXED 0x01 + +struct ATTR_RESIDENT { + __le32 data_size; // 0x10: The size of data + __le16 data_off; // 0x14: Offset to data + u8 flags; // 0x16: resident flags ( 1 - indexed ) + u8 res; // 0x17: +}; // sizeof() = 0x18 + +struct ATTR_NONRESIDENT { + __le64 svcn; // 0x10: Starting VCN of this segment + __le64 evcn; // 0x18: End VCN of this segment + __le16 run_off; // 0x20: Offset to packed runs + // Unit of Compression size for this stream, expressed + // as a log of the cluster size. + // + // 0 means file is not compressed + // 1, 2, 3, and 4 are potentially legal values if the + // stream is compressed, however the implementation + // may only choose to use 4, or possibly 3. Note + // that 4 means cluster size time 16. If convenient + // the implementation may wish to accept a + // reasonable range of legal values here (1-5?), + // even if the implementation only generates + // a smaller set of values itself. + u8 c_unit; // 0x22 + u8 res1[5]; // 0x23: + __le64 alloc_size; // 0x28: The allocated size of attribute in bytes + // (multiple of cluster size) + __le64 data_size; // 0x30: The size of attribute in bytes <= alloc_size + __le64 valid_size; // 0x38: The size of valid part in bytes <= data_size + __le64 total_size; // 0x40: The sum of the allocated clusters for a file + // (present only for the first segment (0 == vcn) + // of compressed attribute) + +}; // sizeof()=0x40 or 0x48 (if compressed) + +/* Possible values of ATTRIB.flags: */ +#define ATTR_FLAG_COMPRESSED cpu_to_le16(0x0001) +#define ATTR_FLAG_COMPRESSED_MASK cpu_to_le16(0x00FF) +#define ATTR_FLAG_ENCRYPTED cpu_to_le16(0x4000) +#define ATTR_FLAG_SPARSED cpu_to_le16(0x8000) + +struct ATTRIB { + enum ATTR_TYPE type; // 0x00: The type of this attribute + __le32 size; // 0x04: The size of this attribute + u8 non_res; // 0x08: Is this attribute non-resident ? + u8 name_len; // 0x09: This attribute name length + __le16 name_off; // 0x0A: Offset to the attribute name + __le16 flags; // 0x0C: See ATTR_FLAG_XXX + __le16 id; // 0x0E: unique id (per record) + + union { + struct ATTR_RESIDENT res; // 0x10 + struct ATTR_NONRESIDENT nres; // 0x10 + }; +}; + +/* Define attribute sizes */ +#define SIZEOF_RESIDENT 0x18 +#define SIZEOF_NONRESIDENT_EX 0x48 +#define SIZEOF_NONRESIDENT 0x40 + +#define SIZEOF_RESIDENT_LE cpu_to_le16(0x18) +#define SIZEOF_NONRESIDENT_EX_LE cpu_to_le16(0x48) +#define SIZEOF_NONRESIDENT_LE cpu_to_le16(0x40) + +static inline u64 attr_ondisk_size(const struct ATTRIB *attr) +{ + return attr->non_res ? ((attr->flags & + (ATTR_FLAG_COMPRESSED | ATTR_FLAG_SPARSED)) ? + le64_to_cpu(attr->nres.total_size) : + le64_to_cpu(attr->nres.alloc_size)) : + QuadAlign(le32_to_cpu(attr->res.data_size)); +} + +static inline u64 attr_size(const struct ATTRIB *attr) +{ + return attr->non_res ? le64_to_cpu(attr->nres.data_size) : + le32_to_cpu(attr->res.data_size); +} + +static inline bool is_attr_encrypted(const struct ATTRIB *attr) +{ + return attr->flags & ATTR_FLAG_ENCRYPTED; +} + +static inline bool is_attr_sparsed(const struct ATTRIB *attr) +{ + return attr->flags & ATTR_FLAG_SPARSED; +} + +static inline bool is_attr_compressed(const struct ATTRIB *attr) +{ + return attr->flags & ATTR_FLAG_COMPRESSED; +} + +static inline bool is_attr_ext(const struct ATTRIB *attr) +{ + return attr->flags & (ATTR_FLAG_SPARSED | ATTR_FLAG_COMPRESSED); +} + +static inline bool is_attr_indexed(const struct ATTRIB *attr) +{ + return !attr->non_res && (attr->res.flags & RESIDENT_FLAG_INDEXED); +} + +static inline __le16 const *attr_name(const struct ATTRIB *attr) +{ + return Add2Ptr(attr, le16_to_cpu(attr->name_off)); +} + +static inline u64 attr_svcn(const struct ATTRIB *attr) +{ + return attr->non_res ? le64_to_cpu(attr->nres.svcn) : 0; +} + +/* the size of resident attribute by its resident size */ +#define BYTES_PER_RESIDENT(b) (0x18 + (b)) + +static_assert(sizeof(struct ATTRIB) == 0x48); +static_assert(sizeof(((struct ATTRIB *)NULL)->res) == 0x08); +static_assert(sizeof(((struct ATTRIB *)NULL)->nres) == 0x38); + +static inline void *resident_data_ex(const struct ATTRIB *attr, u32 datasize) +{ + u32 asize, rsize; + u16 off; + + if (attr->non_res) + return NULL; + + asize = le32_to_cpu(attr->size); + off = le16_to_cpu(attr->res.data_off); + + if (asize < datasize + off) + return NULL; + + rsize = le32_to_cpu(attr->res.data_size); + if (rsize < datasize) + return NULL; + + return Add2Ptr(attr, off); +} + +static inline void *resident_data(const struct ATTRIB *attr) +{ + return Add2Ptr(attr, le16_to_cpu(attr->res.data_off)); +} + +static inline void *attr_run(const struct ATTRIB *attr) +{ + return Add2Ptr(attr, le16_to_cpu(attr->nres.run_off)); +} + +/* Standard information attribute (0x10) */ +struct ATTR_STD_INFO { + __le64 cr_time; // 0x00: File creation file + __le64 m_time; // 0x08: File modification time + __le64 c_time; // 0x10: Last time any attribute was modified + __le64 a_time; // 0x18: File last access time + enum FILE_ATTRIBUTE fa; // 0x20: Standard DOS attributes & more + __le32 max_ver_num; // 0x24: Maximum Number of Versions + __le32 ver_num; // 0x28: Version Number + __le32 class_id; // 0x2C: Class Id from bidirectional Class Id index +}; + +static_assert(sizeof(struct ATTR_STD_INFO) == 0x30); + +#define SECURITY_ID_INVALID 0x00000000 +#define SECURITY_ID_FIRST 0x00000100 + +struct ATTR_STD_INFO5 { + __le64 cr_time; // 0x00: File creation file + __le64 m_time; // 0x08: File modification time + __le64 c_time; // 0x10: Last time any attribute was modified + __le64 a_time; // 0x18: File last access time + enum FILE_ATTRIBUTE fa; // 0x20: Standard DOS attributes & more + __le32 max_ver_num; // 0x24: Maximum Number of Versions + __le32 ver_num; // 0x28: Version Number + __le32 class_id; // 0x2C: Class Id from bidirectional Class Id index + + __le32 owner_id; // 0x30: Owner Id of the user owning the file. + __le32 security_id; // 0x34: The Security Id is a key in the $SII Index and $SDS + __le64 quota_charge; // 0x38: + __le64 usn; // 0x40: Last Update Sequence Number of the file. This is a direct + // index into the file $UsnJrnl. If zero, the USN Journal is + // disabled. +}; + +static_assert(sizeof(struct ATTR_STD_INFO5) == 0x48); + +/* attribute list entry structure (0x20) */ +struct ATTR_LIST_ENTRY { + enum ATTR_TYPE type; // 0x00: The type of attribute + __le16 size; // 0x04: The size of this record + u8 name_len; // 0x06: The length of attribute name + u8 name_off; // 0x07: The offset to attribute name + __le64 vcn; // 0x08: Starting VCN of this attribute + struct MFT_REF ref; // 0x10: MFT record number with attribute + __le16 id; // 0x18: struct ATTRIB ID + __le16 name[3]; // 0x1A: Just to align. To get real name can use bNameOffset + +}; // sizeof(0x20) + +static_assert(sizeof(struct ATTR_LIST_ENTRY) == 0x20); + +static inline u32 le_size(u8 name_len) +{ + return QuadAlign(offsetof(struct ATTR_LIST_ENTRY, name) + + name_len * sizeof(short)); +} + +/* returns 0 if 'attr' has the same type and name */ +static inline int le_cmp(const struct ATTR_LIST_ENTRY *le, + const struct ATTRIB *attr) +{ + return le->type != attr->type || le->name_len != attr->name_len || + (!le->name_len && + memcmp(Add2Ptr(le, le->name_off), + Add2Ptr(attr, le16_to_cpu(attr->name_off)), + le->name_len * sizeof(short))); +} + +static inline __le16 const *le_name(const struct ATTR_LIST_ENTRY *le) +{ + return Add2Ptr(le, le->name_off); +} + +/* File name types (the field type in struct ATTR_FILE_NAME ) */ +#define FILE_NAME_POSIX 0 +#define FILE_NAME_UNICODE 1 +#define FILE_NAME_DOS 2 +#define FILE_NAME_UNICODE_AND_DOS (FILE_NAME_DOS | FILE_NAME_UNICODE) + +/* Filename attribute structure (0x30) */ +struct NTFS_DUP_INFO { + __le64 cr_time; // 0x00: File creation file + __le64 m_time; // 0x08: File modification time + __le64 c_time; // 0x10: Last time any attribute was modified + __le64 a_time; // 0x18: File last access time + __le64 alloc_size; // 0x20: Data attribute allocated size, multiple of cluster size + __le64 data_size; // 0x28: Data attribute size <= Dataalloc_size + enum FILE_ATTRIBUTE fa; // 0x30: Standard DOS attributes & more + __le16 ea_size; // 0x34: Packed EAs + __le16 reparse; // 0x36: Used by Reparse + +}; // 0x38 + +struct ATTR_FILE_NAME { + struct MFT_REF home; // 0x00: MFT record for directory + struct NTFS_DUP_INFO dup;// 0x08 + u8 name_len; // 0x40: File name length in words + u8 type; // 0x41: File name type + __le16 name[]; // 0x42: File name +}; + +static_assert(sizeof(((struct ATTR_FILE_NAME *)NULL)->dup) == 0x38); +static_assert(offsetof(struct ATTR_FILE_NAME, name) == 0x42); +#define SIZEOF_ATTRIBUTE_FILENAME 0x44 +#define SIZEOF_ATTRIBUTE_FILENAME_MAX (0x42 + 255 * 2) + +static inline struct ATTRIB *attr_from_name(struct ATTR_FILE_NAME *fname) +{ + return (struct ATTRIB *)((char *)fname - SIZEOF_RESIDENT); +} + +static inline u16 fname_full_size(const struct ATTR_FILE_NAME *fname) +{ + // don't return struct_size(fname, name, fname->name_len); + return offsetof(struct ATTR_FILE_NAME, name) + + fname->name_len * sizeof(short); +} + +static inline u8 paired_name(u8 type) +{ + if (type == FILE_NAME_UNICODE) + return FILE_NAME_DOS; + if (type == FILE_NAME_DOS) + return FILE_NAME_UNICODE; + return FILE_NAME_POSIX; +} + +/* Index entry defines ( the field flags in NtfsDirEntry ) */ +#define NTFS_IE_HAS_SUBNODES cpu_to_le16(1) +#define NTFS_IE_LAST cpu_to_le16(2) + +/* Directory entry structure */ +struct NTFS_DE { + union { + struct MFT_REF ref; // 0x00: MFT record number with this file + struct { + __le16 data_off; // 0x00: + __le16 data_size; // 0x02: + __le32 res; // 0x04: must be 0 + } view; + }; + __le16 size; // 0x08: The size of this entry + __le16 key_size; // 0x0A: The size of File name length in bytes + 0x42 + __le16 flags; // 0x0C: Entry flags: NTFS_IE_XXX + __le16 res; // 0x0E: + + // Here any indexed attribute can be placed + // One of them is: + // struct ATTR_FILE_NAME AttrFileName; + // + + // The last 8 bytes of this structure contains + // the VBN of subnode + // !!! Note !!! + // This field is presented only if (flags & NTFS_IE_HAS_SUBNODES) + // __le64 vbn; +}; + +static_assert(sizeof(struct NTFS_DE) == 0x10); + +static inline void de_set_vbn_le(struct NTFS_DE *e, __le64 vcn) +{ + __le64 *v = Add2Ptr(e, le16_to_cpu(e->size) - sizeof(__le64)); + + *v = vcn; +} + +static inline void de_set_vbn(struct NTFS_DE *e, CLST vcn) +{ + __le64 *v = Add2Ptr(e, le16_to_cpu(e->size) - sizeof(__le64)); + + *v = cpu_to_le64(vcn); +} + +static inline __le64 de_get_vbn_le(const struct NTFS_DE *e) +{ + return *(__le64 *)Add2Ptr(e, le16_to_cpu(e->size) - sizeof(__le64)); +} + +static inline CLST de_get_vbn(const struct NTFS_DE *e) +{ + __le64 *v = Add2Ptr(e, le16_to_cpu(e->size) - sizeof(__le64)); + + return le64_to_cpu(*v); +} + +static inline struct NTFS_DE *de_get_next(const struct NTFS_DE *e) +{ + return Add2Ptr(e, le16_to_cpu(e->size)); +} + +static inline struct ATTR_FILE_NAME *de_get_fname(const struct NTFS_DE *e) +{ + return le16_to_cpu(e->key_size) >= SIZEOF_ATTRIBUTE_FILENAME ? + Add2Ptr(e, sizeof(struct NTFS_DE)) : + NULL; +} + +static inline bool de_is_last(const struct NTFS_DE *e) +{ + return e->flags & NTFS_IE_LAST; +} + +static inline bool de_has_vcn(const struct NTFS_DE *e) +{ + return e->flags & NTFS_IE_HAS_SUBNODES; +} + +static inline bool de_has_vcn_ex(const struct NTFS_DE *e) +{ + return (e->flags & NTFS_IE_HAS_SUBNODES) && + (u64)(-1) != *((u64 *)Add2Ptr(e, le16_to_cpu(e->size) - + sizeof(__le64))); +} + +#define MAX_BYTES_PER_NAME_ENTRY \ + QuadAlign(sizeof(struct NTFS_DE) + \ + offsetof(struct ATTR_FILE_NAME, name) + \ + NTFS_NAME_LEN * sizeof(short)) + +struct INDEX_HDR { + __le32 de_off; // 0x00: The offset from the start of this structure + // to the first NTFS_DE + __le32 used; // 0x04: The size of this structure plus all + // entries (quad-word aligned) + __le32 total; // 0x08: The allocated size of for this structure plus all entries + u8 flags; // 0x0C: 0x00 = Small directory, 0x01 = Large directory + u8 res[3]; + + // + // de_off + used <= total + // +}; + +static_assert(sizeof(struct INDEX_HDR) == 0x10); + +static inline struct NTFS_DE *hdr_first_de(const struct INDEX_HDR *hdr) +{ + u32 de_off = le32_to_cpu(hdr->de_off); + u32 used = le32_to_cpu(hdr->used); + struct NTFS_DE *e = Add2Ptr(hdr, de_off); + u16 esize; + + if (de_off >= used || de_off >= le32_to_cpu(hdr->total)) + return NULL; + + esize = le16_to_cpu(e->size); + if (esize < sizeof(struct NTFS_DE) || de_off + esize > used) + return NULL; + + return e; +} + +static inline struct NTFS_DE *hdr_next_de(const struct INDEX_HDR *hdr, + const struct NTFS_DE *e) +{ + size_t off = PtrOffset(hdr, e); + u32 used = le32_to_cpu(hdr->used); + u16 esize; + + if (off >= used) + return NULL; + + esize = le16_to_cpu(e->size); + + if (esize < sizeof(struct NTFS_DE) || + off + esize + sizeof(struct NTFS_DE) > used) + return NULL; + + return Add2Ptr(e, esize); +} + +static inline bool hdr_has_subnode(const struct INDEX_HDR *hdr) +{ + return hdr->flags & 1; +} + +struct INDEX_BUFFER { + struct NTFS_RECORD_HEADER rhdr; // 'INDX' + __le64 vbn; // 0x10: vcn if index >= cluster or vsn id index < cluster + struct INDEX_HDR ihdr; // 0x18: +}; + +static_assert(sizeof(struct INDEX_BUFFER) == 0x28); + +static inline bool ib_is_empty(const struct INDEX_BUFFER *ib) +{ + const struct NTFS_DE *first = hdr_first_de(&ib->ihdr); + + return !first || de_is_last(first); +} + +static inline bool ib_is_leaf(const struct INDEX_BUFFER *ib) +{ + return !(ib->ihdr.flags & 1); +} + +/* Index root structure ( 0x90 ) */ +enum COLLATION_RULE { + NTFS_COLLATION_TYPE_BINARY = cpu_to_le32(0), + // $I30 + NTFS_COLLATION_TYPE_FILENAME = cpu_to_le32(0x01), + // $SII of $Secure and $Q of Quota + NTFS_COLLATION_TYPE_UINT = cpu_to_le32(0x10), + // $O of Quota + NTFS_COLLATION_TYPE_SID = cpu_to_le32(0x11), + // $SDH of $Secure + NTFS_COLLATION_TYPE_SECURITY_HASH = cpu_to_le32(0x12), + // $O of ObjId and "$R" for Reparse + NTFS_COLLATION_TYPE_UINTS = cpu_to_le32(0x13) +}; + +static_assert(sizeof(enum COLLATION_RULE) == 4); + +// +struct INDEX_ROOT { + enum ATTR_TYPE type; // 0x00: The type of attribute to index on + enum COLLATION_RULE rule; // 0x04: The rule + __le32 index_block_size;// 0x08: The size of index record + u8 index_block_clst; // 0x0C: The number of clusters or sectors per index + u8 res[3]; + struct INDEX_HDR ihdr; // 0x10: +}; + +static_assert(sizeof(struct INDEX_ROOT) == 0x20); +static_assert(offsetof(struct INDEX_ROOT, ihdr) == 0x10); + +#define VOLUME_FLAG_DIRTY cpu_to_le16(0x0001) +#define VOLUME_FLAG_RESIZE_LOG_FILE cpu_to_le16(0x0002) + +struct VOLUME_INFO { + __le64 res1; // 0x00 + u8 major_ver; // 0x08: NTFS major version number (before .) + u8 minor_ver; // 0x09: NTFS minor version number (after .) + __le16 flags; // 0x0A: Volume flags, see VOLUME_FLAG_XXX + +}; // sizeof=0xC + +#define SIZEOF_ATTRIBUTE_VOLUME_INFO 0xc + +#define NTFS_LABEL_MAX_LENGTH (0x100 / sizeof(short)) +#define NTFS_ATTR_INDEXABLE cpu_to_le32(0x00000002) +#define NTFS_ATTR_DUPALLOWED cpu_to_le32(0x00000004) +#define NTFS_ATTR_MUST_BE_INDEXED cpu_to_le32(0x00000010) +#define NTFS_ATTR_MUST_BE_NAMED cpu_to_le32(0x00000020) +#define NTFS_ATTR_MUST_BE_RESIDENT cpu_to_le32(0x00000040) +#define NTFS_ATTR_LOG_ALWAYS cpu_to_le32(0x00000080) + +/* $AttrDef file entry */ +struct ATTR_DEF_ENTRY { + __le16 name[0x40]; // 0x00: Attr name + enum ATTR_TYPE type; // 0x80: struct ATTRIB type + __le32 res; // 0x84: + enum COLLATION_RULE rule; // 0x88: + __le32 flags; // 0x8C: NTFS_ATTR_XXX (see above) + __le64 min_sz; // 0x90: Minimum attribute data size + __le64 max_sz; // 0x98: Maximum attribute data size +}; + +static_assert(sizeof(struct ATTR_DEF_ENTRY) == 0xa0); + +/* Object ID (0x40) */ +struct OBJECT_ID { + struct GUID ObjId; // 0x00: Unique Id assigned to file + struct GUID BirthVolumeId;// 0x10: Birth Volume Id is the Object Id of the Volume on + // which the Object Id was allocated. It never changes + struct GUID BirthObjectId; // 0x20: Birth Object Id is the first Object Id that was + // ever assigned to this MFT Record. I.e. If the Object Id + // is changed for some reason, this field will reflect the + // original value of the Object Id. + struct GUID DomainId; // 0x30: Domain Id is currently unused but it is intended to be + // used in a network environment where the local machine is + // part of a Windows 2000 Domain. This may be used in a Windows + // 2000 Advanced Server managed domain. +}; + +static_assert(sizeof(struct OBJECT_ID) == 0x40); + +/* O Directory entry structure ( rule = 0x13 ) */ +struct NTFS_DE_O { + struct NTFS_DE de; + struct GUID ObjId; // 0x10: Unique Id assigned to file + struct MFT_REF ref; // 0x20: MFT record number with this file + struct GUID BirthVolumeId; // 0x28: Birth Volume Id is the Object Id of the Volume on + // which the Object Id was allocated. It never changes + struct GUID BirthObjectId; // 0x38: Birth Object Id is the first Object Id that was + // ever assigned to this MFT Record. I.e. If the Object Id + // is changed for some reason, this field will reflect the + // original value of the Object Id. + // This field is valid if data_size == 0x48 + struct GUID BirthDomainId; // 0x48: Domain Id is currently unused but it is intended + // to be used in a network environment where the local + // machine is part of a Windows 2000 Domain. This may be + // used in a Windows 2000 Advanced Server managed domain. +}; + +static_assert(sizeof(struct NTFS_DE_O) == 0x58); + +#define NTFS_OBJECT_ENTRY_DATA_SIZE1 \ + 0x38 // struct NTFS_DE_O.BirthDomainId is not used +#define NTFS_OBJECT_ENTRY_DATA_SIZE2 \ + 0x48 // struct NTFS_DE_O.BirthDomainId is used + +/* Q Directory entry structure ( rule = 0x11 ) */ +struct NTFS_DE_Q { + struct NTFS_DE de; + __le32 owner_id; // 0x10: Unique Id assigned to file + __le32 Version; // 0x14: 0x02 + __le32 flags2; // 0x18: Quota flags, see above + __le64 BytesUsed; // 0x1C: + __le64 ChangeTime; // 0x24: + __le64 WarningLimit; // 0x28: + __le64 HardLimit; // 0x34: + __le64 ExceededTime; // 0x3C: + + // SID is placed here +}; // sizeof() = 0x44 + +#define SIZEOF_NTFS_DE_Q 0x44 + +#define SecurityDescriptorsBlockSize 0x40000 // 256K +#define SecurityDescriptorMaxSize 0x20000 // 128K +#define Log2OfSecurityDescriptorsBlockSize 18 + +struct SECURITY_KEY { + __le32 hash; // Hash value for descriptor + __le32 sec_id; // Security Id (guaranteed unique) +}; + +/* Security descriptors (the content of $Secure::SDS data stream) */ +struct SECURITY_HDR { + struct SECURITY_KEY key; // 0x00: Security Key + __le64 off; // 0x08: Offset of this entry in the file + __le32 size; // 0x10: Size of this entry, 8 byte aligned + // + // Security descriptor itself is placed here + // Total size is 16 byte aligned + // +} __packed; + +#define SIZEOF_SECURITY_HDR 0x14 + +/* SII Directory entry structure */ +struct NTFS_DE_SII { + struct NTFS_DE de; + __le32 sec_id; // 0x10: Key: sizeof(security_id) = wKeySize + struct SECURITY_HDR sec_hdr; // 0x14: +} __packed; + +#define SIZEOF_SII_DIRENTRY 0x28 + +/* SDH Directory entry structure */ +struct NTFS_DE_SDH { + struct NTFS_DE de; + struct SECURITY_KEY key; // 0x10: Key + struct SECURITY_HDR sec_hdr; // 0x18: Data + __le16 magic[2]; // 0x2C: 0x00490049 "I I" +}; + +#define SIZEOF_SDH_DIRENTRY 0x30 + +struct REPARSE_KEY { + __le32 ReparseTag; // 0x00: Reparse Tag + struct MFT_REF ref; // 0x04: MFT record number with this file +}; // sizeof() = 0x0C + +static_assert(offsetof(struct REPARSE_KEY, ref) == 0x04); +#define SIZEOF_REPARSE_KEY 0x0C + +/* Reparse Directory entry structure */ +struct NTFS_DE_R { + struct NTFS_DE de; + struct REPARSE_KEY key; // 0x10: Reparse Key + u32 zero; // 0x1c +}; // sizeof() = 0x20 + +static_assert(sizeof(struct NTFS_DE_R) == 0x20); + +/* CompressReparseBuffer.WofVersion */ +#define WOF_CURRENT_VERSION cpu_to_le32(1) +/* CompressReparseBuffer.WofProvider */ +#define WOF_PROVIDER_WIM cpu_to_le32(1) +/* CompressReparseBuffer.WofProvider */ +#define WOF_PROVIDER_SYSTEM cpu_to_le32(2) +/* CompressReparseBuffer.ProviderVer */ +#define WOF_PROVIDER_CURRENT_VERSION cpu_to_le32(1) + +#define WOF_COMPRESSION_XPRESS4K cpu_to_le32(0) // 4k +#define WOF_COMPRESSION_LZX32K cpu_to_le32(1) // 32k +#define WOF_COMPRESSION_XPRESS8K cpu_to_le32(2) // 8k +#define WOF_COMPRESSION_XPRESS16K cpu_to_le32(3) // 16k + +/* + * ATTR_REPARSE (0xC0) + * + * The reparse struct GUID structure is used by all 3rd party layered drivers to + * store data in a reparse point. For non-Microsoft tags, The struct GUID field + * cannot be GUID_NULL. + * The constraints on reparse tags are defined below. + * Microsoft tags can also be used with this format of the reparse point buffer. + */ +struct REPARSE_POINT { + __le32 ReparseTag; // 0x00: + __le16 ReparseDataLength;// 0x04: + __le16 Reserved; + + struct GUID Guid; // 0x08: + + // + // Here GenericReparseBuffer is placed + // +}; + +static_assert(sizeof(struct REPARSE_POINT) == 0x18); + +// +// Maximum allowed size of the reparse data. +// +#define MAXIMUM_REPARSE_DATA_BUFFER_SIZE (16 * 1024) + +// +// The value of the following constant needs to satisfy the following +// conditions: +// (1) Be at least as large as the largest of the reserved tags. +// (2) Be strictly smaller than all the tags in use. +// +#define IO_REPARSE_TAG_RESERVED_RANGE 1 + +// +// The reparse tags are a ULONG. The 32 bits are laid out as follows: +// +// 3 3 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1 +// 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 +// +-+-+-+-+-----------------------+-------------------------------+ +// |M|R|N|R| Reserved bits | Reparse Tag Value | +// +-+-+-+-+-----------------------+-------------------------------+ +// +// M is the Microsoft bit. When set to 1, it denotes a tag owned by Microsoft. +// All ISVs must use a tag with a 0 in this position. +// Note: If a Microsoft tag is used by non-Microsoft software, the +// behavior is not defined. +// +// R is reserved. Must be zero for non-Microsoft tags. +// +// N is name surrogate. When set to 1, the file represents another named +// entity in the system. +// +// The M and N bits are OR-able. +// The following macros check for the M and N bit values: +// + +// +// Macro to determine whether a reparse point tag corresponds to a tag +// owned by Microsoft. +// +#define IsReparseTagMicrosoft(_tag) (((_tag)&IO_REPARSE_TAG_MICROSOFT)) + +// +// Macro to determine whether a reparse point tag is a name surrogate +// +#define IsReparseTagNameSurrogate(_tag) (((_tag)&IO_REPARSE_TAG_NAME_SURROGATE)) + +// +// The following constant represents the bits that are valid to use in +// reparse tags. +// +#define IO_REPARSE_TAG_VALID_VALUES 0xF000FFFF + +// +// Macro to determine whether a reparse tag is a valid tag. +// +#define IsReparseTagValid(_tag) \ + (!((_tag) & ~IO_REPARSE_TAG_VALID_VALUES) && \ + ((_tag) > IO_REPARSE_TAG_RESERVED_RANGE)) + +// +// Microsoft tags for reparse points. +// + +enum IO_REPARSE_TAG { + IO_REPARSE_TAG_SYMBOLIC_LINK = cpu_to_le32(0), + IO_REPARSE_TAG_NAME_SURROGATE = cpu_to_le32(0x20000000), + IO_REPARSE_TAG_MICROSOFT = cpu_to_le32(0x80000000), + IO_REPARSE_TAG_MOUNT_POINT = cpu_to_le32(0xA0000003), + IO_REPARSE_TAG_SYMLINK = cpu_to_le32(0xA000000C), + IO_REPARSE_TAG_HSM = cpu_to_le32(0xC0000004), + IO_REPARSE_TAG_SIS = cpu_to_le32(0x80000007), + IO_REPARSE_TAG_DEDUP = cpu_to_le32(0x80000013), + IO_REPARSE_TAG_COMPRESS = cpu_to_le32(0x80000017), + + // + // The reparse tag 0x80000008 is reserved for Microsoft internal use + // (may be published in the future) + // + + // + // Microsoft reparse tag reserved for DFS + // + IO_REPARSE_TAG_DFS = cpu_to_le32(0x8000000A), + + // + // Microsoft reparse tag reserved for the file system filter manager + // + IO_REPARSE_TAG_FILTER_MANAGER = cpu_to_le32(0x8000000B), + + // + // Non-Microsoft tags for reparse points + // + + // + // Tag allocated to CONGRUENT, May 2000. Used by IFSTEST + // + IO_REPARSE_TAG_IFSTEST_CONGRUENT = cpu_to_le32(0x00000009), + + // + // Tag allocated to ARKIVIO + // + IO_REPARSE_TAG_ARKIVIO = cpu_to_le32(0x0000000C), + + // + // Tag allocated to SOLUTIONSOFT + // + IO_REPARSE_TAG_SOLUTIONSOFT = cpu_to_le32(0x2000000D), + + // + // Tag allocated to COMMVAULT + // + IO_REPARSE_TAG_COMMVAULT = cpu_to_le32(0x0000000E), + + // OneDrive?? + IO_REPARSE_TAG_CLOUD = cpu_to_le32(0x9000001A), + IO_REPARSE_TAG_CLOUD_1 = cpu_to_le32(0x9000101A), + IO_REPARSE_TAG_CLOUD_2 = cpu_to_le32(0x9000201A), + IO_REPARSE_TAG_CLOUD_3 = cpu_to_le32(0x9000301A), + IO_REPARSE_TAG_CLOUD_4 = cpu_to_le32(0x9000401A), + IO_REPARSE_TAG_CLOUD_5 = cpu_to_le32(0x9000501A), + IO_REPARSE_TAG_CLOUD_6 = cpu_to_le32(0x9000601A), + IO_REPARSE_TAG_CLOUD_7 = cpu_to_le32(0x9000701A), + IO_REPARSE_TAG_CLOUD_8 = cpu_to_le32(0x9000801A), + IO_REPARSE_TAG_CLOUD_9 = cpu_to_le32(0x9000901A), + IO_REPARSE_TAG_CLOUD_A = cpu_to_le32(0x9000A01A), + IO_REPARSE_TAG_CLOUD_B = cpu_to_le32(0x9000B01A), + IO_REPARSE_TAG_CLOUD_C = cpu_to_le32(0x9000C01A), + IO_REPARSE_TAG_CLOUD_D = cpu_to_le32(0x9000D01A), + IO_REPARSE_TAG_CLOUD_E = cpu_to_le32(0x9000E01A), + IO_REPARSE_TAG_CLOUD_F = cpu_to_le32(0x9000F01A), + +}; + +#define SYMLINK_FLAG_RELATIVE 1 + +/* Microsoft reparse buffer. (see DDK for details) */ +struct REPARSE_DATA_BUFFER { + __le32 ReparseTag; // 0x00: + __le16 ReparseDataLength; // 0x04: + __le16 Reserved; + + union { + // If ReparseTag == 0xA0000003 (IO_REPARSE_TAG_MOUNT_POINT) + struct { + __le16 SubstituteNameOffset; // 0x08 + __le16 SubstituteNameLength; // 0x0A + __le16 PrintNameOffset; // 0x0C + __le16 PrintNameLength; // 0x0E + __le16 PathBuffer[]; // 0x10 + } MountPointReparseBuffer; + + // If ReparseTag == 0xA000000C (IO_REPARSE_TAG_SYMLINK) + // https://msdn.microsoft.com/en-us/library/cc232006.aspx + struct { + __le16 SubstituteNameOffset; // 0x08 + __le16 SubstituteNameLength; // 0x0A + __le16 PrintNameOffset; // 0x0C + __le16 PrintNameLength; // 0x0E + // 0-absolute path 1- relative path, SYMLINK_FLAG_RELATIVE + __le32 Flags; // 0x10 + __le16 PathBuffer[]; // 0x14 + } SymbolicLinkReparseBuffer; + + // If ReparseTag == 0x80000017U + struct { + __le32 WofVersion; // 0x08 == 1 + /* 1 - WIM backing provider ("WIMBoot"), + * 2 - System compressed file provider + */ + __le32 WofProvider; // 0x0C + __le32 ProviderVer; // 0x10: == 1 WOF_FILE_PROVIDER_CURRENT_VERSION == 1 + __le32 CompressionFormat; // 0x14: 0, 1, 2, 3. See WOF_COMPRESSION_XXX + } CompressReparseBuffer; + + struct { + u8 DataBuffer[1]; // 0x08 + } GenericReparseBuffer; + }; +}; + +/* ATTR_EA_INFO (0xD0) */ + +#define FILE_NEED_EA 0x80 // See ntifs.h +/* FILE_NEED_EA, indicates that the file to which the EA belongs cannot be + * interpreted without understanding the associated extended attributes. + */ +struct EA_INFO { + __le16 size_pack; // 0x00: Size of buffer to hold in packed form + __le16 count; // 0x02: Count of EA's with FILE_NEED_EA bit set + __le32 size; // 0x04: Size of buffer to hold in unpacked form +}; + +static_assert(sizeof(struct EA_INFO) == 8); + +/* ATTR_EA (0xE0) */ +struct EA_FULL { + __le32 size; // 0x00: (not in packed) + u8 flags; // 0x04 + u8 name_len; // 0x05 + __le16 elength; // 0x06 + u8 name[]; // 0x08 +}; + +static_assert(offsetof(struct EA_FULL, name) == 8); + +#define ACL_REVISION 2 +#define ACL_REVISION_DS 4 + +#define SE_SELF_RELATIVE cpu_to_le16(0x8000) + +struct SECURITY_DESCRIPTOR_RELATIVE { + u8 Revision; + u8 Sbz1; + __le16 Control; + __le32 Owner; + __le32 Group; + __le32 Sacl; + __le32 Dacl; +}; +static_assert(sizeof(struct SECURITY_DESCRIPTOR_RELATIVE) == 0x14); + +struct ACE_HEADER { + u8 AceType; + u8 AceFlags; + __le16 AceSize; +}; +static_assert(sizeof(struct ACE_HEADER) == 4); + +struct ACL { + u8 AclRevision; + u8 Sbz1; + __le16 AclSize; + __le16 AceCount; + __le16 Sbz2; +}; +static_assert(sizeof(struct ACL) == 8); + +struct SID { + u8 Revision; + u8 SubAuthorityCount; + u8 IdentifierAuthority[6]; + __le32 SubAuthority[]; +}; +static_assert(offsetof(struct SID, SubAuthority) == 8); + +// clang-format on diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h new file mode 100644 index 000000000000..0c3ac89c3115 --- /dev/null +++ b/fs/ntfs3/ntfs_fs.h @@ -0,0 +1,1092 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * + * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved. + * + */ + +// clang-format off +#define MINUS_ONE_T ((size_t)(-1)) +/* Biggest MFT / smallest cluster */ +#define MAXIMUM_BYTES_PER_MFT 4096 +#define NTFS_BLOCKS_PER_MFT_RECORD (MAXIMUM_BYTES_PER_MFT / 512) + +#define MAXIMUM_BYTES_PER_INDEX 4096 +#define NTFS_BLOCKS_PER_INODE (MAXIMUM_BYTES_PER_INDEX / 512) + +/* ntfs specific error code when fixup failed*/ +#define E_NTFS_FIXUP 555 +/* ntfs specific error code about resident->nonresident*/ +#define E_NTFS_NONRESIDENT 556 +/* ntfs specific error code about punch hole*/ +#define E_NTFS_NOTALIGNED 557 + + +/* sbi->flags */ +#define NTFS_FLAGS_NODISCARD 0x00000001 +/* Set when LogFile is replaying */ +#define NTFS_FLAGS_LOG_REPLAYING 0x00000008 +/* Set when we changed first MFT's which copy must be updated in $MftMirr */ +#define NTFS_FLAGS_MFTMIRR 0x00001000 +#define NTFS_FLAGS_NEED_REPLAY 0x04000000 + + +/* ni->ni_flags */ +/* + * Data attribute is external compressed (lzx/xpress) + * 1 - WOF_COMPRESSION_XPRESS4K + * 2 - WOF_COMPRESSION_XPRESS8K + * 3 - WOF_COMPRESSION_XPRESS16K + * 4 - WOF_COMPRESSION_LZX32K + */ +#define NI_FLAG_COMPRESSED_MASK 0x0000000f +/* Data attribute is deduplicated */ +#define NI_FLAG_DEDUPLICATED 0x00000010 +#define NI_FLAG_EA 0x00000020 +#define NI_FLAG_DIR 0x00000040 +#define NI_FLAG_RESIDENT 0x00000080 +#define NI_FLAG_UPDATE_PARENT 0x00000100 +// clang-format on + +struct ntfs_mount_options { + struct nls_table *nls; + + kuid_t fs_uid; + kgid_t fs_gid; + u16 fs_fmask_inv; + u16 fs_dmask_inv; + + unsigned uid : 1, /* uid was set */ + gid : 1, /* gid was set */ + fmask : 1, /* fmask was set */ + dmask : 1, /*dmask was set*/ + sys_immutable : 1, /* immutable system files */ + discard : 1, /* issue discard requests on deletions */ + sparse : 1, /*create sparse files*/ + showmeta : 1, /*show meta files*/ + nohidden : 1, /*do not show hidden files*/ + force : 1, /*rw mount dirty volume*/ + no_acs_rules : 1, /*exclude acs rules*/ + prealloc : 1 /*preallocate space when file is growing*/ + ; +}; + +/* special value to unpack and deallocate*/ +#define RUN_DEALLOCATE ((struct runs_tree *)(size_t)1) + +/* TODO: use rb tree instead of array */ +struct runs_tree { + struct ntfs_run *runs; + size_t count; // Currently used size a ntfs_run storage. + size_t allocated; // Currently allocated ntfs_run storage size. +}; + +struct ntfs_buffers { + /* Biggest MFT / smallest cluster = 4096 / 512 = 8 */ + /* Biggest index / smallest cluster = 4096 / 512 = 8 */ + struct buffer_head *bh[PAGE_SIZE >> SECTOR_SHIFT]; + u32 bytes; + u32 nbufs; + u32 off; +}; + +enum ALLOCATE_OPT { + ALLOCATE_DEF = 0, // Allocate all clusters + ALLOCATE_MFT = 1, // Allocate for MFT +}; + +enum bitmap_mutex_classes { + BITMAP_MUTEX_CLUSTERS = 0, + BITMAP_MUTEX_MFT = 1, +}; + +struct wnd_bitmap { + struct super_block *sb; + struct rw_semaphore rw_lock; + + struct runs_tree run; + size_t nbits; + + size_t total_zeroes; // total number of free bits + u16 *free_bits; // free bits in each window + size_t nwnd; + u32 bits_last; // bits in last window + + struct rb_root start_tree; // extents, sorted by 'start' + struct rb_root count_tree; // extents, sorted by 'count + start' + size_t count; // extents count + + /* + * -1 Tree is activated but not updated (too many fragments) + * 0 - Tree is not activated + * 1 - Tree is activated and updated + */ + int uptodated; + size_t extent_min; // Minimal extent used while building + size_t extent_max; // Upper estimate of biggest free block + + /* Zone [bit, end) */ + size_t zone_bit; + size_t zone_end; + + bool set_tail; // not necessary in driver + bool inited; +}; + +typedef int (*NTFS_CMP_FUNC)(const void *key1, size_t len1, const void *key2, + size_t len2, const void *param); + +enum index_mutex_classed { + INDEX_MUTEX_I30 = 0, + INDEX_MUTEX_SII = 1, + INDEX_MUTEX_SDH = 2, + INDEX_MUTEX_SO = 3, + INDEX_MUTEX_SQ = 4, + INDEX_MUTEX_SR = 5, + INDEX_MUTEX_TOTAL +}; + +/* ntfs_index - allocation unit inside directory */ +struct ntfs_index { + struct runs_tree bitmap_run; + struct runs_tree alloc_run; + /* read/write access to 'bitmap_run'/'alloc_run' while ntfs_readdir */ + struct rw_semaphore run_lock; + + /*TODO: remove 'cmp'*/ + NTFS_CMP_FUNC cmp; + + u8 index_bits; // log2(root->index_block_size) + u8 idx2vbn_bits; // log2(root->index_block_clst) + u8 vbn2vbo_bits; // index_block_size < cluster? 9 : cluster_bits + u8 type; // index_mutex_classed +}; + +/* Minimum mft zone */ +#define NTFS_MIN_MFT_ZONE 100 + +/* ntfs file system in-core superblock data */ +struct ntfs_sb_info { + struct super_block *sb; + + u32 discard_granularity; + u64 discard_granularity_mask_inv; // ~(discard_granularity_mask_inv-1) + + u32 cluster_size; // bytes per cluster + u32 cluster_mask; // == cluster_size - 1 + u64 cluster_mask_inv; // ~(cluster_size - 1) + u32 block_mask; // sb->s_blocksize - 1 + u32 blocks_per_cluster; // cluster_size / sb->s_blocksize + + u32 record_size; + u32 sector_size; + u32 index_size; + + u8 sector_bits; + u8 cluster_bits; + u8 record_bits; + + u64 maxbytes; // Maximum size for normal files + u64 maxbytes_sparse; // Maximum size for sparse file + + u32 flags; // See NTFS_FLAGS_XXX + + CLST bad_clusters; // The count of marked bad clusters + + u16 max_bytes_per_attr; // maximum attribute size in record + u16 attr_size_tr; // attribute size threshold (320 bytes) + + /* Records in $Extend */ + CLST objid_no; + CLST quota_no; + CLST reparse_no; + CLST usn_jrnl_no; + + struct ATTR_DEF_ENTRY *def_table; // attribute definition table + u32 def_entries; + u32 ea_max_size; + + struct MFT_REC *new_rec; + + u16 *upcase; + + struct { + u64 lbo, lbo2; + struct ntfs_inode *ni; + struct wnd_bitmap bitmap; // $MFT::Bitmap + /* + * MFT records [11-24) used to expand MFT itself + * They always marked as used in $MFT::Bitmap + * 'reserved_bitmap' contains real bitmap of these records + */ + ulong reserved_bitmap; // bitmap of used records [11 - 24) + size_t next_free; // The next record to allocate from + size_t used; // mft valid size in records + u32 recs_mirr; // Number of records in MFTMirr + u8 next_reserved; + u8 reserved_bitmap_inited; + } mft; + + struct { + struct wnd_bitmap bitmap; // $Bitmap::Data + CLST next_free_lcn; + } used; + + struct { + u64 size; // in bytes + u64 blocks; // in blocks + u64 ser_num; + struct ntfs_inode *ni; + __le16 flags; // cached current VOLUME_INFO::flags, VOLUME_FLAG_DIRTY + u8 major_ver; + u8 minor_ver; + char label[65]; + bool real_dirty; /* real fs state*/ + } volume; + + struct { + struct ntfs_index index_sii; + struct ntfs_index index_sdh; + struct ntfs_inode *ni; + u32 next_id; + u64 next_off; + + __le32 def_security_id; + } security; + + struct { + struct ntfs_index index_r; + struct ntfs_inode *ni; + u64 max_size; // 16K + } reparse; + + struct { + struct ntfs_index index_o; + struct ntfs_inode *ni; + } objid; + + struct { + struct mutex mtx_lznt; + struct lznt *lznt; +#ifdef CONFIG_NTFS3_LZX_XPRESS + struct mutex mtx_xpress; + struct xpress_decompressor *xpress; + struct mutex mtx_lzx; + struct lzx_decompressor *lzx; +#endif + } compress; + + struct ntfs_mount_options options; + struct ratelimit_state msg_ratelimit; +}; + +/* + * one MFT record(usually 1024 bytes), consists of attributes + */ +struct mft_inode { + struct rb_node node; + struct ntfs_sb_info *sbi; + + struct MFT_REC *mrec; + struct ntfs_buffers nb; + + CLST rno; + bool dirty; +}; + +/* nested class for ntfs_inode::ni_lock */ +enum ntfs_inode_mutex_lock_class { + NTFS_INODE_MUTEX_DIRTY, + NTFS_INODE_MUTEX_SECURITY, + NTFS_INODE_MUTEX_OBJID, + NTFS_INODE_MUTEX_REPARSE, + NTFS_INODE_MUTEX_NORMAL, + NTFS_INODE_MUTEX_PARENT, +}; + +/* + * ntfs inode - extends linux inode. consists of one or more mft inodes + */ +struct ntfs_inode { + struct mft_inode mi; // base record + + /* + * Valid size: [0 - i_valid) - these range in file contains valid data + * Range [i_valid - inode->i_size) - contains 0 + * Usually i_valid <= inode->i_size + */ + u64 i_valid; + struct timespec64 i_crtime; + + struct mutex ni_lock; + + /* file attributes from std */ + enum FILE_ATTRIBUTE std_fa; + __le32 std_security_id; + + /* + * tree of mft_inode + * not empty when primary MFT record (usually 1024 bytes) can't save all attributes + * e.g. file becomes too fragmented or contains a lot of names + */ + struct rb_root mi_tree; + + /* + * This member is used in ntfs_readdir to ensure that all subrecords are loaded + */ + u8 mi_loaded; + + union { + struct ntfs_index dir; + struct { + struct rw_semaphore run_lock; + struct runs_tree run; +#ifdef CONFIG_NTFS3_LZX_XPRESS + struct page *offs_page; +#endif + } file; + }; + + struct { + struct runs_tree run; + struct ATTR_LIST_ENTRY *le; // 1K aligned memory + size_t size; + bool dirty; + } attr_list; + + size_t ni_flags; // NI_FLAG_XXX + + struct inode vfs_inode; +}; + +struct indx_node { + struct ntfs_buffers nb; + struct INDEX_BUFFER *index; +}; + +struct ntfs_fnd { + int level; + struct indx_node *nodes[20]; + struct NTFS_DE *de[20]; + struct NTFS_DE *root_de; +}; + +enum REPARSE_SIGN { + REPARSE_NONE = 0, + REPARSE_COMPRESSED = 1, + REPARSE_DEDUPLICATED = 2, + REPARSE_LINK = 3 +}; + +/* functions from attrib.c*/ +int attr_load_runs(struct ATTRIB *attr, struct ntfs_inode *ni, + struct runs_tree *run, const CLST *vcn); +int attr_allocate_clusters(struct ntfs_sb_info *sbi, struct runs_tree *run, + CLST vcn, CLST lcn, CLST len, CLST *pre_alloc, + enum ALLOCATE_OPT opt, CLST *alen, const size_t fr, + CLST *new_lcn); +int attr_make_nonresident(struct ntfs_inode *ni, struct ATTRIB *attr, + struct ATTR_LIST_ENTRY *le, struct mft_inode *mi, + u64 new_size, struct runs_tree *run, + struct ATTRIB **ins_attr, struct page *page); +int attr_set_size(struct ntfs_inode *ni, enum ATTR_TYPE type, + const __le16 *name, u8 name_len, struct runs_tree *run, + u64 new_size, const u64 *new_valid, bool keep_prealloc, + struct ATTRIB **ret); +int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn, + CLST *len, bool *new); +int attr_data_read_resident(struct ntfs_inode *ni, struct page *page); +int attr_data_write_resident(struct ntfs_inode *ni, struct page *page); +int attr_load_runs_vcn(struct ntfs_inode *ni, enum ATTR_TYPE type, + const __le16 *name, u8 name_len, struct runs_tree *run, + CLST vcn); +int attr_load_runs_range(struct ntfs_inode *ni, enum ATTR_TYPE type, + const __le16 *name, u8 name_len, struct runs_tree *run, + u64 from, u64 to); +int attr_wof_frame_info(struct ntfs_inode *ni, struct ATTRIB *attr, + struct runs_tree *run, u64 frame, u64 frames, + u8 frame_bits, u32 *ondisk_size, u64 *vbo_data); +int attr_is_frame_compressed(struct ntfs_inode *ni, struct ATTRIB *attr, + CLST frame, CLST *clst_data); +int attr_allocate_frame(struct ntfs_inode *ni, CLST frame, size_t compr_size, + u64 new_valid); +int attr_collapse_range(struct ntfs_inode *ni, u64 vbo, u64 bytes); +int attr_punch_hole(struct ntfs_inode *ni, u64 vbo, u64 bytes, u32 *frame_size); + +/* functions from attrlist.c*/ +void al_destroy(struct ntfs_inode *ni); +bool al_verify(struct ntfs_inode *ni); +int ntfs_load_attr_list(struct ntfs_inode *ni, struct ATTRIB *attr); +struct ATTR_LIST_ENTRY *al_enumerate(struct ntfs_inode *ni, + struct ATTR_LIST_ENTRY *le); +struct ATTR_LIST_ENTRY *al_find_le(struct ntfs_inode *ni, + struct ATTR_LIST_ENTRY *le, + const struct ATTRIB *attr); +struct ATTR_LIST_ENTRY *al_find_ex(struct ntfs_inode *ni, + struct ATTR_LIST_ENTRY *le, + enum ATTR_TYPE type, const __le16 *name, + u8 name_len, const CLST *vcn); +int al_add_le(struct ntfs_inode *ni, enum ATTR_TYPE type, const __le16 *name, + u8 name_len, CLST svcn, __le16 id, const struct MFT_REF *ref, + struct ATTR_LIST_ENTRY **new_le); +bool al_remove_le(struct ntfs_inode *ni, struct ATTR_LIST_ENTRY *le); +bool al_delete_le(struct ntfs_inode *ni, enum ATTR_TYPE type, CLST vcn, + const __le16 *name, size_t name_len, + const struct MFT_REF *ref); +int al_update(struct ntfs_inode *ni); +static inline size_t al_aligned(size_t size) +{ + return (size + 1023) & ~(size_t)1023; +} + +/* globals from bitfunc.c */ +bool are_bits_clear(const ulong *map, size_t bit, size_t nbits); +bool are_bits_set(const ulong *map, size_t bit, size_t nbits); +size_t get_set_bits_ex(const ulong *map, size_t bit, size_t nbits); + +/* globals from dir.c */ +int ntfs_utf16_to_nls(struct ntfs_sb_info *sbi, const struct le_str *uni, + u8 *buf, int buf_len); +int ntfs_nls_to_utf16(struct ntfs_sb_info *sbi, const u8 *name, u32 name_len, + struct cpu_str *uni, u32 max_ulen, + enum utf16_endian endian); +struct inode *dir_search_u(struct inode *dir, const struct cpu_str *uni, + struct ntfs_fnd *fnd); +bool dir_is_empty(struct inode *dir); +extern const struct file_operations ntfs_dir_operations; + +/* globals from file.c*/ +int ntfs_getattr(struct user_namespace *mnt_userns, const struct path *path, + struct kstat *stat, u32 request_mask, u32 flags); +void ntfs_sparse_cluster(struct inode *inode, struct page *page0, CLST vcn, + CLST len); +int ntfs3_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *attr); +int ntfs_file_open(struct inode *inode, struct file *file); +int ntfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, + __u64 start, __u64 len); +extern const struct inode_operations ntfs_special_inode_operations; +extern const struct inode_operations ntfs_file_inode_operations; +extern const struct file_operations ntfs_file_operations; + +/* globals from frecord.c */ +void ni_remove_mi(struct ntfs_inode *ni, struct mft_inode *mi); +struct ATTR_STD_INFO *ni_std(struct ntfs_inode *ni); +struct ATTR_STD_INFO5 *ni_std5(struct ntfs_inode *ni); +void ni_clear(struct ntfs_inode *ni); +int ni_load_mi_ex(struct ntfs_inode *ni, CLST rno, struct mft_inode **mi); +int ni_load_mi(struct ntfs_inode *ni, struct ATTR_LIST_ENTRY *le, + struct mft_inode **mi); +struct ATTRIB *ni_find_attr(struct ntfs_inode *ni, struct ATTRIB *attr, + struct ATTR_LIST_ENTRY **entry_o, + enum ATTR_TYPE type, const __le16 *name, + u8 name_len, const CLST *vcn, + struct mft_inode **mi); +struct ATTRIB *ni_enum_attr_ex(struct ntfs_inode *ni, struct ATTRIB *attr, + struct ATTR_LIST_ENTRY **le, + struct mft_inode **mi); +struct ATTRIB *ni_load_attr(struct ntfs_inode *ni, enum ATTR_TYPE type, + const __le16 *name, u8 name_len, CLST vcn, + struct mft_inode **pmi); +int ni_load_all_mi(struct ntfs_inode *ni); +bool ni_add_subrecord(struct ntfs_inode *ni, CLST rno, struct mft_inode **mi); +int ni_remove_attr(struct ntfs_inode *ni, enum ATTR_TYPE type, + const __le16 *name, size_t name_len, bool base_only, + const __le16 *id); +int ni_create_attr_list(struct ntfs_inode *ni); +int ni_expand_list(struct ntfs_inode *ni); +int ni_insert_nonresident(struct ntfs_inode *ni, enum ATTR_TYPE type, + const __le16 *name, u8 name_len, + const struct runs_tree *run, CLST svcn, CLST len, + __le16 flags, struct ATTRIB **new_attr, + struct mft_inode **mi); +int ni_insert_resident(struct ntfs_inode *ni, u32 data_size, + enum ATTR_TYPE type, const __le16 *name, u8 name_len, + struct ATTRIB **new_attr, struct mft_inode **mi); +int ni_remove_attr_le(struct ntfs_inode *ni, struct ATTRIB *attr, + struct ATTR_LIST_ENTRY *le); +int ni_delete_all(struct ntfs_inode *ni); +struct ATTR_FILE_NAME *ni_fname_name(struct ntfs_inode *ni, + const struct cpu_str *uni, + const struct MFT_REF *home, + struct ATTR_LIST_ENTRY **entry); +struct ATTR_FILE_NAME *ni_fname_type(struct ntfs_inode *ni, u8 name_type, + struct ATTR_LIST_ENTRY **entry); +int ni_new_attr_flags(struct ntfs_inode *ni, enum FILE_ATTRIBUTE new_fa); +enum REPARSE_SIGN ni_parse_reparse(struct ntfs_inode *ni, struct ATTRIB *attr, + void *buffer); +int ni_write_inode(struct inode *inode, int sync, const char *hint); +#define _ni_write_inode(i, w) ni_write_inode(i, w, __func__) +int ni_fiemap(struct ntfs_inode *ni, struct fiemap_extent_info *fieinfo, + __u64 vbo, __u64 len); +int ni_readpage_cmpr(struct ntfs_inode *ni, struct page *page); +int ni_decompress_file(struct ntfs_inode *ni); +int ni_read_frame(struct ntfs_inode *ni, u64 frame_vbo, struct page **pages, + u32 pages_per_frame); +int ni_write_frame(struct ntfs_inode *ni, struct page **pages, + u32 pages_per_frame); + +/* globals from fslog.c */ +int log_replay(struct ntfs_inode *ni, bool *initialized); + +/* globals from fsntfs.c */ +bool ntfs_fix_pre_write(struct NTFS_RECORD_HEADER *rhdr, size_t bytes); +int ntfs_fix_post_read(struct NTFS_RECORD_HEADER *rhdr, size_t bytes, + bool simple); +int ntfs_extend_init(struct ntfs_sb_info *sbi); +int ntfs_loadlog_and_replay(struct ntfs_inode *ni, struct ntfs_sb_info *sbi); +const struct ATTR_DEF_ENTRY *ntfs_query_def(struct ntfs_sb_info *sbi, + enum ATTR_TYPE Type); +int ntfs_look_for_free_space(struct ntfs_sb_info *sbi, CLST lcn, CLST len, + CLST *new_lcn, CLST *new_len, + enum ALLOCATE_OPT opt); +int ntfs_look_free_mft(struct ntfs_sb_info *sbi, CLST *rno, bool mft, + struct ntfs_inode *ni, struct mft_inode **mi); +void ntfs_mark_rec_free(struct ntfs_sb_info *sbi, CLST rno); +int ntfs_clear_mft_tail(struct ntfs_sb_info *sbi, size_t from, size_t to); +int ntfs_refresh_zone(struct ntfs_sb_info *sbi); +int ntfs_update_mftmirr(struct ntfs_sb_info *sbi, int wait); +enum NTFS_DIRTY_FLAGS { + NTFS_DIRTY_CLEAR = 0, + NTFS_DIRTY_DIRTY = 1, + NTFS_DIRTY_ERROR = 2, +}; +int ntfs_set_state(struct ntfs_sb_info *sbi, enum NTFS_DIRTY_FLAGS dirty); +int ntfs_sb_read(struct super_block *sb, u64 lbo, size_t bytes, void *buffer); +int ntfs_sb_write(struct super_block *sb, u64 lbo, size_t bytes, + const void *buffer, int wait); +int ntfs_sb_write_run(struct ntfs_sb_info *sbi, const struct runs_tree *run, + u64 vbo, const void *buf, size_t bytes); +struct buffer_head *ntfs_bread_run(struct ntfs_sb_info *sbi, + const struct runs_tree *run, u64 vbo); +int ntfs_read_run_nb(struct ntfs_sb_info *sbi, const struct runs_tree *run, + u64 vbo, void *buf, u32 bytes, struct ntfs_buffers *nb); +int ntfs_read_bh(struct ntfs_sb_info *sbi, const struct runs_tree *run, u64 vbo, + struct NTFS_RECORD_HEADER *rhdr, u32 bytes, + struct ntfs_buffers *nb); +int ntfs_get_bh(struct ntfs_sb_info *sbi, const struct runs_tree *run, u64 vbo, + u32 bytes, struct ntfs_buffers *nb); +int ntfs_write_bh(struct ntfs_sb_info *sbi, struct NTFS_RECORD_HEADER *rhdr, + struct ntfs_buffers *nb, int sync); +int ntfs_bio_pages(struct ntfs_sb_info *sbi, const struct runs_tree *run, + struct page **pages, u32 nr_pages, u64 vbo, u32 bytes, + u32 op); +int ntfs_bio_fill_1(struct ntfs_sb_info *sbi, const struct runs_tree *run); +int ntfs_vbo_to_lbo(struct ntfs_sb_info *sbi, const struct runs_tree *run, + u64 vbo, u64 *lbo, u64 *bytes); +struct ntfs_inode *ntfs_new_inode(struct ntfs_sb_info *sbi, CLST nRec, + bool dir); +extern const u8 s_default_security[0x50]; +bool is_sd_valid(const struct SECURITY_DESCRIPTOR_RELATIVE *sd, u32 len); +int ntfs_security_init(struct ntfs_sb_info *sbi); +int ntfs_get_security_by_id(struct ntfs_sb_info *sbi, __le32 security_id, + struct SECURITY_DESCRIPTOR_RELATIVE **sd, + size_t *size); +int ntfs_insert_security(struct ntfs_sb_info *sbi, + const struct SECURITY_DESCRIPTOR_RELATIVE *sd, + u32 size, __le32 *security_id, bool *inserted); +int ntfs_reparse_init(struct ntfs_sb_info *sbi); +int ntfs_objid_init(struct ntfs_sb_info *sbi); +int ntfs_objid_remove(struct ntfs_sb_info *sbi, struct GUID *guid); +int ntfs_insert_reparse(struct ntfs_sb_info *sbi, __le32 rtag, + const struct MFT_REF *ref); +int ntfs_remove_reparse(struct ntfs_sb_info *sbi, __le32 rtag, + const struct MFT_REF *ref); +void mark_as_free_ex(struct ntfs_sb_info *sbi, CLST lcn, CLST len, bool trim); +int run_deallocate(struct ntfs_sb_info *sbi, struct runs_tree *run, bool trim); + +/* globals from index.c */ +int indx_used_bit(struct ntfs_index *indx, struct ntfs_inode *ni, size_t *bit); +void fnd_clear(struct ntfs_fnd *fnd); +static inline struct ntfs_fnd *fnd_get(void) +{ + return ntfs_zalloc(sizeof(struct ntfs_fnd)); +} +static inline void fnd_put(struct ntfs_fnd *fnd) +{ + if (fnd) { + fnd_clear(fnd); + ntfs_free(fnd); + } +} +void indx_clear(struct ntfs_index *idx); +int indx_init(struct ntfs_index *indx, struct ntfs_sb_info *sbi, + const struct ATTRIB *attr, enum index_mutex_classed type); +struct INDEX_ROOT *indx_get_root(struct ntfs_index *indx, struct ntfs_inode *ni, + struct ATTRIB **attr, struct mft_inode **mi); +int indx_read(struct ntfs_index *idx, struct ntfs_inode *ni, CLST vbn, + struct indx_node **node); +int indx_find(struct ntfs_index *indx, struct ntfs_inode *dir, + const struct INDEX_ROOT *root, const void *Key, size_t KeyLen, + const void *param, int *diff, struct NTFS_DE **entry, + struct ntfs_fnd *fnd); +int indx_find_sort(struct ntfs_index *indx, struct ntfs_inode *ni, + const struct INDEX_ROOT *root, struct NTFS_DE **entry, + struct ntfs_fnd *fnd); +int indx_find_raw(struct ntfs_index *indx, struct ntfs_inode *ni, + const struct INDEX_ROOT *root, struct NTFS_DE **entry, + size_t *off, struct ntfs_fnd *fnd); +int indx_insert_entry(struct ntfs_index *indx, struct ntfs_inode *ni, + const struct NTFS_DE *new_de, const void *param, + struct ntfs_fnd *fnd); +int indx_delete_entry(struct ntfs_index *indx, struct ntfs_inode *ni, + const void *key, u32 key_len, const void *param); +int indx_update_dup(struct ntfs_inode *ni, struct ntfs_sb_info *sbi, + const struct ATTR_FILE_NAME *fname, + const struct NTFS_DUP_INFO *dup, int sync); + +/* globals from inode.c */ +struct inode *ntfs_iget5(struct super_block *sb, const struct MFT_REF *ref, + const struct cpu_str *name); +int ntfs_set_size(struct inode *inode, u64 new_size); +int reset_log_file(struct inode *inode); +int ntfs_get_block(struct inode *inode, sector_t vbn, + struct buffer_head *bh_result, int create); +int ntfs3_write_inode(struct inode *inode, struct writeback_control *wbc); +int ntfs_sync_inode(struct inode *inode); +int ntfs_flush_inodes(struct super_block *sb, struct inode *i1, + struct inode *i2); +int inode_write_data(struct inode *inode, const void *data, size_t bytes); +struct inode *ntfs_create_inode(struct user_namespace *mnt_userns, + struct inode *dir, struct dentry *dentry, + const struct cpu_str *uni, umode_t mode, + dev_t dev, const char *symname, u32 size, + struct ntfs_fnd *fnd); +int ntfs_link_inode(struct inode *inode, struct dentry *dentry); +int ntfs_unlink_inode(struct inode *dir, const struct dentry *dentry); +void ntfs_evict_inode(struct inode *inode); +extern const struct inode_operations ntfs_link_inode_operations; +extern const struct address_space_operations ntfs_aops; +extern const struct address_space_operations ntfs_aops_cmpr; + +/* globals from name_i.c*/ +int fill_name_de(struct ntfs_sb_info *sbi, void *buf, const struct qstr *name, + const struct cpu_str *uni); +struct dentry *ntfs3_get_parent(struct dentry *child); + +extern const struct inode_operations ntfs_dir_inode_operations; +extern const struct inode_operations ntfs_special_inode_operations; + +/* globals from record.c */ +int mi_get(struct ntfs_sb_info *sbi, CLST rno, struct mft_inode **mi); +void mi_put(struct mft_inode *mi); +int mi_init(struct mft_inode *mi, struct ntfs_sb_info *sbi, CLST rno); +int mi_read(struct mft_inode *mi, bool is_mft); +struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr); +// TODO: id? +struct ATTRIB *mi_find_attr(struct mft_inode *mi, struct ATTRIB *attr, + enum ATTR_TYPE type, const __le16 *name, + size_t name_len, const __le16 *id); +static inline struct ATTRIB *rec_find_attr_le(struct mft_inode *rec, + struct ATTR_LIST_ENTRY *le) +{ + return mi_find_attr(rec, NULL, le->type, le_name(le), le->name_len, + &le->id); +} +int mi_write(struct mft_inode *mi, int wait); +int mi_format_new(struct mft_inode *mi, struct ntfs_sb_info *sbi, CLST rno, + __le16 flags, bool is_mft); +void mi_mark_free(struct mft_inode *mi); +struct ATTRIB *mi_insert_attr(struct mft_inode *mi, enum ATTR_TYPE type, + const __le16 *name, u8 name_len, u32 asize, + u16 name_off); + +bool mi_remove_attr(struct mft_inode *mi, struct ATTRIB *attr); +bool mi_resize_attr(struct mft_inode *mi, struct ATTRIB *attr, int bytes); +int mi_pack_runs(struct mft_inode *mi, struct ATTRIB *attr, + struct runs_tree *run, CLST len); +static inline bool mi_is_ref(const struct mft_inode *mi, + const struct MFT_REF *ref) +{ + if (le32_to_cpu(ref->low) != mi->rno) + return false; + if (ref->seq != mi->mrec->seq) + return false; + +#ifdef CONFIG_NTFS3_64BIT_CLUSTER + return le16_to_cpu(ref->high) == (mi->rno >> 32); +#else + return !ref->high; +#endif +} + +static inline void mi_get_ref(const struct mft_inode *mi, struct MFT_REF *ref) +{ + ref->low = cpu_to_le32(mi->rno); +#ifdef CONFIG_NTFS3_64BIT_CLUSTER + ref->high = cpu_to_le16(mi->rno >> 32); +#else + ref->high = 0; +#endif + ref->seq = mi->mrec->seq; +} + +/* globals from run.c */ +bool run_lookup_entry(const struct runs_tree *run, CLST vcn, CLST *lcn, + CLST *len, size_t *index); +void run_truncate(struct runs_tree *run, CLST vcn); +void run_truncate_head(struct runs_tree *run, CLST vcn); +void run_truncate_around(struct runs_tree *run, CLST vcn); +bool run_lookup(const struct runs_tree *run, CLST vcn, size_t *Index); +bool run_add_entry(struct runs_tree *run, CLST vcn, CLST lcn, CLST len, + bool is_mft); +bool run_collapse_range(struct runs_tree *run, CLST vcn, CLST len); +bool run_get_entry(const struct runs_tree *run, size_t index, CLST *vcn, + CLST *lcn, CLST *len); +bool run_is_mapped_full(const struct runs_tree *run, CLST svcn, CLST evcn); + +int run_pack(const struct runs_tree *run, CLST svcn, CLST len, u8 *run_buf, + u32 run_buf_size, CLST *packed_vcns); +int run_unpack(struct runs_tree *run, struct ntfs_sb_info *sbi, CLST ino, + CLST svcn, CLST evcn, CLST vcn, const u8 *run_buf, + u32 run_buf_size); + +#ifdef NTFS3_CHECK_FREE_CLST +int run_unpack_ex(struct runs_tree *run, struct ntfs_sb_info *sbi, CLST ino, + CLST svcn, CLST evcn, CLST vcn, const u8 *run_buf, + u32 run_buf_size); +#else +#define run_unpack_ex run_unpack +#endif +int run_get_highest_vcn(CLST vcn, const u8 *run_buf, u64 *highest_vcn); + +/* globals from super.c */ +void *ntfs_set_shared(void *ptr, u32 bytes); +void *ntfs_put_shared(void *ptr); +void ntfs_unmap_meta(struct super_block *sb, CLST lcn, CLST len); +int ntfs_discard(struct ntfs_sb_info *sbi, CLST Lcn, CLST Len); + +/* globals from bitmap.c*/ +int __init ntfs3_init_bitmap(void); +void ntfs3_exit_bitmap(void); +void wnd_close(struct wnd_bitmap *wnd); +static inline size_t wnd_zeroes(const struct wnd_bitmap *wnd) +{ + return wnd->total_zeroes; +} +int wnd_init(struct wnd_bitmap *wnd, struct super_block *sb, size_t nbits); +int wnd_set_free(struct wnd_bitmap *wnd, size_t bit, size_t bits); +int wnd_set_used(struct wnd_bitmap *wnd, size_t bit, size_t bits); +bool wnd_is_free(struct wnd_bitmap *wnd, size_t bit, size_t bits); +bool wnd_is_used(struct wnd_bitmap *wnd, size_t bit, size_t bits); + +/* Possible values for 'flags' 'wnd_find' */ +#define BITMAP_FIND_MARK_AS_USED 0x01 +#define BITMAP_FIND_FULL 0x02 +size_t wnd_find(struct wnd_bitmap *wnd, size_t to_alloc, size_t hint, + size_t flags, size_t *allocated); +int wnd_extend(struct wnd_bitmap *wnd, size_t new_bits); +void wnd_zone_set(struct wnd_bitmap *wnd, size_t Lcn, size_t Len); +int ntfs_trim_fs(struct ntfs_sb_info *sbi, struct fstrim_range *range); + +/* globals from upcase.c */ +int ntfs_cmp_names(const __le16 *s1, size_t l1, const __le16 *s2, size_t l2, + const u16 *upcase, bool bothcase); +int ntfs_cmp_names_cpu(const struct cpu_str *uni1, const struct le_str *uni2, + const u16 *upcase, bool bothcase); + +/* globals from xattr.c */ +#ifdef CONFIG_NTFS3_FS_POSIX_ACL +struct posix_acl *ntfs_get_acl(struct inode *inode, int type); +int ntfs_set_acl(struct user_namespace *mnt_userns, struct inode *inode, + struct posix_acl *acl, int type); +int ntfs_init_acl(struct user_namespace *mnt_userns, struct inode *inode, + struct inode *dir); +#else +#define ntfs_get_acl NULL +#define ntfs_set_acl NULL +#endif + +int ntfs_acl_chmod(struct user_namespace *mnt_userns, struct inode *inode); +int ntfs_permission(struct user_namespace *mnt_userns, struct inode *inode, + int mask); +ssize_t ntfs_listxattr(struct dentry *dentry, char *buffer, size_t size); +extern const struct xattr_handler *ntfs_xattr_handlers[]; + +int ntfs_save_wsl_perm(struct inode *inode); +void ntfs_get_wsl_perm(struct inode *inode); + +/* globals from lznt.c */ +struct lznt *get_lznt_ctx(int level); +size_t compress_lznt(const void *uncompressed, size_t uncompressed_size, + void *compressed, size_t compressed_size, + struct lznt *ctx); +ssize_t decompress_lznt(const void *compressed, size_t compressed_size, + void *uncompressed, size_t uncompressed_size); + +static inline bool is_ntfs3(struct ntfs_sb_info *sbi) +{ + return sbi->volume.major_ver >= 3; +} + +/*(sb->s_flags & SB_ACTIVE)*/ +static inline bool is_mounted(struct ntfs_sb_info *sbi) +{ + return !!sbi->sb->s_root; +} + +static inline bool ntfs_is_meta_file(struct ntfs_sb_info *sbi, CLST rno) +{ + return rno < MFT_REC_FREE || rno == sbi->objid_no || + rno == sbi->quota_no || rno == sbi->reparse_no || + rno == sbi->usn_jrnl_no; +} + +static inline void ntfs_unmap_page(struct page *page) +{ + kunmap(page); + put_page(page); +} + +static inline struct page *ntfs_map_page(struct address_space *mapping, + unsigned long index) +{ + struct page *page = read_mapping_page(mapping, index, NULL); + + if (!IS_ERR(page)) { + kmap(page); + if (!PageError(page)) + return page; + ntfs_unmap_page(page); + return ERR_PTR(-EIO); + } + return page; +} + +static inline size_t wnd_zone_bit(const struct wnd_bitmap *wnd) +{ + return wnd->zone_bit; +} + +static inline size_t wnd_zone_len(const struct wnd_bitmap *wnd) +{ + return wnd->zone_end - wnd->zone_bit; +} + +static inline void run_init(struct runs_tree *run) +{ + run->runs = NULL; + run->count = 0; + run->allocated = 0; +} + +static inline struct runs_tree *run_alloc(void) +{ + return ntfs_zalloc(sizeof(struct runs_tree)); +} + +static inline void run_close(struct runs_tree *run) +{ + ntfs_vfree(run->runs); + memset(run, 0, sizeof(*run)); +} + +static inline void run_free(struct runs_tree *run) +{ + if (run) { + ntfs_vfree(run->runs); + ntfs_free(run); + } +} + +static inline bool run_is_empty(struct runs_tree *run) +{ + return !run->count; +} + +/* NTFS uses quad aligned bitmaps */ +static inline size_t bitmap_size(size_t bits) +{ + return QuadAlign((bits + 7) >> 3); +} + +#define _100ns2seconds 10000000 +#define SecondsToStartOf1970 0x00000002B6109100 + +#define NTFS_TIME_GRAN 100 + +/* + * kernel2nt + * + * converts in-memory kernel timestamp into nt time + */ +static inline __le64 kernel2nt(const struct timespec64 *ts) +{ + // 10^7 units of 100 nanoseconds one second + return cpu_to_le64(_100ns2seconds * + (ts->tv_sec + SecondsToStartOf1970) + + ts->tv_nsec / NTFS_TIME_GRAN); +} + +/* + * nt2kernel + * + * converts on-disk nt time into kernel timestamp + */ +static inline void nt2kernel(const __le64 tm, struct timespec64 *ts) +{ + u64 t = le64_to_cpu(tm) - _100ns2seconds * SecondsToStartOf1970; + + // WARNING: do_div changes its first argument(!) + ts->tv_nsec = do_div(t, _100ns2seconds) * 100; + ts->tv_sec = t; +} + +static inline struct ntfs_sb_info *ntfs_sb(struct super_block *sb) +{ + return sb->s_fs_info; +} + +/* Align up on cluster boundary */ +static inline u64 ntfs_up_cluster(const struct ntfs_sb_info *sbi, u64 size) +{ + return (size + sbi->cluster_mask) & sbi->cluster_mask_inv; +} + +/* Align up on cluster boundary */ +static inline u64 ntfs_up_block(const struct super_block *sb, u64 size) +{ + return (size + sb->s_blocksize - 1) & ~(u64)(sb->s_blocksize - 1); +} + +static inline CLST bytes_to_cluster(const struct ntfs_sb_info *sbi, u64 size) +{ + return (size + sbi->cluster_mask) >> sbi->cluster_bits; +} + +static inline u64 bytes_to_block(const struct super_block *sb, u64 size) +{ + return (size + sb->s_blocksize - 1) >> sb->s_blocksize_bits; +} + +static inline struct buffer_head *ntfs_bread(struct super_block *sb, + sector_t block) +{ + struct buffer_head *bh = sb_bread(sb, block); + + if (bh) + return bh; + + ntfs_err(sb, "failed to read volume at offset 0x%llx", + (u64)block << sb->s_blocksize_bits); + return NULL; +} + +static inline bool is_power_of2(size_t v) +{ + return v && !(v & (v - 1)); +} + +static inline struct ntfs_inode *ntfs_i(struct inode *inode) +{ + return container_of(inode, struct ntfs_inode, vfs_inode); +} + +static inline bool is_compressed(const struct ntfs_inode *ni) +{ + return (ni->std_fa & FILE_ATTRIBUTE_COMPRESSED) || + (ni->ni_flags & NI_FLAG_COMPRESSED_MASK); +} + +static inline int ni_ext_compress_bits(const struct ntfs_inode *ni) +{ + return 0xb + (ni->ni_flags & NI_FLAG_COMPRESSED_MASK); +} + +/* bits - 0xc, 0xd, 0xe, 0xf, 0x10 */ +static inline void ni_set_ext_compress_bits(struct ntfs_inode *ni, u8 bits) +{ + ni->ni_flags |= (bits - 0xb) & NI_FLAG_COMPRESSED_MASK; +} + +static inline bool is_dedup(const struct ntfs_inode *ni) +{ + return ni->ni_flags & NI_FLAG_DEDUPLICATED; +} + +static inline bool is_encrypted(const struct ntfs_inode *ni) +{ + return ni->std_fa & FILE_ATTRIBUTE_ENCRYPTED; +} + +static inline bool is_sparsed(const struct ntfs_inode *ni) +{ + return ni->std_fa & FILE_ATTRIBUTE_SPARSE_FILE; +} + +static inline int is_resident(struct ntfs_inode *ni) +{ + return ni->ni_flags & NI_FLAG_RESIDENT; +} + +static inline void le16_sub_cpu(__le16 *var, u16 val) +{ + *var = cpu_to_le16(le16_to_cpu(*var) - val); +} + +static inline void le32_sub_cpu(__le32 *var, u32 val) +{ + *var = cpu_to_le32(le32_to_cpu(*var) - val); +} + +static inline void nb_put(struct ntfs_buffers *nb) +{ + u32 i, nbufs = nb->nbufs; + + if (!nbufs) + return; + + for (i = 0; i < nbufs; i++) + put_bh(nb->bh[i]); + nb->nbufs = 0; +} + +static inline void put_indx_node(struct indx_node *in) +{ + if (!in) + return; + + ntfs_free(in->index); + nb_put(&in->nb); + ntfs_free(in); +} + +static inline void mi_clear(struct mft_inode *mi) +{ + nb_put(&mi->nb); + ntfs_free(mi->mrec); + mi->mrec = NULL; +} + +static inline void ni_lock(struct ntfs_inode *ni) +{ + mutex_lock_nested(&ni->ni_lock, NTFS_INODE_MUTEX_NORMAL); +} + +static inline void ni_lock_dir(struct ntfs_inode *ni) +{ + mutex_lock_nested(&ni->ni_lock, NTFS_INODE_MUTEX_PARENT); +} + +static inline void ni_unlock(struct ntfs_inode *ni) +{ + mutex_unlock(&ni->ni_lock); +} + +static inline int ni_trylock(struct ntfs_inode *ni) +{ + return mutex_trylock(&ni->ni_lock); +} + +static inline int attr_load_runs_attr(struct ntfs_inode *ni, + struct ATTRIB *attr, + struct runs_tree *run, CLST vcn) +{ + return attr_load_runs_vcn(ni, attr->type, attr_name(attr), + attr->name_len, run, vcn); +} + +static inline void le64_sub_cpu(__le64 *var, u64 val) +{ + *var = cpu_to_le64(le64_to_cpu(*var) - val); +} diff --git a/fs/ntfs3/upcase.c b/fs/ntfs3/upcase.c new file mode 100644 index 000000000000..9617382aca64 --- /dev/null +++ b/fs/ntfs3/upcase.c @@ -0,0 +1,105 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * + * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved. + * + */ +#include <linux/blkdev.h> +#include <linux/buffer_head.h> +#include <linux/module.h> +#include <linux/nls.h> + +#include "debug.h" +#include "ntfs.h" +#include "ntfs_fs.h" + +static inline u16 upcase_unicode_char(const u16 *upcase, u16 chr) +{ + if (chr < 'a') + return chr; + + if (chr <= 'z') + return chr - ('a' - 'A'); + + return upcase[chr]; +} + +/* + * Thanks Kari Argillander <kari.argillander(a)gmail.com> for idea and implementation 'bothcase' + * + * Straigth way to compare names: + * - case insensitive + * - if name equals and 'bothcases' then + * - case sensitive + * 'Straigth way' code scans input names twice in worst case + * Optimized code scans input names only once + */ +int ntfs_cmp_names(const __le16 *s1, size_t l1, const __le16 *s2, size_t l2, + const u16 *upcase, bool bothcase) +{ + int diff1 = 0; + int diff2; + size_t len = min(l1, l2); + + if (!bothcase && upcase) + goto case_insentive; + + for (; len; s1++, s2++, len--) { + diff1 = le16_to_cpu(*s1) - le16_to_cpu(*s2); + if (diff1) { + if (bothcase && upcase) + goto case_insentive; + + return diff1; + } + } + return l1 - l2; + +case_insentive: + for (; len; s1++, s2++, len--) { + diff2 = upcase_unicode_char(upcase, le16_to_cpu(*s1)) - + upcase_unicode_char(upcase, le16_to_cpu(*s2)); + if (diff2) + return diff2; + } + + diff2 = l1 - l2; + return diff2 ? diff2 : diff1; +} + +int ntfs_cmp_names_cpu(const struct cpu_str *uni1, const struct le_str *uni2, + const u16 *upcase, bool bothcase) +{ + const u16 *s1 = uni1->name; + const __le16 *s2 = uni2->name; + size_t l1 = uni1->len; + size_t l2 = uni2->len; + size_t len = min(l1, l2); + int diff1 = 0; + int diff2; + + if (!bothcase && upcase) + goto case_insentive; + + for (; len; s1++, s2++, len--) { + diff1 = *s1 - le16_to_cpu(*s2); + if (diff1) { + if (bothcase && upcase) + goto case_insentive; + + return diff1; + } + } + return l1 - l2; + +case_insentive: + for (; len; s1++, s2++, len--) { + diff2 = upcase_unicode_char(upcase, *s1) - + upcase_unicode_char(upcase, le16_to_cpu(*s2)); + if (diff2) + return diff2; + } + + diff2 = l1 - l2; + return diff2 ? diff2 : diff1; +} -- 2.30.0

2 1

Re: [PATCH OLK-5.10] x86/config: enable btrfs feature
by Xie XiuQi 13 Dec '21

13 Dec '21

Hi, Thanks for your patch. Please subscribe the kernel(a)openeuler.org and kernel-discuss(a)openeuler.org mailing list before sending patches, or your patches would be blocked. Others could not receive your email. Please resend this patch. On 2021/12/13 15:11, Jiao Fenfang wrote: > From: JiaoFenfang <jiaofenfang(a)uniontech.com> > > openEuler inclusion > category: feature > bugzilla: https://gitee.com/openeuler/kernel/issues/I4KVP7?from=project-issue > Add commit message here. > Signed-off-by: Jiao Fenfang <jiaofenfang(a)uniontech.com> > --- > arch/x86/configs/openeuler_defconfig | 8 +++++++- > 1 file changed, 7 insertions(+), 1 deletion(-) > Also enable it on arm64 platform? > diff --git a/arch/x86/configs/openeuler_defconfig b/arch/x86/configs/openeuler_defconfig > index 7b608301823c..01a902eba3b9 100644 > --- a/arch/x86/configs/openeuler_defconfig > +++ b/arch/x86/configs/openeuler_defconfig > @@ -7451,7 +7451,13 @@ CONFIG_XFS_POSIX_ACL=y > CONFIG_GFS2_FS=m > CONFIG_GFS2_FS_LOCKING_DLM=y > # CONFIG_OCFS2_FS is not set > -# CONFIG_BTRFS_FS is not set > +CONFIG_BTRFS_FS=m > +# CONFIG_BTRFS_FS_POSIX_ACL is not set > +# CONFIG_BTRFS_FS_CHECK_INTEGRITY is not set > +# CONFIG_BTRFS_FS_RUN_SANITY_TESTS is not set > +# CONFIG_BTRFS_DEBUG is not set > +# CONFIG_BTRFS_ASSERT is not set > +# CONFIG_BTRFS_FS_REF_VERIFY is not set > # CONFIG_NILFS2_FS is not set > # CONFIG_F2FS_FS is not set > # CONFIG_ZONEFS_FS is not set >

1 0

[PATCH openEuler-1.0-LTS] ixgbe: fix large MTU request from VF
by Yang Yingliang 13 Dec '21

13 Dec '21

From: Jesse Brandeburg <jesse.brandeburg(a)intel.com> mainline inclusion from mainline-v5.13-rc4 commit 63e39d29b3da02e901349f6cd71159818a4737a6 category: bugfix bugzilla: NA CVE: CVE-2021-33098 ----------------------------------------------- Check that the MTU value requested by the VF is in the supported range of MTUs before attempting to set the VF large packet enable, otherwise reject the request. This also avoids unnecessary register updates in the case of the 82599 controller. Fixes: 872844ddb9e4 ("ixgbe: Enable jumbo frames support w/ SR-IOV") Co-developed-by: Piotr Skajewski <piotrx.skajewski(a)intel.com> Signed-off-by: Piotr Skajewski <piotrx.skajewski(a)intel.com> Signed-off-by: Jesse Brandeburg <jesse.brandeburg(a)intel.com> Co-developed-by: Mateusz Palczewski <mateusz.palczewski(a)intel.com> Signed-off-by: Mateusz Palczewski <mateusz.palczewski(a)intel.com> Tested-by: Konrad Jankowski <konrad0.jankowski(a)intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen(a)intel.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Huang Guobin <huangguobin4(a)huawei.com> Reviewed-by: Wei Yongjun <weiyongjun1(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c index f6ffd9fb20793..8aaf856771d7b 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c @@ -467,12 +467,16 @@ static int ixgbe_set_vf_vlan(struct ixgbe_adapter *adapter, int add, int vid, return err; } -static s32 ixgbe_set_vf_lpe(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf) +static int ixgbe_set_vf_lpe(struct ixgbe_adapter *adapter, u32 max_frame, u32 vf) { struct ixgbe_hw *hw = &adapter->hw; - int max_frame = msgbuf[1]; u32 max_frs; + if (max_frame < ETH_MIN_MTU || max_frame > IXGBE_MAX_JUMBO_FRAME_SIZE) { + e_err(drv, "VF max_frame %d out of range\n", max_frame); + return -EINVAL; + } + /* * For 82599EB we have to keep all PFs and VFs operating with * the same max_frame value in order to avoid sending an oversize @@ -532,12 +536,6 @@ static s32 ixgbe_set_vf_lpe(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf) } } - /* MTU < 68 is an error and causes problems on some kernels */ - if (max_frame > IXGBE_MAX_JUMBO_FRAME_SIZE) { - e_err(drv, "VF max_frame %d out of range\n", max_frame); - return -EINVAL; - } - /* pull current max frame size from hardware */ max_frs = IXGBE_READ_REG(hw, IXGBE_MAXFRS); max_frs &= IXGBE_MHADD_MFS_MASK; @@ -1240,7 +1238,7 @@ static int ixgbe_rcv_msg_from_vf(struct ixgbe_adapter *adapter, u32 vf) retval = ixgbe_set_vf_vlan_msg(adapter, msgbuf, vf); break; case IXGBE_VF_SET_LPE: - retval = ixgbe_set_vf_lpe(adapter, msgbuf, vf); + retval = ixgbe_set_vf_lpe(adapter, msgbuf[1], vf); break; case IXGBE_VF_SET_MACVLAN: retval = ixgbe_set_vf_macvlan_msg(adapter, msgbuf, vf); -- 2.25.1

1 0

Re: [PATCH] vfio/iommu_type1: replace kfree with kvfree
by Xie XiuQi 13 Dec '21

13 Dec '21

Hi, Thanks for your patch. Please subscribe the kernel(a)openeuler.org and kernel-discuss(a)openeuler.org mailing list before sending patches, or your patches would be blocked. Please resend this patch, and specific the right branch. Welcome to start a topic at openEuler kernel sig meeting via seeding mail to kernel-discuss(a)openeuler.org. --- 可以通过openEuler kernel 小助手，参加openEuler kernel SIG 微信群。 https://openeuler.gitee.io/kernel-portal/img/wechat/openEuler_kernel_helper… On 2021/12/12 18:14, Jiacheng Shi wrote: > From: billsjchw <billsjc(a)126.com> > > Variables allocated by kvmalloc should not be freed by kfree. > Because they may be allocated by vmalloc. > So we replace kfree with kvfree here. > > Signed-off-by: Jiacheng Shi <billsjc(a)sjtu.edu.cn> > --- > drivers/vfio/vfio_iommu_type1.c | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c > index 5daceec48811..6811a85109aa 100644 > --- a/drivers/vfio/vfio_iommu_type1.c > +++ b/drivers/vfio/vfio_iommu_type1.c > @@ -1150,7 +1150,7 @@ static int vfio_iova_dirty_log_clear(u64 __user *bitmap, > } > > out: > - kfree(bitmap_buffer); > + kvfree(bitmap_buffer); > return ret; > } > >

1 0