diff options
67 files changed, 606 insertions, 313 deletions
diff --git a/Documentation/devicetree/bindings/Makefile b/Documentation/devicetree/bindings/Makefile index 6b0dfd5c17ba..5138a2f6232a 100644 --- a/Documentation/devicetree/bindings/Makefile +++ b/Documentation/devicetree/bindings/Makefile @@ -19,7 +19,9 @@ quiet_cmd_mk_schema = SCHEMA $@ DT_DOCS = $(shell \ cd $(srctree)/$(src) && \ - find * \( -name '*.yaml' ! -name $(DT_TMP_SCHEMA) \) \ + find * \( -name '*.yaml' ! \ + -name $(DT_TMP_SCHEMA) ! \ + -name '*.example.dt.yaml' \) \ ) DT_SCHEMA_FILES ?= $(addprefix $(src)/,$(DT_DOCS)) diff --git a/Documentation/devicetree/bindings/net/fsl-fec.txt b/Documentation/devicetree/bindings/net/fsl-fec.txt index 2d41fb96ce0a..5b88fae0307d 100644 --- a/Documentation/devicetree/bindings/net/fsl-fec.txt +++ b/Documentation/devicetree/bindings/net/fsl-fec.txt @@ -7,18 +7,6 @@ Required properties: - phy-mode : See ethernet.txt file in the same directory Optional properties: -- phy-reset-gpios : Should specify the gpio for phy reset -- phy-reset-duration : Reset duration in milliseconds. Should present - only if property "phy-reset-gpios" is available. Missing the property - will have the duration be 1 millisecond. Numbers greater than 1000 are - invalid and 1 millisecond will be used instead. -- phy-reset-active-high : If present then the reset sequence using the GPIO - specified in the "phy-reset-gpios" property is reversed (H=reset state, - L=operation state). -- phy-reset-post-delay : Post reset delay in milliseconds. If present then - a delay of phy-reset-post-delay milliseconds will be observed after the - phy-reset-gpios has been toggled. Can be omitted thus no delay is - observed. Delay is in range of 1ms to 1000ms. Other delays are invalid. - phy-supply : regulator that powers the Ethernet PHY. - phy-handle : phandle to the PHY device connected to this device. - fixed-link : Assume a fixed link. See fixed-link.txt in the same directory. @@ -47,11 +35,27 @@ Optional properties: For imx6sx, "int0" handles all 3 queues and ENET_MII. "pps" is for the pulse per second interrupt associated with 1588 precision time protocol(PTP). - Optional subnodes: - mdio : specifies the mdio bus in the FEC, used as a container for phy nodes according to phy.txt in the same directory +Deprecated optional properties: + To avoid these, create a phy node according to phy.txt in the same + directory, and point the fec's "phy-handle" property to it. Then use + the phy's reset binding, again described by phy.txt. +- phy-reset-gpios : Should specify the gpio for phy reset +- phy-reset-duration : Reset duration in milliseconds. Should present + only if property "phy-reset-gpios" is available. Missing the property + will have the duration be 1 millisecond. Numbers greater than 1000 are + invalid and 1 millisecond will be used instead. +- phy-reset-active-high : If present then the reset sequence using the GPIO + specified in the "phy-reset-gpios" property is reversed (H=reset state, + L=operation state). +- phy-reset-post-delay : Post reset delay in milliseconds. If present then + a delay of phy-reset-post-delay milliseconds will be observed after the + phy-reset-gpios has been toggled. Can be omitted thus no delay is + observed. Delay is in range of 1ms to 1000ms. Other delays are invalid. + Example: ethernet@83fec000 { diff --git a/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.yaml index 91d3e78b3395..400df2da018a 100644 --- a/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.yaml @@ -37,7 +37,8 @@ properties: hwlocks: true st,syscfg: - $ref: "/schemas/types.yaml#/definitions/phandle-array" + allOf: + - $ref: "/schemas/types.yaml#/definitions/phandle-array" description: Should be phandle/offset/mask items: - description: Phandle to the syscon node which includes IRQ mux selection. diff --git a/MAINTAINERS b/MAINTAINERS index e81e60bd7c26..997a4f8fe88e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8415,7 +8415,6 @@ L: [email protected] T: git git://git.kernel.org/pub/scm/fs/xfs/xfs-linux.git S: Supported -F: fs/iomap.c F: fs/iomap/ F: include/linux/iomap.h diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 6774b03aa405..d42557ee69c2 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -2405,9 +2405,7 @@ long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr, pgprot_t arch_dma_mmap_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs) { - if (!dev_is_dma_coherent(dev)) - return __get_dma_pgprot(attrs, prot); - return prot; + return __get_dma_pgprot(attrs, prot); } void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 1d3f0b5a9940..bd2b039f43a6 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -14,9 +14,7 @@ pgprot_t arch_dma_mmap_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs) { - if (!dev_is_dma_coherent(dev) || (attrs & DMA_ATTR_WRITE_COMBINE)) - return pgprot_writecombine(prot); - return prot; + return pgprot_writecombine(prot); } void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr, diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 77f6ebf97113..d8dcd8820369 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -121,7 +121,6 @@ config PPC select ARCH_32BIT_OFF_T if PPC32 select ARCH_HAS_DEBUG_VIRTUAL select ARCH_HAS_DEVMEM_IS_ALLOWED - select ARCH_HAS_DMA_MMAP_PGPROT select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index ea0c69236789..56dfa7a2a6f2 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -49,8 +49,7 @@ obj-y := cputable.o ptrace.o syscalls.o \ signal.o sysfs.o cacheinfo.o time.o \ prom.o traps.o setup-common.o \ udbg.o misc.o io.o misc_$(BITS).o \ - of_platform.o prom_parse.o \ - dma-common.o + of_platform.o prom_parse.o obj-$(CONFIG_PPC64) += setup_64.o sys_ppc32.o \ signal_64.o ptrace32.o \ paca.o nvram_64.o firmware.o diff --git a/arch/powerpc/kernel/dma-common.c b/arch/powerpc/kernel/dma-common.c deleted file mode 100644 index dc7ef6b17b69..000000000000 --- a/arch/powerpc/kernel/dma-common.c +++ /dev/null @@ -1,17 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Contains common dma routines for all powerpc platforms. - * - * Copyright (C) 2019 Shawn Anastasio. - */ - -#include <linux/mm.h> -#include <linux/dma-noncoherent.h> - -pgprot_t arch_dma_mmap_pgprot(struct device *dev, pgprot_t prot, - unsigned long attrs) -{ - if (!dev_is_dma_coherent(dev)) - return pgprot_noncached(prot); - return prot; -} diff --git a/arch/sh/kernel/disassemble.c b/arch/sh/kernel/disassemble.c index defebf1a9c8a..845543780cc5 100644 --- a/arch/sh/kernel/disassemble.c +++ b/arch/sh/kernel/disassemble.c @@ -475,8 +475,6 @@ static void print_sh_insn(u32 memaddr, u16 insn) printk("dbr"); break; case FD_REG_N: - if (0) - goto d_reg_n; case F_REG_N: printk("fr%d", rn); break; @@ -488,7 +486,7 @@ static void print_sh_insn(u32 memaddr, u16 insn) printk("xd%d", rn & ~1); break; } - d_reg_n: + /* else, fall through */ case D_REG_N: printk("dr%d", rn); break; @@ -497,6 +495,7 @@ static void print_sh_insn(u32 memaddr, u16 insn) printk("xd%d", rm & ~1); break; } + /* else, fall through */ case D_REG_M: printk("dr%d", rm); break; diff --git a/arch/sh/kernel/hw_breakpoint.c b/arch/sh/kernel/hw_breakpoint.c index 3bd010b4c55f..f10d64311127 100644 --- a/arch/sh/kernel/hw_breakpoint.c +++ b/arch/sh/kernel/hw_breakpoint.c @@ -157,6 +157,7 @@ int arch_bp_generic_fields(int sh_len, int sh_type, switch (sh_type) { case SH_BREAKPOINT_READ: *gen_type = HW_BREAKPOINT_R; + break; case SH_BREAKPOINT_WRITE: *gen_type = HW_BREAKPOINT_W; break; diff --git a/drivers/auxdisplay/Kconfig b/drivers/auxdisplay/Kconfig index dd61fdd400f0..68489d1f00bb 100644 --- a/drivers/auxdisplay/Kconfig +++ b/drivers/auxdisplay/Kconfig @@ -448,6 +448,11 @@ config PANEL_BOOT_MESSAGE choice prompt "Backlight initial state" default CHARLCD_BL_FLASH + ---help--- + Select the initial backlight state on boot or module load. + + Previously, there was no option for this: the backlight flashed + briefly on init. Now you can also turn it off/on. config CHARLCD_BL_OFF bool "Off" diff --git a/drivers/auxdisplay/charlcd.c b/drivers/auxdisplay/charlcd.c index 92745efefb54..bef6b85778b6 100644 --- a/drivers/auxdisplay/charlcd.c +++ b/drivers/auxdisplay/charlcd.c @@ -20,7 +20,7 @@ #include <generated/utsrelease.h> -#include <misc/charlcd.h> +#include "charlcd.h" #define LCD_MINOR 156 diff --git a/include/misc/charlcd.h b/drivers/auxdisplay/charlcd.h index 8cf6c18b0adb..00911ad0f3de 100644 --- a/include/misc/charlcd.h +++ b/drivers/auxdisplay/charlcd.h @@ -6,6 +6,9 @@ * Copyright (C) 2016-2017 Glider bvba */ +#ifndef _CHARLCD_H +#define _CHARLCD_H + struct charlcd { const struct charlcd_ops *ops; const unsigned char *char_conv; /* Optional */ @@ -37,3 +40,5 @@ int charlcd_register(struct charlcd *lcd); int charlcd_unregister(struct charlcd *lcd); void charlcd_poke(struct charlcd *lcd); + +#endif /* CHARLCD_H */ diff --git a/drivers/auxdisplay/hd44780.c b/drivers/auxdisplay/hd44780.c index ab15b64707ad..bcbe13092327 100644 --- a/drivers/auxdisplay/hd44780.c +++ b/drivers/auxdisplay/hd44780.c @@ -14,8 +14,7 @@ #include <linux/property.h> #include <linux/slab.h> -#include <misc/charlcd.h> - +#include "charlcd.h" enum hd44780_pin { /* Order does matter due to writing to GPIO array subsets! */ diff --git a/drivers/auxdisplay/panel.c b/drivers/auxdisplay/panel.c index e06de63497cf..85965953683e 100644 --- a/drivers/auxdisplay/panel.c +++ b/drivers/auxdisplay/panel.c @@ -55,7 +55,7 @@ #include <linux/io.h> #include <linux/uaccess.h> -#include <misc/charlcd.h> +#include "charlcd.h" #define KEYPAD_MINOR 185 @@ -1617,6 +1617,8 @@ static void panel_attach(struct parport *port) return; err_lcd_unreg: + if (scan_timer.function) + del_timer_sync(&scan_timer); if (lcd.enabled) charlcd_unregister(lcd.charlcd); err_unreg_device: diff --git a/drivers/infiniband/core/counters.c b/drivers/infiniband/core/counters.c index 45d5164e9574..b79890739a2c 100644 --- a/drivers/infiniband/core/counters.c +++ b/drivers/infiniband/core/counters.c @@ -38,6 +38,9 @@ int rdma_counter_set_auto_mode(struct ib_device *dev, u8 port, int ret; port_counter = &dev->port_data[port].port_counter; + if (!port_counter->hstats) + return -EOPNOTSUPP; + mutex_lock(&port_counter->lock); if (on) { ret = __counter_set_mode(&port_counter->mode, @@ -509,6 +512,9 @@ int rdma_counter_bind_qpn_alloc(struct ib_device *dev, u8 port, if (!rdma_is_port_valid(dev, port)) return -EINVAL; + if (!dev->port_data[port].port_counter.hstats) + return -EOPNOTSUPP; + qp = rdma_counter_get_qp(dev, qp_num); if (!qp) return -ENOENT; diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c index 783e465e7c41..87d40d1ecdde 100644 --- a/drivers/infiniband/core/nldev.c +++ b/drivers/infiniband/core/nldev.c @@ -1952,12 +1952,16 @@ static int stat_get_doit_qp(struct sk_buff *skb, struct nlmsghdr *nlh, if (fill_nldev_handle(msg, device) || nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, port) || - nla_put_u32(msg, RDMA_NLDEV_ATTR_STAT_MODE, mode)) + nla_put_u32(msg, RDMA_NLDEV_ATTR_STAT_MODE, mode)) { + ret = -EMSGSIZE; goto err_msg; + } if ((mode == RDMA_COUNTER_MODE_AUTO) && - nla_put_u32(msg, RDMA_NLDEV_ATTR_STAT_AUTO_MODE_MASK, mask)) + nla_put_u32(msg, RDMA_NLDEV_ATTR_STAT_AUTO_MODE_MASK, mask)) { + ret = -EMSGSIZE; goto err_msg; + } nlmsg_end(msg, nlh); ib_device_put(device); diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c index 2a75c6f8d827..c0e15db34680 100644 --- a/drivers/infiniband/core/umem_odp.c +++ b/drivers/infiniband/core/umem_odp.c @@ -112,10 +112,6 @@ static int ib_umem_notifier_release_trampoline(struct ib_umem_odp *umem_odp, * prevent any further fault handling on this MR. */ ib_umem_notifier_start_account(umem_odp); - umem_odp->dying = 1; - /* Make sure that the fact the umem is dying is out before we release - * all pending page faults. */ - smp_wmb(); complete_all(&umem_odp->notifier_completion); umem_odp->umem.context->invalidate_range( umem_odp, ib_umem_start(umem_odp), ib_umem_end(umem_odp)); diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c index ec4370f99381..af5bbb35c058 100644 --- a/drivers/infiniband/hw/mlx5/devx.c +++ b/drivers/infiniband/hw/mlx5/devx.c @@ -2026,7 +2026,7 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_SUBSCRIBE_EVENT)( event_sub->eventfd = eventfd_ctx_fdget(redirect_fd); - if (IS_ERR(event_sub)) { + if (IS_ERR(event_sub->eventfd)) { err = PTR_ERR(event_sub->eventfd); event_sub->eventfd = NULL; goto err; @@ -2644,12 +2644,13 @@ static int devx_async_event_close(struct inode *inode, struct file *filp) struct devx_async_event_file *ev_file = filp->private_data; struct devx_event_subscription *event_sub, *event_sub_tmp; struct devx_async_event_data *entry, *tmp; + struct mlx5_ib_dev *dev = ev_file->dev; - mutex_lock(&ev_file->dev->devx_event_table.event_xa_lock); + mutex_lock(&dev->devx_event_table.event_xa_lock); /* delete the subscriptions which are related to this FD */ list_for_each_entry_safe(event_sub, event_sub_tmp, &ev_file->subscribed_events_list, file_list) { - devx_cleanup_subscription(ev_file->dev, event_sub); + devx_cleanup_subscription(dev, event_sub); if (event_sub->eventfd) eventfd_ctx_put(event_sub->eventfd); @@ -2658,7 +2659,7 @@ static int devx_async_event_close(struct inode *inode, struct file *filp) kfree_rcu(event_sub, rcu); } - mutex_unlock(&ev_file->dev->devx_event_table.event_xa_lock); + mutex_unlock(&dev->devx_event_table.event_xa_lock); /* free the pending events allocation */ if (!ev_file->omit_data) { @@ -2670,7 +2671,7 @@ static int devx_async_event_close(struct inode *inode, struct file *filp) } uverbs_close_fd(filp); - put_device(&ev_file->dev->ib_dev.dev); + put_device(&dev->ib_dev.dev); return 0; } diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index 81da82050d05..1d257d1b3b0d 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -579,7 +579,6 @@ static int pagefault_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr, u32 flags) { int npages = 0, current_seq, page_shift, ret, np; - bool implicit = false; struct ib_umem_odp *odp_mr = to_ib_umem_odp(mr->umem); bool downgrade = flags & MLX5_PF_FLAGS_DOWNGRADE; bool prefetch = flags & MLX5_PF_FLAGS_PREFETCH; @@ -594,7 +593,6 @@ static int pagefault_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr, if (IS_ERR(odp)) return PTR_ERR(odp); mr = odp->private; - implicit = true; } else { odp = odp_mr; } @@ -682,19 +680,15 @@ next_mr: out: if (ret == -EAGAIN) { - if (implicit || !odp->dying) { - unsigned long timeout = - msecs_to_jiffies(MMU_NOTIFIER_TIMEOUT); - - if (!wait_for_completion_timeout( - &odp->notifier_completion, - timeout)) { - mlx5_ib_warn(dev, "timeout waiting for mmu notifier. seq %d against %d. notifiers_count=%d\n", - current_seq, odp->notifiers_seq, odp->notifiers_count); - } - } else { - /* The MR is being killed, kill the QP as well. */ - ret = -EFAULT; + unsigned long timeout = msecs_to_jiffies(MMU_NOTIFIER_TIMEOUT); + + if (!wait_for_completion_timeout(&odp->notifier_completion, + timeout)) { + mlx5_ib_warn( + dev, + "timeout waiting for mmu notifier. seq %d against %d. notifiers_count=%d\n", + current_seq, odp->notifiers_seq, + odp->notifiers_count); } } diff --git a/drivers/infiniband/sw/siw/Kconfig b/drivers/infiniband/sw/siw/Kconfig index dace276aea14..b622fc62f2cd 100644 --- a/drivers/infiniband/sw/siw/Kconfig +++ b/drivers/infiniband/sw/siw/Kconfig @@ -1,6 +1,6 @@ config RDMA_SIW tristate "Software RDMA over TCP/IP (iWARP) driver" - depends on INET && INFINIBAND && LIBCRC32C && 64BIT + depends on INET && INFINIBAND && LIBCRC32C select DMA_VIRT_OPS help This driver implements the iWARP RDMA transport over diff --git a/drivers/infiniband/sw/siw/siw.h b/drivers/infiniband/sw/siw/siw.h index 03fd7b2f595f..77b1aabf6ff3 100644 --- a/drivers/infiniband/sw/siw/siw.h +++ b/drivers/infiniband/sw/siw/siw.h @@ -214,7 +214,7 @@ struct siw_wqe { struct siw_cq { struct ib_cq base_cq; spinlock_t lock; - u64 *notify; + struct siw_cq_ctrl *notify; struct siw_cqe *queue; u32 cq_put; u32 cq_get; diff --git a/drivers/infiniband/sw/siw/siw_main.c b/drivers/infiniband/sw/siw/siw_main.c index d0f140daf659..05a92f997f60 100644 --- a/drivers/infiniband/sw/siw/siw_main.c +++ b/drivers/infiniband/sw/siw/siw_main.c @@ -160,10 +160,8 @@ static int siw_init_cpulist(void) out_err: siw_cpu_info.num_nodes = 0; - while (i) { + while (--i >= 0) kfree(siw_cpu_info.tx_valid_cpus[i]); - siw_cpu_info.tx_valid_cpus[i--] = NULL; - } kfree(siw_cpu_info.tx_valid_cpus); siw_cpu_info.tx_valid_cpus = NULL; diff --git a/drivers/infiniband/sw/siw/siw_qp.c b/drivers/infiniband/sw/siw/siw_qp.c index e27bd5b35b96..0990307c5d2c 100644 --- a/drivers/infiniband/sw/siw/siw_qp.c +++ b/drivers/infiniband/sw/siw/siw_qp.c @@ -1013,18 +1013,24 @@ out: */ static bool siw_cq_notify_now(struct siw_cq *cq, u32 flags) { - u64 cq_notify; + u32 cq_notify; if (!cq->base_cq.comp_handler) return false; - cq_notify = READ_ONCE(*cq->notify); + /* Read application shared notification state */ + cq_notify = READ_ONCE(cq->notify->flags); if ((cq_notify & SIW_NOTIFY_NEXT_COMPLETION) || ((cq_notify & SIW_NOTIFY_SOLICITED) && (flags & SIW_WQE_SOLICITED))) { - /* dis-arm CQ */ - smp_store_mb(*cq->notify, SIW_NOTIFY_NOT); + /* + * CQ notification is one-shot: Since the + * current CQE causes user notification, + * the CQ gets dis-aremd and must be re-aremd + * by the user for a new notification. + */ + WRITE_ONCE(cq->notify->flags, SIW_NOTIFY_NOT); return true; } diff --git a/drivers/infiniband/sw/siw/siw_verbs.c b/drivers/infiniband/sw/siw/siw_verbs.c index 32dc79d0e898..e7f3a2379d9d 100644 --- a/drivers/infiniband/sw/siw/siw_verbs.c +++ b/drivers/infiniband/sw/siw/siw_verbs.c @@ -1049,7 +1049,7 @@ int siw_create_cq(struct ib_cq *base_cq, const struct ib_cq_init_attr *attr, spin_lock_init(&cq->lock); - cq->notify = &((struct siw_cq_ctrl *)&cq->queue[size])->notify; + cq->notify = (struct siw_cq_ctrl *)&cq->queue[size]; if (udata) { struct siw_uresp_create_cq uresp = {}; @@ -1141,11 +1141,17 @@ int siw_req_notify_cq(struct ib_cq *base_cq, enum ib_cq_notify_flags flags) siw_dbg_cq(cq, "flags: 0x%02x\n", flags); if ((flags & IB_CQ_SOLICITED_MASK) == IB_CQ_SOLICITED) - /* CQ event for next solicited completion */ - smp_store_mb(*cq->notify, SIW_NOTIFY_SOLICITED); + /* + * Enable CQ event for next solicited completion. + * and make it visible to all associated producers. + */ + smp_store_mb(cq->notify->flags, SIW_NOTIFY_SOLICITED); else - /* CQ event for any signalled completion */ - smp_store_mb(*cq->notify, SIW_NOTIFY_ALL); + /* + * Enable CQ event for any signalled completion. + * and make it visible to all associated producers. + */ + smp_store_mb(cq->notify->flags, SIW_NOTIFY_ALL); if (flags & IB_CQ_REPORT_MISSED_EVENTS) return cq->cq_put - cq->cq_get; diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index a9a9fabd3968..c5c93e48b4db 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -1186,8 +1186,8 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid, ste_live = true; break; case STRTAB_STE_0_CFG_ABORT: - if (disable_bypass) - break; + BUG_ON(!disable_bypass); + break; default: BUG(); /* STE corruption */ } diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index a7f9c3edbcb2..d991d40f797f 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -459,13 +459,11 @@ static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys, { struct iommu_domain *domain = iommu_get_dma_domain(dev); struct iommu_dma_cookie *cookie = domain->iova_cookie; - size_t iova_off = 0; + struct iova_domain *iovad = &cookie->iovad; + size_t iova_off = iova_offset(iovad, phys); dma_addr_t iova; - if (cookie->type == IOMMU_DMA_IOVA_COOKIE) { - iova_off = iova_offset(&cookie->iovad, phys); - size = iova_align(&cookie->iovad, size + iova_off); - } + size = iova_align(iovad, size + iova_off); iova = iommu_dma_alloc_iova(domain, size, dma_get_mask(dev), dev); if (!iova) @@ -574,7 +572,7 @@ static void *iommu_dma_alloc_remap(struct device *dev, size_t size, struct iova_domain *iovad = &cookie->iovad; bool coherent = dev_is_dma_coherent(dev); int ioprot = dma_info_to_prot(DMA_BIDIRECTIONAL, coherent, attrs); - pgprot_t prot = arch_dma_mmap_pgprot(dev, PAGE_KERNEL, attrs); + pgprot_t prot = dma_pgprot(dev, PAGE_KERNEL, attrs); unsigned int count, min_size, alloc_sizes = domain->pgsize_bitmap; struct page **pages; struct sg_table sgt; @@ -764,7 +762,7 @@ static int __finalise_sg(struct device *dev, struct scatterlist *sg, int nents, * - and wouldn't make the resulting output segment too long */ if (cur_len && !s_iova_off && (dma_addr & seg_mask) && - (cur_len + s_length <= max_len)) { + (max_len - cur_len >= s_length)) { /* ...then concatenate it with the previous one */ cur_len += s_length; } else { @@ -975,7 +973,7 @@ static void *iommu_dma_alloc_pages(struct device *dev, size_t size, return NULL; if (IS_ENABLED(CONFIG_DMA_REMAP) && (!coherent || PageHighMem(page))) { - pgprot_t prot = arch_dma_mmap_pgprot(dev, PAGE_KERNEL, attrs); + pgprot_t prot = dma_pgprot(dev, PAGE_KERNEL, attrs); cpu_addr = dma_common_contiguous_remap(page, alloc_size, VM_USERMAP, prot, __builtin_return_address(0)); @@ -1035,7 +1033,7 @@ static int iommu_dma_mmap(struct device *dev, struct vm_area_struct *vma, unsigned long pfn, off = vma->vm_pgoff; int ret; - vma->vm_page_prot = arch_dma_mmap_pgprot(dev, vma->vm_page_prot, attrs); + vma->vm_page_prot = dma_pgprot(dev, vma->vm_page_prot, attrs); if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret)) return ret; @@ -1147,16 +1145,21 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev, if (!msi_page) return NULL; - iova = __iommu_dma_map(dev, msi_addr, size, prot); - if (iova == DMA_MAPPING_ERROR) + iova = iommu_dma_alloc_iova(domain, size, dma_get_mask(dev), dev); + if (!iova) goto out_free_page; + if (iommu_map(domain, iova, msi_addr, size, prot)) + goto out_free_iova; + INIT_LIST_HEAD(&msi_page->list); msi_page->phys = msi_addr; msi_page->iova = iova; list_add(&msi_page->list, &cookie->msi_page_list); return msi_page; +out_free_iova: + iommu_dma_free_iova(cookie, iova, size); out_free_page: kfree(msi_page); return NULL; diff --git a/drivers/iommu/intel-iommu-debugfs.c b/drivers/iommu/intel-iommu-debugfs.c index 2b25d9c59336..471f05d452e0 100644 --- a/drivers/iommu/intel-iommu-debugfs.c +++ b/drivers/iommu/intel-iommu-debugfs.c @@ -235,7 +235,7 @@ static void ctx_tbl_walk(struct seq_file *m, struct intel_iommu *iommu, u16 bus) tbl_wlk.ctx_entry = context; m->private = &tbl_wlk; - if (pasid_supported(iommu) && is_pasid_enabled(context)) { + if (dmar_readq(iommu->reg + DMAR_RTADDR_REG) & DMA_RTADDR_SMT) { pasid_dir_ptr = context->lo & VTD_PAGE_MASK; pasid_dir_size = get_pasid_dir_size(context); pasid_dir_walk(m, pasid_dir_ptr, pasid_dir_size); diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index bdaed2da8a55..12d094d08c0a 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -3449,6 +3449,7 @@ static bool iommu_need_mapping(struct device *dev) dmar_domain = to_dmar_domain(domain); dmar_domain->flags |= DOMAIN_FLAG_LOSE_CHILDREN; } + dmar_remove_one_dev_info(dev); get_private_domain_for_dev(dev); } @@ -4790,7 +4791,8 @@ static void __dmar_remove_one_dev_info(struct device_domain_info *info) /* free the private domain */ if (domain->flags & DOMAIN_FLAG_LOSE_CHILDREN && - !(domain->flags & DOMAIN_FLAG_STATIC_IDENTITY)) + !(domain->flags & DOMAIN_FLAG_STATIC_IDENTITY) && + list_empty(&domain->devices)) domain_exit(info->domain); free_devinfo_mem(info); @@ -4803,7 +4805,8 @@ static void dmar_remove_one_dev_info(struct device *dev) spin_lock_irqsave(&device_domain_lock, flags); info = dev->archdata.iommu; - __dmar_remove_one_dev_info(info); + if (info) + __dmar_remove_one_dev_info(info); spin_unlock_irqrestore(&device_domain_lock, flags); } @@ -5281,6 +5284,7 @@ static int intel_iommu_add_device(struct device *dev) if (device_def_domain_type(dev) == IOMMU_DOMAIN_IDENTITY) { ret = iommu_request_dm_for_dev(dev); if (ret) { + dmar_remove_one_dev_info(dev); dmar_domain->flags |= DOMAIN_FLAG_LOSE_CHILDREN; domain_add_dev_info(si_domain, dev); dev_info(dev, @@ -5291,6 +5295,7 @@ static int intel_iommu_add_device(struct device *dev) if (device_def_domain_type(dev) == IOMMU_DOMAIN_DMA) { ret = iommu_request_dma_domain_for_dev(dev); if (ret) { + dmar_remove_one_dev_info(dev); dmar_domain->flags |= DOMAIN_FLAG_LOSE_CHILDREN; if (!get_private_domain_for_dev(dev)) { dev_warn(dev, @@ -5316,6 +5321,8 @@ static void intel_iommu_remove_device(struct device *dev) if (!iommu) return; + dmar_remove_one_dev_info(dev); + iommu_group_remove_device(dev); iommu_device_unlink(&iommu->iommu, dev); diff --git a/drivers/of/irq.c b/drivers/of/irq.c index 7f84bb4903ca..a296eaf52a5b 100644 --- a/drivers/of/irq.c +++ b/drivers/of/irq.c @@ -277,7 +277,7 @@ EXPORT_SYMBOL_GPL(of_irq_parse_raw); * of_irq_parse_one - Resolve an interrupt for a device * @device: the device whose interrupt is to be resolved * @index: index of the interrupt to resolve - * @out_irq: structure of_irq filled by this function + * @out_irq: structure of_phandle_args filled by this function * * This function resolves an interrupt for a node by walking the interrupt tree, * finding which interrupt controller node it is attached to, and returning the diff --git a/drivers/of/resolver.c b/drivers/of/resolver.c index c1b67dd7cd6e..83c766233181 100644 --- a/drivers/of/resolver.c +++ b/drivers/of/resolver.c @@ -206,16 +206,22 @@ static int adjust_local_phandle_references(struct device_node *local_fixups, for_each_child_of_node(local_fixups, child) { for_each_child_of_node(overlay, overlay_child) - if (!node_name_cmp(child, overlay_child)) + if (!node_name_cmp(child, overlay_child)) { + of_node_put(overlay_child); break; + } - if (!overlay_child) + if (!overlay_child) { + of_node_put(child); return -EINVAL; + } err = adjust_local_phandle_references(child, overlay_child, phandle_delta); - if (err) + if (err) { + of_node_put(child); return err; + } } return 0; diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index faf43b1d3dbe..a7549ae32542 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -10776,12 +10776,31 @@ lpfc_cpu_affinity_check(struct lpfc_hba *phba, int vectors) /* This loop sets up all CPUs that are affinitized with a * irq vector assigned to the driver. All affinitized CPUs * will get a link to that vectors IRQ and EQ. + * + * NULL affinity mask handling: + * If irq count is greater than one, log an error message. + * If the null mask is received for the first irq, find the + * first present cpu, and assign the eq index to ensure at + * least one EQ is assigned. */ for (idx = 0; idx < phba->cfg_irq_chann; idx++) { /* Get a CPU mask for all CPUs affinitized to this vector */ maskp = pci_irq_get_affinity(phba->pcidev, idx); - if (!maskp) - continue; + if (!maskp) { + if (phba->cfg_irq_chann > 1) + lpfc_printf_log(phba, KERN_ERR, LOG_INIT, + "3329 No affinity mask found " + "for vector %d (%d)\n", + idx, phba->cfg_irq_chann); + if (!idx) { + cpu = cpumask_first(cpu_present_mask); + cpup = &phba->sli4_hba.cpu_map[cpu]; + cpup->eq = idx; + cpup->irq = pci_irq_vector(phba->pcidev, idx); + cpup->flag |= LPFC_CPU_FIRST_IRQ; + } + break; + } i = 0; /* Loop through all CPUs associated with vector idx */ diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c index 4f1b6f466ff5..b86195e4dc6c 100644 --- a/fs/afs/cmservice.c +++ b/fs/afs/cmservice.c @@ -505,18 +505,14 @@ static void SRXAFSCB_ProbeUuid(struct work_struct *work) struct afs_call *call = container_of(work, struct afs_call, work); struct afs_uuid *r = call->request; - struct { - __be32 match; - } reply; - _enter(""); if (memcmp(r, &call->net->uuid, sizeof(call->net->uuid)) == 0) - reply.match = htonl(0); + afs_send_empty_reply(call); else - reply.match = htonl(1); + rxrpc_kernel_abort_call(call->net->socket, call->rxcall, + 1, 1, "K-1"); - afs_send_simple_reply(call, &reply, sizeof(reply)); afs_put_call(call); _leave(""); } diff --git a/fs/afs/dir.c b/fs/afs/dir.c index e640d67274be..81207dc3c997 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -440,7 +440,7 @@ static int afs_dir_iterate_block(struct afs_vnode *dvnode, * iterate through the data blob that lists the contents of an AFS directory */ static int afs_dir_iterate(struct inode *dir, struct dir_context *ctx, - struct key *key) + struct key *key, afs_dataversion_t *_dir_version) { struct afs_vnode *dvnode = AFS_FS_I(dir); struct afs_xdr_dir_page *dbuf; @@ -460,6 +460,7 @@ static int afs_dir_iterate(struct inode *dir, struct dir_context *ctx, req = afs_read_dir(dvnode, key); if (IS_ERR(req)) return PTR_ERR(req); + *_dir_version = req->data_version; /* round the file position up to the next entry boundary */ ctx->pos += sizeof(union afs_xdr_dirent) - 1; @@ -514,7 +515,10 @@ out: */ static int afs_readdir(struct file *file, struct dir_context *ctx) { - return afs_dir_iterate(file_inode(file), ctx, afs_file_key(file)); + afs_dataversion_t dir_version; + + return afs_dir_iterate(file_inode(file), ctx, afs_file_key(file), + &dir_version); } /* @@ -555,7 +559,8 @@ static int afs_lookup_one_filldir(struct dir_context *ctx, const char *name, * - just returns the FID the dentry name maps to if found */ static int afs_do_lookup_one(struct inode *dir, struct dentry *dentry, - struct afs_fid *fid, struct key *key) + struct afs_fid *fid, struct key *key, + afs_dataversion_t *_dir_version) { struct afs_super_info *as = dir->i_sb->s_fs_info; struct afs_lookup_one_cookie cookie = { @@ -568,7 +573,7 @@ static int afs_do_lookup_one(struct inode *dir, struct dentry *dentry, _enter("{%lu},%p{%pd},", dir->i_ino, dentry, dentry); /* search the directory */ - ret = afs_dir_iterate(dir, &cookie.ctx, key); + ret = afs_dir_iterate(dir, &cookie.ctx, key, _dir_version); if (ret < 0) { _leave(" = %d [iter]", ret); return ret; @@ -642,6 +647,7 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry, struct afs_server *server; struct afs_vnode *dvnode = AFS_FS_I(dir), *vnode; struct inode *inode = NULL, *ti; + afs_dataversion_t data_version = READ_ONCE(dvnode->status.data_version); int ret, i; _enter("{%lu},%p{%pd},", dir->i_ino, dentry, dentry); @@ -669,12 +675,14 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry, cookie->fids[i].vid = as->volume->vid; /* search the directory */ - ret = afs_dir_iterate(dir, &cookie->ctx, key); + ret = afs_dir_iterate(dir, &cookie->ctx, key, &data_version); if (ret < 0) { inode = ERR_PTR(ret); goto out; } + dentry->d_fsdata = (void *)(unsigned long)data_version; + inode = ERR_PTR(-ENOENT); if (!cookie->found) goto out; @@ -968,7 +976,8 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) struct dentry *parent; struct inode *inode; struct key *key; - long dir_version, de_version; + afs_dataversion_t dir_version; + long de_version; int ret; if (flags & LOOKUP_RCU) @@ -1014,20 +1023,20 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) * on a 32-bit system, we only have 32 bits in the dentry to store the * version. */ - dir_version = (long)dir->status.data_version; + dir_version = dir->status.data_version; de_version = (long)dentry->d_fsdata; - if (de_version == dir_version) - goto out_valid; + if (de_version == (long)dir_version) + goto out_valid_noupdate; - dir_version = (long)dir->invalid_before; - if (de_version - dir_version >= 0) + dir_version = dir->invalid_before; + if (de_version - (long)dir_version >= 0) goto out_valid; _debug("dir modified"); afs_stat_v(dir, n_reval); /* search the directory for this vnode */ - ret = afs_do_lookup_one(&dir->vfs_inode, dentry, &fid, key); + ret = afs_do_lookup_one(&dir->vfs_inode, dentry, &fid, key, &dir_version); switch (ret) { case 0: /* the filename maps to something */ @@ -1080,7 +1089,8 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) } out_valid: - dentry->d_fsdata = (void *)dir_version; + dentry->d_fsdata = (void *)(unsigned long)dir_version; +out_valid_noupdate: dput(parent); key_put(key); _leave(" = 1 [valid]"); @@ -1186,6 +1196,20 @@ static void afs_prep_for_new_inode(struct afs_fs_cursor *fc, } /* + * Note that a dentry got changed. We need to set d_fsdata to the data version + * number derived from the result of the operation. It doesn't matter if + * d_fsdata goes backwards as we'll just revalidate. + */ +static void afs_update_dentry_version(struct afs_fs_cursor *fc, + struct dentry *dentry, + struct afs_status_cb *scb) +{ + if (fc->ac.error == 0) + dentry->d_fsdata = + (void *)(unsigned long)scb->status.data_version; +} + +/* * create a directory on an AFS filesystem */ static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) @@ -1227,6 +1251,7 @@ static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) afs_check_for_remote_deletion(&fc, dvnode); afs_vnode_commit_status(&fc, dvnode, fc.cb_break, &data_version, &scb[0]); + afs_update_dentry_version(&fc, dentry, &scb[0]); afs_vnode_new_inode(&fc, dentry, &iget_data, &scb[1]); ret = afs_end_vnode_operation(&fc); if (ret < 0) @@ -1319,6 +1344,7 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry) afs_vnode_commit_status(&fc, dvnode, fc.cb_break, &data_version, scb); + afs_update_dentry_version(&fc, dentry, scb); ret = afs_end_vnode_operation(&fc); if (ret == 0) { afs_dir_remove_subdir(dentry); @@ -1458,6 +1484,7 @@ static int afs_unlink(struct inode *dir, struct dentry *dentry) &data_version, &scb[0]); afs_vnode_commit_status(&fc, vnode, fc.cb_break_2, &data_version_2, &scb[1]); + afs_update_dentry_version(&fc, dentry, &scb[0]); ret = afs_end_vnode_operation(&fc); if (ret == 0 && !(scb[1].have_status || scb[1].have_error)) ret = afs_dir_remove_link(dvnode, dentry, key); @@ -1526,6 +1553,7 @@ static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode, afs_check_for_remote_deletion(&fc, dvnode); afs_vnode_commit_status(&fc, dvnode, fc.cb_break, &data_version, &scb[0]); + afs_update_dentry_version(&fc, dentry, &scb[0]); afs_vnode_new_inode(&fc, dentry, &iget_data, &scb[1]); ret = afs_end_vnode_operation(&fc); if (ret < 0) @@ -1607,6 +1635,7 @@ static int afs_link(struct dentry *from, struct inode *dir, afs_vnode_commit_status(&fc, vnode, fc.cb_break_2, NULL, &scb[1]); ihold(&vnode->vfs_inode); + afs_update_dentry_version(&fc, dentry, &scb[0]); d_instantiate(dentry, &vnode->vfs_inode); mutex_unlock(&vnode->io_lock); @@ -1686,6 +1715,7 @@ static int afs_symlink(struct inode *dir, struct dentry *dentry, afs_check_for_remote_deletion(&fc, dvnode); afs_vnode_commit_status(&fc, dvnode, fc.cb_break, &data_version, &scb[0]); + afs_update_dentry_version(&fc, dentry, &scb[0]); afs_vnode_new_inode(&fc, dentry, &iget_data, &scb[1]); ret = afs_end_vnode_operation(&fc); if (ret < 0) @@ -1791,6 +1821,17 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry, } } + /* This bit is potentially nasty as there's a potential race with + * afs_d_revalidate{,_rcu}(). We have to change d_fsdata on the dentry + * to reflect it's new parent's new data_version after the op, but + * d_revalidate may see old_dentry between the op having taken place + * and the version being updated. + * + * So drop the old_dentry for now to make other threads go through + * lookup instead - which we hold a lock against. + */ + d_drop(old_dentry); + ret = -ERESTARTSYS; if (afs_begin_vnode_operation(&fc, orig_dvnode, key, true)) { afs_dataversion_t orig_data_version; @@ -1802,9 +1843,9 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry, if (orig_dvnode != new_dvnode) { if (mutex_lock_interruptible_nested(&new_dvnode->io_lock, 1) < 0) { afs_end_vnode_operation(&fc); - goto error_rehash; + goto error_rehash_old; } - new_data_version = new_dvnode->status.data_version; + new_data_version = new_dvnode->status.data_version + 1; } else { new_data_version = orig_data_version; new_scb = &scb[0]; @@ -1827,7 +1868,7 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry, } ret = afs_end_vnode_operation(&fc); if (ret < 0) - goto error_rehash; + goto error_rehash_old; } if (ret == 0) { @@ -1853,10 +1894,26 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry, drop_nlink(new_inode); spin_unlock(&new_inode->i_lock); } + + /* Now we can update d_fsdata on the dentries to reflect their + * new parent's data_version. + * + * Note that if we ever implement RENAME_EXCHANGE, we'll have + * to update both dentries with opposing dir versions. + */ + if (new_dvnode != orig_dvnode) { + afs_update_dentry_version(&fc, old_dentry, &scb[1]); + afs_update_dentry_version(&fc, new_dentry, &scb[1]); + } else { + afs_update_dentry_version(&fc, old_dentry, &scb[0]); + afs_update_dentry_version(&fc, new_dentry, &scb[0]); + } d_move(old_dentry, new_dentry); goto error_tmp; } +error_rehash_old: + d_rehash(new_dentry); error_rehash: if (rehash) d_rehash(rehash); diff --git a/fs/afs/file.c b/fs/afs/file.c index 56b69576274d..dd3c55c9101c 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -191,11 +191,13 @@ void afs_put_read(struct afs_read *req) int i; if (refcount_dec_and_test(&req->usage)) { - for (i = 0; i < req->nr_pages; i++) - if (req->pages[i]) - put_page(req->pages[i]); - if (req->pages != req->array) - kfree(req->pages); + if (req->pages) { + for (i = 0; i < req->nr_pages; i++) + if (req->pages[i]) + put_page(req->pages[i]); + if (req->pages != req->array) + kfree(req->pages); + } kfree(req); } } diff --git a/fs/afs/vlclient.c b/fs/afs/vlclient.c index d7e0fd3c00df..cfb0ac4bd039 100644 --- a/fs/afs/vlclient.c +++ b/fs/afs/vlclient.c @@ -56,23 +56,24 @@ static int afs_deliver_vl_get_entry_by_name_u(struct afs_call *call) struct afs_uuid__xdr *xdr; struct afs_uuid *uuid; int j; + int n = entry->nr_servers; tmp = ntohl(uvldb->serverFlags[i]); if (tmp & AFS_VLSF_DONTUSE || (new_only && !(tmp & AFS_VLSF_NEWREPSITE))) continue; if (tmp & AFS_VLSF_RWVOL) { - entry->fs_mask[i] |= AFS_VOL_VTM_RW; + entry->fs_mask[n] |= AFS_VOL_VTM_RW; if (vlflags & AFS_VLF_BACKEXISTS) - entry->fs_mask[i] |= AFS_VOL_VTM_BAK; + entry->fs_mask[n] |= AFS_VOL_VTM_BAK; } if (tmp & AFS_VLSF_ROVOL) - entry->fs_mask[i] |= AFS_VOL_VTM_RO; - if (!entry->fs_mask[i]) + entry->fs_mask[n] |= AFS_VOL_VTM_RO; + if (!entry->fs_mask[n]) continue; xdr = &uvldb->serverNumber[i]; - uuid = (struct afs_uuid *)&entry->fs_server[i]; + uuid = (struct afs_uuid *)&entry->fs_server[n]; uuid->time_low = xdr->time_low; uuid->time_mid = htons(ntohl(xdr->time_mid)); uuid->time_hi_and_version = htons(ntohl(xdr->time_hi_and_version)); diff --git a/fs/seq_file.c b/fs/seq_file.c index 04f09689cd6d..1600034a929b 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -119,6 +119,7 @@ static int traverse(struct seq_file *m, loff_t offset) } if (seq_has_overflowed(m)) goto Eoverflow; + p = m->op->next(m, p, &m->index); if (pos + m->count > offset) { m->from = offset - pos; m->count -= m->from; @@ -126,7 +127,6 @@ static int traverse(struct seq_file *m, loff_t offset) } pos += m->count; m->count = 0; - p = m->op->next(m, p, &m->index); if (pos == offset) break; } diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index baf0b72c0a37..07aad70f3931 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -3835,15 +3835,28 @@ xfs_bmapi_read( XFS_STATS_INC(mp, xs_blk_mapr); ifp = XFS_IFORK_PTR(ip, whichfork); + if (!ifp) { + /* No CoW fork? Return a hole. */ + if (whichfork == XFS_COW_FORK) { + mval->br_startoff = bno; + mval->br_startblock = HOLESTARTBLOCK; + mval->br_blockcount = len; + mval->br_state = XFS_EXT_NORM; + *nmap = 1; + return 0; + } - /* No CoW fork? Return a hole. */ - if (whichfork == XFS_COW_FORK && !ifp) { - mval->br_startoff = bno; - mval->br_startblock = HOLESTARTBLOCK; - mval->br_blockcount = len; - mval->br_state = XFS_EXT_NORM; - *nmap = 1; - return 0; + /* + * A missing attr ifork implies that the inode says we're in + * extents or btree format but failed to pass the inode fork + * verifier while trying to load it. Treat that as a file + * corruption too. + */ +#ifdef DEBUG + xfs_alert(mp, "%s: inode %llu missing fork %d", + __func__, ip->i_ino, whichfork); +#endif /* DEBUG */ + return -EFSCORRUPTED; } if (!(ifp->if_flags & XFS_IFEXTENTS)) { diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c index d1c77fd0815d..0bf56e94bfe9 100644 --- a/fs/xfs/libxfs/xfs_da_btree.c +++ b/fs/xfs/libxfs/xfs_da_btree.c @@ -487,10 +487,8 @@ xfs_da3_split( ASSERT(state->path.active == 0); oldblk = &state->path.blk[0]; error = xfs_da3_root_split(state, oldblk, addblk); - if (error) { - addblk->bp = NULL; - return error; /* GROT: dir is inconsistent */ - } + if (error) + goto out; /* * Update pointers to the node which used to be block 0 and just got @@ -505,7 +503,10 @@ xfs_da3_split( */ node = oldblk->bp->b_addr; if (node->hdr.info.forw) { - ASSERT(be32_to_cpu(node->hdr.info.forw) == addblk->blkno); + if (be32_to_cpu(node->hdr.info.forw) != addblk->blkno) { + error = -EFSCORRUPTED; + goto out; + } node = addblk->bp->b_addr; node->hdr.info.back = cpu_to_be32(oldblk->blkno); xfs_trans_log_buf(state->args->trans, addblk->bp, @@ -514,15 +515,19 @@ xfs_da3_split( } node = oldblk->bp->b_addr; if (node->hdr.info.back) { - ASSERT(be32_to_cpu(node->hdr.info.back) == addblk->blkno); + if (be32_to_cpu(node->hdr.info.back) != addblk->blkno) { + error = -EFSCORRUPTED; + goto out; + } node = addblk->bp->b_addr; node->hdr.info.forw = cpu_to_be32(oldblk->blkno); xfs_trans_log_buf(state->args->trans, addblk->bp, XFS_DA_LOGRANGE(node, &node->hdr.info, sizeof(node->hdr.info))); } +out: addblk->bp = NULL; - return 0; + return error; } /* diff --git a/fs/xfs/libxfs/xfs_dir2_node.c b/fs/xfs/libxfs/xfs_dir2_node.c index afcc6642690a..1fc44efc344d 100644 --- a/fs/xfs/libxfs/xfs_dir2_node.c +++ b/fs/xfs/libxfs/xfs_dir2_node.c @@ -741,7 +741,8 @@ xfs_dir2_leafn_lookup_for_entry( ents = dp->d_ops->leaf_ents_p(leaf); xfs_dir3_leaf_check(dp, bp); - ASSERT(leafhdr.count > 0); + if (leafhdr.count <= 0) + return -EFSCORRUPTED; /* * Look up the hash value in the leaf entries. diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 00e9f5c388d3..7fc3c1ad36bc 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -429,10 +429,7 @@ xfs_log_reserve( ASSERT(*ticp == NULL); tic = xlog_ticket_alloc(log, unit_bytes, cnt, client, permanent, - KM_SLEEP | KM_MAYFAIL); - if (!tic) - return -ENOMEM; - + KM_SLEEP); *ticp = tic; xlog_grant_push_ail(log, tic->t_cnt ? tic->t_unit_res * tic->t_cnt diff --git a/include/asm-generic/5level-fixup.h b/include/asm-generic/5level-fixup.h index bb6cb347018c..f6947da70d71 100644 --- a/include/asm-generic/5level-fixup.h +++ b/include/asm-generic/5level-fixup.h @@ -19,9 +19,24 @@ #define p4d_alloc(mm, pgd, address) (pgd) #define p4d_offset(pgd, start) (pgd) -#define p4d_none(p4d) 0 -#define p4d_bad(p4d) 0 -#define p4d_present(p4d) 1 + +#ifndef __ASSEMBLY__ +static inline int p4d_none(p4d_t p4d) +{ + return 0; +} + +static inline int p4d_bad(p4d_t p4d) +{ + return 0; +} + +static inline int p4d_present(p4d_t p4d) +{ + return 1; +} +#endif + #define p4d_ERROR(p4d) do { } while (0) #define p4d_clear(p4d) pgd_clear(p4d) #define p4d_val(p4d) pgd_val(p4d) diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h index 3813211a9aad..0bff3d7fac92 100644 --- a/include/linux/dma-noncoherent.h +++ b/include/linux/dma-noncoherent.h @@ -42,13 +42,18 @@ void arch_dma_free(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs); long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr, dma_addr_t dma_addr); - -#ifdef CONFIG_ARCH_HAS_DMA_MMAP_PGPROT pgprot_t arch_dma_mmap_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs); + +#ifdef CONFIG_MMU +pgprot_t dma_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs); #else -# define arch_dma_mmap_pgprot(dev, prot, attrs) pgprot_noncached(prot) -#endif +static inline pgprot_t dma_pgprot(struct device *dev, pgprot_t prot, + unsigned long attrs) +{ + return prot; /* no protection bits supported without page tables */ +} +#endif /* CONFIG_MMU */ #ifdef CONFIG_DMA_NONCOHERENT_CACHE_SYNC void arch_dma_cache_sync(struct device *dev, void *vaddr, size_t size, diff --git a/include/linux/gfp.h b/include/linux/gfp.h index fb07b503dc45..f33881688f42 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -510,22 +510,18 @@ alloc_pages(gfp_t gfp_mask, unsigned int order) } extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, struct vm_area_struct *vma, unsigned long addr, - int node, bool hugepage); -#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ - alloc_pages_vma(gfp_mask, order, vma, addr, numa_node_id(), true) + int node); #else #define alloc_pages(gfp_mask, order) \ alloc_pages_node(numa_node_id(), gfp_mask, order) -#define alloc_pages_vma(gfp_mask, order, vma, addr, node, false)\ - alloc_pages(gfp_mask, order) -#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ +#define alloc_pages_vma(gfp_mask, order, vma, addr, node)\ alloc_pages(gfp_mask, order) #endif #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) #define alloc_page_vma(gfp_mask, vma, addr) \ - alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id(), false) + alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id()) #define alloc_page_vma_node(gfp_mask, vma, addr, node) \ - alloc_pages_vma(gfp_mask, 0, vma, addr, node, false) + alloc_pages_vma(gfp_mask, 0, vma, addr, node) extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order); extern unsigned long get_zeroed_page(gfp_t gfp_mask); diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 44c41462be33..2cd4359cb38c 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -668,6 +668,7 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val); +void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val); static inline void mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) @@ -1072,6 +1073,14 @@ static inline void mod_lruvec_page_state(struct page *page, mod_node_page_state(page_pgdat(page), idx, val); } +static inline void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, + int val) +{ + struct page *page = virt_to_head_page(p); + + __mod_node_page_state(page_pgdat(page), idx, val); +} + static inline unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, gfp_t gfp_mask, @@ -1159,6 +1168,16 @@ static inline void __dec_lruvec_page_state(struct page *page, __mod_lruvec_page_state(page, idx, -1); } +static inline void __inc_lruvec_slab_state(void *p, enum node_stat_item idx) +{ + __mod_lruvec_slab_state(p, idx, 1); +} + +static inline void __dec_lruvec_slab_state(void *p, enum node_stat_item idx) +{ + __mod_lruvec_slab_state(p, idx, -1); +} + /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void inc_memcg_state(struct mem_cgroup *memcg, int idx) diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 5228c62af416..bac395f1d00a 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -139,6 +139,8 @@ struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp, struct mempolicy *get_task_policy(struct task_struct *p); struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, unsigned long addr); +struct mempolicy *get_vma_policy(struct vm_area_struct *vma, + unsigned long addr); bool vma_policy_mof(struct vm_area_struct *vma); extern void numa_default_policy(void); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 3a37a89eb7a7..6a7a1083b6fb 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -159,7 +159,16 @@ struct page { /** @pgmap: Points to the hosting device page map. */ struct dev_pagemap *pgmap; void *zone_device_data; - unsigned long _zd_pad_1; /* uses mapping */ + /* + * ZONE_DEVICE private pages are counted as being + * mapped so the next 3 words hold the mapping, index, + * and private fields from the source anonymous or + * page cache page while the page is migrated to device + * private memory. + * ZONE_DEVICE MEMORY_DEVICE_FS_DAX pages also + * use the mapping, index, and private fields when + * pmem backed DAX files are mapped. + */ }; /** @rcu_head: You can use this to free a page by RCU. */ diff --git a/include/uapi/rdma/siw-abi.h b/include/uapi/rdma/siw-abi.h index 7de68f1dc707..af735f55b291 100644 --- a/include/uapi/rdma/siw-abi.h +++ b/include/uapi/rdma/siw-abi.h @@ -180,6 +180,7 @@ struct siw_cqe { * to control CQ arming. */ struct siw_cq_ctrl { - __aligned_u64 notify; + __u32 flags; + __u32 pad; }; #endif diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 59bdceea3737..795c9b095d75 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -47,9 +47,6 @@ u64 dma_direct_get_required_mask(struct device *dev) { u64 max_dma = phys_to_dma_direct(dev, (max_pfn - 1) << PAGE_SHIFT); - if (dev->bus_dma_mask && dev->bus_dma_mask < max_dma) - max_dma = dev->bus_dma_mask; - return (1ULL << (fls64(max_dma) - 1)) * 2 - 1; } @@ -130,10 +127,12 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size, if (!page) return NULL; - if (attrs & DMA_ATTR_NO_KERNEL_MAPPING) { + if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) && + !force_dma_unencrypted(dev)) { /* remove any dirty cache lines on the kernel alias */ if (!PageHighMem(page)) arch_dma_prep_coherent(page, size); + *dma_handle = phys_to_dma(dev, page_to_phys(page)); /* return the page pointer as the opaque cookie */ return page; } @@ -178,7 +177,8 @@ void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr, { unsigned int page_order = get_order(size); - if (attrs & DMA_ATTR_NO_KERNEL_MAPPING) { + if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) && + !force_dma_unencrypted(dev)) { /* cpu_addr is a struct page cookie, not a kernel address */ __dma_direct_free_pages(dev, size, cpu_addr); return; diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index b945239621d8..b0038ca3aa92 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -150,6 +150,23 @@ int dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt, } EXPORT_SYMBOL(dma_get_sgtable_attrs); +#ifdef CONFIG_MMU +/* + * Return the page attributes used for mapping dma_alloc_* memory, either in + * kernel space if remapping is needed, or to userspace through dma_mmap_*. + */ +pgprot_t dma_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs) +{ + if (dev_is_dma_coherent(dev) || + (IS_ENABLED(CONFIG_DMA_NONCOHERENT_CACHE_SYNC) && + (attrs & DMA_ATTR_NON_CONSISTENT))) + return prot; + if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_MMAP_PGPROT)) + return arch_dma_mmap_pgprot(dev, prot, attrs); + return pgprot_noncached(prot); +} +#endif /* CONFIG_MMU */ + /* * Create userspace mapping for the DMA-coherent memory. */ @@ -164,7 +181,7 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma, unsigned long pfn; int ret = -ENXIO; - vma->vm_page_prot = arch_dma_mmap_pgprot(dev, vma->vm_page_prot, attrs); + vma->vm_page_prot = dma_pgprot(dev, vma->vm_page_prot, attrs); if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret)) return ret; diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c index a594aec07882..ffe78f0b2fe4 100644 --- a/kernel/dma/remap.c +++ b/kernel/dma/remap.c @@ -218,7 +218,7 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, /* create a coherent mapping */ ret = dma_common_contiguous_remap(page, size, VM_USERMAP, - arch_dma_mmap_pgprot(dev, PAGE_KERNEL, attrs), + dma_pgprot(dev, PAGE_KERNEL, attrs), __builtin_return_address(0)); if (!ret) { __dma_direct_free_pages(dev, size, page); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 1334ede667a8..738065f765ab 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -644,30 +644,40 @@ release: * available * never: never stall for any thp allocation */ -static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma) +static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma, unsigned long addr) { const bool vma_madvised = !!(vma->vm_flags & VM_HUGEPAGE); + gfp_t this_node = 0; + +#ifdef CONFIG_NUMA + struct mempolicy *pol; + /* + * __GFP_THISNODE is used only when __GFP_DIRECT_RECLAIM is not + * specified, to express a general desire to stay on the current + * node for optimistic allocation attempts. If the defrag mode + * and/or madvise hint requires the direct reclaim then we prefer + * to fallback to other node rather than node reclaim because that + * can lead to excessive reclaim even though there is free memory + * on other nodes. We expect that NUMA preferences are specified + * by memory policies. + */ + pol = get_vma_policy(vma, addr); + if (pol->mode != MPOL_BIND) + this_node = __GFP_THISNODE; + mpol_cond_put(pol); +#endif - /* Always do synchronous compaction */ if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags)) return GFP_TRANSHUGE | (vma_madvised ? 0 : __GFP_NORETRY); - - /* Kick kcompactd and fail quickly */ if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags)) - return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM; - - /* Synchronous compaction if madvised, otherwise kick kcompactd */ + return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM | this_node; if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags)) - return GFP_TRANSHUGE_LIGHT | - (vma_madvised ? __GFP_DIRECT_RECLAIM : - __GFP_KSWAPD_RECLAIM); - - /* Only do synchronous compaction if madvised */ + return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM : + __GFP_KSWAPD_RECLAIM | this_node); if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags)) - return GFP_TRANSHUGE_LIGHT | - (vma_madvised ? __GFP_DIRECT_RECLAIM : 0); - - return GFP_TRANSHUGE_LIGHT; + return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM : + this_node); + return GFP_TRANSHUGE_LIGHT | this_node; } /* Caller must hold page table lock. */ @@ -739,8 +749,8 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) pte_free(vma->vm_mm, pgtable); return ret; } - gfp = alloc_hugepage_direct_gfpmask(vma); - page = alloc_hugepage_vma(gfp, vma, haddr, HPAGE_PMD_ORDER); + gfp = alloc_hugepage_direct_gfpmask(vma, haddr); + page = alloc_pages_vma(gfp, HPAGE_PMD_ORDER, vma, haddr, numa_node_id()); if (unlikely(!page)) { count_vm_event(THP_FAULT_FALLBACK); return VM_FAULT_FALLBACK; @@ -1347,8 +1357,9 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd) alloc: if (__transparent_hugepage_enabled(vma) && !transparent_hugepage_debug_cow()) { - huge_gfp = alloc_hugepage_direct_gfpmask(vma); - new_page = alloc_hugepage_vma(huge_gfp, vma, haddr, HPAGE_PMD_ORDER); + huge_gfp = alloc_hugepage_direct_gfpmask(vma, haddr); + new_page = alloc_pages_vma(huge_gfp, HPAGE_PMD_ORDER, vma, + haddr, numa_node_id()); } else new_page = NULL; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index ede7e7f5d1ab..6d7296dd11b8 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3856,6 +3856,25 @@ retry: page = alloc_huge_page(vma, haddr, 0); if (IS_ERR(page)) { + /* + * Returning error will result in faulting task being + * sent SIGBUS. The hugetlb fault mutex prevents two + * tasks from racing to fault in the same page which + * could result in false unable to allocate errors. + * Page migration does not take the fault mutex, but + * does a clear then write of pte's under page table + * lock. Page fault code could race with migration, + * notice the clear pte and try to allocate a page + * here. Before returning error, get ptl and make + * sure there really is no pte entry. + */ + ptl = huge_pte_lock(h, mm, ptep); + if (!huge_pte_none(huge_ptep_get(ptep))) { + ret = 0; + spin_unlock(ptl); + goto out; + } + spin_unlock(ptl); ret = vmf_error(PTR_ERR(page)); goto out; } diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 6e9e8cca663e..f6e602918dac 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -1966,6 +1966,7 @@ static void kmemleak_disable(void) /* stop any memory operation tracing */ kmemleak_enabled = 0; + kmemleak_early_log = 0; /* check whether it is too early for a kernel thread */ if (kmemleak_initialized) @@ -2009,7 +2010,6 @@ void __init kmemleak_init(void) #ifdef CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF if (!kmemleak_skip_disable) { - kmemleak_early_log = 0; kmemleak_disable(); return; } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index cdbb7a84cb6e..6f5c0c517c49 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -768,6 +768,26 @@ void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, __this_cpu_write(pn->lruvec_stat_cpu->count[idx], x); } +void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val) +{ + struct page *page = virt_to_head_page(p); + pg_data_t *pgdat = page_pgdat(page); + struct mem_cgroup *memcg; + struct lruvec *lruvec; + + rcu_read_lock(); + memcg = memcg_from_slab_page(page); + + /* Untracked pages have no memcg, no lruvec. Update only the node */ + if (!memcg || memcg == root_mem_cgroup) { + __mod_node_page_state(pgdat, idx, val); + } else { + lruvec = mem_cgroup_lruvec(pgdat, memcg); + __mod_lruvec_state(lruvec, idx, val); + } + rcu_read_unlock(); +} + /** * __count_memcg_events - account VM events in a cgroup * @memcg: the memory cgroup @@ -1130,26 +1150,45 @@ void mem_cgroup_iter_break(struct mem_cgroup *root, css_put(&prev->css); } -static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg) +static void __invalidate_reclaim_iterators(struct mem_cgroup *from, + struct mem_cgroup *dead_memcg) { - struct mem_cgroup *memcg = dead_memcg; struct mem_cgroup_reclaim_iter *iter; struct mem_cgroup_per_node *mz; int nid; int i; - for (; memcg; memcg = parent_mem_cgroup(memcg)) { - for_each_node(nid) { - mz = mem_cgroup_nodeinfo(memcg, nid); - for (i = 0; i <= DEF_PRIORITY; i++) { - iter = &mz->iter[i]; - cmpxchg(&iter->position, - dead_memcg, NULL); - } + for_each_node(nid) { + mz = mem_cgroup_nodeinfo(from, nid); + for (i = 0; i <= DEF_PRIORITY; i++) { + iter = &mz->iter[i]; + cmpxchg(&iter->position, + dead_memcg, NULL); } } } +static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg) +{ + struct mem_cgroup *memcg = dead_memcg; + struct mem_cgroup *last; + + do { + __invalidate_reclaim_iterators(memcg, dead_memcg); + last = memcg; + } while ((memcg = parent_mem_cgroup(memcg))); + + /* + * When cgruop1 non-hierarchy mode is used, + * parent_mem_cgroup() does not walk all the way up to the + * cgroup root (root_mem_cgroup). So we have to handle + * dead_memcg from cgroup root separately. + */ + if (last != root_mem_cgroup) + __invalidate_reclaim_iterators(root_mem_cgroup, + dead_memcg); +} + /** * mem_cgroup_scan_tasks - iterate over tasks of a memory cgroup hierarchy * @memcg: hierarchy root diff --git a/mm/mempolicy.c b/mm/mempolicy.c index f48693f75b37..65e0874fce17 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -403,7 +403,7 @@ static const struct mempolicy_operations mpol_ops[MPOL_MAX] = { }, }; -static void migrate_page_add(struct page *page, struct list_head *pagelist, +static int migrate_page_add(struct page *page, struct list_head *pagelist, unsigned long flags); struct queue_pages { @@ -429,11 +429,14 @@ static inline bool queue_pages_required(struct page *page, } /* - * queue_pages_pmd() has three possible return values: - * 1 - pages are placed on the right node or queued successfully. - * 0 - THP was split. - * -EIO - is migration entry or MPOL_MF_STRICT was specified and an existing - * page was already on a node that does not follow the policy. + * queue_pages_pmd() has four possible return values: + * 0 - pages are placed on the right node or queued successfully. + * 1 - there is unmovable page, and MPOL_MF_MOVE* & MPOL_MF_STRICT were + * specified. + * 2 - THP was split. + * -EIO - is migration entry or only MPOL_MF_STRICT was specified and an + * existing page was already on a node that does not follow the + * policy. */ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, unsigned long end, struct mm_walk *walk) @@ -451,23 +454,20 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, if (is_huge_zero_page(page)) { spin_unlock(ptl); __split_huge_pmd(walk->vma, pmd, addr, false, NULL); + ret = 2; goto out; } - if (!queue_pages_required(page, qp)) { - ret = 1; + if (!queue_pages_required(page, qp)) goto unlock; - } - ret = 1; flags = qp->flags; /* go to thp migration */ if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { - if (!vma_migratable(walk->vma)) { - ret = -EIO; + if (!vma_migratable(walk->vma) || + migrate_page_add(page, qp->pagelist, flags)) { + ret = 1; goto unlock; } - - migrate_page_add(page, qp->pagelist, flags); } else ret = -EIO; unlock: @@ -479,6 +479,13 @@ out: /* * Scan through pages checking if pages follow certain conditions, * and move them to the pagelist if they do. + * + * queue_pages_pte_range() has three possible return values: + * 0 - pages are placed on the right node or queued successfully. + * 1 - there is unmovable page, and MPOL_MF_MOVE* & MPOL_MF_STRICT were + * specified. + * -EIO - only MPOL_MF_STRICT was specified and an existing page was already + * on a node that does not follow the policy. */ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) @@ -488,17 +495,17 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; int ret; + bool has_unmovable = false; pte_t *pte; spinlock_t *ptl; ptl = pmd_trans_huge_lock(pmd, vma); if (ptl) { ret = queue_pages_pmd(pmd, ptl, addr, end, walk); - if (ret > 0) - return 0; - else if (ret < 0) + if (ret != 2) return ret; } + /* THP was split, fall through to pte walk */ if (pmd_trans_unstable(pmd)) return 0; @@ -519,14 +526,28 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, if (!queue_pages_required(page, qp)) continue; if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { - if (!vma_migratable(vma)) + /* MPOL_MF_STRICT must be specified if we get here */ + if (!vma_migratable(vma)) { + has_unmovable = true; break; - migrate_page_add(page, qp->pagelist, flags); + } + + /* + * Do not abort immediately since there may be + * temporary off LRU pages in the range. Still + * need migrate other LRU pages. + */ + if (migrate_page_add(page, qp->pagelist, flags)) + has_unmovable = true; } else break; } pte_unmap_unlock(pte - 1, ptl); cond_resched(); + + if (has_unmovable) + return 1; + return addr != end ? -EIO : 0; } @@ -639,7 +660,13 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end, * * If pages found in a given range are on a set of nodes (determined by * @nodes and @flags,) it's isolated and queued to the pagelist which is - * passed via @private.) + * passed via @private. + * + * queue_pages_range() has three possible return values: + * 1 - there is unmovable page, but MPOL_MF_MOVE* & MPOL_MF_STRICT were + * specified. + * 0 - queue pages successfully or no misplaced page. + * -EIO - there is misplaced page and only MPOL_MF_STRICT was specified. */ static int queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, @@ -940,7 +967,7 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask, /* * page migration, thp tail pages can be passed. */ -static void migrate_page_add(struct page *page, struct list_head *pagelist, +static int migrate_page_add(struct page *page, struct list_head *pagelist, unsigned long flags) { struct page *head = compound_head(page); @@ -953,8 +980,19 @@ static void migrate_page_add(struct page *page, struct list_head *pagelist, mod_node_page_state(page_pgdat(head), NR_ISOLATED_ANON + page_is_file_cache(head), hpage_nr_pages(head)); + } else if (flags & MPOL_MF_STRICT) { + /* + * Non-movable page may reach here. And, there may be + * temporary off LRU pages or non-LRU movable pages. + * Treat them as unmovable pages since they can't be + * isolated, so they can't be moved at the moment. It + * should return -EIO for this case too. + */ + return -EIO; } } + + return 0; } /* page allocation callback for NUMA node migration */ @@ -1142,8 +1180,8 @@ static struct page *new_page(struct page *page, unsigned long start) } else if (PageTransHuge(page)) { struct page *thp; - thp = alloc_hugepage_vma(GFP_TRANSHUGE, vma, address, - HPAGE_PMD_ORDER); + thp = alloc_pages_vma(GFP_TRANSHUGE, HPAGE_PMD_ORDER, vma, + address, numa_node_id()); if (!thp) return NULL; prep_transhuge_page(thp); @@ -1157,9 +1195,10 @@ static struct page *new_page(struct page *page, unsigned long start) } #else -static void migrate_page_add(struct page *page, struct list_head *pagelist, +static int migrate_page_add(struct page *page, struct list_head *pagelist, unsigned long flags) { + return -EIO; } int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, @@ -1182,6 +1221,7 @@ static long do_mbind(unsigned long start, unsigned long len, struct mempolicy *new; unsigned long end; int err; + int ret; LIST_HEAD(pagelist); if (flags & ~(unsigned long)MPOL_MF_VALID) @@ -1243,10 +1283,15 @@ static long do_mbind(unsigned long start, unsigned long len, if (err) goto mpol_out; - err = queue_pages_range(mm, start, end, nmask, + ret = queue_pages_range(mm, start, end, nmask, flags | MPOL_MF_INVERT, &pagelist); - if (!err) - err = mbind_range(mm, start, end, new); + + if (ret < 0) { + err = -EIO; + goto up_out; + } + + err = mbind_range(mm, start, end, new); if (!err) { int nr_failed = 0; @@ -1259,13 +1304,14 @@ static long do_mbind(unsigned long start, unsigned long len, putback_movable_pages(&pagelist); } - if (nr_failed && (flags & MPOL_MF_STRICT)) + if ((ret > 0) || (nr_failed && (flags & MPOL_MF_STRICT))) err = -EIO; } else putback_movable_pages(&pagelist); +up_out: up_write(&mm->mmap_sem); - mpol_out: +mpol_out: mpol_put(new); return err; } @@ -1688,7 +1734,7 @@ struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, * freeing by another task. It is the caller's responsibility to free the * extra reference for shared policies. */ -static struct mempolicy *get_vma_policy(struct vm_area_struct *vma, +struct mempolicy *get_vma_policy(struct vm_area_struct *vma, unsigned long addr) { struct mempolicy *pol = __get_vma_policy(vma, addr); @@ -2037,7 +2083,6 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, * @vma: Pointer to VMA or NULL if not available. * @addr: Virtual Address of the allocation. Must be inside the VMA. * @node: Which node to prefer for allocation (modulo policy). - * @hugepage: for hugepages try only the preferred node if possible * * This function allocates a page from the kernel page pool and applies * a NUMA policy associated with the VMA or the current process. @@ -2048,7 +2093,7 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, */ struct page * alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, - unsigned long addr, int node, bool hugepage) + unsigned long addr, int node) { struct mempolicy *pol; struct page *page; @@ -2066,31 +2111,6 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, goto out; } - if (unlikely(IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && hugepage)) { - int hpage_node = node; - - /* - * For hugepage allocation and non-interleave policy which - * allows the current node (or other explicitly preferred - * node) we only try to allocate from the current/preferred - * node and don't fall back to other nodes, as the cost of - * remote accesses would likely offset THP benefits. - * - * If the policy is interleave, or does not allow the current - * node in its nodemask, we allocate the standard way. - */ - if (pol->mode == MPOL_PREFERRED && !(pol->flags & MPOL_F_LOCAL)) - hpage_node = pol->v.preferred_node; - - nmask = policy_nodemask(gfp, pol); - if (!nmask || node_isset(hpage_node, *nmask)) { - mpol_cond_put(pol); - page = __alloc_pages_node(hpage_node, - gfp | __GFP_THISNODE, order); - goto out; - } - } - nmask = policy_nodemask(gfp, pol); preferred_nid = policy_node(gfp, pol, node); page = __alloc_pages_nodemask(gfp, order, preferred_nid, nmask); diff --git a/mm/memremap.c b/mm/memremap.c index 86432650f829..ed70c4e8e52a 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -403,6 +403,30 @@ void __put_devmap_managed_page(struct page *page) mem_cgroup_uncharge(page); + /* + * When a device_private page is freed, the page->mapping field + * may still contain a (stale) mapping value. For example, the + * lower bits of page->mapping may still identify the page as + * an anonymous page. Ultimately, this entire field is just + * stale and wrong, and it will cause errors if not cleared. + * One example is: + * + * migrate_vma_pages() + * migrate_vma_insert_page() + * page_add_new_anon_rmap() + * __page_set_anon_rmap() + * ...checks page->mapping, via PageAnon(page) call, + * and incorrectly concludes that the page is an + * anonymous page. Therefore, it incorrectly, + * silently fails to set up the new anon rmap. + * + * For other types of ZONE_DEVICE pages, migration is either + * handled differently or not done at all, so there is no need + * to clear page->mapping. + */ + if (is_device_private_page(page)) + page->mapping = NULL; + page->pgmap->ops->page_free(page); } else if (!count) __put_page(page); diff --git a/mm/rmap.c b/mm/rmap.c index e5dfe2ae6b0d..003377e24232 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1475,7 +1475,15 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, /* * No need to invalidate here it will synchronize on * against the special swap migration pte. + * + * The assignment to subpage above was computed from a + * swap PTE which results in an invalid pointer. + * Since only PAGE_SIZE pages can currently be + * migrated, just set it to page. This will need to be + * changed when hugepage migrations to device private + * memory are supported. */ + subpage = page; goto discard; } diff --git a/mm/shmem.c b/mm/shmem.c index 626d8c74b973..2bed4761f279 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1466,7 +1466,7 @@ static struct page *shmem_alloc_hugepage(gfp_t gfp, shmem_pseudo_vma_init(&pvma, info, hindex); page = alloc_pages_vma(gfp | __GFP_COMP | __GFP_NORETRY | __GFP_NOWARN, - HPAGE_PMD_ORDER, &pvma, 0, numa_node_id(), true); + HPAGE_PMD_ORDER, &pvma, 0, numa_node_id()); shmem_pseudo_vma_destroy(&pvma); if (page) prep_transhuge_page(page); diff --git a/mm/usercopy.c b/mm/usercopy.c index 2a09796edef8..98e924864554 100644 --- a/mm/usercopy.c +++ b/mm/usercopy.c @@ -147,7 +147,7 @@ static inline void check_bogus_address(const unsigned long ptr, unsigned long n, bool to_user) { /* Reject if object wraps past end of memory. */ - if (ptr + n < ptr) + if (ptr + (n - 1) < ptr) usercopy_abort("wrapped address", NULL, to_user, 0, ptr + n); /* Reject if NULL or ZERO-allocation. */ diff --git a/mm/vmalloc.c b/mm/vmalloc.c index e0fc963acc41..7ba11e12a11f 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -3279,9 +3279,19 @@ retry: goto overflow; /* + * If required width exeeds current VA block, move + * base downwards and then recheck. + */ + if (base + end > va->va_end) { + base = pvm_determine_end_from_reverse(&va, align) - end; + term_area = area; + continue; + } + + /* * If this VA does not fit, move base downwards and recheck. */ - if (base + start < va->va_start || base + end > va->va_end) { + if (base + start < va->va_start) { va = node_to_va(rb_prev(&va->rb_node)); base = pvm_determine_end_from_reverse(&va, align) - end; term_area = area; diff --git a/mm/vmscan.c b/mm/vmscan.c index dbdc46a84f63..c77d1e3761a7 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -88,9 +88,6 @@ struct scan_control { /* Can pages be swapped as part of reclaim? */ unsigned int may_swap:1; - /* e.g. boosted watermark reclaim leaves slabs alone */ - unsigned int may_shrinkslab:1; - /* * Cgroups are not reclaimed below their configured memory.low, * unless we threaten to OOM. If any cgroups are skipped due to @@ -2714,10 +2711,8 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc) shrink_node_memcg(pgdat, memcg, sc, &lru_pages); node_lru_pages += lru_pages; - if (sc->may_shrinkslab) { - shrink_slab(sc->gfp_mask, pgdat->node_id, - memcg, sc->priority); - } + shrink_slab(sc->gfp_mask, pgdat->node_id, memcg, + sc->priority); /* Record the group's reclaim efficiency */ vmpressure(sc->gfp_mask, memcg, false, @@ -3194,7 +3189,6 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order, .may_writepage = !laptop_mode, .may_unmap = 1, .may_swap = 1, - .may_shrinkslab = 1, }; /* @@ -3238,7 +3232,6 @@ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg, .may_unmap = 1, .reclaim_idx = MAX_NR_ZONES - 1, .may_swap = !noswap, - .may_shrinkslab = 1, }; unsigned long lru_pages; @@ -3286,7 +3279,6 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, .may_writepage = !laptop_mode, .may_unmap = 1, .may_swap = may_swap, - .may_shrinkslab = 1, }; set_task_reclaim_state(current, &sc.reclaim_state); @@ -3598,7 +3590,6 @@ restart: */ sc.may_writepage = !laptop_mode && !nr_boost_reclaim; sc.may_swap = !nr_boost_reclaim; - sc.may_shrinkslab = !nr_boost_reclaim; /* * Do some background aging of the anon list, to give diff --git a/mm/workingset.c b/mm/workingset.c index e0b4edcb88c8..c963831d354f 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -380,14 +380,12 @@ void workingset_update_node(struct xa_node *node) if (node->count && node->count == node->nr_values) { if (list_empty(&node->private_list)) { list_lru_add(&shadow_nodes, &node->private_list); - __inc_lruvec_page_state(virt_to_page(node), - WORKINGSET_NODES); + __inc_lruvec_slab_state(node, WORKINGSET_NODES); } } else { if (!list_empty(&node->private_list)) { list_lru_del(&shadow_nodes, &node->private_list); - __dec_lruvec_page_state(virt_to_page(node), - WORKINGSET_NODES); + __dec_lruvec_slab_state(node, WORKINGSET_NODES); } } } @@ -480,7 +478,7 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, } list_lru_isolate(lru, item); - __dec_lruvec_page_state(virt_to_page(node), WORKINGSET_NODES); + __dec_lruvec_slab_state(node, WORKINGSET_NODES); spin_unlock(lru_lock); @@ -503,7 +501,7 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, * shadow entries we were tracking ... */ xas_store(&xas, NULL); - __inc_lruvec_page_state(virt_to_page(node), WORKINGSET_NODERECLAIM); + __inc_lruvec_slab_state(node, WORKINGSET_NODERECLAIM); out_invalid: xa_unlock_irq(&mapping->i_pages); diff --git a/mm/z3fold.c b/mm/z3fold.c index 1a029a7432ee..ed19d98c9dcd 100644 --- a/mm/z3fold.c +++ b/mm/z3fold.c @@ -817,9 +817,19 @@ out: static void z3fold_destroy_pool(struct z3fold_pool *pool) { kmem_cache_destroy(pool->c_handle); - z3fold_unregister_migration(pool); - destroy_workqueue(pool->release_wq); + + /* + * We need to destroy pool->compact_wq before pool->release_wq, + * as any pending work on pool->compact_wq will call + * queue_work(pool->release_wq, &pool->work). + * + * There are still outstanding pages until both workqueues are drained, + * so we cannot unregister migration until then. + */ + destroy_workqueue(pool->compact_wq); + destroy_workqueue(pool->release_wq); + z3fold_unregister_migration(pool); kfree(pool); } diff --git a/samples/auxdisplay/cfag12864b-example.c b/samples/auxdisplay/cfag12864b-example.c index 85571e90191f..bfeab44f81d0 100644 --- a/samples/auxdisplay/cfag12864b-example.c +++ b/samples/auxdisplay/cfag12864b-example.c @@ -245,7 +245,7 @@ int main(int argc, char *argv[]) if (argc != 2) { printf( - "Sintax: %s fbdev\n" + "Syntax: %s fbdev\n" "Usually: /dev/fb0, /dev/fb1...\n", argv[0]); return -1; } diff --git a/security/keys/trusted.c b/security/keys/trusted.c index 9a94672e7adc..ade699131065 100644 --- a/security/keys/trusted.c +++ b/security/keys/trusted.c @@ -1228,24 +1228,11 @@ hashalg_fail: static int __init init_digests(void) { - u8 digest[TPM_MAX_DIGEST_SIZE]; - int ret; - int i; - - ret = tpm_get_random(chip, digest, TPM_MAX_DIGEST_SIZE); - if (ret < 0) - return ret; - if (ret < TPM_MAX_DIGEST_SIZE) - return -EFAULT; - digests = kcalloc(chip->nr_allocated_banks, sizeof(*digests), GFP_KERNEL); if (!digests) return -ENOMEM; - for (i = 0; i < chip->nr_allocated_banks; i++) - memcpy(digests[i].digest, digest, TPM_MAX_DIGEST_SIZE); - return 0; } |