diff --git a/.mailmap b/.mailmap index 5378f04b2566..5e829da09e7f 100644 --- a/.mailmap +++ b/.mailmap @@ -665,6 +665,7 @@ Tomeu Vizoso Thomas Graf Thomas Körper Thomas Pedersen +Thorsten Blum Tiezhu Yang Tingwei Zhang Tirupathi Reddy diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index f2651373f44a..797d048e5691 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -6711,7 +6711,7 @@ 0: no polling (default) thp_anon= [KNL] - Format: ,[KMG]:;-[KMG]: + Format: [KMG],[KMG]:;[KMG]-[KMG]: state is one of "always", "madvise", "never" or "inherit". Control the default behavior of the system with respect to anonymous transparent hugepages. diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst index cfdd16a52e39..a1bb495eab59 100644 --- a/Documentation/admin-guide/mm/transhuge.rst +++ b/Documentation/admin-guide/mm/transhuge.rst @@ -303,7 +303,7 @@ control by passing the parameter ``transparent_hugepage=always`` or kernel command line. Alternatively, each supported anonymous THP size can be controlled by -passing ``thp_anon=,[KMG]:;-[KMG]:``, +passing ``thp_anon=[KMG],[KMG]:;[KMG]-[KMG]:``, where ```` is the THP size (must be a power of 2 of PAGE_SIZE and supported anonymous THP) and ```` is one of ``always``, ``madvise``, ``never`` or ``inherit``. diff --git a/Makefile b/Makefile index 0cfab9428247..fc5058ff79cc 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 12 SUBLEVEL = 0 -EXTRAVERSION = -rc6 +EXTRAVERSION = -rc7 NAME = Baby Opossum Posse # *DOCUMENTATION* diff --git a/arch/arm64/include/asm/mman.h b/arch/arm64/include/asm/mman.h index 9e39217b4afb..798d965760d4 100644 --- a/arch/arm64/include/asm/mman.h +++ b/arch/arm64/include/asm/mman.h @@ -6,6 +6,8 @@ #ifndef BUILD_VDSO #include +#include +#include #include static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot, @@ -31,19 +33,21 @@ static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot, } #define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey) -static inline unsigned long arch_calc_vm_flag_bits(unsigned long flags) +static inline unsigned long arch_calc_vm_flag_bits(struct file *file, + unsigned long flags) { /* * Only allow MTE on anonymous mappings as these are guaranteed to be * backed by tags-capable memory. The vm_flags may be overridden by a * filesystem supporting MTE (RAM-based). */ - if (system_supports_mte() && (flags & MAP_ANONYMOUS)) + if (system_supports_mte() && + ((flags & MAP_ANONYMOUS) || shmem_file(file))) return VM_MTE_ALLOWED; return 0; } -#define arch_calc_vm_flag_bits(flags) arch_calc_vm_flag_bits(flags) +#define arch_calc_vm_flag_bits(file, flags) arch_calc_vm_flag_bits(file, flags) static inline bool arch_validate_prot(unsigned long prot, unsigned long addr __always_unused) diff --git a/arch/parisc/include/asm/mman.h b/arch/parisc/include/asm/mman.h index 89b6beeda0b8..663f587dc789 100644 --- a/arch/parisc/include/asm/mman.h +++ b/arch/parisc/include/asm/mman.h @@ -2,6 +2,7 @@ #ifndef __ASM_MMAN_H__ #define __ASM_MMAN_H__ +#include #include /* PARISC cannot allow mdwe as it needs writable stacks */ @@ -11,7 +12,7 @@ static inline bool arch_memory_deny_write_exec_supported(void) } #define arch_memory_deny_write_exec_supported arch_memory_deny_write_exec_supported -static inline unsigned long arch_calc_vm_flag_bits(unsigned long flags) +static inline unsigned long arch_calc_vm_flag_bits(struct file *file, unsigned long flags) { /* * The stack on parisc grows upwards, so if userspace requests memory @@ -23,6 +24,6 @@ static inline unsigned long arch_calc_vm_flag_bits(unsigned long flags) return 0; } -#define arch_calc_vm_flag_bits(flags) arch_calc_vm_flag_bits(flags) +#define arch_calc_vm_flag_bits(file, flags) arch_calc_vm_flag_bits(file, flags) #endif /* __ASM_MMAN_H__ */ diff --git a/drivers/clk/qcom/clk-alpha-pll.c b/drivers/clk/qcom/clk-alpha-pll.c index f9105443d7db..be9bee6ab65f 100644 --- a/drivers/clk/qcom/clk-alpha-pll.c +++ b/drivers/clk/qcom/clk-alpha-pll.c @@ -40,7 +40,7 @@ #define PLL_USER_CTL(p) ((p)->offset + (p)->regs[PLL_OFF_USER_CTL]) # define PLL_POST_DIV_SHIFT 8 -# define PLL_POST_DIV_MASK(p) GENMASK((p)->width - 1, 0) +# define PLL_POST_DIV_MASK(p) GENMASK((p)->width ? (p)->width - 1 : 3, 0) # define PLL_ALPHA_MSB BIT(15) # define PLL_ALPHA_EN BIT(24) # define PLL_ALPHA_MODE BIT(25) diff --git a/drivers/clk/qcom/gcc-x1e80100.c b/drivers/clk/qcom/gcc-x1e80100.c index 0f578771071f..8ea25aa25dff 100644 --- a/drivers/clk/qcom/gcc-x1e80100.c +++ b/drivers/clk/qcom/gcc-x1e80100.c @@ -3123,7 +3123,7 @@ static struct clk_branch gcc_pcie_3_pipe_clk = { static struct clk_branch gcc_pcie_3_pipediv2_clk = { .halt_reg = 0x58060, - .halt_check = BRANCH_HALT_VOTED, + .halt_check = BRANCH_HALT_SKIP, .clkr = { .enable_reg = 0x52020, .enable_mask = BIT(5), @@ -3248,7 +3248,7 @@ static struct clk_branch gcc_pcie_4_pipe_clk = { static struct clk_branch gcc_pcie_4_pipediv2_clk = { .halt_reg = 0x6b054, - .halt_check = BRANCH_HALT_VOTED, + .halt_check = BRANCH_HALT_SKIP, .clkr = { .enable_reg = 0x52010, .enable_mask = BIT(27), @@ -3373,7 +3373,7 @@ static struct clk_branch gcc_pcie_5_pipe_clk = { static struct clk_branch gcc_pcie_5_pipediv2_clk = { .halt_reg = 0x2f054, - .halt_check = BRANCH_HALT_VOTED, + .halt_check = BRANCH_HALT_SKIP, .clkr = { .enable_reg = 0x52018, .enable_mask = BIT(19), @@ -3511,7 +3511,7 @@ static struct clk_branch gcc_pcie_6a_pipe_clk = { static struct clk_branch gcc_pcie_6a_pipediv2_clk = { .halt_reg = 0x31060, - .halt_check = BRANCH_HALT_VOTED, + .halt_check = BRANCH_HALT_SKIP, .clkr = { .enable_reg = 0x52018, .enable_mask = BIT(28), @@ -3649,7 +3649,7 @@ static struct clk_branch gcc_pcie_6b_pipe_clk = { static struct clk_branch gcc_pcie_6b_pipediv2_clk = { .halt_reg = 0x8d060, - .halt_check = BRANCH_HALT_VOTED, + .halt_check = BRANCH_HALT_SKIP, .clkr = { .enable_reg = 0x52010, .enable_mask = BIT(28), @@ -6155,7 +6155,7 @@ static struct gdsc gcc_usb3_mp_ss1_phy_gdsc = { .pd = { .name = "gcc_usb3_mp_ss1_phy_gdsc", }, - .pwrsts = PWRSTS_OFF_ON, + .pwrsts = PWRSTS_RET_ON, .flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE, }; diff --git a/drivers/clk/qcom/videocc-sm8350.c b/drivers/clk/qcom/videocc-sm8350.c index 5bd6fe3e1298..874d4da95ff8 100644 --- a/drivers/clk/qcom/videocc-sm8350.c +++ b/drivers/clk/qcom/videocc-sm8350.c @@ -452,7 +452,7 @@ static struct gdsc mvs0_gdsc = { .pd = { .name = "mvs0_gdsc", }, - .flags = HW_CTRL | RETAIN_FF_ENABLE, + .flags = HW_CTRL_TRIGGER | RETAIN_FF_ENABLE, .pwrsts = PWRSTS_OFF_ON, }; @@ -461,7 +461,7 @@ static struct gdsc mvs1_gdsc = { .pd = { .name = "mvs1_gdsc", }, - .flags = HW_CTRL | RETAIN_FF_ENABLE, + .flags = HW_CTRL_TRIGGER | RETAIN_FF_ENABLE, .pwrsts = PWRSTS_OFF_ON, }; diff --git a/drivers/i2c/busses/i2c-designware-common.c b/drivers/i2c/busses/i2c-designware-common.c index f31d352d98b5..9d88b4fa03e4 100644 --- a/drivers/i2c/busses/i2c-designware-common.c +++ b/drivers/i2c/busses/i2c-designware-common.c @@ -524,7 +524,7 @@ err_release_lock: void __i2c_dw_disable(struct dw_i2c_dev *dev) { struct i2c_timings *t = &dev->timings; - unsigned int raw_intr_stats; + unsigned int raw_intr_stats, ic_stats; unsigned int enable; int timeout = 100; bool abort_needed; @@ -532,9 +532,11 @@ void __i2c_dw_disable(struct dw_i2c_dev *dev) int ret; regmap_read(dev->map, DW_IC_RAW_INTR_STAT, &raw_intr_stats); + regmap_read(dev->map, DW_IC_STATUS, &ic_stats); regmap_read(dev->map, DW_IC_ENABLE, &enable); - abort_needed = raw_intr_stats & DW_IC_INTR_MST_ON_HOLD; + abort_needed = (raw_intr_stats & DW_IC_INTR_MST_ON_HOLD) || + (ic_stats & DW_IC_STATUS_MASTER_HOLD_TX_FIFO_EMPTY); if (abort_needed) { if (!(enable & DW_IC_ENABLE_ENABLE)) { regmap_write(dev->map, DW_IC_ENABLE, DW_IC_ENABLE_ENABLE); diff --git a/drivers/i2c/busses/i2c-designware-core.h b/drivers/i2c/busses/i2c-designware-core.h index 8e8854ec9882..2d32896d0673 100644 --- a/drivers/i2c/busses/i2c-designware-core.h +++ b/drivers/i2c/busses/i2c-designware-core.h @@ -116,6 +116,7 @@ #define DW_IC_STATUS_RFNE BIT(3) #define DW_IC_STATUS_MASTER_ACTIVITY BIT(5) #define DW_IC_STATUS_SLAVE_ACTIVITY BIT(6) +#define DW_IC_STATUS_MASTER_HOLD_TX_FIFO_EMPTY BIT(7) #define DW_IC_SDA_HOLD_RX_SHIFT 16 #define DW_IC_SDA_HOLD_RX_MASK GENMASK(23, 16) diff --git a/drivers/i2c/muxes/i2c-mux-mule.c b/drivers/i2c/muxes/i2c-mux-mule.c index 8e942470b35f..284ff4afeeac 100644 --- a/drivers/i2c/muxes/i2c-mux-mule.c +++ b/drivers/i2c/muxes/i2c-mux-mule.c @@ -66,8 +66,8 @@ static int mule_i2c_mux_probe(struct platform_device *pdev) priv = i2c_mux_priv(muxc); priv->regmap = dev_get_regmap(mux_dev->parent, NULL); - if (IS_ERR(priv->regmap)) - return dev_err_probe(mux_dev, PTR_ERR(priv->regmap), + if (!priv->regmap) + return dev_err_probe(mux_dev, -ENODEV, "No parent i2c register map\n"); platform_set_drvdata(pdev, muxc); diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 7f892a5ad37b..03025c12b90a 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -525,6 +525,13 @@ static int gic_irq_set_irqchip_state(struct irq_data *d, } gic_poke_irq(d, reg); + + /* + * Force read-back to guarantee that the active state has taken + * effect, and won't race with a guest-driven deactivation. + */ + if (reg == GICD_ISACTIVER) + gic_peek_irq(d, reg); return 0; } diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c index 3dbeffc650d3..6c488b1e2624 100644 --- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c +++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c @@ -593,7 +593,7 @@ vchiq_platform_init_state(struct vchiq_state *state) { struct vchiq_arm_state *platform_state; - platform_state = kzalloc(sizeof(*platform_state), GFP_KERNEL); + platform_state = devm_kzalloc(state->dev, sizeof(*platform_state), GFP_KERNEL); if (!platform_state) return -ENOMEM; @@ -1731,7 +1731,7 @@ static int vchiq_probe(struct platform_device *pdev) return -ENOENT; } - mgmt = kzalloc(sizeof(*mgmt), GFP_KERNEL); + mgmt = devm_kzalloc(&pdev->dev, sizeof(*mgmt), GFP_KERNEL); if (!mgmt) return -ENOMEM; @@ -1789,8 +1789,6 @@ static void vchiq_remove(struct platform_device *pdev) arm_state = vchiq_platform_get_arm_state(&mgmt->state); kthread_stop(arm_state->ka_thread); - - kfree(mgmt); } static struct platform_driver vchiq_driver = { diff --git a/drivers/thunderbolt/retimer.c b/drivers/thunderbolt/retimer.c index 7db9869a9f3f..89d2919d0193 100644 --- a/drivers/thunderbolt/retimer.c +++ b/drivers/thunderbolt/retimer.c @@ -532,6 +532,8 @@ int tb_retimer_scan(struct tb_port *port, bool add) } ret = 0; + if (!IS_ENABLED(CONFIG_USB4_DEBUGFS_MARGINING)) + max = min(last_idx, max); /* Add retimers if they do not exist already */ for (i = 1; i <= max; i++) { diff --git a/drivers/thunderbolt/usb4.c b/drivers/thunderbolt/usb4.c index 0a9b4aeb3fa1..402fdf8b1cde 100644 --- a/drivers/thunderbolt/usb4.c +++ b/drivers/thunderbolt/usb4.c @@ -48,7 +48,7 @@ enum usb4_ba_index { /* Delays in us used with usb4_port_wait_for_bit() */ #define USB4_PORT_DELAY 50 -#define USB4_PORT_SB_DELAY 5000 +#define USB4_PORT_SB_DELAY 1000 static int usb4_native_switch_op(struct tb_switch *sw, u16 opcode, u32 *metadata, u8 *status, diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 427e5660f87c..98114c2827c0 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -2342,10 +2342,18 @@ static int dwc3_suspend_common(struct dwc3 *dwc, pm_message_t msg) u32 reg; int i; - dwc->susphy_state = (dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0)) & - DWC3_GUSB2PHYCFG_SUSPHY) || - (dwc3_readl(dwc->regs, DWC3_GUSB3PIPECTL(0)) & - DWC3_GUSB3PIPECTL_SUSPHY); + if (!pm_runtime_suspended(dwc->dev) && !PMSG_IS_AUTO(msg)) { + dwc->susphy_state = (dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0)) & + DWC3_GUSB2PHYCFG_SUSPHY) || + (dwc3_readl(dwc->regs, DWC3_GUSB3PIPECTL(0)) & + DWC3_GUSB3PIPECTL_SUSPHY); + /* + * TI AM62 platform requires SUSPHY to be + * enabled for system suspend to work. + */ + if (!dwc->susphy_state) + dwc3_enable_susphy(dwc, true); + } switch (dwc->current_dr_role) { case DWC3_GCTL_PRTCAP_DEVICE: @@ -2398,15 +2406,6 @@ static int dwc3_suspend_common(struct dwc3 *dwc, pm_message_t msg) break; } - if (!PMSG_IS_AUTO(msg)) { - /* - * TI AM62 platform requires SUSPHY to be - * enabled for system suspend to work. - */ - if (!dwc->susphy_state) - dwc3_enable_susphy(dwc, true); - } - return 0; } diff --git a/drivers/usb/musb/sunxi.c b/drivers/usb/musb/sunxi.c index d54283fd026b..05b6e7e52e02 100644 --- a/drivers/usb/musb/sunxi.c +++ b/drivers/usb/musb/sunxi.c @@ -293,8 +293,6 @@ static int sunxi_musb_exit(struct musb *musb) if (test_bit(SUNXI_MUSB_FL_HAS_SRAM, &glue->flags)) sunxi_sram_release(musb->controller->parent); - devm_usb_put_phy(glue->dev, glue->xceiv); - return 0; } diff --git a/drivers/usb/serial/io_edgeport.c b/drivers/usb/serial/io_edgeport.c index c7d6b5e3f898..28c71d99e857 100644 --- a/drivers/usb/serial/io_edgeport.c +++ b/drivers/usb/serial/io_edgeport.c @@ -770,11 +770,12 @@ static void edge_bulk_out_data_callback(struct urb *urb) static void edge_bulk_out_cmd_callback(struct urb *urb) { struct edgeport_port *edge_port = urb->context; + struct device *dev = &urb->dev->dev; int status = urb->status; atomic_dec(&CmdUrbs); - dev_dbg(&urb->dev->dev, "%s - FREE URB %p (outstanding %d)\n", - __func__, urb, atomic_read(&CmdUrbs)); + dev_dbg(dev, "%s - FREE URB %p (outstanding %d)\n", __func__, urb, + atomic_read(&CmdUrbs)); /* clean up the transfer buffer */ @@ -784,8 +785,7 @@ static void edge_bulk_out_cmd_callback(struct urb *urb) usb_free_urb(urb); if (status) { - dev_dbg(&urb->dev->dev, - "%s - nonzero write bulk status received: %d\n", + dev_dbg(dev, "%s - nonzero write bulk status received: %d\n", __func__, status); return; } diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 4f18f189f309..9ba5584061c8 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -251,6 +251,7 @@ static void option_instat_callback(struct urb *urb); #define QUECTEL_VENDOR_ID 0x2c7c /* These Quectel products use Quectel's vendor ID */ #define QUECTEL_PRODUCT_EC21 0x0121 +#define QUECTEL_PRODUCT_RG650V 0x0122 #define QUECTEL_PRODUCT_EM061K_LTA 0x0123 #define QUECTEL_PRODUCT_EM061K_LMS 0x0124 #define QUECTEL_PRODUCT_EC25 0x0125 @@ -1273,6 +1274,8 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EG912Y, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EG916Q, 0xff, 0x00, 0x00) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500K, 0xff, 0x00, 0x00) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RG650V, 0xff, 0xff, 0x30) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RG650V, 0xff, 0, 0) }, { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6001) }, { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CMU_300) }, @@ -2320,6 +2323,9 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(0x2cb7, 0x010b, 0xff, 0xff, 0x30) }, /* Fibocom FG150 Diag */ { USB_DEVICE_AND_INTERFACE_INFO(0x2cb7, 0x010b, 0xff, 0, 0) }, /* Fibocom FG150 AT */ { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0111, 0xff) }, /* Fibocom FM160 (MBIM mode) */ + { USB_DEVICE_AND_INTERFACE_INFO(0x2cb7, 0x0112, 0xff, 0xff, 0x30) }, /* Fibocom FG132 Diag */ + { USB_DEVICE_AND_INTERFACE_INFO(0x2cb7, 0x0112, 0xff, 0xff, 0x40) }, /* Fibocom FG132 AT */ + { USB_DEVICE_AND_INTERFACE_INFO(0x2cb7, 0x0112, 0xff, 0, 0) }, /* Fibocom FG132 NMEA */ { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0115, 0xff), /* Fibocom FM135 (laptop MBIM) */ .driver_info = RSVD(5) }, { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a0, 0xff) }, /* Fibocom NL668-AM/NL652-EU (laptop MBIM) */ diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c index c7de9585feb2..13c664317a05 100644 --- a/drivers/usb/serial/qcserial.c +++ b/drivers/usb/serial/qcserial.c @@ -166,6 +166,8 @@ static const struct usb_device_id id_table[] = { {DEVICE_SWI(0x1199, 0x9090)}, /* Sierra Wireless EM7565 QDL */ {DEVICE_SWI(0x1199, 0x9091)}, /* Sierra Wireless EM7565 */ {DEVICE_SWI(0x1199, 0x90d2)}, /* Sierra Wireless EM9191 QDL */ + {DEVICE_SWI(0x1199, 0x90e4)}, /* Sierra Wireless EM86xx QDL*/ + {DEVICE_SWI(0x1199, 0x90e5)}, /* Sierra Wireless EM86xx */ {DEVICE_SWI(0x1199, 0xc080)}, /* Sierra Wireless EM7590 QDL */ {DEVICE_SWI(0x1199, 0xc081)}, /* Sierra Wireless EM7590 */ {DEVICE_SWI(0x413c, 0x81a2)}, /* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card */ diff --git a/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_pdphy.c b/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_pdphy.c index 5b7f52b74a40..726423684bae 100644 --- a/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_pdphy.c +++ b/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_pdphy.c @@ -227,6 +227,10 @@ qcom_pmic_typec_pdphy_pd_transmit_payload(struct pmic_typec_pdphy *pmic_typec_pd spin_lock_irqsave(&pmic_typec_pdphy->lock, flags); + hdr_len = sizeof(msg->header); + txbuf_len = pd_header_cnt_le(msg->header) * 4; + txsize_len = hdr_len + txbuf_len - 1; + ret = regmap_read(pmic_typec_pdphy->regmap, pmic_typec_pdphy->base + USB_PDPHY_RX_ACKNOWLEDGE_REG, &val); @@ -244,10 +248,6 @@ qcom_pmic_typec_pdphy_pd_transmit_payload(struct pmic_typec_pdphy *pmic_typec_pd if (ret) goto done; - hdr_len = sizeof(msg->header); - txbuf_len = pd_header_cnt_le(msg->header) * 4; - txsize_len = hdr_len + txbuf_len - 1; - /* Write message header sizeof(u16) to USB_PDPHY_TX_BUFFER_HDR_REG */ ret = regmap_bulk_write(pmic_typec_pdphy->regmap, pmic_typec_pdphy->base + USB_PDPHY_TX_BUFFER_HDR_REG, diff --git a/drivers/usb/typec/ucsi/ucsi_ccg.c b/drivers/usb/typec/ucsi/ucsi_ccg.c index ba58d11907bc..bccfc03b5986 100644 --- a/drivers/usb/typec/ucsi/ucsi_ccg.c +++ b/drivers/usb/typec/ucsi/ucsi_ccg.c @@ -482,6 +482,8 @@ static void ucsi_ccg_update_set_new_cam_cmd(struct ucsi_ccg *uc, port = uc->orig; new_cam = UCSI_SET_NEW_CAM_GET_AM(*cmd); + if (new_cam >= ARRAY_SIZE(uc->updated)) + return; new_port = &uc->updated[new_cam]; cam = new_port->linked_idx; enter_new_mode = UCSI_SET_NEW_CAM_ENTER(*cmd); diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index dd0a05365e79..73a6f6fd8a8e 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -2036,8 +2036,7 @@ static int ocfs2_xa_remove(struct ocfs2_xa_loc *loc, rc = 0; ocfs2_xa_cleanup_value_truncate(loc, "removing", orig_clusters); - if (rc) - goto out; + goto out; } } diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index b52d85f8ad59..b4521b096058 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -457,10 +457,6 @@ static vm_fault_t mmap_vmcore_fault(struct vm_fault *vmf) #endif } -static const struct vm_operations_struct vmcore_mmap_ops = { - .fault = mmap_vmcore_fault, -}; - /** * vmcore_alloc_buf - allocate buffer in vmalloc memory * @size: size of buffer @@ -488,6 +484,11 @@ static inline char *vmcore_alloc_buf(size_t size) * virtually contiguous user-space in ELF layout. */ #ifdef CONFIG_MMU + +static const struct vm_operations_struct vmcore_mmap_ops = { + .fault = mmap_vmcore_fault, +}; + /* * remap_oldmem_pfn_checked - do remap_oldmem_pfn_range replacing all pages * reported as not being ram with the zero page. diff --git a/include/linux/mman.h b/include/linux/mman.h index bcb201ab7a41..a842783ffa62 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -2,6 +2,7 @@ #ifndef _LINUX_MMAN_H #define _LINUX_MMAN_H +#include #include #include @@ -94,7 +95,7 @@ static inline void vm_unacct_memory(long pages) #endif #ifndef arch_calc_vm_flag_bits -#define arch_calc_vm_flag_bits(flags) 0 +#define arch_calc_vm_flag_bits(file, flags) 0 #endif #ifndef arch_validate_prot @@ -151,13 +152,13 @@ calc_vm_prot_bits(unsigned long prot, unsigned long pkey) * Combine the mmap "flags" argument into "vm_flags" used internally. */ static inline unsigned long -calc_vm_flag_bits(unsigned long flags) +calc_vm_flag_bits(struct file *file, unsigned long flags) { return _calc_vm_trans(flags, MAP_GROWSDOWN, VM_GROWSDOWN ) | _calc_vm_trans(flags, MAP_LOCKED, VM_LOCKED ) | _calc_vm_trans(flags, MAP_SYNC, VM_SYNC ) | _calc_vm_trans(flags, MAP_STACK, VM_NOHUGEPAGE) | - arch_calc_vm_flag_bits(flags); + arch_calc_vm_flag_bits(file, flags); } unsigned long vm_commit_limit(void); @@ -188,16 +189,31 @@ static inline bool arch_memory_deny_write_exec_supported(void) * * d) mmap(PROT_READ | PROT_EXEC) * mmap(PROT_READ | PROT_EXEC | PROT_BTI) + * + * This is only applicable if the user has set the Memory-Deny-Write-Execute + * (MDWE) protection mask for the current process. + * + * @old specifies the VMA flags the VMA originally possessed, and @new the ones + * we propose to set. + * + * Return: false if proposed change is OK, true if not ok and should be denied. */ -static inline bool map_deny_write_exec(struct vm_area_struct *vma, unsigned long vm_flags) +static inline bool map_deny_write_exec(unsigned long old, unsigned long new) { + /* If MDWE is disabled, we have nothing to deny. */ if (!test_bit(MMF_HAS_MDWE, ¤t->mm->flags)) return false; - if ((vm_flags & VM_EXEC) && (vm_flags & VM_WRITE)) + /* If the new VMA is not executable, we have nothing to deny. */ + if (!(new & VM_EXEC)) + return false; + + /* Under MDWE we do not accept newly writably executable VMAs... */ + if (new & VM_WRITE) return true; - if (!(vma->vm_flags & VM_EXEC) && (vm_flags & VM_EXEC)) + /* ...nor previously non-executable VMAs becoming executable. */ + if (!(old & VM_EXEC)) return true; return false; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 1701c782c64e..3c194d440d59 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -821,6 +821,7 @@ struct zone { unsigned long watermark_boost; unsigned long nr_reserved_highatomic; + unsigned long nr_free_highatomic; /* * We don't know if the memory that we're going to allocate will be diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 3625096d5f85..7183e5aca282 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -141,7 +141,8 @@ static inline long get_rlimit_value(struct ucounts *ucounts, enum rlimit_type ty long inc_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v); bool dec_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v); -long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type); +long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type, + bool override_rlimit); void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum rlimit_type type); bool is_rlimit_overlimit(struct ucounts *ucounts, enum rlimit_type type, unsigned long max); diff --git a/kernel/signal.c b/kernel/signal.c index 4344860ffcac..cbabb2d05e0a 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -419,7 +419,8 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t gfp_flags, */ rcu_read_lock(); ucounts = task_ucounts(t); - sigpending = inc_rlimit_get_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING); + sigpending = inc_rlimit_get_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING, + override_rlimit); rcu_read_unlock(); if (!sigpending) return NULL; diff --git a/kernel/ucount.c b/kernel/ucount.c index 8c07714ff27d..696406939be5 100644 --- a/kernel/ucount.c +++ b/kernel/ucount.c @@ -307,7 +307,8 @@ void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum rlimit_type type) do_dec_rlimit_put_ucounts(ucounts, NULL, type); } -long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type) +long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type, + bool override_rlimit) { /* Caller must hold a reference to ucounts */ struct ucounts *iter; @@ -317,10 +318,11 @@ long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type) for (iter = ucounts; iter; iter = iter->ns->ucounts) { long new = atomic_long_add_return(1, &iter->rlimit[type]); if (new < 0 || new > max) - goto unwind; + goto dec_unwind; if (iter == ucounts) ret = new; - max = get_userns_rlimit_max(iter->ns, type); + if (!override_rlimit) + max = get_userns_rlimit_max(iter->ns, type); /* * Grab an extra ucount reference for the caller when * the rlimit count was previously 0. @@ -334,7 +336,6 @@ long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type) dec_unwind: dec = atomic_long_sub_return(1, &iter->rlimit[type]); WARN_ON_ONCE(dec < 0); -unwind: do_dec_rlimit_put_ucounts(ucounts, iter, type); return 0; } diff --git a/lib/objpool.c b/lib/objpool.c index fd108fe0d095..b998b720c732 100644 --- a/lib/objpool.c +++ b/lib/objpool.c @@ -74,15 +74,21 @@ objpool_init_percpu_slots(struct objpool_head *pool, int nr_objs, * warm caches and TLB hits. in default vmalloc is used to * reduce the pressure of kernel slab system. as we know, * mimimal size of vmalloc is one page since vmalloc would - * always align the requested size to page size + * always align the requested size to page size. + * but if vmalloc fails or it is not available (e.g. GFP_ATOMIC) + * allocate percpu slot with kmalloc. */ - if ((pool->gfp & GFP_ATOMIC) == GFP_ATOMIC) - slot = kmalloc_node(size, pool->gfp, cpu_to_node(i)); - else + slot = NULL; + + if ((pool->gfp & (GFP_ATOMIC | GFP_KERNEL)) != GFP_ATOMIC) slot = __vmalloc_node(size, sizeof(void *), pool->gfp, cpu_to_node(i), __builtin_return_address(0)); - if (!slot) - return -ENOMEM; + + if (!slot) { + slot = kmalloc_node(size, pool->gfp, cpu_to_node(i)); + if (!slot) + return -ENOMEM; + } memset(slot, 0, size); pool->cpu_slots[i] = slot; diff --git a/mm/damon/core.c b/mm/damon/core.c index a83f3b736d51..511c3f61ab44 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -1412,7 +1412,7 @@ static void damon_do_apply_schemes(struct damon_ctx *c, damon_for_each_scheme(s, c) { struct damos_quota *quota = &s->quota; - if (c->passed_sample_intervals != s->next_apply_sis) + if (c->passed_sample_intervals < s->next_apply_sis) continue; if (!s->wmarks.activated) @@ -1456,17 +1456,31 @@ static unsigned long damon_feed_loop_next_input(unsigned long last_input, unsigned long score) { const unsigned long goal = 10000; - unsigned long score_goal_diff = max(goal, score) - min(goal, score); - unsigned long score_goal_diff_bp = score_goal_diff * 10000 / goal; - unsigned long compensation = last_input * score_goal_diff_bp / 10000; /* Set minimum input as 10000 to avoid compensation be zero */ const unsigned long min_input = 10000; + unsigned long score_goal_diff, compensation; + bool over_achieving = score > goal; - if (goal > score) + if (score == goal) + return last_input; + if (score >= goal * 2) + return min_input; + + if (over_achieving) + score_goal_diff = score - goal; + else + score_goal_diff = goal - score; + + if (last_input < ULONG_MAX / score_goal_diff) + compensation = last_input * score_goal_diff / goal; + else + compensation = last_input / goal * score_goal_diff; + + if (over_achieving) + return max(last_input - compensation, min_input); + if (last_input < ULONG_MAX - compensation) return last_input + compensation; - if (last_input > compensation + min_input) - return last_input - compensation; - return min_input; + return ULONG_MAX; } #ifdef CONFIG_PSI @@ -1622,7 +1636,7 @@ static void kdamond_apply_schemes(struct damon_ctx *c) bool has_schemes_to_apply = false; damon_for_each_scheme(s, c) { - if (c->passed_sample_intervals != s->next_apply_sis) + if (c->passed_sample_intervals < s->next_apply_sis) continue; if (!s->wmarks.activated) @@ -1642,9 +1656,9 @@ static void kdamond_apply_schemes(struct damon_ctx *c) } damon_for_each_scheme(s, c) { - if (c->passed_sample_intervals != s->next_apply_sis) + if (c->passed_sample_intervals < s->next_apply_sis) continue; - s->next_apply_sis += + s->next_apply_sis = c->passed_sample_intervals + (s->apply_interval_us ? s->apply_interval_us : c->attrs.aggr_interval) / sample_interval; } @@ -2000,7 +2014,7 @@ static int kdamond_fn(void *data) if (ctx->ops.check_accesses) max_nr_accesses = ctx->ops.check_accesses(ctx); - if (ctx->passed_sample_intervals == next_aggregation_sis) { + if (ctx->passed_sample_intervals >= next_aggregation_sis) { kdamond_merge_regions(ctx, max_nr_accesses / 10, sz_limit); @@ -2018,7 +2032,7 @@ static int kdamond_fn(void *data) sample_interval = ctx->attrs.sample_interval ? ctx->attrs.sample_interval : 1; - if (ctx->passed_sample_intervals == next_aggregation_sis) { + if (ctx->passed_sample_intervals >= next_aggregation_sis) { ctx->next_aggregation_sis = next_aggregation_sis + ctx->attrs.aggr_interval / sample_interval; @@ -2028,7 +2042,7 @@ static int kdamond_fn(void *data) ctx->ops.reset_aggregated(ctx); } - if (ctx->passed_sample_intervals == next_ops_update_sis) { + if (ctx->passed_sample_intervals >= next_ops_update_sis) { ctx->next_ops_update_sis = next_ops_update_sis + ctx->attrs.ops_update_interval / sample_interval; diff --git a/mm/filemap.c b/mm/filemap.c index 36d22968be9a..56fa431c52af 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2625,7 +2625,7 @@ ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter, if (unlikely(!iov_iter_count(iter))) return 0; - iov_iter_truncate(iter, inode->i_sb->s_maxbytes); + iov_iter_truncate(iter, inode->i_sb->s_maxbytes - iocb->ki_pos); folio_batch_init(&fbatch); do { diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 2fb328880b50..03fd4bc39ea1 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -3588,10 +3588,27 @@ int split_folio_to_list(struct folio *folio, struct list_head *list) return split_huge_page_to_list_to_order(&folio->page, list, ret); } -void __folio_undo_large_rmappable(struct folio *folio) +/* + * __folio_unqueue_deferred_split() is not to be called directly: + * the folio_unqueue_deferred_split() inline wrapper in mm/internal.h + * limits its calls to those folios which may have a _deferred_list for + * queueing THP splits, and that list is (racily observed to be) non-empty. + * + * It is unsafe to call folio_unqueue_deferred_split() until folio refcount is + * zero: because even when split_queue_lock is held, a non-empty _deferred_list + * might be in use on deferred_split_scan()'s unlocked on-stack list. + * + * If memory cgroups are enabled, split_queue_lock is in the mem_cgroup: it is + * therefore important to unqueue deferred split before changing folio memcg. + */ +bool __folio_unqueue_deferred_split(struct folio *folio) { struct deferred_split *ds_queue; unsigned long flags; + bool unqueued = false; + + WARN_ON_ONCE(folio_ref_count(folio)); + WARN_ON_ONCE(!mem_cgroup_disabled() && !folio_memcg(folio)); ds_queue = get_deferred_split_queue(folio); spin_lock_irqsave(&ds_queue->split_queue_lock, flags); @@ -3603,8 +3620,11 @@ void __folio_undo_large_rmappable(struct folio *folio) MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1); } list_del_init(&folio->_deferred_list); + unqueued = true; } spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); + + return unqueued; /* useful for debug warnings */ } /* partially_mapped=false won't clear PG_partially_mapped folio flag */ @@ -3627,14 +3647,11 @@ void deferred_split_folio(struct folio *folio, bool partially_mapped) return; /* - * The try_to_unmap() in page reclaim path might reach here too, - * this may cause a race condition to corrupt deferred split queue. - * And, if page reclaim is already handling the same folio, it is - * unnecessary to handle it again in shrinker. - * - * Check the swapcache flag to determine if the folio is being - * handled by page reclaim since THP swap would add the folio into - * swap cache before calling try_to_unmap(). + * Exclude swapcache: originally to avoid a corrupt deferred split + * queue. Nowadays that is fully prevented by mem_cgroup_swapout(); + * but if page reclaim is already handling the same folio, it is + * unnecessary to handle it again in the shrinker, so excluding + * swapcache here may still be a useful optimization. */ if (folio_test_swapcache(folio)) return; @@ -3718,8 +3735,8 @@ static unsigned long deferred_split_scan(struct shrinker *shrink, struct deferred_split *ds_queue = &pgdata->deferred_split_queue; unsigned long flags; LIST_HEAD(list); - struct folio *folio, *next; - int split = 0; + struct folio *folio, *next, *prev = NULL; + int split = 0, removed = 0; #ifdef CONFIG_MEMCG if (sc->memcg) @@ -3775,15 +3792,28 @@ next: */ if (!did_split && !folio_test_partially_mapped(folio)) { list_del_init(&folio->_deferred_list); - ds_queue->split_queue_len--; + removed++; + } else { + /* + * That unlocked list_del_init() above would be unsafe, + * unless its folio is separated from any earlier folios + * left on the list (which may be concurrently unqueued) + * by one safe folio with refcount still raised. + */ + swap(folio, prev); } - folio_put(folio); + if (folio) + folio_put(folio); } spin_lock_irqsave(&ds_queue->split_queue_lock, flags); list_splice_tail(&list, &ds_queue->split_queue); + ds_queue->split_queue_len -= removed; spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); + if (prev) + folio_put(prev); + /* * Stop shrinker if we didn't split any page, but the queue is empty. * This can happen if pages were freed under us. diff --git a/mm/internal.h b/mm/internal.h index 93083bbeeefa..64c2eb0b160e 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -108,6 +108,51 @@ static inline void *folio_raw_mapping(const struct folio *folio) return (void *)(mapping & ~PAGE_MAPPING_FLAGS); } +/* + * This is a file-backed mapping, and is about to be memory mapped - invoke its + * mmap hook and safely handle error conditions. On error, VMA hooks will be + * mutated. + * + * @file: File which backs the mapping. + * @vma: VMA which we are mapping. + * + * Returns: 0 if success, error otherwise. + */ +static inline int mmap_file(struct file *file, struct vm_area_struct *vma) +{ + int err = call_mmap(file, vma); + + if (likely(!err)) + return 0; + + /* + * OK, we tried to call the file hook for mmap(), but an error + * arose. The mapping is in an inconsistent state and we most not invoke + * any further hooks on it. + */ + vma->vm_ops = &vma_dummy_vm_ops; + + return err; +} + +/* + * If the VMA has a close hook then close it, and since closing it might leave + * it in an inconsistent state which makes the use of any hooks suspect, clear + * them down by installing dummy empty hooks. + */ +static inline void vma_close(struct vm_area_struct *vma) +{ + if (vma->vm_ops && vma->vm_ops->close) { + vma->vm_ops->close(vma); + + /* + * The mapping is in an inconsistent state, and no further hooks + * may be invoked upon it. + */ + vma->vm_ops = &vma_dummy_vm_ops; + } +} + #ifdef CONFIG_MMU /* Flags for folio_pte_batch(). */ @@ -639,11 +684,11 @@ static inline void folio_set_order(struct folio *folio, unsigned int order) #endif } -void __folio_undo_large_rmappable(struct folio *folio); -static inline void folio_undo_large_rmappable(struct folio *folio) +bool __folio_unqueue_deferred_split(struct folio *folio); +static inline bool folio_unqueue_deferred_split(struct folio *folio) { if (folio_order(folio) <= 1 || !folio_test_large_rmappable(folio)) - return; + return false; /* * At this point, there is no one trying to add the folio to @@ -651,9 +696,9 @@ static inline void folio_undo_large_rmappable(struct folio *folio) * to check without acquiring the split_queue_lock. */ if (data_race(list_empty(&folio->_deferred_list))) - return; + return false; - __folio_undo_large_rmappable(folio); + return __folio_unqueue_deferred_split(folio); } static inline struct folio *page_rmappable_folio(struct page *page) diff --git a/mm/memcontrol-v1.c b/mm/memcontrol-v1.c index 81d8819f13cd..f8744f5630bb 100644 --- a/mm/memcontrol-v1.c +++ b/mm/memcontrol-v1.c @@ -848,6 +848,8 @@ static int mem_cgroup_move_account(struct folio *folio, css_get(&to->css); css_put(&from->css); + /* Warning should never happen, so don't worry about refcount non-0 */ + WARN_ON_ONCE(folio_unqueue_deferred_split(folio)); folio->memcg_data = (unsigned long)to; __folio_memcg_unlock(from); @@ -1217,7 +1219,9 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd, enum mc_target_type target_type; union mc_target target; struct folio *folio; + bool tried_split_before = false; +retry_pmd: ptl = pmd_trans_huge_lock(pmd, vma); if (ptl) { if (mc.precharge < HPAGE_PMD_NR) { @@ -1227,6 +1231,27 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd, target_type = get_mctgt_type_thp(vma, addr, *pmd, &target); if (target_type == MC_TARGET_PAGE) { folio = target.folio; + /* + * Deferred split queue locking depends on memcg, + * and unqueue is unsafe unless folio refcount is 0: + * split or skip if on the queue? first try to split. + */ + if (!list_empty(&folio->_deferred_list)) { + spin_unlock(ptl); + if (!tried_split_before) + split_folio(folio); + folio_unlock(folio); + folio_put(folio); + if (tried_split_before) + return 0; + tried_split_before = true; + goto retry_pmd; + } + /* + * So long as that pmd lock is held, the folio cannot + * be racily added to the _deferred_list, because + * __folio_remove_rmap() will find !partially_mapped. + */ if (folio_isolate_lru(folio)) { if (!mem_cgroup_move_account(folio, true, mc.from, mc.to)) { diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 7845c64a2c57..06df2af97415 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4629,10 +4629,6 @@ static void uncharge_folio(struct folio *folio, struct uncharge_gather *ug) struct obj_cgroup *objcg; VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); - VM_BUG_ON_FOLIO(folio_order(folio) > 1 && - !folio_test_hugetlb(folio) && - !list_empty(&folio->_deferred_list) && - folio_test_partially_mapped(folio), folio); /* * Nobody should be changing or seriously looking at @@ -4679,6 +4675,7 @@ static void uncharge_folio(struct folio *folio, struct uncharge_gather *ug) ug->nr_memory += nr_pages; ug->pgpgout++; + WARN_ON_ONCE(folio_unqueue_deferred_split(folio)); folio->memcg_data = 0; } @@ -4790,6 +4787,9 @@ void mem_cgroup_migrate(struct folio *old, struct folio *new) /* Transfer the charge and the css ref */ commit_charge(new, memcg); + + /* Warning should never happen, so don't worry about refcount non-0 */ + WARN_ON_ONCE(folio_unqueue_deferred_split(old)); old->memcg_data = 0; } @@ -4976,6 +4976,7 @@ void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry) VM_BUG_ON_FOLIO(oldid, folio); mod_memcg_state(swap_memcg, MEMCG_SWAP, nr_entries); + folio_unqueue_deferred_split(folio); folio->memcg_data = 0; if (!mem_cgroup_is_root(memcg)) diff --git a/mm/migrate.c b/mm/migrate.c index fab84a776088..dfa24e41e8f9 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -490,7 +490,7 @@ static int __folio_migrate_mapping(struct address_space *mapping, folio_test_large_rmappable(folio)) { if (!folio_ref_freeze(folio, expected_count)) return -EAGAIN; - folio_undo_large_rmappable(folio); + folio_unqueue_deferred_split(folio); folio_ref_unfreeze(folio, expected_count); } @@ -515,7 +515,7 @@ static int __folio_migrate_mapping(struct address_space *mapping, } /* Take off deferred split queue while frozen and memcg set */ - folio_undo_large_rmappable(folio); + folio_unqueue_deferred_split(folio); /* * Now we know that no one else is looking at the folio: diff --git a/mm/mlock.c b/mm/mlock.c index e3e3dc2b2956..cde076fa7d5e 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -725,14 +725,17 @@ static int apply_mlockall_flags(int flags) } for_each_vma(vmi, vma) { + int error; vm_flags_t newflags; newflags = vma->vm_flags & ~VM_LOCKED_MASK; newflags |= to_add; - /* Ignore errors */ - mlock_fixup(&vmi, vma, &prev, vma->vm_start, vma->vm_end, - newflags); + error = mlock_fixup(&vmi, vma, &prev, vma->vm_start, vma->vm_end, + newflags); + /* Ignore errors, but prev needs fixing up. */ + if (error) + prev = vma; cond_resched(); } out: diff --git a/mm/mmap.c b/mm/mmap.c index bbbad427d7cb..09496916ff7a 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -344,7 +344,7 @@ unsigned long do_mmap(struct file *file, unsigned long addr, * to. we assume access permissions have been handled by the open * of the memory object, so we don't do any here. */ - vm_flags |= calc_vm_prot_bits(prot, pkey) | calc_vm_flag_bits(flags) | + vm_flags |= calc_vm_prot_bits(prot, pkey) | calc_vm_flag_bits(file, flags) | mm->def_flags | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC; /* Obtain the address to map to. we verify (or select) it and ensure @@ -1360,20 +1360,18 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len, return do_vmi_munmap(&vmi, mm, start, len, uf, false); } -unsigned long mmap_region(struct file *file, unsigned long addr, +static unsigned long __mmap_region(struct file *file, unsigned long addr, unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, struct list_head *uf) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma = NULL; pgoff_t pglen = PHYS_PFN(len); - struct vm_area_struct *merge; unsigned long charged = 0; struct vma_munmap_struct vms; struct ma_state mas_detach; struct maple_tree mt_detach; unsigned long end = addr + len; - bool writable_file_mapping = false; int error; VMA_ITERATOR(vmi, mm, addr); VMG_STATE(vmg, mm, &vmi, addr, end, vm_flags, pgoff); @@ -1424,7 +1422,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, /* * clear PTEs while the vma is still in the tree so that rmap * cannot race with the freeing later in the truncate scenario. - * This is also needed for call_mmap(), which is why vm_ops + * This is also needed for mmap_file(), which is why vm_ops * close function is called. */ vms_clean_up_area(&vms, &mas_detach); @@ -1447,35 +1445,35 @@ unsigned long mmap_region(struct file *file, unsigned long addr, vm_flags_init(vma, vm_flags); vma->vm_page_prot = vm_get_page_prot(vm_flags); + if (vma_iter_prealloc(&vmi, vma)) { + error = -ENOMEM; + goto free_vma; + } + if (file) { vma->vm_file = get_file(file); - error = call_mmap(file, vma); + error = mmap_file(file, vma); if (error) - goto unmap_and_free_vma; - - if (vma_is_shared_maywrite(vma)) { - error = mapping_map_writable(file->f_mapping); - if (error) - goto close_and_free_vma; - - writable_file_mapping = true; - } + goto unmap_and_free_file_vma; + /* Drivers cannot alter the address of the VMA. */ + WARN_ON_ONCE(addr != vma->vm_start); /* - * Expansion is handled above, merging is handled below. - * Drivers should not alter the address of the VMA. + * Drivers should not permit writability when previously it was + * disallowed. */ - if (WARN_ON((addr != vma->vm_start))) { - error = -EINVAL; - goto close_and_free_vma; - } + VM_WARN_ON_ONCE(vm_flags != vma->vm_flags && + !(vm_flags & VM_MAYWRITE) && + (vma->vm_flags & VM_MAYWRITE)); vma_iter_config(&vmi, addr, end); /* - * If vm_flags changed after call_mmap(), we should try merge + * If vm_flags changed after mmap_file(), we should try merge * vma again as we may succeed this time. */ if (unlikely(vm_flags != vma->vm_flags && vmg.prev)) { + struct vm_area_struct *merge; + vmg.flags = vma->vm_flags; /* If this fails, state is reset ready for a reattempt. */ merge = vma_merge_new_range(&vmg); @@ -1493,7 +1491,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, vma = merge; /* Update vm_flags to pick up the change. */ vm_flags = vma->vm_flags; - goto unmap_writable; + goto file_expanded; } vma_iter_config(&vmi, addr, end); } @@ -1502,26 +1500,15 @@ unsigned long mmap_region(struct file *file, unsigned long addr, } else if (vm_flags & VM_SHARED) { error = shmem_zero_setup(vma); if (error) - goto free_vma; + goto free_iter_vma; } else { vma_set_anonymous(vma); } - if (map_deny_write_exec(vma, vma->vm_flags)) { - error = -EACCES; - goto close_and_free_vma; - } - - /* Allow architectures to sanity-check the vm_flags */ - if (!arch_validate_flags(vma->vm_flags)) { - error = -EINVAL; - goto close_and_free_vma; - } - - if (vma_iter_prealloc(&vmi, vma)) { - error = -ENOMEM; - goto close_and_free_vma; - } +#ifdef CONFIG_SPARC64 + /* TODO: Fix SPARC ADI! */ + WARN_ON_ONCE(!arch_validate_flags(vm_flags)); +#endif /* Lock the VMA since it is modified after insertion into VMA tree */ vma_start_write(vma); @@ -1535,10 +1522,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, */ khugepaged_enter_vma(vma, vma->vm_flags); - /* Once vma denies write, undo our temporary denial count */ -unmap_writable: - if (writable_file_mapping) - mapping_unmap_writable(file->f_mapping); +file_expanded: file = vma->vm_file; ksm_add_vma(vma); expanded: @@ -1571,24 +1555,17 @@ expanded: vma_set_page_prot(vma); - validate_mm(mm); return addr; -close_and_free_vma: - if (file && !vms.closed_vm_ops && vma->vm_ops && vma->vm_ops->close) - vma->vm_ops->close(vma); +unmap_and_free_file_vma: + fput(vma->vm_file); + vma->vm_file = NULL; - if (file || vma->vm_file) { -unmap_and_free_vma: - fput(vma->vm_file); - vma->vm_file = NULL; - - vma_iter_set(&vmi, vma->vm_end); - /* Undo any partial mapping done by a device driver. */ - unmap_region(&vmi.mas, vma, vmg.prev, vmg.next); - } - if (writable_file_mapping) - mapping_unmap_writable(file->f_mapping); + vma_iter_set(&vmi, vma->vm_end); + /* Undo any partial mapping done by a device driver. */ + unmap_region(&vmi.mas, vma, vmg.prev, vmg.next); +free_iter_vma: + vma_iter_free(&vmi); free_vma: vm_area_free(vma); unacct_error: @@ -1598,10 +1575,43 @@ unacct_error: abort_munmap: vms_abort_munmap_vmas(&vms, &mas_detach); gather_failed: - validate_mm(mm); return error; } +unsigned long mmap_region(struct file *file, unsigned long addr, + unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, + struct list_head *uf) +{ + unsigned long ret; + bool writable_file_mapping = false; + + /* Check to see if MDWE is applicable. */ + if (map_deny_write_exec(vm_flags, vm_flags)) + return -EACCES; + + /* Allow architectures to sanity-check the vm_flags. */ + if (!arch_validate_flags(vm_flags)) + return -EINVAL; + + /* Map writable and ensure this isn't a sealed memfd. */ + if (file && is_shared_maywrite(vm_flags)) { + int error = mapping_map_writable(file->f_mapping); + + if (error) + return error; + writable_file_mapping = true; + } + + ret = __mmap_region(file, addr, len, vm_flags, pgoff, uf); + + /* Clear our write mapping regardless of error. */ + if (writable_file_mapping) + mapping_unmap_writable(file->f_mapping); + + validate_mm(current->mm); + return ret; +} + static int __vm_munmap(unsigned long start, size_t len, bool unlock) { int ret; @@ -1937,7 +1947,7 @@ void exit_mmap(struct mm_struct *mm) do { if (vma->vm_flags & VM_ACCOUNT) nr_accounted += vma_pages(vma); - remove_vma(vma, /* unreachable = */ true, /* closed = */ false); + remove_vma(vma, /* unreachable = */ true); count++; cond_resched(); vma = vma_next(&vmi); diff --git a/mm/mprotect.c b/mm/mprotect.c index 0c5d6d06107d..6f450af3252e 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -810,7 +810,7 @@ static int do_mprotect_pkey(unsigned long start, size_t len, break; } - if (map_deny_write_exec(vma, newflags)) { + if (map_deny_write_exec(vma->vm_flags, newflags)) { error = -EACCES; break; } diff --git a/mm/nommu.c b/mm/nommu.c index 385b0c15add8..e9b5f527ab5b 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -589,8 +589,7 @@ static int delete_vma_from_mm(struct vm_area_struct *vma) */ static void delete_vma(struct mm_struct *mm, struct vm_area_struct *vma) { - if (vma->vm_ops && vma->vm_ops->close) - vma->vm_ops->close(vma); + vma_close(vma); if (vma->vm_file) fput(vma->vm_file); put_nommu_region(vma->vm_region); @@ -843,7 +842,7 @@ static unsigned long determine_vm_flags(struct file *file, { unsigned long vm_flags; - vm_flags = calc_vm_prot_bits(prot, 0) | calc_vm_flag_bits(flags); + vm_flags = calc_vm_prot_bits(prot, 0) | calc_vm_flag_bits(file, flags); if (!file) { /* @@ -885,7 +884,7 @@ static int do_mmap_shared_file(struct vm_area_struct *vma) { int ret; - ret = call_mmap(vma->vm_file, vma); + ret = mmap_file(vma->vm_file, vma); if (ret == 0) { vma->vm_region->vm_top = vma->vm_region->vm_end; return 0; @@ -918,7 +917,7 @@ static int do_mmap_private(struct vm_area_struct *vma, * happy. */ if (capabilities & NOMMU_MAP_DIRECT) { - ret = call_mmap(vma->vm_file, vma); + ret = mmap_file(vma->vm_file, vma); /* shouldn't return success if we're not sharing */ if (WARN_ON_ONCE(!is_nommu_shared_mapping(vma->vm_flags))) ret = -ENOSYS; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 8cfc3600718a..ba160c4998d1 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -635,6 +635,8 @@ compaction_capture(struct capture_control *capc, struct page *page, static inline void account_freepages(struct zone *zone, int nr_pages, int migratetype) { + lockdep_assert_held(&zone->lock); + if (is_migrate_isolate(migratetype)) return; @@ -642,6 +644,9 @@ static inline void account_freepages(struct zone *zone, int nr_pages, if (is_migrate_cma(migratetype)) __mod_zone_page_state(zone, NR_FREE_CMA_PAGES, nr_pages); + else if (is_migrate_highatomic(migratetype)) + WRITE_ONCE(zone->nr_free_highatomic, + zone->nr_free_highatomic + nr_pages); } /* Used for pages not on another list */ @@ -961,9 +966,8 @@ static int free_tail_page_prepare(struct page *head_page, struct page *page) break; case 2: /* the second tail page: deferred_list overlaps ->mapping */ - if (unlikely(!list_empty(&folio->_deferred_list) && - folio_test_partially_mapped(folio))) { - bad_page(page, "partially mapped folio on deferred list"); + if (unlikely(!list_empty(&folio->_deferred_list))) { + bad_page(page, "on deferred list"); goto out; } break; @@ -2682,7 +2686,6 @@ void free_unref_folios(struct folio_batch *folios) unsigned long pfn = folio_pfn(folio); unsigned int order = folio_order(folio); - folio_undo_large_rmappable(folio); if (!free_pages_prepare(&folio->page, order)) continue; /* @@ -3081,11 +3084,10 @@ static inline long __zone_watermark_unusable_free(struct zone *z, /* * If the caller does not have rights to reserves below the min - * watermark then subtract the high-atomic reserves. This will - * over-estimate the size of the atomic reserve but it avoids a search. + * watermark then subtract the free pages reserved for highatomic. */ if (likely(!(alloc_flags & ALLOC_RESERVES))) - unusable_free += z->nr_reserved_highatomic; + unusable_free += READ_ONCE(z->nr_free_highatomic); #ifdef CONFIG_CMA /* If allocation can't use CMA areas don't use free CMA pages */ diff --git a/mm/shmem.c b/mm/shmem.c index 4ba1d00fabda..e87f5d6799a7 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2733,9 +2733,6 @@ static int shmem_mmap(struct file *file, struct vm_area_struct *vma) if (ret) return ret; - /* arm64 - allow memory tagging on RAM-based files */ - vm_flags_set(vma, VM_MTE_ALLOWED); - file_accessed(file); /* This is anonymous shared memory if it is unlinked at the time of mmap */ if (inode->i_nlink) diff --git a/mm/swap.c b/mm/swap.c index a8a117b2dd44..d8547af540eb 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -121,7 +121,7 @@ void __folio_put(struct folio *folio) } page_cache_release(folio); - folio_undo_large_rmappable(folio); + folio_unqueue_deferred_split(folio); mem_cgroup_uncharge(folio); free_unref_page(&folio->page, folio_order(folio)); } @@ -996,7 +996,7 @@ void folios_put_refs(struct folio_batch *folios, unsigned int *refs) free_huge_folio(folio); continue; } - folio_undo_large_rmappable(folio); + folio_unqueue_deferred_split(folio); __page_cache_release(folio, &lruvec, &flags); if (j != i) diff --git a/mm/vma.c b/mm/vma.c index b21ffec33f8e..7621384d64cf 100644 --- a/mm/vma.c +++ b/mm/vma.c @@ -323,11 +323,10 @@ static bool can_vma_merge_right(struct vma_merge_struct *vmg, /* * Close a vm structure and free it. */ -void remove_vma(struct vm_area_struct *vma, bool unreachable, bool closed) +void remove_vma(struct vm_area_struct *vma, bool unreachable) { might_sleep(); - if (!closed && vma->vm_ops && vma->vm_ops->close) - vma->vm_ops->close(vma); + vma_close(vma); if (vma->vm_file) fput(vma->vm_file); mpol_put(vma_policy(vma)); @@ -1115,9 +1114,7 @@ void vms_clean_up_area(struct vma_munmap_struct *vms, vms_clear_ptes(vms, mas_detach, true); mas_set(mas_detach, 0); mas_for_each(mas_detach, vma, ULONG_MAX) - if (vma->vm_ops && vma->vm_ops->close) - vma->vm_ops->close(vma); - vms->closed_vm_ops = true; + vma_close(vma); } /* @@ -1160,7 +1157,7 @@ void vms_complete_munmap_vmas(struct vma_munmap_struct *vms, /* Remove and clean up vmas */ mas_set(mas_detach, 0); mas_for_each(mas_detach, vma, ULONG_MAX) - remove_vma(vma, /* = */ false, vms->closed_vm_ops); + remove_vma(vma, /* unreachable = */ false); vm_unacct_memory(vms->nr_accounted); validate_mm(mm); @@ -1684,8 +1681,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, return new_vma; out_vma_link: - if (new_vma->vm_ops && new_vma->vm_ops->close) - new_vma->vm_ops->close(new_vma); + vma_close(new_vma); if (new_vma->vm_file) fput(new_vma->vm_file); diff --git a/mm/vma.h b/mm/vma.h index 55457cb68200..d58068c0ff2e 100644 --- a/mm/vma.h +++ b/mm/vma.h @@ -42,8 +42,7 @@ struct vma_munmap_struct { int vma_count; /* Number of vmas that will be removed */ bool unlock; /* Unlock after the munmap */ bool clear_ptes; /* If there are outstanding PTE to be cleared */ - bool closed_vm_ops; /* call_mmap() was encountered, so vmas may be closed */ - /* 1 byte hole */ + /* 2 byte hole */ unsigned long nr_pages; /* Number of pages being removed */ unsigned long locked_vm; /* Number of locked pages */ unsigned long nr_accounted; /* Number of VM_ACCOUNT pages */ @@ -198,7 +197,6 @@ static inline void init_vma_munmap(struct vma_munmap_struct *vms, vms->unmap_start = FIRST_USER_ADDRESS; vms->unmap_end = USER_PGTABLES_CEILING; vms->clear_ptes = false; - vms->closed_vm_ops = false; } #endif @@ -269,7 +267,7 @@ int do_vmi_munmap(struct vma_iterator *vmi, struct mm_struct *mm, unsigned long start, size_t len, struct list_head *uf, bool unlock); -void remove_vma(struct vm_area_struct *vma, bool unreachable, bool closed); +void remove_vma(struct vm_area_struct *vma, bool unreachable); void unmap_region(struct ma_state *mas, struct vm_area_struct *vma, struct vm_area_struct *prev, struct vm_area_struct *next); diff --git a/mm/vmscan.c b/mm/vmscan.c index a51720d885bf..4c9b043ffae8 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1479,7 +1479,7 @@ free_it: */ nr_reclaimed += nr_pages; - folio_undo_large_rmappable(folio); + folio_unqueue_deferred_split(folio); if (folio_batch_add(&free_folios, folio) == 0) { mem_cgroup_uncharge_folios(&free_folios); try_to_unmap_flush(); @@ -1867,7 +1867,7 @@ static unsigned int move_folios_to_lru(struct lruvec *lruvec, if (unlikely(folio_put_testzero(folio))) { __folio_clear_lru_flags(folio); - folio_undo_large_rmappable(folio); + folio_unqueue_deferred_split(folio); if (folio_batch_add(&free_folios, folio) == 0) { spin_unlock_irq(&lruvec->lru_lock); mem_cgroup_uncharge_folios(&free_folios); diff --git a/tools/testing/selftests/mm/hugetlb_dio.c b/tools/testing/selftests/mm/hugetlb_dio.c index f9ac20c657ec..60001c142ce9 100644 --- a/tools/testing/selftests/mm/hugetlb_dio.c +++ b/tools/testing/selftests/mm/hugetlb_dio.c @@ -44,13 +44,6 @@ void run_dio_using_hugetlb(unsigned int start_off, unsigned int end_off) if (fd < 0) ksft_exit_fail_perror("Error opening file\n"); - /* Get the free huge pages before allocation */ - free_hpage_b = get_free_hugepages(); - if (free_hpage_b == 0) { - close(fd); - ksft_exit_skip("No free hugepage, exiting!\n"); - } - /* Allocate a hugetlb page */ orig_buffer = mmap(NULL, h_pagesize, mmap_prot, mmap_flags, -1, 0); if (orig_buffer == MAP_FAILED) { @@ -94,8 +87,20 @@ void run_dio_using_hugetlb(unsigned int start_off, unsigned int end_off) int main(void) { size_t pagesize = 0; + int fd; ksft_print_header(); + + /* Open the file to DIO */ + fd = open("/tmp", O_TMPFILE | O_RDWR | O_DIRECT, 0664); + if (fd < 0) + ksft_exit_skip("Unable to allocate file: %s\n", strerror(errno)); + close(fd); + + /* Check if huge pages are free */ + if (!get_free_hugepages()) + ksft_exit_skip("No free hugepage, exiting\n"); + ksft_set_plan(4); /* Get base page size */