From fb12ad5e3179c9667dfcbafe2c5da91f9e700e53 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Thu, 11 Aug 2022 16:11:36 -0700 Subject: Input: bma150 - fix a typo in some comments Remove some extra '0' s/BMA0150_RANGE_xxx/BMA150_RANGE_xxx/ s/BMA0150_BW_xxx/BMA150_BW_xxx Signed-off-by: Christophe JAILLET Link: https://lore.kernel.org/r/a331a6244a1dfbf34dc85f1be6995fa91500c801.1659802757.git.christophe.jaillet@wanadoo.fr Signed-off-by: Dmitry Torokhov --- include/linux/bma150.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bma150.h b/include/linux/bma150.h index 31c9e323a391..4d4a62d49341 100644 --- a/include/linux/bma150.h +++ b/include/linux/bma150.h @@ -33,8 +33,8 @@ struct bma150_cfg { unsigned char lg_hyst; /* Low-G hysterisis */ unsigned char lg_dur; /* Low-G duration */ unsigned char lg_thres; /* Low-G threshold */ - unsigned char range; /* one of BMA0150_RANGE_xxx */ - unsigned char bandwidth; /* one of BMA0150_BW_xxx */ + unsigned char range; /* one of BMA150_RANGE_xxx */ + unsigned char bandwidth; /* one of BMA150_BW_xxx */ }; struct bma150_platform_data { -- cgit v1.2.3 From 36cb6494429bd64b27b7ff8b4af56f8e526da2b4 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Thu, 28 Jul 2022 18:22:20 +0800 Subject: hwrng: core - let sleep be interrupted when unregistering hwrng MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There are two deadlock scenarios that need addressing, which cause problems when the computer goes to sleep, the interface is set down, and hwrng_unregister() is called. When the deadlock is hit, sleep is delayed for tens of seconds, causing it to fail. These scenarios are: 1) The hwrng kthread can't be stopped while it's sleeping, because it uses msleep_interruptible() which does not react to kthread_stop. 2) A normal user thread can't be interrupted by hwrng_unregister() while it's sleeping, because hwrng_unregister() is called from elsewhere. We solve both issues by add a completion object called dying that fulfils waiters once we have started the process in hwrng_unregister. At the same time, we should cleanup a common and useless dmesg splat in the same area. Cc: Reported-by: Gregory Erwin Fixes: fcd09c90c3c5 ("ath9k: use hw_random API instead of directly dumping into random.c") Link: https://lore.kernel.org/all/CAO+Okf6ZJC5-nTE_EJUGQtd8JiCkiEHytGgDsFGTEjs0c00giw@mail.gmail.com/ Link: https://lore.kernel.org/lkml/CAO+Okf5k+C+SE6pMVfPf-d8MfVPVq4PO7EY8Hys_DVXtent3HA@mail.gmail.com/ Link: https://bugs.archlinux.org/task/75138 Signed-off-by: Jason A. Donenfeld Signed-off-by: Herbert Xu Acked-by: Toke Høiland-Jørgensen Acked-by: Kalle Valo Signed-off-by: Herbert Xu --- include/linux/hw_random.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hw_random.h b/include/linux/hw_random.h index aa1d4da03538..77c2885c4c13 100644 --- a/include/linux/hw_random.h +++ b/include/linux/hw_random.h @@ -50,6 +50,7 @@ struct hwrng { struct list_head list; struct kref ref; struct completion cleanup_done; + struct completion dying; }; struct device; @@ -61,4 +62,6 @@ extern int devm_hwrng_register(struct device *dev, struct hwrng *rng); extern void hwrng_unregister(struct hwrng *rng); extern void devm_hwrng_unregister(struct device *dve, struct hwrng *rng); +extern long hwrng_msleep(struct hwrng *rng, unsigned int msecs); + #endif /* LINUX_HWRANDOM_H_ */ -- cgit v1.2.3 From a9da7251ac8bcc2f2358513868f1903ac2809b3d Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Mon, 22 Aug 2022 17:14:58 -0700 Subject: Input: gameport - move from strlcpy with unused retval to strscpy Follow the advice of the below link and prefer 'strscpy' in this subsystem. Conversion is 1:1 because the return value is not used. Generated by a coccinelle script. Signed-off-by: Wolfram Sang Link: https://lore.kernel.org/r/20220818210156.8143-1-wsa+renesas@sang-engineering.com Signed-off-by: Dmitry Torokhov --- include/linux/gameport.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gameport.h b/include/linux/gameport.h index 69081d899492..8c2f00018e89 100644 --- a/include/linux/gameport.h +++ b/include/linux/gameport.h @@ -110,7 +110,7 @@ static inline void gameport_free_port(struct gameport *gameport) static inline void gameport_set_name(struct gameport *gameport, const char *name) { - strlcpy(gameport->name, name, sizeof(gameport->name)); + strscpy(gameport->name, name, sizeof(gameport->name)); } /* -- cgit v1.2.3 From 9d2b2e83ef277b9c7b8852e8717140daa373ccf1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nuno=20S=C3=A1?= Date: Tue, 30 Aug 2022 20:54:10 -0700 Subject: Input: adp5588-keys - support gpi key events as 'gpio keys' MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This change replaces the support for GPIs as key event generators. Instead of reporting the events directly, we add a gpio based irqchip so that these events can be consumed by keys defined in the gpio-keys driver (as it's goal is indeed for keys on GPIOs capable of generating interrupts). With this, the gpio-adp5588 driver can also be dropped. The basic idea is that all the pins that are not being used as part of the keymap matrix can be possibly requested as GPIOs by gpio-keys (it's also fine to use these pins as plain interrupts though that's not really the point). Since the gpiochip now also has irqchip capabilities, we should only remove it after we free the device interrupt (otherwise we could, in theory, be handling GPIs interrupts while the gpiochip is concurrently removed). Thus the call 'adp5588_gpio_add()' is moved and since the setup phase also needs to come before making the gpios visible, we also need to move 'adp5588_setup()'. While at it, always select GPIOLIB so that we don't need to use #ifdef guards. Signed-off-by: Nuno Sá Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20220829131553.690063-2-nuno.sa@analog.com Signed-off-by: Dmitry Torokhov --- include/linux/platform_data/adp5588.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/adp5588.h b/include/linux/platform_data/adp5588.h index 6d3f7d911a92..82170ec8c266 100644 --- a/include/linux/platform_data/adp5588.h +++ b/include/linux/platform_data/adp5588.h @@ -147,8 +147,6 @@ struct adp5588_kpad_platform_data { unsigned en_keylock:1; /* Enable Key Lock feature */ unsigned short unlock_key1; /* Unlock Key 1 */ unsigned short unlock_key2; /* Unlock Key 2 */ - const struct adp5588_gpi_map *gpimap; - unsigned short gpimapsize; const struct adp5588_gpio_platform_data *gpio_data; }; -- cgit v1.2.3 From 6704a86283b7e79ff7ae36d388466428f6672962 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nuno=20S=C3=A1?= Date: Tue, 30 Aug 2022 21:00:14 -0700 Subject: Input: adp5588-keys - add support for fw properties MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Use firmware properties (eg: OF) to get the device specific configuration. This change just replaces the platform data since there was no platform using it and so, it makes no sense having both. Special note to the PULL-UP disable setting that is now supported as part of the gpio subsystem (using 'set_config()' callback). Signed-off-by: Nuno Sá Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20220829131553.690063-5-nuno.sa@analog.com Signed-off-by: Dmitry Torokhov --- include/linux/platform_data/adp5588.h | 169 ---------------------------------- 1 file changed, 169 deletions(-) delete mode 100644 include/linux/platform_data/adp5588.h (limited to 'include/linux') diff --git a/include/linux/platform_data/adp5588.h b/include/linux/platform_data/adp5588.h deleted file mode 100644 index 82170ec8c266..000000000000 --- a/include/linux/platform_data/adp5588.h +++ /dev/null @@ -1,169 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Analog Devices ADP5588 I/O Expander and QWERTY Keypad Controller - * - * Copyright 2009-2010 Analog Devices Inc. - */ - -#ifndef _ADP5588_H -#define _ADP5588_H - -#define DEV_ID 0x00 /* Device ID */ -#define CFG 0x01 /* Configuration Register1 */ -#define INT_STAT 0x02 /* Interrupt Status Register */ -#define KEY_LCK_EC_STAT 0x03 /* Key Lock and Event Counter Register */ -#define Key_EVENTA 0x04 /* Key Event Register A */ -#define Key_EVENTB 0x05 /* Key Event Register B */ -#define Key_EVENTC 0x06 /* Key Event Register C */ -#define Key_EVENTD 0x07 /* Key Event Register D */ -#define Key_EVENTE 0x08 /* Key Event Register E */ -#define Key_EVENTF 0x09 /* Key Event Register F */ -#define Key_EVENTG 0x0A /* Key Event Register G */ -#define Key_EVENTH 0x0B /* Key Event Register H */ -#define Key_EVENTI 0x0C /* Key Event Register I */ -#define Key_EVENTJ 0x0D /* Key Event Register J */ -#define KP_LCK_TMR 0x0E /* Keypad Lock1 to Lock2 Timer */ -#define UNLOCK1 0x0F /* Unlock Key1 */ -#define UNLOCK2 0x10 /* Unlock Key2 */ -#define GPIO_INT_STAT1 0x11 /* GPIO Interrupt Status */ -#define GPIO_INT_STAT2 0x12 /* GPIO Interrupt Status */ -#define GPIO_INT_STAT3 0x13 /* GPIO Interrupt Status */ -#define GPIO_DAT_STAT1 0x14 /* GPIO Data Status, Read twice to clear */ -#define GPIO_DAT_STAT2 0x15 /* GPIO Data Status, Read twice to clear */ -#define GPIO_DAT_STAT3 0x16 /* GPIO Data Status, Read twice to clear */ -#define GPIO_DAT_OUT1 0x17 /* GPIO DATA OUT */ -#define GPIO_DAT_OUT2 0x18 /* GPIO DATA OUT */ -#define GPIO_DAT_OUT3 0x19 /* GPIO DATA OUT */ -#define GPIO_INT_EN1 0x1A /* GPIO Interrupt Enable */ -#define GPIO_INT_EN2 0x1B /* GPIO Interrupt Enable */ -#define GPIO_INT_EN3 0x1C /* GPIO Interrupt Enable */ -#define KP_GPIO1 0x1D /* Keypad or GPIO Selection */ -#define KP_GPIO2 0x1E /* Keypad or GPIO Selection */ -#define KP_GPIO3 0x1F /* Keypad or GPIO Selection */ -#define GPI_EM1 0x20 /* GPI Event Mode 1 */ -#define GPI_EM2 0x21 /* GPI Event Mode 2 */ -#define GPI_EM3 0x22 /* GPI Event Mode 3 */ -#define GPIO_DIR1 0x23 /* GPIO Data Direction */ -#define GPIO_DIR2 0x24 /* GPIO Data Direction */ -#define GPIO_DIR3 0x25 /* GPIO Data Direction */ -#define GPIO_INT_LVL1 0x26 /* GPIO Edge/Level Detect */ -#define GPIO_INT_LVL2 0x27 /* GPIO Edge/Level Detect */ -#define GPIO_INT_LVL3 0x28 /* GPIO Edge/Level Detect */ -#define Debounce_DIS1 0x29 /* Debounce Disable */ -#define Debounce_DIS2 0x2A /* Debounce Disable */ -#define Debounce_DIS3 0x2B /* Debounce Disable */ -#define GPIO_PULL1 0x2C /* GPIO Pull Disable */ -#define GPIO_PULL2 0x2D /* GPIO Pull Disable */ -#define GPIO_PULL3 0x2E /* GPIO Pull Disable */ -#define CMP_CFG_STAT 0x30 /* Comparator Configuration and Status Register */ -#define CMP_CONFG_SENS1 0x31 /* Sensor1 Comparator Configuration Register */ -#define CMP_CONFG_SENS2 0x32 /* L2 Light Sensor Reference Level, Output Falling for Sensor 1 */ -#define CMP1_LVL2_TRIP 0x33 /* L2 Light Sensor Hysteresis (Active when Output Rising) for Sensor 1 */ -#define CMP1_LVL2_HYS 0x34 /* L3 Light Sensor Reference Level, Output Falling For Sensor 1 */ -#define CMP1_LVL3_TRIP 0x35 /* L3 Light Sensor Hysteresis (Active when Output Rising) For Sensor 1 */ -#define CMP1_LVL3_HYS 0x36 /* Sensor 2 Comparator Configuration Register */ -#define CMP2_LVL2_TRIP 0x37 /* L2 Light Sensor Reference Level, Output Falling for Sensor 2 */ -#define CMP2_LVL2_HYS 0x38 /* L2 Light Sensor Hysteresis (Active when Output Rising) for Sensor 2 */ -#define CMP2_LVL3_TRIP 0x39 /* L3 Light Sensor Reference Level, Output Falling For Sensor 2 */ -#define CMP2_LVL3_HYS 0x3A /* L3 Light Sensor Hysteresis (Active when Output Rising) For Sensor 2 */ -#define CMP1_ADC_DAT_R1 0x3B /* Comparator 1 ADC data Register1 */ -#define CMP1_ADC_DAT_R2 0x3C /* Comparator 1 ADC data Register2 */ -#define CMP2_ADC_DAT_R1 0x3D /* Comparator 2 ADC data Register1 */ -#define CMP2_ADC_DAT_R2 0x3E /* Comparator 2 ADC data Register2 */ - -#define ADP5588_DEVICE_ID_MASK 0xF - - /* Configuration Register1 */ -#define ADP5588_AUTO_INC (1 << 7) -#define ADP5588_GPIEM_CFG (1 << 6) -#define ADP5588_OVR_FLOW_M (1 << 5) -#define ADP5588_INT_CFG (1 << 4) -#define ADP5588_OVR_FLOW_IEN (1 << 3) -#define ADP5588_K_LCK_IM (1 << 2) -#define ADP5588_GPI_IEN (1 << 1) -#define ADP5588_KE_IEN (1 << 0) - -/* Interrupt Status Register */ -#define ADP5588_CMP2_INT (1 << 5) -#define ADP5588_CMP1_INT (1 << 4) -#define ADP5588_OVR_FLOW_INT (1 << 3) -#define ADP5588_K_LCK_INT (1 << 2) -#define ADP5588_GPI_INT (1 << 1) -#define ADP5588_KE_INT (1 << 0) - -/* Key Lock and Event Counter Register */ -#define ADP5588_K_LCK_EN (1 << 6) -#define ADP5588_LCK21 0x30 -#define ADP5588_KEC 0xF - -#define ADP5588_MAXGPIO 18 -#define ADP5588_BANK(offs) ((offs) >> 3) -#define ADP5588_BIT(offs) (1u << ((offs) & 0x7)) - -/* Put one of these structures in i2c_board_info platform_data */ - -#define ADP5588_KEYMAPSIZE 80 - -#define GPI_PIN_ROW0 97 -#define GPI_PIN_ROW1 98 -#define GPI_PIN_ROW2 99 -#define GPI_PIN_ROW3 100 -#define GPI_PIN_ROW4 101 -#define GPI_PIN_ROW5 102 -#define GPI_PIN_ROW6 103 -#define GPI_PIN_ROW7 104 -#define GPI_PIN_COL0 105 -#define GPI_PIN_COL1 106 -#define GPI_PIN_COL2 107 -#define GPI_PIN_COL3 108 -#define GPI_PIN_COL4 109 -#define GPI_PIN_COL5 110 -#define GPI_PIN_COL6 111 -#define GPI_PIN_COL7 112 -#define GPI_PIN_COL8 113 -#define GPI_PIN_COL9 114 - -#define GPI_PIN_ROW_BASE GPI_PIN_ROW0 -#define GPI_PIN_ROW_END GPI_PIN_ROW7 -#define GPI_PIN_COL_BASE GPI_PIN_COL0 -#define GPI_PIN_COL_END GPI_PIN_COL9 - -#define GPI_PIN_BASE GPI_PIN_ROW_BASE -#define GPI_PIN_END GPI_PIN_COL_END - -#define ADP5588_GPIMAPSIZE_MAX (GPI_PIN_END - GPI_PIN_BASE + 1) - -struct adp5588_gpi_map { - unsigned short pin; - unsigned short sw_evt; -}; - -struct adp5588_kpad_platform_data { - int rows; /* Number of rows */ - int cols; /* Number of columns */ - const unsigned short *keymap; /* Pointer to keymap */ - unsigned short keymapsize; /* Keymap size */ - unsigned repeat:1; /* Enable key repeat */ - unsigned en_keylock:1; /* Enable Key Lock feature */ - unsigned short unlock_key1; /* Unlock Key 1 */ - unsigned short unlock_key2; /* Unlock Key 2 */ - const struct adp5588_gpio_platform_data *gpio_data; -}; - -struct i2c_client; /* forward declaration */ - -struct adp5588_gpio_platform_data { - int gpio_start; /* GPIO Chip base # */ - const char *const *names; - unsigned irq_base; /* interrupt base # */ - unsigned pullup_dis_mask; /* Pull-Up Disable Mask */ - int (*setup)(struct i2c_client *client, - unsigned gpio, unsigned ngpio, - void *context); - int (*teardown)(struct i2c_client *client, - unsigned gpio, unsigned ngpio, - void *context); - void *context; -}; - -#endif -- cgit v1.2.3 From e34a0425b8ef524355811e7408dc1d53d08dc538 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Fri, 26 Aug 2022 16:34:01 -0300 Subject: vfio/pci: Split linux/vfio_pci_core.h The header in include/linux should have only the exported interface for other vfio_pci modules to use. Internal definitions for vfio_pci.ko should be in a "priv" header along side the .c files. Move the internal declarations out of vfio_pci_core.h. They either move to vfio_pci_priv.h or to the C file that is the only user. Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe Reviewed-by: Cornelia Huck Link: https://lore.kernel.org/r/1-v2-1bd95d72f298+e0e-vfio_pci_priv_jgg@nvidia.com Signed-off-by: Alex Williamson --- include/linux/vfio_pci_core.h | 134 +----------------------------------------- 1 file changed, 1 insertion(+), 133 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index 5579ece4347b..9d18b832e61a 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -20,39 +20,10 @@ #define VFIO_PCI_CORE_H #define VFIO_PCI_OFFSET_SHIFT 40 - #define VFIO_PCI_OFFSET_TO_INDEX(off) (off >> VFIO_PCI_OFFSET_SHIFT) #define VFIO_PCI_INDEX_TO_OFFSET(index) ((u64)(index) << VFIO_PCI_OFFSET_SHIFT) #define VFIO_PCI_OFFSET_MASK (((u64)(1) << VFIO_PCI_OFFSET_SHIFT) - 1) -/* Special capability IDs predefined access */ -#define PCI_CAP_ID_INVALID 0xFF /* default raw access */ -#define PCI_CAP_ID_INVALID_VIRT 0xFE /* default virt access */ - -/* Cap maximum number of ioeventfds per device (arbitrary) */ -#define VFIO_PCI_IOEVENTFD_MAX 1000 - -struct vfio_pci_ioeventfd { - struct list_head next; - struct vfio_pci_core_device *vdev; - struct virqfd *virqfd; - void __iomem *addr; - uint64_t data; - loff_t pos; - int bar; - int count; - bool test_mem; -}; - -struct vfio_pci_irq_ctx { - struct eventfd_ctx *trigger; - struct virqfd *unmask; - struct virqfd *mask; - char *name; - bool masked; - struct irq_bypass_producer producer; -}; - struct vfio_pci_core_device; struct vfio_pci_region; @@ -78,23 +49,6 @@ struct vfio_pci_region { u32 flags; }; -struct vfio_pci_dummy_resource { - struct resource resource; - int index; - struct list_head res_next; -}; - -struct vfio_pci_vf_token { - struct mutex lock; - uuid_t uuid; - int users; -}; - -struct vfio_pci_mmap_vma { - struct vm_area_struct *vma; - struct list_head vma_next; -}; - struct vfio_pci_core_device { struct vfio_device vdev; struct pci_dev *pdev; @@ -141,92 +95,11 @@ struct vfio_pci_core_device { struct rw_semaphore memory_lock; }; -#define is_intx(vdev) (vdev->irq_type == VFIO_PCI_INTX_IRQ_INDEX) -#define is_msi(vdev) (vdev->irq_type == VFIO_PCI_MSI_IRQ_INDEX) -#define is_msix(vdev) (vdev->irq_type == VFIO_PCI_MSIX_IRQ_INDEX) -#define is_irq_none(vdev) (!(is_intx(vdev) || is_msi(vdev) || is_msix(vdev))) -#define irq_is(vdev, type) (vdev->irq_type == type) - -void vfio_pci_intx_mask(struct vfio_pci_core_device *vdev); -void vfio_pci_intx_unmask(struct vfio_pci_core_device *vdev); - -int vfio_pci_set_irqs_ioctl(struct vfio_pci_core_device *vdev, - uint32_t flags, unsigned index, - unsigned start, unsigned count, void *data); - -ssize_t vfio_pci_config_rw(struct vfio_pci_core_device *vdev, - char __user *buf, size_t count, - loff_t *ppos, bool iswrite); - -ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf, - size_t count, loff_t *ppos, bool iswrite); - -#ifdef CONFIG_VFIO_PCI_VGA -ssize_t vfio_pci_vga_rw(struct vfio_pci_core_device *vdev, char __user *buf, - size_t count, loff_t *ppos, bool iswrite); -#else -static inline ssize_t vfio_pci_vga_rw(struct vfio_pci_core_device *vdev, - char __user *buf, size_t count, - loff_t *ppos, bool iswrite) -{ - return -EINVAL; -} -#endif - -long vfio_pci_ioeventfd(struct vfio_pci_core_device *vdev, loff_t offset, - uint64_t data, int count, int fd); - -int vfio_pci_init_perm_bits(void); -void vfio_pci_uninit_perm_bits(void); - -int vfio_config_init(struct vfio_pci_core_device *vdev); -void vfio_config_free(struct vfio_pci_core_device *vdev); - +/* Will be exported for vfio pci drivers usage */ int vfio_pci_register_dev_region(struct vfio_pci_core_device *vdev, unsigned int type, unsigned int subtype, const struct vfio_pci_regops *ops, size_t size, u32 flags, void *data); - -int vfio_pci_set_power_state(struct vfio_pci_core_device *vdev, - pci_power_t state); - -bool __vfio_pci_memory_enabled(struct vfio_pci_core_device *vdev); -void vfio_pci_zap_and_down_write_memory_lock(struct vfio_pci_core_device *vdev); -u16 vfio_pci_memory_lock_and_enable(struct vfio_pci_core_device *vdev); -void vfio_pci_memory_unlock_and_restore(struct vfio_pci_core_device *vdev, - u16 cmd); - -#ifdef CONFIG_VFIO_PCI_IGD -int vfio_pci_igd_init(struct vfio_pci_core_device *vdev); -#else -static inline int vfio_pci_igd_init(struct vfio_pci_core_device *vdev) -{ - return -ENODEV; -} -#endif - -#ifdef CONFIG_VFIO_PCI_ZDEV_KVM -int vfio_pci_info_zdev_add_caps(struct vfio_pci_core_device *vdev, - struct vfio_info_cap *caps); -int vfio_pci_zdev_open_device(struct vfio_pci_core_device *vdev); -void vfio_pci_zdev_close_device(struct vfio_pci_core_device *vdev); -#else -static inline int vfio_pci_info_zdev_add_caps(struct vfio_pci_core_device *vdev, - struct vfio_info_cap *caps) -{ - return -ENODEV; -} - -static inline int vfio_pci_zdev_open_device(struct vfio_pci_core_device *vdev) -{ - return 0; -} - -static inline void vfio_pci_zdev_close_device(struct vfio_pci_core_device *vdev) -{} -#endif - -/* Will be exported for vfio pci drivers usage */ void vfio_pci_core_set_params(bool nointxmask, bool is_disable_vga, bool is_disable_idle_d3); void vfio_pci_core_close_device(struct vfio_device *core_vdev); @@ -256,9 +129,4 @@ void vfio_pci_core_finish_enable(struct vfio_pci_core_device *vdev); pci_ers_result_t vfio_pci_core_aer_err_detected(struct pci_dev *pdev, pci_channel_state_t state); -static inline bool vfio_pci_is_vga(struct pci_dev *pdev) -{ - return (pdev->class >> 8) == PCI_CLASS_DISPLAY_VGA; -} - #endif /* VFIO_PCI_CORE_H */ -- cgit v1.2.3 From 1e979ef5df8b7b604a625343a179b812a7984068 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Fri, 26 Aug 2022 16:34:02 -0300 Subject: vfio/pci: Rename vfio_pci_register_dev_region() As this is part of the vfio_pci_core component it should be called vfio_pci_core_register_dev_region() like everything else exported from this module. Suggested-by: Kevin Tian Signed-off-by: Jason Gunthorpe Reviewed-by: Kevin Tian Reviewed-by: Cornelia Huck Link: https://lore.kernel.org/r/2-v2-1bd95d72f298+e0e-vfio_pci_priv_jgg@nvidia.com Signed-off-by: Alex Williamson --- include/linux/vfio_pci_core.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index 9d18b832e61a..e5cf0d3313a6 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -96,10 +96,10 @@ struct vfio_pci_core_device { }; /* Will be exported for vfio pci drivers usage */ -int vfio_pci_register_dev_region(struct vfio_pci_core_device *vdev, - unsigned int type, unsigned int subtype, - const struct vfio_pci_regops *ops, - size_t size, u32 flags, void *data); +int vfio_pci_core_register_dev_region(struct vfio_pci_core_device *vdev, + unsigned int type, unsigned int subtype, + const struct vfio_pci_regops *ops, + size_t size, u32 flags, void *data); void vfio_pci_core_set_params(bool nointxmask, bool is_disable_vga, bool is_disable_idle_d3); void vfio_pci_core_close_device(struct vfio_device *core_vdev); -- cgit v1.2.3 From 4813724c4b76b62f8e6b60dd5655633d0db1c9a8 Mon Sep 17 00:00:00 2001 From: Abhishek Sahu Date: Mon, 29 Aug 2022 17:18:48 +0530 Subject: vfio/pci: Mask INTx during runtime suspend This patch adds INTx handling during runtime suspend/resume. All the suspend/resume related code for the user to put the device into the low power state will be added in subsequent patches. The INTx lines may be shared among devices. Whenever any INTx interrupt comes for the VFIO devices, then vfio_intx_handler() will be called for each device sharing the interrupt. Inside vfio_intx_handler(), it calls pci_check_and_mask_intx() and checks if the interrupt has been generated for the current device. Now, if the device is already in the D3cold state, then the config space can not be read. Attempt to read config space in D3cold state can cause system unresponsiveness in a few systems. To prevent this, mask INTx in runtime suspend callback, and unmask the same in runtime resume callback. If INTx has been already masked, then no handling is needed in runtime suspend/resume callbacks. 'pm_intx_masked' tracks this, and vfio_pci_intx_mask() has been updated to return true if the INTx vfio_pci_irq_ctx.masked value is changed inside this function. For the runtime suspend which is triggered for the no user of VFIO device, the 'irq_type' will be VFIO_PCI_NUM_IRQS and these callbacks won't do anything. The MSI/MSI-X are not shared so similar handling should not be needed for MSI/MSI-X. vfio_msihandler() triggers eventfd_signal() without doing any device-specific config access. When the user performs any config access or IOCTL after receiving the eventfd notification, then the device will be moved to the D0 state first before servicing any request. Another option was to check this flag 'pm_intx_masked' inside vfio_intx_handler() instead of masking the interrupts. This flag is being set inside the runtime_suspend callback but the device can be in non-D3cold state (for example, if the user has disabled D3cold explicitly by sysfs, the D3cold is not supported in the platform, etc.). Also, in D3cold supported case, the device will be in D0 till the PCI core moves the device into D3cold. In this case, there is a possibility that the device can generate an interrupt. Adding check in the IRQ handler will not clear the IRQ status and the interrupt line will still be asserted. This can cause interrupt flooding. Signed-off-by: Abhishek Sahu Link: https://lore.kernel.org/r/20220829114850.4341-4-abhsahu@nvidia.com Signed-off-by: Alex Williamson --- include/linux/vfio_pci_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index e5cf0d3313a6..a0f1f36e42a2 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -78,6 +78,7 @@ struct vfio_pci_core_device { bool needs_reset; bool nointx; bool needs_pm_restore; + bool pm_intx_masked; struct pci_saved_state *pci_saved_state; struct pci_saved_state *pm_save; int ioeventfds_nr; -- cgit v1.2.3 From cc2742fe3660cc6500021d3da8f937d326392dbd Mon Sep 17 00:00:00 2001 From: Abhishek Sahu Date: Mon, 29 Aug 2022 17:18:49 +0530 Subject: vfio/pci: Implement VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY/EXIT Currently, if the runtime power management is enabled for vfio-pci based devices in the guest OS, then the guest OS will do the register write for PCI_PM_CTRL register. This write request will be handled in vfio_pm_config_write() where it will do the actual register write of PCI_PM_CTRL register. With this, the maximum D3hot state can be achieved for low power. If we can use the runtime PM framework, then we can achieve the D3cold state (on the supported systems) which will help in saving maximum power. 1. D3cold state can't be achieved by writing PCI standard PM config registers. This patch implements the following newly added low power related device features: - VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY - VFIO_DEVICE_FEATURE_LOW_POWER_EXIT The VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY feature will allow the device to make use of low power platform states on the host while the VFIO_DEVICE_FEATURE_LOW_POWER_EXIT will prevent further use of those power states. 2. The vfio-pci driver uses runtime PM framework for low power entry and exit. On the platforms where D3cold state is supported, the runtime PM framework will put the device into D3cold otherwise, D3hot or some other power state will be used. There are various cases where the device will not go into the runtime suspended state. For example, - The runtime power management is disabled on the host side for the device. - The user keeps the device busy after calling LOW_POWER_ENTRY. - There are dependent devices that are still in runtime active state. For these cases, the device will be in the same power state that has been configured by the user through PCI_PM_CTRL register. 3. The hypervisors can implement virtual ACPI methods. For example, in guest linux OS if PCI device ACPI node has _PR3 and _PR0 power resources with _ON/_OFF method, then guest linux OS invokes the _OFF method during D3cold transition and then _ON during D0 transition. The hypervisor can tap these virtual ACPI calls and then call the low power device feature IOCTL. 4. The 'pm_runtime_engaged' flag tracks the entry and exit to runtime PM. This flag is protected with 'memory_lock' semaphore. 5. All the config and other region access are wrapped under pm_runtime_resume_and_get() and pm_runtime_put(). So, if any device access happens while the device is in the runtime suspended state, then the device will be resumed first before access. Once the access has been finished, then the device will again go into the runtime suspended state. 6. The memory region access through mmap will not be allowed in the low power state. Since __vfio_pci_memory_enabled() is a common function, so check for 'pm_runtime_engaged' has been added explicitly in vfio_pci_mmap_fault() to block only mmap'ed access. Signed-off-by: Abhishek Sahu Link: https://lore.kernel.org/r/20220829114850.4341-5-abhsahu@nvidia.com Signed-off-by: Alex Williamson --- include/linux/vfio_pci_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index a0f1f36e42a2..1025d53fde0b 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -79,6 +79,7 @@ struct vfio_pci_core_device { bool nointx; bool needs_pm_restore; bool pm_intx_masked; + bool pm_runtime_engaged; struct pci_saved_state *pci_saved_state; struct pci_saved_state *pm_save; int ioeventfds_nr; -- cgit v1.2.3 From 453e6c98fd2bdae0df9adbc86af8d8bf1164edd5 Mon Sep 17 00:00:00 2001 From: Abhishek Sahu Date: Mon, 29 Aug 2022 17:18:50 +0530 Subject: vfio/pci: Implement VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY_WITH_WAKEUP This patch implements VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY_WITH_WAKEUP device feature. In the VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY, if there is any access for the VFIO device on the host side, then the device will be moved out of the low power state without the user's guest driver involvement. Once the device access has been finished, then the host can move the device again into low power state. With the low power entry happened through VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY_WITH_WAKEUP, the device will not be moved back into the low power state and a notification will be sent to the user by triggering wakeup eventfd. vfio_pci_core_pm_entry() will be called for both the variants of low power feature entry so add an extra argument for wakeup eventfd context and store locally in 'struct vfio_pci_core_device'. For the entry happened without wakeup eventfd, all the exit related handling will be done by the LOW_POWER_EXIT device feature only. When the LOW_POWER_EXIT will be called, then the vfio core layer vfio_device_pm_runtime_get() will increment the usage count and will resume the device. In the driver runtime_resume callback, the 'pm_wake_eventfd_ctx' will be NULL. Then vfio_pci_core_pm_exit() will call vfio_pci_runtime_pm_exit() and all the exit related handling will be done. For the entry happened with wakeup eventfd, in the driver resume callback, eventfd will be triggered and all the exit related handling will be done. When vfio_pci_runtime_pm_exit() will be called by vfio_pci_core_pm_exit(), then it will return early. But if the runtime suspend has not happened on the host side, then all the exit related handling will be done in vfio_pci_core_pm_exit() only. Signed-off-by: Abhishek Sahu Link: https://lore.kernel.org/r/20220829114850.4341-6-abhsahu@nvidia.com Signed-off-by: Alex Williamson --- include/linux/vfio_pci_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index 1025d53fde0b..089b603bcfdc 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -85,6 +85,7 @@ struct vfio_pci_core_device { int ioeventfds_nr; struct eventfd_ctx *err_trigger; struct eventfd_ctx *req_trigger; + struct eventfd_ctx *pm_wake_eventfd_ctx; struct list_head dummy_resources_list; struct mutex ioeventfds_lock; struct list_head ioeventfds_list; -- cgit v1.2.3 From 283945017cbf685546ba7d065f254ad77eb888b1 Mon Sep 17 00:00:00 2001 From: Yuan Can Date: Mon, 15 Aug 2022 01:33:39 +0000 Subject: iommu: Remove comment of dev_has_feat in struct doc dev_has_feat has been removed from iommu_ops in commit 309c56e84602 ("iommu: remove the unused dev_has_feat method"), remove its description in the struct doc. Signed-off-by: Yuan Can Link: https://lore.kernel.org/r/20220815013339.2552-1-yuancan@huawei.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index ea30f00dc145..a004e87e0e1d 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -212,7 +212,7 @@ struct iommu_iotlb_gather { * @of_xlate: add OF master IDs to iommu grouping * @is_attach_deferred: Check if domain attach should be deferred from iommu * driver init to device driver init (default no) - * @dev_has/enable/disable_feat: per device entries to check/enable/disable + * @dev_enable/disable_feat: per device entries to enable/disable * iommu specific features. * @sva_bind: Bind process address space to device * @sva_unbind: Unbind process address space from device -- cgit v1.2.3 From 359ad15763762c713a51300134e784a72eb9cb80 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Mon, 15 Aug 2022 16:26:49 +0100 Subject: iommu: Retire iommu_capable() With all callers now converted to the device-specific version, retire the old bus-based interface, and give drivers the chance to indicate accurate per-instance capabilities. Signed-off-by: Robin Murphy Reviewed-by: Lu Baolu Link: https://lore.kernel.org/r/d8bd8777d06929ad8f49df7fc80e1b9af32a41b5.1660574547.git.robin.murphy@arm.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index a004e87e0e1d..0013a1befe7b 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -227,7 +227,7 @@ struct iommu_iotlb_gather { * @owner: Driver module providing these ops */ struct iommu_ops { - bool (*capable)(enum iommu_cap); + bool (*capable)(struct device *dev, enum iommu_cap); /* Domain allocation and freeing by the iommu driver */ struct iommu_domain *(*domain_alloc)(unsigned iommu_domain_type); @@ -420,7 +420,6 @@ extern int bus_set_iommu(struct bus_type *bus, const struct iommu_ops *ops); extern int bus_iommu_probe(struct bus_type *bus); extern bool iommu_present(struct bus_type *bus); extern bool device_iommu_capable(struct device *dev, enum iommu_cap cap); -extern bool iommu_capable(struct bus_type *bus, enum iommu_cap cap); extern struct iommu_domain *iommu_domain_alloc(struct bus_type *bus); extern struct iommu_group *iommu_group_get_by_id(int id); extern void iommu_domain_free(struct iommu_domain *domain); @@ -697,11 +696,6 @@ static inline bool device_iommu_capable(struct device *dev, enum iommu_cap cap) return false; } -static inline bool iommu_capable(struct bus_type *bus, enum iommu_cap cap) -{ - return false; -} - static inline struct iommu_domain *iommu_domain_alloc(struct bus_type *bus) { return NULL; -- cgit v1.2.3 From 29e932295bfaba792d29e66e8be0637ff3994724 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Mon, 15 Aug 2022 17:20:17 +0100 Subject: iommu: Clean up bus_set_iommu() Clean up the remaining trivial bus_set_iommu() callsites along with the implementation. Now drivers only have to know and care about iommu_device instances, phew! Reviewed-by: Kevin Tian Tested-by: Matthew Rosato # s390 Tested-by: Niklas Schnelle # s390 Signed-off-by: Robin Murphy Link: https://lore.kernel.org/r/ea383d5f4d74ffe200ab61248e5de6e95846180a.1660572783.git.robin.murphy@arm.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 0013a1befe7b..35810f87ae74 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -416,7 +416,6 @@ static inline const struct iommu_ops *dev_iommu_ops(struct device *dev) return dev->iommu->iommu_dev->ops; } -extern int bus_set_iommu(struct bus_type *bus, const struct iommu_ops *ops); extern int bus_iommu_probe(struct bus_type *bus); extern bool iommu_present(struct bus_type *bus); extern bool device_iommu_capable(struct device *dev, enum iommu_cap cap); -- cgit v1.2.3 From fa49364cd5e65797014688cba623541083b3e5b0 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Tue, 16 Aug 2022 18:28:04 +0100 Subject: iommu/dma: Move public interfaces to linux/iommu.h The iommu-dma layer is now mostly encapsulated by iommu_dma_ops, with only a couple more public interfaces left pertaining to MSI integration. Since these depend on the main IOMMU API header anyway, move their declarations there, taking the opportunity to update the half-baked comments to proper kerneldoc along the way. Signed-off-by: Robin Murphy Acked-by: Catalin Marinas Acked-by: Marc Zyngier Link: https://lore.kernel.org/r/9cd99738f52094e6bed44bfee03fa4f288d20695.1660668998.git.robin.murphy@arm.com Signed-off-by: Joerg Roedel --- include/linux/dma-iommu.h | 40 ---------------------------------------- include/linux/iommu.h | 36 ++++++++++++++++++++++++++++++++++++ 2 files changed, 36 insertions(+), 40 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-iommu.h b/include/linux/dma-iommu.h index 24607dc3c2ac..e83de4f1f3d6 100644 --- a/include/linux/dma-iommu.h +++ b/include/linux/dma-iommu.h @@ -15,27 +15,10 @@ /* Domain management interface for IOMMU drivers */ int iommu_get_dma_cookie(struct iommu_domain *domain); -int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base); void iommu_put_dma_cookie(struct iommu_domain *domain); -/* Setup call for arch DMA mapping code */ -void iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 dma_limit); int iommu_dma_init_fq(struct iommu_domain *domain); -/* The DMA API isn't _quite_ the whole story, though... */ -/* - * iommu_dma_prepare_msi() - Map the MSI page in the IOMMU device - * - * The MSI page will be stored in @desc. - * - * Return: 0 on success otherwise an error describing the failure. - */ -int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr); - -/* Update the MSI message if required. */ -void iommu_dma_compose_msi_msg(struct msi_desc *desc, - struct msi_msg *msg); - void iommu_dma_get_resv_regions(struct device *dev, struct list_head *list); void iommu_dma_free_cpu_cached_iovas(unsigned int cpu, @@ -46,15 +29,8 @@ extern bool iommu_dma_forcedac; #else /* CONFIG_IOMMU_DMA */ struct iommu_domain; -struct msi_desc; -struct msi_msg; struct device; -static inline void iommu_setup_dma_ops(struct device *dev, u64 dma_base, - u64 dma_limit) -{ -} - static inline int iommu_dma_init_fq(struct iommu_domain *domain) { return -EINVAL; @@ -65,26 +41,10 @@ static inline int iommu_get_dma_cookie(struct iommu_domain *domain) return -ENODEV; } -static inline int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base) -{ - return -ENODEV; -} - static inline void iommu_put_dma_cookie(struct iommu_domain *domain) { } -static inline int iommu_dma_prepare_msi(struct msi_desc *desc, - phys_addr_t msi_addr) -{ - return 0; -} - -static inline void iommu_dma_compose_msi_msg(struct msi_desc *desc, - struct msi_msg *msg) -{ -} - static inline void iommu_dma_get_resv_regions(struct device *dev, struct list_head *list) { } diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 35810f87ae74..a325532aeab5 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -1063,4 +1063,40 @@ void iommu_debugfs_setup(void); static inline void iommu_debugfs_setup(void) {} #endif +#ifdef CONFIG_IOMMU_DMA +#include + +/* Setup call for arch DMA mapping code */ +void iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 dma_limit); + +int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base); + +int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr); +void iommu_dma_compose_msi_msg(struct msi_desc *desc, struct msi_msg *msg); + +#else /* CONFIG_IOMMU_DMA */ + +struct msi_desc; +struct msi_msg; + +static inline void iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 dma_limit) +{ +} + +static inline int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base) +{ + return -ENODEV; +} + +static inline int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr) +{ + return 0; +} + +static inline void iommu_dma_compose_msi_msg(struct msi_desc *desc, struct msi_msg *msg) +{ +} + +#endif /* CONFIG_IOMMU_DMA */ + #endif /* __LINUX_IOMMU_H */ -- cgit v1.2.3 From aaac38f614871df252aa7459647bf68d42f7c3e7 Mon Sep 17 00:00:00 2001 From: Vasant Hegde Date: Thu, 25 Aug 2022 06:39:36 +0000 Subject: iommu/amd: Initial support for AMD IOMMU v2 page table Introduce IO page table framework support for AMD IOMMU v2 page table. This patch implements 4 level page table within iommu amd driver and supports 4K/2M/1G page sizes. Signed-off-by: Vasant Hegde Link: https://lore.kernel.org/r/20220825063939.8360-7-vasant.hegde@amd.com Signed-off-by: Joerg Roedel --- include/linux/io-pgtable.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index ca98aeadcc80..ffe616db9409 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -16,6 +16,7 @@ enum io_pgtable_fmt { ARM_V7S, ARM_MALI_LPAE, AMD_IOMMU_V1, + AMD_IOMMU_V2, APPLE_DART, IO_PGTABLE_NUM_FMTS, }; @@ -260,6 +261,7 @@ extern struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s2_init_fns; extern struct io_pgtable_init_fns io_pgtable_arm_v7s_init_fns; extern struct io_pgtable_init_fns io_pgtable_arm_mali_lpae_init_fns; extern struct io_pgtable_init_fns io_pgtable_amd_iommu_v1_init_fns; +extern struct io_pgtable_init_fns io_pgtable_amd_iommu_v2_init_fns; extern struct io_pgtable_init_fns io_pgtable_apple_dart_init_fns; #endif /* __IO_PGTABLE_H */ -- cgit v1.2.3 From 58ccf0190d19d9a8a41f8a02b9e06742b58df4a1 Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Thu, 8 Sep 2022 21:34:42 +0300 Subject: vfio: Add an IOVA bitmap support The new facility adds a bunch of wrappers that abstract how an IOVA range is represented in a bitmap that is granulated by a given page_size. So it translates all the lifting of dealing with user pointers into its corresponding kernel addresses backing said user memory into doing finally the (non-atomic) bitmap ops to change various bits. The formula for the bitmap is: data[(iova / page_size) / 64] & (1ULL << (iova % 64)) Where 64 is the number of bits in a unsigned long (depending on arch) It introduces an IOVA iterator that uses a windowing scheme to minimize the pinning overhead, as opposed to pinning it on demand 4K at a time. Assuming a 4K kernel page and 4K requested page size, we can use a single kernel page to hold 512 page pointers, mapping 2M of bitmap, representing 64G of IOVA space. An example usage of these helpers for a given @base_iova, @page_size, @length and __user @data: bitmap = iova_bitmap_alloc(base_iova, page_size, length, data); if (IS_ERR(bitmap)) return -ENOMEM; ret = iova_bitmap_for_each(bitmap, arg, dirty_reporter_fn); iova_bitmap_free(bitmap); Each iteration of the @dirty_reporter_fn is called with a unique @iova and @length argument, indicating the current range available through the iova_bitmap. The @dirty_reporter_fn uses iova_bitmap_set() to mark dirty areas (@iova_length) within that provided range, as following: iova_bitmap_set(bitmap, iova, iova_length); The facility is intended to be used for user bitmaps representing dirtied IOVAs by IOMMU (via IOMMUFD) and PCI Devices (via vfio-pci). Signed-off-by: Joao Martins Signed-off-by: Yishai Hadas Link: https://lore.kernel.org/r/20220908183448.195262-5-yishaih@nvidia.com Signed-off-by: Alex Williamson --- include/linux/iova_bitmap.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) create mode 100644 include/linux/iova_bitmap.h (limited to 'include/linux') diff --git a/include/linux/iova_bitmap.h b/include/linux/iova_bitmap.h new file mode 100644 index 000000000000..c006cf0a25f3 --- /dev/null +++ b/include/linux/iova_bitmap.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2022, Oracle and/or its affiliates. + * Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved + */ +#ifndef _IOVA_BITMAP_H_ +#define _IOVA_BITMAP_H_ + +#include + +struct iova_bitmap; + +typedef int (*iova_bitmap_fn_t)(struct iova_bitmap *bitmap, + unsigned long iova, size_t length, + void *opaque); + +struct iova_bitmap *iova_bitmap_alloc(unsigned long iova, size_t length, + unsigned long page_size, + u64 __user *data); +void iova_bitmap_free(struct iova_bitmap *bitmap); +int iova_bitmap_for_each(struct iova_bitmap *bitmap, void *opaque, + iova_bitmap_fn_t fn); +void iova_bitmap_set(struct iova_bitmap *bitmap, + unsigned long iova, size_t length); + +#endif -- cgit v1.2.3 From 80c4b92a2dc48cce82a0348add48533db7e07314 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Thu, 8 Sep 2022 21:34:43 +0300 Subject: vfio: Introduce the DMA logging feature support Introduce the DMA logging feature support in the vfio core layer. It includes the processing of the device start/stop/report DMA logging UAPIs and calling the relevant driver 'op' to do the work. Specifically, Upon start, the core translates the given input ranges into an interval tree, checks for unexpected overlapping, non aligned ranges and then pass the translated input to the driver for start tracking the given ranges. Upon report, the core translates the given input user space bitmap and page size into an IOVA kernel bitmap iterator. Then it iterates it and call the driver to set the corresponding bits for the dirtied pages in a specific IOVA range. Upon stop, the driver is called to stop the previous started tracking. The next patches from the series will introduce the mlx5 driver implementation for the logging ops. Signed-off-by: Yishai Hadas Link: https://lore.kernel.org/r/20220908183448.195262-6-yishaih@nvidia.com Signed-off-by: Alex Williamson --- include/linux/vfio.h | 28 ++++++++++++++++++++++++++-- 1 file changed, 26 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index e05ddc6fe6a5..0e2826559091 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -14,6 +14,7 @@ #include #include #include +#include struct kvm; @@ -33,10 +34,11 @@ struct vfio_device { struct device *dev; const struct vfio_device_ops *ops; /* - * mig_ops is a static property of the vfio_device which must be set - * prior to registering the vfio_device. + * mig_ops/log_ops is a static property of the vfio_device which must + * be set prior to registering the vfio_device. */ const struct vfio_migration_ops *mig_ops; + const struct vfio_log_ops *log_ops; struct vfio_group *group; struct vfio_device_set *dev_set; struct list_head dev_set_list; @@ -108,6 +110,28 @@ struct vfio_migration_ops { enum vfio_device_mig_state *curr_state); }; +/** + * @log_start: Optional callback to ask the device start DMA logging. + * @log_stop: Optional callback to ask the device stop DMA logging. + * @log_read_and_clear: Optional callback to ask the device read + * and clear the dirty DMAs in some given range. + * + * The vfio core implementation of the DEVICE_FEATURE_DMA_LOGGING_ set + * of features does not track logging state relative to the device, + * therefore the device implementation of vfio_log_ops must handle + * arbitrary user requests. This includes rejecting subsequent calls + * to log_start without an intervening log_stop, as well as graceful + * handling of log_stop and log_read_and_clear from invalid states. + */ +struct vfio_log_ops { + int (*log_start)(struct vfio_device *device, + struct rb_root_cached *ranges, u32 nnodes, u64 *page_size); + int (*log_stop)(struct vfio_device *device); + int (*log_read_and_clear)(struct vfio_device *device, + unsigned long iova, unsigned long length, + struct iova_bitmap *dirty); +}; + /** * vfio_check_feature - Validate user input for the VFIO_DEVICE_FEATURE ioctl * @flags: Arg from the device_feature op -- cgit v1.2.3 From f2042ed21da7f8886c93efefff61f93e6d57e9bd Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Tue, 16 Aug 2022 18:28:05 +0100 Subject: iommu/dma: Make header private Now that dma-iommu.h only contains internal interfaces, make it private to the IOMMU subsytem. Signed-off-by: Robin Murphy Link: https://lore.kernel.org/r/b237e06c56a101f77af142a54b629b27aa179d22.1660668998.git.robin.murphy@arm.com [ joro : re-add stub for iommu_dma_get_resv_regions ] Signed-off-by: Joerg Roedel --- include/linux/dma-iommu.h | 53 ----------------------------------------------- 1 file changed, 53 deletions(-) delete mode 100644 include/linux/dma-iommu.h (limited to 'include/linux') diff --git a/include/linux/dma-iommu.h b/include/linux/dma-iommu.h deleted file mode 100644 index e83de4f1f3d6..000000000000 --- a/include/linux/dma-iommu.h +++ /dev/null @@ -1,53 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2014-2015 ARM Ltd. - */ -#ifndef __DMA_IOMMU_H -#define __DMA_IOMMU_H - -#include -#include - -#ifdef CONFIG_IOMMU_DMA -#include -#include -#include - -/* Domain management interface for IOMMU drivers */ -int iommu_get_dma_cookie(struct iommu_domain *domain); -void iommu_put_dma_cookie(struct iommu_domain *domain); - -int iommu_dma_init_fq(struct iommu_domain *domain); - -void iommu_dma_get_resv_regions(struct device *dev, struct list_head *list); - -void iommu_dma_free_cpu_cached_iovas(unsigned int cpu, - struct iommu_domain *domain); - -extern bool iommu_dma_forcedac; - -#else /* CONFIG_IOMMU_DMA */ - -struct iommu_domain; -struct device; - -static inline int iommu_dma_init_fq(struct iommu_domain *domain) -{ - return -EINVAL; -} - -static inline int iommu_get_dma_cookie(struct iommu_domain *domain) -{ - return -ENODEV; -} - -static inline void iommu_put_dma_cookie(struct iommu_domain *domain) -{ -} - -static inline void iommu_dma_get_resv_regions(struct device *dev, struct list_head *list) -{ -} - -#endif /* CONFIG_IOMMU_DMA */ -#endif /* __DMA_IOMMU_H */ -- cgit v1.2.3 From d79ddb069c5257a924456eb99b53fc1ea715c0a3 Mon Sep 17 00:00:00 2001 From: Chengming Zhou Date: Fri, 26 Aug 2022 00:41:05 +0800 Subject: sched/psi: Move private helpers to sched/stats.h This patch move psi_task_change/psi_task_switch declarations out of PSI public header, since they are only needed for implementing the PSI stats tracking in sched/stats.h psi_task_switch is obvious, psi_task_change can't be public helper since it doesn't check psi_disabled static key. And there is no any user now, so put it in sched/stats.h too. Signed-off-by: Chengming Zhou Signed-off-by: Peter Zijlstra (Intel) Acked-by: Johannes Weiner Link: https://lore.kernel.org/r/20220825164111.29534-5-zhouchengming@bytedance.com --- include/linux/psi.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/psi.h b/include/linux/psi.h index dd74411ac21d..fffd229fbf19 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -18,10 +18,6 @@ extern struct psi_group psi_system; void psi_init(void); -void psi_task_change(struct task_struct *task, int clear, int set); -void psi_task_switch(struct task_struct *prev, struct task_struct *next, - bool sleep); - void psi_memstall_enter(unsigned long *flags); void psi_memstall_leave(unsigned long *flags); -- cgit v1.2.3 From 71dbdde7914d32e86f01ac1f6e54e964c9dfdbd9 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Aug 2022 00:41:07 +0800 Subject: sched/psi: Remove NR_ONCPU task accounting We put all fields updated by the scheduler in the first cacheline of struct psi_group_cpu for performance. Since we want add another PSI_IRQ_FULL to track IRQ/SOFTIRQ pressure, we need to reclaim space first. This patch remove NR_ONCPU task accounting in struct psi_group_cpu, use one bit in state_mask to track instead. Signed-off-by: Johannes Weiner Signed-off-by: Chengming Zhou Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Chengming Zhou Tested-by: Chengming Zhou Link: https://lore.kernel.org/r/20220825164111.29534-7-zhouchengming@bytedance.com --- include/linux/psi_types.h | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h index c7fe7c089718..54cb74946db4 100644 --- a/include/linux/psi_types.h +++ b/include/linux/psi_types.h @@ -15,13 +15,6 @@ enum psi_task_count { NR_IOWAIT, NR_MEMSTALL, NR_RUNNING, - /* - * This can't have values other than 0 or 1 and could be - * implemented as a bit flag. But for now we still have room - * in the first cacheline of psi_group_cpu, and this way we - * don't have to special case any state tracking for it. - */ - NR_ONCPU, /* * For IO and CPU stalls the presence of running/oncpu tasks * in the domain means a partial rather than a full stall. @@ -32,16 +25,18 @@ enum psi_task_count { * threads and memstall ones. */ NR_MEMSTALL_RUNNING, - NR_PSI_TASK_COUNTS = 5, + NR_PSI_TASK_COUNTS = 4, }; /* Task state bitmasks */ #define TSK_IOWAIT (1 << NR_IOWAIT) #define TSK_MEMSTALL (1 << NR_MEMSTALL) #define TSK_RUNNING (1 << NR_RUNNING) -#define TSK_ONCPU (1 << NR_ONCPU) #define TSK_MEMSTALL_RUNNING (1 << NR_MEMSTALL_RUNNING) +/* Only one task can be scheduled, no corresponding task count */ +#define TSK_ONCPU (1 << NR_PSI_TASK_COUNTS) + /* Resources that workloads could be stalled on */ enum psi_res { PSI_IO, @@ -68,6 +63,9 @@ enum psi_states { NR_PSI_STATES = 7, }; +/* Use one bit in the state mask to track TSK_ONCPU */ +#define PSI_ONCPU (1 << NR_PSI_STATES) + enum psi_aggregators { PSI_AVGS = 0, PSI_POLL, -- cgit v1.2.3 From 52b1364ba0b105122d6de0e719b36db705011ac1 Mon Sep 17 00:00:00 2001 From: Chengming Zhou Date: Fri, 26 Aug 2022 00:41:08 +0800 Subject: sched/psi: Add PSI_IRQ to track IRQ/SOFTIRQ pressure Now PSI already tracked workload pressure stall information for CPU, memory and IO. Apart from these, IRQ/SOFTIRQ could have obvious impact on some workload productivity, such as web service workload. When CONFIG_IRQ_TIME_ACCOUNTING, we can get IRQ/SOFTIRQ delta time from update_rq_clock_task(), in which we can record that delta to CPU curr task's cgroups as PSI_IRQ_FULL status. Note we don't use PSI_IRQ_SOME since IRQ/SOFTIRQ always happen in the current task on the CPU, make nothing productive could run even if it were runnable, so we only use PSI_IRQ_FULL. Signed-off-by: Chengming Zhou Signed-off-by: Peter Zijlstra (Intel) Acked-by: Johannes Weiner Link: https://lore.kernel.org/r/20220825164111.29534-8-zhouchengming@bytedance.com --- include/linux/psi_types.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h index 54cb74946db4..40c28171cd91 100644 --- a/include/linux/psi_types.h +++ b/include/linux/psi_types.h @@ -42,7 +42,10 @@ enum psi_res { PSI_IO, PSI_MEM, PSI_CPU, - NR_PSI_RESOURCES = 3, +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + PSI_IRQ, +#endif + NR_PSI_RESOURCES, }; /* @@ -58,9 +61,12 @@ enum psi_states { PSI_MEM_FULL, PSI_CPU_SOME, PSI_CPU_FULL, +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + PSI_IRQ_FULL, +#endif /* Only per-CPU, to weigh the CPU in the global average: */ PSI_NONIDLE, - NR_PSI_STATES = 7, + NR_PSI_STATES, }; /* Use one bit in the state mask to track TSK_ONCPU */ -- cgit v1.2.3 From 57899a6610e67ba26fa3251ebbef4a5ed21efc5d Mon Sep 17 00:00:00 2001 From: Chengming Zhou Date: Fri, 26 Aug 2022 00:41:09 +0800 Subject: sched/psi: Consolidate cgroup_psi() cgroup_psi() can't return psi_group for root cgroup, so we have many open code "psi = cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi". This patch move cgroup_psi() definition to , in which we can return psi_system for root cgroup, so can handle all cgroups. Signed-off-by: Chengming Zhou Signed-off-by: Peter Zijlstra (Intel) Acked-by: Johannes Weiner Link: https://lore.kernel.org/r/20220825164111.29534-9-zhouchengming@bytedance.com --- include/linux/cgroup.h | 5 ----- include/linux/psi.h | 6 ++++++ 2 files changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index b0914aa26506..80cb970257be 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -673,11 +673,6 @@ static inline void pr_cont_cgroup_path(struct cgroup *cgrp) pr_cont_kernfs_path(cgrp->kn); } -static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) -{ - return cgrp->psi; -} - bool cgroup_psi_enabled(void); static inline void cgroup_init_kthreadd(void) diff --git a/include/linux/psi.h b/include/linux/psi.h index fffd229fbf19..362a74ca1d3b 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -7,6 +7,7 @@ #include #include #include +#include struct seq_file; struct css_set; @@ -30,6 +31,11 @@ __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file, poll_table *wait); #ifdef CONFIG_CGROUPS +static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) +{ + return cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi; +} + int psi_cgroup_alloc(struct cgroup *cgrp); void psi_cgroup_free(struct cgroup *cgrp); void cgroup_move_task(struct task_struct *p, struct css_set *to); -- cgit v1.2.3 From dc86aba751e2867244411adda1562f6664747019 Mon Sep 17 00:00:00 2001 From: Chengming Zhou Date: Fri, 26 Aug 2022 00:41:10 +0800 Subject: sched/psi: Cache parent psi_group to speed up group iteration We use iterate_groups() to iterate each level psi_group to update PSI stats, which is a very hot path. In current code, iterate_groups() have to use multiple branches and cgroup_parent() to get parent psi_group for each level, which is not very efficient. This patch cache parent psi_group in struct psi_group, only need to get psi_group of task itself first, then just use group->parent to iterate. Signed-off-by: Chengming Zhou Signed-off-by: Peter Zijlstra (Intel) Acked-by: Johannes Weiner Link: https://lore.kernel.org/r/20220825164111.29534-10-zhouchengming@bytedance.com --- include/linux/psi_types.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h index 40c28171cd91..a0b746258c68 100644 --- a/include/linux/psi_types.h +++ b/include/linux/psi_types.h @@ -151,6 +151,8 @@ struct psi_trigger { }; struct psi_group { + struct psi_group *parent; + /* Protects data used by the aggregator */ struct mutex avgs_lock; -- cgit v1.2.3 From 34f26a15611afb03c33df6819359d36f5b382589 Mon Sep 17 00:00:00 2001 From: Chengming Zhou Date: Wed, 7 Sep 2022 17:03:32 +0800 Subject: sched/psi: Per-cgroup PSI accounting disable/re-enable interface PSI accounts stalls for each cgroup separately and aggregates it at each level of the hierarchy. This may cause non-negligible overhead for some workloads when under deep level of the hierarchy. commit 3958e2d0c34e ("cgroup: make per-cgroup pressure stall tracking configurable") make PSI to skip per-cgroup stall accounting, only account system-wide to avoid this each level overhead. But for our use case, we also want leaf cgroup PSI stats accounted for userspace adjustment on that cgroup, apart from only system-wide adjustment. So this patch introduce a per-cgroup PSI accounting disable/re-enable interface "cgroup.pressure", which is a read-write single value file that allowed values are "0" and "1", the defaults is "1" so per-cgroup PSI stats is enabled by default. Implementation details: It should be relatively straight-forward to disable and re-enable state aggregation, time tracking, averaging on a per-cgroup level, if we can live with losing history from while it was disabled. I.e. the avgs will restart from 0, total= will have gaps. But it's hard or complex to stop/restart groupc->tasks[] updates, which is not implemented in this patch. So we always update groupc->tasks[] and PSI_ONCPU bit in psi_group_change() even when the cgroup PSI stats is disabled. Suggested-by: Johannes Weiner Suggested-by: Tejun Heo Signed-off-by: Chengming Zhou Signed-off-by: Peter Zijlstra (Intel) Acked-by: Johannes Weiner Link: https://lkml.kernel.org/r/20220907090332.2078-1-zhouchengming@bytedance.com --- include/linux/cgroup-defs.h | 3 +++ include/linux/psi.h | 2 ++ include/linux/psi_types.h | 3 +++ 3 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 4bcf56b3491c..7df76b318245 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -428,6 +428,9 @@ struct cgroup { struct cgroup_file procs_file; /* handle for "cgroup.procs" */ struct cgroup_file events_file; /* handle for "cgroup.events" */ + /* handles for "{cpu,memory,io,irq}.pressure" */ + struct cgroup_file psi_files[NR_PSI_RESOURCES]; + /* * The bitmask of subsystems enabled on the child cgroups. * ->subtree_control is the one configured through diff --git a/include/linux/psi.h b/include/linux/psi.h index 362a74ca1d3b..b029a847def1 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -39,6 +39,7 @@ static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) int psi_cgroup_alloc(struct cgroup *cgrp); void psi_cgroup_free(struct cgroup *cgrp); void cgroup_move_task(struct task_struct *p, struct css_set *to); +void psi_cgroup_restart(struct psi_group *group); #endif #else /* CONFIG_PSI */ @@ -60,6 +61,7 @@ static inline void cgroup_move_task(struct task_struct *p, struct css_set *to) { rcu_assign_pointer(p->cgroups, to); } +static inline void psi_cgroup_restart(struct psi_group *group) {} #endif #endif /* CONFIG_PSI */ diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h index a0b746258c68..6e4372735068 100644 --- a/include/linux/psi_types.h +++ b/include/linux/psi_types.h @@ -152,6 +152,7 @@ struct psi_trigger { struct psi_group { struct psi_group *parent; + bool enabled; /* Protects data used by the aggregator */ struct mutex avgs_lock; @@ -194,6 +195,8 @@ struct psi_group { #else /* CONFIG_PSI */ +#define NR_PSI_RESOURCES 0 + struct psi_group { }; #endif /* CONFIG_PSI */ -- cgit v1.2.3 From b9be19eef35587b15da0a5d887d6e04c0c6cefab Mon Sep 17 00:00:00 2001 From: Phil Auld Date: Tue, 6 Sep 2022 16:35:42 -0400 Subject: drivers/base: Fix unsigned comparison to -1 in CPUMAP_FILE_MAX_BYTES As PAGE_SIZE is unsigned long, -1 > PAGE_SIZE when NR_CPUS <= 3. This leads to very large file sizes: topology$ ls -l total 0 -r--r--r-- 1 root root 18446744073709551615 Sep 5 11:59 core_cpus -r--r--r-- 1 root root 4096 Sep 5 11:59 core_cpus_list -r--r--r-- 1 root root 4096 Sep 5 10:58 core_id -r--r--r-- 1 root root 18446744073709551615 Sep 5 10:10 core_siblings -r--r--r-- 1 root root 4096 Sep 5 11:59 core_siblings_list -r--r--r-- 1 root root 18446744073709551615 Sep 5 11:59 die_cpus -r--r--r-- 1 root root 4096 Sep 5 11:59 die_cpus_list -r--r--r-- 1 root root 4096 Sep 5 11:59 die_id -r--r--r-- 1 root root 18446744073709551615 Sep 5 11:59 package_cpus -r--r--r-- 1 root root 4096 Sep 5 11:59 package_cpus_list -r--r--r-- 1 root root 4096 Sep 5 10:58 physical_package_id -r--r--r-- 1 root root 18446744073709551615 Sep 5 10:10 thread_siblings -r--r--r-- 1 root root 4096 Sep 5 11:59 thread_siblings_list Adjust the inequality to catch the case when NR_CPUS is configured to a small value. Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Cc: Yury Norov Cc: stable@vger.kernel.org Cc: feng xiangjun Fixes: 7ee951acd31a ("drivers/base: fix userspace break from using bin_attributes for cpumap and cpulist") Reported-by: feng xiangjun Signed-off-by: Phil Auld Signed-off-by: Yury Norov --- include/linux/cpumask.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index bd047864c7ac..e8ad12b5b9d2 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -1127,9 +1127,10 @@ cpumap_print_list_to_buf(char *buf, const struct cpumask *mask, * cover a worst-case of every other cpu being on one of two nodes for a * very large NR_CPUS. * - * Use PAGE_SIZE as a minimum for smaller configurations. + * Use PAGE_SIZE as a minimum for smaller configurations while avoiding + * unsigned comparison to -1. */ -#define CPUMAP_FILE_MAX_BYTES ((((NR_CPUS * 9)/32 - 1) > PAGE_SIZE) \ +#define CPUMAP_FILE_MAX_BYTES (((NR_CPUS * 9)/32 > PAGE_SIZE) \ ? (NR_CPUS * 9)/32 - 1 : PAGE_SIZE) #define CPULIST_FILE_MAX_BYTES (((NR_CPUS * 7)/2 > PAGE_SIZE) ? (NR_CPUS * 7)/2 : PAGE_SIZE) -- cgit v1.2.3 From a7f4e6e4c47c41869fe5bea17e013b5557c57ed3 Mon Sep 17 00:00:00 2001 From: Zach O'Keefe Date: Wed, 6 Jul 2022 16:59:25 -0700 Subject: mm/thp: add flag to enforce sysfs THP in hugepage_vma_check() MADV_COLLAPSE is not coupled to the kernel-oriented sysfs THP settings[1]. hugepage_vma_check() is the authority on determining if a VMA is eligible for THP allocation/collapse, and currently enforces the sysfs THP settings. Add a flag to disable these checks. For now, only apply this arg to anon and file, which use /sys/kernel/transparent_hugepage/enabled. We can expand this to shmem, which uses /sys/kernel/transparent_hugepage/shmem_enabled, later. Use this flag in collapse_pte_mapped_thp() where previously the VMA flags passed to hugepage_vma_check() were OR'd with VM_HUGEPAGE to elide the VM_HUGEPAGE check in "madvise" THP mode. Prior to "mm: khugepaged: check THP flag in hugepage_vma_check()", this check also didn't check "never" THP mode. As such, this restores the previous behavior of collapse_pte_mapped_thp() where sysfs THP settings are ignored. See comment in code for justification why this is OK. [1] https://lore.kernel.org/linux-mm/CAAa6QmQxay1_=Pmt8oCX2-Va18t44FV-Vs-WsQt_6+qBks4nZA@mail.gmail.com/ Link: https://lkml.kernel.org/r/20220706235936.2197195-8-zokeefe@google.com Signed-off-by: Zach O'Keefe Reviewed-by: Yang Shi Cc: Alex Shi Cc: Andrea Arcangeli Cc: Arnd Bergmann Cc: Axel Rasmussen Cc: Chris Kennelly Cc: Chris Zankel Cc: David Hildenbrand Cc: David Rientjes Cc: Helge Deller Cc: Hugh Dickins Cc: Ivan Kokshaysky Cc: James Bottomley Cc: Jens Axboe Cc: "Kirill A. Shutemov" Cc: Matthew Wilcox Cc: Matt Turner Cc: Max Filippov Cc: Miaohe Lin Cc: Michal Hocko Cc: Minchan Kim Cc: Pasha Tatashin Cc: Pavel Begunkov Cc: Peter Xu Cc: Rongwei Wang Cc: SeongJae Park Cc: Song Liu Cc: Thomas Bogendoerfer Cc: Vlastimil Babka Cc: Zi Yan Cc: Dan Carpenter Cc: "Souptick Joarder (HPE)" Signed-off-by: Andrew Morton --- include/linux/huge_mm.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 768e5261fdae..b0e80cc72b0c 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -168,9 +168,8 @@ static inline bool file_thp_enabled(struct vm_area_struct *vma) !inode_is_open_for_write(inode) && S_ISREG(inode->i_mode); } -bool hugepage_vma_check(struct vm_area_struct *vma, - unsigned long vm_flags, - bool smaps, bool in_pf); +bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags, + bool smaps, bool in_pf, bool enforce_sysfs); #define transparent_hugepage_use_zero_page() \ (transparent_hugepage_flags & \ @@ -321,8 +320,8 @@ static inline bool transhuge_vma_suitable(struct vm_area_struct *vma, } static inline bool hugepage_vma_check(struct vm_area_struct *vma, - unsigned long vm_flags, - bool smaps, bool in_pf) + unsigned long vm_flags, bool smaps, + bool in_pf, bool enforce_sysfs) { return false; } -- cgit v1.2.3 From 7d8faaf155454f8798ec56404faca29a82689c77 Mon Sep 17 00:00:00 2001 From: Zach O'Keefe Date: Wed, 6 Jul 2022 16:59:27 -0700 Subject: mm/madvise: introduce MADV_COLLAPSE sync hugepage collapse This idea was introduced by David Rientjes[1]. Introduce a new madvise mode, MADV_COLLAPSE, that allows users to request a synchronous collapse of memory at their own expense. The benefits of this approach are: * CPU is charged to the process that wants to spend the cycles for the THP * Avoid unpredictable timing of khugepaged collapse Semantics This call is independent of the system-wide THP sysfs settings, but will fail for memory marked VM_NOHUGEPAGE. If the ranges provided span multiple VMAs, the semantics of the collapse over each VMA is independent from the others. This implies a hugepage cannot cross a VMA boundary. If collapse of a given hugepage-aligned/sized region fails, the operation may continue to attempt collapsing the remainder of memory specified. The memory ranges provided must be page-aligned, but are not required to be hugepage-aligned. If the memory ranges are not hugepage-aligned, the start/end of the range will be clamped to the first/last hugepage-aligned address covered by said range. The memory ranges must span at least one hugepage-sized region. All non-resident pages covered by the range will first be swapped/faulted-in, before being internally copied onto a freshly allocated hugepage. Unmapped pages will have their data directly initialized to 0 in the new hugepage. However, for every eligible hugepage aligned/sized region to-be collapsed, at least one page must currently be backed by memory (a PMD covering the address range must already exist). Allocation for the new hugepage may enter direct reclaim and/or compaction, regardless of VMA flags. When the system has multiple NUMA nodes, the hugepage will be allocated from the node providing the most native pages. This operation operates on the current state of the specified process and makes no persistent changes or guarantees on how pages will be mapped, constructed, or faulted in the future Return Value If all hugepage-sized/aligned regions covered by the provided range were either successfully collapsed, or were already PMD-mapped THPs, this operation will be deemed successful. On success, process_madvise(2) returns the number of bytes advised, and madvise(2) returns 0. Else, -1 is returned and errno is set to indicate the error for the most-recently attempted hugepage collapse. Note that many failures might have occurred, since the operation may continue to collapse in the event a single hugepage-sized/aligned region fails. ENOMEM Memory allocation failed or VMA not found EBUSY Memcg charging failed EAGAIN Required resource temporarily unavailable. Try again might succeed. EINVAL Other error: No PMD found, subpage doesn't have Present bit set, "Special" page no backed by struct page, VMA incorrectly sized, address not page-aligned, ... Most notable here is ENOMEM and EBUSY (new to madvise) which are intended to provide the caller with actionable feedback so they may take an appropriate fallback measure. Use Cases An immediate user of this new functionality are malloc() implementations that manage memory in hugepage-sized chunks, but sometimes subrelease memory back to the system in native-sized chunks via MADV_DONTNEED; zapping the pmd. Later, when the memory is hot, the implementation could madvise(MADV_COLLAPSE) to re-back the memory by THPs to regain hugepage coverage and dTLB performance. TCMalloc is such an implementation that could benefit from this[2]. Only privately-mapped anon memory is supported for now, but additional support for file, shmem, and HugeTLB high-granularity mappings[2] is expected. File and tmpfs/shmem support would permit: * Backing executable text by THPs. Current support provided by CONFIG_READ_ONLY_THP_FOR_FS may take a long time on a large system which might impair services from serving at their full rated load after (re)starting. Tricks like mremap(2)'ing text onto anonymous memory to immediately realize iTLB performance prevents page sharing and demand paging, both of which increase steady state memory footprint. With MADV_COLLAPSE, we get the best of both worlds: Peak upfront performance and lower RAM footprints. * Backing guest memory by hugapages after the memory contents have been migrated in native-page-sized chunks to a new host, in a userfaultfd-based live-migration stack. [1] https://lore.kernel.org/linux-mm/d098c392-273a-36a4-1a29-59731cdf5d3d@google.com/ [2] https://github.com/google/tcmalloc/tree/master/tcmalloc [jrdr.linux@gmail.com: avoid possible memory leak in failure path] Link: https://lkml.kernel.org/r/20220713024109.62810-1-jrdr.linux@gmail.com [zokeefe@google.com add missing kfree() to madvise_collapse()] Link: https://lore.kernel.org/linux-mm/20220713024109.62810-1-jrdr.linux@gmail.com/ Link: https://lkml.kernel.org/r/20220713161851.1879439-1-zokeefe@google.com [zokeefe@google.com: delay computation of hpage boundaries until use]] Link: https://lkml.kernel.org/r/20220720140603.1958773-4-zokeefe@google.com Link: https://lkml.kernel.org/r/20220706235936.2197195-10-zokeefe@google.com Signed-off-by: Zach O'Keefe Signed-off-by: "Souptick Joarder (HPE)" Suggested-by: David Rientjes Cc: Alex Shi Cc: Andrea Arcangeli Cc: Arnd Bergmann Cc: Axel Rasmussen Cc: Chris Kennelly Cc: Chris Zankel Cc: David Hildenbrand Cc: Helge Deller Cc: Hugh Dickins Cc: Ivan Kokshaysky Cc: James Bottomley Cc: Jens Axboe Cc: "Kirill A. Shutemov" Cc: Matthew Wilcox Cc: Matt Turner Cc: Max Filippov Cc: Miaohe Lin Cc: Michal Hocko Cc: Minchan Kim Cc: Pasha Tatashin Cc: Pavel Begunkov Cc: Peter Xu Cc: Rongwei Wang Cc: SeongJae Park Cc: Song Liu Cc: Thomas Bogendoerfer Cc: Vlastimil Babka Cc: Yang Shi Cc: Zi Yan Cc: Dan Carpenter Signed-off-by: Andrew Morton --- include/linux/huge_mm.h | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index b0e80cc72b0c..38265f9f782e 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -218,6 +218,9 @@ void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud, int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice); +int madvise_collapse(struct vm_area_struct *vma, + struct vm_area_struct **prev, + unsigned long start, unsigned long end); void vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start, unsigned long end, long adjust_next); spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma); @@ -361,9 +364,16 @@ static inline void split_huge_pmd_address(struct vm_area_struct *vma, static inline int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice) { - BUG(); - return 0; + return -EINVAL; } + +static inline int madvise_collapse(struct vm_area_struct *vma, + struct vm_area_struct **prev, + unsigned long start, unsigned long end) +{ + return -EINVAL; +} + static inline void vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start, unsigned long end, -- cgit v1.2.3 From e9c2dbc8bf71a5039604a1dc45b10f24a2098f3b Mon Sep 17 00:00:00 2001 From: Yang Yang Date: Mon, 8 Aug 2022 00:56:45 +0000 Subject: mm/vmscan: define macros for refaults in struct lruvec The magic number 0 and 1 are used in several places in vmscan.c. Define macros for them to improve code readability. Link: https://lkml.kernel.org/r/20220808005644.1721066-1-yang.yang29@zte.com.cn Signed-off-by: Yang Yang Cc: Johannes Weiner Signed-off-by: Andrew Morton --- include/linux/mmzone.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index e24b40c52468..8f571dc7c524 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -306,6 +306,8 @@ static inline bool is_active_lru(enum lru_list lru) return (lru == LRU_ACTIVE_ANON || lru == LRU_ACTIVE_FILE); } +#define WORKINGSET_ANON 0 +#define WORKINGSET_FILE 1 #define ANON_AND_FILE 2 enum lruvec_flags { -- cgit v1.2.3 From d2226ebd5484afcf9f9b71b394ec1567a7730eb1 Mon Sep 17 00:00:00 2001 From: Feng Tang Date: Fri, 5 Aug 2022 08:59:03 +0800 Subject: mm/hugetlb: add dedicated func to get 'allowed' nodemask for current process Muchun Song found that after MPOL_PREFERRED_MANY policy was introduced in commit b27abaccf8e8 ("mm/mempolicy: add MPOL_PREFERRED_MANY for multiple preferred nodes"), the policy_nodemask_current()'s semantics for this new policy has been changed, which returns 'preferred' nodes instead of 'allowed' nodes. With the changed semantic of policy_nodemask_current, a task with MPOL_PREFERRED_MANY policy could fail to get its reservation even though it can fall back to other nodes (either defined by cpusets or all online nodes) for that reservation failing mmap calles unnecessarily early. The fix is to not consider MPOL_PREFERRED_MANY for reservations at all because they, unlike MPOL_MBIND, do not pose any actual hard constrain. Michal suggested the policy_nodemask_current() is only used by hugetlb, and could be moved to hugetlb code with more explicit name to enforce the 'allowed' semantics for which only MPOL_BIND policy matters. apply_policy_zone() is made extern to be called in hugetlb code and its return value is changed to bool. [1]. https://lore.kernel.org/lkml/20220801084207.39086-1-songmuchun@bytedance.com/t/ Link: https://lkml.kernel.org/r/20220805005903.95563-1-feng.tang@intel.com Fixes: b27abaccf8e8 ("mm/mempolicy: add MPOL_PREFERRED_MANY for multiple preferred nodes") Signed-off-by: Feng Tang Reported-by: Muchun Song Suggested-by: Michal Hocko Acked-by: Michal Hocko Reviewed-by: Muchun Song Cc: Mike Kravetz Cc: Dave Hansen Cc: Ben Widawsky Signed-off-by: Andrew Morton --- include/linux/mempolicy.h | 13 +------------ 1 file changed, 1 insertion(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 668389b4b53d..d232de7cdc56 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -151,13 +151,6 @@ extern bool mempolicy_in_oom_domain(struct task_struct *tsk, const nodemask_t *mask); extern nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy); -static inline nodemask_t *policy_nodemask_current(gfp_t gfp) -{ - struct mempolicy *mpol = get_task_policy(current); - - return policy_nodemask(gfp, mpol); -} - extern unsigned int mempolicy_slab_node(void); extern enum zone_type policy_zone; @@ -189,6 +182,7 @@ static inline bool mpol_is_preferred_many(struct mempolicy *pol) return (pol->mode == MPOL_PREFERRED_MANY); } +extern bool apply_policy_zone(struct mempolicy *policy, enum zone_type zone); #else @@ -294,11 +288,6 @@ static inline void mpol_put_task_policy(struct task_struct *task) { } -static inline nodemask_t *policy_nodemask_current(gfp_t gfp) -{ - return NULL; -} - static inline bool mpol_is_preferred_many(struct mempolicy *pol) { return false; -- cgit v1.2.3 From b84e04f1baeebe6872b22a027cfc558621e842d4 Mon Sep 17 00:00:00 2001 From: Imran Khan Date: Mon, 15 Aug 2022 05:53:53 +1000 Subject: kfence: add sysfs interface to disable kfence for selected slabs. By default kfence allocation can happen for any slab object, whose size is up to PAGE_SIZE, as long as that allocation is the first allocation after expiration of kfence sample interval. But in certain debugging scenarios we may be interested in debugging corruptions involving some specific slub objects like dentry or ext4_* etc. In such cases limiting kfence for allocations involving only specific slub objects will increase the probablity of catching the issue since kfence pool will not be consumed by other slab objects. This patch introduces a sysfs interface '/sys/kernel/slab//skip_kfence' to disable kfence for specific slabs. Having the interface work in this way does not impact current/default behavior of kfence and allows us to use kfence for specific slabs (when needed) as well. The decision to skip/use kfence is taken depending on whether kmem_cache.flags has (newly introduced) SLAB_SKIP_KFENCE flag set or not. Link: https://lkml.kernel.org/r/20220814195353.2540848-1-imran.f.khan@oracle.com Signed-off-by: Imran Khan Reviewed-by: Vlastimil Babka Reviewed-by: Marco Elver Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Roman Gushchin Signed-off-by: Andrew Morton --- include/linux/slab.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 0fefdf528e0d..352e3f082acc 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -119,6 +119,12 @@ */ #define SLAB_NO_USER_FLAGS ((slab_flags_t __force)0x10000000U) +#ifdef CONFIG_KFENCE +#define SLAB_SKIP_KFENCE ((slab_flags_t __force)0x20000000U) +#else +#define SLAB_SKIP_KFENCE 0 +#endif + /* The following flags affect the page allocator grouping pages by mobility */ /* Objects are reclaimable */ #define SLAB_RECLAIM_ACCOUNT ((slab_flags_t __force)0x00020000U) -- cgit v1.2.3 From 736a8ccce99c633b2457996bb9bf2cefff0db43d Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Fri, 29 Jul 2022 16:01:04 +0800 Subject: hugetlb_cgroup: remove unneeded return value The return value of set_hugetlb_cgroup and set_hugetlb_cgroup_rsvd are always ignored. Remove them to clean up the code. Link: https://lkml.kernel.org/r/20220729080106.12752-4-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Reviewed-by: Mike Kravetz Cc: Mina Almasry Signed-off-by: Andrew Morton --- include/linux/hugetlb_cgroup.h | 19 ++++++++----------- 1 file changed, 8 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h index 379344828e78..630cd255d0cf 100644 --- a/include/linux/hugetlb_cgroup.h +++ b/include/linux/hugetlb_cgroup.h @@ -90,32 +90,31 @@ hugetlb_cgroup_from_page_rsvd(struct page *page) return __hugetlb_cgroup_from_page(page, true); } -static inline int __set_hugetlb_cgroup(struct page *page, +static inline void __set_hugetlb_cgroup(struct page *page, struct hugetlb_cgroup *h_cg, bool rsvd) { VM_BUG_ON_PAGE(!PageHuge(page), page); if (compound_order(page) < HUGETLB_CGROUP_MIN_ORDER) - return -1; + return; if (rsvd) set_page_private(page + SUBPAGE_INDEX_CGROUP_RSVD, (unsigned long)h_cg); else set_page_private(page + SUBPAGE_INDEX_CGROUP, (unsigned long)h_cg); - return 0; } -static inline int set_hugetlb_cgroup(struct page *page, +static inline void set_hugetlb_cgroup(struct page *page, struct hugetlb_cgroup *h_cg) { - return __set_hugetlb_cgroup(page, h_cg, false); + __set_hugetlb_cgroup(page, h_cg, false); } -static inline int set_hugetlb_cgroup_rsvd(struct page *page, +static inline void set_hugetlb_cgroup_rsvd(struct page *page, struct hugetlb_cgroup *h_cg) { - return __set_hugetlb_cgroup(page, h_cg, true); + __set_hugetlb_cgroup(page, h_cg, true); } static inline bool hugetlb_cgroup_disabled(void) @@ -199,16 +198,14 @@ hugetlb_cgroup_from_page_rsvd(struct page *page) return NULL; } -static inline int set_hugetlb_cgroup(struct page *page, +static inline void set_hugetlb_cgroup(struct page *page, struct hugetlb_cgroup *h_cg) { - return 0; } -static inline int set_hugetlb_cgroup_rsvd(struct page *page, +static inline void set_hugetlb_cgroup_rsvd(struct page *page, struct hugetlb_cgroup *h_cg) { - return 0; } static inline bool hugetlb_cgroup_disabled(void) -- cgit v1.2.3 From 4d86d4f7227c6f2acfbbbe0623d49865aa71b756 Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Tue, 26 Jul 2022 16:02:41 -0700 Subject: mm: add more BUILD_BUG_ONs to gfp_migratetype() gfp_migratetype() also expects GFP_RECLAIMABLE and GFP_MOVABLE|GFP_RECLAIMABLE to be shiftable into MIGRATE_* enum values, so add some more BUILD_BUG_ONs to reflect this assumption. Link: https://linux-review.googlesource.com/id/Iae64e2182f75c3aca776a486b71a72571d66d83e Link: https://lkml.kernel.org/r/20220726230241.3770532-1-pcc@google.com Signed-off-by: Peter Collingbourne Signed-off-by: Andrew Morton --- include/linux/gfp.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index f314be58fa77..ea6cb9399152 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -18,6 +18,9 @@ static inline int gfp_migratetype(const gfp_t gfp_flags) VM_WARN_ON((gfp_flags & GFP_MOVABLE_MASK) == GFP_MOVABLE_MASK); BUILD_BUG_ON((1UL << GFP_MOVABLE_SHIFT) != ___GFP_MOVABLE); BUILD_BUG_ON((___GFP_MOVABLE >> GFP_MOVABLE_SHIFT) != MIGRATE_MOVABLE); + BUILD_BUG_ON((___GFP_RECLAIMABLE >> GFP_MOVABLE_SHIFT) != MIGRATE_RECLAIMABLE); + BUILD_BUG_ON(((___GFP_MOVABLE | ___GFP_RECLAIMABLE) >> + GFP_MOVABLE_SHIFT) != MIGRATE_HIGHATOMIC); if (unlikely(page_group_by_mobility_disabled)) return MIGRATE_UNMOVABLE; -- cgit v1.2.3 From 33024536bafd9129f1d16ade0974671c648700ac Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Wed, 13 Jul 2022 16:39:51 +0800 Subject: memory tiering: hot page selection with hint page fault latency Patch series "memory tiering: hot page selection", v4. To optimize page placement in a memory tiering system with NUMA balancing, the hot pages in the slow memory nodes need to be identified. Essentially, the original NUMA balancing implementation selects the mostly recently accessed (MRU) pages to promote. But this isn't a perfect algorithm to identify the hot pages. Because the pages with quite low access frequency may be accessed eventually given the NUMA balancing page table scanning period could be quite long (e.g. 60 seconds). So in this patchset, we implement a new hot page identification algorithm based on the latency between NUMA balancing page table scanning and hint page fault. Which is a kind of mostly frequently accessed (MFU) algorithm. In NUMA balancing memory tiering mode, if there are hot pages in slow memory node and cold pages in fast memory node, we need to promote/demote hot/cold pages between the fast and cold memory nodes. A choice is to promote/demote as fast as possible. But the CPU cycles and memory bandwidth consumed by the high promoting/demoting throughput will hurt the latency of some workload because of accessing inflating and slow memory bandwidth contention. A way to resolve this issue is to restrict the max promoting/demoting throughput. It will take longer to finish the promoting/demoting. But the workload latency will be better. This is implemented in this patchset as the page promotion rate limit mechanism. The promotion hot threshold is workload and system configuration dependent. So in this patchset, a method to adjust the hot threshold automatically is implemented. The basic idea is to control the number of the candidate promotion pages to match the promotion rate limit. We used the pmbench memory accessing benchmark tested the patchset on a 2-socket server system with DRAM and PMEM installed. The test results are as follows, pmbench score promote rate (accesses/s) MB/s ------------- ------------ base 146887704.1 725.6 hot selection 165695601.2 544.0 rate limit 162814569.8 165.2 auto adjustment 170495294.0 136.9 From the results above, With hot page selection patch [1/3], the pmbench score increases about 12.8%, and promote rate (overhead) decreases about 25.0%, compared with base kernel. With rate limit patch [2/3], pmbench score decreases about 1.7%, and promote rate decreases about 69.6%, compared with hot page selection patch. With threshold auto adjustment patch [3/3], pmbench score increases about 4.7%, and promote rate decrease about 17.1%, compared with rate limit patch. Baolin helped to test the patchset with MySQL on a machine which contains 1 DRAM node (30G) and 1 PMEM node (126G). sysbench /usr/share/sysbench/oltp_read_write.lua \ ...... --tables=200 \ --table-size=1000000 \ --report-interval=10 \ --threads=16 \ --time=120 The tps can be improved about 5%. This patch (of 3): To optimize page placement in a memory tiering system with NUMA balancing, the hot pages in the slow memory node need to be identified. Essentially, the original NUMA balancing implementation selects the mostly recently accessed (MRU) pages to promote. But this isn't a perfect algorithm to identify the hot pages. Because the pages with quite low access frequency may be accessed eventually given the NUMA balancing page table scanning period could be quite long (e.g. 60 seconds). The most frequently accessed (MFU) algorithm is better. So, in this patch we implemented a better hot page selection algorithm. Which is based on NUMA balancing page table scanning and hint page fault as follows, - When the page tables of the processes are scanned to change PTE/PMD to be PROT_NONE, the current time is recorded in struct page as scan time. - When the page is accessed, hint page fault will occur. The scan time is gotten from the struct page. And The hint page fault latency is defined as hint page fault time - scan time The shorter the hint page fault latency of a page is, the higher the probability of their access frequency to be higher. So the hint page fault latency is a better estimation of the page hot/cold. It's hard to find some extra space in struct page to hold the scan time. Fortunately, we can reuse some bits used by the original NUMA balancing. NUMA balancing uses some bits in struct page to store the page accessing CPU and PID (referring to page_cpupid_xchg_last()). Which is used by the multi-stage node selection algorithm to avoid to migrate pages shared accessed by the NUMA nodes back and forth. But for pages in the slow memory node, even if they are shared accessed by multiple NUMA nodes, as long as the pages are hot, they need to be promoted to the fast memory node. So the accessing CPU and PID information are unnecessary for the slow memory pages. We can reuse these bits in struct page to record the scan time. For the fast memory pages, these bits are used as before. For the hot threshold, the default value is 1 second, which works well in our performance test. All pages with hint page fault latency < hot threshold will be considered hot. It's hard for users to determine the hot threshold. So we don't provide a kernel ABI to set it, just provide a debugfs interface for advanced users to experiment. We will continue to work on a hot threshold automatic adjustment mechanism. The downside of the above method is that the response time to the workload hot spot changing may be much longer. For example, - A previous cold memory area becomes hot - The hint page fault will be triggered. But the hint page fault latency isn't shorter than the hot threshold. So the pages will not be promoted. - When the memory area is scanned again, maybe after a scan period, the hint page fault latency measured will be shorter than the hot threshold and the pages will be promoted. To mitigate this, if there are enough free space in the fast memory node, the hot threshold will not be used, all pages will be promoted upon the hint page fault for fast response. Thanks Zhong Jiang reported and tested the fix for a bug when disabling memory tiering mode dynamically. Link: https://lkml.kernel.org/r/20220713083954.34196-1-ying.huang@intel.com Link: https://lkml.kernel.org/r/20220713083954.34196-2-ying.huang@intel.com Signed-off-by: "Huang, Ying" Reviewed-by: Baolin Wang Tested-by: Baolin Wang Cc: Johannes Weiner Cc: Michal Hocko Cc: Rik van Riel Cc: Mel Gorman Cc: Peter Zijlstra Cc: Dave Hansen Cc: Yang Shi Cc: Zi Yan Cc: Wei Xu Cc: osalvador Cc: Shakeel Butt Cc: Zhong Jiang Cc: Oscar Salvador Signed-off-by: Andrew Morton --- include/linux/mm.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 21f8b27bd9fd..27839b158ca4 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1255,6 +1255,18 @@ static inline int folio_nid(const struct folio *folio) } #ifdef CONFIG_NUMA_BALANCING +/* page access time bits needs to hold at least 4 seconds */ +#define PAGE_ACCESS_TIME_MIN_BITS 12 +#if LAST_CPUPID_SHIFT < PAGE_ACCESS_TIME_MIN_BITS +#define PAGE_ACCESS_TIME_BUCKETS \ + (PAGE_ACCESS_TIME_MIN_BITS - LAST_CPUPID_SHIFT) +#else +#define PAGE_ACCESS_TIME_BUCKETS 0 +#endif + +#define PAGE_ACCESS_TIME_MASK \ + (LAST_CPUPID_MASK << PAGE_ACCESS_TIME_BUCKETS) + static inline int cpu_pid_to_cpupid(int cpu, int pid) { return ((cpu & LAST__CPU_MASK) << LAST__PID_SHIFT) | (pid & LAST__PID_MASK); @@ -1318,12 +1330,25 @@ static inline void page_cpupid_reset_last(struct page *page) page->flags |= LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT; } #endif /* LAST_CPUPID_NOT_IN_PAGE_FLAGS */ + +static inline int xchg_page_access_time(struct page *page, int time) +{ + int last_time; + + last_time = page_cpupid_xchg_last(page, time >> PAGE_ACCESS_TIME_BUCKETS); + return last_time << PAGE_ACCESS_TIME_BUCKETS; +} #else /* !CONFIG_NUMA_BALANCING */ static inline int page_cpupid_xchg_last(struct page *page, int cpupid) { return page_to_nid(page); /* XXX */ } +static inline int xchg_page_access_time(struct page *page, int time) +{ + return 0; +} + static inline int page_cpupid_last(struct page *page) { return page_to_nid(page); /* XXX */ -- cgit v1.2.3 From c6833e10008f976a173dd5abdf992e492cbc3bcf Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Wed, 13 Jul 2022 16:39:52 +0800 Subject: memory tiering: rate limit NUMA migration throughput In NUMA balancing memory tiering mode, if there are hot pages in slow memory node and cold pages in fast memory node, we need to promote/demote hot/cold pages between the fast and cold memory nodes. A choice is to promote/demote as fast as possible. But the CPU cycles and memory bandwidth consumed by the high promoting/demoting throughput will hurt the latency of some workload because of accessing inflating and slow memory bandwidth contention. A way to resolve this issue is to restrict the max promoting/demoting throughput. It will take longer to finish the promoting/demoting. But the workload latency will be better. This is implemented in this patch as the page promotion rate limit mechanism. The number of the candidate pages to be promoted to the fast memory node via NUMA balancing is counted, if the count exceeds the limit specified by the users, the NUMA balancing promotion will be stopped until the next second. A new sysctl knob kernel.numa_balancing_promote_rate_limit_MBps is added for the users to specify the limit. Link: https://lkml.kernel.org/r/20220713083954.34196-3-ying.huang@intel.com Signed-off-by: "Huang, Ying" Reviewed-by: Baolin Wang Tested-by: Baolin Wang Cc: Dave Hansen Cc: Johannes Weiner Cc: Mel Gorman Cc: Michal Hocko Cc: osalvador Cc: Peter Zijlstra Cc: Rik van Riel Cc: Shakeel Butt Cc: Wei Xu Cc: Yang Shi Cc: Zhong Jiang Cc: Zi Yan Signed-off-by: Andrew Morton --- include/linux/mmzone.h | 7 +++++++ include/linux/sched/sysctl.h | 1 + 2 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 8f571dc7c524..a0003eaa751f 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -221,6 +221,7 @@ enum node_stat_item { #endif #ifdef CONFIG_NUMA_BALANCING PGPROMOTE_SUCCESS, /* promote successfully */ + PGPROMOTE_CANDIDATE, /* candidate pages to promote */ #endif NR_VM_NODE_STAT_ITEMS }; @@ -998,6 +999,12 @@ typedef struct pglist_data { struct deferred_split deferred_split_queue; #endif +#ifdef CONFIG_NUMA_BALANCING + /* start time in ms of current promote rate limit period */ + unsigned int nbp_rl_start; + /* number of promote candidate pages at start time of current rate limit period */ + unsigned long nbp_rl_nr_cand; +#endif /* Fields commonly accessed by the page reclaim scanner */ /* diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index e650946816d0..303ee7dd0c7e 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -27,6 +27,7 @@ enum sched_tunable_scaling { #ifdef CONFIG_NUMA_BALANCING extern int sysctl_numa_balancing_mode; +extern unsigned int sysctl_numa_balancing_promote_rate_limit; #else #define sysctl_numa_balancing_mode 0 #endif -- cgit v1.2.3 From c959924b0dc53bf6252793f41480bc01b9792570 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Wed, 13 Jul 2022 16:39:53 +0800 Subject: memory tiering: adjust hot threshold automatically The promotion hot threshold is workload and system configuration dependent. So in this patch, a method to adjust the hot threshold automatically is implemented. The basic idea is to control the number of the candidate promotion pages to match the promotion rate limit. If the hint page fault latency of a page is less than the hot threshold, we will try to promote the page, and the page is called the candidate promotion page. If the number of the candidate promotion pages in the statistics interval is much more than the promotion rate limit, the hot threshold will be decreased to reduce the number of the candidate promotion pages. Otherwise, the hot threshold will be increased to increase the number of the candidate promotion pages. To make the above method works, in each statistics interval, the total number of the pages to check (on which the hint page faults occur) and the hot/cold distribution need to be stable. Because the page tables are scanned linearly in NUMA balancing, but the hot/cold distribution isn't uniform along the address usually, the statistics interval should be larger than the NUMA balancing scan period. So in the patch, the max scan period is used as statistics interval and it works well in our tests. Link: https://lkml.kernel.org/r/20220713083954.34196-4-ying.huang@intel.com Signed-off-by: "Huang, Ying" Reviewed-by: Baolin Wang Tested-by: Baolin Wang Cc: Dave Hansen Cc: Johannes Weiner Cc: Mel Gorman Cc: Michal Hocko Cc: osalvador Cc: Peter Zijlstra Cc: Rik van Riel Cc: Shakeel Butt Cc: Wei Xu Cc: Yang Shi Cc: Zhong Jiang Cc: Zi Yan Signed-off-by: Andrew Morton --- include/linux/mmzone.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index a0003eaa751f..025754b0bc09 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1004,6 +1004,15 @@ typedef struct pglist_data { unsigned int nbp_rl_start; /* number of promote candidate pages at start time of current rate limit period */ unsigned long nbp_rl_nr_cand; + /* promote threshold in ms */ + unsigned int nbp_threshold; + /* start time in ms of current promote threshold adjustment period */ + unsigned int nbp_th_start; + /* + * number of promote candidate pages at stat time of current promote + * threshold adjustment period + */ + unsigned long nbp_th_nr_cand; #endif /* Fields commonly accessed by the page reclaim scanner */ -- cgit v1.2.3 From 0192445cb2f7ed1cd7a95a0fc8c7645480baba25 Mon Sep 17 00:00:00 2001 From: Zi Yan Date: Mon, 15 Aug 2022 10:39:59 -0400 Subject: arch: mm: rename FORCE_MAX_ZONEORDER to ARCH_FORCE_MAX_ORDER This Kconfig option is used by individual arch to set its desired MAX_ORDER. Rename it to reflect its actual use. Link: https://lkml.kernel.org/r/20220815143959.1511278-1-zi.yan@sent.com Acked-by: Mike Rapoport Signed-off-by: Zi Yan Acked-by: Guo Ren [csky] Acked-by: Arnd Bergmann Acked-by: Catalin Marinas [arm64] Acked-by: Huacai Chen [LoongArch] Acked-by: Michael Ellerman [powerpc] Cc: Vineet Gupta Cc: Taichi Sugaya Cc: Neil Armstrong Cc: Qin Jian Cc: Guo Ren Cc: Geert Uytterhoeven Cc: Thomas Bogendoerfer Cc: Dinh Nguyen Cc: Christophe Leroy Cc: Yoshinori Sato Cc: "David S. Miller" Cc: Chris Zankel Cc: Ley Foon Tan Signed-off-by: Andrew Morton --- include/linux/mmzone.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 025754b0bc09..fd61347b4b1f 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -24,10 +24,10 @@ #include /* Free memory management - zoned buddy allocator. */ -#ifndef CONFIG_FORCE_MAX_ZONEORDER +#ifndef CONFIG_ARCH_FORCE_MAX_ORDER #define MAX_ORDER 11 #else -#define MAX_ORDER CONFIG_FORCE_MAX_ZONEORDER +#define MAX_ORDER CONFIG_ARCH_FORCE_MAX_ORDER #endif #define MAX_ORDER_NR_PAGES (1 << (MAX_ORDER - 1)) -- cgit v1.2.3 From fb70c4878d6b3001ef40fa39432a38d8cabdcbf7 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Mon, 15 Aug 2022 19:10:17 +0800 Subject: mm: kill find_min_pfn_with_active_regions() find_min_pfn_with_active_regions() is only called from free_area_init(). Open-code the PHYS_PFN(memblock_start_of_DRAM()) into free_area_init(), and kill find_min_pfn_with_active_regions(). Link: https://lkml.kernel.org/r/20220815111017.39341-1-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Signed-off-by: Andrew Morton --- include/linux/mm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 27839b158ca4..e98ef2cb1176 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2520,7 +2520,6 @@ extern unsigned long absent_pages_in_range(unsigned long start_pfn, unsigned long end_pfn); extern void get_pfn_range_for_nid(unsigned int nid, unsigned long *start_pfn, unsigned long *end_pfn); -extern unsigned long find_min_pfn_with_active_regions(void); #ifndef CONFIG_NUMA static inline int early_pfn_to_nid(unsigned long pfn) -- cgit v1.2.3 From b1d5488a252dc9c0d9574100d0b8d807bf154603 Mon Sep 17 00:00:00 2001 From: Charan Teja Kalla Date: Thu, 18 Aug 2022 19:20:00 +0530 Subject: mm: fix use-after free of page_ext after race with memory-offline The below is one path where race between page_ext and offline of the respective memory blocks will cause use-after-free on the access of page_ext structure. process1 process2 --------- --------- a)doing /proc/page_owner doing memory offline through offline_pages. b) PageBuddy check is failed thus proceed to get the page_owner information through page_ext access. page_ext = lookup_page_ext(page); migrate_pages(); ................. Since all pages are successfully migrated as part of the offline operation,send MEM_OFFLINE notification where for page_ext it calls: offline_page_ext()--> __free_page_ext()--> free_page_ext()--> vfree(ms->page_ext) mem_section->page_ext = NULL c) Check for the PAGE_EXT flags in the page_ext->flags access results into the use-after-free (leading to the translation faults). As mentioned above, there is really no synchronization between page_ext access and its freeing in the memory_offline. The memory offline steps(roughly) on a memory block is as below: 1) Isolate all the pages 2) while(1) try free the pages to buddy.(->free_list[MIGRATE_ISOLATE]) 3) delete the pages from this buddy list. 4) Then free page_ext.(Note: The struct page is still alive as it is freed only during hot remove of the memory which frees the memmap, which steps the user might not perform). This design leads to the state where struct page is alive but the struct page_ext is freed, where the later is ideally part of the former which just representing the page_flags (check [3] for why this design is chosen). The abovementioned race is just one example __but the problem persists in the other paths too involving page_ext->flags access(eg: page_is_idle())__. Fix all the paths where offline races with page_ext access by maintaining synchronization with rcu lock and is achieved in 3 steps: 1) Invalidate all the page_ext's of the sections of a memory block by storing a flag in the LSB of mem_section->page_ext. 2) Wait until all the existing readers to finish working with the ->page_ext's with synchronize_rcu(). Any parallel process that starts after this call will not get page_ext, through lookup_page_ext(), for the block parallel offline operation is being performed. 3) Now safely free all sections ->page_ext's of the block on which offline operation is being performed. Note: If synchronize_rcu() takes time then optimizations can be done in this path through call_rcu()[2]. Thanks to David Hildenbrand for his views/suggestions on the initial discussion[1] and Pavan kondeti for various inputs on this patch. [1] https://lore.kernel.org/linux-mm/59edde13-4167-8550-86f0-11fc67882107@quicinc.com/ [2] https://lore.kernel.org/all/a26ce299-aed1-b8ad-711e-a49e82bdd180@quicinc.com/T/#u [3] https://lore.kernel.org/all/6fa6b7aa-731e-891c-3efb-a03d6a700efa@redhat.com/ [quic_charante@quicinc.com: rename label `loop' to `ext_put_continue' per David] Link: https://lkml.kernel.org/r/1661496993-11473-1-git-send-email-quic_charante@quicinc.com Link: https://lkml.kernel.org/r/1660830600-9068-1-git-send-email-quic_charante@quicinc.com Signed-off-by: Charan Teja Kalla Suggested-by: David Hildenbrand Suggested-by: Michal Hocko Acked-by: Michal Hocko Acked-by: David Hildenbrand Cc: Fernand Sieber Cc: Minchan Kim Cc: Pasha Tatashin Cc: Pavan Kondeti Cc: SeongJae Park Cc: Shakeel Butt Cc: Vlastimil Babka Cc: William Kucharski Signed-off-by: Andrew Morton --- include/linux/page_ext.h | 17 +++++++++++------ include/linux/page_idle.h | 34 ++++++++++++++++++++++++---------- 2 files changed, 35 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h index fabb2e1e087f..ed27198cdaf4 100644 --- a/include/linux/page_ext.h +++ b/include/linux/page_ext.h @@ -55,7 +55,8 @@ static inline void page_ext_init(void) } #endif -struct page_ext *lookup_page_ext(const struct page *page); +extern struct page_ext *page_ext_get(struct page *page); +extern void page_ext_put(struct page_ext *page_ext); static inline struct page_ext *page_ext_next(struct page_ext *curr) { @@ -71,11 +72,6 @@ static inline void pgdat_page_ext_init(struct pglist_data *pgdat) { } -static inline struct page_ext *lookup_page_ext(const struct page *page) -{ - return NULL; -} - static inline void page_ext_init(void) { } @@ -87,5 +83,14 @@ static inline void page_ext_init_flatmem_late(void) static inline void page_ext_init_flatmem(void) { } + +static inline struct page_ext *page_ext_get(struct page *page) +{ + return NULL; +} + +static inline void page_ext_put(struct page_ext *page_ext) +{ +} #endif /* CONFIG_PAGE_EXTENSION */ #endif /* __LINUX_PAGE_EXT_H */ diff --git a/include/linux/page_idle.h b/include/linux/page_idle.h index 4663dfed1293..5cb7bd2078ec 100644 --- a/include/linux/page_idle.h +++ b/include/linux/page_idle.h @@ -13,65 +13,79 @@ * If there is not enough space to store Idle and Young bits in page flags, use * page ext flags instead. */ - static inline bool folio_test_young(struct folio *folio) { - struct page_ext *page_ext = lookup_page_ext(&folio->page); + struct page_ext *page_ext = page_ext_get(&folio->page); + bool page_young; if (unlikely(!page_ext)) return false; - return test_bit(PAGE_EXT_YOUNG, &page_ext->flags); + page_young = test_bit(PAGE_EXT_YOUNG, &page_ext->flags); + page_ext_put(page_ext); + + return page_young; } static inline void folio_set_young(struct folio *folio) { - struct page_ext *page_ext = lookup_page_ext(&folio->page); + struct page_ext *page_ext = page_ext_get(&folio->page); if (unlikely(!page_ext)) return; set_bit(PAGE_EXT_YOUNG, &page_ext->flags); + page_ext_put(page_ext); } static inline bool folio_test_clear_young(struct folio *folio) { - struct page_ext *page_ext = lookup_page_ext(&folio->page); + struct page_ext *page_ext = page_ext_get(&folio->page); + bool page_young; if (unlikely(!page_ext)) return false; - return test_and_clear_bit(PAGE_EXT_YOUNG, &page_ext->flags); + page_young = test_and_clear_bit(PAGE_EXT_YOUNG, &page_ext->flags); + page_ext_put(page_ext); + + return page_young; } static inline bool folio_test_idle(struct folio *folio) { - struct page_ext *page_ext = lookup_page_ext(&folio->page); + struct page_ext *page_ext = page_ext_get(&folio->page); + bool page_idle; if (unlikely(!page_ext)) return false; - return test_bit(PAGE_EXT_IDLE, &page_ext->flags); + page_idle = test_bit(PAGE_EXT_IDLE, &page_ext->flags); + page_ext_put(page_ext); + + return page_idle; } static inline void folio_set_idle(struct folio *folio) { - struct page_ext *page_ext = lookup_page_ext(&folio->page); + struct page_ext *page_ext = page_ext_get(&folio->page); if (unlikely(!page_ext)) return; set_bit(PAGE_EXT_IDLE, &page_ext->flags); + page_ext_put(page_ext); } static inline void folio_clear_idle(struct folio *folio) { - struct page_ext *page_ext = lookup_page_ext(&folio->page); + struct page_ext *page_ext = page_ext_get(&folio->page); if (unlikely(!page_ext)) return; clear_bit(PAGE_EXT_IDLE, &page_ext->flags); + page_ext_put(page_ext); } #endif /* !CONFIG_64BIT */ -- cgit v1.2.3 From e2f8f44b7686bf65747f485ac7c9c43de8b8de09 Mon Sep 17 00:00:00 2001 From: Rolf Eike Beer Date: Mon, 22 Aug 2022 15:01:32 +0200 Subject: mm: pagewalk: fix documentation of PTE hole handling Empty PTEs are passed to the pte_entry callback, not to pte_hole. Link: https://lkml.kernel.org/r/3695521.kQq0lBPeGt@devpool047 Signed-off-by: Rolf Eike Beer Signed-off-by: Andrew Morton --- include/linux/pagewalk.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagewalk.h b/include/linux/pagewalk.h index ac7b38ad5903..f3fafb731ffd 100644 --- a/include/linux/pagewalk.h +++ b/include/linux/pagewalk.h @@ -15,12 +15,12 @@ struct mm_walk; * this handler is required to be able to handle * pmd_trans_huge() pmds. They may simply choose to * split_huge_page() instead of handling it explicitly. - * @pte_entry: if set, called for each non-empty PTE (lowest-level) - * entry + * @pte_entry: if set, called for each PTE (lowest-level) entry, + * including empty ones * @pte_hole: if set, called for each hole at all levels, - * depth is -1 if not known, 0:PGD, 1:P4D, 2:PUD, 3:PMD - * 4:PTE. Any folded depths (where PTRS_PER_P?D is equal - * to 1) are skipped. + * depth is -1 if not known, 0:PGD, 1:P4D, 2:PUD, 3:PMD. + * Any folded depths (where PTRS_PER_P?D is equal to 1) + * are skipped. * @hugetlb_entry: if set, called for each hugetlb entry * @test_walk: caller specific callback function to determine whether * we walk over the current vma or not. Returning 0 means -- cgit v1.2.3 From 408587baee39753304dd572dacf374f75545d25a Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Thu, 25 Aug 2022 00:05:05 +0000 Subject: mm: page_counter: rearrange struct page_counter fields MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit With memcg v2 enabled, memcg->memory.usage is a very hot member for the workloads doing memcg charging on multiple CPUs concurrently. Particularly the network intensive workloads. In addition, there is a false cache sharing between memory.usage and memory.high on the charge path. This patch moves the usage into a separate cacheline and move all the read most fields into separate cacheline. To evaluate the impact of this optimization, on a 72 CPUs machine, we ran the following workload in a three level of cgroup hierarchy. $ netserver -6 # 36 instances of netperf with following params $ netperf -6 -H ::1 -l 60 -t TCP_SENDFILE -- -m 10K Results (average throughput of netperf): Without (6.0-rc1) 10482.7 Mbps With patch 12413.7 Mbps (18.4% improvement) With the patch, the throughput improved by 18.4%. One side-effect of this patch is the increase in the size of struct mem_cgroup. For example with this patch on 64 bit build, the size of struct mem_cgroup increased from 4032 bytes to 4416 bytes. However for the performance improvement, this additional size is worth it. In addition there are opportunities to reduce the size of struct mem_cgroup like deprecation of kmem and tcpmem page counters and better packing. Link: https://lkml.kernel.org/r/20220825000506.239406-3-shakeelb@google.com Signed-off-by: Shakeel Butt Reported-by: kernel test robot Reviewed-by: Feng Tang Acked-by: Soheil Hassas Yeganeh Acked-by: Roman Gushchin Acked-by: Michal Hocko Cc: Eric Dumazet Cc: Johannes Weiner Cc: "Michal Koutný" Cc: Muchun Song Signed-off-by: Andrew Morton --- include/linux/page_counter.h | 35 +++++++++++++++++++++++------------ 1 file changed, 23 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h index 679591301994..78a1c934e416 100644 --- a/include/linux/page_counter.h +++ b/include/linux/page_counter.h @@ -3,15 +3,26 @@ #define _LINUX_PAGE_COUNTER_H #include +#include #include #include +#if defined(CONFIG_SMP) +struct pc_padding { + char x[0]; +} ____cacheline_internodealigned_in_smp; +#define PC_PADDING(name) struct pc_padding name +#else +#define PC_PADDING(name) +#endif + struct page_counter { + /* + * Make sure 'usage' does not share cacheline with any other field. The + * memcg->memory.usage is a hot member of struct mem_cgroup. + */ atomic_long_t usage; - unsigned long min; - unsigned long low; - unsigned long high; - unsigned long max; + PC_PADDING(_pad1_); /* effective memory.min and memory.min usage tracking */ unsigned long emin; @@ -23,18 +34,18 @@ struct page_counter { atomic_long_t low_usage; atomic_long_t children_low_usage; - /* legacy */ unsigned long watermark; unsigned long failcnt; - /* - * 'parent' is placed here to be far from 'usage' to reduce - * cache false sharing, as 'usage' is written mostly while - * parent is frequently read for cgroup's hierarchical - * counting nature. - */ + /* Keep all the read most fields in a separete cacheline. */ + PC_PADDING(_pad2_); + + unsigned long min; + unsigned long low; + unsigned long high; + unsigned long max; struct page_counter *parent; -}; +} ____cacheline_internodealigned_in_smp; #if BITS_PER_LONG == 32 #define PAGE_COUNTER_MAX LONG_MAX -- cgit v1.2.3 From 1813e51eece0ad6f4aacaeb738e7cced46feb470 Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Thu, 25 Aug 2022 00:05:06 +0000 Subject: memcg: increase MEMCG_CHARGE_BATCH to 64 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit For several years, MEMCG_CHARGE_BATCH was kept at 32 but with bigger machines and the network intensive workloads requiring througput in Gbps, 32 is too small and makes the memcg charging path a bottleneck. For now, increase it to 64 for easy acceptance to 6.0. We will need to revisit this in future for ever increasing demand of higher performance. Please note that the memcg charge path drain the per-cpu memcg charge stock, so there should not be any oom behavior change. Though it does have impact on rstat flushing and high limit reclaim backoff. To evaluate the impact of this optimization, on a 72 CPUs machine, we ran the following workload in a three level of cgroup hierarchy. $ netserver -6 # 36 instances of netperf with following params $ netperf -6 -H ::1 -l 60 -t TCP_SENDFILE -- -m 10K Results (average throughput of netperf): Without (6.0-rc1) 10482.7 Mbps With patch 17064.7 Mbps (62.7% improvement) With the patch, the throughput improved by 62.7%. Link: https://lkml.kernel.org/r/20220825000506.239406-4-shakeelb@google.com Signed-off-by: Shakeel Butt Reported-by: kernel test robot Acked-by: Soheil Hassas Yeganeh Reviewed-by: Feng Tang Acked-by: Roman Gushchin Acked-by: Muchun Song Acked-by: Michal Hocko Cc: Eric Dumazet Cc: Johannes Weiner Cc: "Michal Koutný" Signed-off-by: Andrew Morton --- include/linux/memcontrol.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 6257867fbf95..a2461f9a8738 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -354,10 +354,11 @@ struct mem_cgroup { }; /* - * size of first charge trial. "32" comes from vmscan.c's magic value. - * TODO: maybe necessary to use big numbers in big irons. + * size of first charge trial. + * TODO: maybe necessary to use big numbers in big irons or dynamic based of the + * workload. */ -#define MEMCG_CHARGE_BATCH 32U +#define MEMCG_CHARGE_BATCH 64U extern struct mem_cgroup *root_mem_cgroup; -- cgit v1.2.3 From c4f20f1479c456d9dd1c1e6d8bf956a25de742dc Mon Sep 17 00:00:00 2001 From: Li Zhe Date: Thu, 25 Aug 2022 18:27:14 +0800 Subject: page_ext: introduce boot parameter 'early_page_ext' In commit 2f1ee0913ce5 ("Revert "mm: use early_pfn_to_nid in page_ext_init""), we call page_ext_init() after page_alloc_init_late() to avoid some panic problem. It seems that we cannot track early page allocations in current kernel even if page structure has been initialized early. This patch introduces a new boot parameter 'early_page_ext' to resolve this problem. If we pass it to the kernel, page_ext_init() will be moved up and the feature 'deferred initialization of struct pages' will be disabled to initialize the page allocator early and prevent the panic problem above. It can help us to catch early page allocations. This is useful especially when we find that the free memory value is not the same right after different kernel booting. [akpm@linux-foundation.org: fix section issue by removing __meminitdata] Link: https://lkml.kernel.org/r/20220825102714.669-1-lizhe.67@bytedance.com Signed-off-by: Li Zhe Suggested-by: Michal Hocko Acked-by: Michal Hocko Acked-by: Vlastimil Babka Cc: Jason A. Donenfeld Cc: Jonathan Corbet Cc: Kees Cook Cc: Mark-PK Tsai Cc: Masami Hiramatsu (Google) Cc: Steven Rostedt Signed-off-by: Andrew Morton --- include/linux/page_ext.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h index ed27198cdaf4..22be4582faae 100644 --- a/include/linux/page_ext.h +++ b/include/linux/page_ext.h @@ -36,9 +36,15 @@ struct page_ext { unsigned long flags; }; +extern bool early_page_ext; extern unsigned long page_ext_size; extern void pgdat_page_ext_init(struct pglist_data *pgdat); +static inline bool early_page_ext_enabled(void) +{ + return early_page_ext; +} + #ifdef CONFIG_SPARSEMEM static inline void page_ext_init_flatmem(void) { @@ -68,6 +74,11 @@ static inline struct page_ext *page_ext_next(struct page_ext *curr) #else /* !CONFIG_PAGE_EXTENSION */ struct page_ext; +static inline bool early_page_ext_enabled(void) +{ + return false; +} + static inline void pgdat_page_ext_init(struct pglist_data *pgdat) { } -- cgit v1.2.3 From 35b471467f88b8d8b52ba5b006a29b9d057d09bf Mon Sep 17 00:00:00 2001 From: "Vishal Moola (Oracle)" Date: Tue, 23 Aug 2022 17:40:17 -0700 Subject: filemap: add filemap_get_folios_contig() Patch series "Convert to filemap_get_folios_contig()", v3. This patch series replaces find_get_pages_contig() with filemap_get_folios_contig(). This patch (of 7): This function is meant to replace find_get_pages_contig(). Unlike find_get_pages_contig(), filemap_get_folios_contig() no longer takes in a target number of pages to find - It returns up to 15 contiguous folios. To be more consistent with filemap_get_folios(), filemap_get_folios_contig() now also updates the start index passed in, and takes an end index. Link: https://lkml.kernel.org/r/20220824004023.77310-1-vishal.moola@gmail.com Link: https://lkml.kernel.org/r/20220824004023.77310-2-vishal.moola@gmail.com Signed-off-by: Vishal Moola (Oracle) Cc: Chris Mason Cc: Josef Bacik Cc: David Sterba Cc: Ryusuke Konishi Cc: Al Viro Cc: Matthew Wilcox Cc: David Sterba Signed-off-by: Andrew Morton --- include/linux/pagemap.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 0178b2040ea3..8689c32d628b 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -718,6 +718,8 @@ static inline struct page *find_subpage(struct page *head, pgoff_t index) unsigned filemap_get_folios(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch); +unsigned filemap_get_folios_contig(struct address_space *mapping, + pgoff_t *start, pgoff_t end, struct folio_batch *fbatch); unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start, unsigned int nr_pages, struct page **pages); unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index, -- cgit v1.2.3 From 48658d8509d2db3391c95aa74308a2b1fc8e8461 Mon Sep 17 00:00:00 2001 From: "Vishal Moola (Oracle)" Date: Tue, 23 Aug 2022 17:40:23 -0700 Subject: filemap: remove find_get_pages_contig() All callers of find_get_pages_contig() have been removed, so it is no longer needed. Link: https://lkml.kernel.org/r/20220824004023.77310-8-vishal.moola@gmail.com Signed-off-by: Vishal Moola (Oracle) Cc: Al Viro Cc: Chris Mason Cc: David Sterba Cc: David Sterba Cc: Josef Bacik Cc: Matthew Wilcox Cc: Ryusuke Konishi Signed-off-by: Andrew Morton --- include/linux/pagemap.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 8689c32d628b..09de43e36a64 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -720,8 +720,6 @@ unsigned filemap_get_folios(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch); unsigned filemap_get_folios_contig(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch); -unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start, - unsigned int nr_pages, struct page **pages); unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index, pgoff_t end, xa_mark_t tag, unsigned int nr_pages, struct page **pages); -- cgit v1.2.3 From 639118d1571f70b1157b4bb5ac574b0ab0f38099 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Sat, 27 Aug 2022 19:20:43 +0800 Subject: mm: kill is_memblock_offlined() Directly check state of struct memory_block, no need a single function. Link: https://lkml.kernel.org/r/20220827112043.187028-1-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Reviewed-by: David Hildenbrand Reviewed-by: Oscar Salvador Reviewed-by: Anshuman Khandual Signed-off-by: Andrew Morton --- include/linux/memory_hotplug.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index e0b2209ab71c..54675791bc50 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -11,7 +11,6 @@ struct page; struct zone; struct pglist_data; struct mem_section; -struct memory_block; struct memory_group; struct resource; struct vmem_altmap; @@ -333,7 +332,6 @@ extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn, extern void remove_pfn_range_from_zone(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages); -extern bool is_memblock_offlined(struct memory_block *mem); extern int sparse_add_section(int nid, unsigned long pfn, unsigned long nr_pages, struct vmem_altmap *altmap, struct dev_pagemap *pgmap); -- cgit v1.2.3 From b4a0215e11dcfe23a48c65c6d6c82c0c2c551a48 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Sat, 27 Aug 2022 19:19:59 +0800 Subject: mm: fix null-ptr-deref in kswapd_is_running() kswapd_run/stop() will set pgdat->kswapd to NULL, which could race with kswapd_is_running() in kcompactd(), kswapd_run/stop() kcompactd() kswapd_is_running() pgdat->kswapd // error or nomal ptr verify pgdat->kswapd // load non-NULL pgdat->kswapd pgdat->kswapd = NULL task_is_running(pgdat->kswapd) // Null pointer derefence KASAN reports the null-ptr-deref shown below, vmscan: Failed to start kswapd on node 0 ... BUG: KASAN: null-ptr-deref in kcompactd+0x440/0x504 Read of size 8 at addr 0000000000000024 by task kcompactd0/37 CPU: 0 PID: 37 Comm: kcompactd0 Kdump: loaded Tainted: G OE 5.10.60 #1 Hardware name: QEMU KVM Virtual Machine, BIOS 0.0.0 02/06/2015 Call trace: dump_backtrace+0x0/0x394 show_stack+0x34/0x4c dump_stack+0x158/0x1e4 __kasan_report+0x138/0x140 kasan_report+0x44/0xdc __asan_load8+0x94/0xd0 kcompactd+0x440/0x504 kthread+0x1a4/0x1f0 ret_from_fork+0x10/0x18 At present kswapd/kcompactd_run() and kswapd/kcompactd_stop() are protected by mem_hotplug_begin/done(), but without kcompactd(). There is no need to involve memory hotplug lock in kcompactd(), so let's add a new mutex to protect pgdat->kswapd accesses. Also, because the kcompactd task will check the state of kswapd task, it's better to call kcompactd_stop() before kswapd_stop() to reduce lock conflicts. [akpm@linux-foundation.org: add comments] Link: https://lkml.kernel.org/r/20220827111959.186838-1-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Cc: David Hildenbrand Cc: Muchun Song Signed-off-by: Andrew Morton --- include/linux/memory_hotplug.h | 20 ++++++++++++++++++++ include/linux/mmzone.h | 6 ++++-- 2 files changed, 24 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 54675791bc50..51052969dbfe 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -215,6 +215,22 @@ void put_online_mems(void); void mem_hotplug_begin(void); void mem_hotplug_done(void); +/* See kswapd_is_running() */ +static inline void pgdat_kswapd_lock(pg_data_t *pgdat) +{ + mutex_lock(&pgdat->kswapd_lock); +} + +static inline void pgdat_kswapd_unlock(pg_data_t *pgdat) +{ + mutex_unlock(&pgdat->kswapd_lock); +} + +static inline void pgdat_kswapd_lock_init(pg_data_t *pgdat) +{ + mutex_init(&pgdat->kswapd_lock); +} + #else /* ! CONFIG_MEMORY_HOTPLUG */ #define pfn_to_online_page(pfn) \ ({ \ @@ -251,6 +267,10 @@ static inline bool movable_node_is_enabled(void) { return false; } + +static inline void pgdat_kswapd_lock(pg_data_t *pgdat) {} +static inline void pgdat_kswapd_unlock(pg_data_t *pgdat) {} +static inline void pgdat_kswapd_lock_init(pg_data_t *pgdat) {} #endif /* ! CONFIG_MEMORY_HOTPLUG */ /* diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index fd61347b4b1f..18cf0fc5ce67 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -956,8 +956,10 @@ typedef struct pglist_data { atomic_t nr_writeback_throttled;/* nr of writeback-throttled tasks */ unsigned long nr_reclaim_start; /* nr pages written while throttled * when throttling started. */ - struct task_struct *kswapd; /* Protected by - mem_hotplug_begin/done() */ +#ifdef CONFIG_MEMORY_HOTPLUG + struct mutex kswapd_lock; +#endif + struct task_struct *kswapd; /* Protected by kswapd_lock */ int kswapd_order; enum zone_type kswapd_highest_zoneidx; -- cgit v1.2.3 From a38c94ed59fc312b51a33d867444ce73c6805ff6 Mon Sep 17 00:00:00 2001 From: Liu Shixin Date: Mon, 29 Aug 2022 17:57:09 +0800 Subject: mm/thp: simplify has_transparent_hugepage by using IS_BUILTIN Simplify code of has_transparent_hugepage define by using IS_BUILTIN. No functional change. Link: https://lkml.kernel.org/r/20220829095709.3287462-1-liushixin2@huawei.com Signed-off-by: Liu Shixin Reviewed-by: David Hildenbrand Cc: Hugh Dickins Cc: Kefeng Wang Signed-off-by: Andrew Morton --- include/linux/pgtable.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 014ee8f0fbaa..5911761487de 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1598,11 +1598,7 @@ typedef unsigned int pgtbl_mod_mask; #endif #ifndef has_transparent_hugepage -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -#define has_transparent_hugepage() 1 -#else -#define has_transparent_hugepage() 0 -#endif +#define has_transparent_hugepage() IS_BUILTIN(CONFIG_TRANSPARENT_HUGEPAGE) #endif /* -- cgit v1.2.3 From bcd0dea5f4fb3d098b03ef3064fe6c8201d7c515 Mon Sep 17 00:00:00 2001 From: Liu Shixin Date: Mon, 29 Aug 2022 17:51:25 +0800 Subject: mm/thp: remove redundant CONFIG_TRANSPARENT_HUGEPAGE Simplify code by removing redundant CONFIG_TRANSPARENT_HUGEPAGE judgment. No functional change. Link: https://lkml.kernel.org/r/20220829095125.3284567-1-liushixin2@huawei.com Signed-off-by: Liu Shixin Cc: Kefeng Wang Cc: Matthew Wilcox Signed-off-by: Andrew Morton --- include/linux/pgtable.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 5911761487de..d13b4f7cc5be 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1276,8 +1276,7 @@ static inline int pgd_devmap(pgd_t pgd) #endif #if !defined(CONFIG_TRANSPARENT_HUGEPAGE) || \ - (defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ - !defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)) + !defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) static inline int pud_trans_huge(pud_t pud) { return 0; -- cgit v1.2.3 From 214f8796907b8015b778badf4710a4701472779a Mon Sep 17 00:00:00 2001 From: Zhang Yi Date: Thu, 1 Sep 2022 21:34:52 +0800 Subject: fs/buffer: remove __breadahead_gfp() Patch series "fs/buffer: remove ll_rw_block()", v2. ll_rw_block() will skip locked buffer before submitting IO, it assumes that locked buffer means it is under IO. This assumption is not always true because we cannot guarantee every buffer lock path would submit IO. After commit 88dbcbb3a484 ("blkdev: avoid migration stalls for blkdev pages"), buffer_migrate_folio_norefs() becomes one exceptional case, and there may be others. So ll_rw_block() is not safe on the sync read path, we could get false positive EIO return value when filesystem reading metadata. It seems that it could be only used on the readahead path. Unfortunately, many filesystem misuse the ll_rw_block() on the sync read path. This patch set just remove ll_rw_block() and add new friendly helpers, which could prevent false positive EIO on the read metadata path. Thanks for the suggestion from Jan, the original discussion is at [1]. patch 1: remove unused helpers in fs/buffer.c patch 2: add new bh_read_[*] helpers patch 3-11: remove all ll_rw_block() calls in filesystems patch 12-14: do some leftover cleanups. [1]. https://lore.kernel.org/linux-mm/20220825080146.2021641-1-chengzhihao1@huawei.com/ This patch (of 14): No one use __breadahead_gfp() and sb_breadahead_unmovable() any more, remove them. Link: https://lkml.kernel.org/r/20220901133505.2510834-1-yi.zhang@huawei.com Link: https://lkml.kernel.org/r/20220901133505.2510834-2-yi.zhang@huawei.com Signed-off-by: Zhang Yi Reviewed-by: Jan Kara Reviewed-by: Christoph Hellwig Cc: Alexander Viro Cc: Andreas Gruenbacher Cc: Bob Peterson Cc: Evgeniy Dushistov Cc: Heming Zhao Cc: Jens Axboe Cc: Konstantin Komarov Cc: Mark Fasheh Cc: Theodore Ts'o Cc: Yu Kuai Cc: Zhihao Cheng Signed-off-by: Andrew Morton --- include/linux/buffer_head.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 089c9ade4325..c3863c417b00 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -214,8 +214,6 @@ struct buffer_head *__getblk_gfp(struct block_device *bdev, sector_t block, void __brelse(struct buffer_head *); void __bforget(struct buffer_head *); void __breadahead(struct block_device *, sector_t block, unsigned int size); -void __breadahead_gfp(struct block_device *, sector_t block, unsigned int size, - gfp_t gfp); struct buffer_head *__bread_gfp(struct block_device *, sector_t block, unsigned size, gfp_t gfp); void invalidate_bh_lrus(void); @@ -340,12 +338,6 @@ sb_breadahead(struct super_block *sb, sector_t block) __breadahead(sb->s_bdev, block, sb->s_blocksize); } -static inline void -sb_breadahead_unmovable(struct super_block *sb, sector_t block) -{ - __breadahead_gfp(sb->s_bdev, block, sb->s_blocksize, 0); -} - static inline struct buffer_head * sb_getblk(struct super_block *sb, sector_t block) { -- cgit v1.2.3 From fdee117ee86479fd2644bcd9ac2b2469e55722d1 Mon Sep 17 00:00:00 2001 From: Zhang Yi Date: Thu, 1 Sep 2022 21:34:53 +0800 Subject: fs/buffer: add some new buffer read helpers Current ll_rw_block() helper is fragile because it assumes that locked buffer means it's under IO which is submitted by some other who holds the lock, it skip buffer if it failed to get the lock, so it's only safe on the readahead path. Unfortunately, now that most filesystems still use this helper mistakenly on the sync metadata read path. There is no guarantee that the one who holds the buffer lock always submit IO (e.g. buffer_migrate_folio_norefs() after commit 88dbcbb3a484 ("blkdev: avoid migration stalls for blkdev pages"), it could lead to false positive -EIO when submitting reading IO. This patch add some friendly buffer read helpers to prepare replacing ll_rw_block() and similar calls. We can only call bh_readahead_[] helpers for the readahead paths. Link: https://lkml.kernel.org/r/20220901133505.2510834-3-yi.zhang@huawei.com Signed-off-by: Zhang Yi Reviewed-by: Jan Kara Reviewed-by: Christoph Hellwig Signed-off-by: Andrew Morton --- include/linux/buffer_head.h | 38 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) (limited to 'include/linux') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index c3863c417b00..6d09785bed9f 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -232,6 +232,9 @@ void write_boundary_block(struct block_device *bdev, sector_t bblock, unsigned blocksize); int bh_uptodate_or_lock(struct buffer_head *bh); int bh_submit_read(struct buffer_head *bh); +int __bh_read(struct buffer_head *bh, blk_opf_t op_flags, bool wait); +void __bh_read_batch(int nr, struct buffer_head *bhs[], + blk_opf_t op_flags, bool force_lock); extern int buffer_heads_over_limit; @@ -399,6 +402,41 @@ static inline struct buffer_head *__getblk(struct block_device *bdev, return __getblk_gfp(bdev, block, size, __GFP_MOVABLE); } +static inline void bh_readahead(struct buffer_head *bh, blk_opf_t op_flags) +{ + if (!buffer_uptodate(bh) && trylock_buffer(bh)) { + if (!buffer_uptodate(bh)) + __bh_read(bh, op_flags, false); + else + unlock_buffer(bh); + } +} + +static inline void bh_read_nowait(struct buffer_head *bh, blk_opf_t op_flags) +{ + if (!bh_uptodate_or_lock(bh)) + __bh_read(bh, op_flags, false); +} + +/* Returns 1 if buffer uptodated, 0 on success, and -EIO on error. */ +static inline int bh_read(struct buffer_head *bh, blk_opf_t op_flags) +{ + if (bh_uptodate_or_lock(bh)) + return 1; + return __bh_read(bh, op_flags, true); +} + +static inline void bh_read_batch(int nr, struct buffer_head *bhs[]) +{ + __bh_read_batch(nr, bhs, 0, true); +} + +static inline void bh_readahead_batch(int nr, struct buffer_head *bhs[], + blk_opf_t op_flags) +{ + __bh_read_batch(nr, bhs, op_flags, false); +} + /** * __bread() - reads a specified block and returns the bh * @bdev: the block_device to read from -- cgit v1.2.3 From 79f5978420691fb84593f98557ea56f8b32228f2 Mon Sep 17 00:00:00 2001 From: Zhang Yi Date: Thu, 1 Sep 2022 21:35:03 +0800 Subject: fs/buffer: remove ll_rw_block() helper Now that all ll_rw_block() users has been replaced to new safe helpers, we just remove it here. Link: https://lkml.kernel.org/r/20220901133505.2510834-13-yi.zhang@huawei.com Signed-off-by: Zhang Yi Reviewed-by: Jan Kara Reviewed-by: Christoph Hellwig Signed-off-by: Andrew Morton --- include/linux/buffer_head.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 6d09785bed9f..b415d8bc2a09 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -223,7 +223,6 @@ struct buffer_head *alloc_buffer_head(gfp_t gfp_flags); void free_buffer_head(struct buffer_head * bh); void unlock_buffer(struct buffer_head *bh); void __lock_buffer(struct buffer_head *bh); -void ll_rw_block(blk_opf_t, int, struct buffer_head * bh[]); int sync_dirty_buffer(struct buffer_head *bh); int __sync_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags); void write_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags); -- cgit v1.2.3 From 454552d0145486cf82572e73cca266ab6a56e86b Mon Sep 17 00:00:00 2001 From: Zhang Yi Date: Thu, 1 Sep 2022 21:35:05 +0800 Subject: fs/buffer: remove bh_submit_read() helper bh_submit_read() has no user anymore, just remove it. Link: https://lkml.kernel.org/r/20220901133505.2510834-15-yi.zhang@huawei.com Signed-off-by: Zhang Yi Reviewed-by: Jan Kara Reviewed-by: Christoph Hellwig Signed-off-by: Andrew Morton --- include/linux/buffer_head.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index b415d8bc2a09..9b6556d3f110 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -230,7 +230,6 @@ int submit_bh(blk_opf_t, struct buffer_head *); void write_boundary_block(struct block_device *bdev, sector_t bblock, unsigned blocksize); int bh_uptodate_or_lock(struct buffer_head *bh); -int bh_submit_read(struct buffer_head *bh); int __bh_read(struct buffer_head *bh, blk_opf_t op_flags, bool wait); void __bh_read_batch(int nr, struct buffer_head *bhs[], blk_opf_t op_flags, bool force_lock); -- cgit v1.2.3 From 263b899802fc43cd0e6979f819271dfbb93c94af Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Thu, 1 Sep 2022 20:00:21 +0800 Subject: hugetlb: make hugetlb_cma_check() static Patch series "A few cleanup patches for hugetlb", v2. This series contains a few cleanup patches to use helper functions to simplify the codes, remove unneeded nid parameter and so on. More details can be found in the respective changelogs. This patch (of 10): Make hugetlb_cma_check() static as it's only used inside mm/hugetlb.c. Link: https://lkml.kernel.org/r/20220901120030.63318-1-linmiaohe@huawei.com Link: https://lkml.kernel.org/r/20220901120030.63318-2-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Reviewed-by: Muchun Song Cc: Mike Kravetz Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 3ec981a0d8b3..57e72954a482 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -1123,14 +1123,10 @@ static inline spinlock_t *huge_pte_lock(struct hstate *h, #if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_CMA) extern void __init hugetlb_cma_reserve(int order); -extern void __init hugetlb_cma_check(void); #else static inline __init void hugetlb_cma_reserve(int order) { } -static inline __init void hugetlb_cma_check(void) -{ -} #endif bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr); -- cgit v1.2.3 From 088b8aa537c2c767765f1c19b555f21ffe555786 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 1 Sep 2022 10:35:59 +0200 Subject: mm: fix PageAnonExclusive clearing racing with concurrent RCU GUP-fast commit 6c287605fd56 ("mm: remember exclusively mapped anonymous pages with PG_anon_exclusive") made sure that when PageAnonExclusive() has to be cleared during temporary unmapping of a page, that the PTE is cleared/invalidated and that the TLB is flushed. What we want to achieve in all cases is that we cannot end up with a pin on an anonymous page that may be shared, because such pins would be unreliable and could result in memory corruptions when the mapped page and the pin go out of sync due to a write fault. That TLB flush handling was inspired by an outdated comment in mm/ksm.c:write_protect_page(), which similarly required the TLB flush in the past to synchronize with GUP-fast. However, ever since general RCU GUP fast was introduced in commit 2667f50e8b81 ("mm: introduce a general RCU get_user_pages_fast()"), a TLB flush is no longer sufficient to handle concurrent GUP-fast in all cases -- it only handles traditional IPI-based GUP-fast correctly. Peter Xu (thankfully) questioned whether that TLB flush is really required. On architectures that send an IPI broadcast on TLB flush, it works as expected. To synchronize with RCU GUP-fast properly, we're conceptually fine, however, we have to enforce a certain memory order and are missing memory barriers. Let's document that, avoid the TLB flush where possible and use proper explicit memory barriers where required. We shouldn't really care about the additional memory barriers here, as we're not on extremely hot paths -- and we're getting rid of some TLB flushes. We use a smp_mb() pair for handling concurrent pinning and a smp_rmb()/smp_wmb() pair for handling the corner case of only temporary PTE changes but permanent PageAnonExclusive changes. One extreme example, whereby GUP-fast takes a R/O pin and KSM wants to convert an exclusive anonymous page to a KSM page, and that page is already mapped write-protected (-> no PTE change) would be: Thread 0 (KSM) Thread 1 (GUP-fast) (B1) Read the PTE # (B2) skipped without FOLL_WRITE (A1) Clear PTE smp_mb() (A2) Check pinned (B3) Pin the mapped page smp_mb() (A3) Clear PageAnonExclusive smp_wmb() (A4) Restore PTE (B4) Check if the PTE changed smp_rmb() (B5) Check PageAnonExclusive Thread 1 will properly detect that PageAnonExclusive was cleared and back off. Note that we don't need a memory barrier between checking if the page is pinned and clearing PageAnonExclusive, because stores are not speculated. The possible issues due to reordering are of theoretical nature so far and attempts to reproduce the race failed. Especially the "no PTE change" case isn't the common case, because we'd need an exclusive anonymous page that's mapped R/O and the PTE is clean in KSM code -- and using KSM with page pinning isn't extremely common. Further, the clear+TLB flush we used for now implies a memory barrier. So the problematic missing part should be the missing memory barrier after pinning but before checking if the PTE changed. Link: https://lkml.kernel.org/r/20220901083559.67446-1-david@redhat.com Fixes: 6c287605fd56 ("mm: remember exclusively mapped anonymous pages with PG_anon_exclusive") Signed-off-by: David Hildenbrand Cc: Jason Gunthorpe Cc: John Hubbard Cc: Andrea Arcangeli Cc: Hugh Dickins Cc: Peter Xu Cc: Alistair Popple Cc: Nadav Amit Cc: Yang Shi Cc: Vlastimil Babka Cc: Michal Hocko Cc: Mike Kravetz Cc: Andrea Parri Cc: Will Deacon Cc: Peter Zijlstra Cc: "Paul E. McKenney" Cc: Christoph von Recklinghausen Cc: Don Dutile Signed-off-by: Andrew Morton --- include/linux/mm.h | 9 +++++-- include/linux/rmap.h | 66 ++++++++++++++++++++++++++++++++++++++++++++++++---- 2 files changed, 68 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index e98ef2cb1176..8a5ad9d050bf 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2999,8 +2999,8 @@ static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags) * PageAnonExclusive() has to protect against concurrent GUP: * * Ordinary GUP: Using the PT lock * * GUP-fast and fork(): mm->write_protect_seq - * * GUP-fast and KSM or temporary unmapping (swap, migration): - * clear/invalidate+flush of the page table entry + * * GUP-fast and KSM or temporary unmapping (swap, migration): see + * page_try_share_anon_rmap() * * Must be called with the (sub)page that's actually referenced via the * page table entry, which might not necessarily be the head page for a @@ -3021,6 +3021,11 @@ static inline bool gup_must_unshare(unsigned int flags, struct page *page) */ if (!PageAnon(page)) return false; + + /* Paired with a memory barrier in page_try_share_anon_rmap(). */ + if (IS_ENABLED(CONFIG_HAVE_FAST_GUP)) + smp_rmb(); + /* * Note that PageKsm() pages cannot be exclusive, and consequently, * cannot get pinned. diff --git a/include/linux/rmap.h b/include/linux/rmap.h index bf80adca980b..72b2bcc37f73 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -267,7 +267,7 @@ dup: * @page: the exclusive anonymous page to try marking possibly shared * * The caller needs to hold the PT lock and has to have the page table entry - * cleared/invalidated+flushed, to properly sync against GUP-fast. + * cleared/invalidated. * * This is similar to page_try_dup_anon_rmap(), however, not used during fork() * to duplicate a mapping, but instead to prepare for KSM or temporarily @@ -283,12 +283,68 @@ static inline int page_try_share_anon_rmap(struct page *page) { VM_BUG_ON_PAGE(!PageAnon(page) || !PageAnonExclusive(page), page); - /* See page_try_dup_anon_rmap(). */ - if (likely(!is_device_private_page(page) && - unlikely(page_maybe_dma_pinned(page)))) - return -EBUSY; + /* device private pages cannot get pinned via GUP. */ + if (unlikely(is_device_private_page(page))) { + ClearPageAnonExclusive(page); + return 0; + } + /* + * We have to make sure that when we clear PageAnonExclusive, that + * the page is not pinned and that concurrent GUP-fast won't succeed in + * concurrently pinning the page. + * + * Conceptually, PageAnonExclusive clearing consists of: + * (A1) Clear PTE + * (A2) Check if the page is pinned; back off if so. + * (A3) Clear PageAnonExclusive + * (A4) Restore PTE (optional, but certainly not writable) + * + * When clearing PageAnonExclusive, we cannot possibly map the page + * writable again, because anon pages that may be shared must never + * be writable. So in any case, if the PTE was writable it cannot + * be writable anymore afterwards and there would be a PTE change. Only + * if the PTE wasn't writable, there might not be a PTE change. + * + * Conceptually, GUP-fast pinning of an anon page consists of: + * (B1) Read the PTE + * (B2) FOLL_WRITE: check if the PTE is not writable; back off if so. + * (B3) Pin the mapped page + * (B4) Check if the PTE changed by re-reading it; back off if so. + * (B5) If the original PTE is not writable, check if + * PageAnonExclusive is not set; back off if so. + * + * If the PTE was writable, we only have to make sure that GUP-fast + * observes a PTE change and properly backs off. + * + * If the PTE was not writable, we have to make sure that GUP-fast either + * detects a (temporary) PTE change or that PageAnonExclusive is cleared + * and properly backs off. + * + * Consequently, when clearing PageAnonExclusive(), we have to make + * sure that (A1), (A2)/(A3) and (A4) happen in the right memory + * order. In GUP-fast pinning code, we have to make sure that (B3),(B4) + * and (B5) happen in the right memory order. + * + * We assume that there might not be a memory barrier after + * clearing/invalidating the PTE (A1) and before restoring the PTE (A4), + * so we use explicit ones here. + */ + + /* Paired with the memory barrier in try_grab_folio(). */ + if (IS_ENABLED(CONFIG_HAVE_FAST_GUP)) + smp_mb(); + + if (unlikely(page_maybe_dma_pinned(page))) + return -EBUSY; ClearPageAnonExclusive(page); + + /* + * This is conceptually a smp_wmb() paired with the smp_rmb() in + * gup_must_unshare(). + */ + if (IS_ENABLED(CONFIG_HAVE_FAST_GUP)) + smp_mb__after_atomic(); return 0; } -- cgit v1.2.3 From 7bb5da0d490b2d836c5218f5186ee588d2145310 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Thu, 30 Jun 2022 23:32:57 +0100 Subject: kexec: turn all kexec_mutex acquisitions into trylocks Patch series "kexec, panic: Making crash_kexec() NMI safe", v4. This patch (of 2): Most acquistions of kexec_mutex are done via mutex_trylock() - those were a direct "translation" from: 8c5a1cf0ad3a ("kexec: use a mutex for locking rather than xchg()") there have however been two additions since then that use mutex_lock(): crash_get_memory_size() and crash_shrink_memory(). A later commit will replace said mutex with an atomic variable, and locking operations will become atomic_cmpxchg(). Rather than having those mutex_lock() become while (atomic_cmpxchg(&lock, 0, 1)), turn them into trylocks that can return -EBUSY on acquisition failure. This does halve the printable size of the crash kernel, but that's still neighbouring 2G for 32bit kernels which should be ample enough. Link: https://lkml.kernel.org/r/20220630223258.4144112-1-vschneid@redhat.com Link: https://lkml.kernel.org/r/20220630223258.4144112-2-vschneid@redhat.com Signed-off-by: Valentin Schneider Cc: Arnd Bergmann Cc: "Eric W . Biederman" Cc: Juri Lelli Cc: Luis Claudio R. Goncalves Cc: Miaohe Lin Cc: Petr Mladek Cc: Sebastian Andrzej Siewior Cc: Thomas Gleixner Cc: Baoquan He Signed-off-by: Andrew Morton --- include/linux/kexec.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 13e6c4b58f07..41a686996aaa 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -427,7 +427,7 @@ extern int kexec_load_disabled; extern bool kexec_in_progress; int crash_shrink_memory(unsigned long new_size); -size_t crash_get_memory_size(void); +ssize_t crash_get_memory_size(void); #ifndef arch_kexec_protect_crashkres /* -- cgit v1.2.3 From 2be9880dc87342dc7ae459c9ea5c9ee2a45b33d8 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Fri, 19 Aug 2022 09:44:06 +0800 Subject: kernel: exit: cleanup release_thread() Only x86 has own release_thread(), introduce a new weak release_thread() function to clean empty definitions in other ARCHs. Link: https://lkml.kernel.org/r/20220819014406.32266-1-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Acked-by: Guo Ren [csky] Acked-by: Russell King (Oracle) Acked-by: Geert Uytterhoeven Acked-by: Brian Cain Acked-by: Michael Ellerman [powerpc] Acked-by: Stafford Horne [openrisc] Acked-by: Catalin Marinas [arm64] Acked-by: Huacai Chen [LoongArch] Cc: Alexander Gordeev Cc: Anton Ivanov Cc: Borislav Petkov Cc: Christian Borntraeger Cc: Christophe Leroy Cc: Chris Zankel Cc: Dave Hansen Cc: "David S. Miller" Cc: Dinh Nguyen Cc: Guo Ren [csky] Cc: Heiko Carstens Cc: Helge Deller Cc: Ingo Molnar Cc: Ivan Kokshaysky Cc: James Bottomley Cc: Johannes Berg Cc: Jonas Bonn Cc: Matt Turner Cc: Max Filippov Cc: Michal Simek Cc: Nicholas Piggin Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Richard Henderson Cc: Richard Weinberger Cc: Rich Felker Cc: Stefan Kristiansson Cc: Sven Schnelle Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Vineet Gupta Cc: Will Deacon Cc: Xuerui Wang Cc: Yoshinori Sato Signed-off-by: Andrew Morton --- include/linux/sched/task.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 81cab4b01edc..d6c48163c6de 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -127,6 +127,9 @@ static inline void put_task_struct_many(struct task_struct *t, int nr) void put_task_struct_rcu_user(struct task_struct *task); +/* Free all architecture-specific resources held by a thread. */ +void release_thread(struct task_struct *dead_task); + #ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT extern int arch_task_struct_size __read_mostly; #else -- cgit v1.2.3 From da3f52ba359590d8eb465ae0d8b6e11d6fd9432f Mon Sep 17 00:00:00 2001 From: Uros Bizjak Date: Sun, 21 Aug 2022 21:30:11 +0200 Subject: iversion: use atomic64_try_cmpxchg) Use atomic64_try_cmpxchg instead of atomic64_cmpxchg (*ptr, old, new) == old in inode_set_max_iversion_raw, inode_maybe_inc_version and inode_query_iversion. x86 CMPXCHG instruction returns success in ZF flag, so this change saves a compare after cmpxchg (and related move instruction in front of cmpxchg). Also, try_cmpxchg implicitly assigns old *ptr value to "old" when cmpxchg fails, enabling further code simplifications. The loop in inode_maybe_inc_iversion improves from: 5563: 48 89 ca mov %rcx,%rdx 5566: 48 89 c8 mov %rcx,%rax 5569: 48 83 e2 fe and $0xfffffffffffffffe,%rdx 556d: 48 83 c2 02 add $0x2,%rdx 5571: f0 48 0f b1 16 lock cmpxchg %rdx,(%rsi) 5576: 48 39 c1 cmp %rax,%rcx 5579: 0f 84 85 fc ff ff je 5204 <...> 557f: 48 89 c1 mov %rax,%rcx 5582: eb df jmp 5563 <...> to: 5563: 48 89 c2 mov %rax,%rdx 5566: 48 83 e2 fe and $0xfffffffffffffffe,%rdx 556a: 48 83 c2 02 add $0x2,%rdx 556e: f0 48 0f b1 11 lock cmpxchg %rdx,(%rcx) 5573: 0f 84 8b fc ff ff je 5204 <...> 5579: eb e8 jmp 5563 <...> Link: https://lkml.kernel.org/r/20220821193011.88208-1-ubizjak@gmail.com Signed-off-by: Uros Bizjak Signed-off-by: Andrew Morton --- include/linux/iversion.h | 32 +++++++++----------------------- 1 file changed, 9 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iversion.h b/include/linux/iversion.h index 3bfebde5a1a6..eb5a15810169 100644 --- a/include/linux/iversion.h +++ b/include/linux/iversion.h @@ -123,17 +123,12 @@ inode_peek_iversion_raw(const struct inode *inode) static inline void inode_set_max_iversion_raw(struct inode *inode, u64 val) { - u64 cur, old; + u64 cur = inode_peek_iversion_raw(inode); - cur = inode_peek_iversion_raw(inode); - for (;;) { + do { if (cur > val) break; - old = atomic64_cmpxchg(&inode->i_version, cur, val); - if (likely(old == cur)) - break; - cur = old; - } + } while (!atomic64_try_cmpxchg(&inode->i_version, &cur, val)); } /** @@ -197,7 +192,7 @@ inode_set_iversion_queried(struct inode *inode, u64 val) static inline bool inode_maybe_inc_iversion(struct inode *inode, bool force) { - u64 cur, old, new; + u64 cur, new; /* * The i_version field is not strictly ordered with any other inode @@ -211,19 +206,14 @@ inode_maybe_inc_iversion(struct inode *inode, bool force) */ smp_mb(); cur = inode_peek_iversion_raw(inode); - for (;;) { + do { /* If flag is clear then we needn't do anything */ if (!force && !(cur & I_VERSION_QUERIED)) return false; /* Since lowest bit is flag, add 2 to avoid it */ new = (cur & ~I_VERSION_QUERIED) + I_VERSION_INCREMENT; - - old = atomic64_cmpxchg(&inode->i_version, cur, new); - if (likely(old == cur)) - break; - cur = old; - } + } while (!atomic64_try_cmpxchg(&inode->i_version, &cur, new)); return true; } @@ -304,10 +294,10 @@ inode_peek_iversion(const struct inode *inode) static inline u64 inode_query_iversion(struct inode *inode) { - u64 cur, old, new; + u64 cur, new; cur = inode_peek_iversion_raw(inode); - for (;;) { + do { /* If flag is already set, then no need to swap */ if (cur & I_VERSION_QUERIED) { /* @@ -320,11 +310,7 @@ inode_query_iversion(struct inode *inode) } new = cur | I_VERSION_QUERIED; - old = atomic64_cmpxchg(&inode->i_version, cur, new); - if (likely(old == cur)) - break; - cur = old; - } + } while (!atomic64_try_cmpxchg(&inode->i_version, &cur, new)); return cur >> I_VERSION_QUERIED_SHIFT; } -- cgit v1.2.3 From e1d7c7609ae0933b59840390c1b207ac0a925c8b Mon Sep 17 00:00:00 2001 From: Uros Bizjak Date: Mon, 22 Aug 2022 16:38:51 +0200 Subject: bitops: use try_cmpxchg in set_mask_bits and bit_clear_unless Use try_cmpxchg instead of cmpxchg (*ptr, old, new) == old in set_mask_bits and bit_clear_unless. x86 CMPXCHG instruction returns success in ZF flag, so this change saves a compare after cmpxchg (and related move instruction in front of cmpxchg). Also, try_cmpxchg implicitly assigns old *ptr value to "old" when cmpxchg fails, enabling further code simplifications. Link: https://lkml.kernel.org/r/20220822143851.3290-1-ubizjak@gmail.com Signed-off-by: Uros Bizjak Signed-off-by: Andrew Morton --- include/linux/bitops.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 3b89c64bcfd8..fb24a513d917 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -328,10 +328,10 @@ static __always_inline void __assign_bit(long nr, volatile unsigned long *addr, const typeof(*(ptr)) mask__ = (mask), bits__ = (bits); \ typeof(*(ptr)) old__, new__; \ \ + old__ = READ_ONCE(*(ptr)); \ do { \ - old__ = READ_ONCE(*(ptr)); \ new__ = (old__ & ~mask__) | bits__; \ - } while (cmpxchg(ptr, old__, new__) != old__); \ + } while (!try_cmpxchg(ptr, &old__, new__)); \ \ old__; \ }) @@ -343,11 +343,12 @@ static __always_inline void __assign_bit(long nr, volatile unsigned long *addr, const typeof(*(ptr)) clear__ = (clear), test__ = (test);\ typeof(*(ptr)) old__, new__; \ \ + old__ = READ_ONCE(*(ptr)); \ do { \ - old__ = READ_ONCE(*(ptr)); \ + if (old__ & test__) \ + break; \ new__ = old__ & ~clear__; \ - } while (!(old__ & test__) && \ - cmpxchg(ptr, old__, new__) != old__); \ + } while (!try_cmpxchg(ptr, &old__, new__)); \ \ !(old__ & test__); \ }) -- cgit v1.2.3 From a47126ec29f538e1197862919f94d3b6668144a4 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Fri, 9 Sep 2022 15:24:57 -0500 Subject: PCI/PTM: Cache PTM Capability offset Cache the PTM Capability offset instead of searching for it every time we enable/disable PTM or save/restore PTM state. No functional change intended. Link: https://lore.kernel.org/r/20220909202505.314195-2-helgaas@kernel.org Tested-by: Rajvi Jingar Signed-off-by: Bjorn Helgaas Reviewed-by: Kuppuswamy Sathyanarayanan Reviewed-by: Mika Westerberg --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 060af91bafcd..54be939023a3 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -475,6 +475,7 @@ struct pci_dev { unsigned int broken_cmd_compl:1; /* No compl for some cmds */ #endif #ifdef CONFIG_PCIE_PTM + u16 ptm_cap; /* PTM Capability */ unsigned int ptm_root:1; unsigned int ptm_enabled:1; u8 ptm_granularity; -- cgit v1.2.3 From e8bdc5ea481638e0a4fd5639050d2b170417f493 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Fri, 9 Sep 2022 15:25:00 -0500 Subject: PCI/PTM: Add pci_suspend_ptm() and pci_resume_ptm() We disable PTM during suspend because that allows some Root Ports to enter lower-power PM states, which means we also need to disable PTM for all downstream devices. Add pci_suspend_ptm() and pci_resume_ptm() for this purpose. pci_enable_ptm() and pci_disable_ptm() are for drivers to use to enable or disable PTM. They use dev->ptm_enabled to keep track of whether PTM should be enabled. pci_suspend_ptm() and pci_resume_ptm() are PCI core-internal functions to temporarily disable PTM during suspend and (depending on dev->ptm_enabled) re-enable PTM during resume. Enable/disable/suspend/resume all use internal __pci_enable_ptm() and __pci_disable_ptm() functions that only update the PTM Control register. Outline: pci_enable_ptm(struct pci_dev *dev) { __pci_enable_ptm(dev); dev->ptm_enabled = 1; pci_ptm_info(dev); } pci_disable_ptm(struct pci_dev *dev) { if (dev->ptm_enabled) { __pci_disable_ptm(dev); dev->ptm_enabled = 0; } } pci_suspend_ptm(struct pci_dev *dev) { if (dev->ptm_enabled) __pci_disable_ptm(dev); } pci_resume_ptm(struct pci_dev *dev) { if (dev->ptm_enabled) __pci_enable_ptm(dev); } Nothing currently calls pci_resume_ptm(); the suspend path saves the PTM state before disabling PTM, so the PTM state restore in the resume path implicitly re-enables it. A future change will use pci_resume_ptm() to fix some problems with this approach. Link: https://lore.kernel.org/r/20220909202505.314195-5-helgaas@kernel.org Tested-by: Rajvi Jingar Signed-off-by: Bjorn Helgaas Reviewed-by: Mika Westerberg --- include/linux/pci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 54be939023a3..cb5f796e3319 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1678,10 +1678,12 @@ bool pci_ats_disabled(void); #ifdef CONFIG_PCIE_PTM int pci_enable_ptm(struct pci_dev *dev, u8 *granularity); +void pci_disable_ptm(struct pci_dev *dev); bool pcie_ptm_enabled(struct pci_dev *dev); #else static inline int pci_enable_ptm(struct pci_dev *dev, u8 *granularity) { return -EINVAL; } +static inline void pci_disable_ptm(struct pci_dev *dev) { } static inline bool pcie_ptm_enabled(struct pci_dev *dev) { return false; } #endif -- cgit v1.2.3 From f24a0b1c22c2e90abb4ee1f7a3b0f0d8fc2ede5f Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Tue, 16 Aug 2022 13:25:09 +0200 Subject: clk: Mention that .recalc_rate can return 0 on error Multiple platforms (amlogic, imx8) return 0 when the clock rate cannot be determined properly by the recalc_rate hook. Mention in the documentation that the framework is ok with that. Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20220816112530.1837489-5-maxime@cerno.tech Tested-by: Linux Kernel Functional Testing Tested-by: Naresh Kamboju Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 1615010aa0ec..9a14cfa0d201 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -118,8 +118,9 @@ struct clk_duty { * * @recalc_rate Recalculate the rate of this clock, by querying hardware. The * parent rate is an input parameter. It is up to the caller to - * ensure that the prepare_mutex is held across this call. - * Returns the calculated rate. Optional, but recommended - if + * ensure that the prepare_mutex is held across this call. If the + * driver cannot figure out a rate for this clock, it must return + * 0. Returns the calculated rate. Optional, but recommended - if * this op is not set then clock rate will be initialized to 0. * * @round_rate: Given a target rate as input, returns the closest rate actually -- cgit v1.2.3 From c35e84b0977617f96fb1dbef3fb8d71a861325c0 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Tue, 16 Aug 2022 13:25:21 +0200 Subject: clk: Introduce clk_hw_init_rate_request() clk-divider instantiates clk_rate_request internally for its round_rate implementations to share the code with its determine_rate implementations. However, it's missing a few fields (min_rate, max_rate) that would be initialized properly if it was using clk_core_init_rate_req(). Let's create the clk_hw_init_rate_request() function for clock providers to be able to share the code to instation clk_rate_requests with the framework. This will also be useful for some tests introduced in later patches. Tested-by: Alexander Stein # imx8mp Tested-by: Marek Szyprowski # exynos4210, meson g12b Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20220816112530.1837489-17-maxime@cerno.tech Tested-by: Linux Kernel Functional Testing Tested-by: Naresh Kamboju Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 9a14cfa0d201..d857717aa386 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -42,6 +42,8 @@ struct dentry; * struct clk_rate_request - Structure encoding the clk constraints that * a clock user might require. * + * Should be initialized by calling clk_hw_init_rate_request(). + * * @rate: Requested clock rate. This field will be adjusted by * clock drivers according to hardware capabilities. * @min_rate: Minimum rate imposed by clk users. @@ -60,6 +62,10 @@ struct clk_rate_request { struct clk_hw *best_parent_hw; }; +void clk_hw_init_rate_request(const struct clk_hw *hw, + struct clk_rate_request *req, + unsigned long rate); + /** * struct clk_duty - Struture encoding the duty cycle ratio of a clock * -- cgit v1.2.3 From 22fb0e284fbc3c1b85d24c5a1df8ea3ac82ab1d1 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Tue, 16 Aug 2022 13:25:25 +0200 Subject: clk: Constify clk_has_parent() clk_has_parent() doesn't modify the clocks being passed, so let's make it const. Suggested-by: Stephen Boyd Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20220816112530.1837489-21-maxime@cerno.tech Tested-by: Linux Kernel Functional Testing Tested-by: Naresh Kamboju Signed-off-by: Stephen Boyd --- include/linux/clk.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/clk.h b/include/linux/clk.h index c13061cabdfc..1ef013324237 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -799,7 +799,7 @@ int clk_set_rate_exclusive(struct clk *clk, unsigned long rate); * * Returns true if @parent is a possible parent for @clk, false otherwise. */ -bool clk_has_parent(struct clk *clk, struct clk *parent); +bool clk_has_parent(const struct clk *clk, const struct clk *parent); /** * clk_set_rate_range - set a rate range for a clock source -- cgit v1.2.3 From 262ca38f4b6eb418b20b8e1d6d8495c6a98727c1 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Tue, 16 Aug 2022 13:25:26 +0200 Subject: clk: Stop forwarding clk_rate_requests to the parent If the clock cannot modify its rate and has CLK_SET_RATE_PARENT, clk_mux_determine_rate_flags(), clk_core_round_rate_nolock() and a number of drivers will forward the clk_rate_request to the parent clock. clk_core_round_rate_nolock() will pass the pointer directly, which means that we pass a clk_rate_request to the parent that has the rate, min_rate and max_rate of the child, and the best_parent_rate and best_parent_hw fields will be relative to the child as well, so will point to our current clock and its rate. The most common case for CLK_SET_RATE_PARENT is that the child and parent clock rates will be equal, so the rate field isn't a worry, but the other fields are. Similarly, if the parent clock driver ever modifies the best_parent_rate or best_parent_hw, this will be applied to the child once the call to clk_core_round_rate_nolock() is done. best_parent_hw is probably not going to be a valid parent, and best_parent_rate might lead to a parent rate change different to the one that was initially computed. clk_mux_determine_rate_flags() and the affected drivers will copy the request before forwarding it to the parents, so they won't be affected by the latter issue, but the former is still going to be there and will lead to erroneous data and context being passed to the various clock drivers in the same sub-tree. Let's create two new functions, clk_core_forward_rate_req() and clk_hw_forward_rate_request() for the framework and the clock providers that will copy a request from a child clock and update the context to match the parent's. We also update the relevant call sites in the framework and drivers to use that new function. Let's also add a test to make sure we avoid regressions there. Tested-by: Alexander Stein # imx8mp Tested-by: Marek Szyprowski # exynos4210, meson g12b Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20220816112530.1837489-22-maxime@cerno.tech Tested-by: Linux Kernel Functional Testing Tested-by: Naresh Kamboju Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index d857717aa386..8bce6c524f29 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -65,6 +65,11 @@ struct clk_rate_request { void clk_hw_init_rate_request(const struct clk_hw *hw, struct clk_rate_request *req, unsigned long rate); +void clk_hw_forward_rate_request(const struct clk_hw *core, + const struct clk_rate_request *old_req, + const struct clk_hw *parent, + struct clk_rate_request *req, + unsigned long parent_rate); /** * struct clk_duty - Struture encoding the duty cycle ratio of a clock -- cgit v1.2.3 From 253993253466ba7187730b196174146d5247e97b Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Tue, 16 Aug 2022 13:25:28 +0200 Subject: clk: Introduce the clk_hw_get_rate_range function Some clock providers are hand-crafting their clk_rate_request, and need to figure out the current boundaries of their clk_hw to fill it properly. Let's create such a function for clock providers. Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20220816112530.1837489-24-maxime@cerno.tech Tested-by: Linux Kernel Functional Testing Tested-by: Naresh Kamboju Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 8bce6c524f29..8724a3547a79 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -1267,6 +1267,8 @@ int clk_mux_determine_rate_flags(struct clk_hw *hw, struct clk_rate_request *req, unsigned long flags); void clk_hw_reparent(struct clk_hw *hw, struct clk_hw *new_parent); +void clk_hw_get_rate_range(struct clk_hw *hw, unsigned long *min_rate, + unsigned long *max_rate); void clk_hw_set_rate_range(struct clk_hw *hw, unsigned long min_rate, unsigned long max_rate); -- cgit v1.2.3 From 82f00b24f532557fb0e15a6a2747859e4b70c4bd Mon Sep 17 00:00:00 2001 From: Weili Qian Date: Fri, 9 Sep 2022 17:46:55 +0800 Subject: crypto: hisilicon/qm - get hardware features from hardware registers Before hardware V3, hardwares do not provide the feature registers, driver resolves hardware differences based on the hardware version. As a result, the driver does not support the new hardware. Hardware V3 and later versions support to obtain hardware features, such as power-gating management and doorbell isolation, through the hardware registers. To be compatible with later hardware versions, the features of the current device is obtained by reading the hardware registers instead of the hardware version. Signed-off-by: Weili Qian Signed-off-by: Herbert Xu --- include/linux/hisi_acc_qm.h | 31 +++++++++++++++++++++++++++++-- 1 file changed, 29 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h index 116e8bd68c99..851c962ba473 100644 --- a/include/linux/hisi_acc_qm.h +++ b/include/linux/hisi_acc_qm.h @@ -168,6 +168,15 @@ enum qm_vf_state { QM_NOT_READY, }; +enum qm_cap_bits { + QM_SUPPORT_DB_ISOLATION = 0x0, + QM_SUPPORT_FUNC_QOS, + QM_SUPPORT_STOP_QP, + QM_SUPPORT_MB_COMMAND, + QM_SUPPORT_SVA_PREFETCH, + QM_SUPPORT_RPM, +}; + struct dfx_diff_registers { u32 *regs; u32 reg_offset; @@ -258,6 +267,18 @@ struct hisi_qm_err_ini { void (*err_info_init)(struct hisi_qm *qm); }; +struct hisi_qm_cap_info { + u32 type; + /* Register offset */ + u32 offset; + /* Bit offset in register */ + u32 shift; + u32 mask; + u32 v1_val; + u32 v2_val; + u32 v3_val; +}; + struct hisi_qm_list { struct mutex lock; struct list_head list; @@ -278,6 +299,9 @@ struct hisi_qm { struct pci_dev *pdev; void __iomem *io_base; void __iomem *db_io_base; + + /* Capbility version, 0: not supports */ + u32 cap_ver; u32 sqe_size; u32 qp_base; u32 qp_num; @@ -304,6 +328,8 @@ struct hisi_qm { struct hisi_qm_err_info err_info; struct hisi_qm_err_status err_status; unsigned long misc_ctl; /* driver removing and reset sched */ + /* Device capability bit */ + unsigned long caps; struct rw_semaphore qps_lock; struct idr qp_idr; @@ -326,8 +352,6 @@ struct hisi_qm { bool use_sva; bool is_frozen; - /* doorbell isolation enable */ - bool use_db_isolation; resource_size_t phys_base; resource_size_t db_phys_base; struct uacce_device *uacce; @@ -501,6 +525,9 @@ void hisi_qm_pm_init(struct hisi_qm *qm); int hisi_qm_get_dfx_access(struct hisi_qm *qm); void hisi_qm_put_dfx_access(struct hisi_qm *qm); void hisi_qm_regs_dump(struct seq_file *s, struct debugfs_regset32 *regset); +u32 hisi_qm_get_hw_info(struct hisi_qm *qm, + const struct hisi_qm_cap_info *info_table, + u32 index, bool is_read); /* Used by VFIO ACC live migration driver */ struct pci_driver *hisi_sec_get_pf_driver(void); -- cgit v1.2.3 From 129a9f340172b4f3857260a7a7bb9d7b3496ba50 Mon Sep 17 00:00:00 2001 From: Weili Qian Date: Fri, 9 Sep 2022 17:46:56 +0800 Subject: crypto: hisilicon/qm - get qp num and depth from hardware registers Hardware V3 and later versions can obtain qp num and depth supported by the hardware from registers. To be compatible with later hardware versions, get qp num and depth from registers instead of fixed marcos. Signed-off-by: Weili Qian Signed-off-by: Herbert Xu --- include/linux/hisi_acc_qm.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h index 851c962ba473..371c0e7ffd27 100644 --- a/include/linux/hisi_acc_qm.h +++ b/include/linux/hisi_acc_qm.h @@ -109,7 +109,6 @@ QM_MAILBOX_TIMEOUT | QM_FLR_TIMEOUT) #define QM_BASE_CE QM_ECC_1BIT -#define QM_Q_DEPTH 1024 #define QM_MIN_QNUM 2 #define HISI_ACC_SGL_SGE_NR_MAX 255 #define QM_SHAPER_CFG 0x100164 @@ -310,6 +309,8 @@ struct hisi_qm { u32 max_qp_num; u32 vfs_num; u32 db_interval; + u16 eq_depth; + u16 aeq_depth; struct list_head list; struct hisi_qm_list *qm_list; @@ -375,6 +376,8 @@ struct hisi_qp_ops { struct hisi_qp { u32 qp_id; + u16 sq_depth; + u16 cq_depth; u8 alg_type; u8 req_type; -- cgit v1.2.3 From d90fab0deb8e580aa001f6876e4436c21e944f27 Mon Sep 17 00:00:00 2001 From: Weili Qian Date: Fri, 9 Sep 2022 17:46:58 +0800 Subject: crypto: hisilicon/qm - get error type from hardware registers Hardware V3 and later versions support get error type from registers. To be compatible with later hardware versions, get error type from registers instead of fixed marco. Signed-off-by: Weili Qian Signed-off-by: Herbert Xu --- include/linux/hisi_acc_qm.h | 27 ++++----------------------- 1 file changed, 4 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h index 371c0e7ffd27..e230c7c46110 100644 --- a/include/linux/hisi_acc_qm.h +++ b/include/linux/hisi_acc_qm.h @@ -87,28 +87,6 @@ #define PEH_AXUSER_CFG 0x401001 #define PEH_AXUSER_CFG_ENABLE 0xffffffff -#define QM_AXI_RRESP BIT(0) -#define QM_AXI_BRESP BIT(1) -#define QM_ECC_MBIT BIT(2) -#define QM_ECC_1BIT BIT(3) -#define QM_ACC_GET_TASK_TIMEOUT BIT(4) -#define QM_ACC_DO_TASK_TIMEOUT BIT(5) -#define QM_ACC_WB_NOT_READY_TIMEOUT BIT(6) -#define QM_SQ_CQ_VF_INVALID BIT(7) -#define QM_CQ_VF_INVALID BIT(8) -#define QM_SQ_VF_INVALID BIT(9) -#define QM_DB_TIMEOUT BIT(10) -#define QM_OF_FIFO_OF BIT(11) -#define QM_DB_RANDOM_INVALID BIT(12) -#define QM_MAILBOX_TIMEOUT BIT(13) -#define QM_FLR_TIMEOUT BIT(14) - -#define QM_BASE_NFE (QM_AXI_RRESP | QM_AXI_BRESP | QM_ECC_MBIT | \ - QM_ACC_GET_TASK_TIMEOUT | QM_DB_TIMEOUT | \ - QM_OF_FIFO_OF | QM_DB_RANDOM_INVALID | \ - QM_MAILBOX_TIMEOUT | QM_FLR_TIMEOUT) -#define QM_BASE_CE QM_ECC_1BIT - #define QM_MIN_QNUM 2 #define HISI_ACC_SGL_SGE_NR_MAX 255 #define QM_SHAPER_CFG 0x100164 @@ -240,7 +218,10 @@ struct hisi_qm_err_info { char *acpi_rst; u32 msi_wr_port; u32 ecc_2bits_mask; - u32 dev_ce_mask; + u32 qm_shutdown_mask; + u32 dev_shutdown_mask; + u32 qm_reset_mask; + u32 dev_reset_mask; u32 ce; u32 nfe; u32 fe; -- cgit v1.2.3 From 882597aff2d442a52ca173c293939232c2e1ebea Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Wed, 14 Sep 2022 07:14:24 -0700 Subject: Input: auo-pixcir-ts - drop support for platform data Currently there are no users of auo_pixcir_ts_platdata in the mainline, and having it (with legacy gpio numbers) prevents us from converting the driver to gpiod API, so let's drop it. If, in the future, someone wants to use this driver on non-device tree, non-ACPI system, they should use static device properties instead of platform data. Reviewed-by: Heiko Stuebner Link: https://lore.kernel.org/r/20220914141428.2201784-1-dmitry.torokhov@gmail.com Signed-off-by: Dmitry Torokhov --- include/linux/input/auo-pixcir-ts.h | 44 ------------------------------------- 1 file changed, 44 deletions(-) delete mode 100644 include/linux/input/auo-pixcir-ts.h (limited to 'include/linux') diff --git a/include/linux/input/auo-pixcir-ts.h b/include/linux/input/auo-pixcir-ts.h deleted file mode 100644 index ed0776997a7a..000000000000 --- a/include/linux/input/auo-pixcir-ts.h +++ /dev/null @@ -1,44 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Driver for AUO in-cell touchscreens - * - * Copyright (c) 2011 Heiko Stuebner - * - * based on auo_touch.h from Dell Streak kernel - * - * Copyright (c) 2008 QUALCOMM Incorporated. - * Copyright (c) 2008 QUALCOMM USA, INC. - */ - -#ifndef __AUO_PIXCIR_TS_H__ -#define __AUO_PIXCIR_TS_H__ - -/* - * Interrupt modes: - * periodical: interrupt is asserted periodicaly - * compare coordinates: interrupt is asserted when coordinates change - * indicate touch: interrupt is asserted during touch - */ -#define AUO_PIXCIR_INT_PERIODICAL 0x00 -#define AUO_PIXCIR_INT_COMP_COORD 0x01 -#define AUO_PIXCIR_INT_TOUCH_IND 0x02 - -/* - * @gpio_int interrupt gpio - * @int_setting one of AUO_PIXCIR_INT_* - * @init_hw hardwarespecific init - * @exit_hw hardwarespecific shutdown - * @x_max x-resolution - * @y_max y-resolution - */ -struct auo_pixcir_ts_platdata { - int gpio_int; - int gpio_rst; - - int int_setting; - - unsigned int x_max; - unsigned int y_max; -}; - -#endif -- cgit v1.2.3 From 6a164c646999847b843e651f71c53dfaceb2c2b4 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Mon, 9 May 2022 16:04:08 +0200 Subject: genirq: Provide generic_handle_domain_irq_safe(). commit 509853f9e1e7b ("genirq: Provide generic_handle_irq_safe()") addressed the problem of demultiplexing interrupt handlers which are force threaded on PREEMPT_RT enabled kernels which means that the demultiplexed handler is invoked with interrupts enabled which triggers a lockdep warning due to a non-irq safe lock acquisition. The same problem exists for the irq domain based interrupt handling via generic_handle_domain_irq() which has been reported against the AMD pin-ctrl driver. Provide generic_handle_domain_irq_safe() which can used from any context. [ tglx: Split the usage sites out and massaged changelog ] Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/YnkfWFzvusFFktSt@linutronix.de Link: https://bugzilla.kernel.org/show_bug.cgi?id=215954 --- include/linux/irqdesc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index 1cd4e36890fb..844a8e30e6de 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -169,6 +169,7 @@ int generic_handle_irq_safe(unsigned int irq); * conversion failed. */ int generic_handle_domain_irq(struct irq_domain *domain, unsigned int hwirq); +int generic_handle_domain_irq_safe(struct irq_domain *domain, unsigned int hwirq); int generic_handle_domain_nmi(struct irq_domain *domain, unsigned int hwirq); #endif -- cgit v1.2.3 From 38bef8e57f2149acd2c910a98f57dd6291d2e0ec Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Mon, 5 Sep 2022 16:08:17 -0700 Subject: smp: add set_nr_cpu_ids() In preparation to support compile-time nr_cpu_ids, add a setter for the variable. This is a no-op for all arches. Signed-off-by: Yury Norov --- include/linux/cpumask.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index e8ad12b5b9d2..24763997894d 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -39,6 +39,11 @@ typedef struct cpumask { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t; #define nr_cpu_ids 1U #else extern unsigned int nr_cpu_ids; + +static inline void set_nr_cpu_ids(unsigned int nr) +{ + nr_cpu_ids = nr; +} #endif #ifdef CONFIG_CPUMASK_OFFSTACK -- cgit v1.2.3 From 7102b3bb070fdf4580a05cbfc5ad3c0691dc4bf9 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Mon, 5 Sep 2022 16:08:18 -0700 Subject: lib/cpumask: delete misleading comment The comment says that HOTPLUG config option enables all cpus in cpu_possible_mask up to NR_CPUs. This is wrong. Even if HOTPLUG is enabled, the mask is populated on boot with respect to ACPI/DT records. Signed-off-by: Yury Norov --- include/linux/cpumask.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 24763997894d..9d2f0e3e927e 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -72,10 +72,6 @@ static inline void set_nr_cpu_ids(unsigned int nr) * cpu_online_mask is the dynamic subset of cpu_present_mask, * indicating those CPUs available for scheduling. * - * If HOTPLUG is enabled, then cpu_possible_mask is forced to have - * all NR_CPUS bits set, otherwise it is just the set of CPUs that - * ACPI reports present at boot. - * * If HOTPLUG is enabled, then cpu_present_mask varies dynamically, * depending on what ACPI reports as currently plugged in, otherwise * cpu_present_mask is just a copy of cpu_possible_mask. -- cgit v1.2.3 From aa47a7c215e79a2ade6916f163c5a17b561bce4f Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Mon, 5 Sep 2022 16:08:19 -0700 Subject: lib/cpumask: deprecate nr_cpumask_bits Cpumask code is written in assumption that when CONFIG_CPUMASK_OFFSTACK is enabled, all cpumasks have boot-time defined size, otherwise the size is always NR_CPUS. The latter is wrong because the number of possible cpus is always calculated on boot, and it may be less than NR_CPUS. On my 4-cpu arm64 VM the nr_cpu_ids is 4, as expected, and nr_cpumask_bits is 256, which corresponds to NR_CPUS. This not only leads to useless traversing of cpumask bits greater than 4, this also makes some cpumask routines fail. For example, cpumask_full(0b1111000..000) would erroneously return false in the example above because tail bits in the mask are all unset. This patch deprecates nr_cpumask_bits and wires it to nr_cpu_ids unconditionally, so that cpumask routines will not waste time traversing unused part of cpu masks. It also fixes cpumask_full() and similar routines. As a side effect, because now a length of cpumasks is defined at run-time even if CPUMASK_OFFSTACK is disabled, compiler can't optimize corresponding functions. It increases kernel size by ~2.5KB if OFFSTACK is off. This is addressed in the following patch. Signed-off-by: Yury Norov --- include/linux/cpumask.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 9d2f0e3e927e..2f6622cead1f 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -46,13 +46,8 @@ static inline void set_nr_cpu_ids(unsigned int nr) } #endif -#ifdef CONFIG_CPUMASK_OFFSTACK -/* Assuming NR_CPUS is huge, a runtime limit is more efficient. Also, - * not all bits may be allocated. */ +/* Deprecated. Always use nr_cpu_ids. */ #define nr_cpumask_bits nr_cpu_ids -#else -#define nr_cpumask_bits ((unsigned int)NR_CPUS) -#endif /* * The following particular system cpumasks and operations manage -- cgit v1.2.3 From 6f9c07be9d020489326098801f0661f754c7c865 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Mon, 5 Sep 2022 16:08:20 -0700 Subject: lib/cpumask: add FORCE_NR_CPUS config option The size of cpumasks is hard-limited by compile-time parameter NR_CPUS, but defined at boot-time when kernel parses ACPI/DT tables, and stored in nr_cpu_ids. In many practical cases, number of CPUs for a target is known at compile time, and can be provided with NR_CPUS. In that case, compiler may be instructed to rely on NR_CPUS as on actual number of CPUs, not an upper limit. It allows to optimize many cpumask routines and significantly shrink size of the kernel image. This patch adds FORCE_NR_CPUS option to teach the compiler to rely on NR_CPUS and enable corresponding optimizations. If FORCE_NR_CPUS=y, kernel will not set nr_cpu_ids at boot, but only check that the actual number of possible CPUs is equal to NR_CPUS, and WARN if that doesn't hold. The new option is especially useful in embedded applications because kernel configurations are unique for each SoC, the number of CPUs is constant and known well, and memory limitations are typically harder. For my 4-CPU ARM64 build with NR_CPUS=4, FORCE_NR_CPUS=y saves 46KB: add/remove: 3/4 grow/shrink: 46/729 up/down: 652/-46952 (-46300) Signed-off-by: Yury Norov --- include/linux/cpumask.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 2f6622cead1f..1b442fb2001f 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -35,16 +35,20 @@ typedef struct cpumask { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t; */ #define cpumask_pr_args(maskp) nr_cpu_ids, cpumask_bits(maskp) -#if NR_CPUS == 1 -#define nr_cpu_ids 1U +#if (NR_CPUS == 1) || defined(CONFIG_FORCE_NR_CPUS) +#define nr_cpu_ids ((unsigned int)NR_CPUS) #else extern unsigned int nr_cpu_ids; +#endif static inline void set_nr_cpu_ids(unsigned int nr) { +#if (NR_CPUS == 1) || defined(CONFIG_FORCE_NR_CPUS) + WARN_ON(nr != nr_cpu_ids); +#else nr_cpu_ids = nr; -} #endif +} /* Deprecated. Always use nr_cpu_ids. */ #define nr_cpumask_bits nr_cpu_ids -- cgit v1.2.3 From 14a99e130f2758bc826a7e7a8bdf6f7400b54f0f Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Wed, 14 Sep 2022 19:07:28 -0700 Subject: lib/find_bit: create find_first_zero_bit_le() find_first_zero_bit_le() is an alias to find_next_zero_bit_le(), despite that 'next' is known to be slower than 'first' version. Now that we have common FIND_FIRST_BIT() macro helper, it's trivial to implement find_first_zero_bit_le() as a real function. Reviewed-by: Valentin Schneider Signed-off-by: Yury Norov --- include/linux/find.h | 23 ++++++++++++++++++----- 1 file changed, 18 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/find.h b/include/linux/find.h index 424ef67d4a42..2464bff5de04 100644 --- a/include/linux/find.h +++ b/include/linux/find.h @@ -17,6 +17,10 @@ extern unsigned long _find_first_and_bit(const unsigned long *addr1, extern unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size); extern unsigned long _find_last_bit(const unsigned long *addr, unsigned long size); +#ifdef __BIG_ENDIAN +unsigned long _find_first_zero_bit_le(const unsigned long *addr, unsigned long size); +#endif + #ifndef find_next_bit /** * find_next_bit - find the next set bit in a memory region @@ -251,6 +255,20 @@ unsigned long find_next_zero_bit_le(const void *addr, unsigned } #endif +#ifndef find_first_zero_bit_le +static inline +unsigned long find_first_zero_bit_le(const void *addr, unsigned long size) +{ + if (small_const_nbits(size)) { + unsigned long val = swab(*(const unsigned long *)addr) | ~GENMASK(size - 1, 0); + + return val == ~0UL ? size : ffz(val); + } + + return _find_first_zero_bit_le(addr, size); +} +#endif + #ifndef find_next_bit_le static inline unsigned long find_next_bit_le(const void *addr, unsigned @@ -270,11 +288,6 @@ unsigned long find_next_bit_le(const void *addr, unsigned } #endif -#ifndef find_first_zero_bit_le -#define find_first_zero_bit_le(addr, size) \ - find_next_zero_bit_le((addr), (size), 0) -#endif - #else #error "Please fix " #endif -- cgit v1.2.3 From e79864f3164c573afce09ec4b72b75ebe061c14d Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Wed, 14 Sep 2022 19:07:29 -0700 Subject: lib/find_bit: optimize find_next_bit() functions Over the past couple years, the function _find_next_bit() was extended with parameters that modify its behavior to implement and- zero- and le- flavors. The parameters are passed at compile time, but current design prevents a compiler from optimizing out the conditionals. As find_next_bit() API grows, I expect that more parameters will be added. Current design would require more conditional code in _find_next_bit(), which would bloat the helper even more and make it barely readable. This patch replaces _find_next_bit() with a macro FIND_NEXT_BIT, and adds a set of wrappers, so that the compile-time optimizations become possible. The common logic is moved to the new macro, and all flavors may be generated by providing a FETCH macro parameter, like in this example: #define FIND_NEXT_BIT(FETCH, MUNGE, size, start) ... find_next_xornot_and_bit(addr1, addr2, addr3, size, start) { return FIND_NEXT_BIT(addr1[idx] ^ ~addr2[idx] & addr3[idx], /* nop */, size, start); } The FETCH may be of any complexity, as soon as it only refers the bitmap(s) and an iterator idx. MUNGE is here to support _le code generation for BE builds. May be empty. I ran find_bit_benchmark 16 times on top of 6.0-rc2 and 16 times on top of 6.0-rc2 + this series. The results for kvm/x86_64 are: v6.0-rc2 Optimized Difference Z-score Random dense bitmap ns ns ns % find_next_bit: 787735 670546 117189 14.9 3.97 find_next_zero_bit: 777492 664208 113284 14.6 10.51 find_last_bit: 830925 687573 143352 17.3 2.35 find_first_bit: 3874366 3306635 567731 14.7 1.84 find_first_and_bit: 40677125 37739887 2937238 7.2 1.36 find_next_and_bit: 347865 304456 43409 12.5 1.35 Random sparse bitmap find_next_bit: 19816 14021 5795 29.2 6.10 find_next_zero_bit: 1318901 1223794 95107 7.2 1.41 find_last_bit: 14573 13514 1059 7.3 6.92 find_first_bit: 1313321 1249024 64297 4.9 1.53 find_first_and_bit: 8921 8098 823 9.2 4.56 find_next_and_bit: 9796 7176 2620 26.7 5.39 Where the statistics is significant (z-score > 3), the improvement is ~15%. According to the bloat-o-meter, the Image size is 10-11K less: x86_64/defconfig: add/remove: 32/14 grow/shrink: 61/782 up/down: 6344/-16521 (-10177) arm64/defconfig: add/remove: 3/2 grow/shrink: 50/714 up/down: 608/-11556 (-10948) Suggested-by: Linus Torvalds Signed-off-by: Yury Norov --- include/linux/find.h | 23 +++++++++++++++-------- 1 file changed, 15 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/find.h b/include/linux/find.h index 2464bff5de04..dead6f53a97b 100644 --- a/include/linux/find.h +++ b/include/linux/find.h @@ -8,9 +8,12 @@ #include -extern unsigned long _find_next_bit(const unsigned long *addr1, - const unsigned long *addr2, unsigned long nbits, - unsigned long start, unsigned long invert, unsigned long le); +unsigned long _find_next_bit(const unsigned long *addr1, unsigned long nbits, + unsigned long start); +unsigned long _find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long nbits, unsigned long start); +unsigned long _find_next_zero_bit(const unsigned long *addr, unsigned long nbits, + unsigned long start); extern unsigned long _find_first_bit(const unsigned long *addr, unsigned long size); extern unsigned long _find_first_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size); @@ -19,6 +22,10 @@ extern unsigned long _find_last_bit(const unsigned long *addr, unsigned long siz #ifdef __BIG_ENDIAN unsigned long _find_first_zero_bit_le(const unsigned long *addr, unsigned long size); +unsigned long _find_next_zero_bit_le(const unsigned long *addr, unsigned + long size, unsigned long offset); +unsigned long _find_next_bit_le(const unsigned long *addr, unsigned + long size, unsigned long offset); #endif #ifndef find_next_bit @@ -45,7 +52,7 @@ unsigned long find_next_bit(const unsigned long *addr, unsigned long size, return val ? __ffs(val) : size; } - return _find_next_bit(addr, NULL, size, offset, 0UL, 0); + return _find_next_bit(addr, size, offset); } #endif @@ -75,7 +82,7 @@ unsigned long find_next_and_bit(const unsigned long *addr1, return val ? __ffs(val) : size; } - return _find_next_bit(addr1, addr2, size, offset, 0UL, 0); + return _find_next_and_bit(addr1, addr2, size, offset); } #endif @@ -103,7 +110,7 @@ unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, return val == ~0UL ? size : ffz(val); } - return _find_next_bit(addr, NULL, size, offset, ~0UL, 0); + return _find_next_zero_bit(addr, size, offset); } #endif @@ -251,7 +258,7 @@ unsigned long find_next_zero_bit_le(const void *addr, unsigned return val == ~0UL ? size : ffz(val); } - return _find_next_bit(addr, NULL, size, offset, ~0UL, 1); + return _find_next_zero_bit_le(addr, size, offset); } #endif @@ -284,7 +291,7 @@ unsigned long find_next_bit_le(const void *addr, unsigned return val ? __ffs(val) : size; } - return _find_next_bit(addr, NULL, size, offset, 0UL, 1); + return _find_next_bit_le(addr, size, offset); } #endif -- cgit v1.2.3 From cb9ff3f3b84c95867856c3be42de73972feb1249 Mon Sep 17 00:00:00 2001 From: Kevin Tian Date: Wed, 21 Sep 2022 18:43:47 +0800 Subject: vfio: Add helpers for unifying vfio_device life cycle The idea is to let vfio core manage the vfio_device life cycle instead of duplicating the logic cross drivers. This is also a preparatory step for adding struct device into vfio_device. New pair of helpers together with a kref in vfio_device: - vfio_alloc_device() - vfio_put_device() Drivers can register @init/@release callbacks to manage any private state wrapping the vfio_device. However vfio-ccw doesn't fit this model due to a life cycle mess that its private structure mixes both parent and mdev info hence must be allocated/freed outside of the life cycle of vfio device. Per prior discussions this won't be fixed in short term by IBM folks. Instead of waiting for those modifications introduce another helper vfio_init_device() so ccw can call it to initialize a pre-allocated vfio_device. Further implication of the ccw trick is that vfio_device cannot be freed uniformly in vfio core. Instead, require *EVERY* driver to implement @release and free vfio_device inside. Then ccw can choose to delay the free at its own discretion. Another trick down the road is that kvzalloc() is used to accommodate the need of gvt which uses vzalloc() while all others use kzalloc(). So drivers should call a helper vfio_free_device() to free the vfio_device instead of assuming that kfree() or vfree() is appliable. Later once the ccw mess is fixed we can remove those tricks and fully handle structure alloc/free in vfio core. Existing vfio_{un}init_group_dev() will be deprecated after all existing usages are converted to the new model. Suggested-by: Jason Gunthorpe Co-developed-by: Yi Liu Signed-off-by: Yi Liu Signed-off-by: Kevin Tian Reviewed-by: Tony Krowiak Reviewed-by: Jason Gunthorpe Reviewed-by: Eric Auger Link: https://lore.kernel.org/r/20220921104401.38898-2-kevin.tian@intel.com Signed-off-by: Alex Williamson --- include/linux/vfio.h | 25 ++++++++++++++++++++++++- 1 file changed, 24 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 0e2826559091..f67cac700e6f 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -47,7 +47,8 @@ struct vfio_device { struct kvm *kvm; /* Members below here are private, not for driver use */ - refcount_t refcount; + struct kref kref; /* object life cycle */ + refcount_t refcount; /* user count on registered device*/ unsigned int open_count; struct completion comp; struct list_head group_next; @@ -57,6 +58,8 @@ struct vfio_device { /** * struct vfio_device_ops - VFIO bus driver device callbacks * + * @init: initialize private fields in device structure + * @release: Reclaim private fields in device structure * @open_device: Called when the first file descriptor is opened for this device * @close_device: Opposite of open_device * @read: Perform read(2) on device file descriptor @@ -74,6 +77,8 @@ struct vfio_device { */ struct vfio_device_ops { char *name; + int (*init)(struct vfio_device *vdev); + void (*release)(struct vfio_device *vdev); int (*open_device)(struct vfio_device *vdev); void (*close_device)(struct vfio_device *vdev); ssize_t (*read)(struct vfio_device *vdev, char __user *buf, @@ -161,6 +166,24 @@ static inline int vfio_check_feature(u32 flags, size_t argsz, u32 supported_ops, return 1; } +struct vfio_device *_vfio_alloc_device(size_t size, struct device *dev, + const struct vfio_device_ops *ops); +#define vfio_alloc_device(dev_struct, member, dev, ops) \ + container_of(_vfio_alloc_device(sizeof(struct dev_struct) + \ + BUILD_BUG_ON_ZERO(offsetof( \ + struct dev_struct, member)), \ + dev, ops), \ + struct dev_struct, member) + +int vfio_init_device(struct vfio_device *device, struct device *dev, + const struct vfio_device_ops *ops); +void vfio_free_device(struct vfio_device *device); +void vfio_device_release(struct kref *kref); +static inline void vfio_put_device(struct vfio_device *device) +{ + kref_put(&device->kref, vfio_device_release); +} + void vfio_init_group_dev(struct vfio_device *device, struct device *dev, const struct vfio_device_ops *ops); void vfio_uninit_group_dev(struct vfio_device *device); -- cgit v1.2.3 From 63d7c77989de98d3e92611dbb858028b74dca377 Mon Sep 17 00:00:00 2001 From: Yi Liu Date: Wed, 21 Sep 2022 18:43:48 +0800 Subject: vfio/pci: Use the new device life cycle helpers Also introduce two pci core helpers as @init/@release for pci drivers: - vfio_pci_core_init_dev() - vfio_pci_core_release_dev() Signed-off-by: Yi Liu Signed-off-by: Kevin Tian Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20220921104401.38898-3-kevin.tian@intel.com Signed-off-by: Alex Williamson --- include/linux/vfio_pci_core.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index 089b603bcfdc..0499ea836058 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -109,6 +109,8 @@ void vfio_pci_core_close_device(struct vfio_device *core_vdev); void vfio_pci_core_init_device(struct vfio_pci_core_device *vdev, struct pci_dev *pdev, const struct vfio_device_ops *vfio_pci_ops); +int vfio_pci_core_init_dev(struct vfio_device *core_vdev); +void vfio_pci_core_release_dev(struct vfio_device *core_vdev); int vfio_pci_core_register_device(struct vfio_pci_core_device *vdev); void vfio_pci_core_uninit_device(struct vfio_pci_core_device *vdev); void vfio_pci_core_unregister_device(struct vfio_pci_core_device *vdev); -- cgit v1.2.3 From 27aeb915595b87165a3004aab05b2b837d01e6ed Mon Sep 17 00:00:00 2001 From: Yi Liu Date: Wed, 21 Sep 2022 18:43:50 +0800 Subject: vfio/hisi_acc: Use the new device life cycle helpers Tidy up @probe so all migration specific initialization logic is moved to migration specific @init callback. Remove vfio_pci_core_{un}init_device() given no user now. Signed-off-by: Yi Liu Signed-off-by: Kevin Tian Reviewed-by: Jason Gunthorpe Reviewed-by: Shameer Kolothum Link: https://lore.kernel.org/r/20220921104401.38898-5-kevin.tian@intel.com Signed-off-by: Alex Williamson --- include/linux/vfio_pci_core.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index 0499ea836058..367fd79226a3 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -106,13 +106,9 @@ int vfio_pci_core_register_dev_region(struct vfio_pci_core_device *vdev, void vfio_pci_core_set_params(bool nointxmask, bool is_disable_vga, bool is_disable_idle_d3); void vfio_pci_core_close_device(struct vfio_device *core_vdev); -void vfio_pci_core_init_device(struct vfio_pci_core_device *vdev, - struct pci_dev *pdev, - const struct vfio_device_ops *vfio_pci_ops); int vfio_pci_core_init_dev(struct vfio_device *core_vdev); void vfio_pci_core_release_dev(struct vfio_device *core_vdev); int vfio_pci_core_register_device(struct vfio_pci_core_device *vdev); -void vfio_pci_core_uninit_device(struct vfio_pci_core_device *vdev); void vfio_pci_core_unregister_device(struct vfio_pci_core_device *vdev); extern const struct pci_error_handlers vfio_pci_core_err_handlers; int vfio_pci_core_sriov_configure(struct vfio_pci_core_device *vdev, -- cgit v1.2.3 From ebb72b765fb49685c4603d2bff47a4ab5d2580a9 Mon Sep 17 00:00:00 2001 From: Kevin Tian Date: Wed, 21 Sep 2022 18:43:59 +0800 Subject: vfio/ccw: Use the new device life cycle helpers ccw is the only exception which cannot use vfio_alloc_device() because its private device structure is designed to serve both mdev and parent. Life cycle of the parent is managed by css_driver so vfio_ccw_private must be allocated/freed in css_driver probe/remove path instead of conforming to vfio core life cycle for mdev. Given that use a wait/completion scheme so the mdev remove path waits after vfio_put_device() until receiving a completion notification from @release. The completion indicates that all active references on vfio_device have been released. After that point although free of vfio_ccw_private is delayed to css_driver it's at least guaranteed to have no parallel reference on released vfio device part from other code paths. memset() in @probe is removed. vfio_device is either already cleared when probed for the first time or cleared in @release from last probe. The right fix is to introduce separate structures for mdev and parent, but this won't happen in short term per prior discussions. Remove vfio_init/uninit_group_dev() as no user now. Suggested-by: Jason Gunthorpe Signed-off-by: Kevin Tian Reviewed-by: Jason Gunthorpe Reviewed-by: Eric Farman Link: https://lore.kernel.org/r/20220921104401.38898-14-kevin.tian@intel.com Signed-off-by: Alex Williamson --- include/linux/vfio.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index f67cac700e6f..3cf857b1eec7 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -184,9 +184,6 @@ static inline void vfio_put_device(struct vfio_device *device) kref_put(&device->kref, vfio_device_release); } -void vfio_init_group_dev(struct vfio_device *device, struct device *dev, - const struct vfio_device_ops *ops); -void vfio_uninit_group_dev(struct vfio_device *device); int vfio_register_group_dev(struct vfio_device *device); int vfio_register_emulated_iommu_dev(struct vfio_device *device); void vfio_unregister_group_dev(struct vfio_device *device); -- cgit v1.2.3 From 3c28a76124b25882411f005924be73795b6ef078 Mon Sep 17 00:00:00 2001 From: Yi Liu Date: Wed, 21 Sep 2022 18:44:01 +0800 Subject: vfio: Add struct device to vfio_device and replace kref. With it a 'vfio-dev/vfioX' node is created under the sysfs path of the parent, indicating the device is bound to a vfio driver, e.g.: /sys/devices/pci0000\:6f/0000\:6f\:01.0/vfio-dev/vfio0 It is also a preparatory step toward adding cdev for supporting future device-oriented uAPI. Add Documentation/ABI/testing/sysfs-devices-vfio-dev. Suggested-by: Jason Gunthorpe Signed-off-by: Yi Liu Signed-off-by: Kevin Tian Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20220921104401.38898-16-kevin.tian@intel.com Signed-off-by: Alex Williamson --- include/linux/vfio.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 3cf857b1eec7..ee399a768070 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -47,7 +47,8 @@ struct vfio_device { struct kvm *kvm; /* Members below here are private, not for driver use */ - struct kref kref; /* object life cycle */ + unsigned int index; + struct device device; /* device.kref covers object life circle */ refcount_t refcount; /* user count on registered device*/ unsigned int open_count; struct completion comp; @@ -178,10 +179,9 @@ struct vfio_device *_vfio_alloc_device(size_t size, struct device *dev, int vfio_init_device(struct vfio_device *device, struct device *dev, const struct vfio_device_ops *ops); void vfio_free_device(struct vfio_device *device); -void vfio_device_release(struct kref *kref); static inline void vfio_put_device(struct vfio_device *device) { - kref_put(&device->kref, vfio_device_release); + put_device(&device->device); } int vfio_register_group_dev(struct vfio_device *device); -- cgit v1.2.3 From 22873deac9e7b273bbf17eee515c8170510d861a Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Sat, 24 Sep 2022 06:59:59 +0200 Subject: vfs: add vfs_tmpfile_open() helper This helper unifies tmpfile creation with opening. Existing vfs_tmpfile() callers outside of fs/namei.c will be converted to using this helper. There are two such callers: cachefile and overlayfs. The cachefiles code currently uses the open_with_fake_path() helper to open the tmpfile, presumably to disable accounting of the open file. Overlayfs uses tmpfile for copy_up, which means these struct file instances will be short lived, hence it doesn't really matter if they are accounted or not. Disable accounting in this helper too, which should be okay for both callers. Add MAY_OPEN permission checking for consistency. Like for create(2) read/write permissions are not checked. Reviewed-by: Christian Brauner (Microsoft) Signed-off-by: Miklos Szeredi --- include/linux/fs.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 9eced4cc286e..15fafda95dd3 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2007,6 +2007,10 @@ static inline int vfs_whiteout(struct user_namespace *mnt_userns, struct dentry *vfs_tmpfile(struct user_namespace *mnt_userns, struct dentry *dentry, umode_t mode, int open_flag); +struct file *vfs_tmpfile_open(struct user_namespace *mnt_userns, + const struct path *parentpath, + umode_t mode, int open_flag, const struct cred *cred); + int vfs_mkobj(struct dentry *, umode_t, int (*f)(struct dentry *, umode_t, void *), void *); -- cgit v1.2.3 From 3e9d4c593558ea86f49e10e62373a54c7f5a63e4 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Sat, 24 Sep 2022 07:00:00 +0200 Subject: vfs: make vfs_tmpfile() static No callers outside of fs/namei.c anymore. Reviewed-by: Christian Brauner (Microsoft) Signed-off-by: Miklos Szeredi --- include/linux/fs.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 15fafda95dd3..02646542f6bb 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2004,9 +2004,6 @@ static inline int vfs_whiteout(struct user_namespace *mnt_userns, WHITEOUT_DEV); } -struct dentry *vfs_tmpfile(struct user_namespace *mnt_userns, - struct dentry *dentry, umode_t mode, int open_flag); - struct file *vfs_tmpfile_open(struct user_namespace *mnt_userns, const struct path *parentpath, umode_t mode, int open_flag, const struct cred *cred); -- cgit v1.2.3 From 9751b338656f05a0ce918befd5118fcd970c71c6 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Sat, 24 Sep 2022 07:00:00 +0200 Subject: vfs: move open right after ->tmpfile() Create a helper finish_open_simple() that opens the file with the original dentry. Handle the error case here as well to simplify callers. Call this helper right after ->tmpfile() is called. Next patch will change the tmpfile API and move this call into tmpfile instances. Signed-off-by: Miklos Szeredi --- include/linux/fs.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 02646542f6bb..a3c50869e79b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2780,6 +2780,15 @@ extern int finish_open(struct file *file, struct dentry *dentry, int (*open)(struct inode *, struct file *)); extern int finish_no_open(struct file *file, struct dentry *dentry); +/* Helper for the simple case when original dentry is used */ +static inline int finish_open_simple(struct file *file, int error) +{ + if (error) + return error; + + return finish_open(file, file->f_path.dentry, NULL); +} + /* fs/dcache.c */ extern void __init vfs_caches_init_early(void); extern void __init vfs_caches_init(void); -- cgit v1.2.3 From 863f144f12add1f4eab80b70561a90857c524a8b Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Sat, 24 Sep 2022 07:00:00 +0200 Subject: vfs: open inside ->tmpfile() This is in preparation for adding tmpfile support to fuse, which requires that the tmpfile creation and opening are done as a single operation. Replace the 'struct dentry *' argument of i_op->tmpfile with 'struct file *'. Call finish_open_simple() as the last thing in ->tmpfile() instances (may be omitted in the error case). Change d_tmpfile() argument to 'struct file *' as well to make callers more readable. Reviewed-by: Christian Brauner (Microsoft) Signed-off-by: Miklos Szeredi --- include/linux/dcache.h | 3 ++- include/linux/fs.h | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 92c78ed02b54..bde9f8ff8869 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -16,6 +16,7 @@ #include struct path; +struct file; struct vfsmount; /* @@ -250,7 +251,7 @@ extern struct dentry * d_make_root(struct inode *); /* - the ramfs-type tree */ extern void d_genocide(struct dentry *); -extern void d_tmpfile(struct dentry *, struct inode *); +extern void d_tmpfile(struct file *, struct inode *); extern struct dentry *d_find_alias(struct inode *); extern void d_prune_aliases(struct inode *); diff --git a/include/linux/fs.h b/include/linux/fs.h index a3c50869e79b..8218d9964ff8 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2168,7 +2168,7 @@ struct inode_operations { struct file *, unsigned open_flag, umode_t create_mode); int (*tmpfile) (struct user_namespace *, struct inode *, - struct dentry *, umode_t); + struct file *, umode_t); int (*set_acl)(struct user_namespace *, struct inode *, struct posix_acl *, int); int (*fileattr_set)(struct user_namespace *mnt_userns, -- cgit v1.2.3 From 4f58330fcc8482aa90674e1f40f601e82f18ed4a Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Tue, 13 Sep 2022 12:47:20 +0100 Subject: iommu/iova: Fix module config properly IOMMU_IOVA is intended to be an optional library for users to select as and when they desire. Since it can be a module now, this means that built-in code which has chosen not to select it should not fail to link if it happens to have selected as a module by someone else. Replace IS_ENABLED() with IS_REACHABLE() to do the right thing. CC: Thierry Reding Reported-by: John Garry Fixes: 15bbdec3931e ("iommu: Make the iova library a module") Signed-off-by: Robin Murphy Reviewed-by: Thierry Reding Link: https://lore.kernel.org/r/548c2f683ca379aface59639a8f0cccc3a1ac050.1663069227.git.robin.murphy@arm.com Signed-off-by: Joerg Roedel --- include/linux/iova.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iova.h b/include/linux/iova.h index c6ba6d95d79c..83c00fac2acb 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -75,7 +75,7 @@ static inline unsigned long iova_pfn(struct iova_domain *iovad, dma_addr_t iova) return iova >> iova_shift(iovad); } -#if IS_ENABLED(CONFIG_IOMMU_IOVA) +#if IS_REACHABLE(CONFIG_IOMMU_IOVA) int iova_cache_get(void); void iova_cache_put(void); -- cgit v1.2.3 From dc09fe1c5edd9c27a52cb6dc5a7bb4452d45c71c Mon Sep 17 00:00:00 2001 From: Sven Peter Date: Fri, 16 Sep 2022 11:41:51 +0200 Subject: iommu/io-pgtable-dart: Add DART PTE support for t6000 The DARTs present in the M1 Pro/Max/Ultra SoC use a diffent PTE format. They support a 42bit physical address space by shifting the paddr and extending its mask inside the PTE. They also come with mandatory sub-page protection now which we just configure to always allow access to the entire page. This feature is already present but optional on the previous DARTs which allows to unconditionally configure it. Signed-off-by: Sven Peter Co-developed-by: Janne Grunau Signed-off-by: Janne Grunau Reviewed-by: Rob Herring Acked-by: Hector Martin Link: https://lore.kernel.org/r/20220916094152.87137-5-j@jannau.net Signed-off-by: Joerg Roedel --- include/linux/io-pgtable.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index ca98aeadcc80..b768937382cd 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -17,6 +17,7 @@ enum io_pgtable_fmt { ARM_MALI_LPAE, AMD_IOMMU_V1, APPLE_DART, + APPLE_DART2, IO_PGTABLE_NUM_FMTS, }; -- cgit v1.2.3 From 24291caf8447f6fc060c8d00136bdc30ee207f38 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Sat, 17 Sep 2022 20:07:12 -0700 Subject: lib/bitmap: add bitmap_weight_and() The function calculates Hamming weight of (bitmap1 & bitmap2). Now we have to do like this: tmp = bitmap_alloc(nbits); bitmap_and(tmp, map1, map2, nbits); weight = bitmap_weight(tmp, nbits); bitmap_free(tmp); This requires additional memory, adds pressure on alloc subsystem, and way less cache-friendly than just: weight = bitmap_weight_and(map1, map2, nbits); The following patches apply it for cpumask functions. Signed-off-by: Yury Norov --- include/linux/bitmap.h | 12 ++++++++++++ include/linux/cpumask.h | 11 +++++++++++ 2 files changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index f65410a49fda..b2aef45af0db 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -51,6 +51,7 @@ struct device; * bitmap_empty(src, nbits) Are all bits zero in *src? * bitmap_full(src, nbits) Are all bits set in *src? * bitmap_weight(src, nbits) Hamming Weight: number set bits + * bitmap_weight_and(src1, src2, nbits) Hamming Weight of and'ed bitmap * bitmap_set(dst, pos, nbits) Set specified bit area * bitmap_clear(dst, pos, nbits) Clear specified bit area * bitmap_find_next_zero_area(buf, len, pos, n, mask) Find bit free area @@ -164,6 +165,8 @@ bool __bitmap_intersects(const unsigned long *bitmap1, bool __bitmap_subset(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); unsigned int __bitmap_weight(const unsigned long *bitmap, unsigned int nbits); +unsigned int __bitmap_weight_and(const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int nbits); void __bitmap_set(unsigned long *map, unsigned int start, int len); void __bitmap_clear(unsigned long *map, unsigned int start, int len); @@ -439,6 +442,15 @@ unsigned int bitmap_weight(const unsigned long *src, unsigned int nbits) return __bitmap_weight(src, nbits); } +static __always_inline +unsigned long bitmap_weight_and(const unsigned long *src1, + const unsigned long *src2, unsigned int nbits) +{ + if (small_const_nbits(nbits)) + return hweight_long(*src1 & *src2 & BITMAP_LAST_WORD_MASK(nbits)); + return __bitmap_weight_and(src1, src2, nbits); +} + static __always_inline void bitmap_set(unsigned long *map, unsigned int start, unsigned int nbits) { diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 1b442fb2001f..9a71af8097ca 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -586,6 +586,17 @@ static inline unsigned int cpumask_weight(const struct cpumask *srcp) return bitmap_weight(cpumask_bits(srcp), nr_cpumask_bits); } +/** + * cpumask_weight_and - Count of bits in (*srcp1 & *srcp2) + * @srcp1: the cpumask to count bits (< nr_cpu_ids) in. + * @srcp2: the cpumask to count bits (< nr_cpu_ids) in. + */ +static inline unsigned int cpumask_weight_and(const struct cpumask *srcp1, + const struct cpumask *srcp2) +{ + return bitmap_weight_and(cpumask_bits(srcp1), cpumask_bits(srcp2), nr_cpumask_bits); +} + /** * cpumask_shift_right - *dstp = *srcp >> n * @dstp: the cpumask result -- cgit v1.2.3 From 3cea8d475327756066e2a54f0b651bb7284dd448 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Sat, 17 Sep 2022 20:07:13 -0700 Subject: lib: add find_nth{,_and,_andnot}_bit() Kernel lacks for a function that searches for Nth bit in a bitmap. Usually people do it like this: for_each_set_bit(bit, mask, size) if (n-- == 0) return bit; We can do it more efficiently, if we: 1. find a word containing Nth bit, using hweight(); and 2. find the bit, using a helper fns(), that works similarly to __ffs() and ffz(). fns() is implemented as a simple loop. For x86_64, there's PDEP instruction to do that: ret = clz(pdep(1 << idx, num)). However, for large bitmaps the most of improvement comes from using hweight(), so I kept fns() simple. New find_nth_bit() is ~70 times faster on x86_64/kvm in find_bit benchmark: find_nth_bit: 7154190 ns, 16411 iterations for_each_bit: 505493126 ns, 16315 iterations With all that, a family of 3 new functions is added, and used where appropriate in the following patches. Signed-off-by: Yury Norov --- include/linux/bitops.h | 19 +++++++++++ include/linux/find.h | 86 ++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 105 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 3b89c64bcfd8..d7dd83fafeba 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -247,6 +247,25 @@ static inline unsigned long __ffs64(u64 word) return __ffs((unsigned long)word); } +/** + * fns - find N'th set bit in a word + * @word: The word to search + * @n: Bit to find + */ +static inline unsigned long fns(unsigned long word, unsigned int n) +{ + unsigned int bit; + + while (word) { + bit = __ffs(word); + if (n-- == 0) + return bit; + __clear_bit(bit, &word); + } + + return BITS_PER_LONG; +} + /** * assign_bit - Assign value to a bit in memory * @nr: the bit to set diff --git a/include/linux/find.h b/include/linux/find.h index dead6f53a97b..b100944daba0 100644 --- a/include/linux/find.h +++ b/include/linux/find.h @@ -15,6 +15,11 @@ unsigned long _find_next_and_bit(const unsigned long *addr1, const unsigned long unsigned long _find_next_zero_bit(const unsigned long *addr, unsigned long nbits, unsigned long start); extern unsigned long _find_first_bit(const unsigned long *addr, unsigned long size); +unsigned long __find_nth_bit(const unsigned long *addr, unsigned long size, unsigned long n); +unsigned long __find_nth_and_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long size, unsigned long n); +unsigned long __find_nth_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long size, unsigned long n); extern unsigned long _find_first_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size); extern unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size); @@ -136,6 +141,87 @@ unsigned long find_first_bit(const unsigned long *addr, unsigned long size) } #endif +/** + * find_nth_bit - find N'th set bit in a memory region + * @addr: The address to start the search at + * @size: The maximum number of bits to search + * @n: The number of set bit, which position is needed, counting from 0 + * + * The following is semantically equivalent: + * idx = find_nth_bit(addr, size, 0); + * idx = find_first_bit(addr, size); + * + * Returns the bit number of the N'th set bit. + * If no such, returns @size. + */ +static inline +unsigned long find_nth_bit(const unsigned long *addr, unsigned long size, unsigned long n) +{ + if (n >= size) + return size; + + if (small_const_nbits(size)) { + unsigned long val = *addr & GENMASK(size - 1, 0); + + return val ? fns(val, n) : size; + } + + return __find_nth_bit(addr, size, n); +} + +/** + * find_nth_and_bit - find N'th set bit in 2 memory regions + * @addr1: The 1st address to start the search at + * @addr2: The 2nd address to start the search at + * @size: The maximum number of bits to search + * @n: The number of set bit, which position is needed, counting from 0 + * + * Returns the bit number of the N'th set bit. + * If no such, returns @size. + */ +static inline +unsigned long find_nth_and_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long size, unsigned long n) +{ + if (n >= size) + return size; + + if (small_const_nbits(size)) { + unsigned long val = *addr1 & *addr2 & GENMASK(size - 1, 0); + + return val ? fns(val, n) : size; + } + + return __find_nth_and_bit(addr1, addr2, size, n); +} + +/** + * find_nth_andnot_bit - find N'th set bit in 2 memory regions, + * flipping bits in 2nd region + * @addr1: The 1st address to start the search at + * @addr2: The 2nd address to start the search at + * @size: The maximum number of bits to search + * @n: The number of set bit, which position is needed, counting from 0 + * + * Returns the bit number of the N'th set bit. + * If no such, returns @size. + */ +static inline +unsigned long find_nth_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long size, unsigned long n) +{ + if (n >= size) + return size; + + if (small_const_nbits(size)) { + unsigned long val = *addr1 & (~*addr2) & GENMASK(size - 1, 0); + + return val ? fns(val, n) : size; + } + + return __find_nth_andnot_bit(addr1, addr2, size, n); +} + #ifndef find_first_and_bit /** * find_first_and_bit - find the first set bit in both memory regions -- cgit v1.2.3 From 97848c10f9f8a8ce4296b149d06cab424eba05b3 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Sat, 17 Sep 2022 20:07:15 -0700 Subject: lib/bitmap: remove bitmap_ord_to_pos Now that we have find_nth_bit(), we can drop bitmap_ord_to_pos(). Signed-off-by: Yury Norov --- include/linux/bitmap.h | 1 - include/linux/nodemask.h | 3 +-- 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index b2aef45af0db..7d6d73b78147 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -225,7 +225,6 @@ void bitmap_copy_le(unsigned long *dst, const unsigned long *src, unsigned int n #else #define bitmap_copy_le bitmap_copy #endif -unsigned int bitmap_ord_to_pos(const unsigned long *bitmap, unsigned int ord, unsigned int nbits); int bitmap_print_to_pagebuf(bool list, char *buf, const unsigned long *maskp, int nmaskbits); diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 4b71a96190a8..0c45fb066caa 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -508,8 +508,7 @@ static inline int node_random(const nodemask_t *maskp) w = nodes_weight(*maskp); if (w) - bit = bitmap_ord_to_pos(maskp->bits, - get_random_int() % w, MAX_NUMNODES); + bit = find_nth_bit(maskp->bits, MAX_NUMNODES, get_random_int() % w); return bit; #else return 0; -- cgit v1.2.3 From 944c417daeb63fa345fe0f754c57a5a23ca6d701 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Sat, 17 Sep 2022 20:07:16 -0700 Subject: cpumask: add cpumask_nth_{,and,andnot} Add cpumask_nth_{,and,andnot} as wrappers around corresponding find functions, and use it in cpumask_local_spread(). Signed-off-by: Yury Norov --- include/linux/cpumask.h | 44 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 44 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 9a71af8097ca..e4f9136a4a63 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -337,6 +337,50 @@ unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) return i; } +/** + * cpumask_nth - get the first cpu in a cpumask + * @srcp: the cpumask pointer + * @cpu: the N'th cpu to find, starting from 0 + * + * Returns >= nr_cpu_ids if such cpu doesn't exist. + */ +static inline unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *srcp) +{ + return find_nth_bit(cpumask_bits(srcp), nr_cpumask_bits, cpumask_check(cpu)); +} + +/** + * cpumask_nth_and - get the first cpu in 2 cpumasks + * @srcp1: the cpumask pointer + * @srcp2: the cpumask pointer + * @cpu: the N'th cpu to find, starting from 0 + * + * Returns >= nr_cpu_ids if such cpu doesn't exist. + */ +static inline +unsigned int cpumask_nth_and(unsigned int cpu, const struct cpumask *srcp1, + const struct cpumask *srcp2) +{ + return find_nth_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), + nr_cpumask_bits, cpumask_check(cpu)); +} + +/** + * cpumask_nth_andnot - get the first cpu set in 1st cpumask, and clear in 2nd. + * @srcp1: the cpumask pointer + * @srcp2: the cpumask pointer + * @cpu: the N'th cpu to find, starting from 0 + * + * Returns >= nr_cpu_ids if such cpu doesn't exist. + */ +static inline +unsigned int cpumask_nth_andnot(unsigned int cpu, const struct cpumask *srcp1, + const struct cpumask *srcp2) +{ + return find_nth_andnot_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), + nr_cpumask_bits, cpumask_check(cpu)); +} + #define CPU_BITS_NONE \ { \ [0 ... BITS_TO_LONGS(NR_CPUS)-1] = 0UL \ -- cgit v1.2.3 From 21c9e90ab9a4c991d21dd15cc5163c99a885d4a8 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Tue, 30 Aug 2022 20:36:01 +0800 Subject: mm, hwpoison: use num_poisoned_pages_sub() to decrease num_poisoned_pages Use num_poisoned_pages_sub() to combine multiple atomic ops into one. Also num_poisoned_pages_dec() can be killed as there's no caller now. Link: https://lkml.kernel.org/r/20220830123604.25763-4-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Acked-by: Naoya Horiguchi Signed-off-by: Andrew Morton --- include/linux/swapops.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swapops.h b/include/linux/swapops.h index a3d435bf9f97..88825d1785d2 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -485,11 +485,6 @@ static inline void num_poisoned_pages_inc(void) atomic_long_inc(&num_poisoned_pages); } -static inline void num_poisoned_pages_dec(void) -{ - atomic_long_dec(&num_poisoned_pages); -} - static inline void num_poisoned_pages_sub(long i) { atomic_long_sub(i, &num_poisoned_pages); -- cgit v1.2.3 From eba4d770efc86a3710e36b828190858abfa3bb74 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 11 Aug 2022 12:13:26 -0400 Subject: mm/swap: comment all the ifdef in swapops.h swapops.h contains quite a few layers of ifdef, some of the "else" and "endif" doesn't get proper comment on the macro so it's hard to follow on what are they referring to. Add the comments. Link: https://lkml.kernel.org/r/20220811161331.37055-3-peterx@redhat.com Signed-off-by: Peter Xu Suggested-by: Nadav Amit Reviewed-by: Huang Ying Reviewed-by: Alistair Popple Cc: Andi Kleen Cc: Andrea Arcangeli Cc: David Hildenbrand Cc: Hugh Dickins Cc: "Kirill A . Shutemov" Cc: Minchan Kim Cc: Vlastimil Babka Cc: Dave Hansen Signed-off-by: Andrew Morton --- include/linux/swapops.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 88825d1785d2..7d1b74046520 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -247,8 +247,8 @@ extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, #ifdef CONFIG_HUGETLB_PAGE extern void __migration_entry_wait_huge(pte_t *ptep, spinlock_t *ptl); extern void migration_entry_wait_huge(struct vm_area_struct *vma, pte_t *pte); -#endif -#else +#endif /* CONFIG_HUGETLB_PAGE */ +#else /* CONFIG_MIGRATION */ static inline swp_entry_t make_readable_migration_entry(pgoff_t offset) { return swp_entry(0, 0); @@ -276,7 +276,7 @@ static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, #ifdef CONFIG_HUGETLB_PAGE static inline void __migration_entry_wait_huge(pte_t *ptep, spinlock_t *ptl) { } static inline void migration_entry_wait_huge(struct vm_area_struct *vma, pte_t *pte) { } -#endif +#endif /* CONFIG_HUGETLB_PAGE */ static inline int is_writable_migration_entry(swp_entry_t entry) { return 0; @@ -286,7 +286,7 @@ static inline int is_readable_migration_entry(swp_entry_t entry) return 0; } -#endif +#endif /* CONFIG_MIGRATION */ typedef unsigned long pte_marker; @@ -426,7 +426,7 @@ static inline int is_pmd_migration_entry(pmd_t pmd) { return is_swap_pmd(pmd) && is_migration_entry(pmd_to_swp_entry(pmd)); } -#else +#else /* CONFIG_ARCH_ENABLE_THP_MIGRATION */ static inline int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, struct page *page) { @@ -455,7 +455,7 @@ static inline int is_pmd_migration_entry(pmd_t pmd) { return 0; } -#endif +#endif /* CONFIG_ARCH_ENABLE_THP_MIGRATION */ #ifdef CONFIG_MEMORY_FAILURE @@ -490,7 +490,7 @@ static inline void num_poisoned_pages_sub(long i) atomic_long_sub(i, &num_poisoned_pages); } -#else +#else /* CONFIG_MEMORY_FAILURE */ static inline swp_entry_t make_hwpoison_entry(struct page *page) { @@ -509,7 +509,7 @@ static inline void num_poisoned_pages_inc(void) static inline void num_poisoned_pages_sub(long i) { } -#endif +#endif /* CONFIG_MEMORY_FAILURE */ static inline int non_swap_entry(swp_entry_t entry) { -- cgit v1.2.3 From 0d206b5d2e0d7d7f09ac9540e3ab3e35a34f536e Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 11 Aug 2022 12:13:27 -0400 Subject: mm/swap: add swp_offset_pfn() to fetch PFN from swap entry We've got a bunch of special swap entries that stores PFN inside the swap offset fields. To fetch the PFN, normally the user just calls swp_offset() assuming that'll be the PFN. Add a helper swp_offset_pfn() to fetch the PFN instead, fetching only the max possible length of a PFN on the host, meanwhile doing proper check with MAX_PHYSMEM_BITS to make sure the swap offsets can actually store the PFNs properly always using the BUILD_BUG_ON() in is_pfn_swap_entry(). One reason to do so is we never tried to sanitize whether swap offset can really fit for storing PFN. At the meantime, this patch also prepares us with the future possibility to store more information inside the swp offset field, so assuming "swp_offset(entry)" to be the PFN will not stand any more very soon. Replace many of the swp_offset() callers to use swp_offset_pfn() where proper. Note that many of the existing users are not candidates for the replacement, e.g.: (1) When the swap entry is not a pfn swap entry at all, or, (2) when we wanna keep the whole swp_offset but only change the swp type. For the latter, it can happen when fork() triggered on a write-migration swap entry pte, we may want to only change the migration type from write->read but keep the rest, so it's not "fetching PFN" but "changing swap type only". They're left aside so that when there're more information within the swp offset they'll be carried over naturally in those cases. Since at it, dropping hwpoison_entry_to_pfn() because that's exactly what the new swp_offset_pfn() is about. Link: https://lkml.kernel.org/r/20220811161331.37055-4-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: "Huang, Ying" Cc: Alistair Popple Cc: Andi Kleen Cc: Andrea Arcangeli Cc: David Hildenbrand Cc: Hugh Dickins Cc: "Kirill A . Shutemov" Cc: Minchan Kim Cc: Nadav Amit Cc: Vlastimil Babka Cc: Dave Hansen Signed-off-by: Andrew Morton --- include/linux/swapops.h | 35 +++++++++++++++++++++++++++++------ 1 file changed, 29 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 7d1b74046520..578212fbf2be 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -23,6 +23,20 @@ #define SWP_TYPE_SHIFT (BITS_PER_XA_VALUE - MAX_SWAPFILES_SHIFT) #define SWP_OFFSET_MASK ((1UL << SWP_TYPE_SHIFT) - 1) +/* + * Definitions only for PFN swap entries (see is_pfn_swap_entry()). To + * store PFN, we only need SWP_PFN_BITS bits. Each of the pfn swap entries + * can use the extra bits to store other information besides PFN. + */ +#ifdef MAX_PHYSMEM_BITS +#define SWP_PFN_BITS (MAX_PHYSMEM_BITS - PAGE_SHIFT) +#else /* MAX_PHYSMEM_BITS */ +#define SWP_PFN_BITS (BITS_PER_LONG - PAGE_SHIFT) +#endif /* MAX_PHYSMEM_BITS */ +#define SWP_PFN_MASK (BIT(SWP_PFN_BITS) - 1) + +static inline bool is_pfn_swap_entry(swp_entry_t entry); + /* Clear all flags but only keep swp_entry_t related information */ static inline pte_t pte_swp_clear_flags(pte_t pte) { @@ -64,6 +78,17 @@ static inline pgoff_t swp_offset(swp_entry_t entry) return entry.val & SWP_OFFSET_MASK; } +/* + * This should only be called upon a pfn swap entry to get the PFN stored + * in the swap entry. Please refers to is_pfn_swap_entry() for definition + * of pfn swap entry. + */ +static inline unsigned long swp_offset_pfn(swp_entry_t entry) +{ + VM_BUG_ON(!is_pfn_swap_entry(entry)); + return swp_offset(entry) & SWP_PFN_MASK; +} + /* check whether a pte points to a swap entry */ static inline int is_swap_pte(pte_t pte) { @@ -369,7 +394,7 @@ static inline int pte_none_mostly(pte_t pte) static inline struct page *pfn_swap_entry_to_page(swp_entry_t entry) { - struct page *p = pfn_to_page(swp_offset(entry)); + struct page *p = pfn_to_page(swp_offset_pfn(entry)); /* * Any use of migration entries may only occur while the @@ -387,6 +412,9 @@ static inline struct page *pfn_swap_entry_to_page(swp_entry_t entry) */ static inline bool is_pfn_swap_entry(swp_entry_t entry) { + /* Make sure the swp offset can always store the needed fields */ + BUILD_BUG_ON(SWP_TYPE_SHIFT < SWP_PFN_BITS); + return is_migration_entry(entry) || is_device_private_entry(entry) || is_device_exclusive_entry(entry); } @@ -475,11 +503,6 @@ static inline int is_hwpoison_entry(swp_entry_t entry) return swp_type(entry) == SWP_HWPOISON; } -static inline unsigned long hwpoison_entry_to_pfn(swp_entry_t entry) -{ - return swp_offset(entry); -} - static inline void num_poisoned_pages_inc(void) { atomic_long_inc(&num_poisoned_pages); -- cgit v1.2.3 From 2e3468778dbe3ec389a10c21a703bb8e5be5cfbc Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 11 Aug 2022 12:13:29 -0400 Subject: mm: remember young/dirty bit for page migrations When page migration happens, we always ignore the young/dirty bit settings in the old pgtable, and marking the page as old in the new page table using either pte_mkold() or pmd_mkold(), and keeping the pte clean. That's fine from functional-wise, but that's not friendly to page reclaim because the moving page can be actively accessed within the procedure. Not to mention hardware setting the young bit can bring quite some overhead on some systems, e.g. x86_64 needs a few hundreds nanoseconds to set the bit. The same slowdown problem to dirty bits when the memory is first written after page migration happened. Actually we can easily remember the A/D bit configuration and recover the information after the page is migrated. To achieve it, define a new set of bits in the migration swap offset field to cache the A/D bits for old pte. Then when removing/recovering the migration entry, we can recover the A/D bits even if the page changed. One thing to mention is that here we used max_swapfile_size() to detect how many swp offset bits we have, and we'll only enable this feature if we know the swp offset is big enough to store both the PFN value and the A/D bits. Otherwise the A/D bits are dropped like before. Link: https://lkml.kernel.org/r/20220811161331.37055-6-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: "Huang, Ying" Cc: Alistair Popple Cc: Andi Kleen Cc: Andrea Arcangeli Cc: David Hildenbrand Cc: Hugh Dickins Cc: "Kirill A . Shutemov" Cc: Minchan Kim Cc: Nadav Amit Cc: Vlastimil Babka Cc: Dave Hansen Signed-off-by: Andrew Morton --- include/linux/swapops.h | 99 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 99 insertions(+) (limited to 'include/linux') diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 578212fbf2be..11b874f212a2 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -8,6 +8,10 @@ #ifdef CONFIG_MMU +#ifdef CONFIG_SWAP +#include +#endif /* CONFIG_SWAP */ + /* * swapcache pages are stored in the swapper_space radix tree. We want to * get good packing density in that tree, so the index should be dense in @@ -35,6 +39,31 @@ #endif /* MAX_PHYSMEM_BITS */ #define SWP_PFN_MASK (BIT(SWP_PFN_BITS) - 1) +/** + * Migration swap entry specific bitfield definitions. Layout: + * + * |----------+--------------------| + * | swp_type | swp_offset | + * |----------+--------+-+-+-------| + * | | resv |D|A| PFN | + * |----------+--------+-+-+-------| + * + * @SWP_MIG_YOUNG_BIT: Whether the page used to have young bit set (bit A) + * @SWP_MIG_DIRTY_BIT: Whether the page used to have dirty bit set (bit D) + * + * Note: A/D bits will be stored in migration entries iff there're enough + * free bits in arch specific swp offset. By default we'll ignore A/D bits + * when migrating a page. Please refer to migration_entry_supports_ad() + * for more information. If there're more bits besides PFN and A/D bits, + * they should be reserved and always be zeros. + */ +#define SWP_MIG_YOUNG_BIT (SWP_PFN_BITS) +#define SWP_MIG_DIRTY_BIT (SWP_PFN_BITS + 1) +#define SWP_MIG_TOTAL_BITS (SWP_PFN_BITS + 2) + +#define SWP_MIG_YOUNG BIT(SWP_MIG_YOUNG_BIT) +#define SWP_MIG_DIRTY BIT(SWP_MIG_DIRTY_BIT) + static inline bool is_pfn_swap_entry(swp_entry_t entry); /* Clear all flags but only keep swp_entry_t related information */ @@ -265,6 +294,57 @@ static inline swp_entry_t make_writable_migration_entry(pgoff_t offset) return swp_entry(SWP_MIGRATION_WRITE, offset); } +/* + * Returns whether the host has large enough swap offset field to support + * carrying over pgtable A/D bits for page migrations. The result is + * pretty much arch specific. + */ +static inline bool migration_entry_supports_ad(void) +{ + /* + * max_swapfile_size() returns the max supported swp-offset plus 1. + * We can support the migration A/D bits iff the pfn swap entry has + * the offset large enough to cover all of them (PFN, A & D bits). + */ +#ifdef CONFIG_SWAP + return max_swapfile_size() >= (1UL << SWP_MIG_TOTAL_BITS); +#else /* CONFIG_SWAP */ + return false; +#endif /* CONFIG_SWAP */ +} + +static inline swp_entry_t make_migration_entry_young(swp_entry_t entry) +{ + if (migration_entry_supports_ad()) + return swp_entry(swp_type(entry), + swp_offset(entry) | SWP_MIG_YOUNG); + return entry; +} + +static inline bool is_migration_entry_young(swp_entry_t entry) +{ + if (migration_entry_supports_ad()) + return swp_offset(entry) & SWP_MIG_YOUNG; + /* Keep the old behavior of aging page after migration */ + return false; +} + +static inline swp_entry_t make_migration_entry_dirty(swp_entry_t entry) +{ + if (migration_entry_supports_ad()) + return swp_entry(swp_type(entry), + swp_offset(entry) | SWP_MIG_DIRTY); + return entry; +} + +static inline bool is_migration_entry_dirty(swp_entry_t entry) +{ + if (migration_entry_supports_ad()) + return swp_offset(entry) & SWP_MIG_DIRTY; + /* Keep the old behavior of clean page after migration */ + return false; +} + extern void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, spinlock_t *ptl); extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, @@ -311,6 +391,25 @@ static inline int is_readable_migration_entry(swp_entry_t entry) return 0; } +static inline swp_entry_t make_migration_entry_young(swp_entry_t entry) +{ + return entry; +} + +static inline bool is_migration_entry_young(swp_entry_t entry) +{ + return false; +} + +static inline swp_entry_t make_migration_entry_dirty(swp_entry_t entry) +{ + return entry; +} + +static inline bool is_migration_entry_dirty(swp_entry_t entry) +{ + return false; +} #endif /* CONFIG_MIGRATION */ typedef unsigned long pte_marker; -- cgit v1.2.3 From be45a4902c7caa717fee6b2f671e59b396ed395c Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 11 Aug 2022 12:13:30 -0400 Subject: mm/swap: cache maximum swapfile size when init swap We used to have swapfile_maximum_size() fetching a maximum value of swapfile size per-arch. As the caller of max_swapfile_size() grows, this patch introduce a variable "swapfile_maximum_size" and cache the value of old max_swapfile_size(), so that we don't need to calculate the value every time. Caching the value in swapfile_init() is safe because when reaching the phase we should have initialized all the relevant information. Here the major arch to take care of is x86, which defines the max swapfile size based on L1TF mitigation. Here both X86_BUG_L1TF or l1tf_mitigation should have been setup properly when reaching swapfile_init(). As a reference, the code path looks like this for x86: - start_kernel - setup_arch - early_cpu_init - early_identify_cpu --> setup X86_BUG_L1TF - parse_early_param - l1tf_cmdline --> set l1tf_mitigation - check_bugs - l1tf_select_mitigation --> set l1tf_mitigation - arch_call_rest_init - rest_init - kernel_init - kernel_init_freeable - do_basic_setup - do_initcalls --> calls swapfile_init() (initcall level 4) The swapfile size only depends on swp pte format on non-x86 archs, so caching it is safe too. Since at it, rename max_swapfile_size() to arch_max_swapfile_size() because arch can define its own function, so it's more straightforward to have "arch_" as its prefix. At the meantime, export swapfile_maximum_size to replace the old usages of max_swapfile_size(). [peterx@redhat.com: declare arch_max_swapfile_size) in swapfile.h] Link: https://lkml.kernel.org/r/YxTh1GuC6ro5fKL5@xz-m1.local Link: https://lkml.kernel.org/r/20220811161331.37055-7-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: "Huang, Ying" Cc: Alistair Popple Cc: Andi Kleen Cc: Andrea Arcangeli Cc: David Hildenbrand Cc: Hugh Dickins Cc: "Kirill A . Shutemov" Cc: Minchan Kim Cc: Nadav Amit Cc: Vlastimil Babka Cc: Dave Hansen Signed-off-by: Andrew Morton --- include/linux/swapfile.h | 5 ++++- include/linux/swapops.h | 2 +- 2 files changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swapfile.h b/include/linux/swapfile.h index 54078542134c..e2d11ae4e73d 100644 --- a/include/linux/swapfile.h +++ b/include/linux/swapfile.h @@ -8,6 +8,9 @@ */ extern struct swap_info_struct *swap_info[]; extern unsigned long generic_max_swapfile_size(void); -extern unsigned long max_swapfile_size(void); +unsigned long arch_max_swapfile_size(void); + +/* Maximum swapfile size supported for the arch (not inclusive). */ +extern unsigned long swapfile_maximum_size; #endif /* _LINUX_SWAPFILE_H */ diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 11b874f212a2..027b4095e132 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -307,7 +307,7 @@ static inline bool migration_entry_supports_ad(void) * the offset large enough to cover all of them (PFN, A & D bits). */ #ifdef CONFIG_SWAP - return max_swapfile_size() >= (1UL << SWP_MIG_TOTAL_BITS); + return swapfile_maximum_size >= (1UL << SWP_MIG_TOTAL_BITS); #else /* CONFIG_SWAP */ return false; #endif /* CONFIG_SWAP */ -- cgit v1.2.3 From 5154e607967d3f587fda84a40abbf900275016c9 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 11 Aug 2022 12:13:31 -0400 Subject: mm/swap: cache swap migration A/D bits support Introduce a variable swap_migration_ad_supported to cache whether the arch supports swap migration A/D bits. Here one thing to mention is that SWP_MIG_TOTAL_BITS will internally reference the other macro MAX_PHYSMEM_BITS, which is a function call on x86 (constant on all the rest of archs). It's safe to reference it in swapfile_init() because when reaching here we're already during initcalls level 4 so we must have initialized 5-level pgtable for x86_64 (right after early_identify_cpu() finishes). - start_kernel - setup_arch - early_cpu_init - get_cpu_cap --> fetch from CPUID (including X86_FEATURE_LA57) - early_identify_cpu --> clear X86_FEATURE_LA57 (if early lvl5 not enabled (USE_EARLY_PGTABLE_L5)) - arch_call_rest_init - rest_init - kernel_init - kernel_init_freeable - do_basic_setup - do_initcalls --> calls swapfile_init() (initcall level 4) This should slightly speed up the migration swap entry handlings. Link: https://lkml.kernel.org/r/20220811161331.37055-8-peterx@redhat.com Signed-off-by: Peter Xu Cc: Alistair Popple Cc: Andi Kleen Cc: Andrea Arcangeli Cc: David Hildenbrand Cc: Huang Ying Cc: Hugh Dickins Cc: "Kirill A . Shutemov" Cc: Minchan Kim Cc: Nadav Amit Cc: Vlastimil Babka Cc: Dave Hansen Signed-off-by: Andrew Morton --- include/linux/swapfile.h | 2 ++ include/linux/swapops.h | 7 +------ 2 files changed, 3 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swapfile.h b/include/linux/swapfile.h index e2d11ae4e73d..7ed529a77c5b 100644 --- a/include/linux/swapfile.h +++ b/include/linux/swapfile.h @@ -12,5 +12,7 @@ unsigned long arch_max_swapfile_size(void); /* Maximum swapfile size supported for the arch (not inclusive). */ extern unsigned long swapfile_maximum_size; +/* Whether swap migration entry supports storing A/D bits for the arch */ +extern bool swap_migration_ad_supported; #endif /* _LINUX_SWAPFILE_H */ diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 027b4095e132..86b95ccb81bb 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -301,13 +301,8 @@ static inline swp_entry_t make_writable_migration_entry(pgoff_t offset) */ static inline bool migration_entry_supports_ad(void) { - /* - * max_swapfile_size() returns the max supported swp-offset plus 1. - * We can support the migration A/D bits iff the pfn swap entry has - * the offset large enough to cover all of them (PFN, A & D bits). - */ #ifdef CONFIG_SWAP - return swapfile_maximum_size >= (1UL << SWP_MIG_TOTAL_BITS); + return swap_migration_ad_supported; #else /* CONFIG_SWAP */ return false; #endif /* CONFIG_SWAP */ -- cgit v1.2.3 From aa1cf99b87e934e761b46ce2b925335a398980da Mon Sep 17 00:00:00 2001 From: Yang Yang Date: Mon, 15 Aug 2022 07:11:35 +0000 Subject: delayacct: support re-entrance detection of thrashing accounting Once upon a time, we only support accounting thrashing of page cache. Then Joonsoo introduced workingset detection for anonymous pages and we gained the ability to account thrashing of them[1]. For page cache thrashing accounting, there is no suitable place to do it in fs level likes swap_readpage(). So we have to do it in folio_wait_bit_common(). Then for anonymous pages thrashing accounting, we have to do it in both swap_readpage() and folio_wait_bit_common(). This likes PSI, so we should let thrashing accounting supports re-entrance detection. This patch is to prepare complete thrashing accounting, and is based on patch "filemap: make the accounting of thrashing more consistent". [1] commit aae466b0052e ("mm/swap: implement workingset detection for anonymous LRU") Link: https://lkml.kernel.org/r/20220815071134.74551-1-yang.yang29@zte.com.cn Signed-off-by: Yang Yang Signed-off-by: CGEL ZTE Reviewed-by: Ran Xiaokai Reviewed-by: wangyong Acked-by: Joonsoo Kim Signed-off-by: Andrew Morton --- include/linux/delayacct.h | 16 ++++++++-------- include/linux/sched.h | 4 ++++ 2 files changed, 12 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index 58aea2d7385c..0da97dba9ef8 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -73,8 +73,8 @@ extern int delayacct_add_tsk(struct taskstats *, struct task_struct *); extern __u64 __delayacct_blkio_ticks(struct task_struct *); extern void __delayacct_freepages_start(void); extern void __delayacct_freepages_end(void); -extern void __delayacct_thrashing_start(void); -extern void __delayacct_thrashing_end(void); +extern void __delayacct_thrashing_start(bool *in_thrashing); +extern void __delayacct_thrashing_end(bool *in_thrashing); extern void __delayacct_swapin_start(void); extern void __delayacct_swapin_end(void); extern void __delayacct_compact_start(void); @@ -143,22 +143,22 @@ static inline void delayacct_freepages_end(void) __delayacct_freepages_end(); } -static inline void delayacct_thrashing_start(void) +static inline void delayacct_thrashing_start(bool *in_thrashing) { if (!static_branch_unlikely(&delayacct_key)) return; if (current->delays) - __delayacct_thrashing_start(); + __delayacct_thrashing_start(in_thrashing); } -static inline void delayacct_thrashing_end(void) +static inline void delayacct_thrashing_end(bool *in_thrashing) { if (!static_branch_unlikely(&delayacct_key)) return; if (current->delays) - __delayacct_thrashing_end(); + __delayacct_thrashing_end(in_thrashing); } static inline void delayacct_swapin_start(void) @@ -237,9 +237,9 @@ static inline void delayacct_freepages_start(void) {} static inline void delayacct_freepages_end(void) {} -static inline void delayacct_thrashing_start(void) +static inline void delayacct_thrashing_start(bool *in_thrashing) {} -static inline void delayacct_thrashing_end(void) +static inline void delayacct_thrashing_end(bool *in_thrashing) {} static inline void delayacct_swapin_start(void) {} diff --git a/include/linux/sched.h b/include/linux/sched.h index e7b2f8a5c711..d9a2466664f7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -944,6 +944,10 @@ struct task_struct { #ifdef CONFIG_CPU_SUP_INTEL unsigned reported_split_lock:1; #endif +#ifdef CONFIG_TASK_DELAY_ACCT + /* delay due to memory thrashing */ + unsigned in_thrashing:1; +#endif unsigned long atomic_flags; /* Flags requiring atomic access. */ -- cgit v1.2.3 From e1fd09e3d1dd4a1a8b3b33bc1fd647eee9f4e475 Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Sun, 18 Sep 2022 01:59:58 -0600 Subject: mm: x86, arm64: add arch_has_hw_pte_young() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Patch series "Multi-Gen LRU Framework", v14. What's new ========== 1. OpenWrt, in addition to Android, Arch Linux Zen, Armbian, ChromeOS, Liquorix, post-factum and XanMod, is now shipping MGLRU on 5.15. 2. Fixed long-tailed direct reclaim latency seen on high-memory (TBs) machines. The old direct reclaim backoff, which tries to enforce a minimum fairness among all eligible memcgs, over-swapped by about (total_mem>>DEF_PRIORITY)-nr_to_reclaim. The new backoff, which pulls the plug on swapping once the target is met, trades some fairness for curtailed latency: https://lore.kernel.org/r/20220918080010.2920238-10-yuzhao@google.com/ 3. Fixed minior build warnings and conflicts. More comments and nits. TLDR ==== The current page reclaim is too expensive in terms of CPU usage and it often makes poor choices about what to evict. This patchset offers an alternative solution that is performant, versatile and straightforward. Patchset overview ================= The design and implementation overview is in patch 14: https://lore.kernel.org/r/20220918080010.2920238-15-yuzhao@google.com/ 01. mm: x86, arm64: add arch_has_hw_pte_young() 02. mm: x86: add CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG Take advantage of hardware features when trying to clear the accessed bit in many PTEs. 03. mm/vmscan.c: refactor shrink_node() 04. Revert "include/linux/mm_inline.h: fold __update_lru_size() into its sole caller" Minor refactors to improve readability for the following patches. 05. mm: multi-gen LRU: groundwork Adds the basic data structure and the functions that insert pages to and remove pages from the multi-gen LRU (MGLRU) lists. 06. mm: multi-gen LRU: minimal implementation A minimal implementation without optimizations. 07. mm: multi-gen LRU: exploit locality in rmap Exploits spatial locality to improve efficiency when using the rmap. 08. mm: multi-gen LRU: support page table walks Further exploits spatial locality by optionally scanning page tables. 09. mm: multi-gen LRU: optimize multiple memcgs Optimizes the overall performance for multiple memcgs running mixed types of workloads. 10. mm: multi-gen LRU: kill switch Adds a kill switch to enable or disable MGLRU at runtime. 11. mm: multi-gen LRU: thrashing prevention 12. mm: multi-gen LRU: debugfs interface Provide userspace with features like thrashing prevention, working set estimation and proactive reclaim. 13. mm: multi-gen LRU: admin guide 14. mm: multi-gen LRU: design doc Add an admin guide and a design doc. Benchmark results ================= Independent lab results ----------------------- Based on the popularity of searches [01] and the memory usage in Google's public cloud, the most popular open-source memory-hungry applications, in alphabetical order, are: Apache Cassandra Memcached Apache Hadoop MongoDB Apache Spark PostgreSQL MariaDB (MySQL) Redis An independent lab evaluated MGLRU with the most widely used benchmark suites for the above applications. They posted 960 data points along with kernel metrics and perf profiles collected over more than 500 hours of total benchmark time. Their final reports show that, with 95% confidence intervals (CIs), the above applications all performed significantly better for at least part of their benchmark matrices. On 5.14: 1. Apache Spark [02] took 95% CIs [9.28, 11.19]% and [12.20, 14.93]% less wall time to sort three billion random integers, respectively, under the medium- and the high-concurrency conditions, when overcommitting memory. There were no statistically significant changes in wall time for the rest of the benchmark matrix. 2. MariaDB [03] achieved 95% CIs [5.24, 10.71]% and [20.22, 25.97]% more transactions per minute (TPM), respectively, under the medium- and the high-concurrency conditions, when overcommitting memory. There were no statistically significant changes in TPM for the rest of the benchmark matrix. 3. Memcached [04] achieved 95% CIs [23.54, 32.25]%, [20.76, 41.61]% and [21.59, 30.02]% more operations per second (OPS), respectively, for sequential access, random access and Gaussian (distribution) access, when THP=always; 95% CIs [13.85, 15.97]% and [23.94, 29.92]% more OPS, respectively, for random access and Gaussian access, when THP=never. There were no statistically significant changes in OPS for the rest of the benchmark matrix. 4. MongoDB [05] achieved 95% CIs [2.23, 3.44]%, [6.97, 9.73]% and [2.16, 3.55]% more operations per second (OPS), respectively, for exponential (distribution) access, random access and Zipfian (distribution) access, when underutilizing memory; 95% CIs [8.83, 10.03]%, [21.12, 23.14]% and [5.53, 6.46]% more OPS, respectively, for exponential access, random access and Zipfian access, when overcommitting memory. On 5.15: 5. Apache Cassandra [06] achieved 95% CIs [1.06, 4.10]%, [1.94, 5.43]% and [4.11, 7.50]% more operations per second (OPS), respectively, for exponential (distribution) access, random access and Zipfian (distribution) access, when swap was off; 95% CIs [0.50, 2.60]%, [6.51, 8.77]% and [3.29, 6.75]% more OPS, respectively, for exponential access, random access and Zipfian access, when swap was on. 6. Apache Hadoop [07] took 95% CIs [5.31, 9.69]% and [2.02, 7.86]% less average wall time to finish twelve parallel TeraSort jobs, respectively, under the medium- and the high-concurrency conditions, when swap was on. There were no statistically significant changes in average wall time for the rest of the benchmark matrix. 7. PostgreSQL [08] achieved 95% CI [1.75, 6.42]% more transactions per minute (TPM) under the high-concurrency condition, when swap was off; 95% CIs [12.82, 18.69]% and [22.70, 46.86]% more TPM, respectively, under the medium- and the high-concurrency conditions, when swap was on. There were no statistically significant changes in TPM for the rest of the benchmark matrix. 8. Redis [09] achieved 95% CIs [0.58, 5.94]%, [6.55, 14.58]% and [11.47, 19.36]% more total operations per second (OPS), respectively, for sequential access, random access and Gaussian (distribution) access, when THP=always; 95% CIs [1.27, 3.54]%, [10.11, 14.81]% and [8.75, 13.64]% more total OPS, respectively, for sequential access, random access and Gaussian access, when THP=never. Our lab results --------------- To supplement the above results, we ran the following benchmark suites on 5.16-rc7 and found no regressions [10]. fs_fio_bench_hdd_mq pft fs_lmbench pgsql-hammerdb fs_parallelio redis fs_postmark stream hackbench sysbenchthread kernbench tpcc_spark memcached unixbench multichase vm-scalability mutilate will-it-scale nginx [01] https://trends.google.com [02] https://lore.kernel.org/r/20211102002002.92051-1-bot@edi.works/ [03] https://lore.kernel.org/r/20211009054315.47073-1-bot@edi.works/ [04] https://lore.kernel.org/r/20211021194103.65648-1-bot@edi.works/ [05] https://lore.kernel.org/r/20211109021346.50266-1-bot@edi.works/ [06] https://lore.kernel.org/r/20211202062806.80365-1-bot@edi.works/ [07] https://lore.kernel.org/r/20211209072416.33606-1-bot@edi.works/ [08] https://lore.kernel.org/r/20211218071041.24077-1-bot@edi.works/ [09] https://lore.kernel.org/r/20211122053248.57311-1-bot@edi.works/ [10] https://lore.kernel.org/r/20220104202247.2903702-1-yuzhao@google.com/ Read-world applications ======================= Third-party testimonials ------------------------ Konstantin reported [11]: I have Archlinux with 8G RAM + zswap + swap. While developing, I have lots of apps opened such as multiple LSP-servers for different langs, chats, two browsers, etc... Usually, my system gets quickly to a point of SWAP-storms, where I have to kill LSP-servers, restart browsers to free memory, etc, otherwise the system lags heavily and is barely usable. 1.5 day ago I migrated from 5.11.15 kernel to 5.12 + the LRU patchset, and I started up by opening lots of apps to create memory pressure, and worked for a day like this. Till now I had not a single SWAP-storm, and mind you I got 3.4G in SWAP. I was never getting to the point of 3G in SWAP before without a single SWAP-storm. Vaibhav from IBM reported [12]: In a synthetic MongoDB Benchmark, seeing an average of ~19% throughput improvement on POWER10(Radix MMU + 64K Page Size) with MGLRU patches on top of 5.16 kernel for MongoDB + YCSB across three different request distributions, namely, Exponential, Uniform and Zipfan. Shuang from U of Rochester reported [13]: With the MGLRU, fio achieved 95% CIs [38.95, 40.26]%, [4.12, 6.64]% and [9.26, 10.36]% higher throughput, respectively, for random access, Zipfian (distribution) access and Gaussian (distribution) access, when the average number of jobs per CPU is 1; 95% CIs [42.32, 49.15]%, [9.44, 9.89]% and [20.99, 22.86]% higher throughput, respectively, for random access, Zipfian access and Gaussian access, when the average number of jobs per CPU is 2. Daniel from Michigan Tech reported [14]: With Memcached allocating ~100GB of byte-addressable Optante, performance improvement in terms of throughput (measured as queries per second) was about 10% for a series of workloads. Large-scale deployments ----------------------- We've rolled out MGLRU to tens of millions of ChromeOS users and about a million Android users. Google's fleetwide profiling [15] shows an overall 40% decrease in kswapd CPU usage, in addition to improvements in other UX metrics, e.g., an 85% decrease in the number of low-memory kills at the 75th percentile and an 18% decrease in app launch time at the 50th percentile. The downstream kernels that have been using MGLRU include: 1. Android [16] 2. Arch Linux Zen [17] 3. Armbian [18] 4. ChromeOS [19] 5. Liquorix [20] 6. OpenWrt [21] 7. post-factum [22] 8. XanMod [23] [11] https://lore.kernel.org/r/140226722f2032c86301fbd326d91baefe3d7d23.camel@yandex.ru/ [12] https://lore.kernel.org/r/87czj3mux0.fsf@vajain21.in.ibm.com/ [13] https://lore.kernel.org/r/20220105024423.26409-1-szhai2@cs.rochester.edu/ [14] https://lore.kernel.org/r/CA+4-3vksGvKd18FgRinxhqHetBS1hQekJE2gwco8Ja-bJWKtFw@mail.gmail.com/ [15] https://dl.acm.org/doi/10.1145/2749469.2750392 [16] https://android.com [17] https://archlinux.org [18] https://armbian.com [19] https://chromium.org [20] https://liquorix.net [21] https://openwrt.org [22] https://codeberg.org/pf-kernel [23] https://xanmod.org Summary ======= The facts are: 1. The independent lab results and the real-world applications indicate substantial improvements; there are no known regressions. 2. Thrashing prevention, working set estimation and proactive reclaim work out of the box; there are no equivalent solutions. 3. There is a lot of new code; no smaller changes have been demonstrated similar effects. Our options, accordingly, are: 1. Given the amount of evidence, the reported improvements will likely materialize for a wide range of workloads. 2. Gauging the interest from the past discussions, the new features will likely be put to use for both personal computers and data centers. 3. Based on Google's track record, the new code will likely be well maintained in the long term. It'd be more difficult if not impossible to achieve similar effects with other approaches. This patch (of 14): Some architectures automatically set the accessed bit in PTEs, e.g., x86 and arm64 v8.2. On architectures that do not have this capability, clearing the accessed bit in a PTE usually triggers a page fault following the TLB miss of this PTE (to emulate the accessed bit). Being aware of this capability can help make better decisions, e.g., whether to spread the work out over a period of time to reduce bursty page faults when trying to clear the accessed bit in many PTEs. Note that theoretically this capability can be unreliable, e.g., hotplugged CPUs might be different from builtin ones. Therefore it should not be used in architecture-independent code that involves correctness, e.g., to determine whether TLB flushes are required (in combination with the accessed bit). Link: https://lkml.kernel.org/r/20220918080010.2920238-1-yuzhao@google.com Link: https://lkml.kernel.org/r/20220918080010.2920238-2-yuzhao@google.com Signed-off-by: Yu Zhao Reviewed-by: Barry Song Acked-by: Brian Geffon Acked-by: Jan Alexander Steffens (heftig) Acked-by: Oleksandr Natalenko Acked-by: Steven Barrett Acked-by: Suleiman Souhlal Acked-by: Will Deacon Tested-by: Daniel Byrne Tested-by: Donald Carr Tested-by: Holger Hoffstätte Tested-by: Konstantin Kharlamov Tested-by: Shuang Zhai Tested-by: Sofia Trinh Tested-by: Vaibhav Jain Cc: Andi Kleen Cc: Aneesh Kumar K.V Cc: Catalin Marinas Cc: Dave Hansen Cc: Hillf Danton Cc: Jens Axboe Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Linus Torvalds Cc: linux-arm-kernel@lists.infradead.org Cc: Matthew Wilcox Cc: Mel Gorman Cc: Michael Larabel Cc: Michal Hocko Cc: Mike Rapoport Cc: Peter Zijlstra Cc: Tejun Heo Cc: Vlastimil Babka Cc: Miaohe Lin Cc: Mike Rapoport Cc: Qi Zheng Signed-off-by: Andrew Morton --- include/linux/pgtable.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index d13b4f7cc5be..375e8e7e64f4 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -260,6 +260,19 @@ static inline int pmdp_clear_flush_young(struct vm_area_struct *vma, #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif +#ifndef arch_has_hw_pte_young +/* + * Return whether the accessed bit is supported on the local CPU. + * + * This stub assumes accessing through an old PTE triggers a page fault. + * Architectures that automatically set the access bit should overwrite it. + */ +static inline bool arch_has_hw_pte_young(void) +{ + return false; +} +#endif + #ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long address, -- cgit v1.2.3 From eed9a328aa1ae6ac1edaa026957e6882f57de0dd Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Sun, 18 Sep 2022 01:59:59 -0600 Subject: mm: x86: add CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Some architectures support the accessed bit in non-leaf PMD entries, e.g., x86 sets the accessed bit in a non-leaf PMD entry when using it as part of linear address translation [1]. Page table walkers that clear the accessed bit may use this capability to reduce their search space. Note that: 1. Although an inline function is preferable, this capability is added as a configuration option for consistency with the existing macros. 2. Due to the little interest in other varieties, this capability was only tested on Intel and AMD CPUs. Thanks to the following developers for their efforts [2][3]. Randy Dunlap Stephen Rothwell [1]: Intel 64 and IA-32 Architectures Software Developer's Manual Volume 3 (June 2021), section 4.8 [2] https://lore.kernel.org/r/bfdcc7c8-922f-61a9-aa15-7e7250f04af7@infradead.org/ [3] https://lore.kernel.org/r/20220413151513.5a0d7a7e@canb.auug.org.au/ Link: https://lkml.kernel.org/r/20220918080010.2920238-3-yuzhao@google.com Signed-off-by: Yu Zhao Reviewed-by: Barry Song Acked-by: Brian Geffon Acked-by: Jan Alexander Steffens (heftig) Acked-by: Oleksandr Natalenko Acked-by: Steven Barrett Acked-by: Suleiman Souhlal Tested-by: Daniel Byrne Tested-by: Donald Carr Tested-by: Holger Hoffstätte Tested-by: Konstantin Kharlamov Tested-by: Shuang Zhai Tested-by: Sofia Trinh Tested-by: Vaibhav Jain Cc: Andi Kleen Cc: Aneesh Kumar K.V Cc: Catalin Marinas Cc: Dave Hansen Cc: Hillf Danton Cc: Jens Axboe Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Linus Torvalds Cc: Matthew Wilcox Cc: Mel Gorman Cc: Miaohe Lin Cc: Michael Larabel Cc: Michal Hocko Cc: Mike Rapoport Cc: Mike Rapoport Cc: Peter Zijlstra Cc: Qi Zheng Cc: Tejun Heo Cc: Vlastimil Babka Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/pgtable.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 375e8e7e64f4..a108b60a6962 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -213,7 +213,7 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, #endif #ifndef __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG -#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) @@ -234,7 +234,7 @@ static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, BUILD_BUG(); return 0; } -#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG */ #endif #ifndef __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH -- cgit v1.2.3 From aa1b67903a19e026d1749241fad177f6185c2d42 Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Sun, 18 Sep 2022 02:00:01 -0600 Subject: Revert "include/linux/mm_inline.h: fold __update_lru_size() into its sole caller" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch undoes the following refactor: commit 289ccba18af4 ("include/linux/mm_inline.h: fold __update_lru_size() into its sole caller") The upcoming changes to include/linux/mm_inline.h will reuse __update_lru_size(). Link: https://lkml.kernel.org/r/20220918080010.2920238-5-yuzhao@google.com Signed-off-by: Yu Zhao Reviewed-by: Miaohe Lin Acked-by: Brian Geffon Acked-by: Jan Alexander Steffens (heftig) Acked-by: Oleksandr Natalenko Acked-by: Steven Barrett Acked-by: Suleiman Souhlal Tested-by: Daniel Byrne Tested-by: Donald Carr Tested-by: Holger Hoffstätte Tested-by: Konstantin Kharlamov Tested-by: Shuang Zhai Tested-by: Sofia Trinh Tested-by: Vaibhav Jain Cc: Andi Kleen Cc: Aneesh Kumar K.V Cc: Barry Song Cc: Catalin Marinas Cc: Dave Hansen Cc: Hillf Danton Cc: Jens Axboe Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Linus Torvalds Cc: Matthew Wilcox Cc: Mel Gorman Cc: Michael Larabel Cc: Michal Hocko Cc: Mike Rapoport Cc: Mike Rapoport Cc: Peter Zijlstra Cc: Qi Zheng Cc: Tejun Heo Cc: Vlastimil Babka Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/mm_inline.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 7b25b53c474a..fb8aadb81cd6 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -34,7 +34,7 @@ static inline int page_is_file_lru(struct page *page) return folio_is_file_lru(page_folio(page)); } -static __always_inline void update_lru_size(struct lruvec *lruvec, +static __always_inline void __update_lru_size(struct lruvec *lruvec, enum lru_list lru, enum zone_type zid, long nr_pages) { @@ -43,6 +43,13 @@ static __always_inline void update_lru_size(struct lruvec *lruvec, __mod_lruvec_state(lruvec, NR_LRU_BASE + lru, nr_pages); __mod_zone_page_state(&pgdat->node_zones[zid], NR_ZONE_LRU_BASE + lru, nr_pages); +} + +static __always_inline void update_lru_size(struct lruvec *lruvec, + enum lru_list lru, enum zone_type zid, + long nr_pages) +{ + __update_lru_size(lruvec, lru, zid, nr_pages); #ifdef CONFIG_MEMCG mem_cgroup_update_lru_size(lruvec, lru, zid, nr_pages); #endif -- cgit v1.2.3 From ec1c86b25f4bdd9dce6436c0539d2a6ae676e1c4 Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Sun, 18 Sep 2022 02:00:02 -0600 Subject: mm: multi-gen LRU: groundwork MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Evictable pages are divided into multiple generations for each lruvec. The youngest generation number is stored in lrugen->max_seq for both anon and file types as they are aged on an equal footing. The oldest generation numbers are stored in lrugen->min_seq[] separately for anon and file types as clean file pages can be evicted regardless of swap constraints. These three variables are monotonically increasing. Generation numbers are truncated into order_base_2(MAX_NR_GENS+1) bits in order to fit into the gen counter in folio->flags. Each truncated generation number is an index to lrugen->lists[]. The sliding window technique is used to track at least MIN_NR_GENS and at most MAX_NR_GENS generations. The gen counter stores a value within [1, MAX_NR_GENS] while a page is on one of lrugen->lists[]. Otherwise it stores 0. There are two conceptually independent procedures: "the aging", which produces young generations, and "the eviction", which consumes old generations. They form a closed-loop system, i.e., "the page reclaim". Both procedures can be invoked from userspace for the purposes of working set estimation and proactive reclaim. These techniques are commonly used to optimize job scheduling (bin packing) in data centers [1][2]. To avoid confusion, the terms "hot" and "cold" will be applied to the multi-gen LRU, as a new convention; the terms "active" and "inactive" will be applied to the active/inactive LRU, as usual. The protection of hot pages and the selection of cold pages are based on page access channels and patterns. There are two access channels: one through page tables and the other through file descriptors. The protection of the former channel is by design stronger because: 1. The uncertainty in determining the access patterns of the former channel is higher due to the approximation of the accessed bit. 2. The cost of evicting the former channel is higher due to the TLB flushes required and the likelihood of encountering the dirty bit. 3. The penalty of underprotecting the former channel is higher because applications usually do not prepare themselves for major page faults like they do for blocked I/O. E.g., GUI applications commonly use dedicated I/O threads to avoid blocking rendering threads. There are also two access patterns: one with temporal locality and the other without. For the reasons listed above, the former channel is assumed to follow the former pattern unless VM_SEQ_READ or VM_RAND_READ is present; the latter channel is assumed to follow the latter pattern unless outlying refaults have been observed [3][4]. The next patch will address the "outlying refaults". Three macros, i.e., LRU_REFS_WIDTH, LRU_REFS_PGOFF and LRU_REFS_MASK, used later are added in this patch to make the entire patchset less diffy. A page is added to the youngest generation on faulting. The aging needs to check the accessed bit at least twice before handing this page over to the eviction. The first check takes care of the accessed bit set on the initial fault; the second check makes sure this page has not been used since then. This protocol, AKA second chance, requires a minimum of two generations, hence MIN_NR_GENS. [1] https://dl.acm.org/doi/10.1145/3297858.3304053 [2] https://dl.acm.org/doi/10.1145/3503222.3507731 [3] https://lwn.net/Articles/495543/ [4] https://lwn.net/Articles/815342/ Link: https://lkml.kernel.org/r/20220918080010.2920238-6-yuzhao@google.com Signed-off-by: Yu Zhao Acked-by: Brian Geffon Acked-by: Jan Alexander Steffens (heftig) Acked-by: Oleksandr Natalenko Acked-by: Steven Barrett Acked-by: Suleiman Souhlal Tested-by: Daniel Byrne Tested-by: Donald Carr Tested-by: Holger Hoffstätte Tested-by: Konstantin Kharlamov Tested-by: Shuang Zhai Tested-by: Sofia Trinh Tested-by: Vaibhav Jain Cc: Andi Kleen Cc: Aneesh Kumar K.V Cc: Barry Song Cc: Catalin Marinas Cc: Dave Hansen Cc: Hillf Danton Cc: Jens Axboe Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Linus Torvalds Cc: Matthew Wilcox Cc: Mel Gorman Cc: Miaohe Lin Cc: Michael Larabel Cc: Michal Hocko Cc: Mike Rapoport Cc: Mike Rapoport Cc: Peter Zijlstra Cc: Qi Zheng Cc: Tejun Heo Cc: Vlastimil Babka Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/mm_inline.h | 175 ++++++++++++++++++++++++++++++++++++++ include/linux/mmzone.h | 102 ++++++++++++++++++++++ include/linux/page-flags-layout.h | 13 +-- include/linux/page-flags.h | 4 +- include/linux/sched.h | 4 + 5 files changed, 291 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index fb8aadb81cd6..2ff703900fd0 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -40,6 +40,9 @@ static __always_inline void __update_lru_size(struct lruvec *lruvec, { struct pglist_data *pgdat = lruvec_pgdat(lruvec); + lockdep_assert_held(&lruvec->lru_lock); + WARN_ON_ONCE(nr_pages != (int)nr_pages); + __mod_lruvec_state(lruvec, NR_LRU_BASE + lru, nr_pages); __mod_zone_page_state(&pgdat->node_zones[zid], NR_ZONE_LRU_BASE + lru, nr_pages); @@ -101,11 +104,177 @@ static __always_inline enum lru_list folio_lru_list(struct folio *folio) return lru; } +#ifdef CONFIG_LRU_GEN + +static inline bool lru_gen_enabled(void) +{ + return true; +} + +static inline bool lru_gen_in_fault(void) +{ + return current->in_lru_fault; +} + +static inline int lru_gen_from_seq(unsigned long seq) +{ + return seq % MAX_NR_GENS; +} + +static inline int folio_lru_gen(struct folio *folio) +{ + unsigned long flags = READ_ONCE(folio->flags); + + return ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; +} + +static inline bool lru_gen_is_active(struct lruvec *lruvec, int gen) +{ + unsigned long max_seq = lruvec->lrugen.max_seq; + + VM_WARN_ON_ONCE(gen >= MAX_NR_GENS); + + /* see the comment on MIN_NR_GENS */ + return gen == lru_gen_from_seq(max_seq) || gen == lru_gen_from_seq(max_seq - 1); +} + +static inline void lru_gen_update_size(struct lruvec *lruvec, struct folio *folio, + int old_gen, int new_gen) +{ + int type = folio_is_file_lru(folio); + int zone = folio_zonenum(folio); + int delta = folio_nr_pages(folio); + enum lru_list lru = type * LRU_INACTIVE_FILE; + struct lru_gen_struct *lrugen = &lruvec->lrugen; + + VM_WARN_ON_ONCE(old_gen != -1 && old_gen >= MAX_NR_GENS); + VM_WARN_ON_ONCE(new_gen != -1 && new_gen >= MAX_NR_GENS); + VM_WARN_ON_ONCE(old_gen == -1 && new_gen == -1); + + if (old_gen >= 0) + WRITE_ONCE(lrugen->nr_pages[old_gen][type][zone], + lrugen->nr_pages[old_gen][type][zone] - delta); + if (new_gen >= 0) + WRITE_ONCE(lrugen->nr_pages[new_gen][type][zone], + lrugen->nr_pages[new_gen][type][zone] + delta); + + /* addition */ + if (old_gen < 0) { + if (lru_gen_is_active(lruvec, new_gen)) + lru += LRU_ACTIVE; + __update_lru_size(lruvec, lru, zone, delta); + return; + } + + /* deletion */ + if (new_gen < 0) { + if (lru_gen_is_active(lruvec, old_gen)) + lru += LRU_ACTIVE; + __update_lru_size(lruvec, lru, zone, -delta); + return; + } +} + +static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) +{ + unsigned long seq; + unsigned long flags; + int gen = folio_lru_gen(folio); + int type = folio_is_file_lru(folio); + int zone = folio_zonenum(folio); + struct lru_gen_struct *lrugen = &lruvec->lrugen; + + VM_WARN_ON_ONCE_FOLIO(gen != -1, folio); + + if (folio_test_unevictable(folio)) + return false; + /* + * There are three common cases for this page: + * 1. If it's hot, e.g., freshly faulted in or previously hot and + * migrated, add it to the youngest generation. + * 2. If it's cold but can't be evicted immediately, i.e., an anon page + * not in swapcache or a dirty page pending writeback, add it to the + * second oldest generation. + * 3. Everything else (clean, cold) is added to the oldest generation. + */ + if (folio_test_active(folio)) + seq = lrugen->max_seq; + else if ((type == LRU_GEN_ANON && !folio_test_swapcache(folio)) || + (folio_test_reclaim(folio) && + (folio_test_dirty(folio) || folio_test_writeback(folio)))) + seq = lrugen->min_seq[type] + 1; + else + seq = lrugen->min_seq[type]; + + gen = lru_gen_from_seq(seq); + flags = (gen + 1UL) << LRU_GEN_PGOFF; + /* see the comment on MIN_NR_GENS about PG_active */ + set_mask_bits(&folio->flags, LRU_GEN_MASK | BIT(PG_active), flags); + + lru_gen_update_size(lruvec, folio, -1, gen); + /* for folio_rotate_reclaimable() */ + if (reclaiming) + list_add_tail(&folio->lru, &lrugen->lists[gen][type][zone]); + else + list_add(&folio->lru, &lrugen->lists[gen][type][zone]); + + return true; +} + +static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) +{ + unsigned long flags; + int gen = folio_lru_gen(folio); + + if (gen < 0) + return false; + + VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio); + VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); + + /* for folio_migrate_flags() */ + flags = !reclaiming && lru_gen_is_active(lruvec, gen) ? BIT(PG_active) : 0; + flags = set_mask_bits(&folio->flags, LRU_GEN_MASK, flags); + gen = ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; + + lru_gen_update_size(lruvec, folio, gen, -1); + list_del(&folio->lru); + + return true; +} + +#else /* !CONFIG_LRU_GEN */ + +static inline bool lru_gen_enabled(void) +{ + return false; +} + +static inline bool lru_gen_in_fault(void) +{ + return false; +} + +static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) +{ + return false; +} + +static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) +{ + return false; +} + +#endif /* CONFIG_LRU_GEN */ + static __always_inline void lruvec_add_folio(struct lruvec *lruvec, struct folio *folio) { enum lru_list lru = folio_lru_list(folio); + if (lru_gen_add_folio(lruvec, folio, false)) + return; + update_lru_size(lruvec, lru, folio_zonenum(folio), folio_nr_pages(folio)); if (lru != LRU_UNEVICTABLE) @@ -123,6 +292,9 @@ void lruvec_add_folio_tail(struct lruvec *lruvec, struct folio *folio) { enum lru_list lru = folio_lru_list(folio); + if (lru_gen_add_folio(lruvec, folio, true)) + return; + update_lru_size(lruvec, lru, folio_zonenum(folio), folio_nr_pages(folio)); /* This is not expected to be used on LRU_UNEVICTABLE */ @@ -140,6 +312,9 @@ void lruvec_del_folio(struct lruvec *lruvec, struct folio *folio) { enum lru_list lru = folio_lru_list(folio); + if (lru_gen_del_folio(lruvec, folio, false)) + return; + if (lru != LRU_UNEVICTABLE) list_del(&folio->lru); update_lru_size(lruvec, lru, folio_zonenum(folio), diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 18cf0fc5ce67..6f4ea078d90f 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -317,6 +317,102 @@ enum lruvec_flags { */ }; +#endif /* !__GENERATING_BOUNDS_H */ + +/* + * Evictable pages are divided into multiple generations. The youngest and the + * oldest generation numbers, max_seq and min_seq, are monotonically increasing. + * They form a sliding window of a variable size [MIN_NR_GENS, MAX_NR_GENS]. An + * offset within MAX_NR_GENS, i.e., gen, indexes the LRU list of the + * corresponding generation. The gen counter in folio->flags stores gen+1 while + * a page is on one of lrugen->lists[]. Otherwise it stores 0. + * + * A page is added to the youngest generation on faulting. The aging needs to + * check the accessed bit at least twice before handing this page over to the + * eviction. The first check takes care of the accessed bit set on the initial + * fault; the second check makes sure this page hasn't been used since then. + * This process, AKA second chance, requires a minimum of two generations, + * hence MIN_NR_GENS. And to maintain ABI compatibility with the active/inactive + * LRU, e.g., /proc/vmstat, these two generations are considered active; the + * rest of generations, if they exist, are considered inactive. See + * lru_gen_is_active(). + * + * PG_active is always cleared while a page is on one of lrugen->lists[] so that + * the aging needs not to worry about it. And it's set again when a page + * considered active is isolated for non-reclaiming purposes, e.g., migration. + * See lru_gen_add_folio() and lru_gen_del_folio(). + * + * MAX_NR_GENS is set to 4 so that the multi-gen LRU can support twice the + * number of categories of the active/inactive LRU when keeping track of + * accesses through page tables. This requires order_base_2(MAX_NR_GENS+1) bits + * in folio->flags. + */ +#define MIN_NR_GENS 2U +#define MAX_NR_GENS 4U + +#ifndef __GENERATING_BOUNDS_H + +struct lruvec; + +#define LRU_GEN_MASK ((BIT(LRU_GEN_WIDTH) - 1) << LRU_GEN_PGOFF) +#define LRU_REFS_MASK ((BIT(LRU_REFS_WIDTH) - 1) << LRU_REFS_PGOFF) + +#ifdef CONFIG_LRU_GEN + +enum { + LRU_GEN_ANON, + LRU_GEN_FILE, +}; + +/* + * The youngest generation number is stored in max_seq for both anon and file + * types as they are aged on an equal footing. The oldest generation numbers are + * stored in min_seq[] separately for anon and file types as clean file pages + * can be evicted regardless of swap constraints. + * + * Normally anon and file min_seq are in sync. But if swapping is constrained, + * e.g., out of swap space, file min_seq is allowed to advance and leave anon + * min_seq behind. + * + * The number of pages in each generation is eventually consistent and therefore + * can be transiently negative. + */ +struct lru_gen_struct { + /* the aging increments the youngest generation number */ + unsigned long max_seq; + /* the eviction increments the oldest generation numbers */ + unsigned long min_seq[ANON_AND_FILE]; + /* the multi-gen LRU lists, lazily sorted on eviction */ + struct list_head lists[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; + /* the multi-gen LRU sizes, eventually consistent */ + long nr_pages[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; +}; + +void lru_gen_init_lruvec(struct lruvec *lruvec); + +#ifdef CONFIG_MEMCG +void lru_gen_init_memcg(struct mem_cgroup *memcg); +void lru_gen_exit_memcg(struct mem_cgroup *memcg); +#endif + +#else /* !CONFIG_LRU_GEN */ + +static inline void lru_gen_init_lruvec(struct lruvec *lruvec) +{ +} + +#ifdef CONFIG_MEMCG +static inline void lru_gen_init_memcg(struct mem_cgroup *memcg) +{ +} + +static inline void lru_gen_exit_memcg(struct mem_cgroup *memcg) +{ +} +#endif + +#endif /* CONFIG_LRU_GEN */ + struct lruvec { struct list_head lists[NR_LRU_LISTS]; /* per lruvec lru_lock for memcg */ @@ -334,6 +430,10 @@ struct lruvec { unsigned long refaults[ANON_AND_FILE]; /* Various lruvec state flags (enum lruvec_flags) */ unsigned long flags; +#ifdef CONFIG_LRU_GEN + /* evictable pages divided into generations */ + struct lru_gen_struct lrugen; +#endif #ifdef CONFIG_MEMCG struct pglist_data *pgdat; #endif @@ -749,6 +849,8 @@ static inline bool zone_is_empty(struct zone *zone) #define ZONES_PGOFF (NODES_PGOFF - ZONES_WIDTH) #define LAST_CPUPID_PGOFF (ZONES_PGOFF - LAST_CPUPID_WIDTH) #define KASAN_TAG_PGOFF (LAST_CPUPID_PGOFF - KASAN_TAG_WIDTH) +#define LRU_GEN_PGOFF (KASAN_TAG_PGOFF - LRU_GEN_WIDTH) +#define LRU_REFS_PGOFF (LRU_GEN_PGOFF - LRU_REFS_WIDTH) /* * Define the bit shifts to access each section. For non-existent diff --git a/include/linux/page-flags-layout.h b/include/linux/page-flags-layout.h index ef1e3e736e14..240905407a18 100644 --- a/include/linux/page-flags-layout.h +++ b/include/linux/page-flags-layout.h @@ -55,7 +55,8 @@ #define SECTIONS_WIDTH 0 #endif -#if ZONES_WIDTH + SECTIONS_WIDTH + NODES_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS +#if ZONES_WIDTH + LRU_GEN_WIDTH + SECTIONS_WIDTH + NODES_SHIFT \ + <= BITS_PER_LONG - NR_PAGEFLAGS #define NODES_WIDTH NODES_SHIFT #elif defined(CONFIG_SPARSEMEM_VMEMMAP) #error "Vmemmap: No space for nodes field in page flags" @@ -89,8 +90,8 @@ #define LAST_CPUPID_SHIFT 0 #endif -#if ZONES_WIDTH + SECTIONS_WIDTH + NODES_WIDTH + KASAN_TAG_WIDTH + LAST_CPUPID_SHIFT \ - <= BITS_PER_LONG - NR_PAGEFLAGS +#if ZONES_WIDTH + LRU_GEN_WIDTH + SECTIONS_WIDTH + NODES_WIDTH + \ + KASAN_TAG_WIDTH + LAST_CPUPID_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS #define LAST_CPUPID_WIDTH LAST_CPUPID_SHIFT #else #define LAST_CPUPID_WIDTH 0 @@ -100,10 +101,12 @@ #define LAST_CPUPID_NOT_IN_PAGE_FLAGS #endif -#if ZONES_WIDTH + SECTIONS_WIDTH + NODES_WIDTH + KASAN_TAG_WIDTH + LAST_CPUPID_WIDTH \ - > BITS_PER_LONG - NR_PAGEFLAGS +#if ZONES_WIDTH + LRU_GEN_WIDTH + SECTIONS_WIDTH + NODES_WIDTH + \ + KASAN_TAG_WIDTH + LAST_CPUPID_WIDTH > BITS_PER_LONG - NR_PAGEFLAGS #error "Not enough bits in page flags" #endif +#define LRU_REFS_WIDTH 0 + #endif #endif /* _LINUX_PAGE_FLAGS_LAYOUT */ diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 465ff35a8c00..0b0ae5084e60 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -1058,7 +1058,7 @@ static __always_inline void __ClearPageAnonExclusive(struct page *page) 1UL << PG_private | 1UL << PG_private_2 | \ 1UL << PG_writeback | 1UL << PG_reserved | \ 1UL << PG_slab | 1UL << PG_active | \ - 1UL << PG_unevictable | __PG_MLOCKED) + 1UL << PG_unevictable | __PG_MLOCKED | LRU_GEN_MASK) /* * Flags checked when a page is prepped for return by the page allocator. @@ -1069,7 +1069,7 @@ static __always_inline void __ClearPageAnonExclusive(struct page *page) * alloc-free cycle to prevent from reusing the page. */ #define PAGE_FLAGS_CHECK_AT_PREP \ - (PAGEFLAGS_MASK & ~__PG_HWPOISON) + ((PAGEFLAGS_MASK & ~__PG_HWPOISON) | LRU_GEN_MASK | LRU_REFS_MASK) #define PAGE_FLAGS_PRIVATE \ (1UL << PG_private | 1UL << PG_private_2) diff --git a/include/linux/sched.h b/include/linux/sched.h index d9a2466664f7..a2dcfb91df03 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -914,6 +914,10 @@ struct task_struct { #ifdef CONFIG_MEMCG unsigned in_user_fault:1; #endif +#ifdef CONFIG_LRU_GEN + /* whether the LRU algorithm may apply to this access */ + unsigned in_lru_fault:1; +#endif #ifdef CONFIG_COMPAT_BRK unsigned brk_randomized:1; #endif -- cgit v1.2.3 From ac35a490237446b71e3b4b782b1596967edd0aa8 Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Sun, 18 Sep 2022 02:00:03 -0600 Subject: mm: multi-gen LRU: minimal implementation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit To avoid confusion, the terms "promotion" and "demotion" will be applied to the multi-gen LRU, as a new convention; the terms "activation" and "deactivation" will be applied to the active/inactive LRU, as usual. The aging produces young generations. Given an lruvec, it increments max_seq when max_seq-min_seq+1 approaches MIN_NR_GENS. The aging promotes hot pages to the youngest generation when it finds them accessed through page tables; the demotion of cold pages happens consequently when it increments max_seq. Promotion in the aging path does not involve any LRU list operations, only the updates of the gen counter and lrugen->nr_pages[]; demotion, unless as the result of the increment of max_seq, requires LRU list operations, e.g., lru_deactivate_fn(). The aging has the complexity O(nr_hot_pages), since it is only interested in hot pages. The eviction consumes old generations. Given an lruvec, it increments min_seq when lrugen->lists[] indexed by min_seq%MAX_NR_GENS becomes empty. A feedback loop modeled after the PID controller monitors refaults over anon and file types and decides which type to evict when both types are available from the same generation. The protection of pages accessed multiple times through file descriptors takes place in the eviction path. Each generation is divided into multiple tiers. A page accessed N times through file descriptors is in tier order_base_2(N). Tiers do not have dedicated lrugen->lists[], only bits in folio->flags. The aforementioned feedback loop also monitors refaults over all tiers and decides when to protect pages in which tiers (N>1), using the first tier (N=0,1) as a baseline. The first tier contains single-use unmapped clean pages, which are most likely the best choices. In contrast to promotion in the aging path, the protection of a page in the eviction path is achieved by moving this page to the next generation, i.e., min_seq+1, if the feedback loop decides so. This approach has the following advantages: 1. It removes the cost of activation in the buffered access path by inferring whether pages accessed multiple times through file descriptors are statistically hot and thus worth protecting in the eviction path. 2. It takes pages accessed through page tables into account and avoids overprotecting pages accessed multiple times through file descriptors. (Pages accessed through page tables are in the first tier, since N=0.) 3. More tiers provide better protection for pages accessed more than twice through file descriptors, when under heavy buffered I/O workloads. Server benchmark results: Single workload: fio (buffered I/O): +[30, 32]% IOPS BW 5.19-rc1: 2673k 10.2GiB/s patch1-6: 3491k 13.3GiB/s Single workload: memcached (anon): -[4, 6]% Ops/sec KB/sec 5.19-rc1: 1161501.04 45177.25 patch1-6: 1106168.46 43025.04 Configurations: CPU: two Xeon 6154 Mem: total 256G Node 1 was only used as a ram disk to reduce the variance in the results. patch drivers/block/brd.c < gfp_flags = GFP_NOIO | __GFP_ZERO | __GFP_HIGHMEM | __GFP_THISNODE; > page = alloc_pages_node(1, gfp_flags, 0); EOF cat >>/etc/systemd/system.conf <>/etc/memcached.conf </sys/fs/cgroup/user.slice/test/memory.max echo $$ >/sys/fs/cgroup/user.slice/test/cgroup.procs fio -name=mglru --numjobs=72 --directory=/mnt --size=1408m \ --buffered=1 --ioengine=io_uring --iodepth=128 \ --iodepth_batch_submit=32 --iodepth_batch_complete=32 \ --rw=randread --random_distribution=random --norandommap \ --time_based --ramp_time=10m --runtime=5m --group_reporting cat memcached.sh modprobe brd rd_nr=1 rd_size=113246208 swapoff -a mkswap /dev/ram0 swapon /dev/ram0 memtier_benchmark -S /var/run/memcached/memcached.sock \ -P memcache_binary -n allkeys --key-minimum=1 \ --key-maximum=65000000 --key-pattern=P:P -c 1 -t 36 \ --ratio 1:0 --pipeline 8 -d 2000 memtier_benchmark -S /var/run/memcached/memcached.sock \ -P memcache_binary -n allkeys --key-minimum=1 \ --key-maximum=65000000 --key-pattern=R:R -c 1 -t 36 \ --ratio 0:1 --pipeline 8 --randomize --distinct-client-seed Client benchmark results: kswapd profiles: 5.19-rc1 40.33% page_vma_mapped_walk (overhead) 21.80% lzo1x_1_do_compress (real work) 7.53% do_raw_spin_lock 3.95% _raw_spin_unlock_irq 2.52% vma_interval_tree_iter_next 2.37% folio_referenced_one 2.28% vma_interval_tree_subtree_search 1.97% anon_vma_interval_tree_iter_first 1.60% ptep_clear_flush 1.06% __zram_bvec_write patch1-6 39.03% lzo1x_1_do_compress (real work) 18.47% page_vma_mapped_walk (overhead) 6.74% _raw_spin_unlock_irq 3.97% do_raw_spin_lock 2.49% ptep_clear_flush 2.48% anon_vma_interval_tree_iter_first 1.92% folio_referenced_one 1.88% __zram_bvec_write 1.48% memmove 1.31% vma_interval_tree_iter_next Configurations: CPU: single Snapdragon 7c Mem: total 4G ChromeOS MemoryPressure [1] [1] https://chromium.googlesource.com/chromiumos/platform/tast-tests/ Link: https://lkml.kernel.org/r/20220918080010.2920238-7-yuzhao@google.com Signed-off-by: Yu Zhao Acked-by: Brian Geffon Acked-by: Jan Alexander Steffens (heftig) Acked-by: Oleksandr Natalenko Acked-by: Steven Barrett Acked-by: Suleiman Souhlal Tested-by: Daniel Byrne Tested-by: Donald Carr Tested-by: Holger Hoffstätte Tested-by: Konstantin Kharlamov Tested-by: Shuang Zhai Tested-by: Sofia Trinh Tested-by: Vaibhav Jain Cc: Andi Kleen Cc: Aneesh Kumar K.V Cc: Barry Song Cc: Catalin Marinas Cc: Dave Hansen Cc: Hillf Danton Cc: Jens Axboe Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Linus Torvalds Cc: Matthew Wilcox Cc: Mel Gorman Cc: Miaohe Lin Cc: Michael Larabel Cc: Michal Hocko Cc: Mike Rapoport Cc: Mike Rapoport Cc: Peter Zijlstra Cc: Qi Zheng Cc: Tejun Heo Cc: Vlastimil Babka Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/mm_inline.h | 36 ++++++++++++++++++++++++++++++++++ include/linux/mmzone.h | 41 +++++++++++++++++++++++++++++++++++++++ include/linux/page-flags-layout.h | 5 ++++- 3 files changed, 81 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 2ff703900fd0..f2b2296a42f9 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -121,6 +121,33 @@ static inline int lru_gen_from_seq(unsigned long seq) return seq % MAX_NR_GENS; } +static inline int lru_hist_from_seq(unsigned long seq) +{ + return seq % NR_HIST_GENS; +} + +static inline int lru_tier_from_refs(int refs) +{ + VM_WARN_ON_ONCE(refs > BIT(LRU_REFS_WIDTH)); + + /* see the comment in folio_lru_refs() */ + return order_base_2(refs + 1); +} + +static inline int folio_lru_refs(struct folio *folio) +{ + unsigned long flags = READ_ONCE(folio->flags); + bool workingset = flags & BIT(PG_workingset); + + /* + * Return the number of accesses beyond PG_referenced, i.e., N-1 if the + * total number of accesses is N>1, since N=0,1 both map to the first + * tier. lru_tier_from_refs() will account for this off-by-one. Also see + * the comment on MAX_NR_TIERS. + */ + return ((flags & LRU_REFS_MASK) >> LRU_REFS_PGOFF) + workingset; +} + static inline int folio_lru_gen(struct folio *folio) { unsigned long flags = READ_ONCE(folio->flags); @@ -173,6 +200,15 @@ static inline void lru_gen_update_size(struct lruvec *lruvec, struct folio *foli __update_lru_size(lruvec, lru, zone, -delta); return; } + + /* promotion */ + if (!lru_gen_is_active(lruvec, old_gen) && lru_gen_is_active(lruvec, new_gen)) { + __update_lru_size(lruvec, lru, zone, -delta); + __update_lru_size(lruvec, lru + LRU_ACTIVE, zone, delta); + } + + /* demotion requires isolation, e.g., lru_deactivate_fn() */ + VM_WARN_ON_ONCE(lru_gen_is_active(lruvec, old_gen) && !lru_gen_is_active(lruvec, new_gen)); } static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 6f4ea078d90f..7e343420bfb1 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -350,6 +350,28 @@ enum lruvec_flags { #define MIN_NR_GENS 2U #define MAX_NR_GENS 4U +/* + * Each generation is divided into multiple tiers. A page accessed N times + * through file descriptors is in tier order_base_2(N). A page in the first tier + * (N=0,1) is marked by PG_referenced unless it was faulted in through page + * tables or read ahead. A page in any other tier (N>1) is marked by + * PG_referenced and PG_workingset. This implies a minimum of two tiers is + * supported without using additional bits in folio->flags. + * + * In contrast to moving across generations which requires the LRU lock, moving + * across tiers only involves atomic operations on folio->flags and therefore + * has a negligible cost in the buffered access path. In the eviction path, + * comparisons of refaulted/(evicted+protected) from the first tier and the + * rest infer whether pages accessed multiple times through file descriptors + * are statistically hot and thus worth protecting. + * + * MAX_NR_TIERS is set to 4 so that the multi-gen LRU can support twice the + * number of categories of the active/inactive LRU when keeping track of + * accesses through file descriptors. This uses MAX_NR_TIERS-2 spare bits in + * folio->flags. + */ +#define MAX_NR_TIERS 4U + #ifndef __GENERATING_BOUNDS_H struct lruvec; @@ -364,6 +386,16 @@ enum { LRU_GEN_FILE, }; +#define MIN_LRU_BATCH BITS_PER_LONG +#define MAX_LRU_BATCH (MIN_LRU_BATCH * 64) + +/* whether to keep historical stats from evicted generations */ +#ifdef CONFIG_LRU_GEN_STATS +#define NR_HIST_GENS MAX_NR_GENS +#else +#define NR_HIST_GENS 1U +#endif + /* * The youngest generation number is stored in max_seq for both anon and file * types as they are aged on an equal footing. The oldest generation numbers are @@ -386,6 +418,15 @@ struct lru_gen_struct { struct list_head lists[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; /* the multi-gen LRU sizes, eventually consistent */ long nr_pages[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; + /* the exponential moving average of refaulted */ + unsigned long avg_refaulted[ANON_AND_FILE][MAX_NR_TIERS]; + /* the exponential moving average of evicted+protected */ + unsigned long avg_total[ANON_AND_FILE][MAX_NR_TIERS]; + /* the first tier doesn't need protection, hence the minus one */ + unsigned long protected[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS - 1]; + /* can be modified without holding the LRU lock */ + atomic_long_t evicted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS]; + atomic_long_t refaulted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS]; }; void lru_gen_init_lruvec(struct lruvec *lruvec); diff --git a/include/linux/page-flags-layout.h b/include/linux/page-flags-layout.h index 240905407a18..7d79818dc065 100644 --- a/include/linux/page-flags-layout.h +++ b/include/linux/page-flags-layout.h @@ -106,7 +106,10 @@ #error "Not enough bits in page flags" #endif -#define LRU_REFS_WIDTH 0 +/* see the comment on MAX_NR_TIERS */ +#define LRU_REFS_WIDTH min(__LRU_REFS_WIDTH, BITS_PER_LONG - NR_PAGEFLAGS - \ + ZONES_WIDTH - LRU_GEN_WIDTH - SECTIONS_WIDTH - \ + NODES_WIDTH - KASAN_TAG_WIDTH - LAST_CPUPID_WIDTH) #endif #endif /* _LINUX_PAGE_FLAGS_LAYOUT */ -- cgit v1.2.3 From 018ee47f14893d500131dfca2ff9f3ff8ebd4ed2 Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Sun, 18 Sep 2022 02:00:04 -0600 Subject: mm: multi-gen LRU: exploit locality in rmap MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Searching the rmap for PTEs mapping each page on an LRU list (to test and clear the accessed bit) can be expensive because pages from different VMAs (PA space) are not cache friendly to the rmap (VA space). For workloads mostly using mapped pages, searching the rmap can incur the highest CPU cost in the reclaim path. This patch exploits spatial locality to reduce the trips into the rmap. When shrink_page_list() walks the rmap and finds a young PTE, a new function lru_gen_look_around() scans at most BITS_PER_LONG-1 adjacent PTEs. On finding another young PTE, it clears the accessed bit and updates the gen counter of the page mapped by this PTE to (max_seq%MAX_NR_GENS)+1. Server benchmark results: Single workload: fio (buffered I/O): no change Single workload: memcached (anon): +[3, 5]% Ops/sec KB/sec patch1-6: 1106168.46 43025.04 patch1-7: 1147696.57 44640.29 Configurations: no change Client benchmark results: kswapd profiles: patch1-6 39.03% lzo1x_1_do_compress (real work) 18.47% page_vma_mapped_walk (overhead) 6.74% _raw_spin_unlock_irq 3.97% do_raw_spin_lock 2.49% ptep_clear_flush 2.48% anon_vma_interval_tree_iter_first 1.92% folio_referenced_one 1.88% __zram_bvec_write 1.48% memmove 1.31% vma_interval_tree_iter_next patch1-7 48.16% lzo1x_1_do_compress (real work) 8.20% page_vma_mapped_walk (overhead) 7.06% _raw_spin_unlock_irq 2.92% ptep_clear_flush 2.53% __zram_bvec_write 2.11% do_raw_spin_lock 2.02% memmove 1.93% lru_gen_look_around 1.56% free_unref_page_list 1.40% memset Configurations: no change Link: https://lkml.kernel.org/r/20220918080010.2920238-8-yuzhao@google.com Signed-off-by: Yu Zhao Acked-by: Barry Song Acked-by: Brian Geffon Acked-by: Jan Alexander Steffens (heftig) Acked-by: Oleksandr Natalenko Acked-by: Steven Barrett Acked-by: Suleiman Souhlal Tested-by: Daniel Byrne Tested-by: Donald Carr Tested-by: Holger Hoffstätte Tested-by: Konstantin Kharlamov Tested-by: Shuang Zhai Tested-by: Sofia Trinh Tested-by: Vaibhav Jain Cc: Andi Kleen Cc: Aneesh Kumar K.V Cc: Catalin Marinas Cc: Dave Hansen Cc: Hillf Danton Cc: Jens Axboe Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Linus Torvalds Cc: Matthew Wilcox Cc: Mel Gorman Cc: Miaohe Lin Cc: Michael Larabel Cc: Michal Hocko Cc: Mike Rapoport Cc: Mike Rapoport Cc: Peter Zijlstra Cc: Qi Zheng Cc: Tejun Heo Cc: Vlastimil Babka Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/memcontrol.h | 31 +++++++++++++++++++++++++++++++ include/linux/mm.h | 5 +++++ include/linux/mmzone.h | 6 ++++++ 3 files changed, 42 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index a2461f9a8738..9b8ab121d948 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -445,6 +445,7 @@ static inline struct obj_cgroup *__folio_objcg(struct folio *folio) * - LRU isolation * - lock_page_memcg() * - exclusive reference + * - mem_cgroup_trylock_pages() * * For a kmem folio a caller should hold an rcu read lock to protect memcg * associated with a kmem folio from being released. @@ -506,6 +507,7 @@ static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio) * - LRU isolation * - lock_page_memcg() * - exclusive reference + * - mem_cgroup_trylock_pages() * * For a kmem page a caller should hold an rcu read lock to protect memcg * associated with a kmem page from being released. @@ -960,6 +962,23 @@ void unlock_page_memcg(struct page *page); void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val); +/* try to stablize folio_memcg() for all the pages in a memcg */ +static inline bool mem_cgroup_trylock_pages(struct mem_cgroup *memcg) +{ + rcu_read_lock(); + + if (mem_cgroup_disabled() || !atomic_read(&memcg->moving_account)) + return true; + + rcu_read_unlock(); + return false; +} + +static inline void mem_cgroup_unlock_pages(void) +{ + rcu_read_unlock(); +} + /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void mod_memcg_state(struct mem_cgroup *memcg, int idx, int val) @@ -1434,6 +1453,18 @@ static inline void folio_memcg_unlock(struct folio *folio) { } +static inline bool mem_cgroup_trylock_pages(struct mem_cgroup *memcg) +{ + /* to match folio_memcg_rcu() */ + rcu_read_lock(); + return true; +} + +static inline void mem_cgroup_unlock_pages(void) +{ + rcu_read_unlock(); +} + static inline void mem_cgroup_handle_over_high(void) { } diff --git a/include/linux/mm.h b/include/linux/mm.h index 8a5ad9d050bf..7cc9ffc19e7f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1490,6 +1490,11 @@ static inline unsigned long folio_pfn(struct folio *folio) return page_to_pfn(&folio->page); } +static inline struct folio *pfn_folio(unsigned long pfn) +{ + return page_folio(pfn_to_page(pfn)); +} + static inline atomic_t *folio_pincount_ptr(struct folio *folio) { return &folio_page(folio, 1)->compound_pincount; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 7e343420bfb1..9ef5aa37c60c 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -375,6 +375,7 @@ enum lruvec_flags { #ifndef __GENERATING_BOUNDS_H struct lruvec; +struct page_vma_mapped_walk; #define LRU_GEN_MASK ((BIT(LRU_GEN_WIDTH) - 1) << LRU_GEN_PGOFF) #define LRU_REFS_MASK ((BIT(LRU_REFS_WIDTH) - 1) << LRU_REFS_PGOFF) @@ -430,6 +431,7 @@ struct lru_gen_struct { }; void lru_gen_init_lruvec(struct lruvec *lruvec); +void lru_gen_look_around(struct page_vma_mapped_walk *pvmw); #ifdef CONFIG_MEMCG void lru_gen_init_memcg(struct mem_cgroup *memcg); @@ -442,6 +444,10 @@ static inline void lru_gen_init_lruvec(struct lruvec *lruvec) { } +static inline void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) +{ +} + #ifdef CONFIG_MEMCG static inline void lru_gen_init_memcg(struct mem_cgroup *memcg) { -- cgit v1.2.3 From bd74fdaea146029e4fa12c6de89adbe0779348a9 Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Sun, 18 Sep 2022 02:00:05 -0600 Subject: mm: multi-gen LRU: support page table walks MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit To further exploit spatial locality, the aging prefers to walk page tables to search for young PTEs and promote hot pages. A kill switch will be added in the next patch to disable this behavior. When disabled, the aging relies on the rmap only. NB: this behavior has nothing similar with the page table scanning in the 2.4 kernel [1], which searches page tables for old PTEs, adds cold pages to swapcache and unmaps them. To avoid confusion, the term "iteration" specifically means the traversal of an entire mm_struct list; the term "walk" will be applied to page tables and the rmap, as usual. An mm_struct list is maintained for each memcg, and an mm_struct follows its owner task to the new memcg when this task is migrated. Given an lruvec, the aging iterates lruvec_memcg()->mm_list and calls walk_page_range() with each mm_struct on this list to promote hot pages before it increments max_seq. When multiple page table walkers iterate the same list, each of them gets a unique mm_struct; therefore they can run concurrently. Page table walkers ignore any misplaced pages, e.g., if an mm_struct was migrated, pages it left in the previous memcg will not be promoted when its current memcg is under reclaim. Similarly, page table walkers will not promote pages from nodes other than the one under reclaim. This patch uses the following optimizations when walking page tables: 1. It tracks the usage of mm_struct's between context switches so that page table walkers can skip processes that have been sleeping since the last iteration. 2. It uses generational Bloom filters to record populated branches so that page table walkers can reduce their search space based on the query results, e.g., to skip page tables containing mostly holes or misplaced pages. 3. It takes advantage of the accessed bit in non-leaf PMD entries when CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG=y. 4. It does not zigzag between a PGD table and the same PMD table spanning multiple VMAs. IOW, it finishes all the VMAs within the range of the same PMD table before it returns to a PGD table. This improves the cache performance for workloads that have large numbers of tiny VMAs [2], especially when CONFIG_PGTABLE_LEVELS=5. Server benchmark results: Single workload: fio (buffered I/O): no change Single workload: memcached (anon): +[8, 10]% Ops/sec KB/sec patch1-7: 1147696.57 44640.29 patch1-8: 1245274.91 48435.66 Configurations: no change Client benchmark results: kswapd profiles: patch1-7 48.16% lzo1x_1_do_compress (real work) 8.20% page_vma_mapped_walk (overhead) 7.06% _raw_spin_unlock_irq 2.92% ptep_clear_flush 2.53% __zram_bvec_write 2.11% do_raw_spin_lock 2.02% memmove 1.93% lru_gen_look_around 1.56% free_unref_page_list 1.40% memset patch1-8 49.44% lzo1x_1_do_compress (real work) 6.19% page_vma_mapped_walk (overhead) 5.97% _raw_spin_unlock_irq 3.13% get_pfn_folio 2.85% ptep_clear_flush 2.42% __zram_bvec_write 2.08% do_raw_spin_lock 1.92% memmove 1.44% alloc_zspage 1.36% memset Configurations: no change Thanks to the following developers for their efforts [3]. kernel test robot [1] https://lwn.net/Articles/23732/ [2] https://llvm.org/docs/ScudoHardenedAllocator.html [3] https://lore.kernel.org/r/202204160827.ekEARWQo-lkp@intel.com/ Link: https://lkml.kernel.org/r/20220918080010.2920238-9-yuzhao@google.com Signed-off-by: Yu Zhao Acked-by: Brian Geffon Acked-by: Jan Alexander Steffens (heftig) Acked-by: Oleksandr Natalenko Acked-by: Steven Barrett Acked-by: Suleiman Souhlal Tested-by: Daniel Byrne Tested-by: Donald Carr Tested-by: Holger Hoffstätte Tested-by: Konstantin Kharlamov Tested-by: Shuang Zhai Tested-by: Sofia Trinh Tested-by: Vaibhav Jain Cc: Andi Kleen Cc: Aneesh Kumar K.V Cc: Barry Song Cc: Catalin Marinas Cc: Dave Hansen Cc: Hillf Danton Cc: Jens Axboe Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Linus Torvalds Cc: Matthew Wilcox Cc: Mel Gorman Cc: Miaohe Lin Cc: Michael Larabel Cc: Michal Hocko Cc: Mike Rapoport Cc: Mike Rapoport Cc: Peter Zijlstra Cc: Qi Zheng Cc: Tejun Heo Cc: Vlastimil Babka Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/memcontrol.h | 5 +++ include/linux/mm_types.h | 76 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/mmzone.h | 56 +++++++++++++++++++++++++++++++++- include/linux/swap.h | 4 +++ 4 files changed, 140 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 9b8ab121d948..344022f102c2 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -350,6 +350,11 @@ struct mem_cgroup { struct deferred_split deferred_split_queue; #endif +#ifdef CONFIG_LRU_GEN + /* per-memcg mm_struct list */ + struct lru_gen_mm_list mm_list; +#endif + struct mem_cgroup_per_node *nodeinfo[]; }; diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index cf97f3884fda..e1797813cc2c 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -672,6 +672,22 @@ struct mm_struct { */ unsigned long ksm_merging_pages; #endif +#ifdef CONFIG_LRU_GEN + struct { + /* this mm_struct is on lru_gen_mm_list */ + struct list_head list; + /* + * Set when switching to this mm_struct, as a hint of + * whether it has been used since the last time per-node + * page table walkers cleared the corresponding bits. + */ + unsigned long bitmap; +#ifdef CONFIG_MEMCG + /* points to the memcg of "owner" above */ + struct mem_cgroup *memcg; +#endif + } lru_gen; +#endif /* CONFIG_LRU_GEN */ } __randomize_layout; /* @@ -698,6 +714,66 @@ static inline cpumask_t *mm_cpumask(struct mm_struct *mm) return (struct cpumask *)&mm->cpu_bitmap; } +#ifdef CONFIG_LRU_GEN + +struct lru_gen_mm_list { + /* mm_struct list for page table walkers */ + struct list_head fifo; + /* protects the list above */ + spinlock_t lock; +}; + +void lru_gen_add_mm(struct mm_struct *mm); +void lru_gen_del_mm(struct mm_struct *mm); +#ifdef CONFIG_MEMCG +void lru_gen_migrate_mm(struct mm_struct *mm); +#endif + +static inline void lru_gen_init_mm(struct mm_struct *mm) +{ + INIT_LIST_HEAD(&mm->lru_gen.list); + mm->lru_gen.bitmap = 0; +#ifdef CONFIG_MEMCG + mm->lru_gen.memcg = NULL; +#endif +} + +static inline void lru_gen_use_mm(struct mm_struct *mm) +{ + /* + * When the bitmap is set, page reclaim knows this mm_struct has been + * used since the last time it cleared the bitmap. So it might be worth + * walking the page tables of this mm_struct to clear the accessed bit. + */ + WRITE_ONCE(mm->lru_gen.bitmap, -1); +} + +#else /* !CONFIG_LRU_GEN */ + +static inline void lru_gen_add_mm(struct mm_struct *mm) +{ +} + +static inline void lru_gen_del_mm(struct mm_struct *mm) +{ +} + +#ifdef CONFIG_MEMCG +static inline void lru_gen_migrate_mm(struct mm_struct *mm) +{ +} +#endif + +static inline void lru_gen_init_mm(struct mm_struct *mm) +{ +} + +static inline void lru_gen_use_mm(struct mm_struct *mm) +{ +} + +#endif /* CONFIG_LRU_GEN */ + struct mmu_gather; extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm); extern void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm); diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 9ef5aa37c60c..b1635c4020dc 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -408,7 +408,7 @@ enum { * min_seq behind. * * The number of pages in each generation is eventually consistent and therefore - * can be transiently negative. + * can be transiently negative when reset_batch_size() is pending. */ struct lru_gen_struct { /* the aging increments the youngest generation number */ @@ -430,6 +430,53 @@ struct lru_gen_struct { atomic_long_t refaulted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS]; }; +enum { + MM_LEAF_TOTAL, /* total leaf entries */ + MM_LEAF_OLD, /* old leaf entries */ + MM_LEAF_YOUNG, /* young leaf entries */ + MM_NONLEAF_TOTAL, /* total non-leaf entries */ + MM_NONLEAF_FOUND, /* non-leaf entries found in Bloom filters */ + MM_NONLEAF_ADDED, /* non-leaf entries added to Bloom filters */ + NR_MM_STATS +}; + +/* double-buffering Bloom filters */ +#define NR_BLOOM_FILTERS 2 + +struct lru_gen_mm_state { + /* set to max_seq after each iteration */ + unsigned long seq; + /* where the current iteration continues (inclusive) */ + struct list_head *head; + /* where the last iteration ended (exclusive) */ + struct list_head *tail; + /* to wait for the last page table walker to finish */ + struct wait_queue_head wait; + /* Bloom filters flip after each iteration */ + unsigned long *filters[NR_BLOOM_FILTERS]; + /* the mm stats for debugging */ + unsigned long stats[NR_HIST_GENS][NR_MM_STATS]; + /* the number of concurrent page table walkers */ + int nr_walkers; +}; + +struct lru_gen_mm_walk { + /* the lruvec under reclaim */ + struct lruvec *lruvec; + /* unstable max_seq from lru_gen_struct */ + unsigned long max_seq; + /* the next address within an mm to scan */ + unsigned long next_addr; + /* to batch promoted pages */ + int nr_pages[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; + /* to batch the mm stats */ + int mm_stats[NR_MM_STATS]; + /* total batched items */ + int batched; + bool can_swap; + bool force_scan; +}; + void lru_gen_init_lruvec(struct lruvec *lruvec); void lru_gen_look_around(struct page_vma_mapped_walk *pvmw); @@ -480,6 +527,8 @@ struct lruvec { #ifdef CONFIG_LRU_GEN /* evictable pages divided into generations */ struct lru_gen_struct lrugen; + /* to concurrently iterate lru_gen_mm_list */ + struct lru_gen_mm_state mm_state; #endif #ifdef CONFIG_MEMCG struct pglist_data *pgdat; @@ -1176,6 +1225,11 @@ typedef struct pglist_data { unsigned long flags; +#ifdef CONFIG_LRU_GEN + /* kswap mm walk data */ + struct lru_gen_mm_walk mm_walk; +#endif + ZONE_PADDING(_pad2_) /* Per-node vmstats */ diff --git a/include/linux/swap.h b/include/linux/swap.h index 43150b9bbc5c..6308150b234a 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -162,6 +162,10 @@ union swap_header { */ struct reclaim_state { unsigned long reclaimed_slab; +#ifdef CONFIG_LRU_GEN + /* per-thread mm walk data */ + struct lru_gen_mm_walk *mm_walk; +#endif }; #ifdef __KERNEL__ -- cgit v1.2.3 From 354ed597442952fb680c9cafc7e4eb8a76f9514c Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Sun, 18 Sep 2022 02:00:07 -0600 Subject: mm: multi-gen LRU: kill switch MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add /sys/kernel/mm/lru_gen/enabled as a kill switch. Components that can be disabled include: 0x0001: the multi-gen LRU core 0x0002: walking page table, when arch_has_hw_pte_young() returns true 0x0004: clearing the accessed bit in non-leaf PMD entries, when CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG=y [yYnN]: apply to all the components above E.g., echo y >/sys/kernel/mm/lru_gen/enabled cat /sys/kernel/mm/lru_gen/enabled 0x0007 echo 5 >/sys/kernel/mm/lru_gen/enabled cat /sys/kernel/mm/lru_gen/enabled 0x0005 NB: the page table walks happen on the scale of seconds under heavy memory pressure, in which case the mmap_lock contention is a lesser concern, compared with the LRU lock contention and the I/O congestion. So far the only well-known case of the mmap_lock contention happens on Android, due to Scudo [1] which allocates several thousand VMAs for merely a few hundred MBs. The SPF and the Maple Tree also have provided their own assessments [2][3]. However, if walking page tables does worsen the mmap_lock contention, the kill switch can be used to disable it. In this case the multi-gen LRU will suffer a minor performance degradation, as shown previously. Clearing the accessed bit in non-leaf PMD entries can also be disabled, since this behavior was not tested on x86 varieties other than Intel and AMD. [1] https://source.android.com/devices/tech/debug/scudo [2] https://lore.kernel.org/r/20220128131006.67712-1-michel@lespinasse.org/ [3] https://lore.kernel.org/r/20220426150616.3937571-1-Liam.Howlett@oracle.com/ Link: https://lkml.kernel.org/r/20220918080010.2920238-11-yuzhao@google.com Signed-off-by: Yu Zhao Acked-by: Brian Geffon Acked-by: Jan Alexander Steffens (heftig) Acked-by: Oleksandr Natalenko Acked-by: Steven Barrett Acked-by: Suleiman Souhlal Tested-by: Daniel Byrne Tested-by: Donald Carr Tested-by: Holger Hoffstätte Tested-by: Konstantin Kharlamov Tested-by: Shuang Zhai Tested-by: Sofia Trinh Tested-by: Vaibhav Jain Cc: Andi Kleen Cc: Aneesh Kumar K.V Cc: Barry Song Cc: Catalin Marinas Cc: Dave Hansen Cc: Hillf Danton Cc: Jens Axboe Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Linus Torvalds Cc: Matthew Wilcox Cc: Mel Gorman Cc: Miaohe Lin Cc: Michael Larabel Cc: Michal Hocko Cc: Mike Rapoport Cc: Mike Rapoport Cc: Peter Zijlstra Cc: Qi Zheng Cc: Tejun Heo Cc: Vlastimil Babka Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/cgroup.h | 15 ++++++++++++++- include/linux/mm_inline.h | 15 +++++++++++++-- include/linux/mmzone.h | 9 +++++++++ 3 files changed, 36 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index ac5d0515680e..9179463c3c9f 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -432,6 +432,18 @@ static inline void cgroup_put(struct cgroup *cgrp) css_put(&cgrp->self); } +extern struct mutex cgroup_mutex; + +static inline void cgroup_lock(void) +{ + mutex_lock(&cgroup_mutex); +} + +static inline void cgroup_unlock(void) +{ + mutex_unlock(&cgroup_mutex); +} + /** * task_css_set_check - obtain a task's css_set with extra access conditions * @task: the task to obtain css_set for @@ -446,7 +458,6 @@ static inline void cgroup_put(struct cgroup *cgrp) * as locks used during the cgroup_subsys::attach() methods. */ #ifdef CONFIG_PROVE_RCU -extern struct mutex cgroup_mutex; extern spinlock_t css_set_lock; #define task_css_set_check(task, __c) \ rcu_dereference_check((task)->cgroups, \ @@ -708,6 +719,8 @@ struct cgroup; static inline u64 cgroup_id(const struct cgroup *cgrp) { return 1; } static inline void css_get(struct cgroup_subsys_state *css) {} static inline void css_put(struct cgroup_subsys_state *css) {} +static inline void cgroup_lock(void) {} +static inline void cgroup_unlock(void) {} static inline int cgroup_attach_task_all(struct task_struct *from, struct task_struct *t) { return 0; } static inline int cgroupstats_build(struct cgroupstats *stats, diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index f2b2296a42f9..4949eda9a9a2 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -106,10 +106,21 @@ static __always_inline enum lru_list folio_lru_list(struct folio *folio) #ifdef CONFIG_LRU_GEN +#ifdef CONFIG_LRU_GEN_ENABLED static inline bool lru_gen_enabled(void) { - return true; + DECLARE_STATIC_KEY_TRUE(lru_gen_caps[NR_LRU_GEN_CAPS]); + + return static_branch_likely(&lru_gen_caps[LRU_GEN_CORE]); +} +#else +static inline bool lru_gen_enabled(void) +{ + DECLARE_STATIC_KEY_FALSE(lru_gen_caps[NR_LRU_GEN_CAPS]); + + return static_branch_unlikely(&lru_gen_caps[LRU_GEN_CORE]); } +#endif static inline bool lru_gen_in_fault(void) { @@ -222,7 +233,7 @@ static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, VM_WARN_ON_ONCE_FOLIO(gen != -1, folio); - if (folio_test_unevictable(folio)) + if (folio_test_unevictable(folio) || !lrugen->enabled) return false; /* * There are three common cases for this page: diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index b1635c4020dc..95c58c7fbdff 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -387,6 +387,13 @@ enum { LRU_GEN_FILE, }; +enum { + LRU_GEN_CORE, + LRU_GEN_MM_WALK, + LRU_GEN_NONLEAF_YOUNG, + NR_LRU_GEN_CAPS +}; + #define MIN_LRU_BATCH BITS_PER_LONG #define MAX_LRU_BATCH (MIN_LRU_BATCH * 64) @@ -428,6 +435,8 @@ struct lru_gen_struct { /* can be modified without holding the LRU lock */ atomic_long_t evicted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS]; atomic_long_t refaulted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS]; + /* whether the multi-gen LRU is enabled */ + bool enabled; }; enum { -- cgit v1.2.3 From 1332a809d95a4fc763cabe5ecb6d4fb6a6d941b2 Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Sun, 18 Sep 2022 02:00:08 -0600 Subject: mm: multi-gen LRU: thrashing prevention MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add /sys/kernel/mm/lru_gen/min_ttl_ms for thrashing prevention, as requested by many desktop users [1]. When set to value N, it prevents the working set of N milliseconds from getting evicted. The OOM killer is triggered if this working set cannot be kept in memory. Based on the average human detectable lag (~100ms), N=1000 usually eliminates intolerable lags due to thrashing. Larger values like N=3000 make lags less noticeable at the risk of premature OOM kills. Compared with the size-based approach [2], this time-based approach has the following advantages: 1. It is easier to configure because it is agnostic to applications and memory sizes. 2. It is more reliable because it is directly wired to the OOM killer. [1] https://lore.kernel.org/r/Ydza%2FzXKY9ATRoh6@google.com/ [2] https://lore.kernel.org/r/20101028191523.GA14972@google.com/ Link: https://lkml.kernel.org/r/20220918080010.2920238-12-yuzhao@google.com Signed-off-by: Yu Zhao Acked-by: Brian Geffon Acked-by: Jan Alexander Steffens (heftig) Acked-by: Oleksandr Natalenko Acked-by: Steven Barrett Acked-by: Suleiman Souhlal Tested-by: Daniel Byrne Tested-by: Donald Carr Tested-by: Holger Hoffstätte Tested-by: Konstantin Kharlamov Tested-by: Shuang Zhai Tested-by: Sofia Trinh Tested-by: Vaibhav Jain Cc: Andi Kleen Cc: Aneesh Kumar K.V Cc: Barry Song Cc: Catalin Marinas Cc: Dave Hansen Cc: Hillf Danton Cc: Jens Axboe Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Linus Torvalds Cc: Matthew Wilcox Cc: Mel Gorman Cc: Miaohe Lin Cc: Michael Larabel Cc: Michal Hocko Cc: Mike Rapoport Cc: Mike Rapoport Cc: Peter Zijlstra Cc: Qi Zheng Cc: Tejun Heo Cc: Vlastimil Babka Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/mmzone.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 95c58c7fbdff..87347945270b 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -422,6 +422,8 @@ struct lru_gen_struct { unsigned long max_seq; /* the eviction increments the oldest generation numbers */ unsigned long min_seq[ANON_AND_FILE]; + /* the birth time of each generation in jiffies */ + unsigned long timestamps[MAX_NR_GENS]; /* the multi-gen LRU lists, lazily sorted on eviction */ struct list_head lists[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; /* the multi-gen LRU sizes, eventually consistent */ -- cgit v1.2.3 From d6c3af7d8a2ba5602c28841248c551a712ac50f5 Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Sun, 18 Sep 2022 02:00:09 -0600 Subject: mm: multi-gen LRU: debugfs interface MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add /sys/kernel/debug/lru_gen for working set estimation and proactive reclaim. These techniques are commonly used to optimize job scheduling (bin packing) in data centers [1][2]. Compared with the page table-based approach and the PFN-based approach, this lruvec-based approach has the following advantages: 1. It offers better choices because it is aware of memcgs, NUMA nodes, shared mappings and unmapped page cache. 2. It is more scalable because it is O(nr_hot_pages), whereas the PFN-based approach is O(nr_total_pages). Add /sys/kernel/debug/lru_gen_full for debugging. [1] https://dl.acm.org/doi/10.1145/3297858.3304053 [2] https://dl.acm.org/doi/10.1145/3503222.3507731 Link: https://lkml.kernel.org/r/20220918080010.2920238-13-yuzhao@google.com Signed-off-by: Yu Zhao Reviewed-by: Qi Zheng Acked-by: Brian Geffon Acked-by: Jan Alexander Steffens (heftig) Acked-by: Oleksandr Natalenko Acked-by: Steven Barrett Acked-by: Suleiman Souhlal Tested-by: Daniel Byrne Tested-by: Donald Carr Tested-by: Holger Hoffstätte Tested-by: Konstantin Kharlamov Tested-by: Shuang Zhai Tested-by: Sofia Trinh Tested-by: Vaibhav Jain Cc: Andi Kleen Cc: Aneesh Kumar K.V Cc: Barry Song Cc: Catalin Marinas Cc: Dave Hansen Cc: Hillf Danton Cc: Jens Axboe Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Linus Torvalds Cc: Matthew Wilcox Cc: Mel Gorman Cc: Miaohe Lin Cc: Michael Larabel Cc: Michal Hocko Cc: Mike Rapoport Cc: Mike Rapoport Cc: Peter Zijlstra Cc: Tejun Heo Cc: Vlastimil Babka Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/nodemask.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 4b71a96190a8..3a0eec9f2faa 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -493,6 +493,7 @@ static inline int num_node_state(enum node_states state) #define first_online_node 0 #define first_memory_node 0 #define next_online_node(nid) (MAX_NUMNODES) +#define next_memory_node(nid) (MAX_NUMNODES) #define nr_node_ids 1U #define nr_online_nodes 1U -- cgit v1.2.3 From 992bf77591cb7e696fcc59aa7e64d1200b673513 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Thu, 18 Aug 2022 18:40:33 +0530 Subject: mm/demotion: add support for explicit memory tiers Patch series "mm/demotion: Memory tiers and demotion", v15. The current kernel has the basic memory tiering support: Inactive pages on a higher tier NUMA node can be migrated (demoted) to a lower tier NUMA node to make room for new allocations on the higher tier NUMA node. Frequently accessed pages on a lower tier NUMA node can be migrated (promoted) to a higher tier NUMA node to improve the performance. In the current kernel, memory tiers are defined implicitly via a demotion path relationship between NUMA nodes, which is created during the kernel initialization and updated when a NUMA node is hot-added or hot-removed. The current implementation puts all nodes with CPU into the highest tier, and builds the tier hierarchy tier-by-tier by establishing the per-node demotion targets based on the distances between nodes. This current memory tier kernel implementation needs to be improved for several important use cases: * The current tier initialization code always initializes each memory-only NUMA node into a lower tier. But a memory-only NUMA node may have a high performance memory device (e.g. a DRAM-backed memory-only node on a virtual machine) and that should be put into a higher tier. * The current tier hierarchy always puts CPU nodes into the top tier. But on a system with HBM (e.g. GPU memory) devices, these memory-only HBM NUMA nodes should be in the top tier, and DRAM nodes with CPUs are better to be placed into the next lower tier. * Also because the current tier hierarchy always puts CPU nodes into the top tier, when a CPU is hot-added (or hot-removed) and triggers a memory node from CPU-less into a CPU node (or vice versa), the memory tier hierarchy gets changed, even though no memory node is added or removed. This can make the tier hierarchy unstable and make it difficult to support tier-based memory accounting. * A higher tier node can only be demoted to nodes with shortest distance on the next lower tier as defined by the demotion path, not any other node from any lower tier. This strict, demotion order does not work in all use cases (e.g. some use cases may want to allow cross-socket demotion to another node in the same demotion tier as a fallback when the preferred demotion node is out of space), and has resulted in the feature request for an interface to override the system-wide, per-node demotion order from the userspace. This demotion order is also inconsistent with the page allocation fallback order when all the nodes in a higher tier are out of space: The page allocation can fall back to any node from any lower tier, whereas the demotion order doesn't allow that. This patch series make the creation of memory tiers explicit under the control of device driver. Memory Tier Initialization ========================== Linux kernel presents memory devices as NUMA nodes and each memory device is of a specific type. The memory type of a device is represented by its abstract distance. A memory tier corresponds to a range of abstract distance. This allows for classifying memory devices with a specific performance range into a memory tier. By default, all memory nodes are assigned to the default tier with abstract distance 512. A device driver can move its memory nodes from the default tier. For example, PMEM can move its memory nodes below the default tier, whereas GPU can move its memory nodes above the default tier. The kernel initialization code makes the decision on which exact tier a memory node should be assigned to based on the requests from the device drivers as well as the memory device hardware information provided by the firmware. Hot-adding/removing CPUs doesn't affect memory tier hierarchy. This patch (of 10): In the current kernel, memory tiers are defined implicitly via a demotion path relationship between NUMA nodes, which is created during the kernel initialization and updated when a NUMA node is hot-added or hot-removed. The current implementation puts all nodes with CPU into the highest tier, and builds the tier hierarchy by establishing the per-node demotion targets based on the distances between nodes. This current memory tier kernel implementation needs to be improved for several important use cases, The current tier initialization code always initializes each memory-only NUMA node into a lower tier. But a memory-only NUMA node may have a high performance memory device (e.g. a DRAM-backed memory-only node on a virtual machine) that should be put into a higher tier. The current tier hierarchy always puts CPU nodes into the top tier. But on a system with HBM or GPU devices, the memory-only NUMA nodes mapping these devices should be in the top tier, and DRAM nodes with CPUs are better to be placed into the next lower tier. With current kernel higher tier node can only be demoted to nodes with shortest distance on the next lower tier as defined by the demotion path, not any other node from any lower tier. This strict, demotion order does not work in all use cases (e.g. some use cases may want to allow cross-socket demotion to another node in the same demotion tier as a fallback when the preferred demotion node is out of space), This demotion order is also inconsistent with the page allocation fallback order when all the nodes in a higher tier are out of space: The page allocation can fall back to any node from any lower tier, whereas the demotion order doesn't allow that. This patch series address the above by defining memory tiers explicitly. Linux kernel presents memory devices as NUMA nodes and each memory device is of a specific type. The memory type of a device is represented by its abstract distance. A memory tier corresponds to a range of abstract distance. This allows for classifying memory devices with a specific performance range into a memory tier. This patch configures the range/chunk size to be 128. The default DRAM abstract distance is 512. We can have 4 memory tiers below the default DRAM with abstract distance range 0 - 127, 127 - 255, 256- 383, 384 - 511. Faster memory devices can be placed in these faster(higher) memory tiers. Slower memory devices like persistent memory will have abstract distance higher than the default DRAM level. [akpm@linux-foundation.org: fix comment, per Aneesh] Link: https://lkml.kernel.org/r/20220818131042.113280-1-aneesh.kumar@linux.ibm.com Link: https://lkml.kernel.org/r/20220818131042.113280-2-aneesh.kumar@linux.ibm.com Signed-off-by: Aneesh Kumar K.V Reviewed-by: "Huang, Ying" Acked-by: Wei Xu Cc: Alistair Popple Cc: Bharata B Rao Cc: Dan Williams Cc: Dave Hansen Cc: Davidlohr Bueso Cc: Hesham Almatary Cc: Johannes Weiner Cc: Jonathan Cameron Cc: Michal Hocko Cc: Tim Chen Cc: Yang Shi Cc: Jagdish Gediya Cc: SeongJae Park Signed-off-by: Andrew Morton --- include/linux/memory-tiers.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) create mode 100644 include/linux/memory-tiers.h (limited to 'include/linux') diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h new file mode 100644 index 000000000000..ecada7bf4091 --- /dev/null +++ b/include/linux/memory-tiers.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_MEMORY_TIERS_H +#define _LINUX_MEMORY_TIERS_H + +/* + * Each tier cover a abstrace distance chunk size of 128 + */ +#define MEMTIER_CHUNK_BITS 7 +#define MEMTIER_CHUNK_SIZE (1 << MEMTIER_CHUNK_BITS) +/* + * Smaller abstract distance values imply faster (higher) memory tiers. Offset + * the DRAM adistance so that we can accommodate devices with a slightly lower + * adistance value (slightly faster) than default DRAM adistance to be part of + * the same memory tier. + */ +#define MEMTIER_ADISTANCE_DRAM ((4 * MEMTIER_CHUNK_SIZE) + (MEMTIER_CHUNK_SIZE >> 1)) + +#endif /* _LINUX_MEMORY_TIERS_H */ -- cgit v1.2.3 From 9195244022788935eac0df16132394ffa5613542 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Thu, 18 Aug 2022 18:40:34 +0530 Subject: mm/demotion: move memory demotion related code This moves memory demotion related code to mm/memory-tiers.c. No functional change in this patch. Link: https://lkml.kernel.org/r/20220818131042.113280-3-aneesh.kumar@linux.ibm.com Signed-off-by: Aneesh Kumar K.V Reviewed-by: "Huang, Ying" Acked-by: Wei Xu Cc: Alistair Popple Cc: Bharata B Rao Cc: Dan Williams Cc: Dave Hansen Cc: Davidlohr Bueso Cc: Hesham Almatary Cc: Jagdish Gediya Cc: Johannes Weiner Cc: Jonathan Cameron Cc: Michal Hocko Cc: Tim Chen Cc: Yang Shi Cc: SeongJae Park Signed-off-by: Andrew Morton --- include/linux/memory-tiers.h | 8 ++++++++ include/linux/migrate.h | 2 -- 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h index ecada7bf4091..5f24396da76c 100644 --- a/include/linux/memory-tiers.h +++ b/include/linux/memory-tiers.h @@ -15,4 +15,12 @@ */ #define MEMTIER_ADISTANCE_DRAM ((4 * MEMTIER_CHUNK_SIZE) + (MEMTIER_CHUNK_SIZE >> 1)) +#ifdef CONFIG_NUMA +#include +extern bool numa_demotion_enabled; + +#else + +#define numa_demotion_enabled false +#endif /* CONFIG_NUMA */ #endif /* _LINUX_MEMORY_TIERS_H */ diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 22c0a0cf5e0c..96f8c84413fe 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -103,7 +103,6 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping, #if defined(CONFIG_MIGRATION) && defined(CONFIG_NUMA) extern void set_migration_target_nodes(void); extern void migrate_on_reclaim_init(void); -extern bool numa_demotion_enabled; extern int next_demotion_node(int node); #else static inline void set_migration_target_nodes(void) {} @@ -112,7 +111,6 @@ static inline int next_demotion_node(int node) { return NUMA_NO_NODE; } -#define numa_demotion_enabled false #endif #ifdef CONFIG_COMPACTION -- cgit v1.2.3 From c6123a19c9f040e597f55f856c679651c26b31d1 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Thu, 18 Aug 2022 18:40:35 +0530 Subject: mm/demotion: add hotplug callbacks to handle new numa node onlined If the new NUMA node onlined doesn't have a abstract distance assigned, the kernel adds the NUMA node to default memory tier. [aneesh.kumar@linux.ibm.com: fix kernel error with memory hotplug] Link: https://lkml.kernel.org/r/20220825092019.379069-1-aneesh.kumar@linux.ibm.com Link: https://lkml.kernel.org/r/20220818131042.113280-4-aneesh.kumar@linux.ibm.com Signed-off-by: Aneesh Kumar K.V Reviewed-by: "Huang, Ying" Acked-by: Wei Xu Cc: Alistair Popple Cc: Bharata B Rao Cc: Dan Williams Cc: Dave Hansen Cc: Davidlohr Bueso Cc: Hesham Almatary Cc: Jagdish Gediya Cc: Johannes Weiner Cc: Jonathan Cameron Cc: Michal Hocko Cc: Tim Chen Cc: Yang Shi Cc: SeongJae Park Signed-off-by: Andrew Morton --- include/linux/memory-tiers.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h index 5f24396da76c..7ae6308b2191 100644 --- a/include/linux/memory-tiers.h +++ b/include/linux/memory-tiers.h @@ -14,6 +14,7 @@ * the same memory tier. */ #define MEMTIER_ADISTANCE_DRAM ((4 * MEMTIER_CHUNK_SIZE) + (MEMTIER_CHUNK_SIZE >> 1)) +#define MEMTIER_HOTPLUG_PRIO 100 #ifdef CONFIG_NUMA #include -- cgit v1.2.3 From 7b88bda3761b95856cf97822efe8281c8100067b Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Thu, 18 Aug 2022 18:40:36 +0530 Subject: mm/demotion/dax/kmem: set node's abstract distance to MEMTIER_DEFAULT_DAX_ADISTANCE By default, all nodes are assigned to the default memory tier which is the memory tier designated for nodes with DRAM Set dax kmem device node's tier to slower memory tier by assigning abstract distance to MEMTIER_DEFAULT_DAX_ADISTANCE. Low-level drivers like papr_scm or ACPI NFIT can initialize memory device type to a more accurate value based on device tree details or HMAT. If the kernel doesn't find the memory type initialized, a default slower memory type is assigned by the kmem driver. [aneesh.kumar@linux.ibm.com: assign correct memory type for multiple dax devices with the same node affinity] Link: https://lkml.kernel.org/r/20220826100224.542312-1-aneesh.kumar@linux.ibm.com Link: https://lkml.kernel.org/r/20220818131042.113280-5-aneesh.kumar@linux.ibm.com Signed-off-by: Aneesh Kumar K.V Reviewed-by: "Huang, Ying" Acked-by: Wei Xu Cc: Alistair Popple Cc: Bharata B Rao Cc: Dan Williams Cc: Dave Hansen Cc: Davidlohr Bueso Cc: Hesham Almatary Cc: Jagdish Gediya Cc: Johannes Weiner Cc: Jonathan Cameron Cc: Michal Hocko Cc: Tim Chen Cc: Yang Shi Cc: SeongJae Park Signed-off-by: Andrew Morton --- include/linux/memory-tiers.h | 42 +++++++++++++++++++++++++++++++++++++++++- 1 file changed, 41 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h index 7ae6308b2191..49d281866dca 100644 --- a/include/linux/memory-tiers.h +++ b/include/linux/memory-tiers.h @@ -2,6 +2,9 @@ #ifndef _LINUX_MEMORY_TIERS_H #define _LINUX_MEMORY_TIERS_H +#include +#include +#include /* * Each tier cover a abstrace distance chunk size of 128 */ @@ -16,12 +19,49 @@ #define MEMTIER_ADISTANCE_DRAM ((4 * MEMTIER_CHUNK_SIZE) + (MEMTIER_CHUNK_SIZE >> 1)) #define MEMTIER_HOTPLUG_PRIO 100 +struct memory_tier; +struct memory_dev_type { + /* list of memory types that are part of same tier as this type */ + struct list_head tier_sibiling; + /* abstract distance for this specific memory type */ + int adistance; + /* Nodes of same abstract distance */ + nodemask_t nodes; + struct kref kref; + struct memory_tier *memtier; +}; + #ifdef CONFIG_NUMA -#include extern bool numa_demotion_enabled; +struct memory_dev_type *alloc_memory_type(int adistance); +void destroy_memory_type(struct memory_dev_type *memtype); +void init_node_memory_type(int node, struct memory_dev_type *default_type); +void clear_node_memory_type(int node, struct memory_dev_type *memtype); #else #define numa_demotion_enabled false +/* + * CONFIG_NUMA implementation returns non NULL error. + */ +static inline struct memory_dev_type *alloc_memory_type(int adistance) +{ + return NULL; +} + +static inline void destroy_memory_type(struct memory_dev_type *memtype) +{ + +} + +static inline void init_node_memory_type(int node, struct memory_dev_type *default_type) +{ + +} + +static inline void clear_node_memory_type(int node, struct memory_dev_type *memtype) +{ + +} #endif /* CONFIG_NUMA */ #endif /* _LINUX_MEMORY_TIERS_H */ -- cgit v1.2.3 From 6c542ab75714fe90dae292aeb3e91ac53f5ff599 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Thu, 18 Aug 2022 18:40:37 +0530 Subject: mm/demotion: build demotion targets based on explicit memory tiers This patch switch the demotion target building logic to use memory tiers instead of NUMA distance. All N_MEMORY NUMA nodes will be placed in the default memory tier and additional memory tiers will be added by drivers like dax kmem. This patch builds the demotion target for a NUMA node by looking at all memory tiers below the tier to which the NUMA node belongs. The closest node in the immediately following memory tier is used as a demotion target. Since we are now only building demotion target for N_MEMORY NUMA nodes the CPU hotplug calls are removed in this patch. Link: https://lkml.kernel.org/r/20220818131042.113280-6-aneesh.kumar@linux.ibm.com Signed-off-by: Aneesh Kumar K.V Reviewed-by: "Huang, Ying" Acked-by: Wei Xu Cc: Alistair Popple Cc: Bharata B Rao Cc: Dan Williams Cc: Dave Hansen Cc: Davidlohr Bueso Cc: Hesham Almatary Cc: Jagdish Gediya Cc: Johannes Weiner Cc: Jonathan Cameron Cc: Michal Hocko Cc: Tim Chen Cc: Yang Shi Cc: SeongJae Park Signed-off-by: Andrew Morton --- include/linux/memory-tiers.h | 13 +++++++++++++ include/linux/migrate.h | 13 ------------- 2 files changed, 13 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h index 49d281866dca..ce9c6bac6725 100644 --- a/include/linux/memory-tiers.h +++ b/include/linux/memory-tiers.h @@ -37,6 +37,14 @@ struct memory_dev_type *alloc_memory_type(int adistance); void destroy_memory_type(struct memory_dev_type *memtype); void init_node_memory_type(int node, struct memory_dev_type *default_type); void clear_node_memory_type(int node, struct memory_dev_type *memtype); +#ifdef CONFIG_MIGRATION +int next_demotion_node(int node); +#else +static inline int next_demotion_node(int node) +{ + return NUMA_NO_NODE; +} +#endif #else @@ -63,5 +71,10 @@ static inline void clear_node_memory_type(int node, struct memory_dev_type *memt { } + +static inline int next_demotion_node(int node) +{ + return NUMA_NO_NODE; +} #endif /* CONFIG_NUMA */ #endif /* _LINUX_MEMORY_TIERS_H */ diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 96f8c84413fe..704a04f5a074 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -100,19 +100,6 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping, #endif /* CONFIG_MIGRATION */ -#if defined(CONFIG_MIGRATION) && defined(CONFIG_NUMA) -extern void set_migration_target_nodes(void); -extern void migrate_on_reclaim_init(void); -extern int next_demotion_node(int node); -#else -static inline void set_migration_target_nodes(void) {} -static inline void migrate_on_reclaim_init(void) {} -static inline int next_demotion_node(int node) -{ - return NUMA_NO_NODE; -} -#endif - #ifdef CONFIG_COMPACTION bool PageMovable(struct page *page); void __SetPageMovable(struct page *page, const struct movable_operations *ops); -- cgit v1.2.3 From 7766cf7a7e7545ab434a16c6f9531b09efe14dc1 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Thu, 18 Aug 2022 18:40:38 +0530 Subject: mm/demotion: add pg_data_t member to track node memory tier details Also update different helpes to use NODE_DATA()->memtier. Since node specific memtier can change based on the reassignment of NUMA node to a different memory tiers, accessing NODE_DATA()->memtier needs to happen under an rcu read lock or memory_tier_lock. Link: https://lkml.kernel.org/r/20220818131042.113280-7-aneesh.kumar@linux.ibm.com Signed-off-by: Aneesh Kumar K.V Reviewed-by: "Huang, Ying" Acked-by: Wei Xu Cc: Alistair Popple Cc: Bharata B Rao Cc: Dan Williams Cc: Dave Hansen Cc: Davidlohr Bueso Cc: Hesham Almatary Cc: Jagdish Gediya Cc: Johannes Weiner Cc: Jonathan Cameron Cc: Michal Hocko Cc: Tim Chen Cc: Yang Shi Cc: SeongJae Park Signed-off-by: Andrew Morton --- include/linux/mmzone.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 87347945270b..e335a492c2eb 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1246,6 +1246,9 @@ typedef struct pglist_data { /* Per-node vmstats */ struct per_cpu_nodestat __percpu *per_cpu_nodestats; atomic_long_t vm_stat[NR_VM_NODE_STAT_ITEMS]; +#ifdef CONFIG_NUMA + struct memory_tier __rcu *memtier; +#endif } pg_data_t; #define node_present_pages(nid) (NODE_DATA(nid)->node_present_pages) -- cgit v1.2.3 From b26ac6f3ba38fac83db2d72551e6d994d0e0516f Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Thu, 18 Aug 2022 18:40:39 +0530 Subject: mm/demotion: drop memtier from memtype Now that we track node-specific memtier in pg_data_t, we can drop memtier from memtype. Link: https://lkml.kernel.org/r/20220818131042.113280-8-aneesh.kumar@linux.ibm.com Signed-off-by: Aneesh Kumar K.V Reviewed-by: "Huang, Ying" Acked-by: Wei Xu Cc: Alistair Popple Cc: Bharata B Rao Cc: Dan Williams Cc: Dave Hansen Cc: Davidlohr Bueso Cc: Hesham Almatary Cc: Jagdish Gediya Cc: Johannes Weiner Cc: Jonathan Cameron Cc: Michal Hocko Cc: Tim Chen Cc: Yang Shi Cc: SeongJae Park Signed-off-by: Andrew Morton --- include/linux/memory-tiers.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h index ce9c6bac6725..7ca52ad2789f 100644 --- a/include/linux/memory-tiers.h +++ b/include/linux/memory-tiers.h @@ -28,7 +28,6 @@ struct memory_dev_type { /* Nodes of same abstract distance */ nodemask_t nodes; struct kref kref; - struct memory_tier *memtier; }; #ifdef CONFIG_NUMA -- cgit v1.2.3 From 32008027289239100d8d2876f50b15d92bde1855 Mon Sep 17 00:00:00 2001 From: Jagdish Gediya Date: Thu, 18 Aug 2022 18:40:40 +0530 Subject: mm/demotion: demote pages according to allocation fallback order Currently, a higher tier node can only be demoted to selected nodes on the next lower tier as defined by the demotion path. This strict demotion order does not work in all use cases (e.g. some use cases may want to allow cross-socket demotion to another node in the same demotion tier as a fallback when the preferred demotion node is out of space). This demotion order is also inconsistent with the page allocation fallback order when all the nodes in a higher tier are out of space: The page allocation can fall back to any node from any lower tier, whereas the demotion order doesn't allow that currently. This patch adds support to get all the allowed demotion targets for a memory tier. demote_page_list() function is now modified to utilize this allowed node mask as the fallback allocation mask. Link: https://lkml.kernel.org/r/20220818131042.113280-9-aneesh.kumar@linux.ibm.com Signed-off-by: Jagdish Gediya Signed-off-by: Aneesh Kumar K.V Reviewed-by: "Huang, Ying" Acked-by: Wei Xu Cc: Alistair Popple Cc: Bharata B Rao Cc: Dan Williams Cc: Dave Hansen Cc: Davidlohr Bueso Cc: Hesham Almatary Cc: Johannes Weiner Cc: Jonathan Cameron Cc: Michal Hocko Cc: Tim Chen Cc: Yang Shi Cc: SeongJae Park Signed-off-by: Andrew Morton --- include/linux/memory-tiers.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h index 7ca52ad2789f..42791554b9b9 100644 --- a/include/linux/memory-tiers.h +++ b/include/linux/memory-tiers.h @@ -5,6 +5,7 @@ #include #include #include +#include /* * Each tier cover a abstrace distance chunk size of 128 */ @@ -38,11 +39,17 @@ void init_node_memory_type(int node, struct memory_dev_type *default_type); void clear_node_memory_type(int node, struct memory_dev_type *memtype); #ifdef CONFIG_MIGRATION int next_demotion_node(int node); +void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets); #else static inline int next_demotion_node(int node) { return NUMA_NO_NODE; } + +static inline void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets) +{ + *targets = NODE_MASK_NONE; +} #endif #else @@ -75,5 +82,10 @@ static inline int next_demotion_node(int node) { return NUMA_NO_NODE; } + +static inline void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets) +{ + *targets = NODE_MASK_NONE; +} #endif /* CONFIG_NUMA */ #endif /* _LINUX_MEMORY_TIERS_H */ -- cgit v1.2.3 From 467b171af881282fc627328e6c164f044a6df888 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Thu, 18 Aug 2022 18:40:41 +0530 Subject: mm/demotion: update node_is_toptier to work with memory tiers With memory tier support we can have memory only NUMA nodes in the top tier from which we want to avoid promotion tracking NUMA faults. Update node_is_toptier to work with memory tiers. All NUMA nodes are by default top tier nodes. With lower(slower) memory tiers added we consider all memory tiers above a memory tier having CPU NUMA nodes as a top memory tier [sj@kernel.org: include missed header file, memory-tiers.h] Link: https://lkml.kernel.org/r/20220820190720.248704-1-sj@kernel.org [akpm@linux-foundation.org: mm/memory.c needs linux/memory-tiers.h] [aneesh.kumar@linux.ibm.com: make toptier_distance inclusive upper bound of toptiers] Link: https://lkml.kernel.org/r/20220830081457.118960-1-aneesh.kumar@linux.ibm.com Link: https://lkml.kernel.org/r/20220818131042.113280-10-aneesh.kumar@linux.ibm.com Signed-off-by: Aneesh Kumar K.V Reviewed-by: "Huang, Ying" Acked-by: Wei Xu Cc: Alistair Popple Cc: Bharata B Rao Cc: Dan Williams Cc: Dave Hansen Cc: Davidlohr Bueso Cc: Hesham Almatary Cc: Jagdish Gediya Cc: Johannes Weiner Cc: Jonathan Cameron Cc: Michal Hocko Cc: Tim Chen Cc: Yang Shi Cc: SeongJae Park Signed-off-by: Andrew Morton --- include/linux/memory-tiers.h | 11 +++++++++++ include/linux/node.h | 5 ----- 2 files changed, 11 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h index 42791554b9b9..965009aa01d7 100644 --- a/include/linux/memory-tiers.h +++ b/include/linux/memory-tiers.h @@ -40,6 +40,7 @@ void clear_node_memory_type(int node, struct memory_dev_type *memtype); #ifdef CONFIG_MIGRATION int next_demotion_node(int node); void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets); +bool node_is_toptier(int node); #else static inline int next_demotion_node(int node) { @@ -50,6 +51,11 @@ static inline void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *target { *targets = NODE_MASK_NONE; } + +static inline bool node_is_toptier(int node) +{ + return true; +} #endif #else @@ -87,5 +93,10 @@ static inline void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *target { *targets = NODE_MASK_NONE; } + +static inline bool node_is_toptier(int node) +{ + return true; +} #endif /* CONFIG_NUMA */ #endif /* _LINUX_MEMORY_TIERS_H */ diff --git a/include/linux/node.h b/include/linux/node.h index 40d641a8bfb0..9ec680dd607f 100644 --- a/include/linux/node.h +++ b/include/linux/node.h @@ -185,9 +185,4 @@ static inline void register_hugetlbfs_with_node(node_registration_func_t reg, #define to_node(device) container_of(device, struct node, dev) -static inline bool node_is_toptier(int node) -{ - return node_state(node, N_CPU); -} - #endif /* _LINUX_NODE_H_ */ -- cgit v1.2.3 From 3e061d924fe9c7b487ca45935f92fcd414ce6f1a Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Thu, 18 Aug 2022 18:40:42 +0530 Subject: lib/nodemask: optimize node_random for nodemask with single NUMA node The most common case for certain node_random usage (demotion nodemask) is with nodemask weight 1. We can avoid calling get_random_init() in that case and always return the only node set in the nodemask. A simple test as below before = rdtsc_ordered(); for (i= 0; i < 100; i++) { rand = node_random(&nmask); } after = rdtsc_ordered(); Without fix after - before : 16438 With fix after - before : 816 Link: https://lkml.kernel.org/r/20220818131042.113280-11-aneesh.kumar@linux.ibm.com Signed-off-by: Aneesh Kumar K.V Reviewed-by: "Huang, Ying" Acked-by: Wei Xu Cc: Alistair Popple Cc: Bharata B Rao Cc: Dan Williams Cc: Dave Hansen Cc: Davidlohr Bueso Cc: Hesham Almatary Cc: Jagdish Gediya Cc: Johannes Weiner Cc: Jonathan Cameron Cc: Michal Hocko Cc: Tim Chen Cc: Yang Shi Cc: SeongJae Park Signed-off-by: Andrew Morton --- include/linux/nodemask.h | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 3a0eec9f2faa..e66742db741c 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -505,12 +505,21 @@ static inline int num_node_state(enum node_states state) static inline int node_random(const nodemask_t *maskp) { #if defined(CONFIG_NUMA) && (MAX_NUMNODES > 1) - int w, bit = NUMA_NO_NODE; + int w, bit; w = nodes_weight(*maskp); - if (w) + switch (w) { + case 0: + bit = NUMA_NO_NODE; + break; + case 1: + bit = first_node(*maskp); + break; + default: bit = bitmap_ord_to_pos(maskp->bits, - get_random_int() % w, MAX_NUMNODES); + get_random_int() % w, MAX_NUMNODES); + break; + } return bit; #else return 0; -- cgit v1.2.3 From 54a611b605901c7d5d05b6b8f5d04a6ceb0962aa Mon Sep 17 00:00:00 2001 From: "Liam R. Howlett" Date: Tue, 6 Sep 2022 19:48:39 +0000 Subject: Maple Tree: add new data structure Patch series "Introducing the Maple Tree" The maple tree is an RCU-safe range based B-tree designed to use modern processor cache efficiently. There are a number of places in the kernel that a non-overlapping range-based tree would be beneficial, especially one with a simple interface. If you use an rbtree with other data structures to improve performance or an interval tree to track non-overlapping ranges, then this is for you. The tree has a branching factor of 10 for non-leaf nodes and 16 for leaf nodes. With the increased branching factor, it is significantly shorter than the rbtree so it has fewer cache misses. The removal of the linked list between subsequent entries also reduces the cache misses and the need to pull in the previous and next VMA during many tree alterations. The first user that is covered in this patch set is the vm_area_struct, where three data structures are replaced by the maple tree: the augmented rbtree, the vma cache, and the linked list of VMAs in the mm_struct. The long term goal is to reduce or remove the mmap_lock contention. The plan is to get to the point where we use the maple tree in RCU mode. Readers will not block for writers. A single write operation will be allowed at a time. A reader re-walks if stale data is encountered. VMAs would be RCU enabled and this mode would be entered once multiple tasks are using the mm_struct. Davidlor said : Yes I like the maple tree, and at this stage I don't think we can ask for : more from this series wrt the MM - albeit there seems to still be some : folks reporting breakage. Fundamentally I see Liam's work to (re)move : complexity out of the MM (not to say that the actual maple tree is not : complex) by consolidating the three complimentary data structures very : much worth it considering performance does not take a hit. This was very : much a turn off with the range locking approach, which worst case scenario : incurred in prohibitive overhead. Also as Liam and Matthew have : mentioned, RCU opens up a lot of nice performance opportunities, and in : addition academia[1] has shown outstanding scalability of address spaces : with the foundation of replacing the locked rbtree with RCU aware trees. A similar work has been discovered in the academic press https://pdos.csail.mit.edu/papers/rcuvm:asplos12.pdf Sheer coincidence. We designed our tree with the intention of solving the hardest problem first. Upon settling on a b-tree variant and a rough outline, we researched ranged based b-trees and RCU b-trees and did find that article. So it was nice to find reassurances that we were on the right path, but our design choice of using ranges made that paper unusable for us. This patch (of 70): The maple tree is an RCU-safe range based B-tree designed to use modern processor cache efficiently. There are a number of places in the kernel that a non-overlapping range-based tree would be beneficial, especially one with a simple interface. If you use an rbtree with other data structures to improve performance or an interval tree to track non-overlapping ranges, then this is for you. The tree has a branching factor of 10 for non-leaf nodes and 16 for leaf nodes. With the increased branching factor, it is significantly shorter than the rbtree so it has fewer cache misses. The removal of the linked list between subsequent entries also reduces the cache misses and the need to pull in the previous and next VMA during many tree alterations. The first user that is covered in this patch set is the vm_area_struct, where three data structures are replaced by the maple tree: the augmented rbtree, the vma cache, and the linked list of VMAs in the mm_struct. The long term goal is to reduce or remove the mmap_lock contention. The plan is to get to the point where we use the maple tree in RCU mode. Readers will not block for writers. A single write operation will be allowed at a time. A reader re-walks if stale data is encountered. VMAs would be RCU enabled and this mode would be entered once multiple tasks are using the mm_struct. There is additional BUG_ON() calls added within the tree, most of which are in debug code. These will be replaced with a WARN_ON() call in the future. There is also additional BUG_ON() calls within the code which will also be reduced in number at a later date. These exist to catch things such as out-of-range accesses which would crash anyways. Link: https://lkml.kernel.org/r/20220906194824.2110408-1-Liam.Howlett@oracle.com Link: https://lkml.kernel.org/r/20220906194824.2110408-2-Liam.Howlett@oracle.com Signed-off-by: Liam R. Howlett Signed-off-by: Matthew Wilcox (Oracle) Tested-by: David Howells Tested-by: Sven Schnelle Tested-by: Yu Zhao Cc: Vlastimil Babka Cc: David Hildenbrand Cc: Davidlohr Bueso Cc: Catalin Marinas Cc: SeongJae Park Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/maple_tree.h | 685 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 685 insertions(+) create mode 100644 include/linux/maple_tree.h (limited to 'include/linux') diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h new file mode 100644 index 000000000000..2effab72add1 --- /dev/null +++ b/include/linux/maple_tree.h @@ -0,0 +1,685 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +#ifndef _LINUX_MAPLE_TREE_H +#define _LINUX_MAPLE_TREE_H +/* + * Maple Tree - An RCU-safe adaptive tree for storing ranges + * Copyright (c) 2018-2022 Oracle + * Authors: Liam R. Howlett + * Matthew Wilcox + */ + +#include +#include +#include +/* #define CONFIG_MAPLE_RCU_DISABLED */ +/* #define CONFIG_DEBUG_MAPLE_TREE_VERBOSE */ + +/* + * Allocated nodes are mutable until they have been inserted into the tree, + * at which time they cannot change their type until they have been removed + * from the tree and an RCU grace period has passed. + * + * Removed nodes have their ->parent set to point to themselves. RCU readers + * check ->parent before relying on the value that they loaded from the + * slots array. This lets us reuse the slots array for the RCU head. + * + * Nodes in the tree point to their parent unless bit 0 is set. + */ +#if defined(CONFIG_64BIT) || defined(BUILD_VDSO32_64) +/* 64bit sizes */ +#define MAPLE_NODE_SLOTS 31 /* 256 bytes including ->parent */ +#define MAPLE_RANGE64_SLOTS 16 /* 256 bytes */ +#define MAPLE_ARANGE64_SLOTS 10 /* 240 bytes */ +#define MAPLE_ARANGE64_META_MAX 15 /* Out of range for metadata */ +#define MAPLE_ALLOC_SLOTS (MAPLE_NODE_SLOTS - 1) +#else +/* 32bit sizes */ +#define MAPLE_NODE_SLOTS 63 /* 256 bytes including ->parent */ +#define MAPLE_RANGE64_SLOTS 32 /* 256 bytes */ +#define MAPLE_ARANGE64_SLOTS 21 /* 240 bytes */ +#define MAPLE_ARANGE64_META_MAX 31 /* Out of range for metadata */ +#define MAPLE_ALLOC_SLOTS (MAPLE_NODE_SLOTS - 2) +#endif /* defined(CONFIG_64BIT) || defined(BUILD_VDSO32_64) */ + +#define MAPLE_NODE_MASK 255UL + +/* + * The node->parent of the root node has bit 0 set and the rest of the pointer + * is a pointer to the tree itself. No more bits are available in this pointer + * (on m68k, the data structure may only be 2-byte aligned). + * + * Internal non-root nodes can only have maple_range_* nodes as parents. The + * parent pointer is 256B aligned like all other tree nodes. When storing a 32 + * or 64 bit values, the offset can fit into 4 bits. The 16 bit values need an + * extra bit to store the offset. This extra bit comes from a reuse of the last + * bit in the node type. This is possible by using bit 1 to indicate if bit 2 + * is part of the type or the slot. + * + * Once the type is decided, the decision of an allocation range type or a range + * type is done by examining the immutable tree flag for the MAPLE_ALLOC_RANGE + * flag. + * + * Node types: + * 0x??1 = Root + * 0x?00 = 16 bit nodes + * 0x010 = 32 bit nodes + * 0x110 = 64 bit nodes + * + * Slot size and location in the parent pointer: + * type : slot location + * 0x??1 : Root + * 0x?00 : 16 bit values, type in 0-1, slot in 2-6 + * 0x010 : 32 bit values, type in 0-2, slot in 3-6 + * 0x110 : 64 bit values, type in 0-2, slot in 3-6 + */ + +/* + * This metadata is used to optimize the gap updating code and in reverse + * searching for gaps or any other code that needs to find the end of the data. + */ +struct maple_metadata { + unsigned char end; + unsigned char gap; +}; + +/* + * Leaf nodes do not store pointers to nodes, they store user data. Users may + * store almost any bit pattern. As noted above, the optimisation of storing an + * entry at 0 in the root pointer cannot be done for data which have the bottom + * two bits set to '10'. We also reserve values with the bottom two bits set to + * '10' which are below 4096 (ie 2, 6, 10 .. 4094) for internal use. Some APIs + * return errnos as a negative errno shifted right by two bits and the bottom + * two bits set to '10', and while choosing to store these values in the array + * is not an error, it may lead to confusion if you're testing for an error with + * mas_is_err(). + * + * Non-leaf nodes store the type of the node pointed to (enum maple_type in bits + * 3-6), bit 2 is reserved. That leaves bits 0-1 unused for now. + * + * In regular B-Tree terms, pivots are called keys. The term pivot is used to + * indicate that the tree is specifying ranges, Pivots may appear in the + * subtree with an entry attached to the value whereas keys are unique to a + * specific position of a B-tree. Pivot values are inclusive of the slot with + * the same index. + */ + +struct maple_range_64 { + struct maple_pnode *parent; + unsigned long pivot[MAPLE_RANGE64_SLOTS - 1]; + union { + void __rcu *slot[MAPLE_RANGE64_SLOTS]; + struct { + void __rcu *pad[MAPLE_RANGE64_SLOTS - 1]; + struct maple_metadata meta; + }; + }; +}; + +/* + * At tree creation time, the user can specify that they're willing to trade off + * storing fewer entries in a tree in return for storing more information in + * each node. + * + * The maple tree supports recording the largest range of NULL entries available + * in this node, also called gaps. This optimises the tree for allocating a + * range. + */ +struct maple_arange_64 { + struct maple_pnode *parent; + unsigned long pivot[MAPLE_ARANGE64_SLOTS - 1]; + void __rcu *slot[MAPLE_ARANGE64_SLOTS]; + unsigned long gap[MAPLE_ARANGE64_SLOTS]; + struct maple_metadata meta; +}; + +struct maple_alloc { + unsigned long total; + unsigned char node_count; + unsigned int request_count; + struct maple_alloc *slot[MAPLE_ALLOC_SLOTS]; +}; + +struct maple_topiary { + struct maple_pnode *parent; + struct maple_enode *next; /* Overlaps the pivot */ +}; + +enum maple_type { + maple_dense, + maple_leaf_64, + maple_range_64, + maple_arange_64, +}; + + +/** + * DOC: Maple tree flags + * + * * MT_FLAGS_ALLOC_RANGE - Track gaps in this tree + * * MT_FLAGS_USE_RCU - Operate in RCU mode + * * MT_FLAGS_HEIGHT_OFFSET - The position of the tree height in the flags + * * MT_FLAGS_HEIGHT_MASK - The mask for the maple tree height value + * * MT_FLAGS_LOCK_MASK - How the mt_lock is used + * * MT_FLAGS_LOCK_IRQ - Acquired irq-safe + * * MT_FLAGS_LOCK_BH - Acquired bh-safe + * * MT_FLAGS_LOCK_EXTERN - mt_lock is not used + * + * MAPLE_HEIGHT_MAX The largest height that can be stored + */ +#define MT_FLAGS_ALLOC_RANGE 0x01 +#define MT_FLAGS_USE_RCU 0x02 +#define MT_FLAGS_HEIGHT_OFFSET 0x02 +#define MT_FLAGS_HEIGHT_MASK 0x7C +#define MT_FLAGS_LOCK_MASK 0x300 +#define MT_FLAGS_LOCK_IRQ 0x100 +#define MT_FLAGS_LOCK_BH 0x200 +#define MT_FLAGS_LOCK_EXTERN 0x300 + +#define MAPLE_HEIGHT_MAX 31 + + +#define MAPLE_NODE_TYPE_MASK 0x0F +#define MAPLE_NODE_TYPE_SHIFT 0x03 + +#define MAPLE_RESERVED_RANGE 4096 + +#ifdef CONFIG_LOCKDEP +typedef struct lockdep_map *lockdep_map_p; +#define mt_lock_is_held(mt) lock_is_held(mt->ma_external_lock) +#define mt_set_external_lock(mt, lock) \ + (mt)->ma_external_lock = &(lock)->dep_map +#else +typedef struct { /* nothing */ } lockdep_map_p; +#define mt_lock_is_held(mt) 1 +#define mt_set_external_lock(mt, lock) do { } while (0) +#endif + +/* + * If the tree contains a single entry at index 0, it is usually stored in + * tree->ma_root. To optimise for the page cache, an entry which ends in '00', + * '01' or '11' is stored in the root, but an entry which ends in '10' will be + * stored in a node. Bits 3-6 are used to store enum maple_type. + * + * The flags are used both to store some immutable information about this tree + * (set at tree creation time) and dynamic information set under the spinlock. + * + * Another use of flags are to indicate global states of the tree. This is the + * case with the MAPLE_USE_RCU flag, which indicates the tree is currently in + * RCU mode. This mode was added to allow the tree to reuse nodes instead of + * re-allocating and RCU freeing nodes when there is a single user. + */ +struct maple_tree { + union { + spinlock_t ma_lock; + lockdep_map_p ma_external_lock; + }; + void __rcu *ma_root; + unsigned int ma_flags; +}; + +/** + * MTREE_INIT() - Initialize a maple tree + * @name: The maple tree name + * @__flags: The maple tree flags + * + */ +#define MTREE_INIT(name, __flags) { \ + .ma_lock = __SPIN_LOCK_UNLOCKED((name).ma_lock), \ + .ma_flags = __flags, \ + .ma_root = NULL, \ +} + +/** + * MTREE_INIT_EXT() - Initialize a maple tree with an external lock. + * @name: The tree name + * @__flags: The maple tree flags + * @__lock: The external lock + */ +#ifdef CONFIG_LOCKDEP +#define MTREE_INIT_EXT(name, __flags, __lock) { \ + .ma_external_lock = &(__lock).dep_map, \ + .ma_flags = (__flags), \ + .ma_root = NULL, \ +} +#else +#define MTREE_INIT_EXT(name, __flags, __lock) MTREE_INIT(name, __flags) +#endif + +#define DEFINE_MTREE(name) \ + struct maple_tree name = MTREE_INIT(name, 0) + +#define mtree_lock(mt) spin_lock((&(mt)->ma_lock)) +#define mtree_unlock(mt) spin_unlock((&(mt)->ma_lock)) + +/* + * The Maple Tree squeezes various bits in at various points which aren't + * necessarily obvious. Usually, this is done by observing that pointers are + * N-byte aligned and thus the bottom log_2(N) bits are available for use. We + * don't use the high bits of pointers to store additional information because + * we don't know what bits are unused on any given architecture. + * + * Nodes are 256 bytes in size and are also aligned to 256 bytes, giving us 8 + * low bits for our own purposes. Nodes are currently of 4 types: + * 1. Single pointer (Range is 0-0) + * 2. Non-leaf Allocation Range nodes + * 3. Non-leaf Range nodes + * 4. Leaf Range nodes All nodes consist of a number of node slots, + * pivots, and a parent pointer. + */ + +struct maple_node { + union { + struct { + struct maple_pnode *parent; + void __rcu *slot[MAPLE_NODE_SLOTS]; + }; + struct { + void *pad; + struct rcu_head rcu; + struct maple_enode *piv_parent; + unsigned char parent_slot; + enum maple_type type; + unsigned char slot_len; + unsigned int ma_flags; + }; + struct maple_range_64 mr64; + struct maple_arange_64 ma64; + struct maple_alloc alloc; + }; +}; + +/* + * More complicated stores can cause two nodes to become one or three and + * potentially alter the height of the tree. Either half of the tree may need + * to be rebalanced against the other. The ma_topiary struct is used to track + * which nodes have been 'cut' from the tree so that the change can be done + * safely at a later date. This is done to support RCU. + */ +struct ma_topiary { + struct maple_enode *head; + struct maple_enode *tail; + struct maple_tree *mtree; +}; + +void *mtree_load(struct maple_tree *mt, unsigned long index); + +int mtree_insert(struct maple_tree *mt, unsigned long index, + void *entry, gfp_t gfp); +int mtree_insert_range(struct maple_tree *mt, unsigned long first, + unsigned long last, void *entry, gfp_t gfp); +int mtree_alloc_range(struct maple_tree *mt, unsigned long *startp, + void *entry, unsigned long size, unsigned long min, + unsigned long max, gfp_t gfp); +int mtree_alloc_rrange(struct maple_tree *mt, unsigned long *startp, + void *entry, unsigned long size, unsigned long min, + unsigned long max, gfp_t gfp); + +int mtree_store_range(struct maple_tree *mt, unsigned long first, + unsigned long last, void *entry, gfp_t gfp); +int mtree_store(struct maple_tree *mt, unsigned long index, + void *entry, gfp_t gfp); +void *mtree_erase(struct maple_tree *mt, unsigned long index); + +void mtree_destroy(struct maple_tree *mt); +void __mt_destroy(struct maple_tree *mt); + +/** + * mtree_empty() - Determine if a tree has any present entries. + * @mt: Maple Tree. + * + * Context: Any context. + * Return: %true if the tree contains only NULL pointers. + */ +static inline bool mtree_empty(const struct maple_tree *mt) +{ + return mt->ma_root == NULL; +} + +/* Advanced API */ + +/* + * The maple state is defined in the struct ma_state and is used to keep track + * of information during operations, and even between operations when using the + * advanced API. + * + * If state->node has bit 0 set then it references a tree location which is not + * a node (eg the root). If bit 1 is set, the rest of the bits are a negative + * errno. Bit 2 (the 'unallocated slots' bit) is clear. Bits 3-6 indicate the + * node type. + * + * state->alloc either has a request number of nodes or an allocated node. If + * stat->alloc has a requested number of nodes, the first bit will be set (0x1) + * and the remaining bits are the value. If state->alloc is a node, then the + * node will be of type maple_alloc. maple_alloc has MAPLE_NODE_SLOTS - 1 for + * storing more allocated nodes, a total number of nodes allocated, and the + * node_count in this node. node_count is the number of allocated nodes in this + * node. The scaling beyond MAPLE_NODE_SLOTS - 1 is handled by storing further + * nodes into state->alloc->slot[0]'s node. Nodes are taken from state->alloc + * by removing a node from the state->alloc node until state->alloc->node_count + * is 1, when state->alloc is returned and the state->alloc->slot[0] is promoted + * to state->alloc. Nodes are pushed onto state->alloc by putting the current + * state->alloc into the pushed node's slot[0]. + * + * The state also contains the implied min/max of the state->node, the depth of + * this search, and the offset. The implied min/max are either from the parent + * node or are 0-oo for the root node. The depth is incremented or decremented + * every time a node is walked down or up. The offset is the slot/pivot of + * interest in the node - either for reading or writing. + * + * When returning a value the maple state index and last respectively contain + * the start and end of the range for the entry. Ranges are inclusive in the + * Maple Tree. + */ +struct ma_state { + struct maple_tree *tree; /* The tree we're operating in */ + unsigned long index; /* The index we're operating on - range start */ + unsigned long last; /* The last index we're operating on - range end */ + struct maple_enode *node; /* The node containing this entry */ + unsigned long min; /* The minimum index of this node - implied pivot min */ + unsigned long max; /* The maximum index of this node - implied pivot max */ + struct maple_alloc *alloc; /* Allocated nodes for this operation */ + unsigned char depth; /* depth of tree descent during write */ + unsigned char offset; + unsigned char mas_flags; +}; + +struct ma_wr_state { + struct ma_state *mas; + struct maple_node *node; /* Decoded mas->node */ + unsigned long r_min; /* range min */ + unsigned long r_max; /* range max */ + enum maple_type type; /* mas->node type */ + unsigned char offset_end; /* The offset where the write ends */ + unsigned char node_end; /* mas->node end */ + unsigned long *pivots; /* mas->node->pivots pointer */ + unsigned long end_piv; /* The pivot at the offset end */ + void __rcu **slots; /* mas->node->slots pointer */ + void *entry; /* The entry to write */ + void *content; /* The existing entry that is being overwritten */ +}; + +#define mas_lock(mas) spin_lock(&((mas)->tree->ma_lock)) +#define mas_unlock(mas) spin_unlock(&((mas)->tree->ma_lock)) + + +/* + * Special values for ma_state.node. + * MAS_START means we have not searched the tree. + * MAS_ROOT means we have searched the tree and the entry we found lives in + * the root of the tree (ie it has index 0, length 1 and is the only entry in + * the tree). + * MAS_NONE means we have searched the tree and there is no node in the + * tree for this entry. For example, we searched for index 1 in an empty + * tree. Or we have a tree which points to a full leaf node and we + * searched for an entry which is larger than can be contained in that + * leaf node. + * MA_ERROR represents an errno. After dropping the lock and attempting + * to resolve the error, the walk would have to be restarted from the + * top of the tree as the tree may have been modified. + */ +#define MAS_START ((struct maple_enode *)1UL) +#define MAS_ROOT ((struct maple_enode *)5UL) +#define MAS_NONE ((struct maple_enode *)9UL) +#define MAS_PAUSE ((struct maple_enode *)17UL) +#define MA_ERROR(err) \ + ((struct maple_enode *)(((unsigned long)err << 2) | 2UL)) + +#define MA_STATE(name, mt, first, end) \ + struct ma_state name = { \ + .tree = mt, \ + .index = first, \ + .last = end, \ + .node = MAS_START, \ + .min = 0, \ + .max = ULONG_MAX, \ + .alloc = NULL, \ + } + +#define MA_WR_STATE(name, ma_state, wr_entry) \ + struct ma_wr_state name = { \ + .mas = ma_state, \ + .content = NULL, \ + .entry = wr_entry, \ + } + +#define MA_TOPIARY(name, tree) \ + struct ma_topiary name = { \ + .head = NULL, \ + .tail = NULL, \ + .mtree = tree, \ + } + +void *mas_walk(struct ma_state *mas); +void *mas_store(struct ma_state *mas, void *entry); +void *mas_erase(struct ma_state *mas); +int mas_store_gfp(struct ma_state *mas, void *entry, gfp_t gfp); +void mas_store_prealloc(struct ma_state *mas, void *entry); +void *mas_find(struct ma_state *mas, unsigned long max); +void *mas_find_rev(struct ma_state *mas, unsigned long min); +int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp); +bool mas_is_err(struct ma_state *mas); + +bool mas_nomem(struct ma_state *mas, gfp_t gfp); +void mas_pause(struct ma_state *mas); +void maple_tree_init(void); +void mas_destroy(struct ma_state *mas); +int mas_expected_entries(struct ma_state *mas, unsigned long nr_entries); + +void *mas_prev(struct ma_state *mas, unsigned long min); +void *mas_next(struct ma_state *mas, unsigned long max); + +int mas_empty_area(struct ma_state *mas, unsigned long min, unsigned long max, + unsigned long size); + +/* Checks if a mas has not found anything */ +static inline bool mas_is_none(struct ma_state *mas) +{ + return mas->node == MAS_NONE; +} + +/* Checks if a mas has been paused */ +static inline bool mas_is_paused(struct ma_state *mas) +{ + return mas->node == MAS_PAUSE; +} + +void mas_dup_tree(struct ma_state *oldmas, struct ma_state *mas); +void mas_dup_store(struct ma_state *mas, void *entry); + +/* + * This finds an empty area from the highest address to the lowest. + * AKA "Topdown" version, + */ +int mas_empty_area_rev(struct ma_state *mas, unsigned long min, + unsigned long max, unsigned long size); +/** + * mas_reset() - Reset a Maple Tree operation state. + * @mas: Maple Tree operation state. + * + * Resets the error or walk state of the @mas so future walks of the + * array will start from the root. Use this if you have dropped the + * lock and want to reuse the ma_state. + * + * Context: Any context. + */ +static inline void mas_reset(struct ma_state *mas) +{ + mas->node = MAS_START; +} + +/** + * mas_for_each() - Iterate over a range of the maple tree. + * @__mas: Maple Tree operation state (maple_state) + * @__entry: Entry retrieved from the tree + * @__max: maximum index to retrieve from the tree + * + * When returned, mas->index and mas->last will hold the entire range for the + * entry. + * + * Note: may return the zero entry. + * + */ +#define mas_for_each(__mas, __entry, __max) \ + while (((__entry) = mas_find((__mas), (__max))) != NULL) + + +/** + * mas_set_range() - Set up Maple Tree operation state for a different index. + * @mas: Maple Tree operation state. + * @start: New start of range in the Maple Tree. + * @last: New end of range in the Maple Tree. + * + * Move the operation state to refer to a different range. This will + * have the effect of starting a walk from the top; see mas_next() + * to move to an adjacent index. + */ +static inline +void mas_set_range(struct ma_state *mas, unsigned long start, unsigned long last) +{ + mas->index = start; + mas->last = last; + mas->node = MAS_START; +} + +/** + * mas_set() - Set up Maple Tree operation state for a different index. + * @mas: Maple Tree operation state. + * @index: New index into the Maple Tree. + * + * Move the operation state to refer to a different index. This will + * have the effect of starting a walk from the top; see mas_next() + * to move to an adjacent index. + */ +static inline void mas_set(struct ma_state *mas, unsigned long index) +{ + + mas_set_range(mas, index, index); +} + +static inline bool mt_external_lock(const struct maple_tree *mt) +{ + return (mt->ma_flags & MT_FLAGS_LOCK_MASK) == MT_FLAGS_LOCK_EXTERN; +} + +/** + * mt_init_flags() - Initialise an empty maple tree with flags. + * @mt: Maple Tree + * @flags: maple tree flags. + * + * If you need to initialise a Maple Tree with special flags (eg, an + * allocation tree), use this function. + * + * Context: Any context. + */ +static inline void mt_init_flags(struct maple_tree *mt, unsigned int flags) +{ + mt->ma_flags = flags; + if (!mt_external_lock(mt)) + spin_lock_init(&mt->ma_lock); + rcu_assign_pointer(mt->ma_root, NULL); +} + +/** + * mt_init() - Initialise an empty maple tree. + * @mt: Maple Tree + * + * An empty Maple Tree. + * + * Context: Any context. + */ +static inline void mt_init(struct maple_tree *mt) +{ + mt_init_flags(mt, 0); +} + +static inline bool mt_in_rcu(struct maple_tree *mt) +{ +#ifdef CONFIG_MAPLE_RCU_DISABLED + return false; +#endif + return mt->ma_flags & MT_FLAGS_USE_RCU; +} + +/** + * mt_clear_in_rcu() - Switch the tree to non-RCU mode. + * @mt: The Maple Tree + */ +static inline void mt_clear_in_rcu(struct maple_tree *mt) +{ + if (!mt_in_rcu(mt)) + return; + + if (mt_external_lock(mt)) { + BUG_ON(!mt_lock_is_held(mt)); + mt->ma_flags &= ~MT_FLAGS_USE_RCU; + } else { + mtree_lock(mt); + mt->ma_flags &= ~MT_FLAGS_USE_RCU; + mtree_unlock(mt); + } +} + +/** + * mt_set_in_rcu() - Switch the tree to RCU safe mode. + * @mt: The Maple Tree + */ +static inline void mt_set_in_rcu(struct maple_tree *mt) +{ + if (mt_in_rcu(mt)) + return; + + if (mt_external_lock(mt)) { + BUG_ON(!mt_lock_is_held(mt)); + mt->ma_flags |= MT_FLAGS_USE_RCU; + } else { + mtree_lock(mt); + mt->ma_flags |= MT_FLAGS_USE_RCU; + mtree_unlock(mt); + } +} + +void *mt_find(struct maple_tree *mt, unsigned long *index, unsigned long max); +void *mt_find_after(struct maple_tree *mt, unsigned long *index, + unsigned long max); +void *mt_prev(struct maple_tree *mt, unsigned long index, unsigned long min); +void *mt_next(struct maple_tree *mt, unsigned long index, unsigned long max); + +/** + * mt_for_each - Iterate over each entry starting at index until max. + * @__tree: The Maple Tree + * @__entry: The current entry + * @__index: The index to update to track the location in the tree + * @__max: The maximum limit for @index + * + * Note: Will not return the zero entry. + */ +#define mt_for_each(__tree, __entry, __index, __max) \ + for (__entry = mt_find(__tree, &(__index), __max); \ + __entry; __entry = mt_find_after(__tree, &(__index), __max)) + + +#ifdef CONFIG_DEBUG_MAPLE_TREE +extern atomic_t maple_tree_tests_run; +extern atomic_t maple_tree_tests_passed; + +void mt_dump(const struct maple_tree *mt); +void mt_validate(struct maple_tree *mt); +#define MT_BUG_ON(__tree, __x) do { \ + atomic_inc(&maple_tree_tests_run); \ + if (__x) { \ + pr_info("BUG at %s:%d (%u)\n", \ + __func__, __LINE__, __x); \ + mt_dump(__tree); \ + pr_info("Pass: %u Run:%u\n", \ + atomic_read(&maple_tree_tests_passed), \ + atomic_read(&maple_tree_tests_run)); \ + dump_stack(); \ + } else { \ + atomic_inc(&maple_tree_tests_passed); \ + } \ +} while (0) +#else +#define MT_BUG_ON(__tree, __x) BUG_ON(__x) +#endif /* CONFIG_DEBUG_MAPLE_TREE */ + +#endif /*_LINUX_MAPLE_TREE_H */ -- cgit v1.2.3 From d4af56c5c7c6781ca6ca8075e2cf5bc119ed33d1 Mon Sep 17 00:00:00 2001 From: "Liam R. Howlett" Date: Tue, 6 Sep 2022 19:48:45 +0000 Subject: mm: start tracking VMAs with maple tree Start tracking the VMAs with the new maple tree structure in parallel with the rb_tree. Add debug and trace events for maple tree operations and duplicate the rb_tree that is created on forks into the maple tree. The maple tree is added to the mm_struct including the mm_init struct, added support in required mm/mmap functions, added tracking in kernel/fork for process forking, and used to find the unmapped_area and checked against what the rbtree finds. This also moves the mmap_lock() in exit_mmap() since the oom reaper call does walk the VMAs. Otherwise lockdep will be unhappy if oom happens. When splitting a vma fails due to allocations of the maple tree nodes, the error path in __split_vma() calls new->vm_ops->close(new). The page accounting for hugetlb is actually in the close() operation, so it accounts for the removal of 1/2 of the VMA which was not adjusted. This results in a negative exit value. To avoid the negative charge, set vm_start = vm_end and vm_pgoff = 0. There is also a potential accounting issue in special mappings from insert_vm_struct() failing to allocate, so reverse the charge there in the failure scenario. Link: https://lkml.kernel.org/r/20220906194824.2110408-9-Liam.Howlett@oracle.com Signed-off-by: Liam R. Howlett Signed-off-by: Matthew Wilcox (Oracle) Tested-by: Yu Zhao Cc: Catalin Marinas Cc: David Hildenbrand Cc: David Howells Cc: Davidlohr Bueso Cc: SeongJae Park Cc: Sven Schnelle Cc: Vlastimil Babka Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/mm.h | 5 +++++ include/linux/mm_types.h | 3 +++ 2 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 7cc9ffc19e7f..896d04248e66 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2567,6 +2567,8 @@ extern bool arch_has_descending_max_zone_pfns(void); /* nommu.c */ extern atomic_long_t mmap_pages_allocated; extern int nommu_shrink_inode_mappings(struct inode *, size_t, size_t); +/* mmap.c */ +void vma_mas_store(struct vm_area_struct *vma, struct ma_state *mas); /* interval_tree.c */ void vma_interval_tree_insert(struct vm_area_struct *node, @@ -2630,6 +2632,9 @@ extern struct vm_area_struct *copy_vma(struct vm_area_struct **, bool *need_rmap_locks); extern void exit_mmap(struct mm_struct *); +void vma_mas_store(struct vm_area_struct *vma, struct ma_state *mas); +void vma_mas_remove(struct vm_area_struct *vma, struct ma_state *mas); + static inline int check_data_rlimit(unsigned long rlim, unsigned long new, unsigned long start, diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index e1797813cc2c..425bc5f7d477 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -486,6 +487,7 @@ struct kioctx_table; struct mm_struct { struct { struct vm_area_struct *mmap; /* list of VMAs */ + struct maple_tree mm_mt; struct rb_root mm_rb; u64 vmacache_seqnum; /* per-thread vmacache */ #ifdef CONFIG_MMU @@ -697,6 +699,7 @@ struct mm_struct { unsigned long cpu_bitmap[]; }; +#define MM_MT_FLAGS (MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN) extern struct mm_struct init_mm; /* Pointer magic because the dynamic array size confuses some compilers. */ -- cgit v1.2.3 From f39af05949a4280b9f04d5dd0f606b81aac3dae8 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 6 Sep 2022 19:48:46 +0000 Subject: mm: add VMA iterator This thin layer of abstraction over the maple tree state is for iterating over VMAs. You can go forwards, go backwards or ask where the iterator is. Rename the existing vma_next() to __vma_next() -- it will be removed by the end of this series. Link: https://lkml.kernel.org/r/20220906194824.2110408-10-Liam.Howlett@oracle.com Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Liam R. Howlett Acked-by: Vlastimil Babka Reviewed-by: David Hildenbrand Reviewed-by: Davidlohr Bueso Tested-by: Yu Zhao Cc: Catalin Marinas Cc: David Howells Cc: SeongJae Park Cc: Sven Schnelle Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/mm.h | 32 ++++++++++++++++++++++++++++++++ include/linux/mm_types.h | 21 +++++++++++++++++++++ 2 files changed, 53 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 896d04248e66..3701da1fac5f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -661,6 +661,38 @@ static inline bool vma_is_accessible(struct vm_area_struct *vma) return vma->vm_flags & VM_ACCESS_FLAGS; } +static inline +struct vm_area_struct *vma_find(struct vma_iterator *vmi, unsigned long max) +{ + return mas_find(&vmi->mas, max); +} + +static inline struct vm_area_struct *vma_next(struct vma_iterator *vmi) +{ + /* + * Uses vma_find() to get the first VMA when the iterator starts. + * Calling mas_next() could skip the first entry. + */ + return vma_find(vmi, ULONG_MAX); +} + +static inline struct vm_area_struct *vma_prev(struct vma_iterator *vmi) +{ + return mas_prev(&vmi->mas, 0); +} + +static inline unsigned long vma_iter_addr(struct vma_iterator *vmi) +{ + return vmi->mas.index; +} + +#define for_each_vma(__vmi, __vma) \ + while (((__vma) = vma_next(&(__vmi))) != NULL) + +/* The MM code likes to work with exclusive end addresses */ +#define for_each_vma_range(__vmi, __vma, __end) \ + while (((__vma) = vma_find(&(__vmi), (__end) - 1)) != NULL) + #ifdef CONFIG_SHMEM /* * The vma_is_shmem is not inline because it is used only by slow diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 425bc5f7d477..d0b51fbdf5d4 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -777,6 +777,27 @@ static inline void lru_gen_use_mm(struct mm_struct *mm) #endif /* CONFIG_LRU_GEN */ +struct vma_iterator { + struct ma_state mas; +}; + +#define VMA_ITERATOR(name, __mm, __addr) \ + struct vma_iterator name = { \ + .mas = { \ + .tree = &(__mm)->mm_mt, \ + .index = __addr, \ + .node = MAS_START, \ + }, \ + } + +static inline void vma_iter_init(struct vma_iterator *vmi, + struct mm_struct *mm, unsigned long addr) +{ + vmi->mas.tree = &mm->mm_mt; + vmi->mas.index = addr; + vmi->mas.node = MAS_START; +} + struct mmu_gather; extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm); extern void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm); -- cgit v1.2.3 From c9dbe82cb99db5b6029c6bc43fcf7881d3f50268 Mon Sep 17 00:00:00 2001 From: "Liam R. Howlett" Date: Tue, 6 Sep 2022 19:48:47 +0000 Subject: kernel/fork: use maple tree for dup_mmap() during forking The maple tree was already tracking VMAs in this function by an earlier commit, but the rbtree iterator was being used to iterate the list. Change the iterator to use a maple tree native iterator and switch to the maple tree advanced API to avoid multiple walks of the tree during insert operations. Unexport the now-unused vma_store() function. For performance reasons we bulk allocate the maple tree nodes. The node calculations are done internally to the tree and use the VMA count and assume the worst-case node requirements. The VM_DONT_COPY flag does not allow for the most efficient copy method of the tree and so a bulk loading algorithm is used. Link: https://lkml.kernel.org/r/20220906194824.2110408-15-Liam.Howlett@oracle.com Signed-off-by: Liam R. Howlett Signed-off-by: Matthew Wilcox (Oracle) Acked-by: Vlastimil Babka Tested-by: Yu Zhao Cc: Catalin Marinas Cc: David Hildenbrand Cc: David Howells Cc: Davidlohr Bueso Cc: SeongJae Park Cc: Sven Schnelle Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/mm.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 3701da1fac5f..646ea4d3bd74 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2599,8 +2599,6 @@ extern bool arch_has_descending_max_zone_pfns(void); /* nommu.c */ extern atomic_long_t mmap_pages_allocated; extern int nommu_shrink_inode_mappings(struct inode *, size_t, size_t); -/* mmap.c */ -void vma_mas_store(struct vm_area_struct *vma, struct ma_state *mas); /* interval_tree.c */ void vma_interval_tree_insert(struct vm_area_struct *node, -- cgit v1.2.3 From 524e00b36e8c547f5582eef3fb645a8d9fc5e3df Mon Sep 17 00:00:00 2001 From: "Liam R. Howlett" Date: Tue, 6 Sep 2022 19:48:48 +0000 Subject: mm: remove rb tree. Remove the RB tree and start using the maple tree for vm_area_struct tracking. Drop validate_mm() calls in expand_upwards() and expand_downwards() as the lock is not held. Link: https://lkml.kernel.org/r/20220906194824.2110408-18-Liam.Howlett@oracle.com Signed-off-by: Liam R. Howlett Tested-by: Yu Zhao Cc: Catalin Marinas Cc: David Hildenbrand Cc: David Howells Cc: Davidlohr Bueso Cc: "Matthew Wilcox (Oracle)" Cc: SeongJae Park Cc: Sven Schnelle Cc: Vlastimil Babka Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/mm.h | 2 -- include/linux/mm_types.h | 14 -------------- 2 files changed, 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 646ea4d3bd74..dfce1aaa7a64 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2654,8 +2654,6 @@ extern int __split_vma(struct mm_struct *, struct vm_area_struct *, extern int split_vma(struct mm_struct *, struct vm_area_struct *, unsigned long addr, int new_below); extern int insert_vm_struct(struct mm_struct *, struct vm_area_struct *); -extern void __vma_link_rb(struct mm_struct *, struct vm_area_struct *, - struct rb_node **, struct rb_node *); extern void unlink_file_vma(struct vm_area_struct *); extern struct vm_area_struct *copy_vma(struct vm_area_struct **, unsigned long addr, unsigned long len, pgoff_t pgoff, diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index d0b51fbdf5d4..ac747273c4d6 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -410,19 +410,6 @@ struct vm_area_struct { /* linked list of VM areas per task, sorted by address */ struct vm_area_struct *vm_next, *vm_prev; - - struct rb_node vm_rb; - - /* - * Largest free memory gap in bytes to the left of this VMA. - * Either between this VMA and vma->vm_prev, or between one of the - * VMAs below us in the VMA rbtree and its ->vm_prev. This helps - * get_unmapped_area find a free area of the right size. - */ - unsigned long rb_subtree_gap; - - /* Second cache line starts here. */ - struct mm_struct *vm_mm; /* The address space we belong to. */ /* @@ -488,7 +475,6 @@ struct mm_struct { struct { struct vm_area_struct *mmap; /* list of VMAs */ struct maple_tree mm_mt; - struct rb_root mm_rb; u64 vmacache_seqnum; /* per-thread vmacache */ #ifdef CONFIG_MMU unsigned long (*get_unmapped_area) (struct file *filp, -- cgit v1.2.3 From dc8635b25e87232f62276c02899b9d21dd0793c2 Mon Sep 17 00:00:00 2001 From: "Liam R. Howlett" Date: Tue, 6 Sep 2022 19:48:49 +0000 Subject: mm: optimize find_exact_vma() to use vma_lookup() Use vma_lookup() to walk the tree to the start value requested. If the vma at the start does not match, then the answer is NULL and there is no need to look at the next vma the way that find_vma() would. Link: https://lkml.kernel.org/r/20220906194824.2110408-21-Liam.Howlett@oracle.com Signed-off-by: Liam R. Howlett Reviewed-by: Vlastimil Babka Tested-by: Yu Zhao Cc: Catalin Marinas Cc: David Hildenbrand Cc: David Howells Cc: Davidlohr Bueso Cc: "Matthew Wilcox (Oracle)" Cc: SeongJae Park Cc: Sven Schnelle Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index dfce1aaa7a64..a80083091f53 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2850,7 +2850,7 @@ static inline unsigned long vma_pages(struct vm_area_struct *vma) static inline struct vm_area_struct *find_exact_vma(struct mm_struct *mm, unsigned long vm_start, unsigned long vm_end) { - struct vm_area_struct *vma = find_vma(mm, vm_start); + struct vm_area_struct *vma = vma_lookup(mm, vm_start); if (vma && (vma->vm_start != vm_start || vma->vm_end != vm_end)) vma = NULL; -- cgit v1.2.3 From abdba2dda0c477ca708a939b02f9b2e74666ed2d Mon Sep 17 00:00:00 2001 From: "Liam R. Howlett" Date: Tue, 6 Sep 2022 19:48:50 +0000 Subject: mm: use maple tree operations for find_vma_intersection() Move find_vma_intersection() to mmap.c and change implementation to maple tree. When searching for a vma within a range, it is easier to use the maple tree interface. Exported find_vma_intersection() for kvm module. Link: https://lkml.kernel.org/r/20220906194824.2110408-24-Liam.Howlett@oracle.com Signed-off-by: Liam R. Howlett Tested-by: Yu Zhao Cc: Catalin Marinas Cc: David Hildenbrand Cc: David Howells Cc: Davidlohr Bueso Cc: "Matthew Wilcox (Oracle)" Cc: SeongJae Park Cc: Sven Schnelle Cc: Vlastimil Babka Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/mm.h | 22 ++++------------------ 1 file changed, 4 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index a80083091f53..06a6b8db75b7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2778,26 +2778,12 @@ extern struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long add extern struct vm_area_struct * find_vma_prev(struct mm_struct * mm, unsigned long addr, struct vm_area_struct **pprev); -/** - * find_vma_intersection() - Look up the first VMA which intersects the interval - * @mm: The process address space. - * @start_addr: The inclusive start user address. - * @end_addr: The exclusive end user address. - * - * Returns: The first VMA within the provided range, %NULL otherwise. Assumes - * start_addr < end_addr. +/* + * Look up the first VMA which intersects the interval [start_addr, end_addr) + * NULL if none. Assume start_addr < end_addr. */ -static inline struct vm_area_struct *find_vma_intersection(struct mm_struct *mm, - unsigned long start_addr, - unsigned long end_addr) -{ - struct vm_area_struct *vma = find_vma(mm, start_addr); - - if (vma && end_addr <= vma->vm_start) - vma = NULL; - return vma; -} + unsigned long start_addr, unsigned long end_addr); /** * vma_lookup() - Find a VMA at a specific address -- cgit v1.2.3 From 7964cf8caa4dfa42c4149f3833d3878713cda3dc Mon Sep 17 00:00:00 2001 From: "Liam R. Howlett" Date: Tue, 6 Sep 2022 19:48:51 +0000 Subject: mm: remove vmacache By using the maple tree and the maple tree state, the vmacache is no longer beneficial and is complicating the VMA code. Remove the vmacache to reduce the work in keeping it up to date and code complexity. Link: https://lkml.kernel.org/r/20220906194824.2110408-26-Liam.Howlett@oracle.com Signed-off-by: Liam R. Howlett Acked-by: Vlastimil Babka Tested-by: Yu Zhao Cc: Catalin Marinas Cc: David Hildenbrand Cc: David Howells Cc: Davidlohr Bueso Cc: "Matthew Wilcox (Oracle)" Cc: SeongJae Park Cc: Sven Schnelle Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/mm_types.h | 1 - include/linux/mm_types_task.h | 12 ------------ include/linux/sched.h | 1 - include/linux/vm_event_item.h | 4 ---- include/linux/vmacache.h | 28 ---------------------------- include/linux/vmstat.h | 6 ------ 6 files changed, 52 deletions(-) delete mode 100644 include/linux/vmacache.h (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index ac747273c4d6..4541b74b1bdb 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -475,7 +475,6 @@ struct mm_struct { struct { struct vm_area_struct *mmap; /* list of VMAs */ struct maple_tree mm_mt; - u64 vmacache_seqnum; /* per-thread vmacache */ #ifdef CONFIG_MMU unsigned long (*get_unmapped_area) (struct file *filp, unsigned long addr, unsigned long len, diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h index c1bc6731125c..0bb4b6da9993 100644 --- a/include/linux/mm_types_task.h +++ b/include/linux/mm_types_task.h @@ -24,18 +24,6 @@ IS_ENABLED(CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK)) #define ALLOC_SPLIT_PTLOCKS (SPINLOCK_SIZE > BITS_PER_LONG/8) -/* - * The per task VMA cache array: - */ -#define VMACACHE_BITS 2 -#define VMACACHE_SIZE (1U << VMACACHE_BITS) -#define VMACACHE_MASK (VMACACHE_SIZE - 1) - -struct vmacache { - u64 seqnum; - struct vm_area_struct *vmas[VMACACHE_SIZE]; -}; - /* * When updating this, please also update struct resident_page_types[] in * kernel/fork.c diff --git a/include/linux/sched.h b/include/linux/sched.h index a2dcfb91df03..fbac3c19fe35 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -861,7 +861,6 @@ struct task_struct { struct mm_struct *active_mm; /* Per-thread vma caching: */ - struct vmacache vmacache; #ifdef SPLIT_RSS_COUNTING struct task_rss_stat rss_stat; diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index f3fc36cd2276..3518dba1e02f 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -129,10 +129,6 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, NR_TLB_LOCAL_FLUSH_ALL, NR_TLB_LOCAL_FLUSH_ONE, #endif /* CONFIG_DEBUG_TLBFLUSH */ -#ifdef CONFIG_DEBUG_VM_VMACACHE - VMACACHE_FIND_CALLS, - VMACACHE_FIND_HITS, -#endif #ifdef CONFIG_SWAP SWAP_RA, SWAP_RA_HIT, diff --git a/include/linux/vmacache.h b/include/linux/vmacache.h deleted file mode 100644 index 6fce268a4588..000000000000 --- a/include/linux/vmacache.h +++ /dev/null @@ -1,28 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __LINUX_VMACACHE_H -#define __LINUX_VMACACHE_H - -#include -#include - -static inline void vmacache_flush(struct task_struct *tsk) -{ - memset(tsk->vmacache.vmas, 0, sizeof(tsk->vmacache.vmas)); -} - -extern void vmacache_update(unsigned long addr, struct vm_area_struct *newvma); -extern struct vm_area_struct *vmacache_find(struct mm_struct *mm, - unsigned long addr); - -#ifndef CONFIG_MMU -extern struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm, - unsigned long start, - unsigned long end); -#endif - -static inline void vmacache_invalidate(struct mm_struct *mm) -{ - mm->vmacache_seqnum++; -} - -#endif /* __LINUX_VMACACHE_H */ diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index bfe38869498d..19cf5b6892ce 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -125,12 +125,6 @@ static inline void vm_events_fold_cpu(int cpu) #define count_vm_tlb_events(x, y) do { (void)(y); } while (0) #endif -#ifdef CONFIG_DEBUG_VM_VMACACHE -#define count_vm_vmacache_event(x) count_vm_event(x) -#else -#define count_vm_vmacache_event(x) do {} while (0) -#endif - #define __count_zid_vm_events(item, zid, delta) \ __count_vm_events(item##_NORMAL - ZONE_NORMAL + zid, delta) -- cgit v1.2.3 From d7c62295570f012e1d386ae6ed472b36baf037ad Mon Sep 17 00:00:00 2001 From: "Liam R. Howlett" Date: Tue, 6 Sep 2022 19:48:51 +0000 Subject: mm: convert vma_lookup() to use mtree_load() Unlike the rbtree, the Maple Tree will return a NULL if there's nothing at a particular address. Since the previous commit dropped the vmacache, it is now possible to consult the tree directly. Link: https://lkml.kernel.org/r/20220906194824.2110408-27-Liam.Howlett@oracle.com Signed-off-by: Liam R. Howlett Signed-off-by: Matthew Wilcox (Oracle) Acked-by: Vlastimil Babka Tested-by: Yu Zhao Cc: Catalin Marinas Cc: David Hildenbrand Cc: David Howells Cc: Davidlohr Bueso Cc: SeongJae Park Cc: Sven Schnelle Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/mm.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 06a6b8db75b7..49a58807719b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2795,12 +2795,7 @@ struct vm_area_struct *find_vma_intersection(struct mm_struct *mm, static inline struct vm_area_struct *vma_lookup(struct mm_struct *mm, unsigned long addr) { - struct vm_area_struct *vma = find_vma(mm, addr); - - if (vma && addr < vma->vm_start) - vma = NULL; - - return vma; + return mtree_load(&mm->mm_mt, addr); } static inline unsigned long vm_start_gap(struct vm_area_struct *vma) -- cgit v1.2.3 From 11f9a21ab65542189372b7d64bb2d2937dfdc9dc Mon Sep 17 00:00:00 2001 From: "Liam R. Howlett" Date: Tue, 6 Sep 2022 19:48:52 +0000 Subject: mm/mmap: reorganize munmap to use maple states Remove __do_munmap() in favour of do_munmap(), do_mas_munmap(), and do_mas_align_munmap(). do_munmap() is a wrapper to create a maple state for any callers that have not been converted to the maple tree. do_mas_munmap() takes a maple state to mumap a range. This is just a small function which checks for error conditions and aligns the end of the range. do_mas_align_munmap() uses the aligned range to mumap a range. do_mas_align_munmap() starts with the first VMA in the range, then finds the last VMA in the range. Both start and end are split if necessary. Then the VMAs are removed from the linked list and the mm mlock count is updated at the same time. Followed by a single tree operation of overwriting the area in with a NULL. Finally, the detached list is unmapped and freed. By reorganizing the munmap calls as outlined, it is now possible to avoid extra work of aligning pre-aligned callers which are known to be safe, avoid extra VMA lookups or tree walks for modifications. detach_vmas_to_be_unmapped() is no longer used, so drop this code. vm_brk_flags() can just call the do_mas_munmap() as it checks for intersecting VMAs directly. Link: https://lkml.kernel.org/r/20220906194824.2110408-29-Liam.Howlett@oracle.com Signed-off-by: Liam R. Howlett Tested-by: Yu Zhao Cc: Catalin Marinas Cc: David Hildenbrand Cc: David Howells Cc: Davidlohr Bueso Cc: "Matthew Wilcox (Oracle)" Cc: SeongJae Park Cc: Sven Schnelle Cc: Vlastimil Babka Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/mm.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 49a58807719b..579449d6c23b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2710,8 +2710,9 @@ extern unsigned long mmap_region(struct file *file, unsigned long addr, extern unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, unsigned long pgoff, unsigned long *populate, struct list_head *uf); -extern int __do_munmap(struct mm_struct *, unsigned long, size_t, - struct list_head *uf, bool downgrade); +extern int do_mas_munmap(struct ma_state *mas, struct mm_struct *mm, + unsigned long start, size_t len, struct list_head *uf, + bool downgrade); extern int do_munmap(struct mm_struct *, unsigned long, size_t, struct list_head *uf); extern int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int behavior); -- cgit v1.2.3 From 69dbe6daf1041e32e003f966d71f70f20c63af53 Mon Sep 17 00:00:00 2001 From: "Liam R. Howlett" Date: Tue, 6 Sep 2022 19:48:57 +0000 Subject: userfaultfd: use maple tree iterator to iterate VMAs Don't use the mm_struct linked list or the vma->vm_next in prep for removal. Link: https://lkml.kernel.org/r/20220906194824.2110408-45-Liam.Howlett@oracle.com Signed-off-by: Liam R. Howlett Tested-by: Yu Zhao Cc: Catalin Marinas Cc: David Hildenbrand Cc: David Howells Cc: Davidlohr Bueso Cc: "Matthew Wilcox (Oracle)" Cc: SeongJae Park Cc: Sven Schnelle Cc: Vlastimil Babka Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/userfaultfd_k.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index e1b8a915e9e9..f07e6998bb68 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -175,9 +175,8 @@ extern bool userfaultfd_remove(struct vm_area_struct *vma, unsigned long start, unsigned long end); -extern int userfaultfd_unmap_prep(struct vm_area_struct *vma, - unsigned long start, unsigned long end, - struct list_head *uf); +extern int userfaultfd_unmap_prep(struct mm_struct *mm, unsigned long start, + unsigned long end, struct list_head *uf); extern void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf); @@ -258,7 +257,7 @@ static inline bool userfaultfd_remove(struct vm_area_struct *vma, return true; } -static inline int userfaultfd_unmap_prep(struct vm_area_struct *vma, +static inline int userfaultfd_unmap_prep(struct mm_struct *mm, unsigned long start, unsigned long end, struct list_head *uf) { -- cgit v1.2.3 From 763ecb035029f500d7e6dc99acd1ad299b7726a1 Mon Sep 17 00:00:00 2001 From: "Liam R. Howlett" Date: Tue, 6 Sep 2022 19:49:06 +0000 Subject: mm: remove the vma linked list Replace any vm_next use with vma_find(). Update free_pgtables(), unmap_vmas(), and zap_page_range() to use the maple tree. Use the new free_pgtables() and unmap_vmas() in do_mas_align_munmap(). At the same time, alter the loop to be more compact. Now that free_pgtables() and unmap_vmas() take a maple tree as an argument, rearrange do_mas_align_munmap() to use the new tree to hold the vmas to remove. Remove __vma_link_list() and __vma_unlink_list() as they are exclusively used to update the linked list. Drop linked list update from __insert_vm_struct(). Rework validation of tree as it was depending on the linked list. [yang.lee@linux.alibaba.com: fix one kernel-doc comment] Link: https://bugzilla.openanolis.cn/show_bug.cgi?id=1949 Link: https://lkml.kernel.org/r/20220824021918.94116-1-yang.lee@linux.alibaba.comLink: https://lkml.kernel.org/r/20220906194824.2110408-69-Liam.Howlett@oracle.com Signed-off-by: Liam R. Howlett Signed-off-by: Yang Li Tested-by: Yu Zhao Cc: Catalin Marinas Cc: David Hildenbrand Cc: David Howells Cc: Davidlohr Bueso Cc: "Matthew Wilcox (Oracle)" Cc: SeongJae Park Cc: Sven Schnelle Cc: Vlastimil Babka Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/mm.h | 5 +++-- include/linux/mm_types.h | 4 ---- 2 files changed, 3 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 579449d6c23b..37384a84f71a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1857,8 +1857,9 @@ void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, unsigned long size); void zap_page_range(struct vm_area_struct *vma, unsigned long address, unsigned long size); -void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma, - unsigned long start, unsigned long end); +void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt, + struct vm_area_struct *start_vma, unsigned long start, + unsigned long end); struct mmu_notifier_range; diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 4541b74b1bdb..5e32211cb5a9 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -408,8 +408,6 @@ struct vm_area_struct { unsigned long vm_end; /* The first byte after our end address within vm_mm. */ - /* linked list of VM areas per task, sorted by address */ - struct vm_area_struct *vm_next, *vm_prev; struct mm_struct *vm_mm; /* The address space we belong to. */ /* @@ -473,7 +471,6 @@ struct vm_area_struct { struct kioctx_table; struct mm_struct { struct { - struct vm_area_struct *mmap; /* list of VMAs */ struct maple_tree mm_mt; #ifdef CONFIG_MMU unsigned long (*get_unmapped_area) (struct file *filp, @@ -488,7 +485,6 @@ struct mm_struct { unsigned long mmap_compat_legacy_base; #endif unsigned long task_size; /* size of task vm space */ - unsigned long highest_vm_end; /* highest vma end address */ pgd_t * pgd; #ifdef CONFIG_MEMBARRIER -- cgit v1.2.3 From bf3980c85212fc71512d27a46f5aab66f46ca284 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Tue, 31 May 2022 15:30:59 -0700 Subject: mm: drop oom code from exit_mmap The primary reason to invoke the oom reaper from the exit_mmap path used to be a prevention of an excessive oom killing if the oom victim exit races with the oom reaper (see [1] for more details). The invocation has moved around since then because of the interaction with the munlock logic but the underlying reason has remained the same (see [2]). Munlock code is no longer a problem since [3] and there shouldn't be any blocking operation before the memory is unmapped by exit_mmap so the oom reaper invocation can be dropped. The unmapping part can be done with the non-exclusive mmap_sem and the exclusive one is only required when page tables are freed. Remove the oom_reaper from exit_mmap which will make the code easier to read. This is really unlikely to make any observable difference although some microbenchmarks could benefit from one less branch that needs to be evaluated even though it almost never is true. [1] 212925802454 ("mm: oom: let oom_reap_task and exit_mmap run concurrently") [2] 27ae357fa82b ("mm, oom: fix concurrent munlock and oom reaper unmap, v3") [3] a213e5cf71cb ("mm/munlock: delete munlock_vma_pages_all(), allow oomreap") [akpm@linux-foundation.org: restore Suren's mmap_read_lock() optimization] Link: https://lkml.kernel.org/r/20220531223100.510392-1-surenb@google.com Signed-off-by: Suren Baghdasaryan Acked-by: Michal Hocko Cc: Andrea Arcangeli Cc: Christian Brauner (Microsoft) Cc: Christoph Hellwig Cc: David Hildenbrand Cc: David Rientjes Cc: Jann Horn Cc: Johannes Weiner Cc: John Hubbard Cc: "Kirill A . Shutemov" Cc: Liam Howlett Cc: Matthew Wilcox Cc: Minchan Kim Cc: Oleg Nesterov Cc: Peter Xu Cc: Roman Gushchin Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton --- include/linux/oom.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/oom.h b/include/linux/oom.h index 02d1e7bbd8cd..6cdde62b078b 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -106,8 +106,6 @@ static inline vm_fault_t check_stable_address_space(struct mm_struct *mm) return 0; } -bool __oom_reap_task_mm(struct mm_struct *mm); - long oom_badness(struct task_struct *p, unsigned long totalpages); -- cgit v1.2.3 From b3541d912a84dc40cabb516f2deeac9ae6fa30da Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Tue, 31 May 2022 15:31:00 -0700 Subject: mm: delete unused MMF_OOM_VICTIM flag With the last usage of MMF_OOM_VICTIM in exit_mmap gone, this flag is now unused and can be removed. [akpm@linux-foundation.org: remove comment about now-removed mm_is_oom_victim()] Link: https://lkml.kernel.org/r/20220531223100.510392-2-surenb@google.com Signed-off-by: Suren Baghdasaryan Acked-by: Michal Hocko Cc: David Rientjes Cc: Matthew Wilcox Cc: Johannes Weiner Cc: Roman Gushchin Cc: Minchan Kim Cc: "Kirill A . Shutemov" Cc: Andrea Arcangeli Cc: Christian Brauner (Microsoft) Cc: Christoph Hellwig Cc: Oleg Nesterov Cc: David Hildenbrand Cc: Jann Horn Cc: Shakeel Butt Cc: Peter Xu Cc: John Hubbard Cc: Shuah Khan Cc: Liam Howlett Signed-off-by: Andrew Morton --- include/linux/oom.h | 9 --------- include/linux/sched/coredump.h | 7 +++---- 2 files changed, 3 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/oom.h b/include/linux/oom.h index 6cdde62b078b..7d0c9c48a0c5 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -77,15 +77,6 @@ static inline bool tsk_is_oom_victim(struct task_struct * tsk) return tsk->signal->oom_mm; } -/* - * Use this helper if tsk->mm != mm and the victim mm needs a special - * handling. This is guaranteed to stay true after once set. - */ -static inline bool mm_is_oom_victim(struct mm_struct *mm) -{ - return test_bit(MMF_OOM_VICTIM, &mm->flags); -} - /* * Checks whether a page fault on the given mm is still reliable. * This is no longer true if the oom reaper started to reap the diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index 4d0a5be28b70..8270ad7ae14c 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -71,9 +71,8 @@ static inline int get_dumpable(struct mm_struct *mm) #define MMF_UNSTABLE 22 /* mm is unstable for copy_from_user */ #define MMF_HUGE_ZERO_PAGE 23 /* mm has ever used the global huge zero page */ #define MMF_DISABLE_THP 24 /* disable THP for all VMAs */ -#define MMF_OOM_VICTIM 25 /* mm is the oom victim */ -#define MMF_OOM_REAP_QUEUED 26 /* mm was queued for oom_reaper */ -#define MMF_MULTIPROCESS 27 /* mm is shared between processes */ +#define MMF_OOM_REAP_QUEUED 25 /* mm was queued for oom_reaper */ +#define MMF_MULTIPROCESS 26 /* mm is shared between processes */ /* * MMF_HAS_PINNED: Whether this mm has pinned any pages. This can be either * replaced in the future by mm.pinned_vm when it becomes stable, or grow into @@ -81,7 +80,7 @@ static inline int get_dumpable(struct mm_struct *mm) * pinned pages were unpinned later on, we'll still keep this bit set for the * lifecycle of this mm, just for simplicity. */ -#define MMF_HAS_PINNED 28 /* FOLL_PIN has run, never cleared */ +#define MMF_HAS_PINNED 27 /* FOLL_PIN has run, never cleared */ #define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP) #define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\ -- cgit v1.2.3 From 474098edac262ae26bfab1c48445877075a31cbd Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 25 Aug 2022 18:46:57 +0200 Subject: mm/gup: replace FOLL_NUMA by gup_can_follow_protnone() Patch series "mm: minor cleanups around NUMA hinting". Working on some GUP cleanups (e.g., getting rid of some FOLL_ flags) and preparing for other GUP changes (getting rid of FOLL_FORCE|FOLL_WRITE for for taking a R/O longterm pin), this is something I can easily send out independently. Get rid of FOLL_NUMA, allow FOLL_FORCE access to PROT_NONE mapped pages in GUP-fast, and fixup some documentation around NUMA hinting. This patch (of 3): No need for a special flag that is not even properly documented to be internal-only. Let's just factor this check out and get rid of this flag. The separate function has the nice benefit that we can centralize comments. Link: https://lkml.kernel.org/r/20220825164659.89824-2-david@redhat.com Link: https://lkml.kernel.org/r/20220825164659.89824-1-david@redhat.com Signed-off-by: David Hildenbrand Cc: Andrea Arcangeli Cc: Hugh Dickins Cc: Jason Gunthorpe Cc: John Hubbard Cc: Matthew Wilcox Cc: Mel Gorman Cc: Peter Xu Signed-off-by: Andrew Morton --- include/linux/mm.h | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 37384a84f71a..eb25cae06c55 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2933,7 +2933,6 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, * and return without waiting upon it */ #define FOLL_NOFAULT 0x80 /* do not fault in pages */ #define FOLL_HWPOISON 0x100 /* check page is hwpoisoned */ -#define FOLL_NUMA 0x200 /* force NUMA hinting page fault */ #define FOLL_MIGRATION 0x400 /* wait for page to replace migration entry */ #define FOLL_TRIED 0x800 /* a retry, previous pass started an IO */ #define FOLL_REMOTE 0x2000 /* we are working on non-current tsk/mm */ @@ -3054,6 +3053,21 @@ static inline bool gup_must_unshare(unsigned int flags, struct page *page) return !PageAnonExclusive(page); } +/* + * Indicates whether GUP can follow a PROT_NONE mapped page, or whether + * a (NUMA hinting) fault is required. + */ +static inline bool gup_can_follow_protnone(unsigned int flags) +{ + /* + * FOLL_FORCE has to be able to make progress even if the VMA is + * inaccessible. Further, FOLL_FORCE access usually does not represent + * application behaviour and we should avoid triggering NUMA hinting + * faults. + */ + return flags & FOLL_FORCE; +} + typedef int (*pte_fn_t)(pte_t *pte, unsigned long addr, void *data); extern int apply_to_page_range(struct mm_struct *mm, unsigned long address, unsigned long size, pte_fn_t fn, void *data); -- cgit v1.2.3 From 7014887a01587d8c50871d5985cd572ca08b29c0 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 25 Aug 2022 18:46:59 +0200 Subject: mm: fixup documentation regarding pte_numa() and PROT_NUMA pte_numa() no longer exists -- replaced by pte_protnone() -- and PROT_NUMA probably never existed: MM_CP_PROT_NUMA also ends up using PROT_NONE. Let's fixup the doc. Link: https://lkml.kernel.org/r/20220825164659.89824-4-david@redhat.com Signed-off-by: David Hildenbrand Cc: Andrea Arcangeli Cc: Hugh Dickins Cc: Jason Gunthorpe Cc: John Hubbard Cc: Matthew Wilcox Cc: Mel Gorman Cc: Peter Xu Signed-off-by: Andrew Morton --- include/linux/mm_types.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 5e32211cb5a9..26573ba485f3 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -614,22 +614,22 @@ struct mm_struct { #endif #ifdef CONFIG_NUMA_BALANCING /* - * numa_next_scan is the next time that the PTEs will be marked - * pte_numa. NUMA hinting faults will gather statistics and - * migrate pages to new nodes if necessary. + * numa_next_scan is the next time that PTEs will be remapped + * PROT_NONE to trigger NUMA hinting faults; such faults gather + * statistics and migrate pages to new nodes if necessary. */ unsigned long numa_next_scan; - /* Restart point for scanning and setting pte_numa */ + /* Restart point for scanning and remapping PTEs. */ unsigned long numa_scan_offset; - /* numa_scan_seq prevents two threads setting pte_numa */ + /* numa_scan_seq prevents two threads remapping PTEs. */ int numa_scan_seq; #endif /* * An operation with batched TLB flushing is going on. Anything * that can move process memory needs to flush the TLB when - * moving a PROT_NONE or PROT_NUMA mapped page. + * moving a PROT_NONE mapped page. */ atomic_t tlb_flush_pending; #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH -- cgit v1.2.3 From 974f4367dd315acc15ad4a6453f8304aea60dfbd Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Tue, 23 Aug 2022 11:22:30 +0200 Subject: mm: reduce noise in show_mem for lowmem allocations While discussing early DMA pool pre-allocation failure with Christoph [1] I have realized that the allocation failure warning is rather noisy for constrained allocations like GFP_DMA{32}. Those zones are usually not populated on all nodes very often as their memory ranges are constrained. This is an attempt to reduce the ballast that doesn't provide any relevant information for those allocation failures investigation. Please note that I have only compile tested it (in my default config setup) and I am throwing it mostly to see what people think about it. [1] http://lkml.kernel.org/r/20220817060647.1032426-1-hch@lst.de [mhocko@suse.com: update] Link: https://lkml.kernel.org/r/Yw29bmJTIkKogTiW@dhcp22.suse.cz [mhocko@suse.com: fix build] [akpm@linux-foundation.org: fix it for mapletree] [akpm@linux-foundation.org: update it for Michal's update] [mhocko@suse.com: fix arch/powerpc/xmon/xmon.c] Link: https://lkml.kernel.org/r/Ywh3C4dKB9B93jIy@dhcp22.suse.cz [akpm@linux-foundation.org: fix arch/sparc/kernel/setup_32.c] Link: https://lkml.kernel.org/r/YwScVmVofIZkopkF@dhcp22.suse.cz Signed-off-by: Michal Hocko Acked-by: Johannes Weiner Acked-by: Vlastimil Babka Cc: Christoph Hellwig Cc: Mel Gorman Cc: Dan Carpenter Signed-off-by: Andrew Morton --- include/linux/mm.h | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index eb25cae06c55..e56dd8f7eae1 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1838,7 +1838,11 @@ extern void pagefault_out_of_memory(void); */ #define SHOW_MEM_FILTER_NODES (0x0001u) /* disallowed nodes */ -extern void show_free_areas(unsigned int flags, nodemask_t *nodemask); +extern void __show_free_areas(unsigned int flags, nodemask_t *nodemask, int max_zone_idx); +static void __maybe_unused show_free_areas(unsigned int flags, nodemask_t *nodemask) +{ + __show_free_areas(flags, nodemask, MAX_NR_ZONES - 1); +} #ifdef CONFIG_MMU extern bool can_do_mlock(void); @@ -2578,7 +2582,12 @@ extern void calculate_min_free_kbytes(void); extern int __meminit init_per_zone_wmark_min(void); extern void mem_init(void); extern void __init mmap_init(void); -extern void show_mem(unsigned int flags, nodemask_t *nodemask); + +extern void __show_mem(unsigned int flags, nodemask_t *nodemask, int max_zone_idx); +static inline void show_mem(unsigned int flags, nodemask_t *nodemask) +{ + __show_mem(flags, nodemask, MAX_NR_ZONES - 1); +} extern long si_mem_available(void); extern void si_meminfo(struct sysinfo * val); extern void si_meminfo_node(struct sysinfo *val, int nid); -- cgit v1.2.3 From e6ad640bc404eb298dd1880113131768ddf5c6a8 Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Fri, 26 Aug 2022 23:06:42 +0000 Subject: mm: deduplicate cacheline padding code There are three users (mmzone.h, memcontrol.h, page_counter.h) using similar code for forcing cacheline padding between fields of different structures. Dedup that code. Link: https://lkml.kernel.org/r/20220826230642.566725-1-shakeelb@google.com Signed-off-by: Shakeel Butt Suggested-by: Feng Tang Reviewed-by: Feng Tang Acked-by: Michal Hocko Signed-off-by: Andrew Morton --- include/linux/cache.h | 13 +++++++++++++ include/linux/memcontrol.h | 13 ++----------- include/linux/mmzone.h | 24 +++++------------------- include/linux/page_counter.h | 13 ++----------- 4 files changed, 22 insertions(+), 41 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cache.h b/include/linux/cache.h index d742c57eaee5..5da1bbd96154 100644 --- a/include/linux/cache.h +++ b/include/linux/cache.h @@ -85,4 +85,17 @@ #define cache_line_size() L1_CACHE_BYTES #endif +/* + * Helper to add padding within a struct to ensure data fall into separate + * cachelines. + */ +#if defined(CONFIG_SMP) +struct cacheline_padding { + char x[0]; +} ____cacheline_internodealigned_in_smp; +#define CACHELINE_PADDING(name) struct cacheline_padding name +#else +#define CACHELINE_PADDING(name) +#endif + #endif /* __LINUX_CACHE_H */ diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 344022f102c2..60545e4a1c03 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -185,15 +185,6 @@ struct mem_cgroup_thresholds { struct mem_cgroup_threshold_ary *spare; }; -#if defined(CONFIG_SMP) -struct memcg_padding { - char x[0]; -} ____cacheline_internodealigned_in_smp; -#define MEMCG_PADDING(name) struct memcg_padding name -#else -#define MEMCG_PADDING(name) -#endif - /* * Remember four most recent foreign writebacks with dirty pages in this * cgroup. Inode sharing is expected to be uncommon and, even if we miss @@ -304,7 +295,7 @@ struct mem_cgroup { spinlock_t move_lock; unsigned long move_lock_flags; - MEMCG_PADDING(_pad1_); + CACHELINE_PADDING(_pad1_); /* memory.stat */ struct memcg_vmstats vmstats; @@ -326,7 +317,7 @@ struct mem_cgroup { struct list_head objcg_list; #endif - MEMCG_PADDING(_pad2_); + CACHELINE_PADDING(_pad2_); /* * set > 0 if pages under this cgroup are moving to other cgroup. diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index e335a492c2eb..c69c08156822 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -121,20 +121,6 @@ static inline bool free_area_empty(struct free_area *area, int migratetype) struct pglist_data; -/* - * Add a wild amount of padding here to ensure data fall into separate - * cachelines. There are very few zone structures in the machine, so space - * consumption is not a concern here. - */ -#if defined(CONFIG_SMP) -struct zone_padding { - char x[0]; -} ____cacheline_internodealigned_in_smp; -#define ZONE_PADDING(name) struct zone_padding name; -#else -#define ZONE_PADDING(name) -#endif - #ifdef CONFIG_NUMA enum numa_stat_item { NUMA_HIT, /* allocated in intended node */ @@ -837,7 +823,7 @@ struct zone { int initialized; /* Write-intensive fields used from the page allocator */ - ZONE_PADDING(_pad1_) + CACHELINE_PADDING(_pad1_); /* free areas of different sizes */ struct free_area free_area[MAX_ORDER]; @@ -849,7 +835,7 @@ struct zone { spinlock_t lock; /* Write-intensive fields used by compaction and vmstats. */ - ZONE_PADDING(_pad2_) + CACHELINE_PADDING(_pad2_); /* * When free pages are below this point, additional steps are taken @@ -886,7 +872,7 @@ struct zone { bool contiguous; - ZONE_PADDING(_pad3_) + CACHELINE_PADDING(_pad3_); /* Zone statistics */ atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS]; atomic_long_t vm_numa_event[NR_VM_NUMA_EVENT_ITEMS]; @@ -1196,7 +1182,7 @@ typedef struct pglist_data { #endif /* CONFIG_NUMA */ /* Write-intensive fields used by page reclaim */ - ZONE_PADDING(_pad1_) + CACHELINE_PADDING(_pad1_); #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /* @@ -1241,7 +1227,7 @@ typedef struct pglist_data { struct lru_gen_mm_walk mm_walk; #endif - ZONE_PADDING(_pad2_) + CACHELINE_PADDING(_pad2_); /* Per-node vmstats */ struct per_cpu_nodestat __percpu *per_cpu_nodestats; diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h index 78a1c934e416..c141ea9a95ef 100644 --- a/include/linux/page_counter.h +++ b/include/linux/page_counter.h @@ -7,22 +7,13 @@ #include #include -#if defined(CONFIG_SMP) -struct pc_padding { - char x[0]; -} ____cacheline_internodealigned_in_smp; -#define PC_PADDING(name) struct pc_padding name -#else -#define PC_PADDING(name) -#endif - struct page_counter { /* * Make sure 'usage' does not share cacheline with any other field. The * memcg->memory.usage is a hot member of struct mem_cgroup. */ atomic_long_t usage; - PC_PADDING(_pad1_); + CACHELINE_PADDING(_pad1_); /* effective memory.min and memory.min usage tracking */ unsigned long emin; @@ -38,7 +29,7 @@ struct page_counter { unsigned long failcnt; /* Keep all the read most fields in a separete cacheline. */ - PC_PADDING(_pad2_); + CACHELINE_PADDING(_pad2_); unsigned long min; unsigned long low; -- cgit v1.2.3 From cb4df4cae4f2bd8cf7a32eff81178fce31600f7c Mon Sep 17 00:00:00 2001 From: xu xin Date: Tue, 30 Aug 2022 14:38:38 +0000 Subject: ksm: count allocated ksm rmap_items for each process Patch series "ksm: count allocated rmap_items and update documentation", v5. KSM can save memory by merging identical pages, but also can consume additional memory, because it needs to generate rmap_items to save each scanned page's brief rmap information. To determine how beneficial the ksm-policy (like madvise), they are using brings, so we add a new interface /proc//ksm_stat for each process The value "ksm_rmap_items" in it indicates the total allocated ksm rmap_items of this process. The detailed description can be seen in the following patches' commit message. This patch (of 2): KSM can save memory by merging identical pages, but also can consume additional memory, because it needs to generate rmap_items to save each scanned page's brief rmap information. Some of these pages may be merged, but some may not be abled to be merged after being checked several times, which are unprofitable memory consumed. The information about whether KSM save memory or consume memory in system-wide range can be determined by the comprehensive calculation of pages_sharing, pages_shared, pages_unshared and pages_volatile. A simple approximate calculation: profit =~ pages_sharing * sizeof(page) - (all_rmap_items) * sizeof(rmap_item); where all_rmap_items equals to the sum of pages_sharing, pages_shared, pages_unshared and pages_volatile. But we cannot calculate this kind of ksm profit inner single-process wide because the information of ksm rmap_item's number of a process is lacked. For user applications, if this kind of information could be obtained, it helps upper users know how beneficial the ksm-policy (like madvise) they are using brings, and then optimize their app code. For example, one application madvise 1000 pages as MERGEABLE, while only a few pages are really merged, then it's not cost-efficient. So we add a new interface /proc//ksm_stat for each process in which the value of ksm_rmap_itmes is only shown now and so more values can be added in future. So similarly, we can calculate the ksm profit approximately for a single process by: profit =~ ksm_merging_pages * sizeof(page) - ksm_rmap_items * sizeof(rmap_item); where ksm_merging_pages is shown at /proc//ksm_merging_pages, and ksm_rmap_items is shown in /proc//ksm_stat. Link: https://lkml.kernel.org/r/20220830143731.299702-1-xu.xin16@zte.com.cn Link: https://lkml.kernel.org/r/20220830143838.299758-1-xu.xin16@zte.com.cn Signed-off-by: xu xin Reviewed-by: Xiaokai Ran Reviewed-by: Yang Yang Signed-off-by: CGEL ZTE Cc: Alexey Dobriyan Cc: Bagas Sanjaya Cc: Hugh Dickins Cc: Izik Eidus Cc: Matthew Wilcox Signed-off-by: Andrew Morton --- include/linux/mm_types.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 26573ba485f3..8f30f262431c 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -654,6 +654,11 @@ struct mm_struct { * merging. */ unsigned long ksm_merging_pages; + /* + * Represent how many pages are checked for ksm merging + * including merged and not merged. + */ + unsigned long ksm_rmap_items; #endif #ifdef CONFIG_LRU_GEN struct { -- cgit v1.2.3 From 3008119a3dd8052b7e5c07488e20a7abb0d287f2 Mon Sep 17 00:00:00 2001 From: Gaosheng Cui Date: Fri, 23 Sep 2022 17:00:12 +0800 Subject: ftrace: Remove obsoleted code from ftrace and task_struct The trace of "struct task_struct" was no longer used since commit 345ddcc882d8 ("ftrace: Have set_ftrace_pid use the bitmap like events do"), and the functions about flags for current->trace is useless, so remove them. Link: https://lkml.kernel.org/r/20220923090012.505990-1-cuigaosheng1@huawei.com Signed-off-by: Gaosheng Cui Signed-off-by: Steven Rostedt (Google) --- include/linux/ftrace.h | 41 ----------------------------------------- include/linux/sched.h | 3 --- 2 files changed, 44 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 0b61371e287b..62557d4bffc2 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -1122,47 +1122,6 @@ static inline void unpause_graph_tracing(void) { } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ #ifdef CONFIG_TRACING - -/* flags for current->trace */ -enum { - TSK_TRACE_FL_TRACE_BIT = 0, - TSK_TRACE_FL_GRAPH_BIT = 1, -}; -enum { - TSK_TRACE_FL_TRACE = 1 << TSK_TRACE_FL_TRACE_BIT, - TSK_TRACE_FL_GRAPH = 1 << TSK_TRACE_FL_GRAPH_BIT, -}; - -static inline void set_tsk_trace_trace(struct task_struct *tsk) -{ - set_bit(TSK_TRACE_FL_TRACE_BIT, &tsk->trace); -} - -static inline void clear_tsk_trace_trace(struct task_struct *tsk) -{ - clear_bit(TSK_TRACE_FL_TRACE_BIT, &tsk->trace); -} - -static inline int test_tsk_trace_trace(struct task_struct *tsk) -{ - return tsk->trace & TSK_TRACE_FL_TRACE; -} - -static inline void set_tsk_trace_graph(struct task_struct *tsk) -{ - set_bit(TSK_TRACE_FL_GRAPH_BIT, &tsk->trace); -} - -static inline void clear_tsk_trace_graph(struct task_struct *tsk) -{ - clear_bit(TSK_TRACE_FL_GRAPH_BIT, &tsk->trace); -} - -static inline int test_tsk_trace_graph(struct task_struct *tsk) -{ - return tsk->trace & TSK_TRACE_FL_GRAPH; -} - enum ftrace_dump_mode; extern enum ftrace_dump_mode ftrace_dump_on_oops; diff --git a/include/linux/sched.h b/include/linux/sched.h index e7b2f8a5c711..c7ee04e9147a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1381,9 +1381,6 @@ struct task_struct { #endif #ifdef CONFIG_TRACING - /* State flags for use by tracers: */ - unsigned long trace; - /* Bitmask and counter of trace recursion: */ unsigned long trace_recursion; #endif /* CONFIG_TRACING */ -- cgit v1.2.3 From 612d5494aef9bd2ab68d585a8c0ac2b16d12d520 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Tue, 27 Sep 2022 20:45:57 +0800 Subject: irqchip: Make irqchip_init() usable on pure ACPI systems Pure ACPI systems (e.g., LoongArch) do not need OF_IRQ, but still require irqchip_init() to perform the ACPI irqchip probing, even when OF_IRQ isn't selected. Relax the dependency to enable the generic irqchip support when ACPI_GENERIC_GSI is configured. Signed-off-by: Huacai Chen Tested-by: Tiezhu Yang [maz: revamped commit message] Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20220927124557.3246737-1-chenhuacai@loongson.cn --- include/linux/of_irq.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h index 83fccd0c9bba..d6d3eae2f145 100644 --- a/include/linux/of_irq.h +++ b/include/linux/of_irq.h @@ -37,9 +37,8 @@ extern unsigned int irq_create_of_mapping(struct of_phandle_args *irq_data); extern int of_irq_to_resource(struct device_node *dev, int index, struct resource *r); -extern void of_irq_init(const struct of_device_id *matches); - #ifdef CONFIG_OF_IRQ +extern void of_irq_init(const struct of_device_id *matches); extern int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_args *out_irq); extern int of_irq_count(struct device_node *dev); @@ -57,6 +56,9 @@ extern struct irq_domain *of_msi_map_get_device_domain(struct device *dev, extern void of_msi_configure(struct device *dev, struct device_node *np); u32 of_msi_map_id(struct device *dev, struct device_node *msi_np, u32 id_in); #else +static inline void of_irq_init(const struct of_device_id *matches) +{ +} static inline int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_args *out_irq) { -- cgit v1.2.3 From 334f7d42db3eb0274aa6b4aba7ce14d87df3fef0 Mon Sep 17 00:00:00 2001 From: Frank Li Date: Thu, 22 Sep 2022 11:12:42 -0500 Subject: irqchip: Allow extra fields to be passed to IRQCHIP_PLATFORM_DRIVER_END IRQCHIP_PLATFORM_DRIVER_* doesn't allow some fields (such as .pm) to be set in the platform_driver structure. Make IRQCHIP_PLATFORM_DRIVER_END variadic so that .pm or another field can be set if needed. Signed-off-by: Frank Li [maz: revamped commit message] Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20220922161246.20586-3-Frank.Li@nxp.com --- include/linux/irqchip.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/irqchip.h b/include/linux/irqchip.h index 3a091d0710ae..d5e6024cb2a8 100644 --- a/include/linux/irqchip.h +++ b/include/linux/irqchip.h @@ -44,7 +44,8 @@ static const struct of_device_id drv_name##_irqchip_match_table[] = { #define IRQCHIP_MATCH(compat, fn) { .compatible = compat, \ .data = typecheck_irq_init_cb(fn), }, -#define IRQCHIP_PLATFORM_DRIVER_END(drv_name) \ + +#define IRQCHIP_PLATFORM_DRIVER_END(drv_name, ...) \ {}, \ }; \ MODULE_DEVICE_TABLE(of, drv_name##_irqchip_match_table); \ @@ -56,6 +57,7 @@ static struct platform_driver drv_name##_driver = { \ .owner = THIS_MODULE, \ .of_match_table = drv_name##_irqchip_match_table, \ .suppress_bind_attrs = true, \ + __VA_ARGS__ \ }, \ }; \ builtin_platform_driver(drv_name##_driver) -- cgit v1.2.3 From f3304ecd7f060db1d4197fbdce5a503259f770d3 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Fri, 16 Sep 2022 15:29:53 +0900 Subject: linux/export: use inline assembler to populate symbol CRCs Since commit 7b4537199a4a ("kbuild: link symbol CRCs at final link, removing CONFIG_MODULE_REL_CRCS"), the module versioning on the (non-upstreamed-yet) kvx Linux port is broken due to unexpected padding for __crc_* symbols. The kvx GCC adds padding so u32 gets 8-byte alignment instead of 4. I do not know if this happens for upstream architectures in general, but any compiler has the freedom to insert padding for faster access. Use the inline assembler to directly specify the wanted data layout. This is how we previously did before the breakage. Link: https://lore.kernel.org/lkml/20220817161438.32039-1-ysionneau@kalray.eu/ Link: https://lore.kernel.org/linux-kbuild/31ce5305-a76b-13d7-ea55-afca82c46cf2@kalray.eu/ Fixes: 7b4537199a4a ("kbuild: link symbol CRCs at final link, removing CONFIG_MODULE_REL_CRCS") Reported-by: Yann Sionneau Signed-off-by: Masahiro Yamada Tested-by: Yann Sionneau --- include/linux/export-internal.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/export-internal.h b/include/linux/export-internal.h index c2b1d4fd5987..fe7e6ba918f1 100644 --- a/include/linux/export-internal.h +++ b/include/linux/export-internal.h @@ -10,8 +10,10 @@ #include #include -/* __used is needed to keep __crc_* for LTO */ #define SYMBOL_CRC(sym, crc, sec) \ - u32 __section("___kcrctab" sec "+" #sym) __used __crc_##sym = crc + asm(".section \"___kcrctab" sec "+" #sym "\",\"a\"" "\n" \ + "__crc_" #sym ":" "\n" \ + ".long " #crc "\n" \ + ".previous" "\n") #endif /* __LINUX_EXPORT_INTERNAL_H__ */ -- cgit v1.2.3 From 7e9fbbb1b776d8d7969551565bc246f74ec53b27 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Wed, 28 Sep 2022 13:39:38 -0400 Subject: ring-buffer: Add ring_buffer_wake_waiters() On closing of a file that represents a ring buffer or flushing the file, there may be waiters on the ring buffer that needs to be woken up and exit the ring_buffer_wait() function. Add ring_buffer_wake_waiters() to wake up the waiters on the ring buffer and allow them to exit the wait loop. Link: https://lkml.kernel.org/r/20220928133938.28dc2c27@gandalf.local.home Cc: stable@vger.kernel.org Cc: Ingo Molnar Cc: Andrew Morton Fixes: 15693458c4bc0 ("tracing/ring-buffer: Move poll wake ups into ring buffer code") Signed-off-by: Steven Rostedt (Google) --- include/linux/ring_buffer.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index dac53fd3afea..2504df9a0453 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -101,7 +101,7 @@ __ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *k int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full); __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu, struct file *filp, poll_table *poll_table); - +void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu); #define RING_BUFFER_ALL_CPUS -1 -- cgit v1.2.3 From f3ddb74ad0790030c9592229fb14d8c451f4e9a8 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Tue, 27 Sep 2022 19:15:27 -0400 Subject: tracing: Wake up ring buffer waiters on closing of the file When the file that represents the ring buffer is closed, there may be waiters waiting on more input from the ring buffer. Call ring_buffer_wake_waiters() to wake up any waiters when the file is closed. Link: https://lkml.kernel.org/r/20220927231825.182416969@goodmis.org Cc: stable@vger.kernel.org Cc: Ingo Molnar Cc: Andrew Morton Fixes: e30f53aad2202 ("tracing: Do not busy wait in buffer splice") Signed-off-by: Steven Rostedt (Google) --- include/linux/trace_events.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 8401dec93c15..20749bd9db71 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -92,6 +92,7 @@ struct trace_iterator { unsigned int temp_size; char *fmt; /* modified format holder */ unsigned int fmt_size; + long wait_index; /* trace_seq for __print_flags() and __print_symbolic() etc. */ struct trace_seq tmp_seq; -- cgit v1.2.3 From 39d6d08b2edf99c4b39a689a70bf0adee065b357 Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Thu, 28 Jul 2022 16:33:08 -0700 Subject: tracing/user_events: Use bits vs bytes for enabled status page data User processes may require many events and when they do the cache performance of a byte index status check is less ideal than a bit index. The previous event limit per-page was 4096, the new limit is 32,768. This change adds a bitwise index to the user_reg struct. Programs check that the bit at status_bit has a bit set within the status page(s). Link: https://lkml.kernel.org/r/20220728233309.1896-6-beaub@linux.microsoft.com Link: https://lore.kernel.org/all/2059213643.196683.1648499088753.JavaMail.zimbra@efficios.com/ Suggested-by: Mathieu Desnoyers Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- include/linux/user_events.h | 15 +++------------ 1 file changed, 3 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/user_events.h b/include/linux/user_events.h index 736e05603463..592a3fbed98e 100644 --- a/include/linux/user_events.h +++ b/include/linux/user_events.h @@ -20,15 +20,6 @@ #define USER_EVENTS_SYSTEM "user_events" #define USER_EVENTS_PREFIX "u:" -/* Bits 0-6 are for known probe types, Bit 7 is for unknown probes */ -#define EVENT_BIT_FTRACE 0 -#define EVENT_BIT_PERF 1 -#define EVENT_BIT_OTHER 7 - -#define EVENT_STATUS_FTRACE (1 << EVENT_BIT_FTRACE) -#define EVENT_STATUS_PERF (1 << EVENT_BIT_PERF) -#define EVENT_STATUS_OTHER (1 << EVENT_BIT_OTHER) - /* Create dynamic location entry within a 32-bit value */ #define DYN_LOC(offset, size) ((size) << 16 | (offset)) @@ -45,12 +36,12 @@ struct user_reg { /* Input: Pointer to string with event name, description and flags */ __u64 name_args; - /* Output: Byte index of the event within the status page */ - __u32 status_index; + /* Output: Bitwise index of the event within the status page */ + __u32 status_bit; /* Output: Index of the event to use when writing data */ __u32 write_index; -}; +} __attribute__((__packed__)); #define DIAG_IOC_MAGIC '*' -- cgit v1.2.3 From 88269151be679b9accb2f1e73487eaeb9eae9e39 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Thu, 29 Sep 2022 17:32:49 -0700 Subject: of: base: make of_device_compatible_match() accept const device node of_device_is_compatible() accepts const device node pointer, there is no reason why of_device_compatible_match() can't do the same. Signed-off-by: Dmitry Torokhov Link: https://lore.kernel.org/r/YzY5MaU5N4A2st5R@google.com Signed-off-by: Rob Herring --- include/linux/of.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index 766d002bddb9..6b79ef9a6541 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -342,7 +342,7 @@ extern int of_property_read_string_helper(const struct device_node *np, const char **out_strs, size_t sz, int index); extern int of_device_is_compatible(const struct device_node *device, const char *); -extern int of_device_compatible_match(struct device_node *device, +extern int of_device_compatible_match(const struct device_node *device, const char *const *compat); extern bool of_device_is_available(const struct device_node *device); extern bool of_device_is_big_endian(const struct device_node *device); @@ -562,7 +562,7 @@ static inline int of_device_is_compatible(const struct device_node *device, return 0; } -static inline int of_device_compatible_match(struct device_node *device, +static inline int of_device_compatible_match(const struct device_node *device, const char *const *compat) { return 0; -- cgit v1.2.3 From 854701ba4c39afae2362ba19a580c461cb183e4f Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Mon, 19 Sep 2022 14:05:54 -0700 Subject: net: fix cpu_max_bits_warn() usage in netif_attrmask_next{,_and} The functions require to be passed with a cpu index prior to one that is the first to start search, so the valid input range is [-1, nr_cpu_ids-1). However, the code checks against [-1, nr_cpu_ids). Acked-by: Jakub Kicinski Signed-off-by: Yury Norov --- include/linux/netdevice.h | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 05d6f3facd5a..4d6d5a2dd82e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3643,9 +3643,8 @@ static inline bool netif_attr_test_online(unsigned long j, static inline unsigned int netif_attrmask_next(int n, const unsigned long *srcp, unsigned int nr_bits) { - /* -1 is a legal arg here. */ - if (n != -1) - cpu_max_bits_warn(n, nr_bits); + /* n is a prior cpu */ + cpu_max_bits_warn(n + 1, nr_bits); if (srcp) return find_next_bit(srcp, nr_bits, n + 1); @@ -3666,9 +3665,8 @@ static inline int netif_attrmask_next_and(int n, const unsigned long *src1p, const unsigned long *src2p, unsigned int nr_bits) { - /* -1 is a legal arg here. */ - if (n != -1) - cpu_max_bits_warn(n, nr_bits); + /* n is a prior cpu */ + cpu_max_bits_warn(n + 1, nr_bits); if (src1p && src2p) return find_next_and_bit(src1p, src2p, nr_bits, n + 1); -- cgit v1.2.3 From 33e67710beda78aed38a2fe10be6088d4aeb1c53 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Mon, 19 Sep 2022 14:05:55 -0700 Subject: cpumask: switch for_each_cpu{,_not} to use for_each_bit() The difference between for_each_cpu() and for_each_set_bit() is that the latter uses cpumask_next() instead of find_next_bit(), and so calls cpumask_check(). This check is useless because the iterator value is not provided by user. It generates false-positives for the very last iteration of for_each_cpu(). Signed-off-by: Yury Norov --- include/linux/cpumask.h | 12 +++--------- include/linux/find.h | 5 +++++ 2 files changed, 8 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index e4f9136a4a63..9c85774d45a4 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -246,9 +246,7 @@ unsigned int cpumask_next_and(int n, const struct cpumask *src1p, * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu(cpu, mask) \ - for ((cpu) = -1; \ - (cpu) = cpumask_next((cpu), (mask)), \ - (cpu) < nr_cpu_ids;) + for_each_set_bit(cpu, cpumask_bits(mask), nr_cpumask_bits) /** * for_each_cpu_not - iterate over every cpu in a complemented mask @@ -258,9 +256,7 @@ unsigned int cpumask_next_and(int n, const struct cpumask *src1p, * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_not(cpu, mask) \ - for ((cpu) = -1; \ - (cpu) = cpumask_next_zero((cpu), (mask)), \ - (cpu) < nr_cpu_ids;) + for_each_clear_bit(cpu, cpumask_bits(mask), nr_cpumask_bits) #if NR_CPUS == 1 static inline @@ -313,9 +309,7 @@ unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int sta * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_and(cpu, mask1, mask2) \ - for ((cpu) = -1; \ - (cpu) = cpumask_next_and((cpu), (mask1), (mask2)), \ - (cpu) < nr_cpu_ids;) + for_each_and_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), nr_cpumask_bits) /** * cpumask_any_but - return a "random" in a cpumask, but not this one. diff --git a/include/linux/find.h b/include/linux/find.h index b100944daba0..128615a3f93e 100644 --- a/include/linux/find.h +++ b/include/linux/find.h @@ -390,6 +390,11 @@ unsigned long find_next_bit_le(const void *addr, unsigned (bit) < (size); \ (bit) = find_next_bit((addr), (size), (bit) + 1)) +#define for_each_and_bit(bit, addr1, addr2, size) \ + for ((bit) = find_next_and_bit((addr1), (addr2), (size), 0); \ + (bit) < (size); \ + (bit) = find_next_and_bit((addr1), (addr2), (size), (bit) + 1)) + /* same as for_each_set_bit() but use bit as value to start with */ #define for_each_set_bit_from(bit, addr, size) \ for ((bit) = find_next_bit((addr), (size), (bit)); \ -- cgit v1.2.3 From 6cc18331a987c4a29d66b9c4fd292587fba4d7bd Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Mon, 19 Sep 2022 14:05:56 -0700 Subject: lib/find_bit: add find_next{,_and}_bit_wrap The helper is better optimized for the worst case: in case of empty cpumask, current code traverses 2 * size: next = cpumask_next_and(prev, src1p, src2p); if (next >= nr_cpu_ids) next = cpumask_first_and(src1p, src2p); At bitmap level we can stop earlier after checking 'size + offset' bits. Signed-off-by: Yury Norov --- include/linux/find.h | 46 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 46 insertions(+) (limited to 'include/linux') diff --git a/include/linux/find.h b/include/linux/find.h index 128615a3f93e..77c087b7a451 100644 --- a/include/linux/find.h +++ b/include/linux/find.h @@ -290,6 +290,52 @@ unsigned long find_last_bit(const unsigned long *addr, unsigned long size) } #endif +/** + * find_next_and_bit_wrap - find the next set bit in both memory regions + * @addr1: The first address to base the search on + * @addr2: The second address to base the search on + * @size: The bitmap size in bits + * @offset: The bitnumber to start searching at + * + * Returns the bit number for the next set bit, or first set bit up to @offset + * If no bits are set, returns @size. + */ +static inline +unsigned long find_next_and_bit_wrap(const unsigned long *addr1, + const unsigned long *addr2, + unsigned long size, unsigned long offset) +{ + unsigned long bit = find_next_and_bit(addr1, addr2, size, offset); + + if (bit < size) + return bit; + + bit = find_first_and_bit(addr1, addr2, offset); + return bit < offset ? bit : size; +} + +/** + * find_next_bit_wrap - find the next set bit in both memory regions + * @addr: The first address to base the search on + * @size: The bitmap size in bits + * @offset: The bitnumber to start searching at + * + * Returns the bit number for the next set bit, or first set bit up to @offset + * If no bits are set, returns @size. + */ +static inline +unsigned long find_next_bit_wrap(const unsigned long *addr, + unsigned long size, unsigned long offset) +{ + unsigned long bit = find_next_bit(addr, size, offset); + + if (bit < size) + return bit; + + bit = find_first_bit(addr, offset); + return bit < offset ? bit : size; +} + /** * find_next_clump8 - find next 8-bit clump with set bits in a memory region * @clump: location to store copy of found clump -- cgit v1.2.3 From 4fe49b3b97c2640147c46519c2a6fdb06df34f5f Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Mon, 19 Sep 2022 14:05:57 -0700 Subject: lib/bitmap: introduce for_each_set_bit_wrap() macro Add for_each_set_bit_wrap() macro and use it in for_each_cpu_wrap(). The new macro is based on __for_each_wrap() iterator, which is simpler and smaller than cpumask_next_wrap(). Signed-off-by: Yury Norov --- include/linux/cpumask.h | 6 ++---- include/linux/find.h | 39 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 41 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 9c85774d45a4..13b32dd9803b 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -289,10 +289,8 @@ unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int sta * * After the loop, cpu is >= nr_cpu_ids. */ -#define for_each_cpu_wrap(cpu, mask, start) \ - for ((cpu) = cpumask_next_wrap((start)-1, (mask), (start), false); \ - (cpu) < nr_cpumask_bits; \ - (cpu) = cpumask_next_wrap((cpu), (mask), (start), true)) +#define for_each_cpu_wrap(cpu, mask, start) \ + for_each_set_bit_wrap(cpu, cpumask_bits(mask), nr_cpumask_bits, start) /** * for_each_cpu_and - iterate over every cpu in both masks diff --git a/include/linux/find.h b/include/linux/find.h index 77c087b7a451..3b746a183216 100644 --- a/include/linux/find.h +++ b/include/linux/find.h @@ -336,6 +336,32 @@ unsigned long find_next_bit_wrap(const unsigned long *addr, return bit < offset ? bit : size; } +/* + * Helper for for_each_set_bit_wrap(). Make sure you're doing right thing + * before using it alone. + */ +static inline +unsigned long __for_each_wrap(const unsigned long *bitmap, unsigned long size, + unsigned long start, unsigned long n) +{ + unsigned long bit; + + /* If not wrapped around */ + if (n > start) { + /* and have a bit, just return it. */ + bit = find_next_bit(bitmap, size, n); + if (bit < size) + return bit; + + /* Otherwise, wrap around and ... */ + n = 0; + } + + /* Search the other part. */ + bit = find_next_bit(bitmap, start, n); + return bit < start ? bit : size; +} + /** * find_next_clump8 - find next 8-bit clump with set bits in a memory region * @clump: location to store copy of found clump @@ -514,6 +540,19 @@ unsigned long find_next_bit_le(const void *addr, unsigned (b) = find_next_zero_bit((addr), (size), (e) + 1), \ (e) = find_next_bit((addr), (size), (b) + 1)) +/** + * for_each_set_bit_wrap - iterate over all set bits starting from @start, and + * wrapping around the end of bitmap. + * @bit: offset for current iteration + * @addr: bitmap address to base the search on + * @size: bitmap size in number of bits + * @start: Starting bit for bitmap traversing, wrapping around the bitmap end + */ +#define for_each_set_bit_wrap(bit, addr, size, start) \ + for ((bit) = find_next_bit_wrap((addr), (size), (start)); \ + (bit) < (size); \ + (bit) = __for_each_wrap((addr), (size), (start), (bit) + 1)) + /** * for_each_set_clump8 - iterate over bitmap for each 8-bit clump with set bits * @start: bit offset to start search and to store the current iteration offset -- cgit v1.2.3 From fdae96a3fc7f70eb8ff9619550d7fa604719626a Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Mon, 19 Sep 2022 14:05:58 -0700 Subject: lib/find: optimize for_each() macros Moving an iterator of the macros inside conditional part of for-loop helps to generate a better code. It had been first implemented in commit 7baac8b91f9871ba ("cpumask: make for_each_cpu_mask a bit smaller"). Now that cpumask for-loops are the aliases to bitmap loops, it's worth to optimize them the same way. Bloat-o-meter says: add/remove: 8/12 grow/shrink: 147/592 up/down: 4876/-24416 (-19540) Signed-off-by: Yury Norov --- include/linux/find.h | 56 +++++++++++++++++++++++----------------------------- 1 file changed, 25 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/find.h b/include/linux/find.h index 3b746a183216..0cdfab9734a6 100644 --- a/include/linux/find.h +++ b/include/linux/find.h @@ -458,31 +458,25 @@ unsigned long find_next_bit_le(const void *addr, unsigned #endif #define for_each_set_bit(bit, addr, size) \ - for ((bit) = find_next_bit((addr), (size), 0); \ - (bit) < (size); \ - (bit) = find_next_bit((addr), (size), (bit) + 1)) + for ((bit) = 0; (bit) = find_next_bit((addr), (size), (bit)), (bit) < (size); (bit)++) #define for_each_and_bit(bit, addr1, addr2, size) \ - for ((bit) = find_next_and_bit((addr1), (addr2), (size), 0); \ - (bit) < (size); \ - (bit) = find_next_and_bit((addr1), (addr2), (size), (bit) + 1)) + for ((bit) = 0; \ + (bit) = find_next_and_bit((addr1), (addr2), (size), (bit)), (bit) < (size);\ + (bit)++) /* same as for_each_set_bit() but use bit as value to start with */ #define for_each_set_bit_from(bit, addr, size) \ - for ((bit) = find_next_bit((addr), (size), (bit)); \ - (bit) < (size); \ - (bit) = find_next_bit((addr), (size), (bit) + 1)) + for (; (bit) = find_next_bit((addr), (size), (bit)), (bit) < (size); (bit)++) #define for_each_clear_bit(bit, addr, size) \ - for ((bit) = find_next_zero_bit((addr), (size), 0); \ - (bit) < (size); \ - (bit) = find_next_zero_bit((addr), (size), (bit) + 1)) + for ((bit) = 0; \ + (bit) = find_next_zero_bit((addr), (size), (bit)), (bit) < (size); \ + (bit)++) /* same as for_each_clear_bit() but use bit as value to start with */ #define for_each_clear_bit_from(bit, addr, size) \ - for ((bit) = find_next_zero_bit((addr), (size), (bit)); \ - (bit) < (size); \ - (bit) = find_next_zero_bit((addr), (size), (bit) + 1)) + for (; (bit) = find_next_zero_bit((addr), (size), (bit)), (bit) < (size); (bit)++) /** * for_each_set_bitrange - iterate over all set bit ranges [b; e) @@ -492,11 +486,11 @@ unsigned long find_next_bit_le(const void *addr, unsigned * @size: bitmap size in number of bits */ #define for_each_set_bitrange(b, e, addr, size) \ - for ((b) = find_next_bit((addr), (size), 0), \ - (e) = find_next_zero_bit((addr), (size), (b) + 1); \ + for ((b) = 0; \ + (b) = find_next_bit((addr), (size), b), \ + (e) = find_next_zero_bit((addr), (size), (b) + 1), \ (b) < (size); \ - (b) = find_next_bit((addr), (size), (e) + 1), \ - (e) = find_next_zero_bit((addr), (size), (b) + 1)) + (b) = (e) + 1) /** * for_each_set_bitrange_from - iterate over all set bit ranges [b; e) @@ -506,11 +500,11 @@ unsigned long find_next_bit_le(const void *addr, unsigned * @size: bitmap size in number of bits */ #define for_each_set_bitrange_from(b, e, addr, size) \ - for ((b) = find_next_bit((addr), (size), (b)), \ - (e) = find_next_zero_bit((addr), (size), (b) + 1); \ + for (; \ + (b) = find_next_bit((addr), (size), (b)), \ + (e) = find_next_zero_bit((addr), (size), (b) + 1), \ (b) < (size); \ - (b) = find_next_bit((addr), (size), (e) + 1), \ - (e) = find_next_zero_bit((addr), (size), (b) + 1)) + (b) = (e) + 1) /** * for_each_clear_bitrange - iterate over all unset bit ranges [b; e) @@ -520,11 +514,11 @@ unsigned long find_next_bit_le(const void *addr, unsigned * @size: bitmap size in number of bits */ #define for_each_clear_bitrange(b, e, addr, size) \ - for ((b) = find_next_zero_bit((addr), (size), 0), \ - (e) = find_next_bit((addr), (size), (b) + 1); \ + for ((b) = 0; \ + (b) = find_next_zero_bit((addr), (size), (b)), \ + (e) = find_next_bit((addr), (size), (b) + 1), \ (b) < (size); \ - (b) = find_next_zero_bit((addr), (size), (e) + 1), \ - (e) = find_next_bit((addr), (size), (b) + 1)) + (b) = (e) + 1) /** * for_each_clear_bitrange_from - iterate over all unset bit ranges [b; e) @@ -534,11 +528,11 @@ unsigned long find_next_bit_le(const void *addr, unsigned * @size: bitmap size in number of bits */ #define for_each_clear_bitrange_from(b, e, addr, size) \ - for ((b) = find_next_zero_bit((addr), (size), (b)), \ - (e) = find_next_bit((addr), (size), (b) + 1); \ + for (; \ + (b) = find_next_zero_bit((addr), (size), (b)), \ + (e) = find_next_bit((addr), (size), (b) + 1), \ (b) < (size); \ - (b) = find_next_zero_bit((addr), (size), (e) + 1), \ - (e) = find_next_bit((addr), (size), (b) + 1)) + (b) = (e) + 1) /** * for_each_set_bit_wrap - iterate over all set bits starting from @start, and -- cgit v1.2.3 From 78e5a3399421ad79fc024e6d78e2deb7809d26af Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Mon, 19 Sep 2022 14:05:53 -0700 Subject: cpumask: fix checking valid cpu range The range of valid CPUs is [0, nr_cpu_ids). Some cpumask functions are passed with a shifted CPU index, and for them, the valid range is [-1, nr_cpu_ids-1). Currently for those functions, we check the index against [-1, nr_cpu_ids), which is wrong. Signed-off-by: Yury Norov --- include/linux/cpumask.h | 19 ++++++++----------- 1 file changed, 8 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 13b32dd9803b..286804bfe3b7 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -174,9 +174,8 @@ static inline unsigned int cpumask_last(const struct cpumask *srcp) static inline unsigned int cpumask_next(int n, const struct cpumask *srcp) { - /* -1 is a legal arg here. */ - if (n != -1) - cpumask_check(n); + /* n is a prior cpu */ + cpumask_check(n + 1); return find_next_bit(cpumask_bits(srcp), nr_cpumask_bits, n + 1); } @@ -189,9 +188,8 @@ unsigned int cpumask_next(int n, const struct cpumask *srcp) */ static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) { - /* -1 is a legal arg here. */ - if (n != -1) - cpumask_check(n); + /* n is a prior cpu */ + cpumask_check(n + 1); return find_next_zero_bit(cpumask_bits(srcp), nr_cpumask_bits, n+1); } @@ -231,9 +229,8 @@ static inline unsigned int cpumask_next_and(int n, const struct cpumask *src1p, const struct cpumask *src2p) { - /* -1 is a legal arg here. */ - if (n != -1) - cpumask_check(n); + /* n is a prior cpu */ + cpumask_check(n + 1); return find_next_and_bit(cpumask_bits(src1p), cpumask_bits(src2p), nr_cpumask_bits, n + 1); } @@ -263,8 +260,8 @@ static inline unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap) { cpumask_check(start); - if (n != -1) - cpumask_check(n); + /* n is a prior cpu */ + cpumask_check(n + 1); /* * Return the first available CPU when wrapping, or when starting before cpu0, -- cgit v1.2.3 From 79e1119b7e0099c6c9379ca3129ffb7aa2a1c249 Mon Sep 17 00:00:00 2001 From: Qi Zheng Date: Wed, 31 Aug 2022 11:19:47 +0800 Subject: ksm: remove redundant declarations in ksm.h Currently, for struct stable_node, no one uses it in both the include/linux/ksm.h file and the file that contains it. For struct mem_cgroup, it's also not used in ksm.h. So they're all redundant, just remove them. Link: https://lkml.kernel.org/r/20220831031951.43152-4-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng Cc: Johannes Weiner Cc: Matthew Wilcox Cc: Mike Rapoport Cc: Minchan Kim Cc: Vlastimil Babka Cc: Yang Shi Signed-off-by: Andrew Morton --- include/linux/ksm.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 0b4f17418f64..7e232ba59b86 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -15,9 +15,6 @@ #include #include -struct stable_node; -struct mem_cgroup; - #ifdef CONFIG_KSM int ksm_madvise(struct vm_area_struct *vma, unsigned long start, unsigned long end, int advice, unsigned long *vm_flags); -- cgit v1.2.3 From 379708ffde1b049bc41084e0a0572c44c8a1d2c4 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 2 Sep 2022 20:45:58 +0100 Subject: mm: add the first tail page to struct folio Some of the static checkers get confused by extracting the page from the folio and referring to fields in the first tail page. Adding these fields to struct folio lets us avoid doing that. It has the risk that people will refer to those fields without checking that the folio is actually a large folio, so prefix them with underscores and document the preferred function to use instead. Link: https://lkml.kernel.org/r/20220902194653.1739778-3-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/mm_types.h | 30 +++++++++++++++++++++++++++++- 1 file changed, 29 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 8f30f262431c..5c87d0f292a2 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -245,6 +245,13 @@ struct page { * @_refcount: Do not access this member directly. Use folio_ref_count() * to find how many references there are to this folio. * @memcg_data: Memory Control Group data. + * @_flags_1: For large folios, additional page flags. + * @__head: Points to the folio. Do not use. + * @_folio_dtor: Which destructor to use for this folio. + * @_folio_order: Do not use directly, call folio_order(). + * @_total_mapcount: Do not use directly, call folio_entire_mapcount(). + * @_pincount: Do not use directly, call folio_maybe_dma_pinned(). + * @_folio_nr_pages: Do not use directly, call folio_nr_pages(). * * A folio is a physically, virtually and logically contiguous set * of bytes. It is a power-of-two in size, and it is aligned to that @@ -283,9 +290,17 @@ struct folio { }; struct page page; }; + unsigned long _flags_1; + unsigned long __head; + unsigned char _folio_dtor; + unsigned char _folio_order; + atomic_t _total_mapcount; + atomic_t _pincount; +#ifdef CONFIG_64BIT + unsigned int _folio_nr_pages; +#endif }; -static_assert(sizeof(struct page) == sizeof(struct folio)); #define FOLIO_MATCH(pg, fl) \ static_assert(offsetof(struct page, pg) == offsetof(struct folio, fl)) FOLIO_MATCH(flags, flags); @@ -300,6 +315,19 @@ FOLIO_MATCH(_refcount, _refcount); FOLIO_MATCH(memcg_data, memcg_data); #endif #undef FOLIO_MATCH +#define FOLIO_MATCH(pg, fl) \ + static_assert(offsetof(struct folio, fl) == \ + offsetof(struct page, pg) + sizeof(struct page)) +FOLIO_MATCH(flags, _flags_1); +FOLIO_MATCH(compound_head, __head); +FOLIO_MATCH(compound_dtor, _folio_dtor); +FOLIO_MATCH(compound_order, _folio_order); +FOLIO_MATCH(compound_mapcount, _total_mapcount); +FOLIO_MATCH(compound_pincount, _pincount); +#ifdef CONFIG_64BIT +FOLIO_MATCH(compound_nr, _folio_nr_pages); +#endif +#undef FOLIO_MATCH static inline atomic_t *folio_mapcount_ptr(struct folio *folio) { -- cgit v1.2.3 From c3a15bff46cb5149aeae4c8ae69443d791fa6578 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 2 Sep 2022 20:45:59 +0100 Subject: mm: reimplement folio_order() and folio_nr_pages() Instead of calling compound_order() and compound_nr_pages(), use the folio directly. Saves 1905 bytes from mm/filemap.o due to folio_test_large() now being a cheaper check than PageHead(). Link: https://lkml.kernel.org/r/20220902194653.1739778-4-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/mm.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index e56dd8f7eae1..a37c8a29c49b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -729,7 +729,9 @@ static inline unsigned int compound_order(struct page *page) */ static inline unsigned int folio_order(struct folio *folio) { - return compound_order(&folio->page); + if (!folio_test_large(folio)) + return 0; + return folio->_folio_order; } #include @@ -1659,7 +1661,13 @@ static inline void set_page_links(struct page *page, enum zone_type zone, */ static inline long folio_nr_pages(struct folio *folio) { - return compound_nr(&folio->page); + if (!folio_test_large(folio)) + return 1; +#ifdef CONFIG_64BIT + return folio->_folio_nr_pages; +#else + return 1L << folio->_folio_order; +#endif } /** -- cgit v1.2.3 From d788f5b374c2ba204fed57e39acf2452acc24812 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 2 Sep 2022 20:46:00 +0100 Subject: mm: add split_folio() This wrapper removes a need to use split_huge_page(&folio->page). Convert two callers. Link: https://lkml.kernel.org/r/20220902194653.1739778-5-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/huge_mm.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 38265f9f782e..a1341fdcf666 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -444,6 +444,11 @@ static inline int split_folio_to_list(struct folio *folio, return split_huge_page_to_list(&folio->page, list); } +static inline int split_folio(struct folio *folio) +{ + return split_folio_to_list(folio, NULL); +} + /* * archs that select ARCH_WANTS_THP_SWAP but don't support THP_SWP due to * limitations in the implementation like arm64 MTE can override this to -- cgit v1.2.3 From 681ecf6301786cb06942b57f0ef7103b07ae6813 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 2 Sep 2022 20:46:01 +0100 Subject: mm: add folio_add_lru_vma() Convert lru_cache_add_inactive_or_unevictable() to folio_add_lru_vma() and add a compatibility wrapper. Link: https://lkml.kernel.org/r/20220902194653.1739778-6-willy@infradead.org Signed-off-by: "Matthew Wilcox (Oracle)" Signed-off-by: Andrew Morton --- include/linux/swap.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 6308150b234a..2ede1e3695d9 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -379,11 +379,11 @@ extern unsigned long totalreserve_pages; /* linux/mm/swap.c */ -extern void lru_note_cost(struct lruvec *lruvec, bool file, - unsigned int nr_pages); -extern void lru_note_cost_folio(struct folio *); -extern void folio_add_lru(struct folio *); -extern void lru_cache_add(struct page *); +void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages); +void lru_note_cost_folio(struct folio *); +void folio_add_lru(struct folio *); +void folio_add_lru_vma(struct folio *, struct vm_area_struct *); +void lru_cache_add(struct page *); void mark_page_accessed(struct page *); void folio_mark_accessed(struct folio *); -- cgit v1.2.3 From 907ea17eb2b436f07332c935476d77893abae735 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 2 Sep 2022 20:46:04 +0100 Subject: shmem: convert shmem_replace_page() to use folios throughout Introduce folio_set_swap_entry() to abstract how both folio->private and swp_entry_t work. Use swap_address_space() directly instead of indirecting through folio_mapping(). Include an assertion that the old folio is not large as we only allocate a single-page folio to replace it. Use folio_put_refs() instead of calling folio_put() twice. Link: https://lkml.kernel.org/r/20220902194653.1739778-9-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/swap.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 2ede1e3695d9..61e13d1a4cab 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -355,6 +355,11 @@ static inline swp_entry_t folio_swap_entry(struct folio *folio) return entry; } +static inline void folio_set_swap_entry(struct folio *folio, swp_entry_t entry) +{ + folio->private = (void *)entry.val; +} + /* linux/mm/workingset.c */ void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages); void *workingset_eviction(struct folio *folio, struct mem_cgroup *target_memcg); -- cgit v1.2.3 From bdb0ed54a4768dc3c2613d4c45f94c887d43cd7a Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 2 Sep 2022 20:46:06 +0100 Subject: mm/swapfile: convert try_to_free_swap() to folio_free_swap() Add kernel-doc for folio_free_swap() and make it return bool. Add a try_to_free_swap() compatibility wrapper. Link: https://lkml.kernel.org/r/20220902194653.1739778-11-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/swap.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 61e13d1a4cab..dac6308d878e 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -490,6 +490,7 @@ static inline long get_nr_swap_pages(void) extern void si_swapinfo(struct sysinfo *); swp_entry_t folio_alloc_swap(struct folio *folio); +bool folio_free_swap(struct folio *folio); extern void put_swap_page(struct page *page, swp_entry_t entry); extern swp_entry_t get_swap_page_of_type(int); extern int get_swap_pages(int n, swp_entry_t swp_entries[], int entry_size); @@ -606,6 +607,11 @@ static inline swp_entry_t folio_alloc_swap(struct folio *folio) return entry; } +static inline bool folio_free_swap(struct folio *folio) +{ + return false; +} + static inline int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block) -- cgit v1.2.3 From 4081f7446d95a9d3ced12dc04ff02c187a761e90 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 2 Sep 2022 20:46:09 +0100 Subject: mm/swap: convert put_swap_page() to put_swap_folio() With all callers now using a folio, we can convert this function. Link: https://lkml.kernel.org/r/20220902194653.1739778-14-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/swap.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index dac6308d878e..42cbef554de6 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -491,7 +491,7 @@ static inline long get_nr_swap_pages(void) extern void si_swapinfo(struct sysinfo *); swp_entry_t folio_alloc_swap(struct folio *folio); bool folio_free_swap(struct folio *folio); -extern void put_swap_page(struct page *page, swp_entry_t entry); +void put_swap_folio(struct folio *folio, swp_entry_t entry); extern swp_entry_t get_swap_page_of_type(int); extern int get_swap_pages(int n, swp_entry_t swp_entries[], int entry_size); extern int add_swap_count_continuation(swp_entry_t, gfp_t); @@ -576,7 +576,7 @@ static inline void swap_free(swp_entry_t swp) { } -static inline void put_swap_page(struct page *page, swp_entry_t swp) +static inline void put_swap_folio(struct folio *folio, swp_entry_t swp) { } -- cgit v1.2.3 From 6599591816f522c1cc8ec4eb5cea75738963756a Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 2 Sep 2022 20:46:12 +0100 Subject: memcg: convert mem_cgroup_swapin_charge_page() to mem_cgroup_swapin_charge_folio() All callers now have a folio, so pass it in here and remove an unnecessary call to page_folio(). Link: https://lkml.kernel.org/r/20220902194653.1739778-17-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/memcontrol.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 60545e4a1c03..ca0df42662ad 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -688,7 +688,7 @@ static inline int mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, return __mem_cgroup_charge(folio, mm, gfp); } -int mem_cgroup_swapin_charge_page(struct page *page, struct mm_struct *mm, +int mem_cgroup_swapin_charge_folio(struct folio *folio, struct mm_struct *mm, gfp_t gfp, swp_entry_t entry); void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry); @@ -1254,7 +1254,7 @@ static inline int mem_cgroup_charge(struct folio *folio, return 0; } -static inline int mem_cgroup_swapin_charge_page(struct page *page, +static inline int mem_cgroup_swapin_charge_folio(struct folio *folio, struct mm_struct *mm, gfp_t gfp, swp_entry_t entry) { return 0; -- cgit v1.2.3 From 4e1fc793ad9892cec67b40c9f67583160e08f695 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 2 Sep 2022 20:46:20 +0100 Subject: shmem: add shmem_get_folio() With no remaining callers of shmem_getpage_gfp(), add shmem_get_folio() and reimplement shmem_getpage() as a call to shmem_get_folio(). Link: https://lkml.kernel.org/r/20220902194653.1739778-25-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/shmem_fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index ff0b990de83d..f4bd50b08a91 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -113,6 +113,8 @@ enum sgp_type { extern int shmem_getpage(struct inode *inode, pgoff_t index, struct page **pagep, enum sgp_type sgp); +int shmem_get_folio(struct inode *inode, pgoff_t index, struct folio **foliop, + enum sgp_type sgp); static inline struct page *shmem_read_mapping_page( struct address_space *mapping, pgoff_t index) -- cgit v1.2.3 From 923e2f0e7c30db5c1ee5d680050ab781e6c114fb Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 2 Sep 2022 20:46:29 +0100 Subject: shmem: remove shmem_getpage() With all callers removed, remove this wrapper function. The flags are now mysteriously called SGP, but I think we can live with that. Link: https://lkml.kernel.org/r/20220902194653.1739778-34-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/shmem_fs.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index f4bd50b08a91..f24071e3c826 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -102,7 +102,7 @@ extern unsigned long shmem_swap_usage(struct vm_area_struct *vma); extern unsigned long shmem_partial_swap_usage(struct address_space *mapping, pgoff_t start, pgoff_t end); -/* Flag allocation requirements to shmem_getpage */ +/* Flag allocation requirements to shmem_get_folio */ enum sgp_type { SGP_READ, /* don't exceed i_size, don't allocate page */ SGP_NOALLOC, /* similar, but fail on hole or use fallocated page */ @@ -111,8 +111,6 @@ enum sgp_type { SGP_FALLOC, /* like SGP_WRITE, but make existing page Uptodate */ }; -extern int shmem_getpage(struct inode *inode, pgoff_t index, - struct page **pagep, enum sgp_type sgp); int shmem_get_folio(struct inode *inode, pgoff_t index, struct folio **foliop, enum sgp_type sgp); -- cgit v1.2.3 From 9202d527b715f67bcdccbb9b712b65fe053f8109 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 2 Sep 2022 20:46:43 +0100 Subject: memcg: convert mem_cgroup_swap_full() to take a folio All callers now have a folio, so convert the function to take a folio. Saves a couple of calls to compound_head(). Link: https://lkml.kernel.org/r/20220902194653.1739778-48-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/swap.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 42cbef554de6..d8bd6401c3e7 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -692,7 +692,7 @@ static inline void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_p } extern long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg); -extern bool mem_cgroup_swap_full(struct page *page); +extern bool mem_cgroup_swap_full(struct folio *folio); #else static inline void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry) { @@ -714,7 +714,7 @@ static inline long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg) return get_nr_swap_pages(); } -static inline bool mem_cgroup_swap_full(struct page *page) +static inline bool mem_cgroup_swap_full(struct folio *folio) { return vm_swap_full(); } -- cgit v1.2.3 From 3b344157c0c15b8f9588e3021dfb22ee25f4508a Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 2 Sep 2022 20:46:44 +0100 Subject: mm: remove try_to_free_swap() All callers have now been converted to folio_free_swap() and we can remove this wrapper. Link: https://lkml.kernel.org/r/20220902194653.1739778-49-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/swap.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index d8bd6401c3e7..fc8d98660326 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -510,7 +510,6 @@ extern int __swp_swapcount(swp_entry_t entry); extern int swp_swapcount(swp_entry_t entry); extern struct swap_info_struct *page_swap_info(struct page *); extern struct swap_info_struct *swp_swap_info(swp_entry_t entry); -extern int try_to_free_swap(struct page *); struct backing_dev_info; extern int init_swap_address_space(unsigned int type, unsigned long nr_pages); extern void exit_swap_address_space(unsigned int type); @@ -595,11 +594,6 @@ static inline int swp_swapcount(swp_entry_t entry) return 0; } -static inline int try_to_free_swap(struct page *page) -{ - return 0; -} - static inline swp_entry_t folio_alloc_swap(struct folio *folio) { swp_entry_t entry; -- cgit v1.2.3 From 29eea9b5a9c9ecf21164a082a42bfabe06fdcb30 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 2 Sep 2022 20:46:50 +0100 Subject: mm: convert page_get_anon_vma() to folio_get_anon_vma() With all callers now passing in a folio, rename the function and convert all callers. Removes a couple of calls to compound_head() and a reference to page->mapping. Link: https://lkml.kernel.org/r/20220902194653.1739778-55-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/rmap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 72b2bcc37f73..3d56e3712bb2 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -163,7 +163,7 @@ static inline void anon_vma_merge(struct vm_area_struct *vma, unlink_anon_vmas(next); } -struct anon_vma *page_get_anon_vma(struct page *page); +struct anon_vma *folio_get_anon_vma(struct folio *folio); /* RMAP flags, currently only relevant for some anon rmap operations. */ typedef int __bitwise rmap_t; -- cgit v1.2.3 From 0c826c0b6a176b9ed5ace7106fd1770bb48f1898 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 2 Sep 2022 20:46:51 +0100 Subject: rmap: remove page_unlock_anon_vma_read() This was simply an alias for anon_vma_unlock_read() since 2011. Link: https://lkml.kernel.org/r/20220902194653.1739778-56-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/rmap.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 3d56e3712bb2..ca3e4ba6c58c 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -458,13 +458,8 @@ struct rmap_walk_control { void rmap_walk(struct folio *folio, struct rmap_walk_control *rwc); void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc); - -/* - * Called by memory-failure.c to kill processes. - */ struct anon_vma *folio_lock_anon_vma_read(struct folio *folio, struct rmap_walk_control *rwc); -void page_unlock_anon_vma_read(struct anon_vma *anon_vma); #else /* !CONFIG_MMU */ -- cgit v1.2.3 From 19672a9e4a75252871cba319f4e3b859b8fdf671 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 2 Sep 2022 20:46:53 +0100 Subject: mm: convert lock_page_or_retry() to folio_lock_or_retry() Remove a call to compound_head() in each of the two callers. Link: https://lkml.kernel.org/r/20220902194653.1739778-58-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/pagemap.h | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 09de43e36a64..32846b6306db 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -989,19 +989,16 @@ static inline int lock_page_killable(struct page *page) } /* - * lock_page_or_retry - Lock the page, unless this would block and the + * folio_lock_or_retry - Lock the folio, unless this would block and the * caller indicated that it can handle a retry. * * Return value and mmap_lock implications depend on flags; see * __folio_lock_or_retry(). */ -static inline bool lock_page_or_retry(struct page *page, struct mm_struct *mm, - unsigned int flags) +static inline bool folio_lock_or_retry(struct folio *folio, + struct mm_struct *mm, unsigned int flags) { - struct folio *folio; might_sleep(); - - folio = page_folio(page); return folio_trylock(folio) || __folio_lock_or_retry(folio, mm, flags); } -- cgit v1.2.3 From f372bde922e2ced8e0b5a928887b4cf587cc4453 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Mon, 5 Sep 2022 23:05:29 +0200 Subject: kasan: only define kasan_metadata_size for Generic mode KASAN provides a helper for calculating the size of per-object metadata stored in the redzone. As now only the Generic mode uses per-object metadata, only define kasan_metadata_size() for this mode. Link: https://lkml.kernel.org/r/8f81d4938b80446bc72538a08217009f328a3e23.1662411799.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Reviewed-by: Marco Elver Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Dmitry Vyukov Cc: Evgenii Stepanov Cc: Peter Collingbourne Signed-off-by: Andrew Morton --- include/linux/kasan.h | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index b092277bf48d..027df7599573 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -150,14 +150,6 @@ static __always_inline void kasan_cache_create_kmalloc(struct kmem_cache *cache) __kasan_cache_create_kmalloc(cache); } -size_t __kasan_metadata_size(struct kmem_cache *cache); -static __always_inline size_t kasan_metadata_size(struct kmem_cache *cache) -{ - if (kasan_enabled()) - return __kasan_metadata_size(cache); - return 0; -} - void __kasan_poison_slab(struct slab *slab); static __always_inline void kasan_poison_slab(struct slab *slab) { @@ -282,7 +274,6 @@ static inline void kasan_cache_create(struct kmem_cache *cache, unsigned int *size, slab_flags_t *flags) {} static inline void kasan_cache_create_kmalloc(struct kmem_cache *cache) {} -static inline size_t kasan_metadata_size(struct kmem_cache *cache) { return 0; } static inline void kasan_poison_slab(struct slab *slab) {} static inline void kasan_unpoison_object_data(struct kmem_cache *cache, void *object) {} @@ -333,6 +324,8 @@ static inline void kasan_unpoison_task_stack(struct task_struct *task) {} #ifdef CONFIG_KASAN_GENERIC +size_t kasan_metadata_size(struct kmem_cache *cache); + void kasan_cache_shrink(struct kmem_cache *cache); void kasan_cache_shutdown(struct kmem_cache *cache); void kasan_record_aux_stack(void *ptr); @@ -340,6 +333,12 @@ void kasan_record_aux_stack_noalloc(void *ptr); #else /* CONFIG_KASAN_GENERIC */ +/* Tag-based KASAN modes do not use per-object metadata. */ +static inline size_t kasan_metadata_size(struct kmem_cache *cache) +{ + return 0; +} + static inline void kasan_cache_shrink(struct kmem_cache *cache) {} static inline void kasan_cache_shutdown(struct kmem_cache *cache) {} static inline void kasan_record_aux_stack(void *ptr) {} -- cgit v1.2.3 From 3b7f8813e9ecf7fe91f2f8dc3b581a111cd374a5 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Mon, 5 Sep 2022 23:05:30 +0200 Subject: kasan: only define kasan_never_merge for Generic mode KASAN prevents merging of slab caches whose objects have per-object metadata stored in redzones. As now only the Generic mode uses per-object metadata, define kasan_never_merge() only for this mode. Link: https://lkml.kernel.org/r/81ed01f29ff3443580b7e2fe362a8b47b1e8006d.1662411799.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Reviewed-by: Marco Elver Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Dmitry Vyukov Cc: Evgenii Stepanov Cc: Peter Collingbourne Signed-off-by: Andrew Morton --- include/linux/kasan.h | 18 ++++++------------ 1 file changed, 6 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 027df7599573..9743d4b3a918 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -103,14 +103,6 @@ struct kasan_cache { bool is_kmalloc; }; -slab_flags_t __kasan_never_merge(void); -static __always_inline slab_flags_t kasan_never_merge(void) -{ - if (kasan_enabled()) - return __kasan_never_merge(); - return 0; -} - void __kasan_unpoison_range(const void *addr, size_t size); static __always_inline void kasan_unpoison_range(const void *addr, size_t size) { @@ -261,10 +253,6 @@ static __always_inline bool kasan_check_byte(const void *addr) #else /* CONFIG_KASAN */ -static inline slab_flags_t kasan_never_merge(void) -{ - return 0; -} static inline void kasan_unpoison_range(const void *address, size_t size) {} static inline void kasan_poison_pages(struct page *page, unsigned int order, bool init) {} @@ -325,6 +313,7 @@ static inline void kasan_unpoison_task_stack(struct task_struct *task) {} #ifdef CONFIG_KASAN_GENERIC size_t kasan_metadata_size(struct kmem_cache *cache); +slab_flags_t kasan_never_merge(void); void kasan_cache_shrink(struct kmem_cache *cache); void kasan_cache_shutdown(struct kmem_cache *cache); @@ -338,6 +327,11 @@ static inline size_t kasan_metadata_size(struct kmem_cache *cache) { return 0; } +/* And thus nothing prevents cache merging. */ +static inline slab_flags_t kasan_never_merge(void) +{ + return 0; +} static inline void kasan_cache_shrink(struct kmem_cache *cache) {} static inline void kasan_cache_shutdown(struct kmem_cache *cache) {} -- cgit v1.2.3 From 26f21f3ac76df6cf3b447e8231f8754991165475 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Mon, 5 Sep 2022 23:05:31 +0200 Subject: kasan: only define metadata offsets for Generic mode Hide the definitions of alloc_meta_offset and free_meta_offset under an ifdef CONFIG_KASAN_GENERIC check, as these fields are now only used when the Generic mode is enabled. Link: https://lkml.kernel.org/r/d4bafa0534facafd1a23c465a94261e64f366493.1662411799.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Reviewed-by: Marco Elver Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Dmitry Vyukov Cc: Evgenii Stepanov Cc: Peter Collingbourne Signed-off-by: Andrew Morton --- include/linux/kasan.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 9743d4b3a918..a212c2e3f32d 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -98,8 +98,10 @@ static inline bool kasan_has_integrated_init(void) #ifdef CONFIG_KASAN struct kasan_cache { +#ifdef CONFIG_KASAN_GENERIC int alloc_meta_offset; int free_meta_offset; +#endif bool is_kmalloc; }; -- cgit v1.2.3 From 682ed08924407b719fa0b1123a26971748d76ace Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Mon, 5 Sep 2022 23:05:33 +0200 Subject: kasan: only define kasan_cache_create for Generic mode Right now, kasan_cache_create() assigns SLAB_KASAN for all KASAN modes and then sets up metadata-related cache parameters for the Generic mode. SLAB_KASAN is used in two places: 1. In slab_ksize() to account for per-object metadata when calculating the size of the accessible memory within the object. 2. In slab_common.c via kasan_never_merge() to prevent merging of caches with per-object metadata. Both cases are only relevant when per-object metadata is present, which is only the case with the Generic mode. Thus, assign SLAB_KASAN and define kasan_cache_create() only for the Generic mode. Also update the SLAB_KASAN-related comment. Link: https://lkml.kernel.org/r/61faa2aa1906e2d02c97d00ddf99ce8911dda095.1662411799.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Reviewed-by: Marco Elver Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Dmitry Vyukov Cc: Evgenii Stepanov Cc: Peter Collingbourne Signed-off-by: Andrew Morton --- include/linux/kasan.h | 18 ++++++------------ include/linux/slab.h | 2 +- 2 files changed, 7 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index a212c2e3f32d..d811b3d7d2a1 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -128,15 +128,6 @@ static __always_inline void kasan_unpoison_pages(struct page *page, __kasan_unpoison_pages(page, order, init); } -void __kasan_cache_create(struct kmem_cache *cache, unsigned int *size, - slab_flags_t *flags); -static __always_inline void kasan_cache_create(struct kmem_cache *cache, - unsigned int *size, slab_flags_t *flags) -{ - if (kasan_enabled()) - __kasan_cache_create(cache, size, flags); -} - void __kasan_cache_create_kmalloc(struct kmem_cache *cache); static __always_inline void kasan_cache_create_kmalloc(struct kmem_cache *cache) { @@ -260,9 +251,6 @@ static inline void kasan_poison_pages(struct page *page, unsigned int order, bool init) {} static inline void kasan_unpoison_pages(struct page *page, unsigned int order, bool init) {} -static inline void kasan_cache_create(struct kmem_cache *cache, - unsigned int *size, - slab_flags_t *flags) {} static inline void kasan_cache_create_kmalloc(struct kmem_cache *cache) {} static inline void kasan_poison_slab(struct slab *slab) {} static inline void kasan_unpoison_object_data(struct kmem_cache *cache, @@ -316,6 +304,8 @@ static inline void kasan_unpoison_task_stack(struct task_struct *task) {} size_t kasan_metadata_size(struct kmem_cache *cache); slab_flags_t kasan_never_merge(void); +void kasan_cache_create(struct kmem_cache *cache, unsigned int *size, + slab_flags_t *flags); void kasan_cache_shrink(struct kmem_cache *cache); void kasan_cache_shutdown(struct kmem_cache *cache); @@ -334,6 +324,10 @@ static inline slab_flags_t kasan_never_merge(void) { return 0; } +/* And no cache-related metadata initialization is required. */ +static inline void kasan_cache_create(struct kmem_cache *cache, + unsigned int *size, + slab_flags_t *flags) {} static inline void kasan_cache_shrink(struct kmem_cache *cache) {} static inline void kasan_cache_shutdown(struct kmem_cache *cache) {} diff --git a/include/linux/slab.h b/include/linux/slab.h index 352e3f082acc..617a39f7db46 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -106,7 +106,7 @@ # define SLAB_ACCOUNT 0 #endif -#ifdef CONFIG_KASAN +#ifdef CONFIG_KASAN_GENERIC #define SLAB_KASAN ((slab_flags_t __force)0x08000000U) #else #define SLAB_KASAN 0 -- cgit v1.2.3 From 36001cba4f728e7fa2a58bc69fece22eaeef5cca Mon Sep 17 00:00:00 2001 From: Kaixu Xia Date: Tue, 6 Sep 2022 23:18:47 +0800 Subject: mm/damon/core: iterate the regions list from current point in damon_set_regions() We iterate the whole regions list every time to get the first/last regions intersecting with the specific range in damon_set_regions(), in order to add new region or resize existing regions to fit in the specific range. Actually, it is unnecessary to iterate the new added regions and the front regions that have been checked. Just iterate the regions list from the current point using list_for_each_entry_from() every time to improve performance. The kunit tests passed: [PASSED] damon_test_apply_three_regions1 [PASSED] damon_test_apply_three_regions2 [PASSED] damon_test_apply_three_regions3 [PASSED] damon_test_apply_three_regions4 Link: https://lkml.kernel.org/r/1662477527-13003-1-git-send-email-kaixuxia@tencent.com Signed-off-by: Kaixu Xia Reviewed-by: SeongJae Park Signed-off-by: Andrew Morton --- include/linux/damon.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 7b1f4a488230..d54acec048d6 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -463,9 +463,17 @@ static inline struct damon_region *damon_last_region(struct damon_target *t) return list_last_entry(&t->regions_list, struct damon_region, list); } +static inline struct damon_region *damon_first_region(struct damon_target *t) +{ + return list_first_entry(&t->regions_list, struct damon_region, list); +} + #define damon_for_each_region(r, t) \ list_for_each_entry(r, &t->regions_list, list) +#define damon_for_each_region_from(r, t) \ + list_for_each_entry_from(r, &t->regions_list, list) + #define damon_for_each_region_safe(r, next, t) \ list_for_each_entry_safe(r, next, &t->regions_list, list) -- cgit v1.2.3 From 4f9bc69ac5ce34071a9a51343bc81ca76cb2e3f1 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Wed, 7 Sep 2022 14:08:42 +0800 Subject: mm: reuse pageblock_start/end_pfn() macro Move pageblock_start_pfn/pageblock_end_pfn() into pageblock-flags.h, then they could be used somewhere else, not only in compaction, also use ALIGN_DOWN() instead of round_down() to be pair with ALIGN(), which should be same for pageblock usage. Link: https://lkml.kernel.org/r/20220907060844.126891-1-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Acked-by: Mike Rapoport Reviewed-by: David Hildenbrand Cc: Oscar Salvador Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/pageblock-flags.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h index 83c7248053a1..a09b7fe6bbf8 100644 --- a/include/linux/pageblock-flags.h +++ b/include/linux/pageblock-flags.h @@ -53,6 +53,8 @@ extern unsigned int pageblock_order; #endif /* CONFIG_HUGETLB_PAGE */ #define pageblock_nr_pages (1UL << pageblock_order) +#define pageblock_start_pfn(pfn) ALIGN_DOWN((pfn), pageblock_nr_pages) +#define pageblock_end_pfn(pfn) ALIGN((pfn) + 1, pageblock_nr_pages) /* Forward declaration */ struct page; -- cgit v1.2.3 From 5f7fa13fa858c17580ed513bd5e0a4b36d68fdd6 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Wed, 7 Sep 2022 14:08:43 +0800 Subject: mm: add pageblock_align() macro Add pageblock_align() macro and use it to simplify code. Link: https://lkml.kernel.org/r/20220907060844.126891-2-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Acked-by: Mike Rapoport Reviewed-by: David Hildenbrand Cc: Oscar Salvador Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/pageblock-flags.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h index a09b7fe6bbf8..293c76630fa8 100644 --- a/include/linux/pageblock-flags.h +++ b/include/linux/pageblock-flags.h @@ -53,6 +53,7 @@ extern unsigned int pageblock_order; #endif /* CONFIG_HUGETLB_PAGE */ #define pageblock_nr_pages (1UL << pageblock_order) +#define pageblock_align(pfn) ALIGN((pfn), pageblock_nr_pages) #define pageblock_start_pfn(pfn) ALIGN_DOWN((pfn), pageblock_nr_pages) #define pageblock_end_pfn(pfn) ALIGN((pfn) + 1, pageblock_nr_pages) -- cgit v1.2.3 From ee0913c4719610204315a0d8a35122c6233249e0 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Wed, 7 Sep 2022 14:08:44 +0800 Subject: mm: add pageblock_aligned() macro Add pageblock_aligned() and use it to simplify code. Link: https://lkml.kernel.org/r/20220907060844.126891-3-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Acked-by: Mike Rapoport Cc: David Hildenbrand Cc: Oscar Salvador Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/pageblock-flags.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h index 293c76630fa8..5f1ae07d724b 100644 --- a/include/linux/pageblock-flags.h +++ b/include/linux/pageblock-flags.h @@ -54,6 +54,7 @@ extern unsigned int pageblock_order; #define pageblock_nr_pages (1UL << pageblock_order) #define pageblock_align(pfn) ALIGN((pfn), pageblock_nr_pages) +#define pageblock_aligned(pfn) IS_ALIGNED((pfn), pageblock_nr_pages) #define pageblock_start_pfn(pfn) ALIGN_DOWN((pfn), pageblock_nr_pages) #define pageblock_end_pfn(pfn) ALIGN((pfn) + 1, pageblock_nr_pages) -- cgit v1.2.3 From 410f8e82689e1e66044fea51ef852054a09502b7 Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Wed, 7 Sep 2022 04:35:35 +0000 Subject: memcg: extract memcg_vmstats from struct mem_cgroup Patch series "memcg: reduce memory overhead of memory cgroups". Currently a lot of memory is wasted to maintain the vmevents for memory cgroups as we have multiple arrays of size NR_VM_EVENT_ITEMS which can be as large as 110. However memcg code uses small portion of those entries. This patch series eliminate this overhead by removing the unneeded vmevent entries from memory cgroup data structures. This patch (of 3): This is a preparatory patch to reduce the memory overhead of memory cgroup. The struct memcg_vmstats is the largest object embedded into the struct mem_cgroup. This patch extracts struct memcg_vmstats from struct mem_cgroup to ease the following patches in reducing the size of struct memcg_vmstats. Link: https://lkml.kernel.org/r/20220907043537.3457014-1-shakeelb@google.com Link: https://lkml.kernel.org/r/20220907043537.3457014-2-shakeelb@google.com Signed-off-by: Shakeel Butt Acked-by: Roman Gushchin Cc: Johannes Weiner Cc: Michal Hocko Cc: Muchun Song Signed-off-by: Andrew Morton --- include/linux/memcontrol.h | 37 ++++--------------------------------- 1 file changed, 4 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index ca0df42662ad..dc7d40e575d5 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -80,29 +80,8 @@ enum mem_cgroup_events_target { MEM_CGROUP_NTARGETS, }; -struct memcg_vmstats_percpu { - /* Local (CPU and cgroup) page state & events */ - long state[MEMCG_NR_STAT]; - unsigned long events[NR_VM_EVENT_ITEMS]; - - /* Delta calculation for lockless upward propagation */ - long state_prev[MEMCG_NR_STAT]; - unsigned long events_prev[NR_VM_EVENT_ITEMS]; - - /* Cgroup1: threshold notifications & softlimit tree updates */ - unsigned long nr_page_events; - unsigned long targets[MEM_CGROUP_NTARGETS]; -}; - -struct memcg_vmstats { - /* Aggregated (CPU and subtree) page state & events */ - long state[MEMCG_NR_STAT]; - unsigned long events[NR_VM_EVENT_ITEMS]; - - /* Pending child counts during tree propagation */ - long state_pending[MEMCG_NR_STAT]; - unsigned long events_pending[NR_VM_EVENT_ITEMS]; -}; +struct memcg_vmstats_percpu; +struct memcg_vmstats; struct mem_cgroup_reclaim_iter { struct mem_cgroup *position; @@ -298,7 +277,7 @@ struct mem_cgroup { CACHELINE_PADDING(_pad1_); /* memory.stat */ - struct memcg_vmstats vmstats; + struct memcg_vmstats *vmstats; /* memory.events */ atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS]; @@ -1001,15 +980,7 @@ static inline void mod_memcg_page_state(struct page *page, rcu_read_unlock(); } -static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) -{ - long x = READ_ONCE(memcg->vmstats.state[idx]); -#ifdef CONFIG_SMP - if (x < 0) - x = 0; -#endif - return x; -} +unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx); static inline unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx) -- cgit v1.2.3 From f5a79d7c0c87c8d88bb5e3f3c898258fdf1b3b05 Mon Sep 17 00:00:00 2001 From: Yajun Deng Date: Thu, 8 Sep 2022 19:14:43 +0000 Subject: mm/damon: introduce struct damos_access_pattern damon_new_scheme() has too many parameters, so introduce struct damos_access_pattern to simplify it. In additon, we can't use a bpf trace kprobe that has more than 5 parameters. Link: https://lkml.kernel.org/r/20220908191443.129534-1-sj@kernel.org Signed-off-by: Yajun Deng Signed-off-by: SeongJae Park Reviewed-by: SeongJae Park Signed-off-by: Andrew Morton --- include/linux/damon.h | 37 ++++++++++++++++++++----------------- 1 file changed, 20 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index d54acec048d6..90f20675da22 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -216,13 +216,26 @@ struct damos_stat { }; /** - * struct damos - Represents a Data Access Monitoring-based Operation Scheme. + * struct damos_access_pattern - Target access pattern of the given scheme. * @min_sz_region: Minimum size of target regions. * @max_sz_region: Maximum size of target regions. * @min_nr_accesses: Minimum ``->nr_accesses`` of target regions. * @max_nr_accesses: Maximum ``->nr_accesses`` of target regions. * @min_age_region: Minimum age of target regions. * @max_age_region: Maximum age of target regions. + */ +struct damos_access_pattern { + unsigned long min_sz_region; + unsigned long max_sz_region; + unsigned int min_nr_accesses; + unsigned int max_nr_accesses; + unsigned int min_age_region; + unsigned int max_age_region; +}; + +/** + * struct damos - Represents a Data Access Monitoring-based Operation Scheme. + * @pattern: Access pattern of target regions. * @action: &damo_action to be applied to the target regions. * @quota: Control the aggressiveness of this scheme. * @wmarks: Watermarks for automated (in)activation of this scheme. @@ -230,10 +243,8 @@ struct damos_stat { * @list: List head for siblings. * * For each aggregation interval, DAMON finds regions which fit in the - * condition (&min_sz_region, &max_sz_region, &min_nr_accesses, - * &max_nr_accesses, &min_age_region, &max_age_region) and applies &action to - * those. To avoid consuming too much CPU time or IO resources for the - * &action, "a is used. + * &pattern and applies &action to those. To avoid consuming too much + * CPU time or IO resources for the &action, "a is used. * * To do the work only when needed, schemes can be activated for specific * system situations using &wmarks. If all schemes that registered to the @@ -248,12 +259,7 @@ struct damos_stat { * &action is applied. */ struct damos { - unsigned long min_sz_region; - unsigned long max_sz_region; - unsigned int min_nr_accesses; - unsigned int max_nr_accesses; - unsigned int min_age_region; - unsigned int max_age_region; + struct damos_access_pattern pattern; enum damos_action action; struct damos_quota quota; struct damos_watermarks wmarks; @@ -509,12 +515,9 @@ void damon_destroy_region(struct damon_region *r, struct damon_target *t); int damon_set_regions(struct damon_target *t, struct damon_addr_range *ranges, unsigned int nr_ranges); -struct damos *damon_new_scheme( - unsigned long min_sz_region, unsigned long max_sz_region, - unsigned int min_nr_accesses, unsigned int max_nr_accesses, - unsigned int min_age_region, unsigned int max_age_region, - enum damos_action action, struct damos_quota *quota, - struct damos_watermarks *wmarks); +struct damos *damon_new_scheme(struct damos_access_pattern *pattern, + enum damos_action action, struct damos_quota *quota, + struct damos_watermarks *wmarks); void damon_add_scheme(struct damon_ctx *ctx, struct damos *s); void damon_destroy_scheme(struct damos *s); -- cgit v1.2.3 From 0d83b2d89dbfad17b62d4e7fb8f0b0525ba1a204 Mon Sep 17 00:00:00 2001 From: Xin Hao Date: Fri, 9 Sep 2022 21:36:06 +0000 Subject: mm/damon: remove duplicate get_monitoring_region() definitions In lru_sort.c and reclaim.c, they are all defining get_monitoring_region() function, there is no need to define it separately. As 'get_monitoring_region()' is not a 'static' function anymore, we try to use a prefix to distinguish with other functions, so there rename it to 'damon_find_biggest_system_ram'. Link: https://lkml.kernel.org/r/20220909213606.136221-1-sj@kernel.org Signed-off-by: Xin Hao Signed-off-by: SeongJae Park Suggested-by: SeongJae Park Reviewed-by: SeongJae Park Signed-off-by: Andrew Morton --- include/linux/damon.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 90f20675da22..016b6c9c03d6 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -549,6 +549,8 @@ static inline bool damon_target_has_pid(const struct damon_ctx *ctx) int damon_start(struct damon_ctx **ctxs, int nr_ctxs, bool exclusive); int damon_stop(struct damon_ctx **ctxs, int nr_ctxs); +bool damon_find_biggest_system_ram(unsigned long *start, unsigned long *end); + #endif /* CONFIG_DAMON */ #endif /* _DAMON_H */ -- cgit v1.2.3 From 13cc378403a83e70430ae9bad53fd65199f21fe1 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Fri, 9 Sep 2022 10:57:11 +0800 Subject: writeback: remove unused macro DIRTY_FULL_SCOPE It's introduced but never used. Remove it. Link: https://lkml.kernel.org/r/20220909025711.32012-1-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Reviewed-by: Jan Kara Acked-by: Jens Axboe Cc: Bart Van Assche Cc: David Howells Cc: Matthew Wilcox Cc: NeilBrown Cc: Vlastimil Babka Cc: zhanglianjie Signed-off-by: Andrew Morton --- include/linux/writeback.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 3f045f6d6c4f..06f9291b6fd5 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -17,20 +17,12 @@ struct bio; DECLARE_PER_CPU(int, dirty_throttle_leaks); /* - * The 1/4 region under the global dirty thresh is for smooth dirty throttling: - * - * (thresh - thresh/DIRTY_FULL_SCOPE, thresh) - * - * Further beyond, all dirtier tasks will enter a loop waiting (possibly long - * time) for the dirty pages to drop, unless written enough pages. - * * The global dirty threshold is normally equal to the global dirty limit, * except when the system suddenly allocates a lot of anonymous memory and * knocks down the global dirty threshold quickly, in which case the global * dirty limit will follow down slowly to prevent livelocking all dirtier tasks. */ #define DIRTY_SCOPE 8 -#define DIRTY_FULL_SCOPE (DIRTY_SCOPE / 2) struct backing_dev_info; -- cgit v1.2.3 From cbeaa77b044938cfe91818821ece6b0b1511e967 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Tue, 13 Sep 2022 17:44:32 +0000 Subject: mm/damon/core: use a dedicated struct for monitoring attributes DAMON monitoring attributes are directly defined as fields of 'struct damon_ctx'. This makes 'struct damon_ctx' a little long and complicated. This commit defines and uses a struct, 'struct damon_attrs', which is dedicated for only the monitoring attributes to make the purpose of the five values clearer and simplify 'struct damon_ctx'. Link: https://lkml.kernel.org/r/20220913174449.50645-6-sj@kernel.org Signed-off-by: SeongJae Park Signed-off-by: Andrew Morton --- include/linux/damon.h | 30 ++++++++++++++++++++---------- 1 file changed, 20 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 016b6c9c03d6..2ceee8b07726 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -389,13 +389,15 @@ struct damon_callback { }; /** - * struct damon_ctx - Represents a context for each monitoring. This is the - * main interface that allows users to set the attributes and get the results - * of the monitoring. + * struct damon_attrs - Monitoring attributes for accuracy/overhead control. * * @sample_interval: The time between access samplings. * @aggr_interval: The time between monitor results aggregations. * @ops_update_interval: The time between monitoring operations updates. + * @min_nr_regions: The minimum number of adaptive monitoring + * regions. + * @max_nr_regions: The maximum number of adaptive monitoring + * regions. * * For each @sample_interval, DAMON checks whether each region is accessed or * not. It aggregates and keeps the access information (number of accesses to @@ -405,7 +407,21 @@ struct damon_callback { * @ops_update_interval. All time intervals are in micro-seconds. * Please refer to &struct damon_operations and &struct damon_callback for more * detail. + */ +struct damon_attrs { + unsigned long sample_interval; + unsigned long aggr_interval; + unsigned long ops_update_interval; + unsigned long min_nr_regions; + unsigned long max_nr_regions; +}; + +/** + * struct damon_ctx - Represents a context for each monitoring. This is the + * main interface that allows users to set the attributes and get the results + * of the monitoring. * + * @attrs: Monitoring attributes for accuracy/overhead control. * @kdamond: Kernel thread who does the monitoring. * @kdamond_lock: Mutex for the synchronizations with @kdamond. * @@ -427,15 +443,11 @@ struct damon_callback { * @ops: Set of monitoring operations for given use cases. * @callback: Set of callbacks for monitoring events notifications. * - * @min_nr_regions: The minimum number of adaptive monitoring regions. - * @max_nr_regions: The maximum number of adaptive monitoring regions. * @adaptive_targets: Head of monitoring targets (&damon_target) list. * @schemes: Head of schemes (&damos) list. */ struct damon_ctx { - unsigned long sample_interval; - unsigned long aggr_interval; - unsigned long ops_update_interval; + struct damon_attrs attrs; /* private: internal use only */ struct timespec64 last_aggregation; @@ -448,8 +460,6 @@ struct damon_ctx { struct damon_operations ops; struct damon_callback callback; - unsigned long min_nr_regions; - unsigned long max_nr_regions; struct list_head adaptive_targets; struct list_head schemes; }; -- cgit v1.2.3 From bead3b00088eb8016b32cafa7e0701b3283e68a4 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Tue, 13 Sep 2022 17:44:33 +0000 Subject: mm/damon/core: reduce parameters for damon_set_attrs() Number of parameters for 'damon_set_attrs()' is six. As it could be confusing and verbose, this commit reduces the number by receiving single pointer to a 'struct damon_attrs'. Link: https://lkml.kernel.org/r/20220913174449.50645-7-sj@kernel.org Signed-off-by: SeongJae Park Signed-off-by: Andrew Morton --- include/linux/damon.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 2ceee8b07726..c5dc0c77c772 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -540,9 +540,7 @@ unsigned int damon_nr_regions(struct damon_target *t); struct damon_ctx *damon_new_ctx(void); void damon_destroy_ctx(struct damon_ctx *ctx); -int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int, - unsigned long aggr_int, unsigned long ops_upd_int, - unsigned long min_nr_reg, unsigned long max_nr_reg); +int damon_set_attrs(struct damon_ctx *ctx, struct damon_attrs *attrs); int damon_set_schemes(struct damon_ctx *ctx, struct damos **schemes, ssize_t nr_schemes); int damon_nr_running_ctxs(void); -- cgit v1.2.3 From b958d4d08fbfe938af24ea06ebbf839b48fa18a9 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Wed, 14 Sep 2022 15:26:02 +0800 Subject: mm: hugetlb: simplify per-node sysfs creation and removal Patch series "simplify handling of per-node sysfs creation and removal", v4. This patch (of 2): The following commit offload per-node sysfs creation and removal to a kworker and did not say why it is needed. And it also said "I don't know that this is absolutely required". It seems like the author was not sure as well. Since it only complicates the code, this patch will revert the changes to simplify the code. 39da08cb074c ("hugetlb: offload per node attribute registrations") We could use memory hotplug notifier to do per-node sysfs creation and removal instead of inserting those operations to node registration and unregistration. Then, it can reduce the code coupling between node.c and hugetlb.c. Also, it can simplify the code. Link: https://lkml.kernel.org/r/20220914072603.60293-1-songmuchun@bytedance.com Link: https://lkml.kernel.org/r/20220914072603.60293-2-songmuchun@bytedance.com Signed-off-by: Muchun Song Acked-by: Mike Kravetz Acked-by: David Hildenbrand Cc: Andi Kleen Cc: Greg Kroah-Hartman Cc: Muchun Song Cc: Oscar Salvador Cc: Rafael J. Wysocki Signed-off-by: Andrew Morton --- include/linux/node.h | 24 ++++-------------------- 1 file changed, 4 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/node.h b/include/linux/node.h index 9ec680dd607f..427a5975cf40 100644 --- a/include/linux/node.h +++ b/include/linux/node.h @@ -2,15 +2,15 @@ /* * include/linux/node.h - generic node definition * - * This is mainly for topological representation. We define the - * basic 'struct node' here, which can be embedded in per-arch + * This is mainly for topological representation. We define the + * basic 'struct node' here, which can be embedded in per-arch * definitions of processors. * * Basic handling of the devices is done in drivers/base/node.c - * and system devices are handled in drivers/base/sys.c. + * and system devices are handled in drivers/base/sys.c. * * Nodes are exported via driverfs in the class/node/devices/ - * directory. + * directory. */ #ifndef _LINUX_NODE_H_ #define _LINUX_NODE_H_ @@ -18,7 +18,6 @@ #include #include #include -#include /** * struct node_hmem_attrs - heterogeneous memory performance attributes @@ -84,10 +83,6 @@ static inline void node_set_perf_attrs(unsigned int nid, struct node { struct device dev; struct list_head access_list; - -#if defined(CONFIG_MEMORY_HOTPLUG) && defined(CONFIG_HUGETLBFS) - struct work_struct node_work; -#endif #ifdef CONFIG_HMEM_REPORTING struct list_head cache_attrs; struct device *cache_dev; @@ -96,7 +91,6 @@ struct node { struct memory_block; extern struct node *node_devices[]; -typedef void (*node_registration_func_t)(struct node *); #if defined(CONFIG_MEMORY_HOTPLUG) && defined(CONFIG_NUMA) void register_memory_blocks_under_node(int nid, unsigned long start_pfn, @@ -144,11 +138,6 @@ extern void unregister_memory_block_under_nodes(struct memory_block *mem_blk); extern int register_memory_node_under_compute_node(unsigned int mem_nid, unsigned int cpu_nid, unsigned access); - -#ifdef CONFIG_HUGETLBFS -extern void register_hugetlbfs_with_node(node_registration_func_t doregister, - node_registration_func_t unregister); -#endif #else static inline void node_dev_init(void) { @@ -176,11 +165,6 @@ static inline int unregister_cpu_under_node(unsigned int cpu, unsigned int nid) static inline void unregister_memory_block_under_nodes(struct memory_block *mem_blk) { } - -static inline void register_hugetlbfs_with_node(node_registration_func_t reg, - node_registration_func_t unreg) -{ -} #endif #define to_node(device) container_of(device, struct node, dev) -- cgit v1.2.3 From a4a00b451ef5e1deb959088e25e248f4ee399792 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Wed, 14 Sep 2022 15:26:03 +0800 Subject: mm: hugetlb: eliminate memory-less nodes handling The memory-notify-based approach aims to handle meory-less nodes, however, it just adds the complexity of code as pointed by David in thread [1]. The handling of memory-less nodes is introduced by commit 4faf8d950ec4 ("hugetlb: handle memory hot-plug events"). >From its commit message, we cannot find any necessity of handling this case. So, we can simply register/unregister sysfs entries in register_node/unregister_node to simlify the code. BTW, hotplug callback added because in hugetlb_register_all_nodes() we register sysfs nodes only for N_MEMORY nodes, seeing commit 9b5e5d0fdc91, which said it was a preparation for handling memory-less nodes via memory hotplug. Since we want to remove memory hotplug, so make sure we only register per-node sysfs for online (N_ONLINE) nodes in hugetlb_register_all_nodes(). https://lore.kernel.org/linux-mm/60933ffc-b850-976c-78a0-0ee6e0ea9ef0@redhat.com/ [1] Link: https://lkml.kernel.org/r/20220914072603.60293-3-songmuchun@bytedance.com Suggested-by: David Hildenbrand Signed-off-by: Muchun Song Acked-by: David Hildenbrand Cc: Andi Kleen Cc: Greg Kroah-Hartman Cc: Mike Kravetz Cc: Oscar Salvador Cc: Rafael J. Wysocki Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 57e72954a482..6d7f39754060 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -16,6 +16,7 @@ struct ctl_table; struct user_struct; struct mmu_gather; +struct node; #ifndef is_hugepd typedef struct { unsigned long pd; } hugepd_t; @@ -935,6 +936,11 @@ static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, } #endif +#ifdef CONFIG_NUMA +void hugetlb_register_node(struct node *node); +void hugetlb_unregister_node(struct node *node); +#endif + #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; @@ -1109,6 +1115,14 @@ static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { } + +static inline void hugetlb_register_node(struct node *node) +{ +} + +static inline void hugetlb_unregister_node(struct node *node) +{ +} #endif /* CONFIG_HUGETLB_PAGE */ static inline spinlock_t *huge_pte_lock(struct hstate *h, -- cgit v1.2.3 From c195c3215741746b1eb7ab7980b926ddc37a4be3 Mon Sep 17 00:00:00 2001 From: Ke Sun Date: Wed, 14 Sep 2022 10:17:38 +0800 Subject: mm/filemap: make folio_put_wait_locked static It's only used in mm/filemap.c, since commit ("mm/migrate.c: rework migration_entry_wait() to not take a pageref"). Make it static. Link: https://lkml.kernel.org/r/20220914021738.3228011-1-sunke@kylinos.cn Signed-off-by: Ke Sun Reported-by: k2ci Signed-off-by: Andrew Morton --- include/linux/pagemap.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 32846b6306db..23125ab87ded 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -1039,7 +1039,6 @@ static inline int wait_on_page_locked_killable(struct page *page) return folio_wait_locked_killable(page_folio(page)); } -int folio_put_wait_locked(struct folio *folio, int state); void wait_on_page_writeback(struct page *page); void folio_wait_writeback(struct folio *folio); int folio_wait_writeback_killable(struct folio *folio); -- cgit v1.2.3 From 7e1813d48dd30e6c6f235f6661d1bc108fcab528 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Wed, 14 Sep 2022 15:18:04 -0700 Subject: hugetlb: rename remove_huge_page to hugetlb_delete_from_page_cache remove_huge_page removes a hugetlb page from the page cache. Change to hugetlb_delete_from_page_cache as it is a more descriptive name. huge_add_to_page_cache is global in scope, but only deals with hugetlb pages. For consistency and clarity, rename to hugetlb_add_to_page_cache. Link: https://lkml.kernel.org/r/20220914221810.95771-4-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Reviewed-by: Miaohe Lin Cc: Andrea Arcangeli Cc: "Aneesh Kumar K.V" Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Davidlohr Bueso Cc: James Houghton Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Mina Almasry Cc: Muchun Song Cc: Naoya Horiguchi Cc: Pasha Tatashin Cc: Peter Xu Cc: Prakash Sangappa Cc: Sven Schnelle Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 6d7f39754060..4893d6d07099 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -666,7 +666,7 @@ struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask); struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address); -int huge_add_to_page_cache(struct page *page, struct address_space *mapping, +int hugetlb_add_to_page_cache(struct page *page, struct address_space *mapping, pgoff_t idx); void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, unsigned long address, struct page *page); -- cgit v1.2.3 From 8d9bfb2608145cf3e408428c224099e1585471af Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Wed, 14 Sep 2022 15:18:07 -0700 Subject: hugetlb: add vma based lock for pmd sharing Allocate a new hugetlb_vma_lock structure and hang off vm_private_data for synchronization use by vmas that could be involved in pmd sharing. This data structure contains a rw semaphore that is the primary tool used for synchronization. This new structure is ref counted, so that it can exist when NOT attached to a vma. This is only helpful in resolving lock ordering issues where code may need to obtain the vma_lock while there are no guarantees the vma may go away. By obtaining a ref on the structure, it can be guaranteed that at least the rw semaphore will not go away. Only add infrastructure for the new lock here. Actual use will be added in subsequent patches. [mike.kravetz@oracle.com: fix build issue for missing hugetlb_vma_lock_release] Link: https://lkml.kernel.org/r/YyNUtA1vRASOE4+M@monkey Link: https://lkml.kernel.org/r/20220914221810.95771-7-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Reviewed-by: Miaohe Lin Cc: Andrea Arcangeli Cc: "Aneesh Kumar K.V" Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Davidlohr Bueso Cc: James Houghton Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Mina Almasry Cc: Muchun Song Cc: Naoya Horiguchi Cc: Pasha Tatashin Cc: Peter Xu Cc: Prakash Sangappa Cc: Sven Schnelle Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 43 +++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 41 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 4893d6d07099..7b70aa931729 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -115,6 +115,12 @@ struct file_region { #endif }; +struct hugetlb_vma_lock { + struct kref refs; + struct rw_semaphore rw_sema; + struct vm_area_struct *vma; +}; + extern struct resv_map *resv_map_alloc(void); void resv_map_release(struct kref *ref); @@ -127,7 +133,7 @@ struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages, long min_hpages); void hugepage_put_subpool(struct hugepage_subpool *spool); -void reset_vma_resv_huge_pages(struct vm_area_struct *vma); +void hugetlb_dup_vma_private(struct vm_area_struct *vma); void clear_vma_resv_huge_pages(struct vm_area_struct *vma); int hugetlb_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int hugetlb_overcommit_handler(struct ctl_table *, int, void *, size_t *, @@ -215,6 +221,14 @@ struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address, struct page *follow_huge_pgd(struct mm_struct *mm, unsigned long address, pgd_t *pgd, int flags); +void hugetlb_vma_lock_read(struct vm_area_struct *vma); +void hugetlb_vma_unlock_read(struct vm_area_struct *vma); +void hugetlb_vma_lock_write(struct vm_area_struct *vma); +void hugetlb_vma_unlock_write(struct vm_area_struct *vma); +int hugetlb_vma_trylock_write(struct vm_area_struct *vma); +void hugetlb_vma_assert_locked(struct vm_area_struct *vma); +void hugetlb_vma_lock_release(struct kref *kref); + int pmd_huge(pmd_t pmd); int pud_huge(pud_t pud); unsigned long hugetlb_change_protection(struct vm_area_struct *vma, @@ -226,7 +240,7 @@ void hugetlb_unshare_all_pmds(struct vm_area_struct *vma); #else /* !CONFIG_HUGETLB_PAGE */ -static inline void reset_vma_resv_huge_pages(struct vm_area_struct *vma) +static inline void hugetlb_dup_vma_private(struct vm_area_struct *vma) { } @@ -337,6 +351,31 @@ static inline int prepare_hugepage_range(struct file *file, return -EINVAL; } +static inline void hugetlb_vma_lock_read(struct vm_area_struct *vma) +{ +} + +static inline void hugetlb_vma_unlock_read(struct vm_area_struct *vma) +{ +} + +static inline void hugetlb_vma_lock_write(struct vm_area_struct *vma) +{ +} + +static inline void hugetlb_vma_unlock_write(struct vm_area_struct *vma) +{ +} + +static inline int hugetlb_vma_trylock_write(struct vm_area_struct *vma) +{ + return 1; +} + +static inline void hugetlb_vma_assert_locked(struct vm_area_struct *vma) +{ +} + static inline int pmd_huge(pmd_t pmd) { return 0; -- cgit v1.2.3 From 83a4f1ef45a90d740bc6edf6a2533b14a3e5d183 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Thu, 15 Sep 2022 17:03:36 +0200 Subject: stackdepot: reserve 5 extra bits in depot_stack_handle_t Some users (currently only KMSAN) may want to use spare bits in depot_stack_handle_t. Let them do so by adding @extra_bits to __stack_depot_save() to store arbitrary flags, and providing stack_depot_get_extra_bits() to retrieve those flags. Also adapt KASAN to the new prototype by passing extra_bits=0, as KASAN does not intend to store additional information in the stack handle. Link: https://lkml.kernel.org/r/20220915150417.722975-3-glider@google.com Signed-off-by: Alexander Potapenko Reviewed-by: Marco Elver Cc: Alexander Viro Cc: Alexei Starovoitov Cc: Andrey Konovalov Cc: Andrey Konovalov Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Christoph Hellwig Cc: Christoph Lameter Cc: David Rientjes Cc: Dmitry Vyukov Cc: Eric Biggers Cc: Eric Biggers Cc: Eric Dumazet Cc: Greg Kroah-Hartman Cc: Herbert Xu Cc: Ilya Leoshkevich Cc: Ingo Molnar Cc: Jens Axboe Cc: Joonsoo Kim Cc: Kees Cook Cc: Mark Rutland Cc: Matthew Wilcox Cc: Michael S. Tsirkin Cc: Pekka Enberg Cc: Peter Zijlstra Cc: Petr Mladek Cc: Stephen Rothwell Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Vegard Nossum Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/stackdepot.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index bc2797955de9..9ca7798d7a31 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -14,9 +14,15 @@ #include typedef u32 depot_stack_handle_t; +/* + * Number of bits in the handle that stack depot doesn't use. Users may store + * information in them. + */ +#define STACK_DEPOT_EXTRA_BITS 5 depot_stack_handle_t __stack_depot_save(unsigned long *entries, unsigned int nr_entries, + unsigned int extra_bits, gfp_t gfp_flags, bool can_alloc); /* @@ -59,6 +65,8 @@ depot_stack_handle_t stack_depot_save(unsigned long *entries, unsigned int stack_depot_fetch(depot_stack_handle_t handle, unsigned long **entries); +unsigned int stack_depot_get_extra_bits(depot_stack_handle_t handle); + int stack_depot_snprint(depot_stack_handle_t handle, char *buf, size_t size, int spaces); -- cgit v1.2.3 From 33b75c1d884e81ec97525e0a6fdcb187adf273f4 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Thu, 15 Sep 2022 17:03:37 +0200 Subject: instrumented.h: allow instrumenting both sides of copy_from_user() Introduce instrument_copy_from_user_before() and instrument_copy_from_user_after() hooks to be invoked before and after the call to copy_from_user(). KASAN and KCSAN will be only using instrument_copy_from_user_before(), but for KMSAN we'll need to insert code after copy_from_user(). Link: https://lkml.kernel.org/r/20220915150417.722975-4-glider@google.com Signed-off-by: Alexander Potapenko Reviewed-by: Marco Elver Cc: Alexander Viro Cc: Alexei Starovoitov Cc: Andrey Konovalov Cc: Andrey Konovalov Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Christoph Hellwig Cc: Christoph Lameter Cc: David Rientjes Cc: Dmitry Vyukov Cc: Eric Biggers Cc: Eric Biggers Cc: Eric Dumazet Cc: Greg Kroah-Hartman Cc: Herbert Xu Cc: Ilya Leoshkevich Cc: Ingo Molnar Cc: Jens Axboe Cc: Joonsoo Kim Cc: Kees Cook Cc: Mark Rutland Cc: Matthew Wilcox Cc: Michael S. Tsirkin Cc: Pekka Enberg Cc: Peter Zijlstra Cc: Petr Mladek Cc: Stephen Rothwell Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Vegard Nossum Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/instrumented.h | 21 +++++++++++++++++++-- include/linux/uaccess.h | 19 ++++++++++++++----- 2 files changed, 33 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/instrumented.h b/include/linux/instrumented.h index 42faebbaa202..ee8f7d17d34f 100644 --- a/include/linux/instrumented.h +++ b/include/linux/instrumented.h @@ -120,7 +120,7 @@ instrument_copy_to_user(void __user *to, const void *from, unsigned long n) } /** - * instrument_copy_from_user - instrument writes of copy_from_user + * instrument_copy_from_user_before - add instrumentation before copy_from_user * * Instrument writes to kernel memory, that are due to copy_from_user (and * variants). The instrumentation should be inserted before the accesses. @@ -130,10 +130,27 @@ instrument_copy_to_user(void __user *to, const void *from, unsigned long n) * @n number of bytes to copy */ static __always_inline void -instrument_copy_from_user(const void *to, const void __user *from, unsigned long n) +instrument_copy_from_user_before(const void *to, const void __user *from, unsigned long n) { kasan_check_write(to, n); kcsan_check_write(to, n); } +/** + * instrument_copy_from_user_after - add instrumentation after copy_from_user + * + * Instrument writes to kernel memory, that are due to copy_from_user (and + * variants). The instrumentation should be inserted after the accesses. + * + * @to destination address + * @from source address + * @n number of bytes to copy + * @left number of bytes not copied (as returned by copy_from_user) + */ +static __always_inline void +instrument_copy_from_user_after(const void *to, const void __user *from, + unsigned long n, unsigned long left) +{ +} + #endif /* _LINUX_INSTRUMENTED_H */ diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 47e5d374c7eb..afb18f198843 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -58,20 +58,28 @@ static __always_inline __must_check unsigned long __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n) { - instrument_copy_from_user(to, from, n); + unsigned long res; + + instrument_copy_from_user_before(to, from, n); check_object_size(to, n, false); - return raw_copy_from_user(to, from, n); + res = raw_copy_from_user(to, from, n); + instrument_copy_from_user_after(to, from, n, res); + return res; } static __always_inline __must_check unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n) { + unsigned long res; + might_fault(); + instrument_copy_from_user_before(to, from, n); if (should_fail_usercopy()) return n; - instrument_copy_from_user(to, from, n); check_object_size(to, n, false); - return raw_copy_from_user(to, from, n); + res = raw_copy_from_user(to, from, n); + instrument_copy_from_user_after(to, from, n, res); + return res; } /** @@ -115,8 +123,9 @@ _copy_from_user(void *to, const void __user *from, unsigned long n) unsigned long res = n; might_fault(); if (!should_fail_usercopy() && likely(access_ok(from, n))) { - instrument_copy_from_user(to, from, n); + instrument_copy_from_user_before(to, from, n); res = raw_copy_from_user(to, from, n); + instrument_copy_from_user_after(to, from, n, res); } if (unlikely(res)) memset(to + (n - res), 0, res); -- cgit v1.2.3 From 888f84a6da4d17e453058169fa7b235fff34f5bf Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Thu, 15 Sep 2022 17:03:38 +0200 Subject: x86: asm: instrument usercopy in get_user() and put_user() Use hooks from instrumented.h to notify bug detection tools about usercopy events in variations of get_user() and put_user(). Link: https://lkml.kernel.org/r/20220915150417.722975-5-glider@google.com Signed-off-by: Alexander Potapenko Cc: Alexander Viro Cc: Alexei Starovoitov Cc: Andrey Konovalov Cc: Andrey Konovalov Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Christoph Hellwig Cc: Christoph Lameter Cc: David Rientjes Cc: Dmitry Vyukov Cc: Eric Biggers Cc: Eric Biggers Cc: Eric Dumazet Cc: Greg Kroah-Hartman Cc: Herbert Xu Cc: Ilya Leoshkevich Cc: Ingo Molnar Cc: Jens Axboe Cc: Joonsoo Kim Cc: Kees Cook Cc: Marco Elver Cc: Mark Rutland Cc: Matthew Wilcox Cc: Michael S. Tsirkin Cc: Pekka Enberg Cc: Peter Zijlstra Cc: Petr Mladek Cc: Stephen Rothwell Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Vegard Nossum Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/instrumented.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/instrumented.h b/include/linux/instrumented.h index ee8f7d17d34f..9f1dba8f717b 100644 --- a/include/linux/instrumented.h +++ b/include/linux/instrumented.h @@ -153,4 +153,32 @@ instrument_copy_from_user_after(const void *to, const void __user *from, { } +/** + * instrument_get_user() - add instrumentation to get_user()-like macros + * + * get_user() and friends are fragile, so it may depend on the implementation + * whether the instrumentation happens before or after the data is copied from + * the userspace. + * + * @to destination variable, may not be address-taken + */ +#define instrument_get_user(to) \ +({ \ +}) + +/** + * instrument_put_user() - add instrumentation to put_user()-like macros + * + * put_user() and friends are fragile, so it may depend on the implementation + * whether the instrumentation happens before or after the data is copied from + * the userspace. + * + * @from source address + * @ptr userspace pointer to copy to + * @size number of bytes to copy + */ +#define instrument_put_user(from, ptr, size) \ +({ \ +}) + #endif /* _LINUX_INSTRUMENTED_H */ -- cgit v1.2.3 From 9b448bc25b776daab3215393c3ce6953dd3bb8ad Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Thu, 15 Sep 2022 17:03:41 +0200 Subject: kmsan: introduce __no_sanitize_memory and __no_kmsan_checks __no_sanitize_memory is a function attribute that instructs KMSAN to skip a function during instrumentation. This is needed to e.g. implement the noinstr functions. __no_kmsan_checks is a function attribute that makes KMSAN ignore the uninitialized values coming from the function's inputs, and initialize the function's outputs. Functions marked with this attribute can't be inlined into functions not marked with it, and vice versa. This behavior is overridden by __always_inline. __SANITIZE_MEMORY__ is a macro that's defined iff the file is instrumented with KMSAN. This is not the same as CONFIG_KMSAN, which is defined for every file. Link: https://lkml.kernel.org/r/20220915150417.722975-8-glider@google.com Signed-off-by: Alexander Potapenko Reviewed-by: Marco Elver Cc: Alexander Viro Cc: Alexei Starovoitov Cc: Andrey Konovalov Cc: Andrey Konovalov Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Christoph Hellwig Cc: Christoph Lameter Cc: David Rientjes Cc: Dmitry Vyukov Cc: Eric Biggers Cc: Eric Biggers Cc: Eric Dumazet Cc: Greg Kroah-Hartman Cc: Herbert Xu Cc: Ilya Leoshkevich Cc: Ingo Molnar Cc: Jens Axboe Cc: Joonsoo Kim Cc: Kees Cook Cc: Mark Rutland Cc: Matthew Wilcox Cc: Michael S. Tsirkin Cc: Pekka Enberg Cc: Peter Zijlstra Cc: Petr Mladek Cc: Stephen Rothwell Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Vegard Nossum Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/compiler-clang.h | 23 +++++++++++++++++++++++ include/linux/compiler-gcc.h | 6 ++++++ 2 files changed, 29 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index c84fec767445..4fa0cc4cbd2c 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -51,6 +51,29 @@ #define __no_sanitize_undefined #endif +#if __has_feature(memory_sanitizer) +#define __SANITIZE_MEMORY__ +/* + * Unlike other sanitizers, KMSAN still inserts code into functions marked with + * no_sanitize("kernel-memory"). Using disable_sanitizer_instrumentation + * provides the behavior consistent with other __no_sanitize_ attributes, + * guaranteeing that __no_sanitize_memory functions remain uninstrumented. + */ +#define __no_sanitize_memory __disable_sanitizer_instrumentation + +/* + * The __no_kmsan_checks attribute ensures that a function does not produce + * false positive reports by: + * - initializing all local variables and memory stores in this function; + * - skipping all shadow checks; + * - passing initialized arguments to this function's callees. + */ +#define __no_kmsan_checks __attribute__((no_sanitize("kernel-memory"))) +#else +#define __no_sanitize_memory +#define __no_kmsan_checks +#endif + /* * Support for __has_feature(coverage_sanitizer) was added in Clang 13 together * with no_sanitize("coverage"). Prior versions of Clang support coverage diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 9b157b71036f..f55a37efdb97 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -114,6 +114,12 @@ #define __SANITIZE_ADDRESS__ #endif +/* + * GCC does not support KMSAN. + */ +#define __no_sanitize_memory +#define __no_kmsan_checks + /* * Turn individual warnings and errors on and off locally, depending * on version. -- cgit v1.2.3 From 5de0ce85f5a4d2883eae6f48eb015bc5dfbd91e9 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Thu, 15 Sep 2022 17:03:42 +0200 Subject: kmsan: mark noinstr as __no_sanitize_memory noinstr functions should never be instrumented, so make KMSAN skip them by applying the __no_sanitize_memory attribute. Link: https://lkml.kernel.org/r/20220915150417.722975-9-glider@google.com Signed-off-by: Alexander Potapenko Reviewed-by: Marco Elver Cc: Alexander Viro Cc: Alexei Starovoitov Cc: Andrey Konovalov Cc: Andrey Konovalov Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Christoph Hellwig Cc: Christoph Lameter Cc: David Rientjes Cc: Dmitry Vyukov Cc: Eric Biggers Cc: Eric Biggers Cc: Eric Dumazet Cc: Greg Kroah-Hartman Cc: Herbert Xu Cc: Ilya Leoshkevich Cc: Ingo Molnar Cc: Jens Axboe Cc: Joonsoo Kim Cc: Kees Cook Cc: Mark Rutland Cc: Matthew Wilcox Cc: Michael S. Tsirkin Cc: Pekka Enberg Cc: Peter Zijlstra Cc: Petr Mladek Cc: Stephen Rothwell Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Vegard Nossum Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/compiler_types.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 4f2a819fd60a..015207a6e2bf 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -229,7 +229,8 @@ struct ftrace_likely_data { /* Section for code which can't be instrumented at all */ #define noinstr \ noinline notrace __attribute((__section__(".noinstr.text"))) \ - __no_kcsan __no_sanitize_address __no_profile __no_sanitize_coverage + __no_kcsan __no_sanitize_address __no_profile __no_sanitize_coverage \ + __no_sanitize_memory #endif /* __KERNEL__ */ -- cgit v1.2.3 From f80be4571b19b9fd8dd1528cd2a2f123aff51f70 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Thu, 15 Sep 2022 17:03:45 +0200 Subject: kmsan: add KMSAN runtime core MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit For each memory location KernelMemorySanitizer maintains two types of metadata: 1. The so-called shadow of that location - а byte:byte mapping describing whether or not individual bits of memory are initialized (shadow is 0) or not (shadow is 1). 2. The origins of that location - а 4-byte:4-byte mapping containing 4-byte IDs of the stack traces where uninitialized values were created. Each struct page now contains pointers to two struct pages holding KMSAN metadata (shadow and origins) for the original struct page. Utility routines in mm/kmsan/core.c and mm/kmsan/shadow.c handle the metadata creation, addressing, copying and checking. mm/kmsan/report.c performs error reporting in the cases an uninitialized value is used in a way that leads to undefined behavior. KMSAN compiler instrumentation is responsible for tracking the metadata along with the kernel memory. mm/kmsan/instrumentation.c provides the implementation for instrumentation hooks that are called from files compiled with -fsanitize=kernel-memory. To aid parameter passing (also done at instrumentation level), each task_struct now contains a struct kmsan_task_state used to track the metadata of function parameters and return values for that task. Finally, this patch provides CONFIG_KMSAN that enables KMSAN, and declares CFLAGS_KMSAN, which are applied to files compiled with KMSAN. The KMSAN_SANITIZE:=n Makefile directive can be used to completely disable KMSAN instrumentation for certain files. Similarly, KMSAN_ENABLE_CHECKS:=n disables KMSAN checks and makes newly created stack memory initialized. Users can also use functions from include/linux/kmsan-checks.h to mark certain memory regions as uninitialized or initialized (this is called "poisoning" and "unpoisoning") or check that a particular region is initialized. Link: https://lkml.kernel.org/r/20220915150417.722975-12-glider@google.com Signed-off-by: Alexander Potapenko Acked-by: Marco Elver Cc: Alexander Viro Cc: Alexei Starovoitov Cc: Andrey Konovalov Cc: Andrey Konovalov Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Christoph Hellwig Cc: Christoph Lameter Cc: David Rientjes Cc: Dmitry Vyukov Cc: Eric Biggers Cc: Eric Biggers Cc: Eric Dumazet Cc: Greg Kroah-Hartman Cc: Herbert Xu Cc: Ilya Leoshkevich Cc: Ingo Molnar Cc: Jens Axboe Cc: Joonsoo Kim Cc: Kees Cook Cc: Mark Rutland Cc: Matthew Wilcox Cc: Michael S. Tsirkin Cc: Pekka Enberg Cc: Peter Zijlstra Cc: Petr Mladek Cc: Stephen Rothwell Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Vegard Nossum Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/kmsan-checks.h | 64 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/kmsan_types.h | 35 ++++++++++++++++++++++++ include/linux/mm_types.h | 12 +++++++++ include/linux/sched.h | 5 ++++ 4 files changed, 116 insertions(+) create mode 100644 include/linux/kmsan-checks.h create mode 100644 include/linux/kmsan_types.h (limited to 'include/linux') diff --git a/include/linux/kmsan-checks.h b/include/linux/kmsan-checks.h new file mode 100644 index 000000000000..a6522a0c28df --- /dev/null +++ b/include/linux/kmsan-checks.h @@ -0,0 +1,64 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * KMSAN checks to be used for one-off annotations in subsystems. + * + * Copyright (C) 2017-2022 Google LLC + * Author: Alexander Potapenko + * + */ + +#ifndef _LINUX_KMSAN_CHECKS_H +#define _LINUX_KMSAN_CHECKS_H + +#include + +#ifdef CONFIG_KMSAN + +/** + * kmsan_poison_memory() - Mark the memory range as uninitialized. + * @address: address to start with. + * @size: size of buffer to poison. + * @flags: GFP flags for allocations done by this function. + * + * Until other data is written to this range, KMSAN will treat it as + * uninitialized. Error reports for this memory will reference the call site of + * kmsan_poison_memory() as origin. + */ +void kmsan_poison_memory(const void *address, size_t size, gfp_t flags); + +/** + * kmsan_unpoison_memory() - Mark the memory range as initialized. + * @address: address to start with. + * @size: size of buffer to unpoison. + * + * Until other data is written to this range, KMSAN will treat it as + * initialized. + */ +void kmsan_unpoison_memory(const void *address, size_t size); + +/** + * kmsan_check_memory() - Check the memory range for being initialized. + * @address: address to start with. + * @size: size of buffer to check. + * + * If any piece of the given range is marked as uninitialized, KMSAN will report + * an error. + */ +void kmsan_check_memory(const void *address, size_t size); + +#else + +static inline void kmsan_poison_memory(const void *address, size_t size, + gfp_t flags) +{ +} +static inline void kmsan_unpoison_memory(const void *address, size_t size) +{ +} +static inline void kmsan_check_memory(const void *address, size_t size) +{ +} + +#endif + +#endif /* _LINUX_KMSAN_CHECKS_H */ diff --git a/include/linux/kmsan_types.h b/include/linux/kmsan_types.h new file mode 100644 index 000000000000..8bfa6c98176d --- /dev/null +++ b/include/linux/kmsan_types.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * A minimal header declaring types added by KMSAN to existing kernel structs. + * + * Copyright (C) 2017-2022 Google LLC + * Author: Alexander Potapenko + * + */ +#ifndef _LINUX_KMSAN_TYPES_H +#define _LINUX_KMSAN_TYPES_H + +/* These constants are defined in the MSan LLVM instrumentation pass. */ +#define KMSAN_RETVAL_SIZE 800 +#define KMSAN_PARAM_SIZE 800 + +struct kmsan_context_state { + char param_tls[KMSAN_PARAM_SIZE]; + char retval_tls[KMSAN_RETVAL_SIZE]; + char va_arg_tls[KMSAN_PARAM_SIZE]; + char va_arg_origin_tls[KMSAN_PARAM_SIZE]; + u64 va_arg_overflow_size_tls; + char param_origin_tls[KMSAN_PARAM_SIZE]; + u32 retval_origin_tls; +}; + +#undef KMSAN_PARAM_SIZE +#undef KMSAN_RETVAL_SIZE + +struct kmsan_ctx { + struct kmsan_context_state cstate; + int kmsan_in_runtime; + bool allow_reporting; +}; + +#endif /* _LINUX_KMSAN_TYPES_H */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 5c87d0f292a2..500e536796ca 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -224,6 +224,18 @@ struct page { not kmapped, ie. highmem) */ #endif /* WANT_PAGE_VIRTUAL */ +#ifdef CONFIG_KMSAN + /* + * KMSAN metadata for this page: + * - shadow page: every bit indicates whether the corresponding + * bit of the original page is initialized (0) or not (1); + * - origin page: every 4 bytes contain an id of the stack trace + * where the uninitialized value was created. + */ + struct page *kmsan_shadow; + struct page *kmsan_origin; +#endif + #ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS int _last_cpupid; #endif diff --git a/include/linux/sched.h b/include/linux/sched.h index fbac3c19fe35..88a043f7235e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -1362,6 +1363,10 @@ struct task_struct { #endif #endif +#ifdef CONFIG_KMSAN + struct kmsan_ctx kmsan_ctx; +#endif + #if IS_ENABLED(CONFIG_KUNIT) struct kunit *kunit_test; #endif -- cgit v1.2.3 From b073d7f8aee4ebf05d10e3380df377b73120cf16 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Thu, 15 Sep 2022 17:03:48 +0200 Subject: mm: kmsan: maintain KMSAN metadata for page operations Insert KMSAN hooks that make the necessary bookkeeping changes: - poison page shadow and origins in alloc_pages()/free_page(); - clear page shadow and origins in clear_page(), copy_user_highpage(); - copy page metadata in copy_highpage(), wp_page_copy(); - handle vmap()/vunmap()/iounmap(); Link: https://lkml.kernel.org/r/20220915150417.722975-15-glider@google.com Signed-off-by: Alexander Potapenko Cc: Alexander Viro Cc: Alexei Starovoitov Cc: Andrey Konovalov Cc: Andrey Konovalov Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Christoph Hellwig Cc: Christoph Lameter Cc: David Rientjes Cc: Dmitry Vyukov Cc: Eric Biggers Cc: Eric Biggers Cc: Eric Dumazet Cc: Greg Kroah-Hartman Cc: Herbert Xu Cc: Ilya Leoshkevich Cc: Ingo Molnar Cc: Jens Axboe Cc: Joonsoo Kim Cc: Kees Cook Cc: Marco Elver Cc: Mark Rutland Cc: Matthew Wilcox Cc: Michael S. Tsirkin Cc: Pekka Enberg Cc: Peter Zijlstra Cc: Petr Mladek Cc: Stephen Rothwell Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Vegard Nossum Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/highmem.h | 3 + include/linux/kmsan.h | 145 ++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 148 insertions(+) create mode 100644 include/linux/kmsan.h (limited to 'include/linux') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 25679035ca28..e9912da5441b 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -6,6 +6,7 @@ #include #include #include +#include #include #include #include @@ -311,6 +312,7 @@ static inline void copy_user_highpage(struct page *to, struct page *from, vfrom = kmap_local_page(from); vto = kmap_local_page(to); copy_user_page(vto, vfrom, vaddr, to); + kmsan_unpoison_memory(page_address(to), PAGE_SIZE); kunmap_local(vto); kunmap_local(vfrom); } @@ -326,6 +328,7 @@ static inline void copy_highpage(struct page *to, struct page *from) vfrom = kmap_local_page(from); vto = kmap_local_page(to); copy_page(vto, vfrom); + kmsan_copy_page_meta(to, from); kunmap_local(vto); kunmap_local(vfrom); } diff --git a/include/linux/kmsan.h b/include/linux/kmsan.h new file mode 100644 index 000000000000..b36bf3db835e --- /dev/null +++ b/include/linux/kmsan.h @@ -0,0 +1,145 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * KMSAN API for subsystems. + * + * Copyright (C) 2017-2022 Google LLC + * Author: Alexander Potapenko + * + */ +#ifndef _LINUX_KMSAN_H +#define _LINUX_KMSAN_H + +#include +#include +#include + +struct page; + +#ifdef CONFIG_KMSAN + +/** + * kmsan_alloc_page() - Notify KMSAN about an alloc_pages() call. + * @page: struct page pointer returned by alloc_pages(). + * @order: order of allocated struct page. + * @flags: GFP flags used by alloc_pages() + * + * KMSAN marks 1<<@order pages starting at @page as uninitialized, unless + * @flags contain __GFP_ZERO. + */ +void kmsan_alloc_page(struct page *page, unsigned int order, gfp_t flags); + +/** + * kmsan_free_page() - Notify KMSAN about a free_pages() call. + * @page: struct page pointer passed to free_pages(). + * @order: order of deallocated struct page. + * + * KMSAN marks freed memory as uninitialized. + */ +void kmsan_free_page(struct page *page, unsigned int order); + +/** + * kmsan_copy_page_meta() - Copy KMSAN metadata between two pages. + * @dst: destination page. + * @src: source page. + * + * KMSAN copies the contents of metadata pages for @src into the metadata pages + * for @dst. If @dst has no associated metadata pages, nothing happens. + * If @src has no associated metadata pages, @dst metadata pages are unpoisoned. + */ +void kmsan_copy_page_meta(struct page *dst, struct page *src); + +/** + * kmsan_map_kernel_range_noflush() - Notify KMSAN about a vmap. + * @start: start of vmapped range. + * @end: end of vmapped range. + * @prot: page protection flags used for vmap. + * @pages: array of pages. + * @page_shift: page_shift passed to vmap_range_noflush(). + * + * KMSAN maps shadow and origin pages of @pages into contiguous ranges in + * vmalloc metadata address range. + */ +void kmsan_vmap_pages_range_noflush(unsigned long start, unsigned long end, + pgprot_t prot, struct page **pages, + unsigned int page_shift); + +/** + * kmsan_vunmap_kernel_range_noflush() - Notify KMSAN about a vunmap. + * @start: start of vunmapped range. + * @end: end of vunmapped range. + * + * KMSAN unmaps the contiguous metadata ranges created by + * kmsan_map_kernel_range_noflush(). + */ +void kmsan_vunmap_range_noflush(unsigned long start, unsigned long end); + +/** + * kmsan_ioremap_page_range() - Notify KMSAN about a ioremap_page_range() call. + * @addr: range start. + * @end: range end. + * @phys_addr: physical range start. + * @prot: page protection flags used for ioremap_page_range(). + * @page_shift: page_shift argument passed to vmap_range_noflush(). + * + * KMSAN creates new metadata pages for the physical pages mapped into the + * virtual memory. + */ +void kmsan_ioremap_page_range(unsigned long addr, unsigned long end, + phys_addr_t phys_addr, pgprot_t prot, + unsigned int page_shift); + +/** + * kmsan_iounmap_page_range() - Notify KMSAN about a iounmap_page_range() call. + * @start: range start. + * @end: range end. + * + * KMSAN unmaps the metadata pages for the given range and, unlike for + * vunmap_page_range(), also deallocates them. + */ +void kmsan_iounmap_page_range(unsigned long start, unsigned long end); + +#else + +static inline int kmsan_alloc_page(struct page *page, unsigned int order, + gfp_t flags) +{ + return 0; +} + +static inline void kmsan_free_page(struct page *page, unsigned int order) +{ +} + +static inline void kmsan_copy_page_meta(struct page *dst, struct page *src) +{ +} + +static inline void kmsan_vmap_pages_range_noflush(unsigned long start, + unsigned long end, + pgprot_t prot, + struct page **pages, + unsigned int page_shift) +{ +} + +static inline void kmsan_vunmap_range_noflush(unsigned long start, + unsigned long end) +{ +} + +static inline void kmsan_ioremap_page_range(unsigned long start, + unsigned long end, + phys_addr_t phys_addr, + pgprot_t prot, + unsigned int page_shift) +{ +} + +static inline void kmsan_iounmap_page_range(unsigned long start, + unsigned long end) +{ +} + +#endif + +#endif /* _LINUX_KMSAN_H */ -- cgit v1.2.3 From 68ef169a1dd20df5cfa5a161b7304ad9fdd14c36 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Thu, 15 Sep 2022 17:03:49 +0200 Subject: mm: kmsan: call KMSAN hooks from SLUB code In order to report uninitialized memory coming from heap allocations KMSAN has to poison them unless they're created with __GFP_ZERO. It's handy that we need KMSAN hooks in the places where init_on_alloc/init_on_free initialization is performed. In addition, we apply __no_kmsan_checks to get_freepointer_safe() to suppress reports when accessing freelist pointers that reside in freed objects. Link: https://lkml.kernel.org/r/20220915150417.722975-16-glider@google.com Signed-off-by: Alexander Potapenko Reviewed-by: Marco Elver Cc: Alexander Viro Cc: Alexei Starovoitov Cc: Andrey Konovalov Cc: Andrey Konovalov Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Christoph Hellwig Cc: Christoph Lameter Cc: David Rientjes Cc: Dmitry Vyukov Cc: Eric Biggers Cc: Eric Biggers Cc: Eric Dumazet Cc: Greg Kroah-Hartman Cc: Herbert Xu Cc: Ilya Leoshkevich Cc: Ingo Molnar Cc: Jens Axboe Cc: Joonsoo Kim Cc: Kees Cook Cc: Mark Rutland Cc: Matthew Wilcox Cc: Michael S. Tsirkin Cc: Pekka Enberg Cc: Peter Zijlstra Cc: Petr Mladek Cc: Stephen Rothwell Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Vegard Nossum Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/kmsan.h | 57 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 57 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kmsan.h b/include/linux/kmsan.h index b36bf3db835e..5c4e0079054e 100644 --- a/include/linux/kmsan.h +++ b/include/linux/kmsan.h @@ -14,6 +14,7 @@ #include struct page; +struct kmem_cache; #ifdef CONFIG_KMSAN @@ -48,6 +49,44 @@ void kmsan_free_page(struct page *page, unsigned int order); */ void kmsan_copy_page_meta(struct page *dst, struct page *src); +/** + * kmsan_slab_alloc() - Notify KMSAN about a slab allocation. + * @s: slab cache the object belongs to. + * @object: object pointer. + * @flags: GFP flags passed to the allocator. + * + * Depending on cache flags and GFP flags, KMSAN sets up the metadata of the + * newly created object, marking it as initialized or uninitialized. + */ +void kmsan_slab_alloc(struct kmem_cache *s, void *object, gfp_t flags); + +/** + * kmsan_slab_free() - Notify KMSAN about a slab deallocation. + * @s: slab cache the object belongs to. + * @object: object pointer. + * + * KMSAN marks the freed object as uninitialized. + */ +void kmsan_slab_free(struct kmem_cache *s, void *object); + +/** + * kmsan_kmalloc_large() - Notify KMSAN about a large slab allocation. + * @ptr: object pointer. + * @size: object size. + * @flags: GFP flags passed to the allocator. + * + * Similar to kmsan_slab_alloc(), but for large allocations. + */ +void kmsan_kmalloc_large(const void *ptr, size_t size, gfp_t flags); + +/** + * kmsan_kfree_large() - Notify KMSAN about a large slab deallocation. + * @ptr: object pointer. + * + * Similar to kmsan_slab_free(), but for large allocations. + */ +void kmsan_kfree_large(const void *ptr); + /** * kmsan_map_kernel_range_noflush() - Notify KMSAN about a vmap. * @start: start of vmapped range. @@ -114,6 +153,24 @@ static inline void kmsan_copy_page_meta(struct page *dst, struct page *src) { } +static inline void kmsan_slab_alloc(struct kmem_cache *s, void *object, + gfp_t flags) +{ +} + +static inline void kmsan_slab_free(struct kmem_cache *s, void *object) +{ +} + +static inline void kmsan_kmalloc_large(const void *ptr, size_t size, + gfp_t flags) +{ +} + +static inline void kmsan_kfree_large(const void *ptr) +{ +} + static inline void kmsan_vmap_pages_range_noflush(unsigned long start, unsigned long end, pgprot_t prot, -- cgit v1.2.3 From 50b5e49ca694a60f84a2a12d62b6cb6ec8e3649f Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Thu, 15 Sep 2022 17:03:50 +0200 Subject: kmsan: handle task creation and exiting Tell KMSAN that a new task is created, so the tool creates a backing metadata structure for that task. Link: https://lkml.kernel.org/r/20220915150417.722975-17-glider@google.com Signed-off-by: Alexander Potapenko Cc: Alexander Viro Cc: Alexei Starovoitov Cc: Andrey Konovalov Cc: Andrey Konovalov Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Christoph Hellwig Cc: Christoph Lameter Cc: David Rientjes Cc: Dmitry Vyukov Cc: Eric Biggers Cc: Eric Biggers Cc: Eric Dumazet Cc: Greg Kroah-Hartman Cc: Herbert Xu Cc: Ilya Leoshkevich Cc: Ingo Molnar Cc: Jens Axboe Cc: Joonsoo Kim Cc: Kees Cook Cc: Marco Elver Cc: Mark Rutland Cc: Matthew Wilcox Cc: Michael S. Tsirkin Cc: Pekka Enberg Cc: Peter Zijlstra Cc: Petr Mladek Cc: Stephen Rothwell Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Vegard Nossum Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/kmsan.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kmsan.h b/include/linux/kmsan.h index 5c4e0079054e..354aee6f7b1a 100644 --- a/include/linux/kmsan.h +++ b/include/linux/kmsan.h @@ -15,9 +15,22 @@ struct page; struct kmem_cache; +struct task_struct; #ifdef CONFIG_KMSAN +/** + * kmsan_task_create() - Initialize KMSAN state for the task. + * @task: task to initialize. + */ +void kmsan_task_create(struct task_struct *task); + +/** + * kmsan_task_exit() - Notify KMSAN that a task has exited. + * @task: task about to finish. + */ +void kmsan_task_exit(struct task_struct *task); + /** * kmsan_alloc_page() - Notify KMSAN about an alloc_pages() call. * @page: struct page pointer returned by alloc_pages(). @@ -139,6 +152,14 @@ void kmsan_iounmap_page_range(unsigned long start, unsigned long end); #else +static inline void kmsan_task_create(struct task_struct *task) +{ +} + +static inline void kmsan_task_exit(struct task_struct *task) +{ +} + static inline int kmsan_alloc_page(struct page *page, unsigned int order, gfp_t flags) { -- cgit v1.2.3 From 3c206509826094e85ead0b056f484db96829248d Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Thu, 15 Sep 2022 17:03:51 +0200 Subject: init: kmsan: call KMSAN initialization routines kmsan_init_shadow() scans the mappings created at boot time and creates metadata pages for those mappings. When the memblock allocator returns pages to pagealloc, we reserve 2/3 of those pages and use them as metadata for the remaining 1/3. Once KMSAN starts, every page allocated by pagealloc has its associated shadow and origin pages. kmsan_initialize() initializes the bookkeeping for init_task and enables KMSAN. Link: https://lkml.kernel.org/r/20220915150417.722975-18-glider@google.com Signed-off-by: Alexander Potapenko Cc: Alexander Viro Cc: Alexei Starovoitov Cc: Andrey Konovalov Cc: Andrey Konovalov Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Christoph Hellwig Cc: Christoph Lameter Cc: David Rientjes Cc: Dmitry Vyukov Cc: Eric Biggers Cc: Eric Biggers Cc: Eric Dumazet Cc: Greg Kroah-Hartman Cc: Herbert Xu Cc: Ilya Leoshkevich Cc: Ingo Molnar Cc: Jens Axboe Cc: Joonsoo Kim Cc: Kees Cook Cc: Marco Elver Cc: Mark Rutland Cc: Matthew Wilcox Cc: Michael S. Tsirkin Cc: Pekka Enberg Cc: Peter Zijlstra Cc: Petr Mladek Cc: Stephen Rothwell Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Vegard Nossum Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/kmsan.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kmsan.h b/include/linux/kmsan.h index 354aee6f7b1a..e00de976ee43 100644 --- a/include/linux/kmsan.h +++ b/include/linux/kmsan.h @@ -31,6 +31,28 @@ void kmsan_task_create(struct task_struct *task); */ void kmsan_task_exit(struct task_struct *task); +/** + * kmsan_init_shadow() - Initialize KMSAN shadow at boot time. + * + * Allocate and initialize KMSAN metadata for early allocations. + */ +void __init kmsan_init_shadow(void); + +/** + * kmsan_init_runtime() - Initialize KMSAN state and enable KMSAN. + */ +void __init kmsan_init_runtime(void); + +/** + * kmsan_memblock_free_pages() - handle freeing of memblock pages. + * @page: struct page to free. + * @order: order of @page. + * + * Freed pages are either returned to buddy allocator or held back to be used + * as metadata pages. + */ +bool __init kmsan_memblock_free_pages(struct page *page, unsigned int order); + /** * kmsan_alloc_page() - Notify KMSAN about an alloc_pages() call. * @page: struct page pointer returned by alloc_pages(). @@ -152,6 +174,20 @@ void kmsan_iounmap_page_range(unsigned long start, unsigned long end); #else +static inline void kmsan_init_shadow(void) +{ +} + +static inline void kmsan_init_runtime(void) +{ +} + +static inline bool kmsan_memblock_free_pages(struct page *page, + unsigned int order) +{ + return true; +} + static inline void kmsan_task_create(struct task_struct *task) { } -- cgit v1.2.3 From 75cf0290271bf6dae9dee982aef15242dadf97e4 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Thu, 15 Sep 2022 17:03:52 +0200 Subject: instrumented.h: add KMSAN support To avoid false positives, KMSAN needs to unpoison the data copied from the userspace. To detect infoleaks - check the memory buffer passed to copy_to_user(). Link: https://lkml.kernel.org/r/20220915150417.722975-19-glider@google.com Signed-off-by: Alexander Potapenko Reviewed-by: Marco Elver Cc: Alexander Viro Cc: Alexei Starovoitov Cc: Andrey Konovalov Cc: Andrey Konovalov Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Christoph Hellwig Cc: Christoph Lameter Cc: David Rientjes Cc: Dmitry Vyukov Cc: Eric Biggers Cc: Eric Biggers Cc: Eric Dumazet Cc: Greg Kroah-Hartman Cc: Herbert Xu Cc: Ilya Leoshkevich Cc: Ingo Molnar Cc: Jens Axboe Cc: Joonsoo Kim Cc: Kees Cook Cc: Mark Rutland Cc: Matthew Wilcox Cc: Michael S. Tsirkin Cc: Pekka Enberg Cc: Peter Zijlstra Cc: Petr Mladek Cc: Stephen Rothwell Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Vegard Nossum Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/instrumented.h | 18 +++++++++++++----- include/linux/kmsan-checks.h | 19 +++++++++++++++++++ 2 files changed, 32 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/instrumented.h b/include/linux/instrumented.h index 9f1dba8f717b..501fa8486749 100644 --- a/include/linux/instrumented.h +++ b/include/linux/instrumented.h @@ -2,7 +2,7 @@ /* * This header provides generic wrappers for memory access instrumentation that - * the compiler cannot emit for: KASAN, KCSAN. + * the compiler cannot emit for: KASAN, KCSAN, KMSAN. */ #ifndef _LINUX_INSTRUMENTED_H #define _LINUX_INSTRUMENTED_H @@ -10,6 +10,7 @@ #include #include #include +#include #include /** @@ -117,6 +118,7 @@ instrument_copy_to_user(void __user *to, const void *from, unsigned long n) { kasan_check_read(from, n); kcsan_check_read(from, n); + kmsan_copy_to_user(to, from, n, 0); } /** @@ -151,6 +153,7 @@ static __always_inline void instrument_copy_from_user_after(const void *to, const void __user *from, unsigned long n, unsigned long left) { + kmsan_unpoison_memory(to, n - left); } /** @@ -162,10 +165,14 @@ instrument_copy_from_user_after(const void *to, const void __user *from, * * @to destination variable, may not be address-taken */ -#define instrument_get_user(to) \ -({ \ +#define instrument_get_user(to) \ +({ \ + u64 __tmp = (u64)(to); \ + kmsan_unpoison_memory(&__tmp, sizeof(__tmp)); \ + to = __tmp; \ }) + /** * instrument_put_user() - add instrumentation to put_user()-like macros * @@ -177,8 +184,9 @@ instrument_copy_from_user_after(const void *to, const void __user *from, * @ptr userspace pointer to copy to * @size number of bytes to copy */ -#define instrument_put_user(from, ptr, size) \ -({ \ +#define instrument_put_user(from, ptr, size) \ +({ \ + kmsan_copy_to_user(ptr, &from, sizeof(from), 0); \ }) #endif /* _LINUX_INSTRUMENTED_H */ diff --git a/include/linux/kmsan-checks.h b/include/linux/kmsan-checks.h index a6522a0c28df..c4cae333deec 100644 --- a/include/linux/kmsan-checks.h +++ b/include/linux/kmsan-checks.h @@ -46,6 +46,21 @@ void kmsan_unpoison_memory(const void *address, size_t size); */ void kmsan_check_memory(const void *address, size_t size); +/** + * kmsan_copy_to_user() - Notify KMSAN about a data transfer to userspace. + * @to: destination address in the userspace. + * @from: source address in the kernel. + * @to_copy: number of bytes to copy. + * @left: number of bytes not copied. + * + * If this is a real userspace data transfer, KMSAN checks the bytes that were + * actually copied to ensure there was no information leak. If @to belongs to + * the kernel space (which is possible for compat syscalls), KMSAN just copies + * the metadata. + */ +void kmsan_copy_to_user(void __user *to, const void *from, size_t to_copy, + size_t left); + #else static inline void kmsan_poison_memory(const void *address, size_t size, @@ -58,6 +73,10 @@ static inline void kmsan_unpoison_memory(const void *address, size_t size) static inline void kmsan_check_memory(const void *address, size_t size) { } +static inline void kmsan_copy_to_user(void __user *to, const void *from, + size_t to_copy, size_t left) +{ +} #endif -- cgit v1.2.3 From 7ade4f10779cb46f5c29ced9b7a41f68501cf0ed Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Thu, 15 Sep 2022 17:03:55 +0200 Subject: dma: kmsan: unpoison DMA mappings KMSAN doesn't know about DMA memory writes performed by devices. We unpoison such memory when it's mapped to avoid false positive reports. Link: https://lkml.kernel.org/r/20220915150417.722975-22-glider@google.com Signed-off-by: Alexander Potapenko Cc: Alexander Viro Cc: Alexei Starovoitov Cc: Andrey Konovalov Cc: Andrey Konovalov Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Christoph Hellwig Cc: Christoph Lameter Cc: David Rientjes Cc: Dmitry Vyukov Cc: Eric Biggers Cc: Eric Biggers Cc: Eric Dumazet Cc: Greg Kroah-Hartman Cc: Herbert Xu Cc: Ilya Leoshkevich Cc: Ingo Molnar Cc: Jens Axboe Cc: Joonsoo Kim Cc: Kees Cook Cc: Marco Elver Cc: Mark Rutland Cc: Matthew Wilcox Cc: Michael S. Tsirkin Cc: Pekka Enberg Cc: Peter Zijlstra Cc: Petr Mladek Cc: Stephen Rothwell Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Vegard Nossum Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/kmsan.h | 41 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kmsan.h b/include/linux/kmsan.h index e00de976ee43..dac296da45c5 100644 --- a/include/linux/kmsan.h +++ b/include/linux/kmsan.h @@ -9,6 +9,7 @@ #ifndef _LINUX_KMSAN_H #define _LINUX_KMSAN_H +#include #include #include #include @@ -16,6 +17,7 @@ struct page; struct kmem_cache; struct task_struct; +struct scatterlist; #ifdef CONFIG_KMSAN @@ -172,6 +174,35 @@ void kmsan_ioremap_page_range(unsigned long addr, unsigned long end, */ void kmsan_iounmap_page_range(unsigned long start, unsigned long end); +/** + * kmsan_handle_dma() - Handle a DMA data transfer. + * @page: first page of the buffer. + * @offset: offset of the buffer within the first page. + * @size: buffer size. + * @dir: one of possible dma_data_direction values. + * + * Depending on @direction, KMSAN: + * * checks the buffer, if it is copied to device; + * * initializes the buffer, if it is copied from device; + * * does both, if this is a DMA_BIDIRECTIONAL transfer. + */ +void kmsan_handle_dma(struct page *page, size_t offset, size_t size, + enum dma_data_direction dir); + +/** + * kmsan_handle_dma_sg() - Handle a DMA transfer using scatterlist. + * @sg: scatterlist holding DMA buffers. + * @nents: number of scatterlist entries. + * @dir: one of possible dma_data_direction values. + * + * Depending on @direction, KMSAN: + * * checks the buffers in the scatterlist, if they are copied to device; + * * initializes the buffers, if they are copied from device; + * * does both, if this is a DMA_BIDIRECTIONAL transfer. + */ +void kmsan_handle_dma_sg(struct scatterlist *sg, int nents, + enum dma_data_direction dir); + #else static inline void kmsan_init_shadow(void) @@ -254,6 +285,16 @@ static inline void kmsan_iounmap_page_range(unsigned long start, { } +static inline void kmsan_handle_dma(struct page *page, size_t offset, + size_t size, enum dma_data_direction dir) +{ +} + +static inline void kmsan_handle_dma_sg(struct scatterlist *sg, int nents, + enum dma_data_direction dir) +{ +} + #endif #endif /* _LINUX_KMSAN_H */ -- cgit v1.2.3 From 553a80188a5d7164d2b0688b06bf3fe297023bfe Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Thu, 15 Sep 2022 17:03:57 +0200 Subject: kmsan: handle memory sent to/from USB Depending on the value of is_out kmsan_handle_urb() KMSAN either marks the data copied to the kernel from a USB device as initialized, or checks the data sent to the device for being initialized. Link: https://lkml.kernel.org/r/20220915150417.722975-24-glider@google.com Signed-off-by: Alexander Potapenko Cc: Alexander Viro Cc: Alexei Starovoitov Cc: Andrey Konovalov Cc: Andrey Konovalov Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Christoph Hellwig Cc: Christoph Lameter Cc: David Rientjes Cc: Dmitry Vyukov Cc: Eric Biggers Cc: Eric Biggers Cc: Eric Dumazet Cc: Greg Kroah-Hartman Cc: Herbert Xu Cc: Ilya Leoshkevich Cc: Ingo Molnar Cc: Jens Axboe Cc: Joonsoo Kim Cc: Kees Cook Cc: Marco Elver Cc: Mark Rutland Cc: Matthew Wilcox Cc: Michael S. Tsirkin Cc: Pekka Enberg Cc: Peter Zijlstra Cc: Petr Mladek Cc: Stephen Rothwell Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Vegard Nossum Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/kmsan.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kmsan.h b/include/linux/kmsan.h index dac296da45c5..c473e0e21683 100644 --- a/include/linux/kmsan.h +++ b/include/linux/kmsan.h @@ -18,6 +18,7 @@ struct page; struct kmem_cache; struct task_struct; struct scatterlist; +struct urb; #ifdef CONFIG_KMSAN @@ -203,6 +204,16 @@ void kmsan_handle_dma(struct page *page, size_t offset, size_t size, void kmsan_handle_dma_sg(struct scatterlist *sg, int nents, enum dma_data_direction dir); +/** + * kmsan_handle_urb() - Handle a USB data transfer. + * @urb: struct urb pointer. + * @is_out: data transfer direction (true means output to hardware). + * + * If @is_out is true, KMSAN checks the transfer buffer of @urb. Otherwise, + * KMSAN initializes the transfer buffer. + */ +void kmsan_handle_urb(const struct urb *urb, bool is_out); + #else static inline void kmsan_init_shadow(void) @@ -295,6 +306,10 @@ static inline void kmsan_handle_dma_sg(struct scatterlist *sg, int nents, { } +static inline void kmsan_handle_urb(const struct urb *urb, bool is_out) +{ +} + #endif #endif /* _LINUX_KMSAN_H */ -- cgit v1.2.3 From ff901d80fff6d65ada6f2a60a1f7d180ee2e0416 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Thu, 15 Sep 2022 17:04:09 +0200 Subject: x86: kmsan: use __msan_ string functions where possible. Unless stated otherwise (by explicitly calling __memcpy(), __memset() or __memmove()) we want all string functions to call their __msan_ versions (e.g. __msan_memcpy() instead of memcpy()), so that shadow and origin values are updated accordingly. Bootloader must still use the default string functions to avoid crashes. Link: https://lkml.kernel.org/r/20220915150417.722975-36-glider@google.com Signed-off-by: Alexander Potapenko Cc: Alexander Viro Cc: Alexei Starovoitov Cc: Andrey Konovalov Cc: Andrey Konovalov Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Christoph Hellwig Cc: Christoph Lameter Cc: David Rientjes Cc: Dmitry Vyukov Cc: Eric Biggers Cc: Eric Biggers Cc: Eric Dumazet Cc: Greg Kroah-Hartman Cc: Herbert Xu Cc: Ilya Leoshkevich Cc: Ingo Molnar Cc: Jens Axboe Cc: Joonsoo Kim Cc: Kees Cook Cc: Marco Elver Cc: Mark Rutland Cc: Matthew Wilcox Cc: Michael S. Tsirkin Cc: Pekka Enberg Cc: Peter Zijlstra Cc: Petr Mladek Cc: Stephen Rothwell Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Vegard Nossum Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/fortify-string.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index 3b401fa0f374..6c8a1a29d0b6 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -285,8 +285,10 @@ __FORTIFY_INLINE void fortify_memset_chk(__kernel_size_t size, * __builtin_object_size() must be captured here to avoid evaluating argument * side-effects further into the macro layers. */ +#ifndef CONFIG_KMSAN #define memset(p, c, s) __fortify_memset_chk(p, c, s, \ __builtin_object_size(p, 0), __builtin_object_size(p, 1)) +#endif /* * To make sure the compiler can enforce protection against buffer overflows, -- cgit v1.2.3 From 6cae637fa26df867449c6bc20ea8bc693abe49b0 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Thu, 15 Sep 2022 17:04:14 +0200 Subject: entry: kmsan: introduce kmsan_unpoison_entry_regs() struct pt_regs passed into IRQ entry code is set up by uninstrumented asm functions, therefore KMSAN may not notice the registers are initialized. kmsan_unpoison_entry_regs() unpoisons the contents of struct pt_regs, preventing potential false positives. Unlike kmsan_unpoison_memory(), it can be called under kmsan_in_runtime(), which is often the case in IRQ entry code. Link: https://lkml.kernel.org/r/20220915150417.722975-41-glider@google.com Signed-off-by: Alexander Potapenko Cc: Alexander Viro Cc: Alexei Starovoitov Cc: Andrey Konovalov Cc: Andrey Konovalov Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Christoph Hellwig Cc: Christoph Lameter Cc: David Rientjes Cc: Dmitry Vyukov Cc: Eric Biggers Cc: Eric Biggers Cc: Eric Dumazet Cc: Greg Kroah-Hartman Cc: Herbert Xu Cc: Ilya Leoshkevich Cc: Ingo Molnar Cc: Jens Axboe Cc: Joonsoo Kim Cc: Kees Cook Cc: Marco Elver Cc: Mark Rutland Cc: Matthew Wilcox Cc: Michael S. Tsirkin Cc: Pekka Enberg Cc: Peter Zijlstra Cc: Petr Mladek Cc: Stephen Rothwell Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Vegard Nossum Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/kmsan.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kmsan.h b/include/linux/kmsan.h index c473e0e21683..e38ae3c34618 100644 --- a/include/linux/kmsan.h +++ b/include/linux/kmsan.h @@ -214,6 +214,17 @@ void kmsan_handle_dma_sg(struct scatterlist *sg, int nents, */ void kmsan_handle_urb(const struct urb *urb, bool is_out); +/** + * kmsan_unpoison_entry_regs() - Handle pt_regs in low-level entry code. + * @regs: struct pt_regs pointer received from assembly code. + * + * KMSAN unpoisons the contents of the passed pt_regs, preventing potential + * false positive reports. Unlike kmsan_unpoison_memory(), + * kmsan_unpoison_entry_regs() can be called from the regions where + * kmsan_in_runtime() returns true, which is the case in early entry code. + */ +void kmsan_unpoison_entry_regs(const struct pt_regs *regs); + #else static inline void kmsan_init_shadow(void) @@ -310,6 +321,10 @@ static inline void kmsan_handle_urb(const struct urb *urb, bool is_out) { } +static inline void kmsan_unpoison_entry_regs(const struct pt_regs *regs) +{ +} + #endif #endif /* _LINUX_KMSAN_H */ -- cgit v1.2.3 From 16bc1b0f0269b6110f6d25880b52947d354e2980 Mon Sep 17 00:00:00 2001 From: Kaixu Xia Date: Thu, 15 Sep 2022 19:33:41 +0800 Subject: mm/damon: use 'struct damon_target *' instead of 'void *' in target_valid() We could use 'struct damon_target *' directly instead of 'void *' in target_valid() operation to make code simple. Link: https://lkml.kernel.org/r/1663241621-13293-1-git-send-email-kaixuxia@tencent.com Signed-off-by: Kaixu Xia Reviewed-by: SeongJae Park Signed-off-by: Andrew Morton --- include/linux/damon.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index c5dc0c77c772..1dda8d0068e5 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -346,7 +346,7 @@ struct damon_operations { unsigned long (*apply_scheme)(struct damon_ctx *context, struct damon_target *t, struct damon_region *r, struct damos *scheme); - bool (*target_valid)(void *target); + bool (*target_valid)(struct damon_target *t); void (*cleanup)(struct damon_ctx *context); }; -- cgit v1.2.3 From cc713520bdc1b84fc5394f6ac8649b93ad2c5dde Mon Sep 17 00:00:00 2001 From: Kaixu Xia Date: Fri, 16 Sep 2022 23:20:35 +0800 Subject: mm/damon: return void from damon_set_schemes() There is no point in returning an int from damon_set_schemes(). It always returns 0 which is meaningless for the caller, so change it to return void directly. Link: https://lkml.kernel.org/r/1663341635-12675-1-git-send-email-kaixuxia@tencent.com Signed-off-by: Kaixu Xia Reviewed-by: SeongJae Park Reviewed-by: Muchun Song Signed-off-by: Andrew Morton --- include/linux/damon.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 1dda8d0068e5..e7808a84675f 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -541,7 +541,7 @@ unsigned int damon_nr_regions(struct damon_target *t); struct damon_ctx *damon_new_ctx(void); void damon_destroy_ctx(struct damon_ctx *ctx); int damon_set_attrs(struct damon_ctx *ctx, struct damon_attrs *attrs); -int damon_set_schemes(struct damon_ctx *ctx, +void damon_set_schemes(struct damon_ctx *ctx, struct damos **schemes, ssize_t nr_schemes); int damon_nr_running_ctxs(void); bool damon_is_registered_ops(enum damon_ops_id id); -- cgit v1.2.3 From 638a9ae97ab596f1f7b7522dad709e69cb5b4e9d Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Fri, 16 Sep 2022 15:22:44 +0800 Subject: mm: remove obsolete macro NR_PCP_ORDER_MASK and NR_PCP_ORDER_WIDTH Since commit 8b10b465d0e1 ("mm/page_alloc: free pages in a single pass during bulk free"), they're not used anymore. Remove them. Link: https://lkml.kernel.org/r/20220916072257.9639-4-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Reviewed-by: David Hildenbrand Reviewed-by: Anshuman Khandual Reviewed-by: Oscar Salvador Cc: Matthew Wilcox Signed-off-by: Andrew Morton --- include/linux/mmzone.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index c69c08156822..3ff1e757d5aa 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -564,13 +564,6 @@ enum zone_watermarks { #define NR_LOWORDER_PCP_LISTS (MIGRATE_PCPTYPES * (PAGE_ALLOC_COSTLY_ORDER + 1)) #define NR_PCP_LISTS (NR_LOWORDER_PCP_LISTS + NR_PCP_THP) -/* - * Shift to encode migratetype and order in the same integer, with order - * in the least significant bits. - */ -#define NR_PCP_ORDER_WIDTH 8 -#define NR_PCP_ORDER_MASK ((1<_watermark[WMARK_MIN] + z->watermark_boost) #define low_wmark_pages(z) (z->_watermark[WMARK_LOW] + z->watermark_boost) #define high_wmark_pages(z) (z->_watermark[WMARK_HIGH] + z->watermark_boost) -- cgit v1.2.3 From 5749fcc5f04cef4091dea0c2ba6b5c5f5e05a549 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Fri, 16 Sep 2022 15:22:46 +0800 Subject: mm/page_alloc: add __init annotations to init_mem_debugging_and_hardening() It's only called by mm_init(). Add __init annotations to it. Link: https://lkml.kernel.org/r/20220916072257.9639-6-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Reviewed-by: David Hildenbrand Reviewed-by: Anshuman Khandual Reviewed-by: Oscar Salvador Cc: Matthew Wilcox Signed-off-by: Andrew Morton --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index a37c8a29c49b..8bbcccbc5565 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3092,7 +3092,7 @@ extern int apply_to_existing_page_range(struct mm_struct *mm, unsigned long address, unsigned long size, pte_fn_t fn, void *data); -extern void init_mem_debugging_and_hardening(void); +extern void __init init_mem_debugging_and_hardening(void); #ifdef CONFIG_PAGE_POISONING extern void __kernel_poison_pages(struct page *page, int numpages); extern void __kernel_unpoison_pages(struct page *page, int numpages); -- cgit v1.2.3 From 30e3b5d7c82f78c63c53197b5d8b99636bb60d56 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Fri, 16 Sep 2022 15:22:48 +0800 Subject: mm: remove obsolete pgdat_is_empty() There's no caller. Remove it. Link: https://lkml.kernel.org/r/20220916072257.9639-8-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Reviewed-by: David Hildenbrand Reviewed-by: Anshuman Khandual Reviewed-by: Oscar Salvador Cc: Matthew Wilcox Signed-off-by: Andrew Morton --- include/linux/mmzone.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 3ff1e757d5aa..4c8510f26b02 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1241,11 +1241,6 @@ static inline unsigned long pgdat_end_pfn(pg_data_t *pgdat) return pgdat->node_start_pfn + pgdat->node_spanned_pages; } -static inline bool pgdat_is_empty(pg_data_t *pgdat) -{ - return !pgdat->node_start_pfn && !pgdat->node_spanned_pages; -} - #include void build_all_zonelists(pg_data_t *pgdat); -- cgit v1.2.3 From f774a6a6fd39e1b5677bdf71f6813b382faddeeb Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Fri, 16 Sep 2022 15:22:51 +0800 Subject: mm, memory_hotplug: remove obsolete generic_free_nodedata() Commit 390511e1476e ("mm, memory_hotplug: drop arch_free_nodedata") drops the last caller of generic_free_nodedata(). Remove it too. Link: https://lkml.kernel.org/r/20220916072257.9639-11-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Reviewed-by: David Hildenbrand Reviewed-by: Anshuman Khandual Reviewed-by: Oscar Salvador Cc: Matthew Wilcox Signed-off-by: Andrew Morton --- include/linux/memory_hotplug.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 51052969dbfe..9fcbf5706595 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -43,11 +43,6 @@ extern void arch_refresh_nodedata(int nid, pg_data_t *pgdat); ({ \ memblock_alloc(sizeof(*pgdat), SMP_CACHE_BYTES); \ }) -/* - * This definition is just for error path in node hotadd. - * For node hotremove, we have to replace this. - */ -#define generic_free_nodedata(pgdat) kfree(pgdat) extern pg_data_t *node_data[]; static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat) @@ -63,9 +58,6 @@ static inline pg_data_t *generic_alloc_nodedata(int nid) BUG(); return NULL; } -static inline void generic_free_nodedata(pg_data_t *pgdat) -{ -} static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat) { } -- cgit v1.2.3 From def76fd549c513bb90278a8d6d0fe3ef3faa20a7 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Fri, 16 Sep 2022 15:22:56 +0800 Subject: mm/page_alloc: remove obsolete gfpflags_normal_context() Since commit dacb5d8875cc ("tcp: fix page frag corruption on page fault"), there's no caller of gfpflags_normal_context(). Remove it as this helper is strictly tied to the sk page frag usage and there won't be other user in the future. [linmiaohe@huawei.com: fix htmldocs] Link: https://lkml.kernel.org/r/1bc55727-9b66-0e9e-c306-f10c4716ea89@huawei.com Link: https://lkml.kernel.org/r/20220916072257.9639-16-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Reviewed-by: David Hildenbrand Reviewed-by: Anshuman Khandual Reviewed-by: Oscar Salvador Cc: Matthew Wilcox Signed-off-by: Andrew Morton --- include/linux/gfp.h | 23 ----------------------- 1 file changed, 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index ea6cb9399152..ef4aea3b356e 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -36,29 +36,6 @@ static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags) return !!(gfp_flags & __GFP_DIRECT_RECLAIM); } -/** - * gfpflags_normal_context - is gfp_flags a normal sleepable context? - * @gfp_flags: gfp_flags to test - * - * Test whether @gfp_flags indicates that the allocation is from the - * %current context and allowed to sleep. - * - * An allocation being allowed to block doesn't mean it owns the %current - * context. When direct reclaim path tries to allocate memory, the - * allocation context is nested inside whatever %current was doing at the - * time of the original allocation. The nested allocation may be allowed - * to block but modifying anything %current owns can corrupt the outer - * context's expectations. - * - * %true result from this function indicates that the allocation context - * can sleep and use anything that's associated with %current. - */ -static inline bool gfpflags_normal_context(const gfp_t gfp_flags) -{ - return (gfp_flags & (__GFP_DIRECT_RECLAIM | __GFP_MEMALLOC)) == - __GFP_DIRECT_RECLAIM; -} - #ifdef CONFIG_HIGHMEM #define OPT_ZONE_HIGHMEM ZONE_HIGHMEM #else -- cgit v1.2.3 From 233f0b31bd9503ce2be7be0bde69c67287c8a741 Mon Sep 17 00:00:00 2001 From: Kaixu Xia Date: Tue, 20 Sep 2022 16:53:22 +0000 Subject: mm/damon: deduplicate damon_{reclaim,lru_sort}_apply_parameters() The bodies of damon_{reclaim,lru_sort}_apply_parameters() contain duplicates. This commit adds a common function damon_set_region_biggest_system_ram_default() to remove the duplicates. Link: https://lkml.kernel.org/r/6329f00d.a70a0220.9bb29.3678SMTPIN_ADDED_BROKEN@mx.google.com Signed-off-by: Kaixu Xia Suggested-by: SeongJae Park Reviewed-by: SeongJae Park Signed-off-by: SeongJae Park Signed-off-by: Andrew Morton --- include/linux/damon.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index e7808a84675f..ed5470f50bab 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -557,7 +557,8 @@ static inline bool damon_target_has_pid(const struct damon_ctx *ctx) int damon_start(struct damon_ctx **ctxs, int nr_ctxs, bool exclusive); int damon_stop(struct damon_ctx **ctxs, int nr_ctxs); -bool damon_find_biggest_system_ram(unsigned long *start, unsigned long *end); +int damon_set_region_biggest_system_ram_default(struct damon_target *t, + unsigned long *start, unsigned long *end); #endif /* CONFIG_DAMON */ -- cgit v1.2.3 From 2eb989195d9a361d13d66ffb8738847649e080ad Mon Sep 17 00:00:00 2001 From: Kairui Song Date: Tue, 20 Sep 2022 02:06:33 +0800 Subject: mm: memcontrol: use memcg_kmem_enabled in count_objcg_event Patch series "mm: memcontrol: cleanup and optimize for two accounting params", v2. This patch (of 2): There are currently two helpers for checking if cgroup kmem accounting is enabled: - mem_cgroup_kmem_disabled - memcg_kmem_enabled mem_cgroup_kmem_disabled is a simple helper that returns true if cgroup.memory=nokmem is specified, otherwise returns false. memcg_kmem_enabled is a bit different, it returns true if cgroup.memory=nokmem is not specified and there was at least one non-root memory control enabled cgroup ever created. This help improve performance when kmem accounting was not actually activated. And it's optimized with static branch. The usage of mem_cgroup_kmem_disabled is for sub-systems that need to preallocate data for kmem accounting since they could be initialized before kmem accounting is activated. But count_objcg_event doesn't need that, so using memcg_kmem_enabled is better here. Link: https://lkml.kernel.org/r/20220919180634.45958-1-ryncsn@gmail.com Link: https://lkml.kernel.org/r/20220919180634.45958-2-ryncsn@gmail.com Signed-off-by: Kairui Song Acked-by: Shakeel Butt Acked-by: Roman Gushchin Acked-by: Muchun Song Cc: Johannes Weiner Cc: Michal Hocko Signed-off-by: Andrew Morton --- include/linux/memcontrol.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index dc7d40e575d5..ef479e554253 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1778,7 +1778,7 @@ static inline void count_objcg_event(struct obj_cgroup *objcg, { struct mem_cgroup *memcg; - if (mem_cgroup_kmem_disabled()) + if (!memcg_kmem_enabled()) return; rcu_read_lock(); -- cgit v1.2.3 From 7c6c6cc4d3a213e7303ef06ff40f6193df01839c Mon Sep 17 00:00:00 2001 From: Zach O'Keefe Date: Thu, 22 Sep 2022 15:40:37 -0700 Subject: mm/shmem: add flag to enforce shmem THP in hugepage_vma_check() Patch series "mm: add file/shmem support to MADV_COLLAPSE", v4. This series builds on top of the previous "mm: userspace hugepage collapse" series which introduced the MADV_COLLAPSE madvise mode and added support for private, anonymous mappings[2], by adding support for file and shmem backed memory to CONFIG_READ_ONLY_THP_FOR_FS=y kernels. File and shmem support have been added with effort to align with existing MADV_COLLAPSE semantics and policy decisions[3]. Collapse of shmem-backed memory ignores kernel-guiding directives and heuristics including all sysfs settings (transparent_hugepage/shmem_enabled), and tmpfs huge= mount options (shmem always supports large folios). Like anonymous mappings, on successful return of MADV_COLLAPSE on file/shmem memory, the contents of memory mapped by the addresses provided will be synchronously pmd-mapped THPs. This functionality unlocks two important uses: (1) Immediately back executable text by THPs. Current support provided by CONFIG_READ_ONLY_THP_FOR_FS may take a long time on a large system which might impair services from serving at their full rated load after (re)starting. Tricks like mremap(2)'ing text onto anonymous memory to immediately realize iTLB performance prevents page sharing and demand paging, both of which increase steady state memory footprint. Now, we can have the best of both worlds: Peak upfront performance and lower RAM footprints. (2) userfaultfd-based live migration of virtual machines satisfy UFFD faults by fetching native-sized pages over the network (to avoid latency of transferring an entire hugepage). However, after guest memory has been fully copied to the new host, MADV_COLLAPSE can be used to immediately increase guest performance. khugepaged has received a small improvement by association and can now detect and collapse pte-mapped THPs. However, there is still work to be done along the file collapse path. Compound pages of arbitrary order still needs to be supported and THP collapse needs to be converted to using folios in general. Eventually, we'd like to move away from the read-only and executable-mapped constraints currently imposed on eligible files and support any inode claiming huge folio support. That said, I think the series as-is covers enough to claim that MADV_COLLAPSE supports file/shmem memory. Patches 1-3 Implement the guts of the series. Patch 4 Is a tracepoint for debugging. Patches 5-9 Refactor existing khugepaged selftests to work with new memory types + new collapse tests. Patch 10 Adds a userfaultfd selftest mode to mimic a functional test of UFFDIO_REGISTER_MODE_MINOR+MADV_COLLAPSE live migration. (v4 note: "userfaultfd shmem" selftest is failing as of Sep 22 mm-unstable) [1] https://lore.kernel.org/linux-mm/YyiK8YvVcrtZo0z3@google.com/ [2] https://lore.kernel.org/linux-mm/20220706235936.2197195-1-zokeefe@google.com/ [3] https://lore.kernel.org/linux-mm/YtBmhaiPHUTkJml8@google.com/ [4] https://lore.kernel.org/linux-mm/20220922222731.1124481-1-zokeefe@google.com/ [5] https://lore.kernel.org/linux-mm/20220922184651.1016461-1-zokeefe@google.com/ This patch (of 10): Extend 'mm/thp: add flag to enforce sysfs THP in hugepage_vma_check()' to shmem, allowing callers to ignore /sys/kernel/transparent_hugepage/shmem_enabled and tmpfs huge= mount. This is intended to be used by MADV_COLLAPSE, and the rationale is analogous to the anon/file case: MADV_COLLAPSE is not coupled to directives that advise the kernel's decisions on when THPs should be considered eligible. shmem/tmpfs always claims large folio support, regardless of sysfs or mount options. [shy828301@gmail.com: test shmem_huge_force explicitly] Link: https://lore.kernel.org/linux-mm/CAHbLzko3A5-TpS0BgBeKkx5cuOkWgLvWXQH=TdgW-baO4rPtdg@mail.gmail.com/ Link: https://lkml.kernel.org/r/20220922224046.1143204-1-zokeefe@google.com Link: https://lkml.kernel.org/r/20220907144521.3115321-2-zokeefe@google.com Link: https://lkml.kernel.org/r/20220922224046.1143204-2-zokeefe@google.com Signed-off-by: Zach O'Keefe Reviewed-by: Yang Shi Cc: Axel Rasmussen Cc: Chris Kennelly Cc: David Hildenbrand Cc: David Rientjes Cc: Hugh Dickins Cc: James Houghton Cc: "Kirill A. Shutemov" Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Minchan Kim Cc: Pasha Tatashin Cc: Peter Xu Cc: Rongwei Wang Cc: SeongJae Park Cc: Song Liu Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/shmem_fs.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index f24071e3c826..d500ea967dc7 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -92,11 +92,13 @@ extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, extern void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end); int shmem_unuse(unsigned int type); -extern bool shmem_is_huge(struct vm_area_struct *vma, - struct inode *inode, pgoff_t index); -static inline bool shmem_huge_enabled(struct vm_area_struct *vma) +extern bool shmem_is_huge(struct vm_area_struct *vma, struct inode *inode, + pgoff_t index, bool shmem_huge_force); +static inline bool shmem_huge_enabled(struct vm_area_struct *vma, + bool shmem_huge_force) { - return shmem_is_huge(vma, file_inode(vma->vm_file), vma->vm_pgoff); + return shmem_is_huge(vma, file_inode(vma->vm_file), vma->vm_pgoff, + shmem_huge_force); } extern unsigned long shmem_swap_usage(struct vm_area_struct *vma); extern unsigned long shmem_partial_swap_usage(struct address_space *mapping, -- cgit v1.2.3 From 34488399fa08faaf664743fa54b271eb6f9e1321 Mon Sep 17 00:00:00 2001 From: Zach O'Keefe Date: Thu, 22 Sep 2022 15:40:39 -0700 Subject: mm/madvise: add file and shmem support to MADV_COLLAPSE Add support for MADV_COLLAPSE to collapse shmem-backed and file-backed memory into THPs (requires CONFIG_READ_ONLY_THP_FOR_FS=y). On success, the backing memory will be a hugepage. For the memory range and process provided, the page tables will synchronously have a huge pmd installed, mapping the THP. Other mappings of the file extent mapped by the memory range may be added to a set of entries that khugepaged will later process and attempt update their page tables to map the THP by a pmd. This functionality unlocks two important uses: (1) Immediately back executable text by THPs. Current support provided by CONFIG_READ_ONLY_THP_FOR_FS may take a long time on a large system which might impair services from serving at their full rated load after (re)starting. Tricks like mremap(2)'ing text onto anonymous memory to immediately realize iTLB performance prevents page sharing and demand paging, both of which increase steady state memory footprint. Now, we can have the best of both worlds: Peak upfront performance and lower RAM footprints. (2) userfaultfd-based live migration of virtual machines satisfy UFFD faults by fetching native-sized pages over the network (to avoid latency of transferring an entire hugepage). However, after guest memory has been fully copied to the new host, MADV_COLLAPSE can be used to immediately increase guest performance. Since khugepaged is single threaded, this change now introduces possibility of collapse contexts racing in file collapse path. There a important few places to consider: (1) hpage_collapse_scan_file(), when we xas_pause() and drop RCU. We could have the memory collapsed out from under us, but the next xas_for_each() iteration will correctly pick up the hugepage. The hugepage might not be up to date (insofar as copying of small page contents might not have completed - the page still may be locked), but regardless what small page index we were iterating over, we'll find the hugepage and identify it as a suitably aligned compound page of order HPAGE_PMD_ORDER. In khugepaged path, we locklessly check the value of the pmd, and only add it to deferred collapse array if we find pmd mapping pte table. This is fine, since other values that could have raced in right afterwards denote failure, or that the memory was successfully collapsed, so we don't need further processing. In madvise path, we'll take mmap_lock() in write to serialize against page table updates and will know what to do based on the true value of the pmd: recheck all ptes if we point to a pte table, directly install the pmd, if the pmd has been cleared, but memory not yet faulted, or nothing at all if we find a huge pmd. It's worth putting emphasis here on how we treat the none pmd here. If khugepaged has processed this mm's page tables already, it will have left the pmd cleared (ready for refault by the process). Depending on the VMA flags and sysfs settings, amount of RAM on the machine, and the current load, could be a relatively common occurrence - and as such is one we'd like to handle successfully in MADV_COLLAPSE. When we see the none pmd in collapse_pte_mapped_thp(), we've locked mmap_lock in write and checked (a) huepaged_vma_check() to see if the backing memory is appropriate still, along with VMA sizing and appropriate hugepage alignment within the file, and (b) we've found a hugepage head of order HPAGE_PMD_ORDER at the offset in the file mapped by our hugepage-aligned virtual address. Even though the common-case is likely race with khugepaged, given these checks (regardless how we got here - we could be operating on a completely different file than originally checked in hpage_collapse_scan_file() for all we know) it should be safe to directly make the pmd a huge pmd pointing to this hugepage. (2) collapse_file() is mostly serialized on the same file extent by lock sequence: | lock hupepage | lock mapping->i_pages | lock 1st page | unlock mapping->i_pages | | lock mapping->i_pages | page_ref_freeze(3) | xas_store(hugepage) | unlock mapping->i_pages | page_ref_unfreeze(1) | unlock 1st page V unlock hugepage Once a context (who already has their fresh hugepage locked) locks mapping->i_pages exclusively, it will hold said lock until it locks the first page, and it will hold that lock until the after the hugepage has been added to the page cache (and will unlock the hugepage after page table update, though that isn't important here). A racing context that loses the race for mapping->i_pages will then lose the race to locking the first page. Here - depending on how far the other racing context has gotten - we might find the new hugepage (in which case we'll exit cleanly when we check PageTransCompound()), or we'll find the "old" 1st small page (in which we'll exit cleanly when we discover unexpected refcount of 2 after isolate_lru_page()). This is assuming we are able to successfully lock the page we find - in shmem path, we could just fail the trylock and exit cleanly anyways. Failure path in collapse_file() is similar: once we hold lock on 1st small page, we are serialized against other collapse contexts. Before the 1st small page is unlocked, we add it back to the pagecache and unfreeze the refcount appropriately. Contexts who lost the race to the 1st small page will then find the same 1st small page with the correct refcount and will be able to proceed. [zokeefe@google.com: don't check pmd value twice in collapse_pte_mapped_thp()] Link: https://lkml.kernel.org/r/20220927033854.477018-1-zokeefe@google.com [shy828301@gmail.com: Delete hugepage_vma_revalidate_anon(), remove check for multi-add in khugepaged_add_pte_mapped_thp()] Link: https://lore.kernel.org/linux-mm/CAHbLzkrtpM=ic7cYAHcqkubah5VTR8N5=k5RT8MTvv5rN1Y91w@mail.gmail.com/ Link: https://lkml.kernel.org/r/20220907144521.3115321-4-zokeefe@google.com Link: https://lkml.kernel.org/r/20220922224046.1143204-4-zokeefe@google.com Signed-off-by: Zach O'Keefe Cc: Axel Rasmussen Cc: Chris Kennelly Cc: David Hildenbrand Cc: David Rientjes Cc: Hugh Dickins Cc: James Houghton Cc: "Kirill A. Shutemov" Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Minchan Kim Cc: Pasha Tatashin Cc: Peter Xu Cc: Rongwei Wang Cc: SeongJae Park Cc: Song Liu Cc: Vlastimil Babka Cc: Yang Shi Signed-off-by: Andrew Morton --- include/linux/khugepaged.h | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h index 384f034ae947..70162d707caf 100644 --- a/include/linux/khugepaged.h +++ b/include/linux/khugepaged.h @@ -16,11 +16,13 @@ extern void khugepaged_enter_vma(struct vm_area_struct *vma, unsigned long vm_flags); extern void khugepaged_min_free_kbytes_update(void); #ifdef CONFIG_SHMEM -extern void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr); +extern int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, + bool install_pmd); #else -static inline void collapse_pte_mapped_thp(struct mm_struct *mm, - unsigned long addr) +static inline int collapse_pte_mapped_thp(struct mm_struct *mm, + unsigned long addr, bool install_pmd) { + return 0; } #endif @@ -46,9 +48,10 @@ static inline void khugepaged_enter_vma(struct vm_area_struct *vma, unsigned long vm_flags) { } -static inline void collapse_pte_mapped_thp(struct mm_struct *mm, - unsigned long addr) +static inline int collapse_pte_mapped_thp(struct mm_struct *mm, + unsigned long addr, bool install_pmd) { + return 0; } static inline void khugepaged_min_free_kbytes_update(void) -- cgit v1.2.3 From 6b91e5dfb3c7ef485587e7ab494dcb47bcdadce3 Mon Sep 17 00:00:00 2001 From: Gaosheng Cui Date: Thu, 22 Sep 2022 19:09:35 +0800 Subject: mm: remove unused inline functions from include/linux/mm_inline.h Remove the following unused inline functions from mm_inline.h: 1. All uses of add_page_to_lru_list_tail() have been removed since commit 7a3dbfe8a52b ("mm/swap: convert lru_deactivate_file to a folio_batch"), and it can be replaced by lruvec_add_folio_tail(). 2. All uses of __clear_page_lru_flags() have been removed since commit 188e8caee968 ("mm/swap: convert __page_cache_release() to use a folio"), and it can be replaced by __folio_clear_lru_flags(). They are useless, so remove them. Link: https://lkml.kernel.org/r/20220922110935.1495099-1-cuigaosheng1@huawei.com Signed-off-by: Gaosheng Cui Signed-off-by: Andrew Morton --- include/linux/mm_inline.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 4949eda9a9a2..e8ed225d8f7c 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -76,11 +76,6 @@ static __always_inline void __folio_clear_lru_flags(struct folio *folio) __folio_clear_unevictable(folio); } -static __always_inline void __clear_page_lru_flags(struct page *page) -{ - __folio_clear_lru_flags(page_folio(page)); -} - /** * folio_lru_list - Which LRU list should a folio be on? * @folio: The folio to test. @@ -348,12 +343,6 @@ void lruvec_add_folio_tail(struct lruvec *lruvec, struct folio *folio) list_add_tail(&folio->lru, &lruvec->lists[lru]); } -static __always_inline void add_page_to_lru_list_tail(struct page *page, - struct lruvec *lruvec) -{ - lruvec_add_folio_tail(lruvec, page_folio(page)); -} - static __always_inline void lruvec_del_folio(struct lruvec *lruvec, struct folio *folio) { -- cgit v1.2.3 From e55b9f96860f6c6026cff97966a740576285e07b Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Mon, 26 Sep 2022 09:57:04 -0400 Subject: mm: memcontrol: drop dead CONFIG_MEMCG_SWAP config symbol Since 2d1c498072de ("mm: memcontrol: make swap tracking an integral part of memory control"), CONFIG_MEMCG_SWAP hasn't been a user-visible config option anymore, it just means CONFIG_MEMCG && CONFIG_SWAP. Update the sites accordingly and drop the symbol. [ While touching the docs, remove two references to CONFIG_MEMCG_KMEM, which hasn't been a user-visible symbol for over half a decade. ] Link: https://lkml.kernel.org/r/20220926135704.400818-5-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Shakeel Butt Cc: Hugh Dickins Cc: Michal Hocko Cc: Roman Gushchin Signed-off-by: Andrew Morton --- include/linux/swap.h | 2 +- include/linux/swap_cgroup.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index fc8d98660326..a18cf4b7c724 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -666,7 +666,7 @@ static inline void folio_throttle_swaprate(struct folio *folio, gfp_t gfp) cgroup_throttle_swaprate(&folio->page, gfp); } -#ifdef CONFIG_MEMCG_SWAP +#if defined(CONFIG_MEMCG) && defined(CONFIG_SWAP) void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry); int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry); static inline int mem_cgroup_try_charge_swap(struct folio *folio, diff --git a/include/linux/swap_cgroup.h b/include/linux/swap_cgroup.h index a12dd1c3966c..ae73a87775b3 100644 --- a/include/linux/swap_cgroup.h +++ b/include/linux/swap_cgroup.h @@ -4,7 +4,7 @@ #include -#ifdef CONFIG_MEMCG_SWAP +#if defined(CONFIG_MEMCG) && defined(CONFIG_SWAP) extern unsigned short swap_cgroup_cmpxchg(swp_entry_t ent, unsigned short old, unsigned short new); @@ -40,6 +40,6 @@ static inline void swap_cgroup_swapoff(int type) return; } -#endif /* CONFIG_MEMCG_SWAP */ +#endif #endif /* __LINUX_SWAP_CGROUP_H */ -- cgit v1.2.3 From 8f824b4abd31c5ea32ae1d6725c47bdb247d18da Mon Sep 17 00:00:00 2001 From: Jiangshan Yi Date: Mon, 5 Sep 2022 10:10:34 +0800 Subject: init.h: fix spelling typo in comment Fix spelling typo in comment. Link: https://lkml.kernel.org/r/20220905021034.947701-1-13667453960@163.com Signed-off-by: Jiangshan Yi Reported-by: k2ci Signed-off-by: Andrew Morton --- include/linux/init.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/init.h b/include/linux/init.h index baf0b29a7010..3254766ebbf2 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -134,7 +134,7 @@ static inline initcall_t initcall_from_entry(initcall_entry_t *entry) extern initcall_entry_t __con_initcall_start[], __con_initcall_end[]; -/* Used for contructor calls. */ +/* Used for constructor calls. */ typedef void (*ctor_fn_t)(void); struct file_system_type; -- cgit v1.2.3 From 5ca14835dc429c09fefb290f60343fe266382760 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Fri, 9 Sep 2022 13:57:41 -0700 Subject: fs: uninline inode_maybe_inc_iversion() It has many callsites and is large. text data bss dec hex filename 91796 15984 512 108292 1a704 mm/shmem.o-before 91180 15984 512 107676 1a49c mm/shmem.o-after Acked-by: Jeff Layton Cc: Chuck Lever Cc: Alexander Viro Cc: Hugh Dickins Signed-off-by: Andrew Morton --- include/linux/iversion.h | 46 +--------------------------------------------- 1 file changed, 1 insertion(+), 45 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iversion.h b/include/linux/iversion.h index eb5a15810169..e27bd4f55d84 100644 --- a/include/linux/iversion.h +++ b/include/linux/iversion.h @@ -172,51 +172,7 @@ inode_set_iversion_queried(struct inode *inode, u64 val) I_VERSION_QUERIED); } -/** - * inode_maybe_inc_iversion - increments i_version - * @inode: inode with the i_version that should be updated - * @force: increment the counter even if it's not necessary? - * - * Every time the inode is modified, the i_version field must be seen to have - * changed by any observer. - * - * If "force" is set or the QUERIED flag is set, then ensure that we increment - * the value, and clear the queried flag. - * - * In the common case where neither is set, then we can return "false" without - * updating i_version. - * - * If this function returns false, and no other metadata has changed, then we - * can avoid logging the metadata. - */ -static inline bool -inode_maybe_inc_iversion(struct inode *inode, bool force) -{ - u64 cur, new; - - /* - * The i_version field is not strictly ordered with any other inode - * information, but the legacy inode_inc_iversion code used a spinlock - * to serialize increments. - * - * Here, we add full memory barriers to ensure that any de-facto - * ordering with other info is preserved. - * - * This barrier pairs with the barrier in inode_query_iversion() - */ - smp_mb(); - cur = inode_peek_iversion_raw(inode); - do { - /* If flag is clear then we needn't do anything */ - if (!force && !(cur & I_VERSION_QUERIED)) - return false; - - /* Since lowest bit is flag, add 2 to avoid it */ - new = (cur & ~I_VERSION_QUERIED) + I_VERSION_INCREMENT; - } while (!atomic64_try_cmpxchg(&inode->i_version, &cur, new)); - return true; -} - +bool inode_maybe_inc_iversion(struct inode *inode, bool force); /** * inode_inc_iversion - forcibly increment i_version -- cgit v1.2.3 From 5d0ce3595ab75330a15cec914096efbbb8b41e4a Mon Sep 17 00:00:00 2001 From: Jiebin Sun Date: Wed, 14 Sep 2022 03:25:37 +0800 Subject: percpu: add percpu_counter_add_local and percpu_counter_sub_local Patch series "/msg: mitigate the lock contention in ipc/msg", v6. Here are two patches to mitigate the lock contention in ipc/msg. The 1st patch is to add the new interface percpu_counter_add_local and percpu_counter_sub_local. The batch size in percpu_counter_add_batch should be very large in heavy writing and rare reading case. Add the "_local" version, and mostly it will do local adding, reduce the global updating and mitigate lock contention in writing. The 2nd patch is to use percpu_counter instead of atomic update in ipc/msg. The msg_bytes and msg_hdrs atomic counters are frequently updated when IPC msg queue is in heavy use, causing heavy cache bounce and overhead. Change them to percpu_counter greatly improve the performance. Since there is one percpu struct per namespace, additional memory cost is minimal. Reading of the count done in msgctl call, which is infrequent. So the need to sum up the counts in each CPU is infrequent. This patch (of 2): The batch size in percpu_counter_add_batch should be very large in heavy writing and rare reading case. Add the "_local" version, and mostly it will do local adding, reduce the global updating and mitigate lock contention in writing. Link: https://lkml.kernel.org/r/20220913192538.3023708-1-jiebin.sun@intel.com Link: https://lkml.kernel.org/r/20220913192538.3023708-2-jiebin.sun@intel.com Signed-off-by: Jiebin Sun Reviewed-by: Tim Chen Cc: Alexander Mikhalitsyn Cc: Alexey Gladkov Cc: Christoph Lameter Cc: Dennis Zhou Cc: "Eric W . Biederman" Cc: Manfred Spraul Cc: Shakeel Butt Cc: Tejun Heo Cc: Vasily Averin Cc: Davidlohr Bueso Signed-off-by: Andrew Morton --- include/linux/percpu_counter.h | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) (limited to 'include/linux') diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h index 01861eebed79..8ed5fba6d156 100644 --- a/include/linux/percpu_counter.h +++ b/include/linux/percpu_counter.h @@ -15,6 +15,9 @@ #include #include +/* percpu_counter batch for local add or sub */ +#define PERCPU_COUNTER_LOCAL_BATCH INT_MAX + #ifdef CONFIG_SMP struct percpu_counter { @@ -56,6 +59,22 @@ static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) percpu_counter_add_batch(fbc, amount, percpu_counter_batch); } +/* + * With percpu_counter_add_local() and percpu_counter_sub_local(), counts + * are accumulated in local per cpu counter and not in fbc->count until + * local count overflows PERCPU_COUNTER_LOCAL_BATCH. This makes counter + * write efficient. + * But percpu_counter_sum(), instead of percpu_counter_read(), needs to be + * used to add up the counts from each CPU to account for all the local + * counts. So percpu_counter_add_local() and percpu_counter_sub_local() + * should be used when a counter is updated frequently and read rarely. + */ +static inline void +percpu_counter_add_local(struct percpu_counter *fbc, s64 amount) +{ + percpu_counter_add_batch(fbc, amount, PERCPU_COUNTER_LOCAL_BATCH); +} + static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc) { s64 ret = __percpu_counter_sum(fbc); @@ -138,6 +157,13 @@ percpu_counter_add(struct percpu_counter *fbc, s64 amount) preempt_enable(); } +/* non-SMP percpu_counter_add_local is the same with percpu_counter_add */ +static inline void +percpu_counter_add_local(struct percpu_counter *fbc, s64 amount) +{ + percpu_counter_add(fbc, amount); +} + static inline void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch) { @@ -193,4 +219,10 @@ static inline void percpu_counter_sub(struct percpu_counter *fbc, s64 amount) percpu_counter_add(fbc, -amount); } +static inline void +percpu_counter_sub_local(struct percpu_counter *fbc, s64 amount) +{ + percpu_counter_add_local(fbc, -amount); +} + #endif /* _LINUX_PERCPU_COUNTER_H */ -- cgit v1.2.3 From 72d1e611082eda18689106a0c192f2827072713c Mon Sep 17 00:00:00 2001 From: Jiebin Sun Date: Wed, 14 Sep 2022 03:25:38 +0800 Subject: ipc/msg: mitigate the lock contention with percpu counter The msg_bytes and msg_hdrs atomic counters are frequently updated when IPC msg queue is in heavy use, causing heavy cache bounce and overhead. Change them to percpu_counter greatly improve the performance. Since there is one percpu struct per namespace, additional memory cost is minimal. Reading of the count done in msgctl call, which is infrequent. So the need to sum up the counts in each CPU is infrequent. Apply the patch and test the pts/stress-ng-1.4.0 -- system v message passing (160 threads). Score gain: 3.99x CPU: ICX 8380 x 2 sockets Core number: 40 x 2 physical cores Benchmark: pts/stress-ng-1.4.0 -- system v message passing (160 threads) [akpm@linux-foundation.org: coding-style cleanups] [jiebin.sun@intel.com: avoid negative value by overflow in msginfo] Link: https://lkml.kernel.org/r/20220920150809.4014944-1-jiebin.sun@intel.com [akpm@linux-foundation.org: fix min() warnings] Link: https://lkml.kernel.org/r/20220913192538.3023708-3-jiebin.sun@intel.com Signed-off-by: Jiebin Sun Reviewed-by: Tim Chen Cc: Alexander Mikhalitsyn Cc: Alexey Gladkov Cc: Christoph Lameter Cc: Davidlohr Bueso Cc: Dennis Zhou Cc: "Eric W . Biederman" Cc: Manfred Spraul Cc: Shakeel Butt Cc: Tejun Heo Cc: Vasily Averin Signed-off-by: Andrew Morton --- include/linux/ipc_namespace.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index e3e8c8662b49..e8240cf2611a 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -11,6 +11,7 @@ #include #include #include +#include struct user_namespace; @@ -36,8 +37,8 @@ struct ipc_namespace { unsigned int msg_ctlmax; unsigned int msg_ctlmnb; unsigned int msg_ctlmni; - atomic_t msg_bytes; - atomic_t msg_hdrs; + struct percpu_counter percpu_msg_bytes; + struct percpu_counter percpu_msg_hdrs; size_t shm_ctlmax; size_t shm_ctlall; -- cgit v1.2.3 From 5d10f480f77b67332e4835ad565bfe4cb8528159 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Thu, 18 Aug 2022 10:23:16 +0200 Subject: thermal/of: Remove the thermal_zone_of_get_sensor_id() function The function thermal_zone_of_get_sensor_id() is no longer used anywhere, remove it. Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20220818082316.2717095-2-daniel.lezcano@linaro.org --- include/linux/thermal.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 6f1ec4fb7ef8..9ecc128944a1 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -308,9 +308,6 @@ void devm_thermal_of_zone_unregister(struct device *dev, struct thermal_zone_dev void thermal_of_zone_unregister(struct thermal_zone_device *tz); -int thermal_zone_of_get_sensor_id(struct device_node *tz_np, - struct device_node *sensor_np, - u32 *id); #else static inline struct thermal_zone_device *thermal_of_zone_register(struct device_node *sensor, int id, void *data, @@ -334,13 +331,6 @@ static inline void devm_thermal_of_zone_unregister(struct device *dev, struct thermal_zone_device *tz) { } - -static inline int thermal_zone_of_get_sensor_id(struct device_node *tz_np, - struct device_node *sensor_np, - u32 *id) -{ - return -ENOENT; -} #endif #ifdef CONFIG_THERMAL -- cgit v1.2.3 From 4c99256013fa4e0fe9733ca1bab2b5684ccc02a1 Mon Sep 17 00:00:00 2001 From: Raul E Rangel Date: Thu, 29 Sep 2022 10:19:09 -0600 Subject: gpiolib: acpi: Add wake_capable variants of acpi_dev_gpio_irq_get The ACPI spec defines the SharedAndWake and ExclusiveAndWake share type keywords. This is an indication that the GPIO IRQ can also be used as a wake source. This change exposes the wake_capable bit so drivers can correctly enable wake functionality instead of making an assumption. Signed-off-by: Raul E Rangel Reviewed-by: Mika Westerberg Reviewed-by: Andy Shevchenko Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 6f64b2f3dc54..cd7371a5f283 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1202,7 +1202,8 @@ bool acpi_gpio_get_irq_resource(struct acpi_resource *ares, struct acpi_resource_gpio **agpio); bool acpi_gpio_get_io_resource(struct acpi_resource *ares, struct acpi_resource_gpio **agpio); -int acpi_dev_gpio_irq_get_by(struct acpi_device *adev, const char *name, int index); +int acpi_dev_gpio_irq_wake_get_by(struct acpi_device *adev, const char *name, int index, + bool *wake_capable); #else static inline bool acpi_gpio_get_irq_resource(struct acpi_resource *ares, struct acpi_resource_gpio **agpio) @@ -1214,16 +1215,28 @@ static inline bool acpi_gpio_get_io_resource(struct acpi_resource *ares, { return false; } -static inline int acpi_dev_gpio_irq_get_by(struct acpi_device *adev, - const char *name, int index) +static inline int acpi_dev_gpio_irq_wake_get_by(struct acpi_device *adev, const char *name, + int index, bool *wake_capable) { return -ENXIO; } #endif +static inline int acpi_dev_gpio_irq_wake_get(struct acpi_device *adev, int index, + bool *wake_capable) +{ + return acpi_dev_gpio_irq_wake_get_by(adev, NULL, index, wake_capable); +} + +static inline int acpi_dev_gpio_irq_get_by(struct acpi_device *adev, const char *name, + int index) +{ + return acpi_dev_gpio_irq_wake_get_by(adev, name, index, NULL); +} + static inline int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index) { - return acpi_dev_gpio_irq_get_by(adev, NULL, index); + return acpi_dev_gpio_irq_wake_get_by(adev, NULL, index, NULL); } /* Device properties */ -- cgit v1.2.3 From 5ff811604f93bdd2650beed80b48c2ca16c6fba6 Mon Sep 17 00:00:00 2001 From: Raul E Rangel Date: Thu, 29 Sep 2022 10:19:10 -0600 Subject: ACPI: resources: Add wake_capable parameter to acpi_dev_irq_flags ACPI IRQ/Interrupt resources contain a bit that describes if the interrupt should wake the system. This change exposes that bit via a new IORESOURCE_IRQ_WAKECAPABLE flag. Drivers should check this flag before arming an IRQ to wake the system. Signed-off-by: Raul E Rangel Reviewed-by: Andy Shevchenko Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 2 +- include/linux/ioport.h | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index cd7371a5f283..ea2efbdbeee5 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -495,7 +495,7 @@ bool acpi_dev_resource_address_space(struct acpi_resource *ares, struct resource_win *win); bool acpi_dev_resource_ext_address_space(struct acpi_resource *ares, struct resource_win *win); -unsigned long acpi_dev_irq_flags(u8 triggering, u8 polarity, u8 shareable); +unsigned long acpi_dev_irq_flags(u8 triggering, u8 polarity, u8 shareable, u8 wake_capable); unsigned int acpi_dev_get_irq_type(int triggering, int polarity); bool acpi_dev_resource_interrupt(struct acpi_resource *ares, int index, struct resource *res); diff --git a/include/linux/ioport.h b/include/linux/ioport.h index 616b683563a9..3baeea4d903b 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -79,7 +79,8 @@ struct resource { #define IORESOURCE_IRQ_HIGHLEVEL (1<<2) #define IORESOURCE_IRQ_LOWLEVEL (1<<3) #define IORESOURCE_IRQ_SHAREABLE (1<<4) -#define IORESOURCE_IRQ_OPTIONAL (1<<5) +#define IORESOURCE_IRQ_OPTIONAL (1<<5) +#define IORESOURCE_IRQ_WAKECAPABLE (1<<6) /* PnP DMA specific bits (IORESOURCE_BITS) */ #define IORESOURCE_DMA_TYPE_MASK (3<<0) -- cgit v1.2.3 From e7fd8b68404f3d8bc03f85bc3c078d67096be06f Mon Sep 17 00:00:00 2001 From: Kai-Heng Feng Date: Thu, 29 Sep 2022 15:05:23 +0800 Subject: kernel/reboot: Add SYS_OFF_MODE_RESTART_PREPARE mode Add SYS_OFF_MODE_RESTART_PREPARE callbacks to be invoked before a system restart. Suggested-by: Dmitry Osipenko Reviewed-by: Dmitry Osipenko Signed-off-by: Kai-Heng Feng [ rjw: Changelog edits ] Signed-off-by: Rafael J. Wysocki --- include/linux/reboot.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/reboot.h b/include/linux/reboot.h index e5d9ef886179..2b6bb593be5b 100644 --- a/include/linux/reboot.h +++ b/include/linux/reboot.h @@ -105,6 +105,14 @@ enum sys_off_mode { */ SYS_OFF_MODE_POWER_OFF, + /** + * @SYS_OFF_MODE_RESTART_PREPARE: + * + * Handlers prepare system to be restarted. Handlers are + * allowed to sleep. + */ + SYS_OFF_MODE_RESTART_PREPARE, + /** * @SYS_OFF_MODE_RESTART: * -- cgit v1.2.3 From da4ab869e37cf81f93333ba74b16e0ea6d322e15 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 25 May 2022 06:11:00 -0400 Subject: libceph: drop last_piece flag from ceph_msg_data_cursor ceph_msg_data_next is always passed a NULL pointer for this field. Some of the "next" operations look at it in order to determine the length, but we can just take the min of the data on the page or cursor->resid. Signed-off-by: Jeff Layton Reviewed-by: Xiubo Li Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov --- include/linux/ceph/messenger.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index e7f2fb2fc207..99c1726be6ee 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -207,7 +207,6 @@ struct ceph_msg_data_cursor { struct ceph_msg_data *data; /* current data item */ size_t resid; /* bytes not yet consumed */ - bool last_piece; /* current is last piece */ bool need_crc; /* crc update needed */ union { #ifdef CONFIG_BLOCK @@ -498,8 +497,7 @@ void ceph_con_discard_requeued(struct ceph_connection *con, u64 reconnect_seq); void ceph_msg_data_cursor_init(struct ceph_msg_data_cursor *cursor, struct ceph_msg *msg, size_t length); struct page *ceph_msg_data_next(struct ceph_msg_data_cursor *cursor, - size_t *page_offset, size_t *length, - bool *last_piece); + size_t *page_offset, size_t *length); void ceph_msg_data_advance(struct ceph_msg_data_cursor *cursor, size_t bytes); u32 ceph_crc32c_page(u32 crc, struct page *page, unsigned int page_offset, -- cgit v1.2.3 From bdef2b7896df293736330eb6eb0f43947049b828 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 23 Sep 2022 11:26:41 +0200 Subject: vfio/mdev: make mdev.h standalone includable Include and so that users of this headers don't need to do that and remove those includes that aren't needed any more. Signed-off-by: Christoph Hellwig Reviewed-by: Eric Farman Reviewed-by: Jason Gunthorpe Reviewed-by: Tony Krowiak Reviewed-by: Kevin Tian Reviewed-by: Kirti Wankhede Link: https://lore.kernel.org/r/20220923092652.100656-4-hch@lst.de Signed-off-by: Alex Williamson --- include/linux/mdev.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mdev.h b/include/linux/mdev.h index 47ad3b104d9e..a5d8ae6132a2 100644 --- a/include/linux/mdev.h +++ b/include/linux/mdev.h @@ -10,6 +10,9 @@ #ifndef MDEV_H #define MDEV_H +#include +#include + struct mdev_type; struct mdev_device { -- cgit v1.2.3 From 89345d5177aa0f6d678251e1e0870b0eeb1ab510 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 23 Sep 2022 11:26:42 +0200 Subject: vfio/mdev: embedd struct mdev_parent in the parent data structure Simplify mdev_{un}register_device by requiring the caller to pass in a structure allocate as part of the parent device structure. This removes the need for a list of parents and the separate mdev_parent refcount as we can simplify rely on the reference to the parent device. Signed-off-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Reviewed-by: Tony Krowiak Reviewed-by: Kevin Tian Reviewed-by: Kirti Wankhede Reviewed-by: Eric Farman Link: https://lore.kernel.org/r/20220923092652.100656-5-hch@lst.de Signed-off-by: Alex Williamson --- include/linux/mdev.h | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mdev.h b/include/linux/mdev.h index a5d8ae6132a2..262512c2a8ff 100644 --- a/include/linux/mdev.h +++ b/include/linux/mdev.h @@ -23,6 +23,16 @@ struct mdev_device { bool active; }; +/* embedded into the struct device that the mdev devices hang off */ +struct mdev_parent { + struct device *dev; + struct mdev_driver *mdev_driver; + struct kset *mdev_types_kset; + struct list_head type_list; + /* Synchronize device creation/removal with parent unregistration */ + struct rw_semaphore unreg_sem; +}; + static inline struct mdev_device *to_mdev_device(struct device *dev) { return container_of(dev, struct mdev_device, dev); @@ -70,8 +80,9 @@ struct mdev_driver { extern struct bus_type mdev_bus_type; -int mdev_register_device(struct device *dev, struct mdev_driver *mdev_driver); -void mdev_unregister_device(struct device *dev); +int mdev_register_parent(struct mdev_parent *parent, struct device *dev, + struct mdev_driver *mdev_driver); +void mdev_unregister_parent(struct mdev_parent *parent); int mdev_register_driver(struct mdev_driver *drv); void mdev_unregister_driver(struct mdev_driver *drv); -- cgit v1.2.3 From da44c340c4fe9d9653ae84fa6a60f406bafcffce Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 23 Sep 2022 11:26:43 +0200 Subject: vfio/mdev: simplify mdev_type handling Instead of abusing struct attribute_group to control initialization of struct mdev_type, just define the actual attributes in the mdev_driver, allocate the mdev_type structures in the caller and pass them to mdev_register_parent. This allows the caller to use container_of to get at the containing structure and thus significantly simplify the code. Signed-off-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Reviewed-by: Tony Krowiak Reviewed-by: Kevin Tian Reviewed-by: Kirti Wankhede Reviewed-by: Eric Farman Link: https://lore.kernel.org/r/20220923092652.100656-6-hch@lst.de Signed-off-by: Alex Williamson --- include/linux/mdev.h | 26 ++++++++++++++++++-------- 1 file changed, 18 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mdev.h b/include/linux/mdev.h index 262512c2a8ff..19bc93c10e8c 100644 --- a/include/linux/mdev.h +++ b/include/linux/mdev.h @@ -23,14 +23,27 @@ struct mdev_device { bool active; }; +struct mdev_type { + /* set by the driver before calling mdev_register parent: */ + const char *sysfs_name; + + /* set by the core, can be used drivers */ + struct mdev_parent *parent; + + /* internal only */ + struct kobject kobj; + struct kobject *devices_kobj; +}; + /* embedded into the struct device that the mdev devices hang off */ struct mdev_parent { struct device *dev; struct mdev_driver *mdev_driver; struct kset *mdev_types_kset; - struct list_head type_list; /* Synchronize device creation/removal with parent unregistration */ struct rw_semaphore unreg_sem; + struct mdev_type **types; + unsigned int nr_types; }; static inline struct mdev_device *to_mdev_device(struct device *dev) @@ -38,8 +51,6 @@ static inline struct mdev_device *to_mdev_device(struct device *dev) return container_of(dev, struct mdev_device, dev); } -unsigned int mdev_get_type_group_id(struct mdev_device *mdev); -unsigned int mtype_get_type_group_id(struct mdev_type *mtype); struct device *mtype_get_parent_dev(struct mdev_type *mtype); /* interface for exporting mdev supported type attributes */ @@ -66,22 +77,21 @@ struct mdev_type_attribute mdev_type_attr_##_name = \ * struct mdev_driver - Mediated device driver * @probe: called when new device created * @remove: called when device removed - * @supported_type_groups: Attributes to define supported types. It is mandatory - * to provide supported types. + * @types_attrs: attributes to the type kobjects. * @driver: device driver structure - * **/ struct mdev_driver { int (*probe)(struct mdev_device *dev); void (*remove)(struct mdev_device *dev); - struct attribute_group **supported_type_groups; + const struct attribute * const *types_attrs; struct device_driver driver; }; extern struct bus_type mdev_bus_type; int mdev_register_parent(struct mdev_parent *parent, struct device *dev, - struct mdev_driver *mdev_driver); + struct mdev_driver *mdev_driver, struct mdev_type **types, + unsigned int nr_types); void mdev_unregister_parent(struct mdev_parent *parent); int mdev_register_driver(struct mdev_driver *drv); -- cgit v1.2.3 From cbf3bb28aaeaee425ca7b9c537a3efff1f8c98ae Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 23 Sep 2022 11:26:44 +0200 Subject: vfio/mdev: remove mdev_from_dev Just open code it in the only caller. Signed-off-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Reviewed-by: Kevin Tian Reviewed-by: Kirti Wankhede Link: https://lore.kernel.org/r/20220923092652.100656-7-hch@lst.de Signed-off-by: Alex Williamson --- include/linux/mdev.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mdev.h b/include/linux/mdev.h index 19bc93c10e8c..4f558de52fd9 100644 --- a/include/linux/mdev.h +++ b/include/linux/mdev.h @@ -102,9 +102,5 @@ static inline struct device *mdev_dev(struct mdev_device *mdev) { return &mdev->dev; } -static inline struct mdev_device *mdev_from_dev(struct device *dev) -{ - return dev->bus == &mdev_bus_type ? to_mdev_device(dev) : NULL; -} #endif /* MDEV_H */ -- cgit v1.2.3 From 2815fe149ffa8e1a022b2830ab62999135c00a4e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 23 Sep 2022 11:26:45 +0200 Subject: vfio/mdev: unexport mdev_bus_type mdev_bus_type is only used in mdev.ko now, so unexport it. Signed-off-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Reviewed-by: Kevin Tian Reviewed-by: Kirti Wankhede Link: https://lore.kernel.org/r/20220923092652.100656-8-hch@lst.de Signed-off-by: Alex Williamson --- include/linux/mdev.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mdev.h b/include/linux/mdev.h index 4f558de52fd9..6c179d2b8927 100644 --- a/include/linux/mdev.h +++ b/include/linux/mdev.h @@ -87,8 +87,6 @@ struct mdev_driver { struct device_driver driver; }; -extern struct bus_type mdev_bus_type; - int mdev_register_parent(struct mdev_parent *parent, struct device *dev, struct mdev_driver *mdev_driver, struct mdev_type **types, unsigned int nr_types); -- cgit v1.2.3 From 062e720cd209d8091c4f3d118d93973f02209aca Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 23 Sep 2022 11:26:46 +0200 Subject: vfio/mdev: remove mdev_parent_dev Just open code the dereferences in the only user. Signed-off-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Reviewed-by: Kevin Tian Reviewed-by: Kirti Wankhede Link: https://lore.kernel.org/r/20220923092652.100656-9-hch@lst.de Signed-off-by: Alex Williamson --- include/linux/mdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mdev.h b/include/linux/mdev.h index 6c179d2b8927..bbedffcb38d4 100644 --- a/include/linux/mdev.h +++ b/include/linux/mdev.h @@ -95,7 +95,6 @@ void mdev_unregister_parent(struct mdev_parent *parent); int mdev_register_driver(struct mdev_driver *drv); void mdev_unregister_driver(struct mdev_driver *drv); -struct device *mdev_parent_dev(struct mdev_device *mdev); static inline struct device *mdev_dev(struct mdev_device *mdev) { return &mdev->dev; -- cgit v1.2.3 From c7c1f38f6cba7e3249866c06639ea62755f0a24e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 23 Sep 2022 11:26:47 +0200 Subject: vfio/mdev: remove mtype_get_parent_dev Just open code the dereferences in the only user. Signed-off-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Reviewed-by: Jason J. Herne Reviewed-by: Kevin Tian Reviewed-by: Kirti Wankhede Reviewed-by: Eric Farman Link: https://lore.kernel.org/r/20220923092652.100656-10-hch@lst.de Signed-off-by: Alex Williamson --- include/linux/mdev.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mdev.h b/include/linux/mdev.h index bbedffcb38d4..e445f809ceca 100644 --- a/include/linux/mdev.h +++ b/include/linux/mdev.h @@ -51,8 +51,6 @@ static inline struct mdev_device *to_mdev_device(struct device *dev) return container_of(dev, struct mdev_device, dev); } -struct device *mtype_get_parent_dev(struct mdev_type *mtype); - /* interface for exporting mdev supported type attributes */ struct mdev_type_attribute { struct attribute attr; -- cgit v1.2.3 From 290aac5df88a83e264b3a73ec146e5e5b3c45793 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Fri, 23 Sep 2022 11:26:48 +0200 Subject: vfio/mdev: consolidate all the device_api sysfs into the core code Every driver just emits a static string, simply feed it through the ops and provide a standard sysfs show function. Signed-off-by: Jason Gunthorpe Signed-off-by: Christoph Hellwig Reviewed-by: Tony Krowiak Reviewed-by: Kevin Tian Reviewed-by: Kirti Wankhede Reviewed-by: Eric Farman Link: https://lore.kernel.org/r/20220923092652.100656-11-hch@lst.de Signed-off-by: Alex Williamson --- include/linux/mdev.h | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mdev.h b/include/linux/mdev.h index e445f809ceca..af1ff0165b8d 100644 --- a/include/linux/mdev.h +++ b/include/linux/mdev.h @@ -61,11 +61,6 @@ struct mdev_type_attribute { size_t count); }; -#define MDEV_TYPE_ATTR(_name, _mode, _show, _store) \ -struct mdev_type_attribute mdev_type_attr_##_name = \ - __ATTR(_name, _mode, _show, _store) -#define MDEV_TYPE_ATTR_RW(_name) \ - struct mdev_type_attribute mdev_type_attr_##_name = __ATTR_RW(_name) #define MDEV_TYPE_ATTR_RO(_name) \ struct mdev_type_attribute mdev_type_attr_##_name = __ATTR_RO(_name) #define MDEV_TYPE_ATTR_WO(_name) \ @@ -73,12 +68,14 @@ struct mdev_type_attribute mdev_type_attr_##_name = \ /** * struct mdev_driver - Mediated device driver + * @device_api: string to return for the device_api sysfs * @probe: called when new device created * @remove: called when device removed * @types_attrs: attributes to the type kobjects. * @driver: device driver structure **/ struct mdev_driver { + const char *device_api; int (*probe)(struct mdev_device *dev); void (*remove)(struct mdev_device *dev); const struct attribute * const *types_attrs; -- cgit v1.2.3 From 0bc79069ccbdbe26492493dd0c4e38b7cadf8ad5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 23 Sep 2022 11:26:49 +0200 Subject: vfio/mdev: consolidate all the name sysfs into the core code Every driver just emits a static string, simply add a field to the mdev_type for the driver to fill out or fall back to the sysfs name and provide a standard sysfs show function. Signed-off-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Reviewed-by: Kevin Tian Reviewed-by: Kirti Wankhede Reviewed-by: Eric Farman Link: https://lore.kernel.org/r/20220923092652.100656-12-hch@lst.de Signed-off-by: Alex Williamson --- include/linux/mdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mdev.h b/include/linux/mdev.h index af1ff0165b8d..4bb8a58b577b 100644 --- a/include/linux/mdev.h +++ b/include/linux/mdev.h @@ -26,6 +26,7 @@ struct mdev_device { struct mdev_type { /* set by the driver before calling mdev_register parent: */ const char *sysfs_name; + const char *pretty_name; /* set by the core, can be used drivers */ struct mdev_parent *parent; -- cgit v1.2.3 From f2fbc72e6da4f8e01fe5fe3d6871a791e76271c3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 23 Sep 2022 11:26:50 +0200 Subject: vfio/mdev: consolidate all the available_instance sysfs into the core code Every driver just print a number, simply add a method to the mdev_driver to return it and provide a standard sysfs show function. Signed-off-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Reviewed-by: Kevin Tian Reviewed-by: Kirti Wankhede Reviewed-by: Eric Farman Link: https://lore.kernel.org/r/20220923092652.100656-13-hch@lst.de Signed-off-by: Alex Williamson --- include/linux/mdev.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mdev.h b/include/linux/mdev.h index 4bb8a58b577b..d39e08a1824c 100644 --- a/include/linux/mdev.h +++ b/include/linux/mdev.h @@ -72,6 +72,7 @@ struct mdev_type_attribute { * @device_api: string to return for the device_api sysfs * @probe: called when new device created * @remove: called when device removed + * @get_available: Return the max number of instances that can be created * @types_attrs: attributes to the type kobjects. * @driver: device driver structure **/ @@ -79,6 +80,7 @@ struct mdev_driver { const char *device_api; int (*probe)(struct mdev_device *dev); void (*remove)(struct mdev_device *dev); + unsigned int (*get_available)(struct mdev_type *mtype); const struct attribute * const *types_attrs; struct device_driver driver; }; -- cgit v1.2.3 From 685a1537f4c603cfcaf4b9be56ff6a571f7ddd08 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 23 Sep 2022 11:26:51 +0200 Subject: vfio/mdev: consolidate all the description sysfs into the core code Every driver just emits a string, simply add a method to the mdev_driver to return it and provide a standard sysfs show function. Remove the now unused types_attrs field in struct mdev_driver and the support code for it. Signed-off-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Reviewed-by: Kevin Tian Reviewed-by: Kirti Wankhede Link: https://lore.kernel.org/r/20220923092652.100656-14-hch@lst.de Signed-off-by: Alex Williamson --- include/linux/mdev.h | 19 ++----------------- 1 file changed, 2 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mdev.h b/include/linux/mdev.h index d39e08a1824c..33674cb5ed5d 100644 --- a/include/linux/mdev.h +++ b/include/linux/mdev.h @@ -52,28 +52,13 @@ static inline struct mdev_device *to_mdev_device(struct device *dev) return container_of(dev, struct mdev_device, dev); } -/* interface for exporting mdev supported type attributes */ -struct mdev_type_attribute { - struct attribute attr; - ssize_t (*show)(struct mdev_type *mtype, - struct mdev_type_attribute *attr, char *buf); - ssize_t (*store)(struct mdev_type *mtype, - struct mdev_type_attribute *attr, const char *buf, - size_t count); -}; - -#define MDEV_TYPE_ATTR_RO(_name) \ - struct mdev_type_attribute mdev_type_attr_##_name = __ATTR_RO(_name) -#define MDEV_TYPE_ATTR_WO(_name) \ - struct mdev_type_attribute mdev_type_attr_##_name = __ATTR_WO(_name) - /** * struct mdev_driver - Mediated device driver * @device_api: string to return for the device_api sysfs * @probe: called when new device created * @remove: called when device removed * @get_available: Return the max number of instances that can be created - * @types_attrs: attributes to the type kobjects. + * @show_description: Print a description of the mtype * @driver: device driver structure **/ struct mdev_driver { @@ -81,7 +66,7 @@ struct mdev_driver { int (*probe)(struct mdev_device *dev); void (*remove)(struct mdev_device *dev); unsigned int (*get_available)(struct mdev_type *mtype); - const struct attribute * const *types_attrs; + ssize_t (*show_description)(struct mdev_type *mtype, char *buf); struct device_driver driver; }; -- cgit v1.2.3 From 9c799c224d6ebc5be51065bd3217a2d7eea23b8f Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Fri, 23 Sep 2022 11:26:52 +0200 Subject: vfio/mdev: add mdev available instance checking to the core Many of the mdev drivers use a simple counter for keeping track of the available instances. Move this code to the core code and store the counter in the mdev_parent. Implement it using correct locking, fixing mdpy. Drivers just provide the value in the mdev_driver at registration time and the core code takes care of maintaining it and exposing the value in sysfs. [hch: count instances per-parent instead of per-type, use an atomic_t to avoid taking mdev_list_lock in the show method] Signed-off-by: Jason Gunthorpe Signed-off-by: Christoph Hellwig Reviewed-by: Kevin Tian Reviewed-by: Kirti Wankhede Reviewed-by: Eric Farman Link: https://lore.kernel.org/r/20220923092652.100656-15-hch@lst.de Signed-off-by: Alex Williamson --- include/linux/mdev.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mdev.h b/include/linux/mdev.h index 33674cb5ed5d..139d05b26f82 100644 --- a/include/linux/mdev.h +++ b/include/linux/mdev.h @@ -45,6 +45,7 @@ struct mdev_parent { struct rw_semaphore unreg_sem; struct mdev_type **types; unsigned int nr_types; + atomic_t available_instances; }; static inline struct mdev_device *to_mdev_device(struct device *dev) @@ -55,6 +56,7 @@ static inline struct mdev_device *to_mdev_device(struct device *dev) /** * struct mdev_driver - Mediated device driver * @device_api: string to return for the device_api sysfs + * @max_instances: maximum number of instances supported (optional) * @probe: called when new device created * @remove: called when device removed * @get_available: Return the max number of instances that can be created @@ -63,6 +65,7 @@ static inline struct mdev_device *to_mdev_device(struct device *dev) **/ struct mdev_driver { const char *device_api; + unsigned int max_instances; int (*probe)(struct mdev_device *dev); void (*remove)(struct mdev_device *dev); unsigned int (*get_available)(struct mdev_type *mtype); -- cgit v1.2.3 From 34e1ed189fab1b7533befb266b96051104c1deb6 Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Mon, 8 Aug 2022 19:40:38 +0200 Subject: PM: Improve EXPORT_*_DEV_PM_OPS macros Update the _EXPORT_DEV_PM_OPS() internal macro. It was not used anywhere outside pm.h and pm_runtime.h, so it is safe to update it. Before, this macro would take a few parameters to be used as sleep and runtime callbacks. This made it unsuitable to use with different callbacks, for instance the "noirq" ones. It is now semantically different: instead of creating a conditionally exported dev_pm_ops structure, it only contains part of the definition. This macro should however never be used directly (hence the trailing underscore). Instead, the following four macros are provided: - EXPORT_DEV_PM_OPS(name) - EXPORT_GPL_DEV_PM_OPS(name) - EXPORT_NS_DEV_PM_OPS(name, ns) - EXPORT_NS_GPL_DEV_PM_OPS(name, ns) For instance, it is now possible to conditionally export noirq suspend/resume PM functions like this: EXPORT_GPL_DEV_PM_OPS(foo_pm_ops) = { NOIRQ_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) }; The existing helper macros EXPORT_*_SIMPLE_DEV_PM_OPS() and EXPORT_*_RUNTIME_DEV_PM_OPS() have been updated to use these new macros. Signed-off-by: Paul Cercueil Reviewed-by: Jonathan Cameron Signed-off-by: Rafael J. Wysocki --- include/linux/pm.h | 37 +++++++++++++++++++++++-------------- include/linux/pm_runtime.h | 20 ++++++++++++-------- 2 files changed, 35 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index 871c9c49ec9d..93cd34f00822 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -375,19 +375,20 @@ const struct dev_pm_ops name = { \ } #ifdef CONFIG_PM -#define _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, runtime_suspend_fn, \ - runtime_resume_fn, idle_fn, sec, ns) \ - _DEFINE_DEV_PM_OPS(name, suspend_fn, resume_fn, runtime_suspend_fn, \ - runtime_resume_fn, idle_fn); \ - __EXPORT_SYMBOL(name, sec, ns) +#define _EXPORT_DEV_PM_OPS(name, sec, ns) \ + const struct dev_pm_ops name; \ + __EXPORT_SYMBOL(name, sec, ns); \ + const struct dev_pm_ops name #else -#define _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, runtime_suspend_fn, \ - runtime_resume_fn, idle_fn, sec, ns) \ -static __maybe_unused _DEFINE_DEV_PM_OPS(__static_##name, suspend_fn, \ - resume_fn, runtime_suspend_fn, \ - runtime_resume_fn, idle_fn) +#define _EXPORT_DEV_PM_OPS(name, sec, ns) \ + static __maybe_unused const struct dev_pm_ops __static_##name #endif +#define EXPORT_DEV_PM_OPS(name) _EXPORT_DEV_PM_OPS(name, "", "") +#define EXPORT_GPL_DEV_PM_OPS(name) _EXPORT_DEV_PM_OPS(name, "_gpl", "") +#define EXPORT_NS_DEV_PM_OPS(name, ns) _EXPORT_DEV_PM_OPS(name, "", #ns) +#define EXPORT_NS_GPL_DEV_PM_OPS(name, ns) _EXPORT_DEV_PM_OPS(name, "_gpl", #ns) + /* * Use this if you want to use the same suspend and resume callbacks for suspend * to RAM and hibernation. @@ -399,13 +400,21 @@ static __maybe_unused _DEFINE_DEV_PM_OPS(__static_##name, suspend_fn, \ _DEFINE_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL) #define EXPORT_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ - _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL, "", "") + EXPORT_DEV_PM_OPS(name) = { \ + SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ + } #define EXPORT_GPL_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ - _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL, "_gpl", "") + EXPORT_GPL_DEV_PM_OPS(name) = { \ + SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ + } #define EXPORT_NS_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn, ns) \ - _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL, "", #ns) + EXPORT_NS_DEV_PM_OPS(name, ns) = { \ + SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ + } #define EXPORT_NS_GPL_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn, ns) \ - _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL, "_gpl", #ns) + EXPORT_NS_GPL_DEV_PM_OPS(name, ns) = { \ + SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ + } /* Deprecated. Use DEFINE_SIMPLE_DEV_PM_OPS() instead. */ #define SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 0a41b2dcccad..9a8151a2bdea 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -40,17 +40,21 @@ resume_fn, idle_fn) #define EXPORT_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ - _EXPORT_DEV_PM_OPS(name, pm_runtime_force_suspend, pm_runtime_force_resume, \ - suspend_fn, resume_fn, idle_fn, "", "") + EXPORT_DEV_PM_OPS(name) = { \ + RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ + } #define EXPORT_GPL_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ - _EXPORT_DEV_PM_OPS(name, pm_runtime_force_suspend, pm_runtime_force_resume, \ - suspend_fn, resume_fn, idle_fn, "_gpl", "") + EXPORT_GPL_DEV_PM_OPS(name) = { \ + RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ + } #define EXPORT_NS_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn, ns) \ - _EXPORT_DEV_PM_OPS(name, pm_runtime_force_suspend, pm_runtime_force_resume, \ - suspend_fn, resume_fn, idle_fn, "", #ns) + EXPORT_NS_DEV_PM_OPS(name, ns) = { \ + RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ + } #define EXPORT_NS_GPL_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn, ns) \ - _EXPORT_DEV_PM_OPS(name, pm_runtime_force_suspend, pm_runtime_force_resume, \ - suspend_fn, resume_fn, idle_fn, "_gpl", #ns) + EXPORT_NS_GPL_DEV_PM_OPS(name, ns) = { \ + RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ + } #ifdef CONFIG_PM extern struct workqueue_struct *pm_wq; -- cgit v1.2.3 From a9cfee0ef98e99c8b1951dfd1d57a88580354d0d Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Wed, 28 Sep 2022 23:38:53 +0800 Subject: f2fs: support recording stop_checkpoint reason into super_block This patch supports to record stop_checkpoint error into f2fs_super_block.s_stop_reason[]. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index d445150c5350..5dd1e52b8997 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -73,6 +73,20 @@ struct f2fs_device { __le32 total_segments; } __packed; +/* reason of stop_checkpoint */ +enum stop_cp_reason { + STOP_CP_REASON_SHUTDOWN, + STOP_CP_REASON_FAULT_INJECT, + STOP_CP_REASON_META_PAGE, + STOP_CP_REASON_WRITE_FAIL, + STOP_CP_REASON_CORRUPTED_SUMMARY, + STOP_CP_REASON_UPDATE_INODE, + STOP_CP_REASON_FLUSH_FAIL, + STOP_CP_REASON_MAX, +}; + +#define MAX_STOP_REASON 32 + struct f2fs_super_block { __le32 magic; /* Magic Number */ __le16 major_ver; /* Major Version */ @@ -116,7 +130,8 @@ struct f2fs_super_block { __u8 hot_ext_count; /* # of hot file extension */ __le16 s_encoding; /* Filename charset encoding */ __le16 s_encoding_flags; /* Filename charset encoding flags */ - __u8 reserved[306]; /* valid reserved region */ + __u8 s_stop_reason[MAX_STOP_REASON]; /* stop checkpoint reason */ + __u8 reserved[274]; /* valid reserved region */ __le32 crc; /* checksum of superblock */ } __packed; -- cgit v1.2.3 From 95fa90c9e5a7f14c2497d5b032544478c9377c3a Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Wed, 28 Sep 2022 23:38:54 +0800 Subject: f2fs: support recording errors into superblock This patch supports to record detail reason of FSCORRUPTED error into f2fs_super_block.s_errors[]. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 25 ++++++++++++++++++++++++- 1 file changed, 24 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 5dd1e52b8997..ee0d75d9a302 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -87,6 +87,28 @@ enum stop_cp_reason { #define MAX_STOP_REASON 32 +/* detail reason for EFSCORRUPTED */ +enum f2fs_error { + ERROR_CORRUPTED_CLUSTER, + ERROR_FAIL_DECOMPRESSION, + ERROR_INVALID_BLKADDR, + ERROR_CORRUPTED_DIRENT, + ERROR_CORRUPTED_INODE, + ERROR_INCONSISTENT_SUMMARY, + ERROR_INCONSISTENT_FOOTER, + ERROR_INCONSISTENT_SUM_TYPE, + ERROR_CORRUPTED_JOURNAL, + ERROR_INCONSISTENT_NODE_COUNT, + ERROR_INCONSISTENT_BLOCK_COUNT, + ERROR_INVALID_CURSEG, + ERROR_INCONSISTENT_SIT, + ERROR_CORRUPTED_VERITY_XATTR, + ERROR_CORRUPTED_XATTR, + ERROR_MAX, +}; + +#define MAX_F2FS_ERRORS 16 + struct f2fs_super_block { __le32 magic; /* Magic Number */ __le16 major_ver; /* Major Version */ @@ -131,7 +153,8 @@ struct f2fs_super_block { __le16 s_encoding; /* Filename charset encoding */ __le16 s_encoding_flags; /* Filename charset encoding flags */ __u8 s_stop_reason[MAX_STOP_REASON]; /* stop checkpoint reason */ - __u8 reserved[274]; /* valid reserved region */ + __u8 s_errors[MAX_F2FS_ERRORS]; /* reason of image corrupts */ + __u8 reserved[258]; /* valid reserved region */ __le32 crc; /* checksum of superblock */ } __packed; -- cgit v1.2.3 From 07d2872bf4c864eb83d034263c155746a2fb7a3b Mon Sep 17 00:00:00 2001 From: Avri Altman Date: Wed, 28 Sep 2022 12:57:44 +0300 Subject: mmc: core: Add SD card quirk for broken discard Some SD-cards from Sandisk that are SDA-6.0 compliant reports they supports discard, while they actually don't. This might cause mk2fs to fail while trying to format the card and revert it to a read-only mode. To fix this problem, let's add a card quirk (MMC_QUIRK_BROKEN_SD_DISCARD) to indicate that we shall fall-back to use the legacy erase command instead. Signed-off-by: Avri Altman Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220928095744.16455-1-avri.altman@wdc.com [Ulf: Updated the commit message] Signed-off-by: Ulf Hansson --- include/linux/mmc/card.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index 8a30de08e913..c726ea781255 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -293,6 +293,7 @@ struct mmc_card { #define MMC_QUIRK_BROKEN_IRQ_POLLING (1<<11) /* Polling SDIO_CCCR_INTx could create a fake interrupt */ #define MMC_QUIRK_TRIM_BROKEN (1<<12) /* Skip trim */ #define MMC_QUIRK_BROKEN_HPI (1<<13) /* Disable broken HPI support */ +#define MMC_QUIRK_BROKEN_SD_DISCARD (1<<14) /* Disable broken SD discard support */ bool reenable_cmdq; /* Re-enable Command Queue */ -- cgit v1.2.3 From 90d482908eedd56f01a707325aa541cf9c40f936 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Mon, 3 Oct 2022 16:34:17 +0100 Subject: lib/find_bit: Introduce find_next_andnot_bit() In preparation of introducing for_each_cpu_andnot(), add a variant of find_next_bit() that negate the bits in @addr2 when ANDing them with the bits in @addr1. Signed-off-by: Valentin Schneider --- include/linux/find.h | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) (limited to 'include/linux') diff --git a/include/linux/find.h b/include/linux/find.h index 0cdfab9734a6..2235af19e7e1 100644 --- a/include/linux/find.h +++ b/include/linux/find.h @@ -12,6 +12,8 @@ unsigned long _find_next_bit(const unsigned long *addr1, unsigned long nbits, unsigned long start); unsigned long _find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long nbits, unsigned long start); +unsigned long _find_next_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long nbits, unsigned long start); unsigned long _find_next_zero_bit(const unsigned long *addr, unsigned long nbits, unsigned long start); extern unsigned long _find_first_bit(const unsigned long *addr, unsigned long size); @@ -91,6 +93,37 @@ unsigned long find_next_and_bit(const unsigned long *addr1, } #endif +#ifndef find_next_andnot_bit +/** + * find_next_andnot_bit - find the next set bit in *addr1 excluding all the bits + * in *addr2 + * @addr1: The first address to base the search on + * @addr2: The second address to base the search on + * @size: The bitmap size in bits + * @offset: The bitnumber to start searching at + * + * Returns the bit number for the next set bit + * If no bits are set, returns @size. + */ +static inline +unsigned long find_next_andnot_bit(const unsigned long *addr1, + const unsigned long *addr2, unsigned long size, + unsigned long offset) +{ + if (small_const_nbits(size)) { + unsigned long val; + + if (unlikely(offset >= size)) + return size; + + val = *addr1 & ~*addr2 & GENMASK(size - 1, offset); + return val ? __ffs(val) : size; + } + + return _find_next_andnot_bit(addr1, addr2, size, offset); +} +#endif + #ifndef find_next_zero_bit /** * find_next_zero_bit - find the next cleared bit in a memory region -- cgit v1.2.3 From 5f75ff295c662c1c8fb9e1737e9dc3b9a1e7fb29 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Mon, 3 Oct 2022 16:34:18 +0100 Subject: cpumask: Introduce for_each_cpu_andnot() for_each_cpu_and() is very convenient as it saves having to allocate a temporary cpumask to store the result of cpumask_and(). The same issue applies to cpumask_andnot() which doesn't actually need temporary storage for iteration purposes. Following what has been done for for_each_cpu_and(), introduce for_each_cpu_andnot(). Signed-off-by: Valentin Schneider --- include/linux/cpumask.h | 18 ++++++++++++++++++ include/linux/find.h | 5 +++++ 2 files changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 286804bfe3b7..2f065ad97541 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -306,6 +306,24 @@ unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int sta #define for_each_cpu_and(cpu, mask1, mask2) \ for_each_and_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), nr_cpumask_bits) +/** + * for_each_cpu_andnot - iterate over every cpu present in one mask, excluding + * those present in another. + * @cpu: the (optionally unsigned) integer iterator + * @mask1: the first cpumask pointer + * @mask2: the second cpumask pointer + * + * This saves a temporary CPU mask in many places. It is equivalent to: + * struct cpumask tmp; + * cpumask_andnot(&tmp, &mask1, &mask2); + * for_each_cpu(cpu, &tmp) + * ... + * + * After the loop, cpu is >= nr_cpu_ids. + */ +#define for_each_cpu_andnot(cpu, mask1, mask2) \ + for_each_andnot_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), nr_cpumask_bits) + /** * cpumask_any_but - return a "random" in a cpumask, but not this one. * @mask: the cpumask to search diff --git a/include/linux/find.h b/include/linux/find.h index 2235af19e7e1..ccaf61a0f5fd 100644 --- a/include/linux/find.h +++ b/include/linux/find.h @@ -498,6 +498,11 @@ unsigned long find_next_bit_le(const void *addr, unsigned (bit) = find_next_and_bit((addr1), (addr2), (size), (bit)), (bit) < (size);\ (bit)++) +#define for_each_andnot_bit(bit, addr1, addr2, size) \ + for ((bit) = 0; \ + (bit) = find_next_andnot_bit((addr1), (addr2), (size), (bit)), (bit) < (size);\ + (bit)++) + /* same as for_each_set_bit() but use bit as value to start with */ #define for_each_set_bit_from(bit, addr, size) \ for (; (bit) = find_next_bit((addr), (size), (bit)), (bit) < (size); (bit)++) -- cgit v1.2.3 From 39494194f93bed7926d4b3bd03a6a76ba23e612b Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 5 Oct 2022 15:57:35 -0400 Subject: SUNRPC: Fix races with rpc_killall_tasks() Ensure that we immediately call rpc_exit_task() after waking up, and that the tk_rpc_status cannot get clobbered by some other function. Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- include/linux/sunrpc/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index acc62647317c..647247040ef9 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -209,6 +209,7 @@ struct rpc_task *rpc_run_task(const struct rpc_task_setup *); struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req); void rpc_put_task(struct rpc_task *); void rpc_put_task_async(struct rpc_task *); +bool rpc_task_set_rpc_status(struct rpc_task *task, int rpc_status); void rpc_signal_task(struct rpc_task *); void rpc_exit_task(struct rpc_task *); void rpc_exit(struct rpc_task *, int); -- cgit v1.2.3 From f8423909ecca208834a9d704e58409800f8b5f21 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 5 Oct 2022 15:57:36 -0400 Subject: SUNRPC: Add a helper to allow pNFS drivers to selectively cancel RPC calls Add the helper rpc_cancel_tasks(), which uses a caller-defined selection function to define a set of in-flight RPC calls to cancel. This is mainly intended for pNFS drivers which are subject to a layout recall, and which may therefore want to cancel all pending I/O using that layout in order to redrive it after the layout recall has been satisfied. Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- include/linux/sunrpc/sched.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 647247040ef9..cdcf0fe56a6f 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -210,11 +210,16 @@ struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req); void rpc_put_task(struct rpc_task *); void rpc_put_task_async(struct rpc_task *); bool rpc_task_set_rpc_status(struct rpc_task *task, int rpc_status); +void rpc_task_try_cancel(struct rpc_task *task, int error); void rpc_signal_task(struct rpc_task *); void rpc_exit_task(struct rpc_task *); void rpc_exit(struct rpc_task *, int); void rpc_release_calldata(const struct rpc_call_ops *, void *); void rpc_killall_tasks(struct rpc_clnt *); +unsigned long rpc_cancel_tasks(struct rpc_clnt *clnt, int error, + bool (*fnmatch)(const struct rpc_task *, + const void *), + const void *data); void rpc_execute(struct rpc_task *); void rpc_init_priority_wait_queue(struct rpc_wait_queue *, const char *); void rpc_init_wait_queue(struct rpc_wait_queue *, const char *); -- cgit v1.2.3 From dc4c4304855a5721d214e2a53e17df5152dd5f34 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 5 Oct 2022 15:57:37 -0400 Subject: SUNRPC: Add API to force the client to disconnect Allow the caller to force a disconnection of the RPC client so that we can clear any pending requests that are buffered in the socket. Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- include/linux/sunrpc/clnt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 75eea5ebb179..770ef2cb5775 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -246,6 +246,7 @@ void rpc_clnt_xprt_switch_remove_xprt(struct rpc_clnt *, struct rpc_xprt *); bool rpc_clnt_xprt_switch_has_addr(struct rpc_clnt *clnt, const struct sockaddr *sap); void rpc_clnt_xprt_set_online(struct rpc_clnt *clnt, struct rpc_xprt *xprt); +void rpc_clnt_disconnect(struct rpc_clnt *clnt); void rpc_cleanup_clids(void); static inline int rpc_reply_expected(struct rpc_task *task) -- cgit v1.2.3 From e3e6e1d16a4cf7b63159ec71774e822194071954 Mon Sep 17 00:00:00 2001 From: Hawkins Jiawei Date: Tue, 27 Sep 2022 07:34:59 +0800 Subject: wifi: wext: use flex array destination for memcpy() Syzkaller reports buffer overflow false positive as follows: ------------[ cut here ]------------ memcpy: detected field-spanning write (size 8) of single field "&compat_event->pointer" at net/wireless/wext-core.c:623 (size 4) WARNING: CPU: 0 PID: 3607 at net/wireless/wext-core.c:623 wireless_send_event+0xab5/0xca0 net/wireless/wext-core.c:623 Modules linked in: CPU: 1 PID: 3607 Comm: syz-executor659 Not tainted 6.0.0-rc6-next-20220921-syzkaller #0 [...] Call Trace: ioctl_standard_call+0x155/0x1f0 net/wireless/wext-core.c:1022 wireless_process_ioctl+0xc8/0x4c0 net/wireless/wext-core.c:955 wext_ioctl_dispatch net/wireless/wext-core.c:988 [inline] wext_ioctl_dispatch net/wireless/wext-core.c:976 [inline] wext_handle_ioctl+0x26b/0x280 net/wireless/wext-core.c:1049 sock_ioctl+0x285/0x640 net/socket.c:1220 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:870 [inline] __se_sys_ioctl fs/ioctl.c:856 [inline] __x64_sys_ioctl+0x193/0x200 fs/ioctl.c:856 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd [...] Wireless events will be sent on the appropriate channels in wireless_send_event(). Different wireless events may have different payload structure and size, so kernel uses **len** and **cmd** field in struct __compat_iw_event as wireless event common LCP part, uses **pointer** as a label to mark the position of remaining different part. Yet the problem is that, **pointer** is a compat_caddr_t type, which may be smaller than the relative structure at the same position. So during wireless_send_event() tries to parse the wireless events payload, it may trigger the memcpy() run-time destination buffer bounds checking when the relative structure's data is copied to the position marked by **pointer**. This patch solves it by introducing flexible-array field **ptr_bytes**, to mark the position of the wireless events remaining part next to LCP part. What's more, this patch also adds **ptr_len** variable in wireless_send_event() to improve its maintainability. Reported-and-tested-by: syzbot+473754e5af963cf014cf@syzkaller.appspotmail.com Link: https://lore.kernel.org/all/00000000000070db2005e95a5984@google.com/ Suggested-by: Kees Cook Reviewed-by: Kees Cook Signed-off-by: Hawkins Jiawei Signed-off-by: Johannes Berg --- include/linux/wireless.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/wireless.h b/include/linux/wireless.h index 2d1b54556eff..e6e34d74dda0 100644 --- a/include/linux/wireless.h +++ b/include/linux/wireless.h @@ -26,7 +26,15 @@ struct compat_iw_point { struct __compat_iw_event { __u16 len; /* Real length of this stuff */ __u16 cmd; /* Wireless IOCTL */ - compat_caddr_t pointer; + + union { + compat_caddr_t pointer; + + /* we need ptr_bytes to make memcpy() run-time destination + * buffer bounds checking happy, nothing special + */ + DECLARE_FLEX_ARRAY(__u8, ptr_bytes); + }; }; #define IW_EV_COMPAT_LCP_LEN offsetof(struct __compat_iw_event, pointer) #define IW_EV_COMPAT_POINT_OFF offsetof(struct compat_iw_point, length) -- cgit v1.2.3 From cdbd952bb7b5fca36676b3d318796b196b127397 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Mon, 15 Aug 2022 18:04:20 -0400 Subject: virtio: drop vp_legacy_set_queue_size There's actually no way to set queue size on legacy virtio pci. Signed-off-by: Michael S. Tsirkin Message-Id: <20220815220447.155860-1-mst@redhat.com> --- include/linux/virtio_pci_legacy.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio_pci_legacy.h b/include/linux/virtio_pci_legacy.h index e5d665faf00e..a8dc757d0367 100644 --- a/include/linux/virtio_pci_legacy.h +++ b/include/linux/virtio_pci_legacy.h @@ -32,8 +32,6 @@ void vp_legacy_set_queue_address(struct virtio_pci_legacy_device *ldev, u16 index, u32 queue_pfn); bool vp_legacy_get_queue_enable(struct virtio_pci_legacy_device *ldev, u16 idx); -void vp_legacy_set_queue_size(struct virtio_pci_legacy_device *ldev, - u16 idx, u16 size); u16 vp_legacy_get_queue_size(struct virtio_pci_legacy_device *ldev, u16 idx); int vp_legacy_probe(struct virtio_pci_legacy_device *ldev); -- cgit v1.2.3 From 90fea5a800c3dd80fb8ad9a02929bcef5fde42b8 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Tue, 27 Sep 2022 15:48:08 +0800 Subject: vdpa: device feature provisioning This patch allows the device features to be provisioned through netlink. A new attribute is introduced to allow the userspace to pass a 64bit device features during device adding. This provides several advantages: - Allow to provision a subset of the features to ease the cross vendor live migration. - Better debug-ability for vDPA framework and parent. Reviewed-by: Eli Cohen Signed-off-by: Jason Wang Message-Id: <20220927074810.28627-2-jasowang@redhat.com> Signed-off-by: Michael S. Tsirkin --- include/linux/vdpa.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index d282f464d2f1..6d0f5e4e82c2 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -104,6 +104,7 @@ struct vdpa_iova_range { }; struct vdpa_dev_set_config { + u64 device_features; struct { u8 mac[ETH_ALEN]; u16 mtu; -- cgit v1.2.3 From 4b22ef042d6f54a6e5899555f2db71749133eca8 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Fri, 7 Oct 2022 11:04:39 -0300 Subject: vfio: Add vfio_file_is_group() This replaces uses of vfio_file_iommu_group() which were only detecting if the file is a VFIO file with no interest in the actual group. The only remaning user of vfio_file_iommu_group() is in KVM for the SPAPR stuff. It passes the iommu_group into the arch code through kvm for some reason. Tested-by: Matthew Rosato Tested-by: Christian Borntraeger Tested-by: Eric Farman Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/1-v2-15417f29324e+1c-vfio_group_disassociate_jgg@nvidia.com Signed-off-by: Alex Williamson --- include/linux/vfio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index ee399a768070..e7cebeb875dd 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -199,6 +199,7 @@ int vfio_mig_get_next_state(struct vfio_device *device, * External user API */ struct iommu_group *vfio_file_iommu_group(struct file *file); +bool vfio_file_is_group(struct file *file); bool vfio_file_enforced_coherent(struct file *file); void vfio_file_set_kvm(struct file *file, struct kvm *kvm); bool vfio_file_has_dev(struct file *file, struct vfio_device *device); -- cgit v1.2.3 From 9afd20a5a1b3558950b5e12f3ed057ef93c64a05 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Mon, 10 Oct 2022 09:52:37 +0530 Subject: clk: spear: Move prototype to accessible header Fixes the following W=1 kernel build warning(s): drivers/clk/spear/spear6xx_clock.c:116:13: warning: no previous prototype for function 'spear6xx_clk_init' [-Wmissing-prototypes] Reported-by: kernel test robot Signed-off-by: Viresh Kumar Signed-off-by: Arnd Bergmann --- include/linux/clk/spear.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk/spear.h b/include/linux/clk/spear.h index a64d034ceddd..eaf95ca656f8 100644 --- a/include/linux/clk/spear.h +++ b/include/linux/clk/spear.h @@ -8,6 +8,20 @@ #ifndef __LINUX_CLK_SPEAR_H #define __LINUX_CLK_SPEAR_H +#ifdef CONFIG_ARCH_SPEAR3XX +void __init spear3xx_clk_init(void __iomem *misc_base, + void __iomem *soc_config_base); +#else +static inline void __init spear3xx_clk_init(void __iomem *misc_base, + void __iomem *soc_config_base) {} +#endif + +#ifdef CONFIG_ARCH_SPEAR6XX +void __init spear6xx_clk_init(void __iomem *misc_base); +#else +static inline void __init spear6xx_clk_init(void __iomem *misc_base) {} +#endif + #ifdef CONFIG_MACH_SPEAR1310 void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base); #else -- cgit v1.2.3 From ca5eebda3e1c1a58a1c5a337da393ed6734593e3 Mon Sep 17 00:00:00 2001 From: Brian Foster Date: Mon, 3 Oct 2022 09:35:34 -0400 Subject: block: avoid sign extend problem with default queue flags mask request_queue->queue_flags is unsigned long, which is 8-bytes on 64-bit architectures. Most queue flag modifications occur through bit field helpers, but default flags can be logically OR'd via the QUEUE_FLAG_MQ_DEFAULT mask. If this mask happens to include bit 31, the assignment can sign extend the field and set all upper 32 bits. This exact problem has been observed on a downstream kernel that happens to use bit 31 for QUEUE_FLAG_NOWAIT. This is not an immediate problem for current upstream because bit 31 is not included in the default flag assignment (and is not used at all, actually). Regardless, fix up the QUEUE_FLAG_MQ_DEFAULT mask definition to avoid the landmine in the future. Signed-off-by: Brian Foster Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20221003133534.1075582-1-bfoster@redhat.com Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 49373d002631..e4fb47753177 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -580,9 +580,9 @@ struct request_queue { #define QUEUE_FLAG_NOWAIT 29 /* device supports NOWAIT */ #define QUEUE_FLAG_SQ_SCHED 30 /* single queue style io dispatch */ -#define QUEUE_FLAG_MQ_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ - (1 << QUEUE_FLAG_SAME_COMP) | \ - (1 << QUEUE_FLAG_NOWAIT)) +#define QUEUE_FLAG_MQ_DEFAULT ((1UL << QUEUE_FLAG_IO_STAT) | \ + (1UL << QUEUE_FLAG_SAME_COMP) | \ + (1UL << QUEUE_FLAG_NOWAIT)) void blk_queue_flag_set(unsigned int flag, struct request_queue *q); void blk_queue_flag_clear(unsigned int flag, struct request_queue *q); -- cgit v1.2.3 From 81895a65ec63ee1daec3255dc1a06675d2fbe915 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 5 Oct 2022 16:43:38 +0200 Subject: treewide: use prandom_u32_max() when possible, part 1 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Rather than incurring a division or requesting too many random bytes for the given range, use the prandom_u32_max() function, which only takes the minimum required bytes from the RNG and avoids divisions. This was done mechanically with this coccinelle script: @basic@ expression E; type T; identifier get_random_u32 =~ "get_random_int|prandom_u32|get_random_u32"; typedef u64; @@ ( - ((T)get_random_u32() % (E)) + prandom_u32_max(E) | - ((T)get_random_u32() & ((E) - 1)) + prandom_u32_max(E * XXX_MAKE_SURE_E_IS_POW2) | - ((u64)(E) * get_random_u32() >> 32) + prandom_u32_max(E) | - ((T)get_random_u32() & ~PAGE_MASK) + prandom_u32_max(PAGE_SIZE) ) @multi_line@ identifier get_random_u32 =~ "get_random_int|prandom_u32|get_random_u32"; identifier RAND; expression E; @@ - RAND = get_random_u32(); ... when != RAND - RAND %= (E); + RAND = prandom_u32_max(E); // Find a potential literal @literal_mask@ expression LITERAL; type T; identifier get_random_u32 =~ "get_random_int|prandom_u32|get_random_u32"; position p; @@ ((T)get_random_u32()@p & (LITERAL)) // Add one to the literal. @script:python add_one@ literal << literal_mask.LITERAL; RESULT; @@ value = None if literal.startswith('0x'): value = int(literal, 16) elif literal[0] in '123456789': value = int(literal, 10) if value is None: print("I don't know how to handle %s" % (literal)) cocci.include_match(False) elif value == 2**32 - 1 or value == 2**31 - 1 or value == 2**24 - 1 or value == 2**16 - 1 or value == 2**8 - 1: print("Skipping 0x%x for cleanup elsewhere" % (value)) cocci.include_match(False) elif value & (value + 1) != 0: print("Skipping 0x%x because it's not a power of two minus one" % (value)) cocci.include_match(False) elif literal.startswith('0x'): coccinelle.RESULT = cocci.make_expr("0x%x" % (value + 1)) else: coccinelle.RESULT = cocci.make_expr("%d" % (value + 1)) // Replace the literal mask with the calculated result. @plus_one@ expression literal_mask.LITERAL; position literal_mask.p; expression add_one.RESULT; identifier FUNC; @@ - (FUNC()@p & (LITERAL)) + prandom_u32_max(RESULT) @collapse_ret@ type T; identifier VAR; expression E; @@ { - T VAR; - VAR = (E); - return VAR; + return E; } @drop_var@ type T; identifier VAR; @@ { - T VAR; ... when != VAR } Reviewed-by: Greg Kroah-Hartman Reviewed-by: Kees Cook Reviewed-by: Yury Norov Reviewed-by: KP Singh Reviewed-by: Jan Kara # for ext4 and sbitmap Reviewed-by: Christoph Böhmwalder # for drbd Acked-by: Jakub Kicinski Acked-by: Heiko Carstens # for s390 Acked-by: Ulf Hansson # for mmc Acked-by: Darrick J. Wong # for xfs Signed-off-by: Jason A. Donenfeld --- include/linux/nodemask.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 378956c93c94..efef68c9352a 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -516,7 +516,7 @@ static inline int node_random(const nodemask_t *maskp) bit = first_node(*maskp); break; default: - bit = find_nth_bit(maskp->bits, MAX_NUMNODES, get_random_int() % w); + bit = find_nth_bit(maskp->bits, MAX_NUMNODES, prandom_u32_max(w)); break; } return bit; -- cgit v1.2.3 From de492c83cae0af72de370b9404aacda93dafcad5 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 5 Oct 2022 17:50:20 +0200 Subject: prandom: remove unused functions With no callers left of prandom_u32() and prandom_bytes(), as well as get_random_int(), remove these deprecated wrappers, in favor of get_random_u32() and get_random_bytes(). Reviewed-by: Greg Kroah-Hartman Reviewed-by: Kees Cook Reviewed-by: Yury Norov Acked-by: Jakub Kicinski Signed-off-by: Jason A. Donenfeld --- include/linux/prandom.h | 12 ------------ include/linux/random.h | 5 ----- 2 files changed, 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/prandom.h b/include/linux/prandom.h index 78db003bc290..e0a0759dd09c 100644 --- a/include/linux/prandom.h +++ b/include/linux/prandom.h @@ -12,18 +12,6 @@ #include #include -/* Deprecated: use get_random_u32 instead. */ -static inline u32 prandom_u32(void) -{ - return get_random_u32(); -} - -/* Deprecated: use get_random_bytes instead. */ -static inline void prandom_bytes(void *buf, size_t nbytes) -{ - return get_random_bytes(buf, nbytes); -} - struct rnd_state { __u32 s1, s2, s3, s4; }; diff --git a/include/linux/random.h b/include/linux/random.h index 08322f700cdc..147a5e0d0b8e 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -42,10 +42,6 @@ u8 get_random_u8(void); u16 get_random_u16(void); u32 get_random_u32(void); u64 get_random_u64(void); -static inline unsigned int get_random_int(void) -{ - return get_random_u32(); -} static inline unsigned long get_random_long(void) { #if BITS_PER_LONG == 64 @@ -100,7 +96,6 @@ declare_get_random_var_wait(u8, u8) declare_get_random_var_wait(u16, u16) declare_get_random_var_wait(u32, u32) declare_get_random_var_wait(u64, u32) -declare_get_random_var_wait(int, unsigned int) declare_get_random_var_wait(long, unsigned long) #undef declare_get_random_var -- cgit v1.2.3 From 6a961bffd1c3505c13b4d33bbb8385fe08239cb8 Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Fri, 2 Sep 2022 11:41:46 +0800 Subject: include/linux/entry-common.h: remove has_signal comment of arch_do_signal_or_restart() prototype The argument has_signal of arch_do_signal_or_restart() has been removed in commit 8ba62d37949e ("task_work: Call tracehook_notify_signal from get_signal on all architectures"), let us remove the related comment. Link: https://lkml.kernel.org/r/1662090106-5545-1-git-send-email-yangtiezhu@loongson.cn Fixes: 8ba62d37949e ("task_work: Call tracehook_notify_signal from get_signal on all architectures") Signed-off-by: Tiezhu Yang Reviewed-by: Kees Cook Signed-off-by: Andrew Morton --- include/linux/entry-common.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h index 84a466b176cf..d95ab85f96ba 100644 --- a/include/linux/entry-common.h +++ b/include/linux/entry-common.h @@ -253,7 +253,6 @@ static __always_inline void arch_exit_to_user_mode(void) { } /** * arch_do_signal_or_restart - Architecture specific signal delivery function * @regs: Pointer to currents pt_regs - * @has_signal: actual signal to handle * * Invoked from exit_to_user_mode_loop(). */ -- cgit v1.2.3 From fac35ba763ed07ba93154c95ffc0c4a55023707f Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Thu, 1 Sep 2022 18:41:31 +0800 Subject: mm/hugetlb: fix races when looking up a CONT-PTE/PMD size hugetlb page On some architectures (like ARM64), it can support CONT-PTE/PMD size hugetlb, which means it can support not only PMD/PUD size hugetlb (2M and 1G), but also CONT-PTE/PMD size(64K and 32M) if a 4K page size specified. So when looking up a CONT-PTE size hugetlb page by follow_page(), it will use pte_offset_map_lock() to get the pte entry lock for the CONT-PTE size hugetlb in follow_page_pte(). However this pte entry lock is incorrect for the CONT-PTE size hugetlb, since we should use huge_pte_lock() to get the correct lock, which is mm->page_table_lock. That means the pte entry of the CONT-PTE size hugetlb under current pte lock is unstable in follow_page_pte(), we can continue to migrate or poison the pte entry of the CONT-PTE size hugetlb, which can cause some potential race issues, even though they are under the 'pte lock'. For example, suppose thread A is trying to look up a CONT-PTE size hugetlb page by move_pages() syscall under the lock, however antoher thread B can migrate the CONT-PTE hugetlb page at the same time, which will cause thread A to get an incorrect page, if thread A also wants to do page migration, then data inconsistency error occurs. Moreover we have the same issue for CONT-PMD size hugetlb in follow_huge_pmd(). To fix above issues, rename the follow_huge_pmd() as follow_huge_pmd_pte() to handle PMD and PTE level size hugetlb, which uses huge_pte_lock() to get the correct pte entry lock to make the pte entry stable. Mike said: Support for CONT_PMD/_PTE was added with bb9dd3df8ee9 ("arm64: hugetlb: refactor find_num_contig()"). Patch series "Support for contiguous pte hugepages", v4. However, I do not believe these code paths were executed until migration support was added with 5480280d3f2d ("arm64/mm: enable HugeTLB migration for contiguous bit HugeTLB pages") I would go with 5480280d3f2d for the Fixes: targe. Link: https://lkml.kernel.org/r/635f43bdd85ac2615a58405da82b4d33c6e5eb05.1662017562.git.baolin.wang@linux.alibaba.com Fixes: 5480280d3f2d ("arm64/mm: enable HugeTLB migration for contiguous bit HugeTLB pages") Signed-off-by: Baolin Wang Suggested-by: Mike Kravetz Reviewed-by: Mike Kravetz Cc: David Hildenbrand Cc: Muchun Song Cc: Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 3ec981a0d8b3..67c88b82fc32 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -207,8 +207,8 @@ struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, struct page *follow_huge_pd(struct vm_area_struct *vma, unsigned long address, hugepd_t hpd, int flags, int pdshift); -struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, - pmd_t *pmd, int flags); +struct page *follow_huge_pmd_pte(struct vm_area_struct *vma, unsigned long address, + int flags); struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address, pud_t *pud, int flags); struct page *follow_huge_pgd(struct mm_struct *mm, unsigned long address, @@ -312,8 +312,8 @@ static inline struct page *follow_huge_pd(struct vm_area_struct *vma, return NULL; } -static inline struct page *follow_huge_pmd(struct mm_struct *mm, - unsigned long address, pmd_t *pmd, int flags) +static inline struct page *follow_huge_pmd_pte(struct vm_area_struct *vma, + unsigned long address, int flags) { return NULL; } -- cgit v1.2.3 From 0091bfc81741b8d3aeb3b7ab8636f911b2de6e80 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Mon, 3 Oct 2022 13:59:47 +0100 Subject: io_uring/af_unix: defer registered files gc to io_uring release Instead of putting io_uring's registered files in unix_gc() we want it to be done by io_uring itself. The trick here is to consider io_uring registered files for cycle detection but not actually putting them down. Because io_uring can't register other ring instances, this will remove all refs to the ring file triggering the ->release path and clean up with io_ring_ctx_free(). Cc: stable@vger.kernel.org Fixes: 6b06314c47e1 ("io_uring: add file set registration") Reported-and-tested-by: David Bouman Signed-off-by: Pavel Begunkov Signed-off-by: Thadeu Lima de Souza Cascardo [axboe: add kerneldoc comment to skb, fold in skb leak fix] Signed-off-by: Jens Axboe --- include/linux/skbuff.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9fcf534f2d92..7be5bb4c94b6 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -803,6 +803,7 @@ typedef unsigned char *sk_buff_data_t; * @csum_level: indicates the number of consecutive checksums found in * the packet minus one that have been verified as * CHECKSUM_UNNECESSARY (max 3) + * @scm_io_uring: SKB holds io_uring registered files * @dst_pending_confirm: need to confirm neighbour * @decrypted: Decrypted SKB * @slow_gro: state present at GRO time, slower prepare step required @@ -982,6 +983,7 @@ struct sk_buff { #endif __u8 slow_gro:1; __u8 csum_not_inet:1; + __u8 scm_io_uring:1; #ifdef CONFIG_NET_SCHED __u16 tc_index; /* traffic control index */ -- cgit v1.2.3 From b7a817752efc850603c4c23ed78da2b990a6a34a Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 4 Oct 2022 03:19:25 +0100 Subject: io_uring: remove notif leftovers Notifications were killed but there is a couple of fields and struct declarations left, remove them. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/8df8877d677be5a2b43afd936d600e60105ea960.1664849941.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index aa4d90a53866..f5b687a787a3 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -34,9 +34,6 @@ struct io_file_table { unsigned int alloc_hint; }; -struct io_notif; -struct io_notif_slot; - struct io_hash_bucket { spinlock_t lock; struct hlist_head list; @@ -242,8 +239,6 @@ struct io_ring_ctx { unsigned nr_user_files; unsigned nr_user_bufs; struct io_mapped_ubuf **user_bufs; - struct io_notif_slot *notif_slots; - unsigned nr_notif_slots; struct io_submit_state submit_state; -- cgit v1.2.3 From 7be1c1a3c7b13fb259bb5159662a7b83622013b8 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 11 Oct 2022 20:55:31 +0300 Subject: mm: more vma cache removal Link: https://lkml.kernel.org/r/Y0WuE3Riv4iy5Jx8@localhost.localdomain Fixes: 7964cf8caa4d ("mm: remove vmacache") Signed-off-by: Alexey Dobriyan Acked-by: Liam Howlett Signed-off-by: Andrew Morton --- include/linux/sched.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 88a043f7235e..e0bb85cf8bdd 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -861,8 +861,6 @@ struct task_struct { struct mm_struct *mm; struct mm_struct *active_mm; - /* Per-thread vma caching: */ - #ifdef SPLIT_RSS_COUNTING struct task_rss_stat rss_stat; #endif -- cgit v1.2.3 From 652e04464d3944226052c827bdaaf5113b072870 Mon Sep 17 00:00:00 2001 From: Xin Hao Date: Tue, 27 Sep 2022 08:19:45 +0800 Subject: mm/damon: move sz_damon_region to damon_sz_region Rename sz_damon_region() to damon_sz_region(), and move it to "include/linux/damon.h", because in many places, we can to use this func. Link: https://lkml.kernel.org/r/20220927001946.85375-1-xhao@linux.alibaba.com Signed-off-by: Xin Hao Suggested-by: SeongJae Park Reviewed-by: SeongJae Park Signed-off-by: Andrew Morton --- include/linux/damon.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index ed5470f50bab..620ada094c3b 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -484,6 +484,12 @@ static inline struct damon_region *damon_first_region(struct damon_target *t) return list_first_entry(&t->regions_list, struct damon_region, list); } +static inline unsigned long damon_sz_region(struct damon_region *r) +{ + return r->ar.end - r->ar.start; +} + + #define damon_for_each_region(r, t) \ list_for_each_entry(r, &t->regions_list, list) -- cgit v1.2.3 From 16ce101db85db694a91380aa4c89b25530871d33 Mon Sep 17 00:00:00 2001 From: Alistair Popple Date: Wed, 28 Sep 2022 22:01:15 +1000 Subject: mm/memory.c: fix race when faulting a device private page MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Patch series "Fix several device private page reference counting issues", v2 This series aims to fix a number of page reference counting issues in drivers dealing with device private ZONE_DEVICE pages. These result in use-after-free type bugs, either from accessing a struct page which no longer exists because it has been removed or accessing fields within the struct page which are no longer valid because the page has been freed. During normal usage it is unlikely these will cause any problems. However without these fixes it is possible to crash the kernel from userspace. These crashes can be triggered either by unloading the kernel module or unbinding the device from the driver prior to a userspace task exiting. In modules such as Nouveau it is also possible to trigger some of these issues by explicitly closing the device file-descriptor prior to the task exiting and then accessing device private memory. This involves some minor changes to both PowerPC and AMD GPU code. Unfortunately I lack hardware to test either of those so any help there would be appreciated. The changes mimic what is done in for both Nouveau and hmm-tests though so I doubt they will cause problems. This patch (of 8): When the CPU tries to access a device private page the migrate_to_ram() callback associated with the pgmap for the page is called. However no reference is taken on the faulting page. Therefore a concurrent migration of the device private page can free the page and possibly the underlying pgmap. This results in a race which can crash the kernel due to the migrate_to_ram() function pointer becoming invalid. It also means drivers can't reliably read the zone_device_data field because the page may have been freed with memunmap_pages(). Close the race by getting a reference on the page while holding the ptl to ensure it has not been freed. Unfortunately the elevated reference count will cause the migration required to handle the fault to fail. To avoid this failure pass the faulting page into the migrate_vma functions so that if an elevated reference count is found it can be checked to see if it's expected or not. [mpe@ellerman.id.au: fix build] Link: https://lkml.kernel.org/r/87fsgbf3gh.fsf@mpe.ellerman.id.au Link: https://lkml.kernel.org/r/cover.60659b549d8509ddecafad4f498ee7f03bb23c69.1664366292.git-series.apopple@nvidia.com Link: https://lkml.kernel.org/r/d3e813178a59e565e8d78d9b9a4e2562f6494f90.1664366292.git-series.apopple@nvidia.com Signed-off-by: Alistair Popple Acked-by: Felix Kuehling Cc: Jason Gunthorpe Cc: John Hubbard Cc: Ralph Campbell Cc: Michael Ellerman Cc: Lyude Paul Cc: Alex Deucher Cc: Alex Sierra Cc: Ben Skeggs Cc: Christian König Cc: Dan Williams Cc: David Hildenbrand Cc: "Huang, Ying" Cc: Matthew Wilcox Cc: Yang Shi Cc: Zi Yan Signed-off-by: Andrew Morton --- include/linux/migrate.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 704a04f5a074..52090d1f9230 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -62,6 +62,8 @@ extern const char *migrate_reason_names[MR_TYPES]; #ifdef CONFIG_MIGRATION extern void putback_movable_pages(struct list_head *l); +int migrate_folio_extra(struct address_space *mapping, struct folio *dst, + struct folio *src, enum migrate_mode mode, int extra_count); int migrate_folio(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode); extern int migrate_pages(struct list_head *l, new_page_t new, free_page_t free, @@ -197,6 +199,12 @@ struct migrate_vma { */ void *pgmap_owner; unsigned long flags; + + /* + * Set to vmf->page if this is being called to migrate a page as part of + * a migrate_to_ram() callback. + */ + struct page *fault_page; }; int migrate_vma_setup(struct migrate_vma *args); -- cgit v1.2.3 From ef233450898f8893dafa193a9f3211fa077a3d05 Mon Sep 17 00:00:00 2001 From: Alistair Popple Date: Wed, 28 Sep 2022 22:01:16 +1000 Subject: mm: free device private pages have zero refcount MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since 27674ef6c73f ("mm: remove the extra ZONE_DEVICE struct page refcount") device private pages have no longer had an extra reference count when the page is in use. However before handing them back to the owning device driver we add an extra reference count such that free pages have a reference count of one. This makes it difficult to tell if a page is free or not because both free and in use pages will have a non-zero refcount. Instead we should return pages to the drivers page allocator with a zero reference count. Kernel code can then safely use kernel functions such as get_page_unless_zero(). Link: https://lkml.kernel.org/r/cf70cf6f8c0bdb8aaebdbfb0d790aea4c683c3c6.1664366292.git-series.apopple@nvidia.com Signed-off-by: Alistair Popple Acked-by: Felix Kuehling Cc: Jason Gunthorpe Cc: Michael Ellerman Cc: Alex Deucher Cc: Christian König Cc: Ben Skeggs Cc: Lyude Paul Cc: Ralph Campbell Cc: Alex Sierra Cc: John Hubbard Cc: Dan Williams Cc: David Hildenbrand Cc: "Huang, Ying" Cc: Matthew Wilcox Cc: Yang Shi Cc: Zi Yan Signed-off-by: Andrew Morton --- include/linux/memremap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/memremap.h b/include/linux/memremap.h index c3b4cc84877b..7fcaf3180a5b 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -187,6 +187,7 @@ static inline bool folio_is_device_coherent(const struct folio *folio) } #ifdef CONFIG_ZONE_DEVICE +void zone_device_page_init(struct page *page); void *memremap_pages(struct dev_pagemap *pgmap, int nid); void memunmap_pages(struct dev_pagemap *pgmap); void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap); -- cgit v1.2.3 From e778406b40dbb1342a1888cd751ca9d2982a12e2 Mon Sep 17 00:00:00 2001 From: Alistair Popple Date: Wed, 28 Sep 2022 22:01:19 +1000 Subject: mm/migrate_device.c: add migrate_device_range() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Device drivers can use the migrate_vma family of functions to migrate existing private anonymous mappings to device private pages. These pages are backed by memory on the device with drivers being responsible for copying data to and from device memory. Device private pages are freed via the pgmap->page_free() callback when they are unmapped and their refcount drops to zero. Alternatively they may be freed indirectly via migration back to CPU memory in response to a pgmap->migrate_to_ram() callback called whenever the CPU accesses an address mapped to a device private page. In other words drivers cannot control the lifetime of data allocated on the devices and must wait until these pages are freed from userspace. This causes issues when memory needs to reclaimed on the device, either because the device is going away due to a ->release() callback or because another user needs to use the memory. Drivers could use the existing migrate_vma functions to migrate data off the device. However this would require them to track the mappings of each page which is both complicated and not always possible. Instead drivers need to be able to migrate device pages directly so they can free up device memory. To allow that this patch introduces the migrate_device family of functions which are functionally similar to migrate_vma but which skips the initial lookup based on mapping. Link: https://lkml.kernel.org/r/868116aab70b0c8ee467d62498bb2cf0ef907295.1664366292.git-series.apopple@nvidia.com Signed-off-by: Alistair Popple Cc: "Huang, Ying" Cc: Zi Yan Cc: Matthew Wilcox Cc: Yang Shi Cc: David Hildenbrand Cc: Ralph Campbell Cc: John Hubbard Cc: Alex Deucher Cc: Alex Sierra Cc: Ben Skeggs Cc: Christian König Cc: Dan Williams Cc: Felix Kuehling Cc: Jason Gunthorpe Cc: Lyude Paul Cc: Michael Ellerman Signed-off-by: Andrew Morton --- include/linux/migrate.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 52090d1f9230..3ef77f52a4f0 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -210,6 +210,13 @@ struct migrate_vma { int migrate_vma_setup(struct migrate_vma *args); void migrate_vma_pages(struct migrate_vma *migrate); void migrate_vma_finalize(struct migrate_vma *migrate); +int migrate_device_range(unsigned long *src_pfns, unsigned long start, + unsigned long npages); +void migrate_device_pages(unsigned long *src_pfns, unsigned long *dst_pfns, + unsigned long npages); +void migrate_device_finalize(unsigned long *src_pfns, + unsigned long *dst_pfns, unsigned long npages); + #endif /* CONFIG_MIGRATION */ #endif /* _LINUX_MIGRATE_H */ -- cgit v1.2.3 From 57d849636a04a12713dd3a10a97cb9658ec7edf6 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Wed, 12 Oct 2022 11:06:35 +0800 Subject: clk: at91: fix the build with binutils 2.27 There is an issue when build with older versions of binutils 2.27.0, arch/arm/mach-at91/pm_suspend.S: Assembler messages: arch/arm/mach-at91/pm_suspend.S:1086: Error: garbage following instruction -- `ldr tmp1,=0x00020010UL' Use UL() macro to fix the issue in assembly file. Fixes: 4fd36e458392 ("ARM: at91: pm: add plla disable/enable support for sam9x60") Signed-off-by: Kefeng Wang Link: https://lore.kernel.org/r/20221012030635.13140-1-wangkefeng.wang@huawei.com Signed-off-by: Stephen Boyd --- include/linux/clk/at91_pmc.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk/at91_pmc.h b/include/linux/clk/at91_pmc.h index 3484309b59bf..7af499bdbecb 100644 --- a/include/linux/clk/at91_pmc.h +++ b/include/linux/clk/at91_pmc.h @@ -12,6 +12,8 @@ #ifndef AT91_PMC_H #define AT91_PMC_H +#include + #define AT91_PMC_V1 (1) /* PMC version 1 */ #define AT91_PMC_V2 (2) /* PMC version 2 [SAM9X60] */ @@ -45,8 +47,8 @@ #define AT91_PMC_PCSR 0x18 /* Peripheral Clock Status Register */ #define AT91_PMC_PLL_ACR 0x18 /* PLL Analog Control Register [for SAM9X60] */ -#define AT91_PMC_PLL_ACR_DEFAULT_UPLL 0x12020010UL /* Default PLL ACR value for UPLL */ -#define AT91_PMC_PLL_ACR_DEFAULT_PLLA 0x00020010UL /* Default PLL ACR value for PLLA */ +#define AT91_PMC_PLL_ACR_DEFAULT_UPLL UL(0x12020010) /* Default PLL ACR value for UPLL */ +#define AT91_PMC_PLL_ACR_DEFAULT_PLLA UL(0x00020010) /* Default PLL ACR value for PLLA */ #define AT91_PMC_PLL_ACR_UTMIVR (1 << 12) /* UPLL Voltage regulator Control */ #define AT91_PMC_PLL_ACR_UTMIBG (1 << 13) /* UPLL Bandgap Control */ -- cgit v1.2.3 From e36ce448a08d43de69e7449eb225805a7a8addf8 Mon Sep 17 00:00:00 2001 From: Hyeonggon Yoo <42.hyeyoo@gmail.com> Date: Sat, 15 Oct 2022 13:34:29 +0900 Subject: mm/slab: use kmalloc_node() for off slab freelist_idx_t array allocation After commit d6a71648dbc0 ("mm/slab: kmalloc: pass requests larger than order-1 page to page allocator"), SLAB passes large ( > PAGE_SIZE * 2) requests to buddy like SLUB does. SLAB has been using kmalloc caches to allocate freelist_idx_t array for off slab caches. But after the commit, freelist_size can be bigger than KMALLOC_MAX_CACHE_SIZE. Instead of using pointer to kmalloc cache, use kmalloc_node() and only check if the kmalloc cache is off slab during calculate_slab_order(). If freelist_size > KMALLOC_MAX_CACHE_SIZE, no looping condition happens as it allocates freelist_idx_t array directly from buddy. Link: https://lore.kernel.org/all/20221014205818.GA1428667@roeck-us.net/ Reported-and-tested-by: Guenter Roeck Fixes: d6a71648dbc0 ("mm/slab: kmalloc: pass requests larger than order-1 page to page allocator") Signed-off-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Signed-off-by: Vlastimil Babka --- include/linux/slab_def.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index e24c9aff6fed..f0ffad6a3365 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -33,7 +33,6 @@ struct kmem_cache { size_t colour; /* cache colouring range */ unsigned int colour_off; /* colour offset */ - struct kmem_cache *freelist_cache; unsigned int freelist_size; /* constructor func */ -- cgit v1.2.3 From 80493877d7d0ae0cbe62921d748682811c58026f Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Sun, 16 Oct 2022 00:53:51 +0900 Subject: Revert "cpumask: fix checking valid cpu range". This reverts commit 78e5a3399421 ("cpumask: fix checking valid cpu range"). syzbot is hitting WARN_ON_ONCE(cpu >= nr_cpumask_bits) warning at cpu_max_bits_warn() [1], for commit 78e5a3399421 ("cpumask: fix checking valid cpu range") is broken. Obviously that patch hits WARN_ON_ONCE() when e.g. reading /proc/cpuinfo because passing "cpu + 1" instead of "cpu" will trivially hit cpu == nr_cpumask_bits condition. Although syzbot found this problem in linux-next.git on 2022/09/27 [2], this problem was not fixed immediately. As a result, that patch was sent to linux.git before the patch author recognizes this problem, and syzbot started failing to test changes in linux.git since 2022/10/10 [3]. Andrew Jones proposed a fix for x86 and riscv architectures [4]. But [2] and [5] indicate that affected locations are not limited to arch code. More delay before we find and fix affected locations, less tested kernel (and more difficult to bisect and fix) before release. We should have inspected and fixed basically all cpumask users before applying that patch. We should not crash kernels in order to ask existing cpumask users to update their code, even if limited to CONFIG_DEBUG_PER_CPU_MAPS=y case. Link: https://syzkaller.appspot.com/bug?extid=d0fd2bf0dd6da72496dd [1] Link: https://syzkaller.appspot.com/bug?extid=21da700f3c9f0bc40150 [2] Link: https://syzkaller.appspot.com/bug?extid=51a652e2d24d53e75734 [3] Link: https://lkml.kernel.org/r/20221014155845.1986223-1-ajones@ventanamicro.com [4] Link: https://syzkaller.appspot.com/bug?extid=4d46c43d81c3bd155060 [5] Reported-by: Andrew Jones Reported-by: syzbot+d0fd2bf0dd6da72496dd@syzkaller.appspotmail.com Signed-off-by: Tetsuo Handa Cc: Yury Norov Cc: Borislav Petkov Signed-off-by: Linus Torvalds --- include/linux/cpumask.h | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 2f065ad97541..c2aa0aa26b45 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -174,8 +174,9 @@ static inline unsigned int cpumask_last(const struct cpumask *srcp) static inline unsigned int cpumask_next(int n, const struct cpumask *srcp) { - /* n is a prior cpu */ - cpumask_check(n + 1); + /* -1 is a legal arg here. */ + if (n != -1) + cpumask_check(n); return find_next_bit(cpumask_bits(srcp), nr_cpumask_bits, n + 1); } @@ -188,8 +189,9 @@ unsigned int cpumask_next(int n, const struct cpumask *srcp) */ static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) { - /* n is a prior cpu */ - cpumask_check(n + 1); + /* -1 is a legal arg here. */ + if (n != -1) + cpumask_check(n); return find_next_zero_bit(cpumask_bits(srcp), nr_cpumask_bits, n+1); } @@ -229,8 +231,9 @@ static inline unsigned int cpumask_next_and(int n, const struct cpumask *src1p, const struct cpumask *src2p) { - /* n is a prior cpu */ - cpumask_check(n + 1); + /* -1 is a legal arg here. */ + if (n != -1) + cpumask_check(n); return find_next_and_bit(cpumask_bits(src1p), cpumask_bits(src2p), nr_cpumask_bits, n + 1); } @@ -260,8 +263,8 @@ static inline unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap) { cpumask_check(start); - /* n is a prior cpu */ - cpumask_check(n + 1); + if (n != -1) + cpumask_check(n); /* * Return the first available CPU when wrapping, or when starting before cpu0, -- cgit v1.2.3 From 5d0f5953b60f5f7a278085b55ddc73e2932f4c33 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 15 Sep 2022 12:09:30 -0700 Subject: srcu: Convert ->srcu_lock_count and ->srcu_unlock_count to atomic NMI-safe variants of srcu_read_lock() and srcu_read_unlock() are needed by printk(), which on many architectures entails read-modify-write atomic operations. This commit prepares Tree SRCU for this change by making both ->srcu_lock_count and ->srcu_unlock_count by atomic_long_t. [ paulmck: Apply feedback from John Ogness. ] Link: https://lore.kernel.org/all/20220910221947.171557773@linutronix.de/ Signed-off-by: Paul E. McKenney Reviewed-by: Frederic Weisbecker Cc: Thomas Gleixner Cc: John Ogness Cc: Petr Mladek --- include/linux/srcutree.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index e3014319d1ad..0c4eca07d78d 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -23,8 +23,8 @@ struct srcu_struct; */ struct srcu_data { /* Read-side state. */ - unsigned long srcu_lock_count[2]; /* Locks per CPU. */ - unsigned long srcu_unlock_count[2]; /* Unlocks per CPU. */ + atomic_long_t srcu_lock_count[2]; /* Locks per CPU. */ + atomic_long_t srcu_unlock_count[2]; /* Unlocks per CPU. */ /* Update-side state. */ spinlock_t __private lock ____cacheline_internodealigned_in_smp; -- cgit v1.2.3 From 2e83b879fb91dafe995967b46a1d38a5b0889242 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 15 Sep 2022 14:29:07 -0700 Subject: srcu: Create an srcu_read_lock_nmisafe() and srcu_read_unlock_nmisafe() On strict load-store architectures, the use of this_cpu_inc() by srcu_read_lock() and srcu_read_unlock() is not NMI-safe in TREE SRCU. To see this suppose that an NMI arrives in the middle of srcu_read_lock(), just after it has read ->srcu_lock_count, but before it has written the incremented value back to memory. If that NMI handler also does srcu_read_lock() and srcu_read_lock() on that same srcu_struct structure, then upon return from that NMI handler, the interrupted srcu_read_lock() will overwrite the NMI handler's update to ->srcu_lock_count, but leave unchanged the NMI handler's update by srcu_read_unlock() to ->srcu_unlock_count. This can result in a too-short SRCU grace period, which can in turn result in arbitrary memory corruption. If the NMI handler instead interrupts the srcu_read_unlock(), this can result in eternal SRCU grace periods, which is not much better. This commit therefore creates a pair of new srcu_read_lock_nmisafe() and srcu_read_unlock_nmisafe() functions, which allow SRCU readers in both NMI handlers and in process and IRQ context. It is bad practice to mix the existing and the new _nmisafe() primitives on the same srcu_struct structure. Use one set or the other, not both. Just to underline that "bad practice" point, using srcu_read_lock() at process level and srcu_read_lock_nmisafe() in your NMI handler will not, repeat NOT, work. If you do not immediately understand why this is the case, please review the earlier paragraphs in this commit log. [ paulmck: Apply kernel test robot feedback. ] [ paulmck: Apply feedback from Randy Dunlap. ] [ paulmck: Apply feedback from John Ogness. ] [ paulmck: Apply feedback from Frederic Weisbecker. ] Link: https://lore.kernel.org/all/20220910221947.171557773@linutronix.de/ Signed-off-by: Paul E. McKenney Acked-by: Randy Dunlap # build-tested Reviewed-by: Frederic Weisbecker Cc: Thomas Gleixner Cc: John Ogness Cc: Petr Mladek --- include/linux/srcu.h | 51 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 51 insertions(+) (limited to 'include/linux') diff --git a/include/linux/srcu.h b/include/linux/srcu.h index 01226e4d960a..4fac088072c3 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -64,6 +64,20 @@ unsigned long get_state_synchronize_srcu(struct srcu_struct *ssp); unsigned long start_poll_synchronize_srcu(struct srcu_struct *ssp); bool poll_state_synchronize_srcu(struct srcu_struct *ssp, unsigned long cookie); +#ifdef CONFIG_NEED_SRCU_NMI_SAFE +int __srcu_read_lock_nmisafe(struct srcu_struct *ssp) __acquires(ssp); +void __srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx) __releases(ssp); +#else +static inline int __srcu_read_lock_nmisafe(struct srcu_struct *ssp) +{ + return __srcu_read_lock(ssp); +} +static inline void __srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx) +{ + __srcu_read_unlock(ssp, idx); +} +#endif /* CONFIG_NEED_SRCU_NMI_SAFE */ + #ifdef CONFIG_SRCU void srcu_init(void); #else /* #ifdef CONFIG_SRCU */ @@ -166,6 +180,25 @@ static inline int srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp) return retval; } +/** + * srcu_read_lock_nmisafe - register a new reader for an SRCU-protected structure. + * @ssp: srcu_struct in which to register the new reader. + * + * Enter an SRCU read-side critical section, but in an NMI-safe manner. + * See srcu_read_lock() for more information. + */ +static inline int srcu_read_lock_nmisafe(struct srcu_struct *ssp) __acquires(ssp) +{ + int retval; + + if (IS_ENABLED(CONFIG_NEED_SRCU_NMI_SAFE)) + retval = __srcu_read_lock_nmisafe(ssp); + else + retval = __srcu_read_lock(ssp); + rcu_lock_acquire(&(ssp)->dep_map); + return retval; +} + /* Used by tracing, cannot be traced and cannot invoke lockdep. */ static inline notrace int srcu_read_lock_notrace(struct srcu_struct *ssp) __acquires(ssp) @@ -191,6 +224,24 @@ static inline void srcu_read_unlock(struct srcu_struct *ssp, int idx) __srcu_read_unlock(ssp, idx); } +/** + * srcu_read_unlock_nmisafe - unregister a old reader from an SRCU-protected structure. + * @ssp: srcu_struct in which to unregister the old reader. + * @idx: return value from corresponding srcu_read_lock(). + * + * Exit an SRCU read-side critical section, but in an NMI-safe manner. + */ +static inline void srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx) + __releases(ssp) +{ + WARN_ON_ONCE(idx & ~0x1); + rcu_lock_release(&(ssp)->dep_map); + if (IS_ENABLED(CONFIG_NEED_SRCU_NMI_SAFE)) + __srcu_read_unlock_nmisafe(ssp, idx); + else + __srcu_read_unlock(ssp, idx); +} + /* Used by tracing, cannot be traced and cannot call lockdep. */ static inline notrace void srcu_read_unlock_notrace(struct srcu_struct *ssp, int idx) __releases(ssp) -- cgit v1.2.3 From 27120e7d2c4d5c438b76f9c6330037a52ad0722e Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 19 Sep 2022 14:03:07 -0700 Subject: srcu: Check for consistent per-CPU per-srcu_struct NMI safety This commit adds runtime checks to verify that a given srcu_struct uses consistent NMI-safe (or not) read-side primitives on a per-CPU basis. Link: https://lore.kernel.org/all/20220910221947.171557773@linutronix.de/ Signed-off-by: Paul E. McKenney Reviewed-by: Frederic Weisbecker Cc: Thomas Gleixner Cc: John Ogness Cc: Petr Mladek --- include/linux/srcu.h | 12 ++++++------ include/linux/srcutree.h | 5 +++++ 2 files changed, 11 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/srcu.h b/include/linux/srcu.h index 4fac088072c3..1a7840c1b87a 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -65,14 +65,14 @@ unsigned long start_poll_synchronize_srcu(struct srcu_struct *ssp); bool poll_state_synchronize_srcu(struct srcu_struct *ssp, unsigned long cookie); #ifdef CONFIG_NEED_SRCU_NMI_SAFE -int __srcu_read_lock_nmisafe(struct srcu_struct *ssp) __acquires(ssp); -void __srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx) __releases(ssp); +int __srcu_read_lock_nmisafe(struct srcu_struct *ssp, bool chknmisafe) __acquires(ssp); +void __srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx, bool chknmisafe) __releases(ssp); #else -static inline int __srcu_read_lock_nmisafe(struct srcu_struct *ssp) +static inline int __srcu_read_lock_nmisafe(struct srcu_struct *ssp, bool chknmisafe) { return __srcu_read_lock(ssp); } -static inline void __srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx) +static inline void __srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx, bool chknmisafe) { __srcu_read_unlock(ssp, idx); } @@ -192,7 +192,7 @@ static inline int srcu_read_lock_nmisafe(struct srcu_struct *ssp) __acquires(ssp int retval; if (IS_ENABLED(CONFIG_NEED_SRCU_NMI_SAFE)) - retval = __srcu_read_lock_nmisafe(ssp); + retval = __srcu_read_lock_nmisafe(ssp, true); else retval = __srcu_read_lock(ssp); rcu_lock_acquire(&(ssp)->dep_map); @@ -237,7 +237,7 @@ static inline void srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx) WARN_ON_ONCE(idx & ~0x1); rcu_lock_release(&(ssp)->dep_map); if (IS_ENABLED(CONFIG_NEED_SRCU_NMI_SAFE)) - __srcu_read_unlock_nmisafe(ssp, idx); + __srcu_read_unlock_nmisafe(ssp, idx, true); else __srcu_read_unlock(ssp, idx); } diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 0c4eca07d78d..1ef8f2a4884f 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -25,6 +25,7 @@ struct srcu_data { /* Read-side state. */ atomic_long_t srcu_lock_count[2]; /* Locks per CPU. */ atomic_long_t srcu_unlock_count[2]; /* Unlocks per CPU. */ + int srcu_nmi_safety; /* NMI-safe srcu_struct structure? */ /* Update-side state. */ spinlock_t __private lock ____cacheline_internodealigned_in_smp; @@ -42,6 +43,10 @@ struct srcu_data { struct srcu_struct *ssp; }; +#define SRCU_NMI_UNKNOWN 0x0 +#define SRCU_NMI_NMI_UNSAFE 0x1 +#define SRCU_NMI_NMI_SAFE 0x2 + /* * Node in SRCU combining tree, similar in function to rcu_data. */ -- cgit v1.2.3 From e29a4915db1480f96e0bc2e928699d086a71f43c Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 13 Oct 2022 19:22:44 +0200 Subject: srcu: Debug NMI safety even on archs that don't require it Currently the NMI safety debugging is only performed on architectures that don't support NMI-safe this_cpu_inc(). Reorder the code so that other architectures like x86 also detect bad uses. [ paulmck: Apply kernel test robot, Stephen Rothwell, and Zqiang feedback. ] Signed-off-by: Frederic Weisbecker Signed-off-by: Paul E. McKenney --- include/linux/srcu.h | 36 ++++++++++++++++++++++++------------ include/linux/srcutree.h | 4 ---- 2 files changed, 24 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/srcu.h b/include/linux/srcu.h index 1a7840c1b87a..f0814ffca34b 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -65,14 +65,14 @@ unsigned long start_poll_synchronize_srcu(struct srcu_struct *ssp); bool poll_state_synchronize_srcu(struct srcu_struct *ssp, unsigned long cookie); #ifdef CONFIG_NEED_SRCU_NMI_SAFE -int __srcu_read_lock_nmisafe(struct srcu_struct *ssp, bool chknmisafe) __acquires(ssp); -void __srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx, bool chknmisafe) __releases(ssp); +int __srcu_read_lock_nmisafe(struct srcu_struct *ssp) __acquires(ssp); +void __srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx) __releases(ssp); #else -static inline int __srcu_read_lock_nmisafe(struct srcu_struct *ssp, bool chknmisafe) +static inline int __srcu_read_lock_nmisafe(struct srcu_struct *ssp) { return __srcu_read_lock(ssp); } -static inline void __srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx, bool chknmisafe) +static inline void __srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx) { __srcu_read_unlock(ssp, idx); } @@ -118,6 +118,18 @@ static inline int srcu_read_lock_held(const struct srcu_struct *ssp) #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ +#define SRCU_NMI_UNKNOWN 0x0 +#define SRCU_NMI_UNSAFE 0x1 +#define SRCU_NMI_SAFE 0x2 + +#if defined(CONFIG_PROVE_RCU) && defined(CONFIG_TREE_SRCU) +void srcu_check_nmi_safety(struct srcu_struct *ssp, bool nmi_safe); +#else +static inline void srcu_check_nmi_safety(struct srcu_struct *ssp, + bool nmi_safe) { } +#endif + + /** * srcu_dereference_check - fetch SRCU-protected pointer for later dereferencing * @p: the pointer to fetch and protect for later dereferencing @@ -175,6 +187,7 @@ static inline int srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp) { int retval; + srcu_check_nmi_safety(ssp, false); retval = __srcu_read_lock(ssp); rcu_lock_acquire(&(ssp)->dep_map); return retval; @@ -191,10 +204,8 @@ static inline int srcu_read_lock_nmisafe(struct srcu_struct *ssp) __acquires(ssp { int retval; - if (IS_ENABLED(CONFIG_NEED_SRCU_NMI_SAFE)) - retval = __srcu_read_lock_nmisafe(ssp, true); - else - retval = __srcu_read_lock(ssp); + srcu_check_nmi_safety(ssp, true); + retval = __srcu_read_lock_nmisafe(ssp); rcu_lock_acquire(&(ssp)->dep_map); return retval; } @@ -205,6 +216,7 @@ srcu_read_lock_notrace(struct srcu_struct *ssp) __acquires(ssp) { int retval; + srcu_check_nmi_safety(ssp, false); retval = __srcu_read_lock(ssp); return retval; } @@ -220,6 +232,7 @@ static inline void srcu_read_unlock(struct srcu_struct *ssp, int idx) __releases(ssp) { WARN_ON_ONCE(idx & ~0x1); + srcu_check_nmi_safety(ssp, false); rcu_lock_release(&(ssp)->dep_map); __srcu_read_unlock(ssp, idx); } @@ -235,17 +248,16 @@ static inline void srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx) __releases(ssp) { WARN_ON_ONCE(idx & ~0x1); + srcu_check_nmi_safety(ssp, true); rcu_lock_release(&(ssp)->dep_map); - if (IS_ENABLED(CONFIG_NEED_SRCU_NMI_SAFE)) - __srcu_read_unlock_nmisafe(ssp, idx, true); - else - __srcu_read_unlock(ssp, idx); + __srcu_read_unlock_nmisafe(ssp, idx); } /* Used by tracing, cannot be traced and cannot call lockdep. */ static inline notrace void srcu_read_unlock_notrace(struct srcu_struct *ssp, int idx) __releases(ssp) { + srcu_check_nmi_safety(ssp, false); __srcu_read_unlock(ssp, idx); } diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 1ef8f2a4884f..c689a81752c9 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -43,10 +43,6 @@ struct srcu_data { struct srcu_struct *ssp; }; -#define SRCU_NMI_UNKNOWN 0x0 -#define SRCU_NMI_NMI_UNSAFE 0x1 -#define SRCU_NMI_NMI_SAFE 0x2 - /* * Node in SRCU combining tree, similar in function to rcu_data. */ -- cgit v1.2.3 From f733615e39aa2d6ddeef33b7b2c9aa6a5a2c2785 Mon Sep 17 00:00:00 2001 From: John Ogness Date: Mon, 7 Nov 2022 15:21:59 +0106 Subject: rcu: Implement lockdep_rcu_enabled for !CONFIG_DEBUG_LOCK_ALLOC Provide an implementation for debug_lockdep_rcu_enabled() when CONFIG_DEBUG_LOCK_ALLOC is not enabled. This allows code to check if rcu lockdep debugging is available without needing an extra check if CONFIG_DEBUG_LOCK_ALLOC is enabled. Signed-off-by: John Ogness Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 08605ce7379d..65178c40ab6f 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -340,6 +340,11 @@ static inline int rcu_read_lock_any_held(void) return !preemptible(); } +static inline int debug_lockdep_rcu_enabled(void) +{ + return 0; +} + #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ #ifdef CONFIG_PROVE_RCU -- cgit v1.2.3 From 0cd7e350abc40eed5d3b60292dc102f700c88388 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 22 Nov 2022 13:53:57 -0800 Subject: rcu: Make SRCU mandatory Kernels configured with CONFIG_PRINTK=n and CONFIG_SRCU=n get build failures. This causes trouble for deep embedded systems. But given that there are more than 25 instances of "select SRCU" in the kernel, it is hard to believe that there are many kernels running in production without SRCU. This commit therefore makes SRCU mandatory. The SRCU Kconfig option remains for backwards compatibility, and will be removed when it is no longer used. [ paulmck: Update per kernel test robot feedback. ] Reported-by: John Ogness Reported-by: Petr Mladek Signed-off-by: Paul E. McKenney Cc: Acked-by: Randy Dunlap # build-tested Reviewed-by: John Ogness --- include/linux/rcutiny.h | 4 ---- include/linux/srcu.h | 9 +-------- 2 files changed, 1 insertion(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 768196a5f39d..d40b21ec7e0d 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -154,11 +154,7 @@ static inline bool rcu_preempt_need_deferred_qs(struct task_struct *t) return false; } static inline void rcu_preempt_deferred_qs(struct task_struct *t) { } -#ifdef CONFIG_SRCU void rcu_scheduler_starting(void); -#else /* #ifndef CONFIG_SRCU */ -static inline void rcu_scheduler_starting(void) { } -#endif /* #else #ifndef CONFIG_SRCU */ static inline void rcu_end_inkernel_boot(void) { } static inline bool rcu_inkernel_boot_has_ended(void) { return true; } static inline bool rcu_is_watching(void) { return true; } diff --git a/include/linux/srcu.h b/include/linux/srcu.h index f0814ffca34b..9b9d0bbf1d3c 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -47,11 +47,8 @@ int init_srcu_struct(struct srcu_struct *ssp); #include #elif defined(CONFIG_TREE_SRCU) #include -#elif defined(CONFIG_SRCU) -#error "Unknown SRCU implementation specified to kernel configuration" #else -/* Dummy definition for things like notifiers. Actual use gets link error. */ -struct srcu_struct { }; +#error "Unknown SRCU implementation specified to kernel configuration" #endif void call_srcu(struct srcu_struct *ssp, struct rcu_head *head, @@ -78,11 +75,7 @@ static inline void __srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx) } #endif /* CONFIG_NEED_SRCU_NMI_SAFE */ -#ifdef CONFIG_SRCU void srcu_init(void); -#else /* #ifdef CONFIG_SRCU */ -static inline void srcu_init(void) { } -#endif /* #else #ifdef CONFIG_SRCU */ #ifdef CONFIG_DEBUG_LOCK_ALLOC -- cgit v1.2.3 From d9a4af5690e26afa8a2eb83c575d3a9ef52cde1d Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 16 Nov 2022 17:27:14 +0106 Subject: printk: Convert console_drivers list to hlist Replace the open coded single linked list with a hlist so a conversion to SRCU protected list walks can reuse the existing primitives. Co-developed-by: John Ogness Signed-off-by: John Ogness Signed-off-by: Thomas Gleixner Reviewed-by: Greg Kroah-Hartman Reviewed-by: Sergey Senozhatsky Reviewed-by: Petr Mladek Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20221116162152.193147-3-john.ogness@linutronix.de --- include/linux/console.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/console.h b/include/linux/console.h index 8c1686e2c233..7b5f21f9e469 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -15,6 +15,7 @@ #define _LINUX_CONSOLE_H_ 1 #include +#include #include struct vc_data; @@ -154,14 +155,16 @@ struct console { u64 seq; unsigned long dropped; void *data; - struct console *next; + struct hlist_node node; }; +extern struct hlist_head console_list; + /* * for_each_console() allows you to iterate on each console */ #define for_each_console(con) \ - for (con = console_drivers; con != NULL; con = con->next) + hlist_for_each_entry(con, &console_list, node) extern int console_set_on_cmdline; extern struct console *early_console; @@ -174,7 +177,6 @@ enum con_flush_mode { extern int add_preferred_console(char *name, int idx, char *options); extern void register_console(struct console *); extern int unregister_console(struct console *); -extern struct console *console_drivers; extern void console_lock(void); extern int console_trylock(void); extern void console_unlock(void); -- cgit v1.2.3 From 6c4afa79147e4aa86665795695ac4a5f25e73176 Mon Sep 17 00:00:00 2001 From: John Ogness Date: Wed, 16 Nov 2022 17:27:15 +0106 Subject: printk: Prepare for SRCU console list protection Provide an NMI-safe SRCU protected variant to walk the console list. Note that all console fields are now set before adding the console to the list to avoid the console becoming visible by SCRU readers before being fully initialized. This is a preparatory change for a new console infrastructure which operates independent of the console BKL. Suggested-by: Thomas Gleixner Signed-off-by: John Ogness Acked-by: Miguel Ojeda Reviewed-by: Paul E. McKenney Reviewed-by: Petr Mladek Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20221116162152.193147-4-john.ogness@linutronix.de --- include/linux/console.h | 28 +++++++++++++++++++++++++++- 1 file changed, 27 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/console.h b/include/linux/console.h index 7b5f21f9e469..f4f0c9523835 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -15,7 +15,7 @@ #define _LINUX_CONSOLE_H_ 1 #include -#include +#include #include struct vc_data; @@ -158,8 +158,34 @@ struct console { struct hlist_node node; }; +#ifdef CONFIG_DEBUG_LOCK_ALLOC +extern bool console_srcu_read_lock_is_held(void); +#else +static inline bool console_srcu_read_lock_is_held(void) +{ + return 1; +} +#endif + +extern int console_srcu_read_lock(void); +extern void console_srcu_read_unlock(int cookie); + extern struct hlist_head console_list; +/** + * for_each_console_srcu() - Iterator over registered consoles + * @con: struct console pointer used as loop cursor + * + * Although SRCU guarantees the console list will be consistent, the + * struct console fields may be updated by other CPUs while iterating. + * + * Requires console_srcu_read_lock to be held. Can be invoked from + * any context. + */ +#define for_each_console_srcu(con) \ + hlist_for_each_entry_srcu(con, &console_list, node, \ + console_srcu_read_lock_is_held()) + /* * for_each_console() allows you to iterate on each console */ -- cgit v1.2.3 From 4dc64682ad37abb02c54ca598430ac27de60c21a Mon Sep 17 00:00:00 2001 From: John Ogness Date: Mon, 21 Nov 2022 12:16:12 +0106 Subject: printk: introduce console_list_lock Currently there exist races in register_console(), where the types of registered consoles are checked (without holding the console_lock) and then after acquiring the console_lock, it is assumed that the list has not changed. Also, some code that performs console_unregister() make similar assumptions. It might be possible to fix these races using the console_lock. But it would require a complex analysis of all console drivers to make sure that the console_lock is not taken in match() and setup() callbacks. And we really prefer to split up and reduce the responsibilities of console_lock rather than expand its complexity. Therefore, introduce a new console_list_lock to provide full synchronization for any console list changes. In addition, also use console_list_lock for synchronization of console->flags updates. All flags are either static or modified only during the console registration. There are only two exceptions. The first exception is CON_ENABLED, which is also modified by console_start()/console_stop(). Therefore, these functions must also take the console_list_lock. The second exception is when the flags are modified by the console driver init code before the console is registered. These will be ignored because they are not visible to the rest of the system via the console_drivers list. Note that one of the various responsibilities of the console_lock is also intended to provide console list and console->flags synchronization. Later changes will update call sites relying on the console_lock for these purposes. Once all call sites have been updated, the console_lock will be relieved of synchronizing console_list and console->flags updates. Suggested-by: Thomas Gleixner Signed-off-by: John Ogness Reviewed-by: Petr Mladek Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/87sficwokr.fsf@jogness.linutronix.de --- include/linux/console.h | 23 ++++++++++++++++++++--- 1 file changed, 20 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/console.h b/include/linux/console.h index f4f0c9523835..24d83e24840b 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -158,6 +158,14 @@ struct console { struct hlist_node node; }; +#ifdef CONFIG_LOCKDEP +extern void lockdep_assert_console_list_lock_held(void); +#else +static inline void lockdep_assert_console_list_lock_held(void) +{ +} +#endif + #ifdef CONFIG_DEBUG_LOCK_ALLOC extern bool console_srcu_read_lock_is_held(void); #else @@ -170,6 +178,9 @@ static inline bool console_srcu_read_lock_is_held(void) extern int console_srcu_read_lock(void); extern void console_srcu_read_unlock(int cookie); +extern void console_list_lock(void) __acquires(console_mutex); +extern void console_list_unlock(void) __releases(console_mutex); + extern struct hlist_head console_list; /** @@ -186,10 +197,16 @@ extern struct hlist_head console_list; hlist_for_each_entry_srcu(con, &console_list, node, \ console_srcu_read_lock_is_held()) -/* - * for_each_console() allows you to iterate on each console +/** + * for_each_console() - Iterator over registered consoles + * @con: struct console pointer used as loop cursor + * + * The console list and the console->flags are immutable while iterating. + * + * Requires console_list_lock to be held. */ -#define for_each_console(con) \ +#define for_each_console(con) \ + lockdep_assert_console_list_lock_held(); \ hlist_for_each_entry(con, &console_list, node) extern int console_set_on_cmdline; -- cgit v1.2.3 From 100bdef2c198b8dc64df011dc4a2152db913c8ba Mon Sep 17 00:00:00 2001 From: John Ogness Date: Wed, 16 Nov 2022 17:27:24 +0106 Subject: console: introduce wrappers to read/write console flags After switching to SRCU for console list iteration, some readers will begin readings console->flags as a data race. Locklessly reading console->flags provides a consistent value because there is at most one CPU modifying console->flags and that CPU is using only read-modify-write operations. Introduce a wrapper for SRCU iterators to read console flags. Introduce a matching wrapper to write to flags of registered consoles. Writing to flags of registered consoles is synchronized by the console_list_lock. Signed-off-by: John Ogness Reviewed-by: Petr Mladek Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20221116162152.193147-13-john.ogness@linutronix.de --- include/linux/console.h | 45 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) (limited to 'include/linux') diff --git a/include/linux/console.h b/include/linux/console.h index 24d83e24840b..c1ca461d088a 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -183,6 +183,51 @@ extern void console_list_unlock(void) __releases(console_mutex); extern struct hlist_head console_list; +/** + * console_srcu_read_flags - Locklessly read the console flags + * @con: struct console pointer of console to read flags from + * + * This function provides the necessary READ_ONCE() and data_race() + * notation for locklessly reading the console flags. The READ_ONCE() + * in this function matches the WRITE_ONCE() when @flags are modified + * for registered consoles with console_srcu_write_flags(). + * + * Only use this function to read console flags when locklessly + * iterating the console list via srcu. + * + * Context: Any context. + */ +static inline short console_srcu_read_flags(const struct console *con) +{ + WARN_ON_ONCE(!console_srcu_read_lock_is_held()); + + /* + * Locklessly reading console->flags provides a consistent + * read value because there is at most one CPU modifying + * console->flags and that CPU is using only read-modify-write + * operations to do so. + */ + return data_race(READ_ONCE(con->flags)); +} + +/** + * console_srcu_write_flags - Write flags for a registered console + * @con: struct console pointer of console to write flags to + * @flags: new flags value to write + * + * Only use this function to write flags for registered consoles. It + * requires holding the console_list_lock. + * + * Context: Any context. + */ +static inline void console_srcu_write_flags(struct console *con, short flags) +{ + lockdep_assert_console_list_lock_held(); + + /* This matches the READ_ONCE() in console_srcu_read_flags(). */ + WRITE_ONCE(con->flags, flags); +} + /** * for_each_console_srcu() - Iterator over registered consoles * @con: struct console pointer used as loop cursor -- cgit v1.2.3 From 1fd4224a6b641f1949e27bf350b5b1c1e47e2ccc Mon Sep 17 00:00:00 2001 From: John Ogness Date: Wed, 16 Nov 2022 17:27:33 +0106 Subject: console: introduce console_is_registered() Currently it is not possible for drivers to detect if they have already successfully registered their console. Several drivers have multiple paths that lead to console registration. To avoid attempting a 2nd registration (which leads to a WARN), drivers are implementing their own solution. Introduce console_is_registered() so drivers can easily identify if their console is currently registered. A _locked() variant is also provided if the caller is already holding the console_list_lock. Signed-off-by: John Ogness Reviewed-by: Petr Mladek Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20221116162152.193147-22-john.ogness@linutronix.de --- include/linux/console.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/console.h b/include/linux/console.h index c1ca461d088a..f716e1dd9eaf 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -228,6 +228,34 @@ static inline void console_srcu_write_flags(struct console *con, short flags) WRITE_ONCE(con->flags, flags); } +/* Variant of console_is_registered() when the console_list_lock is held. */ +static inline bool console_is_registered_locked(const struct console *con) +{ + lockdep_assert_console_list_lock_held(); + return !hlist_unhashed(&con->node); +} + +/* + * console_is_registered - Check if the console is registered + * @con: struct console pointer of console to check + * + * Context: Process context. May sleep while acquiring console list lock. + * Return: true if the console is in the console list, otherwise false. + * + * If false is returned for a console that was previously registered, it + * can be assumed that the console's unregistration is fully completed, + * including the exit() callback after console list removal. + */ +static inline bool console_is_registered(const struct console *con) +{ + bool ret; + + console_list_lock(); + ret = console_is_registered_locked(con); + console_list_unlock(); + return ret; +} + /** * for_each_console_srcu() - Iterator over registered consoles * @con: struct console pointer used as loop cursor -- cgit v1.2.3 From 452b9b24754044eced1508f9090611f3d9aa4ca5 Mon Sep 17 00:00:00 2001 From: John Ogness Date: Wed, 16 Nov 2022 17:27:34 +0106 Subject: serial_core: replace uart_console_enabled() with uart_console_registered() All users of uart_console_enabled() really want to know if a console is registered. It is not reliable to check for CON_ENABLED in order to identify if a console is registered. Use console_is_registered() instead. A _locked() variant is provided because uart_set_options() is always called with the console_list_lock held and must check if a console is registered in order to synchronize with kgdboc. Signed-off-by: John Ogness Reviewed-by: Petr Mladek Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20221116162152.193147-23-john.ogness@linutronix.de --- include/linux/serial_core.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index d657f2a42a7b..91871464b99d 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -743,9 +743,15 @@ static const bool earlycon_acpi_spcr_enable EARLYCON_USED_OR_UNUSED; static inline int setup_earlycon(char *buf) { return 0; } #endif -static inline bool uart_console_enabled(struct uart_port *port) +/* Variant of uart_console_registered() when the console_list_lock is held. */ +static inline bool uart_console_registered_locked(struct uart_port *port) { - return uart_console(port) && (port->cons->flags & CON_ENABLED); + return uart_console(port) && console_is_registered_locked(port->cons); +} + +static inline bool uart_console_registered(struct uart_port *port) +{ + return uart_console(port) && console_is_registered(port->cons); } struct uart_port *uart_get_console(struct uart_port *ports, int nr, -- cgit v1.2.3 From 6f8836756f3cbb02bfd1f0e033516585250318a9 Mon Sep 17 00:00:00 2001 From: John Ogness Date: Wed, 16 Nov 2022 17:27:44 +0106 Subject: printk, xen: fbfront: create/use safe function for forcing preferred With commit 9e124fe16ff2("xen: Enable console tty by default in domU if it's not a dummy") a hack was implemented to make sure that the tty console remains the console behind the /dev/console device. The main problem with the hack is that, after getting the console pointer to the tty console, it is assumed the pointer is still valid after releasing the console_sem. This assumption is incorrect and unsafe. Make the hack safe by introducing a new function console_force_preferred_locked() and perform the full operation under the console_list_lock. Signed-off-by: John Ogness Reviewed-by: Petr Mladek Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20221116162152.193147-33-john.ogness@linutronix.de --- include/linux/console.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/console.h b/include/linux/console.h index f716e1dd9eaf..9cea254b34b8 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -291,6 +291,7 @@ enum con_flush_mode { }; extern int add_preferred_console(char *name, int idx, char *options); +extern void console_force_preferred_locked(struct console *con); extern void register_console(struct console *); extern int unregister_console(struct console *); extern void console_lock(void); -- cgit v1.2.3